aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/hyperv/hv_init.c6
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/microcode_amd.h2
-rw-r--r--arch/x86/include/asm/module.h60
-rw-r--r--arch/x86/include/asm/nospec-branch.h21
-rw-r--r--arch/x86/include/asm/vermagic.h68
-rw-r--r--arch/x86/kernel/cpu/intel.c54
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c14
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h1
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c16
-rw-r--r--arch/x86/kernel/umip.c2
-rw-r--r--arch/x86/kvm/Makefile4
-rw-r--r--arch/x86/kvm/svm/sev.c6
-rw-r--r--arch/x86/kvm/svm/svm.c10
-rw-r--r--arch/x86/kvm/svm/vmenter.S10
-rw-r--r--arch/x86/kvm/vmx/nested.c21
-rw-r--r--arch/x86/kvm/vmx/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c21
-rw-r--r--arch/x86/platform/efi/efi_64.c16
21 files changed, 214 insertions, 126 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d6104ea8af0..1197b5596d5a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -149,7 +149,7 @@ config X86
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
- select HAVE_ARCH_USERFAULTFD_WP if USERFAULTFD
+ select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD
select HAVE_ARCH_VMAP_STACK if X86_64
select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_ASM_MODVERSIONS
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index b0da5320bcff..624f5d9b0f79 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -20,6 +20,7 @@
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
+#include <linux/kernel.h>
#include <linux/cpuhotplug.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
@@ -419,11 +420,14 @@ void hyperv_cleanup(void)
}
EXPORT_SYMBOL_GPL(hyperv_cleanup);
-void hyperv_report_panic(struct pt_regs *regs, long err)
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
{
static bool panic_reported;
u64 guest_id;
+ if (in_die && !panic_on_oops)
+ return;
+
/*
* We prefer to report panic on 'die' chain as we have proper
* registers to report, but if we miss it (e.g. on BUG()) we need
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cdcf48d52a12..8391c115c0ec 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -178,8 +178,10 @@ extern void efi_free_boot_services(void);
extern pgd_t * __init efi_uv1_memmap_phys_prolog(void);
extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd);
+/* kexec external ABI */
struct efi_setup_data {
u64 fw_vendor;
+ u64 __unused;
u64 tables;
u64 smbios;
u64 reserved[8];
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 6685e1218959..7063b5a43220 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
unsigned int mpb[0];
};
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
#ifdef CONFIG_MICROCODE_AMD
extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index c215d2762488..e988bac0a4a1 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -13,64 +13,4 @@ struct mod_arch_specific {
#endif
};
-#ifdef CONFIG_X86_64
-/* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M486SX
-#define MODULE_PROC_FAMILY "486SX "
-#elif defined CONFIG_M486
-#define MODULE_PROC_FAMILY "486 "
-#elif defined CONFIG_M586
-#define MODULE_PROC_FAMILY "586 "
-#elif defined CONFIG_M586TSC
-#define MODULE_PROC_FAMILY "586TSC "
-#elif defined CONFIG_M586MMX
-#define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
-#elif defined CONFIG_MATOM
-#define MODULE_PROC_FAMILY "ATOM "
-#elif defined CONFIG_M686
-#define MODULE_PROC_FAMILY "686 "
-#elif defined CONFIG_MPENTIUMII
-#define MODULE_PROC_FAMILY "PENTIUMII "
-#elif defined CONFIG_MPENTIUMIII
-#define MODULE_PROC_FAMILY "PENTIUMIII "
-#elif defined CONFIG_MPENTIUMM
-#define MODULE_PROC_FAMILY "PENTIUMM "
-#elif defined CONFIG_MPENTIUM4
-#define MODULE_PROC_FAMILY "PENTIUM4 "
-#elif defined CONFIG_MK6
-#define MODULE_PROC_FAMILY "K6 "
-#elif defined CONFIG_MK7
-#define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_MELAN
-#define MODULE_PROC_FAMILY "ELAN "
-#elif defined CONFIG_MCRUSOE
-#define MODULE_PROC_FAMILY "CRUSOE "
