21 files changed, 328 insertions, 298 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6aef9ee28a39..6462e3dd98f4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -21,7 +21,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
 CFLAGS_REMOVE_sev.o = -pg
-CFLAGS_REMOVE_cc_platform.o = -pg
 endif
 
 KASAN_SANITIZE_head$(BITS).o				:= n
@@ -30,7 +29,6 @@ KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
 KASAN_SANITIZE_stacktrace.o				:= n
 KASAN_SANITIZE_paravirt.o				:= n
 KASAN_SANITIZE_sev.o					:= n
-KASAN_SANITIZE_cc_platform.o				:= n
 
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
@@ -49,7 +47,6 @@ endif
 KCOV_INSTRUMENT		:= n
 
 CFLAGS_head$(BITS).o	+= -fno-stack-protector
-CFLAGS_cc_platform.o	+= -fno-stack-protector
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
@@ -151,8 +148,6 @@ obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
 obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
 
-obj-$(CONFIG_ARCH_HAS_CC_PLATFORM)	+= cc_platform.o
-
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index cf340d85946a..fc17b3f136fe 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -3,7 +3,7 @@
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
-obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_msr.o
+obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc.o
 
 ifneq ($(CONFIG_ACPI_PROCESSOR),)
 obj-y				+= cstate.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 5b6d1a95776f..0d01e7f5078c 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1328,6 +1328,17 @@ static int __init disable_acpi_pci(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init disable_acpi_xsdt(const struct dmi_system_id *d)
+{
+	if (!acpi_force) {
+		pr_notice("%s detected: force use of acpi=rsdt\n", d->ident);
+		acpi_gbl_do_not_use_xsdt = TRUE;
+	} else {
+		pr_notice("Warning: DMI blacklist says broken, but acpi XSDT forced\n");
+	}
+	return 0;
+}
+
 static int __init dmi_disable_acpi(const struct dmi_system_id *d)
 {
 	if (!acpi_force) {
@@ -1451,6 +1462,19 @@ static const struct dmi_system_id acpi_dmi_table[] __initconst = {
 		     DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
 		     },
 	 },
+	/*
+	 * Boxes that need ACPI XSDT use disabled due to corrupted tables
+	 */
+	{
+	 .callback = disable_acpi_xsdt,
+	 .ident = "Advantech DAC-BJ01",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "Bearlake CRB Board"),
+		     DMI_MATCH(DMI_BIOS_VERSION, "V1.12"),
+		     DMI_MATCH(DMI_BIOS_DATE, "02/01/2011"),
+		     },
+	 },
 	{}
 };
 
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
new file mode 100644
index 000000000000..df1644d9b3b6
--- /dev/null
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cppc.c: CPPC Interface for x86
+ * Copyright (c) 2016, Intel Corporation.
+ */
+
+#include <acpi/cppc_acpi.h>
+#include <asm/msr.h>
+#include <asm/processor.h>
+#include <asm/topology.h>
+
+/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
+
+bool cpc_ffh_supported(void)
+{
+	return true;
+}
+
+int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
+{
+	int err;
+
+	err = rdmsrl_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 = rdmsrl_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 = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val);
+	}
+	return err;
+}
+
+bool amd_set_max_freq_ratio(u64 *ratio)
+{
+	struct cppc_perf_caps perf_caps;
+	u64 highest_perf, nominal_perf;
+	u64 perf_ratio;
+	int rc;
+
+	if (!ratio)
+		return false;
+
+	rc = cppc_get_perf_caps(0, &perf_caps);
+	if (rc) {
+		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		return false;
+	}
+
+	highest_perf = amd_get_highest_perf();
+	nominal_perf = perf_caps.nominal_perf;
+
+	if (!highest_perf || !nominal_perf) {
+		pr_debug("Could not retrieve highest or nominal performance\n");
+		return false;
+	}
+
+	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
+	/* midpoint between max_boost and max_P */
+	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
+	if (!perf_ratio) {
+		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
+		return false;
+	}
+
+	*ratio = perf_ratio;
+	arch_set_max_freq_ratio(false);
+
+	return true;
+}
+
+static DEFINE_MUTEX(freq_invariance_lock);
+
+void init_freq_invariance_cppc(void)
+{
+	static bool secondary;
+
+	mutex_lock(&freq_invariance_lock);
+
+	init_freq_invariance(secondary, true);
+	secondary = true;
+
+	mutex_unlock(&freq_invariance_lock);
+}
diff --git a/arch/x86/kernel/acpi/cppc_msr.c b/arch/x86/kernel/acpi/cppc_msr.c
deleted file mode 100644
index b961de569e7e..000000000000
--- a/arch/x86/kernel/acpi/cppc_msr.c
+++ /dev/null
@@ -1,49 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * cppc_msr.c:  MSR Interface for CPPC
- * Copyright (c) 2016, Intel Corporation.
- */
-
-#include <acpi/cppc_acpi.h>
-#include <asm/msr.h>
-
-/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
-
-bool cpc_ffh_supported(void)
-{
-	return true;
-}
-
-int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
-{
-	int err;
-
-	err = rdmsrl_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 = rdmsrl_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 = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val);
-	}
-	return err;
-}
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 1e97f944b47d..3b7f4cdbf2e0 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -15,6 +15,7 @@
 #include <asm/desc.h>
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
+#include <asm/hypervisor.h>
 
