Merge tag 'kvm-riscv-6.3-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 6.3

- Fix wrong usage of PGDIR_SIZE to check page sizes
- Fix privilege mode setting in kvm_riscv_vcpu_trap_redirect()
- Redirect illegal instruction traps to guest
- SBI PMU support for guest

25 files changed, 271 insertions, 58 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 9cf07322875a..73ed982d4100 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -14,13 +14,13 @@ endif
 
 ifdef CONFIG_CC_IS_GCC
 RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
 endif
 ifdef CONFIG_CC_IS_CLANG
 RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
 RETPOLINE_VDSO_CFLAGS	:= -mretpoline
 endif
+RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 
 ifdef CONFIG_RETHUNK
 RETHUNK_CFLAGS		:= -mfunction-return=thunk-extern
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index 5521ea12f44e..aa9b96457584 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -32,7 +32,7 @@ intcall:
 	movw	%dx, %si
 	movw	%sp, %di
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl
 
 	/* Pop full state from the stack */
 	popal
@@ -67,7 +67,7 @@ intcall:
 	jz	4f
 	movw	%sp, %si
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl
 4:	addw	$44, %sp
 
 	/* Restore state and return */
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index d4a314cc50d6..321a5011042d 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode)
 
 	/* Load the new page-table. */
 	write_cr3(top_level_pgt);
+
+	/*
+	 * Now that the required page table mappings are established and a
+	 * GHCB can be used, check for SNP guest/HV feature compatibility.
+	 */
+	snp_check_features();
 }
 
 static pte_t *split_large_pmd(struct x86_mapping_info *info,
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 62208ec04ca4..20118fb7c53b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -126,6 +126,7 @@ static inline void console_init(void)
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 void sev_enable(struct boot_params *bp);
+void snp_check_features(void);
 void sev_es_shutdown_ghcb(void);
 extern bool sev_es_check_ghcb_fault(unsigned long address);
 void snp_set_page_private(unsigned long paddr);
@@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp)
 	if (bp)
 		bp->cc_blob_address = 0;
 }
+static inline void snp_check_features(void) { }
 static inline void sev_es_shutdown_ghcb(void) { }
 static inline bool sev_es_check_ghcb_fault(unsigned long address)
 {
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index c93930d5ccbd..d63ad8f99f83 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void)
 		error("Can't unmap GHCB page");
 }
 
+static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set,
+					     unsigned int reason, u64 exit_info_2)
+{
+	u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason);
+
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST);
+	ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
+	ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
+
+	while (true)
+		asm volatile("hlt\n" : : : "memory");
+}
+
 bool sev_es_check_ghcb_fault(unsigned long address)
 {
 	/* Check whether the fault was on the GHCB page */
@@ -270,6 +287,59 @@ static void enforce_vmpl0(void)
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
 }
 
+/*
+ * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
+ * guest side implementation for proper functioning of the guest. If any
+ * of these features are enabled in the hypervisor but are lacking guest
+ * side implementation, the behavior of the guest will be undefined. The
+ * guest could fail in non-obvious way making it difficult to debug.
+ *
+ * As the behavior of reserved feature bits is unknown to be on the
+ * safe side add them to the required features mask.
+ */
+#define SNP_FEATURES_IMPL_REQ	(MSR_AMD64_SNP_VTOM |			\
+				 MSR_AMD64_SNP_REFLECT_VC |		\
+				 MSR_AMD64_SNP_RESTRICTED_INJ |		\
+				 MSR_AMD64_SNP_ALT_INJ |		\
+				 MSR_AMD64_SNP_DEBUG_SWAP |		\
+				 MSR_AMD64_SNP_VMPL_SSS |		\
+				 MSR_AMD64_SNP_SECURE_TSC |		\
+				 MSR_AMD64_SNP_VMGEXIT_PARAM |		\
+				 MSR_AMD64_SNP_VMSA_REG_PROTECTION |	\
+				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
+				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
+				 MSR_AMD64_SNP_RESERVED_MASK)
+
+/*
+ * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented
+ * by the guest kernel. As and when a new feature is implemented in the
+ * guest kernel, a corresponding bit should be added to the mask.
+ */
+#define SNP_FEATURES_PRESENT (0)
+
+void snp_check_features(void)
+{
+	u64 unsupported;
+
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	/*
+	 * Terminate the boot if hypervisor has enabled any feature lacking
+	 * guest side implementation. Pass on the unsupported features mask through
+	 * EXIT_INFO_2 of the GHCB protocol so that those features can be reported
+	 * as part of the guest boot failure.
+	 */
+	unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+	if (unsupported) {
+		if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb()))
+			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+		sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN,
+				      GHCB_SNP_UNSUPPORTED, unsupported);
+	}
+}
+
 void sev_enable(struct boot_params *bp)
 {
 	unsigned int eax, ebx, ecx, edx;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aa53d042b943..73bd0d70817e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6339,6 +6339,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+	case INTEL_FAM6_EMERALDRAPIDS_X:
 		pmem = true;
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index a2834bc93149..551741e79e03 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,6 +41,7 @@
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
  *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+ *					  MTL
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -51,50 +52,50 @@
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
  *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- *						ICL,TGL,RKL,ADL,RPL
+ *						ICL,TGL,RKL,ADL,RPL,MTL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
  *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- *						RPL,SPR
+ *						RPL,SPR,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
  *						GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- *						KBL,CML,ICL,TGL,RKL,ADL,RPL
+ *						KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
  *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
  *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
  *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- *						TNT,RKL,ADL,RPL
+ *						TNT,RKL,ADL,RPL,MTL
  *			       Scope: Package (physical package)
  *
  */
@@ -676,6 +677,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&icx_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&icx_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&icx_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&icx_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&icl_cstates),
@@ -686,6 +688,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&adl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6f1ccc57a692..459b1aafd4d4 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
 	{},
 };
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index ecced3a52668..c65d8906cbcf 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_BROADWELL_G:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+	case INTEL_FAM6_EMERALDRAPIDS_X:
 