-#elif defined CONFIG_MEFFICEON
-#define MODULE_PROC_FAMILY "EFFICEON "
-#elif defined CONFIG_MWINCHIPC6
-#define MODULE_PROC_FAMILY "WINCHIPC6 "
-#elif defined CONFIG_MWINCHIP3D
-#define MODULE_PROC_FAMILY "WINCHIP3D "
-#elif defined CONFIG_MCYRIXIII
-#define MODULE_PROC_FAMILY "CYRIXIII "
-#elif defined CONFIG_MVIAC3_2
-#define MODULE_PROC_FAMILY "VIAC3-2 "
-#elif defined CONFIG_MVIAC7
-#define MODULE_PROC_FAMILY "VIAC7 "
-#elif defined CONFIG_MGEODEGX1
-#define MODULE_PROC_FAMILY "GEODEGX1 "
-#elif defined CONFIG_MGEODE_LX
-#define MODULE_PROC_FAMILY "GEODE "
-#else
-#error unknown processor family
-#endif
-
-#ifdef CONFIG_X86_32
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-#endif
-
#endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 07e95dcb40ad..7e9a281e2660 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -237,27 +237,6 @@ enum ssb_mitigation {
extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];
-/*
- * On VMEXIT we must ensure that no RSB predictions learned in the guest
- * can be followed in the host, by overwriting the RSB completely. Both
- * retpoline and IBRS mitigations for Spectre v2 need this; only on future
- * CPUs with IBRS_ALL *might* it be avoided.
- */
-static inline void vmexit_fill_RSB(void)
-{
-#ifdef CONFIG_RETPOLINE
- unsigned long loops;
-
- asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE("jmp 910f",
- __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
- X86_FEATURE_RETPOLINE)
- "910:"
- : "=r" (loops), ASM_CALL_CONSTRAINT
- : : "memory" );
-#endif
-}
-
static __always_inline
void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
{
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
new file mode 100644
index 000000000000..75884d2cdec3
--- /dev/null
+++ b/arch/x86/include/asm/vermagic.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_X86_64
+/* X86_64 does not define MODULE_PROC_FAMILY */
+#elif defined CONFIG_M486SX
+#define MODULE_PROC_FAMILY "486SX "
+#elif defined CONFIG_M486
+#define MODULE_PROC_FAMILY "486 "
+#elif defined CONFIG_M586
+#define MODULE_PROC_FAMILY "586 "
+#elif defined CONFIG_M586TSC
+#define MODULE_PROC_FAMILY "586TSC "
+#elif defined CONFIG_M586MMX
+#define MODULE_PROC_FAMILY "586MMX "
+#elif defined CONFIG_MCORE2
+#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
+#elif defined CONFIG_M686
+#define MODULE_PROC_FAMILY "686 "
+#elif defined CONFIG_MPENTIUMII
+#define MODULE_PROC_FAMILY "PENTIUMII "
+#elif defined CONFIG_MPENTIUMIII
+#define MODULE_PROC_FAMILY "PENTIUMIII "
+#elif defined CONFIG_MPENTIUMM
+#define MODULE_PROC_FAMILY "PENTIUMM "
+#elif defined CONFIG_MPENTIUM4
+#define MODULE_PROC_FAMILY "PENTIUM4 "
+#elif defined CONFIG_MK6
+#define MODULE_PROC_FAMILY "K6 "
+#elif defined CONFIG_MK7
+#define MODULE_PROC_FAMILY "K7 "
+#elif defined CONFIG_MK8
+#define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_MELAN
+#define MODULE_PROC_FAMILY "ELAN "
+#elif defined CONFIG_MCRUSOE
+#define MODULE_PROC_FAMILY "CRUSOE "
+#elif defined CONFIG_MEFFICEON
+#define MODULE_PROC_FAMILY "EFFICEON "
+#elif defined CONFIG_MWINCHIPC6
+#define MODULE_PROC_FAMILY "WINCHIPC6 "
+#elif defined CONFIG_MWINCHIP3D
+#define MODULE_PROC_FAMILY "WINCHIP3D "
+#elif defined CONFIG_MCYRIXIII
+#define MODULE_PROC_FAMILY "CYRIXIII "
+#elif defined CONFIG_MVIAC3_2
+#define MODULE_PROC_FAMILY "VIAC3-2 "
+#elif defined CONFIG_MVIAC7
+#define MODULE_PROC_FAMILY "VIAC7 "
+#elif defined CONFIG_MGEODEGX1
+#define MODULE_PROC_FAMILY "GEODEGX1 "
+#elif defined CONFIG_MGEODE_LX
+#define MODULE_PROC_FAMILY "GEODE "
+#else
+#error unknown processor family
+#endif
+
+#ifdef CONFIG_X86_32
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+#else
+# define MODULE_ARCH_VERMAGIC ""
+#endif
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index bf08d4508ecb..a19a680542ce 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1119,35 +1119,53 @@ void switch_to_sld(unsigned long tifn)
sld_update_msr(!(tifn & _TIF_SLD));
}
-#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY}