 #include <linux/ftrace.h>
 #include "../../realmode/rm/wakeup.h"
@@ -140,9 +141,9 @@ static int __init acpi_sleep_setup(char *str)
 			acpi_realmode_flags |= 4;
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_hwsig", 8) == 0)
-			acpi_check_s4_hw_signature(1);
+			acpi_check_s4_hw_signature = 1;
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
-			acpi_check_s4_hw_signature(0);
+			acpi_check_s4_hw_signature = 0;
 #endif
 		if (strncmp(str, "nonvs", 5) == 0)
 			acpi_nvs_nosave();
@@ -160,3 +161,21 @@ static int __init acpi_sleep_setup(char *str)
 }
 
 __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
diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c
deleted file mode 100644
index 6a6ffcd978f6..000000000000
--- a/arch/x86/kernel/cc_platform.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Confidential Computing Platform Capability checks
- *
- * Copyright (C) 2021 Advanced Micro Devices, Inc.
- *
- * Author: Tom Lendacky <thomas.lendacky@amd.com>
- */
-
-#include <linux/export.h>
-#include <linux/cc_platform.h>
-#include <linux/mem_encrypt.h>
-
-#include <asm/mshyperv.h>
-#include <asm/processor.h>
-
-static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr)
-{
-#ifdef CONFIG_INTEL_TDX_GUEST
-	return false;
-#else
-	return false;
-#endif
-}
-
-/*
- * SME and SEV are very similar but they are not the same, so there are
- * times that the kernel will need to distinguish between SME and SEV. The
- * cc_platform_has() function is used for this.  When a distinction isn't
- * needed, the CC_ATTR_MEM_ENCRYPT attribute can be used.
- *
- * The trampoline code is a good example for this requirement.  Before
- * paging is activated, SME will access all memory as decrypted, but SEV
- * will access all memory as encrypted.  So, when APs are being brought
- * up under SME the trampoline area cannot be encrypted, whereas under SEV
- * the trampoline area must be encrypted.
- */
-static bool amd_cc_platform_has(enum cc_attr attr)
-{
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-	switch (attr) {
-	case CC_ATTR_MEM_ENCRYPT:
-		return sme_me_mask;
-
-	case CC_ATTR_HOST_MEM_ENCRYPT:
-		return sme_me_mask && !(sev_status & MSR_AMD64_SEV_ENABLED);
-
-	case CC_ATTR_GUEST_MEM_ENCRYPT:
-		return sev_status & MSR_AMD64_SEV_ENABLED;
-
-	case CC_ATTR_GUEST_STATE_ENCRYPT:
-		return sev_status & MSR_AMD64_SEV_ES_ENABLED;
-
-	/*
-	 * With SEV, the rep string I/O instructions need to be unrolled
-	 * but SEV-ES supports them through the #VC handler.
-	 */
-	case CC_ATTR_GUEST_UNROLL_STRING_IO:
-		return (sev_status & MSR_AMD64_SEV_ENABLED) &&
-			!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
-
-	default:
-		return false;
-	}
-#else
-	return false;
-#endif
-}
-
-static bool hyperv_cc_platform_has(enum cc_attr attr)
-{
-	return attr == CC_ATTR_GUEST_MEM_ENCRYPT;
-}
-
-bool cc_platform_has(enum cc_attr attr)
-{
-	if (sme_me_mask)
-		return amd_cc_platform_has(attr);
-
-	if (hv_is_isolation_supported())
-		return hyperv_cc_platform_has(attr);
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(cc_platform_has);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4edb6f0f628c..0c0b09796ced 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -394,35 +394,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
 }
 
