Merge tag 'kvmarm-fixes-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.9, part #1

 - Ensure perf events programmed to count during guest execution
   are actually enabled before entering the guest in the nVHE
   configuration.

 - Restore out-of-range handler for stage-2 translation faults.

 - Several fixes to stage-2 TLB invalidations to avoid stale
   translations, possibly including partial walk caches.

 - Fix early handling of architectural VHE-only systems to ensure E2H is
   appropriately set.

 - Correct a format specifier warning in the arch_timer selftest.

 - Make the KVM banner message correctly handle all of the possible
   configurations.

12 files changed, 114 insertions, 128 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ba8cf5e9ce56..5c1e6d6be267 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2307,6 +2307,8 @@ void arch_smt_update(void)
 
 void __init arch_cpu_finalize_init(void)
 {
+	struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info);
+
 	identify_boot_cpu();
 
 	select_idle_routine();
@@ -2345,6 +2347,13 @@ void __init arch_cpu_finalize_init(void)
 	fpu__init_system();
 	fpu__init_cpu();
 
+	/*
+	 * Ensure that access to the per CPU representation has the initial
+	 * boot CPU configuration.
+	 */
+	*c = boot_cpu_data;
+	c->initialized = true;
+
 	alternative_instructions();
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 303fef824167..e0fd57a8ba84 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -45,70 +45,70 @@ bool hyperv_paravisor_present __ro_after_init;
 EXPORT_SYMBOL_GPL(hyperv_paravisor_present);
 
 #if IS_ENABLED(CONFIG_HYPERV)
-static inline unsigned int hv_get_nested_reg(unsigned int reg)
+static inline unsigned int hv_get_nested_msr(unsigned int reg)
 {
-	if (hv_is_sint_reg(reg))
-		return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0;
+	if (hv_is_sint_msr(reg))
+		return reg - HV_X64_MSR_SINT0 + HV_X64_MSR_NESTED_SINT0;
 
 	switch (reg) {
-	case HV_REGISTER_SIMP:
-		return HV_REGISTER_NESTED_SIMP;
-	case HV_REGISTER_SIEFP:
-		return HV_REGISTER_NESTED_SIEFP;
-	case HV_REGISTER_SVERSION:
-		return HV_REGISTER_NESTED_SVERSION;
-	case HV_REGISTER_SCONTROL:
-		return HV_REGISTER_NESTED_SCONTROL;
-	case HV_REGISTER_EOM:
-		return HV_REGISTER_NESTED_EOM;
+	case HV_X64_MSR_SIMP:
+		return HV_X64_MSR_NESTED_SIMP;
+	case HV_X64_MSR_SIEFP:
+		return HV_X64_MSR_NESTED_SIEFP;
+	case HV_X64_MSR_SVERSION:
+		return HV_X64_MSR_NESTED_SVERSION;
+	case HV_X64_MSR_SCONTROL:
+		return HV_X64_MSR_NESTED_SCONTROL;
+	case HV_X64_MSR_EOM:
+		return HV_X64_MSR_NESTED_EOM;
 	default:
 		return reg;
 	}
 }
 
-u64 hv_get_non_nested_register(unsigned int reg)
+u64 hv_get_non_nested_msr(unsigned int reg)
 {
 	u64 value;
 
-	if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present)
+	if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
 		hv_ivm_msr_read(reg, &value);
 	else
 		rdmsrl(reg, value);
 	return value;
 }
-EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
 
-void hv_set_non_nested_register(unsigned int reg, u64 value)
+void hv_set_non_nested_msr(unsigned int reg, u64 value)
 {
-	if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) {
+	if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) {
 		hv_ivm_msr_write(reg, value);
 
 		/* Write proxy bit via wrmsl instruction */
-		if (hv_is_sint_reg(reg))
+		if (hv_is_sint_msr(reg))
 			wrmsrl(reg, value | 1 << 20);
 	} else {
 		wrmsrl(reg, value);
 	}
 }
-EXPORT_SYMBOL_GPL(hv_set_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
 
-u64 hv_get_register(unsigned int reg)
+u64 hv_get_msr(unsigned int reg)
 {
 	if (hv_nested)
-		reg = hv_get_nested_reg(reg);
+		reg = hv_get_nested_msr(reg);
 