 	case INTEL_FAM6_ATOM_SILVERMONT:
 	case INTEL_FAM6_ATOM_SILVERMONT_D:
@@ -107,6 +108,8 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
+	case INTEL_FAM6_METEORLAKE:
+	case INTEL_FAM6_METEORLAKE_L:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 65064d9f7fa6..8eb74cf386db 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -14,6 +14,7 @@
 #include <asm/mmu.h>
 #include <asm/mpspec.h>
 #include <asm/x86_init.h>
+#include <asm/cpufeature.h>
 
 #ifdef CONFIG_ACPI_APEI
 # include <asm/pgtable_types.h>
@@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void);
 /* Physical address to resume after wakeup */
 unsigned long acpi_get_wakeup_address(void);
 
+static inline bool acpi_skip_set_wakeup_address(void)
+{
+	return cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+
+#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
+
 /*
  * Check if the CPU can handle C2 and deeper
  */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b049d950612f..ca97442e8d49 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno)
 		asm("mov %%db6, %0" :"=r" (val));
 		break;
 	case 7:
-		asm("mov %%db7, %0" :"=r" (val));
+		/*
+		 * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them
+		 * with other code.
+		 *
+		 * This is needed because a DR7 access can cause a #VC exception
+		 * when running under SEV-ES. Taking a #VC exception is not a
+		 * safe thing to do just anywhere in the entry code and
+		 * re-ordering might place the access into an unsafe location.
+		 *
+		 * This happened in the NMI handler, where the DR7 read was
+		 * re-ordered to happen before the call to sev_es_ist_enter(),
+		 * causing stack recursion.
+		 */
+		asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER);
 		break;
 	default:
 		BUG();
@@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 		asm("mov %0, %%db6"	::"r" (value));
 		break;
 	case 7:
-		asm("mov %0, %%db7"	::"r" (value));
+		/*
+		 * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them
+		 * with other code.
+		 *
+		 * While is didn't happen with a DR7 write (see the DR7 read
+		 * comment above which explains where it happened), add the
+		 * __FORCE_ORDER here too to avoid similar problems in the
+		 * future.
+		 */
+		asm volatile("mov %0, %%db7"	::"r" (value), __FORCE_ORDER);
 		break;
 	default:
 		BUG();
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 37ff47552bcb..d3fe82c5d6b6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -566,6 +566,26 @@
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 #define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
+/* SNP feature bits enabled by the hypervisor */
+#define MSR_AMD64_SNP_VTOM			BIT_ULL(3)
+#define MSR_AMD64_SNP_REFLECT_VC		BIT_ULL(4)
+#define MSR_AMD64_SNP_RESTRICTED_INJ		BIT_ULL(5)
+#define MSR_AMD64_SNP_ALT_INJ			BIT_ULL(6)
+#define MSR_AMD64_SNP_DEBUG_SWAP		BIT_ULL(7)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS		BIT_ULL(8)
+#define MSR_AMD64_SNP_BTB_ISOLATION		BIT_ULL(9)
+#define MSR_AMD64_SNP_VMPL_SSS			BIT_ULL(10)
+#define MSR_AMD64_SNP_SECURE_TSC		BIT_ULL(11)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM		BIT_ULL(12)
+#define MSR_AMD64_SNP_IBS_VIRT			BIT_ULL(14)
+#define MSR_AMD64_SNP_VMSA_REG_PROTECTION	BIT_ULL(16)
+#define MSR_AMD64_SNP_SMT_PROTECTION		BIT_ULL(17)
+
+/* SNP feature bits reserved for future use. */
+#define MSR_AMD64_SNP_RESERVED_BIT13		BIT_ULL(13)
+#define MSR_AMD64_SNP_RESERVED_BIT15		BIT_ULL(15)
+#define MSR_AMD64_SNP_RESERVED_MASK		GENMASK_ULL(63, 18)
+
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
 /* AMD Collaborative Processor Performance Control MSRs */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index f69c168391aa..80e1df482337 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -116,6 +116,12 @@
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
+#define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
+#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
+	/* SW_EXITINFO1[3:0] */					\
+	(((((u64)reason_set) & 0xf)) |				\
+	/* SW_EXITINFO1[11:4] */				\
+	((((u64)reason_code) & 0xff) << 4))
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
 /* Exit code reserved for hypervisor/software use */
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 1f60a2b27936..fdbb5f07448f 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)
 