-
/*
- * The following processors have the split lock detection feature. But
- * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot
- * be enumerated. Enable it by family and model matching on these
- * processors.
+ * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should
+ * only be trusted if it is confirmed that a CPU model implements a
+ * specific feature at a particular bit position.
+ *
+ * The possible driver data field values:
+ *
+ * - 0: CPU models that are known to have the per-core split-lock detection
+ * feature even though they do not enumerate IA32_CORE_CAPABILITIES.
+ *
+ * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use
+ * bit 5 to enumerate the per-core split-lock detection feature.
*/
static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
- SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X),
- SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, 1),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, 1),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, 1),
{}
};
void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
{
- u64 ia32_core_caps = 0;
+ const struct x86_cpu_id *m;
+ u64 ia32_core_caps;
+
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return;
- if (c->x86_vendor != X86_VENDOR_INTEL)
+ m = x86_match_cpu(split_lock_cpu_ids);
+ if (!m)
return;
- if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) {
- /* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */
+
+ switch (m->driver_data) {
+ case 0:
+ break;
+ case 1:
+ if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES))
+ return;
rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
- } else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
- /* Enumerate split lock detection by family and model. */
- if (x86_match_cpu(split_lock_cpu_ids))
- ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT;
+ if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT))
+ return;
+ break;
+ default:
+ return;
}
- if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
- split_lock_setup();
+ split_lock_setup();
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..ebf34c7bc8bc 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void)
ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
- pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
- ms_hyperv.features, ms_hyperv.hints);
+ pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+ ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
}
+ /*
+ * Hyper-V expects to get crash register data or kmsg when
+ * crash enlightment is available and system crashes. Set
+ * crash_kexec_post_notifiers to be true to make sure that
+ * calling crash enlightment interface before running kdump
+ * kernel.
+ */
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+ crash_kexec_post_notifiers = true;
+
#ifdef CONFIG_X86_LOCAL_APIC
if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 89049b343c7a..d8cc5223b7ce 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
d->id = id;
cpumask_set_cpu(cpu, &d->cpu_mask);
+ rdt_domain_reconfigure_cdp(r);
+
if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
kfree(d);
return;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 181c992f448c..3dd13f3a8b23 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -601,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 064e9ef44cd6..5a359d9fcc05 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable)
return 0;
}
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+ if (!r->alloc_capable)
+ return;
+
+ if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+ l2_qos_cfg_update(&r->alloc_enabled);
+
+ if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+ l3_qos_cfg_update(&r->alloc_enabled);
+}
+
/*
* Enable or disable the MBA software controller
* which helps user specify bandwidth in MBps.
@@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
* If the rdtgroup is a mon group and parent directory
* is a valid "mon_groups" directory, remove the mon group.