-static void amd_detect_ppin(struct cpuinfo_x86 *c)
-{
-	unsigned long long val;
-
-	if (!cpu_has(c, X86_FEATURE_AMD_PPIN))
-		return;
-
-	/* When PPIN is defined in CPUID, still need to check PPIN_CTL MSR */
-	if (rdmsrl_safe(MSR_AMD_PPIN_CTL, &val))
-		goto clear_ppin;
-
-	/* PPIN is locked in disabled mode, clear feature bit */
-	if ((val & 3UL) == 1UL)
-		goto clear_ppin;
-
-	/* If PPIN is disabled, try to enable it */
-	if (!(val & 2UL)) {
-		wrmsrl_safe(MSR_AMD_PPIN_CTL,  val | 2UL);
-		rdmsrl_safe(MSR_AMD_PPIN_CTL, &val);
-	}
-
-	/* If PPIN_EN bit is 1, return from here; otherwise fall through */
-	if (val & 2UL)
-		return;
-
-clear_ppin:
-	clear_cpu_cap(c, X86_FEATURE_AMD_PPIN);
-}
-
 u32 amd_get_nodes_per_socket(void)
 {
 	return nodes_per_socket;
@@ -585,6 +556,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 *	      the SME physical address space reduction value.
 	 *	      If BIOS has not enabled SME then don't advertise the
 	 *	      SME feature (set in scattered.c).
+	 *	      If the kernel has not enabled SME via any means then
+	 *	      don't advertise the SME feature.
 	 *   For SEV: If BIOS has not enabled SEV then don't advertise the
 	 *            SEV and SEV_ES feature (set in scattered.c).
 	 *
@@ -607,6 +580,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 		if (IS_ENABLED(CONFIG_X86_32))
 			goto clear_all;
 
+		if (!sme_me_mask)
+			setup_clear_cpu_cap(X86_FEATURE_SME);
+
 		rdmsrl(MSR_K7_HWCR, msr);
 		if (!(msr & MSR_K7_HWCR_SMMLOCK))
 			goto clear_sev;
@@ -947,7 +923,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	amd_detect_cmp(c);
 	amd_get_topology(c);
 	srat_detect_node(c);
-	amd_detect_ppin(c);
 
 	init_amd_cacheinfo(c);
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7b8382c11788..64deb7727d00 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -88,6 +88,83 @@ EXPORT_SYMBOL_GPL(get_llc_id);
 /* L2 cache ID of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID;
 
+static struct ppin_info {
+	int	feature;
+	int	msr_ppin_ctl;
+	int	msr_ppin;
+} ppin_info[] = {
+	[X86_VENDOR_INTEL] = {
+		.feature = X86_FEATURE_INTEL_PPIN,
+		.msr_ppin_ctl = MSR_PPIN_CTL,
+		.msr_ppin = MSR_PPIN
+	},
+	[X86_VENDOR_AMD] = {
+		.feature = X86_FEATURE_AMD_PPIN,
+		.msr_ppin_ctl = MSR_AMD_PPIN_CTL,
+		.msr_ppin = MSR_AMD_PPIN
+	},
+};
+
+static const struct x86_cpu_id ppin_cpuids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_AMD_PPIN, &ppin_info[X86_VENDOR_AMD]),
+	X86_MATCH_FEATURE(X86_FEATURE_INTEL_PPIN, &ppin_info[X86_VENDOR_INTEL]),
+
+	/* Legacy models without CPUID enumeration */
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &ppin_info[X86_VENDOR_INTEL]),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &ppin_info[X86_VENDOR_INTEL]),
+
+	{}
+};
+
+static void ppin_init(struct cpuinfo_x86 *c)
+{
+	const struct x86_cpu_id *id;
+	unsigned long long val;
+	struct ppin_info *info;
+
+	id = x86_match_cpu(ppin_cpuids);
+	if (!id)
+		return;
+
+	/*
+	 * Testing the presence of the MSR is not enough. Need to check
+	 * that the PPIN_CTL allows reading of the PPIN.
+	 */
+	info = (struct ppin_info *)id->driver_data;
+
+	if (rdmsrl_safe(info->msr_ppin_ctl, &val))
+		goto clear_ppin;
+
+	if ((val & 3UL) == 1UL) {
+		/* PPIN locked in disabled mode */
+		goto clear_ppin;
+	}
+
+	/* If PPIN is disabled, try to enable */
+	if (!(val & 2UL)) {
+		wrmsrl_safe(info->msr_ppin_ctl,  val | 2UL);
+		rdmsrl_safe(info->msr_ppin_ctl, &val);
+	}
+
+	/* Is the enable bit set? */
+	if (val & 2UL) {
+		c->ppin = __rdmsr(info->msr_ppin);
+		set_cpu_cap(c, info->feature);
+		return;
+	}
+
+clear_ppin:
+	clear_cpu_cap(c, info->feature);
+}
+
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
@@ -1655,6 +1732,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 			c->x86_capability[i] |= boot_cpu_data.x86_capability[i];
 	}
 