 static void disable_freq_invariance_workfn(struct work_struct *work)
 {
+	int cpu;
+
 	static_branch_disable(&arch_scale_freq_key);
+
+	/*
+	 * Set arch_freq_scale to a default value on all cpus
+	 * This negates the effect of scaling
+	 */
+	for_each_possible_cpu(cpu)
+		per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE;
 }
 
 static DECLARE_WORK(disable_freq_invariance_work,
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index efe0c30d3a12..77538abeb72a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 	return entry;
 }
 
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_val;
+
+	/*
+	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+	 * with a valid event code for supported resource type and the bits
+	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+	 * are error bits.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
 static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
@@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
-	if (am)
+	if (am) {
 		memset(am, 0, sizeof(*am));
+
+		/* Record any initial, non-zero count value. */
+		__rmid_read(rmid, eventid, &am->prev_msr);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
+	int ret;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;
 
-	/*
-	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
-	 * with a valid event code for supported resource type and the bits
-	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
-	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
-	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
-	 * are error bits.
-	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
-	if (msr_val & RMID_VAL_ERROR)
-		return -EIO;
-	if (msr_val & RMID_VAL_UNAVAIL)
-		return -EINVAL;
+	ret = __rmid_read(rmid, eventid, &msr_val);
+	if (ret)
+		return ret;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e5a48f05e787..5993da21d822 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_sched_in() during context switch.
 	 */
-	barrier();
+	smp_mb();
 
 	/*
 	 * By now, the task's closid and rmid are set. If the task is current
@@ -2402,6 +2404,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			WRITE_ONCE(t->rmid, to->mon.rmid);
 
 			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and resctrl_sched_in()
+			 * during context switch.
+			 */
+			smp_mb();
+
+			/*
 			 * If the task is on a CPU, set the CPU in the mask.
 			 * The detection is inaccurate as tasks might move or
 			 * schedule before the smp function call takes place.
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 3aa5304200c5..4d8aff05a509 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq)
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+	irq_set_status_flags(irq, IRQ_LEVEL);
 	enable_irq(irq);
 	lapic_assign_legacy_vector(irq, true);
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index beb1bada1b0a..c683666876f1 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -65,8 +65,10 @@ void __init init_ISA_irqs(void)
 
 	legacy_pic->init(0);
 
-	for (i = 0; i < nr_legacy_irqs(); i++)
+	for (i = 0; i < nr_legacy_irqs(); i++) {
 		irq_set_chip_and_handler(i, chip, handle_level_irq);
+		irq_set_status_flags(i, IRQ_LEVEL);
+	}
 }
 
 void __init init_IRQ(void)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0f82c247e1fd..7896acf05117 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3539,18 +3539,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
 