*/
- if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+ if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+ rdtgrp != &rdtgroup_default) {
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
ret = rdtgroup_ctrl_remove(kn, rdtgrp);
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 4d732a444711..8d5cbe1bbb3b 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -81,7 +81,7 @@
#define UMIP_INST_SLDT 3 /* 0F 00 /0 */
#define UMIP_INST_STR 4 /* 0F 00 /1 */
-const char * const umip_insns[5] = {
+static const char * const umip_insns[5] = {
[UMIP_INST_SGDT] = "SGDT",
[UMIP_INST_SIDT] = "SIDT",
[UMIP_INST_SMSW] = "SMSW",
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a789759b7261..4a3081e9f4b5 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -3,6 +3,10 @@
ccflags-y += -Iarch/x86/kvm
ccflags-$(CONFIG_KVM_WERROR) += -Werror
+ifeq ($(CONFIG_FRAME_POINTER),y)
+OBJECT_FILES_NON_STANDARD_vmenter.o := y
+endif
+
KVM := ../../../virt/kvm
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0e3fc311d7da..cf912b4aaba8 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -12,6 +12,7 @@
#include <linux/kernel.h>
#include <linux/highmem.h>
#include <linux/psp-sev.h>
+#include <linux/pagemap.h>
#include <linux/swap.h>
#include "x86.h"
@@ -1117,7 +1118,7 @@ int __init sev_hardware_setup(void)
/* Maximum number of encrypted guests supported simultaneously */
max_sev_asid = cpuid_ecx(0x8000001F);
- if (!max_sev_asid)
+ if (!svm_sev_enabled())
return 1;
/* Minimum ASID value that should be used for SEV guest */
@@ -1156,6 +1157,9 @@ err:
void sev_hardware_teardown(void)
{
+ if (!svm_sev_enabled())
+ return;
+
bitmap_free(sev_asid_bitmap);
bitmap_free(sev_reclaim_asid_bitmap);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2be5bbae3a40..2f379bacbb26 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3276,7 +3276,7 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
svm_complete_interrupts(svm);
}
-bool __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
+void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
static void svm_vcpu_run(struct kvm_vcpu *vcpu)
{
@@ -3330,13 +3330,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
*/
x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
- local_irq_enable();
-
__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
#ifdef CONFIG_X86_64
wrmsrl(MSR_GS_BASE, svm->host.gs_base);
#else
@@ -3366,8 +3361,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
reload_tss(vcpu);
- local_irq_disable();
-
x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
vcpu->arch.cr2 = svm->vmcb->save.cr2;
@@ -3411,7 +3404,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
mark_all_clean(svm->vmcb);
}
-STACK_FRAME_NON_STANDARD(svm_vcpu_run);
static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root)
{
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index fa1af90067e9..bf944334003a 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -3,6 +3,7 @@
#include <asm/asm.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
#define WORD_SIZE (BITS_PER_LONG / 8)
@@ -35,7 +36,6 @@
*/
SYM_FUNC_START(__svm_vcpu_run)
push %_ASM_BP
- mov %_ASM_SP, %_ASM_BP
#ifdef CONFIG_X86_64
push %r15
push %r14
@@ -78,6 +78,7 @@ SYM_FUNC_START(__svm_vcpu_run)
pop %_ASM_AX
/* Enter guest mode */
+ sti
1: vmload %_ASM_AX
jmp 3f
2: cmpb $0, kvm_rebooting
@@ -99,6 +100,13 @@ SYM_FUNC_START(__svm_vcpu_run)
ud2
_ASM_EXTABLE(5b, 6b)
7:
+ cli
+
+#ifdef CONFIG_RETPOLINE
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+#endif
+
/* "POP" @regs to RAX. */
pop %_ASM_AX
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index cbc9ea2de28f..fd78ffbde644 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5533,8 +5533,25 @@ static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu,
return 1 & (b >> (field & 7));
}
+static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12)
+{
+ u32 entry_intr_info = vmcs12->vm_entry_intr_info_field;
+
+ if (nested_cpu_has_mtf(vmcs12))
+ return true;
+
+ /*
+ * An MTF VM-exit may be injected into the guest by setting the
+ * interruption-type to 7 (other event) and the vector field to 0. Such
+ * is the case regardless of the 'monitor trap flag' VM-execution
+ * control.