+	ppin_init(c);
+
 	/* Init Machine Check Exception if available. */
 	mcheck_cpu_init(c);
 
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 9f4b508886dd..1940d305db1c 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -993,6 +993,7 @@ static struct attribute *default_attrs[] = {
 	NULL,	/* possibly interrupt_enable if supported, see below */
 	NULL,
 };
+ATTRIBUTE_GROUPS(default);
 
 #define to_block(k)	container_of(k, struct threshold_block, kobj)
 #define to_attr(a)	container_of(a, struct threshold_attr, attr)
@@ -1029,7 +1030,7 @@ static void threshold_block_release(struct kobject *kobj);
 
 static struct kobj_type threshold_ktype = {
 	.sysfs_ops		= &threshold_ops,
-	.default_attrs		= default_attrs,
+	.default_groups		= default_groups,
 	.release		= threshold_block_release,
 };
 
@@ -1101,10 +1102,10 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb
 	b->threshold_limit	= THRESHOLD_MAX;
 
 	if (b->interrupt_capable) {
-		threshold_ktype.default_attrs[2] = &interrupt_enable.attr;
+		default_attrs[2] = &interrupt_enable.attr;
 		b->interrupt_enable = 1;
 	} else {
-		threshold_ktype.default_attrs[2] = NULL;
+		default_attrs[2] = NULL;
 	}
 
 	INIT_LIST_HEAD(&b->miscj);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 5818b837fd4d..4f1e825033ce 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -138,12 +138,7 @@ void mce_setup(struct mce *m)
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
 	m->apicid = cpu_data(m->extcpu).initial_apicid;
 	m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
-
-	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
-		m->ppin = __rdmsr(MSR_PPIN);
-	else if (this_cpu_has(X86_FEATURE_AMD_PPIN))
-		m->ppin = __rdmsr(MSR_AMD_PPIN);
-
+	m->ppin = cpu_data(m->extcpu).ppin;
 	m->microcode = boot_cpu_data.microcode;
 }
 
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index baafbb37be67..95275a5e57e0 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -470,47 +470,6 @@ void intel_clear_lmce(void)
 	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
 }
 
-static void intel_ppin_init(struct cpuinfo_x86 *c)
-{
-	unsigned long long val;
-
-	/*
-	 * Even if testing the presence of the MSR would be enough, we don't
-	 * want to risk the situation where other models reuse this MSR for
-	 * other purposes.
-	 */
-	switch (c->x86_model) {
-	case INTEL_FAM6_IVYBRIDGE_X:
-	case INTEL_FAM6_HASWELL_X:
-	case INTEL_FAM6_BROADWELL_D:
-	case INTEL_FAM6_BROADWELL_X:
-	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_ICELAKE_D:
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-	case INTEL_FAM6_XEON_PHI_KNL:
-	case INTEL_FAM6_XEON_PHI_KNM:
-
-		if (rdmsrl_safe(MSR_PPIN_CTL, &val))
-			return;
-
-		if ((val & 3UL) == 1UL) {
-			/* PPIN locked in disabled mode */
-			return;
-		}
-
-		/* If PPIN is disabled, try to enable */
-		if (!(val & 2UL)) {
-			wrmsrl_safe(MSR_PPIN_CTL,  val | 2UL);
-			rdmsrl_safe(MSR_PPIN_CTL, &val);
-		}
-
-		/* Is the enable bit set? */
-		if (val & 2UL)
-			set_cpu_cap(c, X86_FEATURE_INTEL_PPIN);
-	}
-}
-
 /*
  * Enable additional error logs from the integrated
  * memory controller on processors that support this.
@@ -535,7 +494,6 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_cmci();
 	intel_init_lmce();
-	intel_ppin_init(c);
 	intel_imc_init(c);
 }
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 5a99f993e639..e0a572472052 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -33,6 +33,7 @@
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/numa.h>
+#include <asm/coco.h>
 