-	if (var->unusable || !var->present)
-		ar = 1 << 16;
-	else {
-		ar = var->type & 15;
-		ar |= (var->s & 1) << 4;
-		ar |= (var->dpl & 3) << 5;
-		ar |= (var->present & 1) << 7;
-		ar |= (var->avl & 1) << 12;
-		ar |= (var->l & 1) << 13;
-		ar |= (var->db & 1) << 14;
-		ar |= (var->g & 1) << 15;
-	}
+	ar = var->type & 15;
+	ar |= (var->s & 1) << 4;
+	ar |= (var->dpl & 3) << 5;
+	ar |= (var->present & 1) << 7;
+	ar |= (var->avl & 1) << 12;
+	ar |= (var->l & 1) << 13;
+	ar |= (var->db & 1) << 14;
+	ar |= (var->g & 1) << 15;
+	ar |= (var->unusable || !var->present) << 16;
 
 	return ar;
 }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d3987359d441..cb258f58fdc8 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -26,6 +26,7 @@
 #include <asm/pti.h>
 #include <asm/text-patching.h>
 #include <asm/memtype.h>
+#include <asm/paravirt.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -804,6 +805,9 @@ void __init poking_init(void)
 	poking_mm = mm_alloc();
 	BUG_ON(!poking_mm);
 
+	/* Xen PV guests need the PGD to be pinned. */
+	paravirt_arch_dup_mmap(NULL, poking_mm);
+
 	/*
 	 * Randomize the poking address, but make sure that the following page
 	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 46de9cf5c91d..fb4b1b5e0dea 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
 		u8 mtrr_type, uniform;
 
 		mtrr_type = mtrr_type_lookup(start, end, &uniform);
-		if (mtrr_type != MTRR_TYPE_WRBACK)
+		if (mtrr_type != MTRR_TYPE_WRBACK &&
+		    mtrr_type != MTRR_TYPE_INVALID)
 			return _PAGE_CACHE_MODE_UC_MINUS;
 
 		return _PAGE_CACHE_MODE_WB;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 758cbfe55daa..4b3efaa82ab7 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/efi.h>
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
@@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
 	return mcfg_res.flags;
 }
 
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+	efi_memory_desc_t *md;
+	u64 size, mmio_start, mmio_end;
+
+	for_each_efi_memory_desc(md) {
+		if (md->type == EFI_MEMORY_MAPPED_IO) {
+			size = md->num_pages << EFI_PAGE_SHIFT;
+			mmio_start = md->phys_addr;
+			mmio_end = mmio_start + size;
+
+			/*
+			 * N.B. Caller supplies (start, start + size),
+			 * so to match, mmio_end is the first address
+			 * *past* the EFI_MEMORY_MAPPED_IO area.
+			 */
+			if (mmio_start <= start && end <= mmio_end)
+				return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
 typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
 
 static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 				     struct pci_mmcfg_region *cfg,
-				     struct device *dev, int with_e820)
+				     struct device *dev, const char *method)
 {
 	u64 addr = cfg->res.start;
 	u64 size = resource_size(&cfg->res);
 	u64 old_size = size;
 	int num_buses;
-	char *method = with_e820 ? "E820" : "ACPI motherboard resources";
 
 	while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
 		size >>= 1;
@@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		return false;
 
 	if (dev)
-		dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+		dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
 			 &cfg->res, method);
 	else
-		pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+		pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
 		       &cfg->res, method);
 
 	if (old_size != size) {
@@ -500,7 +526,8 @@ static bool __ref
 pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
 {
 	if (!early && !acpi_disabled) {
-		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+				       "ACPI motherboard resource"))
 			return true;
 
 		if (dev)
@@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			       "MMCONFIG at %pR not reserved in "
 			       "ACPI motherboard resources\n",
 			       &cfg->res);
+
+		if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+				       "EfiMemoryMappedIO"))
+			return true;
 	}
 
 	/*
@@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 	/* Don't try to do this check unless configuration
 	   type 1 is available. how about type 2 ?*/
 	if (raw_pci_ops)
-		return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
+		return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+					  "E820 entry");
 
 	return false;
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index b94f727251b6..8babce71915f 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
 	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
 		for (i = 0; i < msidesc->nvec_used; i++)
 			xen_destroy_irq(msidesc->irq + i);
+		msidesc->irq = 0;
 	}
 }
 
@@ -433,6 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = {
 };
 
 static struct msi_domain_info xen_pci_msi_domain_info = {
+	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
 	.ops			= &xen_pci_msi_domain_ops,
 };
 
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 48a3eb09d951..650cdbbdaf45 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -7,7 +7,7 @@
 #include <asm/elf.h>
 
 
-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
 	return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
 }
@@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
 	return 1;
 }
 
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 58db86f7b384..9bdc3b656b2c 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn)
 	return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
 }
 
-static inline unsigned p2m_index(unsigned long pfn)
-{
-	return pfn % P2M_PER_PAGE;
-}
-
 static void p2m_top_mfn_init(unsigned long *top)
 {
 	unsigned i;