-	return hv_get_non_nested_register(reg);
+	return hv_get_non_nested_msr(reg);
 }
-EXPORT_SYMBOL_GPL(hv_get_register);
+EXPORT_SYMBOL_GPL(hv_get_msr);
 
-void hv_set_register(unsigned int reg, u64 value)
+void hv_set_msr(unsigned int reg, u64 value)
 {
 	if (hv_nested)
-		reg = hv_get_nested_reg(reg);
+		reg = hv_get_nested_msr(reg);
 
-	hv_set_non_nested_register(reg, value);
+	hv_set_non_nested_msr(reg, value);
 }
-EXPORT_SYMBOL_GPL(hv_set_register);
+EXPORT_SYMBOL_GPL(hv_set_msr);
 
 static void (*vmbus_handler)(void);
 static void (*hv_stimer0_handler)(void);
@@ -352,13 +352,24 @@ static void __init reduced_hw_init(void)
 	x86_init.irqs.pre_vector_init	= x86_init_noop;
 }
 
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
+{
+	unsigned int hv_max_functions;
+
+	hv_max_functions = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS);
+	if (hv_max_functions < HYPERV_CPUID_VERSION) {
+		pr_err("%s: Could not detect Hyper-V version\n", __func__);
+		return -ENODEV;
+	}
+
+	cpuid(HYPERV_CPUID_VERSION, &info->eax, &info->ebx, &info->ecx, &info->edx);
+
+	return 0;
+}
+
 static void __init ms_hyperv_init_platform(void)
 {
 	int hv_max_functions_eax;
-	int hv_host_info_eax;
-	int hv_host_info_ebx;
-	int hv_host_info_ecx;
-	int hv_host_info_edx;
 
 #ifdef CONFIG_PARAVIRT
 	pv_info.name = "Hyper-V";
@@ -409,21 +420,6 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("Hyper-V: running on a nested hypervisor\n");
 	}
 
-	/*
-	 * Extract host information.
-	 */
-	if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) {
-		hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION);
-		hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION);
-		hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION);
-		hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION);
-
-		pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n",
-			hv_host_info_ebx >> 16, hv_host_info_ebx & 0xFFFF,
-			hv_host_info_eax, hv_host_info_edx & 0xFFFFFF,
-			hv_host_info_ecx, hv_host_info_edx >> 24);
-	}
-
 	if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
 		x86_platform.calibrate_tsc = hv_get_tsc_khz;
@@ -456,7 +452,7 @@ static void __init ms_hyperv_init_platform(void)
 				/* To be supported: more work is required.  */
 				ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
 
-				/* HV_REGISTER_CRASH_CTL is unsupported. */
+				/* HV_MSR_CRASH_CTL is unsupported. */
 				ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
 
 				/* Don't trust Hyper-V's TLB-flushing hypercalls. */
@@ -648,6 +644,7 @@ const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
 	.init.x2apic_available	= ms_hyperv_x2apic_available,
 	.init.msi_ext_dest_id	= ms_hyperv_msi_ext_dest_id,
 	.init.init_platform	= ms_hyperv_init_platform,
+	.init.guest_late_init	= ms_hyperv_late_init,
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare,
 	.runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish,
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 3259b1d4fefe..aaca8d235dc2 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -415,6 +415,17 @@ void __init topology_init_possible_cpus(void)
 	unsigned int total = assigned + disabled;
 	u32 apicid, firstid;
 
+	/*
+	 * If there was no APIC registered, then fake one so that the
+	 * topology bitmap is populated. That ensures that the code below
+	 * is valid and the various query interfaces can be used
+	 * unconditionally. This does not affect the actual APIC code in
+	 * any way because either the local APIC address has not been
+	 * registered or the local APIC was disabled on the command line.
+	 */
+	if (topo_info.boot_cpu_apic_id == BAD_APICID)
+		topology_register_boot_apic(0);
+
 	if (!restrict_to_up()) {
 		if (WARN_ON_ONCE(assigned > nr_cpu_ids)) {
 			disabled += assigned - nr_cpu_ids;
diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c
index a50ae8d63d1c..9a6069e7133c 100644
--- a/arch/x86/kernel/cpu/topology_common.c
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -140,7 +140,7 @@ static void parse_topology(struct topo_scan *tscan, bool early)
 	}
 }
 