 /* Is Linux running as the root partition? */
 bool hv_root_partition;
@@ -344,6 +345,11 @@ static void __init ms_hyperv_init_platform(void)
 		 */
 		swiotlb_force = SWIOTLB_FORCE;
 #endif
+		/* Isolation VMs are unenlightened SEV-based VMs, thus this check: */
+		if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+			if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE)
+				cc_set_vendor(CC_VENDOR_HYPERV);
+		}
 	}
 
 	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 21d1f062895a..4143b1e4c5c6 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,7 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_INTEL_PPIN,	CPUID_EBX,  0, 0x00000007, 1 },
 	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
 	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
 	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8dea01ffc5c1..19821f027cb3 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -612,6 +612,13 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
 		fpu_inherit_perms(dst_fpu);
 	fpregs_unlock();
 
+	/*
+	 * Children never inherit PASID state.
+	 * Force it to have its init value:
+	 */
+	if (use_xsave())
+		dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID;
+
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index de563db9cdcd..4f5ecbbaae77 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -126,7 +126,7 @@ static bool __head check_la57_support(unsigned long physaddr)
 }
 #endif
 
-static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
 {
 	unsigned long vaddr, vaddr_end;
 	int i;
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4bce802d25fb..e73f7df362f5 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -292,7 +292,6 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
 		 reason, smp_processor_id());
 
-	pr_emerg("Do you have a strange power saving mode enabled?\n");
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
 		nmi_panic(regs, "NMI: Not continuing");
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 81d8ef036637..e131d71b3cae 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -765,8 +765,11 @@ void stop_this_cpu(void *dummy)
 	 * without the encryption bit, they don't race each other when flushed
 	 * and potentially end up with the wrong entry being committed to
 	 * memory.
+	 *
+	 * Test the CPUID bit directly because the machine might've cleared
+	 * X86_FEATURE_SME due to cmdline options.
 	 */
-	if (boot_cpu_has(X86_FEATURE_SME))
+	if (cpuid_eax(0x8000001f) & BIT(0))
 		native_wbinvd();
 	for (;;) {
 		/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 617012f4619f..2ef14772dc04 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -83,10 +83,6 @@
 #include <asm/hw_irq.h>
 #include <asm/stackprotector.h>
 
-#ifdef CONFIG_ACPI_CPPC_LIB
-#include <acpi/cppc_acpi.h>
-#endif
-
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
@@ -155,8 +151,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
-static void init_freq_invariance(bool secondary, bool cppc_ready);
-
 /*
  * Report back to the Boot Processor during boot time or to the caller processor
  * during CPU online.
@@ -2097,48 +2091,6 @@ out:
 	return true;
 }
 
-#ifdef CONFIG_ACPI_CPPC_LIB
-static bool amd_set_max_freq_ratio(void)
-{
-	struct cppc_perf_caps perf_caps;
-	u64 highest_perf, 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 false;
-	}
-
-	highest_perf = amd_get_highest_perf();
-	nominal_perf = perf_caps.nominal_perf;
-
-	if (!highest_perf || !nominal_perf) {
-		pr_debug("Could not retrieve highest or nominal performance\n");
-		return false;
-	}
-
-	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
-	/* midpoint between max_boost and max_P */
-	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
-	if (!perf_ratio) {
-		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
-		return false;
-	}
-
-	arch_turbo_freq_ratio = perf_ratio;
-	arch_set_max_freq_ratio(false);
-
-	return true;
-}
-#else
-static bool amd_set_max_freq_ratio(void)
-{
-	return false;
-}
-#endif
-
 static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
@@ -2167,7 +2119,7 @@ static void register_freq_invariance_syscore_ops(void)
 static inline void register_freq_invariance_syscore_ops(void) {}
 #endif
 
-static void init_freq_invariance(bool secondary, bool cppc_ready)
+void init_freq_invariance(bool secondary, bool cppc_ready)
 {
 	bool ret = false;
 