+ */
+ return entry_intr_info == (INTR_INFO_VALID_MASK
+ | INTR_TYPE_OTHER_EVENT);
+}
+
/*
- * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
+ * Return true if we should exit from L2 to L1 to handle an exit, or false if we
* should handle it ourselves in L0 (and then continue L2). Only call this
* when in is_guest_mode (L2).
*/
@@ -5633,7 +5650,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
case EXIT_REASON_MWAIT_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
case EXIT_REASON_MONITOR_TRAP_FLAG:
- return nested_cpu_has_mtf(vmcs12);
+ return nested_vmx_exit_handled_mtf(vmcs12);
case EXIT_REASON_MONITOR_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
case EXIT_REASON_PAUSE_INSTRUCTION:
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 83050977490c..c2c6335a998c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4572,7 +4572,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
*/
static void kvm_machine_check(void)
{
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_MCE)
struct pt_regs regs = {
.cs = 3, /* Fake ring 3 no matter what the guest ran on */
.flags = X86_EFLAGS_IF,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3bf2ecafd027..c5835f9cb9ad 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3060,6 +3060,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_PERF_CTL:
case MSR_AMD64_DC_CFG:
case MSR_F15H_EX_CFG:
+ /*
+ * Intel Sandy Bridge CPUs must support the RAPL (running average power
+ * limit) MSRs. Just return 0, as we do not want to expose the host
+ * data here. Do not conditionalize this on CPUID, as KVM does not do
+ * so for existing CPU-specific MSRs.
+ */
+ case MSR_RAPL_POWER_UNIT:
+ case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */
+ case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */
+ case MSR_PKG_ENERGY_STATUS: /* Total package */
+ case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */
msr_info->data = 0;
break;
case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
@@ -5049,10 +5060,13 @@ set_identity_unlock:
r = -EFAULT;
if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
goto out;
+ mutex_lock(&kvm->lock);
r = -ENXIO;
if (!kvm->arch.vpit)
- goto out;
+ goto set_pit_out;
r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+ mutex_unlock(&kvm->lock);
break;
}
case KVM_GET_PIT2: {
@@ -5072,10 +5086,13 @@ set_identity_unlock:
r = -EFAULT;
if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
goto out;
+ mutex_lock(&kvm->lock);
r = -ENXIO;
if (!kvm->arch.vpit)
- goto out;
+ goto set_pit2_out;
r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+ mutex_unlock(&kvm->lock);
break;
}
case KVM_REINJECT_CONTROL: {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 211bb9358b73..c5e393f8bb3f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -202,7 +202,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size)
int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
- unsigned long pfn, text, pf;
+ unsigned long pfn, text, pf, rodata;
struct page *page;
unsigned npages;
pgd_t *pgd = efi_mm.pgd;
@@ -256,7 +256,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */
- npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT;
+ npages = (_etext - _text) >> PAGE_SHIFT;
text = __pa(_text);
pfn = text >> PAGE_SHIFT;
@@ -266,6 +266,14 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
return 1;
}
+ npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT;
+ rodata = __pa(__start_rodata);
+ pfn = rodata >> PAGE_SHIFT;
+ if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) {
+ pr_err("Failed to map kernel rodata 1:1\n");
+ return 1;
+ }
+
return 0;
}
@@ -638,7 +646,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
phys_vendor = virt_to_phys_or_null(vnd);
phys_data = virt_to_phys_or_null_size(data, data_size);
- if (!phys_name || !phys_data)
+ if (!phys_name || (data && !phys_data))
status = EFI_INVALID_PARAMETER;
else
status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -669,7 +677,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
phys_vendor = virt_to_phys_or_null(vnd);
phys_data = virt_to_phys_or_null_size(data, data_size);
- if (!phys_name || !phys_data)
+ if (!phys_name || (data && !phys_data))
status = EFI_INVALID_PARAMETER;
else
status = efi_thunk(set_variable, phys_name, phys_vendor,