-static void topo_set_ids(struct topo_scan *tscan)
+static void topo_set_ids(struct topo_scan *tscan, bool early)
 {
 	struct cpuinfo_x86 *c = tscan->c;
 	u32 apicid = c->topo.apicid;
@@ -148,8 +148,10 @@ static void topo_set_ids(struct topo_scan *tscan)
 	c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN);
 	c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN);
 
-	c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
-	c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+	if (!early) {
+		c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
+		c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+	}
 
 	/* Package relative core ID */
 	c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >>
@@ -187,7 +189,7 @@ void cpu_parse_topology(struct cpuinfo_x86 *c)
 		       tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]);
 	}
 
-	topo_set_ids(&tscan);
+	topo_set_ids(&tscan, false);
 }
 
 void __init cpu_init_topology(struct cpuinfo_x86 *c)
@@ -208,7 +210,7 @@ void __init cpu_init_topology(struct cpuinfo_x86 *c)
 		x86_topo_system.dom_size[dom] = 1U << sft;
 	}
 
-	topo_set_ids(&tscan);
+	topo_set_ids(&tscan, true);
 
 	/*
 	 * AMD systems have Nodes per package which cannot be mapped to
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index b66f540de054..6f1b379e3b38 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1016,17 +1016,6 @@ void __init e820__reserve_setup_data(void)
 
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
-		/*
-		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
-		 * kexec and do not need to be reserved.
-		 */
-		if (data->type != SETUP_EFI &&
-		    data->type != SETUP_IMA &&
-		    data->type != SETUP_RNG_SEED)
-			e820__range_update_kexec(pa_data,
-						 sizeof(*data) + data->len,
-						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-
 		if (data->type == SETUP_INDIRECT) {
 			len += data->len;
 			early_memunmap(data, sizeof(*data));
@@ -1038,12 +1027,9 @@ void __init e820__reserve_setup_data(void)
 
 			indirect = (struct setup_indirect *)data->data;
 
-			if (indirect->type != SETUP_INDIRECT) {
+			if (indirect->type != SETUP_INDIRECT)
 				e820__range_update(indirect->addr, indirect->len,
 						   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-				e820__range_update_kexec(indirect->addr, indirect->len,
-							 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-			}
 		}
 
 		pa_data = pa_next;
@@ -1051,7 +1037,6 @@ void __init e820__reserve_setup_data(void)
 	}
 
 	e820__update_table(e820_table);
-	e820__update_table(e820_table_kexec);
 
 	pr_info("extended physical RAM map:\n");
 	e820__print_table("reserve setup_data");
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 117e74c44e75..33a214b1a4ce 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -178,10 +178,11 @@ void fpu__init_cpu_xstate(void)
 	 * Must happen after CR4 setup and before xsetbv() to allow KVM
 	 * lazy passthrough.  Write independent of the dynamic state static
 	 * key as that does not work on the boot CPU. This also ensures
-	 * that any stale state is wiped out from XFD.
+	 * that any stale state is wiped out from XFD. Reset the per CPU
+	 * xfd cache too.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_XFD))
-		wrmsrl(MSR_IA32_XFD, init_fpstate.xfd);
+		xfd_set_state(init_fpstate.xfd);
 
 	/*
 	 * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 3518fb26d06b..19ca623ffa2a 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs
 #endif
 
 #ifdef CONFIG_X86_64
+static inline void xfd_set_state(u64 xfd)
+{
+	wrmsrl(MSR_IA32_XFD, xfd);
+	__this_cpu_write(xfd_state, xfd);
+}
+
 static inline void xfd_update_state(struct fpstate *fpstate)
 {
 	if (fpu_state_size_dynamic()) {
 		u64 xfd = fpstate->xfd;
 