@@ -2187,7 +2139,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready)
 		if (!cppc_ready) {
 			return;
 		}
-		ret = amd_set_max_freq_ratio();
+		ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
 	}
 
 	if (ret) {
@@ -2200,22 +2152,6 @@ static void init_freq_invariance(bool secondary, bool cppc_ready)
 	}
 }
 
-#ifdef CONFIG_ACPI_CPPC_LIB
-static DEFINE_MUTEX(freq_invariance_lock);
-
-void init_freq_invariance_cppc(void)
-{
-	static bool secondary;
-
-	mutex_lock(&freq_invariance_lock);
-
-	init_freq_invariance(secondary, true);
-	secondary = true;
-
-	mutex_unlock(&freq_invariance_lock);
-}
-#endif
-
 static void disable_freq_invariance_workfn(struct work_struct *work)
 {
 	static_branch_disable(&arch_scale_freq_key);
@@ -2264,8 +2200,4 @@ error:
 	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
 	schedule_work(&disable_freq_invariance_work);
 }
-#else
-static inline void init_freq_invariance(bool secondary, bool cppc_ready)
-{
-}
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8143693a7ea6..2e37862e3a8c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -39,6 +39,7 @@
 #include <linux/io.h>
 #include <linux/hardirq.h>
 #include <linux/atomic.h>
+#include <linux/ioasid.h>
 
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
@@ -559,6 +560,57 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
 	return true;
 }
 
+/*
+ * The unprivileged ENQCMD instruction generates #GPs if the
+ * IA32_PASID MSR has not been populated.  If possible, populate
+ * the MSR from a PASID previously allocated to the mm.
+ */
+static bool try_fixup_enqcmd_gp(void)
+{
+#ifdef CONFIG_IOMMU_SVA
+	u32 pasid;
+
+	/*
+	 * MSR_IA32_PASID is managed using XSAVE.  Directly
+	 * writing to the MSR is only possible when fpregs
+	 * are valid and the fpstate is not.  This is
+	 * guaranteed when handling a userspace exception
+	 * in *before* interrupts are re-enabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Hardware without ENQCMD will not generate
+	 * #GPs that can be fixed up here.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
+		return false;
+
+	pasid = current->mm->pasid;
+
+	/*
+	 * If the mm has not been allocated a
+	 * PASID, the #GP can not be fixed up.
+	 */
+	if (!pasid_valid(pasid))
+		return false;
+
+	/*
+	 * Did this thread already have its PASID activated?
+	 * If so, the #GP must be from something else.
+	 */
+	if (current->pasid_activated)
+		return false;
+
+	wrmsrl(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
+	current->pasid_activated = 1;
+
+	return true;
+#else
+	return false;
+#endif
+}
+
 DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 {
 	char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR;
@@ -567,6 +619,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 	unsigned long gp_addr;
 	int ret;
 
+	if (user_mode(regs) && try_fixup_enqcmd_gp())
+		return;
+
 	cond_local_irq_enable(regs);
 
 	if (static_cpu_has(X86_FEATURE_UMIP)) {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 7d20c1d34a3c..e84ee5cdbd8c 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -129,6 +129,11 @@ struct x86_cpuinit_ops x86_cpuinit = {
 
 static void default_nmi_init(void) { };
 
+static void enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { }
+static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return false; }
+static bool enc_tlb_flush_required_noop(bool enc) { return false; }
+static bool enc_cache_flush_required_noop(void) { return false; }
+
 struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
@@ -138,9 +143,16 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
 	.get_nmi_reason			= default_get_nmi_reason,
-	.save_sched_clock_state 	= tsc_save_sched_clock_state,
-	.restore_sched_clock_state 	= tsc_restore_sched_clock_state,
+	.save_sched_clock_state		= tsc_save_sched_clock_state,
+	.restore_sched_clock_state	= tsc_restore_sched_clock_state,
 	.hyper.pin_vcpu			= x86_op_int_noop,
+
+	.guest = {
+		.enc_status_change_prepare = enc_status_change_prepare_noop,
+		.enc_status_change_finish  = enc_status_change_finish_noop,
+		.enc_tlb_flush_required	   = enc_tlb_flush_required_noop,
+		.enc_cache_flush_required  = enc_cache_flush_required_noop,
+	},
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);