-		if (__this_cpu_read(xfd_state) != xfd) {
-			wrmsrl(MSR_IA32_XFD, xfd);
-			__this_cpu_write(xfd_state, xfd);
-		}
+		if (__this_cpu_read(xfd_state) != xfd)
+			xfd_set_state(xfd);
 	}
 }
 
 extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu);
 #else
+static inline void xfd_set_state(u64 xfd) { }
+
 static inline void xfd_update_state(struct fpstate *fpstate) { }
 
 static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) {
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 212e8e06aeba..a817ed0724d1 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -81,6 +81,13 @@ static inline bool check_la57_support(void)
 	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
+	RIP_REL_REF(__pgtable_l5_enabled)	= 1;
+	RIP_REL_REF(pgdir_shift)		= 48;
+	RIP_REL_REF(ptrs_per_p4d)		= 512;
+	RIP_REL_REF(page_offset_base)		= __PAGE_OFFSET_BASE_L5;
+	RIP_REL_REF(vmalloc_base)		= __VMALLOC_BASE_L5;
+	RIP_REL_REF(vmemmap_base)		= __VMEMMAP_BASE_L5;
+
 	return true;
 }
 
@@ -175,7 +182,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 		p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
 		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
 
-		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE_NOENC;
+		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
 	}
 
 	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
@@ -431,15 +438,6 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
 				(__START_KERNEL & PGDIR_MASK)));
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
-	if (check_la57_support()) {
-		__pgtable_l5_enabled	= 1;
-		pgdir_shift		= 48;
-		ptrs_per_p4d		= 512;
-		page_offset_base	= __PAGE_OFFSET_BASE_L5;
-		vmalloc_base		= __VMALLOC_BASE_L5;
-		vmemmap_base		= __VMEMMAP_BASE_L5;
-	}
-
 	cr4_init_shadow();
 
 	/* Kill off the identity-map trampoline */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 091b3ab76a18..d0e49bd7c6f3 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -373,7 +373,16 @@ out:
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	if (is_endbr(*(u32 *)addr)) {
+	u32 insn;
+
+	/*
+	 * Since 'addr' is not guaranteed to be safe to access, use
+	 * copy_from_kernel_nofault() to read the instruction:
+	 */
+	if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
+		return NULL;
+
+	if (is_endbr(insn)) {
 		*on_func_entry = !offset || offset == 4;
 		if (*on_func_entry)
 			offset = 4;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 1ccd30c8246f..e89171b0347a 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -197,12 +197,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	if (!smp_check_mpc(mpc, oem, str))
 		return 0;
 
-	/* Initialize the lapic mapping */
-	if (!acpi_lapic)
-		register_lapic_address(mpc->lapic);
-
-	if (early)
+	if (early) {
+		/* Initialize the lapic mapping */
+		if (!acpi_lapic)
+			register_lapic_address(mpc->lapic);
 		return 1;
+	}
 
 	/* Now process the configuration blocks. */
 	while (count < mpc->length) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3e1e96efadfe..ef206500ed6f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1206,16 +1206,6 @@ void __init i386_reserve_resources(void)
 
 #endif /* CONFIG_X86_32 */
 
-#ifndef CONFIG_SMP
-void __init smp_prepare_boot_cpu(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	*c = boot_cpu_data;
-	c->initialized = true;
-}
-#endif
-
 static struct notifier_block kernel_offset_notifier = {
 	.notifier_call = dump_kernel_offset
 };
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fe355c89f6c1..76bb65045c64 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -313,14 +313,6 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-static void __init smp_store_boot_cpu_info(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	*c = boot_cpu_data;
-	c->initialized = true;
-}
-
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -1039,29 +1031,15 @@ static __init void disable_smp(void)
 	cpumask_set_cpu(0, topology_die_cpumask(0));
 }
 
-static void __init smp_cpu_index_default(void)
-{
-	int i;
-	struct cpuinfo_x86 *c;
-
-	for_each_possible_cpu(i) {
-		c = &cpu_data(i);
-		/* mark all to hotplug */
-		c->cpu_index = nr_cpu_ids;
-	}
-}
-
 void __init smp_prepare_cpus_common(void)
 {
 	unsigned int i;
 
-	smp_cpu_index_default();
-
-	/*
-	 * Setup boot CPU information
-	 */
-	smp_store_boot_cpu_info(); /* Final full version of the data */
-	mb();
+	/* Mark all except the boot CPU as hotpluggable */
+	for_each_possible_cpu(i) {
+		if (i)
+			per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids;
+	}
 
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);