summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/kvm/arm.c5
-rw-r--r--arch/arm64/kvm/irq.h16
-rw-r--r--arch/arm64/kvm/mmu.c2
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c2
-rw-r--r--arch/powerpc/kvm/irq.h22
-rw-r--r--arch/powerpc/kvm/powerpc.c18
-rw-r--r--arch/s390/kvm/irq.h19
-rw-r--r--arch/s390/kvm/kvm-s390.c5
-rw-r--r--arch/x86/events/intel/lbr.c6
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h99
-rw-r--r--arch/x86/include/asm/perf_event.h6
-rw-r--r--arch/x86/include/asm/svm.h93
-rw-r--r--arch/x86/include/uapi/asm/kvm.h5
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kvm/Kconfig11
-rw-r--r--arch/x86/kvm/Makefile1
-rw-r--r--arch/x86/kvm/cpuid.c4
-rw-r--r--arch/x86/kvm/emulate.c355
-rw-r--r--arch/x86/kvm/irq.c5
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h5
-rw-r--r--arch/x86/kvm/kvm_emulate.h48
-rw-r--r--arch/x86/kvm/lapic.c8
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu/mmu.c160
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h33
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h6
-rw-r--r--arch/x86/kvm/mmu/spte.c12
-rw-r--r--arch/x86/kvm/mmu/spte.h19
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c114
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h2
-rw-r--r--arch/x86/kvm/pmu.c90
-rw-r--r--arch/x86/kvm/pmu.h6
-rw-r--r--arch/x86/kvm/smm.c649
-rw-r--r--arch/x86/kvm/smm.h168
-rw-r--r--arch/x86/kvm/svm/nested.c3
-rw-r--r--arch/x86/kvm/svm/pmu.c4
-rw-r--r--arch/x86/kvm/svm/sev.c2
-rw-r--r--arch/x86/kvm/svm/svm.c46
-rw-r--r--arch/x86/kvm/vmx/capabilities.h24
-rw-r--r--arch/x86/kvm/vmx/nested.c1
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c11
-rw-r--r--arch/x86/kvm/vmx/vmcs12.h5
-rw-r--r--arch/x86/kvm/vmx/vmx.c46
-rw-r--r--arch/x86/kvm/x86.c403
-rw-r--r--arch/x86/kvm/x86.h1
47 files changed, 1451 insertions, 1097 deletions
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 94d33e296e10..7b107fa540fa 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2130,6 +2130,11 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
return NULL;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return irqchip_in_kernel(kvm);
+}
+
bool kvm_arch_has_irq_bypass(void)
{
return true;
diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h
deleted file mode 100644
index 0d257de42c10..000000000000
--- a/arch/arm64/kvm/irq.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * irq.h: in kernel interrupt controller related definitions
- * Copyright (c) 2016 Red Hat, Inc.
- *
- * This header is included by irqchip.c. However, on ARM, interrupt
- * controller declarations are located in include/kvm/arm_vgic.h since
- * they are mostly shared between arm and arm64.
- */
-
-#ifndef __IRQ_H
-#define __IRQ_H
-
-#include <kvm/arm_vgic.h>
-
-#endif
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 60ee3d9f01f8..f154d4a7fae0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1239,7 +1239,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
smp_rmb();
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
write_fault, &writable, NULL);
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index e9744b41a226..4939f57b6f6a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -598,7 +598,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
write_ok = true;
} else {
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, &write_ok, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 5d5e12f3bf86..9d3743ca16d5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -846,7 +846,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long pfn;
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, upgrade_p, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h
deleted file mode 100644
index e6463f866abc..000000000000
--- a/arch/powerpc/kvm/irq.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __IRQ_H
-#define __IRQ_H
-
-#include <linux/kvm_host.h>
-
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
- int ret = 0;
-
-#ifdef CONFIG_KVM_MPIC
- ret = ret || (kvm->arch.mpic != NULL);
-#endif
-#ifdef CONFIG_KVM_XICS
- ret = ret || (kvm->arch.xics != NULL);
- ret = ret || (kvm->arch.xive != NULL);
-#endif
- smp_rmb();
- return ret;
-}
-
-#endif
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b850b0efa201..04494a4fb37a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -36,7 +36,6 @@
#include <asm/setup.h>
#include "timing.h"
-#include "irq.h"
#include "../mm/mmu_decl.h"
#define CREATE_TRACE_POINTS
@@ -2165,10 +2164,25 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
return 0;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ int ret = 0;
+
+#ifdef CONFIG_KVM_MPIC
+ ret = ret || (kvm->arch.mpic != NULL);
+#endif
+#ifdef CONFIG_KVM_XICS
+ ret = ret || (kvm->arch.xics != NULL);
+ ret = ret || (kvm->arch.xive != NULL);
+#endif
+ smp_rmb();
+ return ret;
+}
+
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
bool line_status)
{
- if (!irqchip_in_kernel(kvm))
+ if (!kvm_arch_irqchip_in_kernel(kvm))
return -ENXIO;
irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
deleted file mode 100644
index 484608c71dd0..000000000000
--- a/arch/s390/kvm/irq.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * s390 irqchip routines
- *
- * Copyright IBM Corp. 2014
- *
- * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
- */
-#ifndef __KVM_IRQ_H
-#define __KVM_IRQ_H
-
-#include <linux/kvm_host.h>
-
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
- return 1;
-}
-
-#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index bc491a73815c..5c7532dbc96b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -5567,6 +5567,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return true;
+}
+
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 8259d725054d..4dbde69c423b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1603,10 +1603,8 @@ clear_arch_lbr:
* x86_perf_get_lbr - get the LBR records information
*
* @lbr: the caller's memory to store the LBR records information
- *
- * Returns: 0 indicates the LBR info has been successfully obtained
*/
-int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
int lbr_fmt = x86_pmu.intel_cap.lbr_format;
@@ -1614,8 +1612,6 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
lbr->from = x86_pmu.lbr_from;
lbr->to = x86_pmu.lbr_to;
lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
-
- return 0;
}
EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 82ba4a564e58..ea58e67e9a67 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -110,10 +110,12 @@ KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt)
KVM_X86_OP_OPTIONAL(set_hv_timer)
KVM_X86_OP_OPTIONAL(cancel_hv_timer)
KVM_X86_OP(setup_mce)
+#ifdef CONFIG_KVM_SMM
KVM_X86_OP(smi_allowed)
KVM_X86_OP(enter_smm)
KVM_X86_OP(leave_smm)
KVM_X86_OP(enable_smi_window)
+#endif
KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f05ebaa26f0f..598eb3b9ae44 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -81,7 +81,9 @@
#define KVM_REQ_NMI KVM_ARCH_REQ(9)
#define KVM_REQ_PMU KVM_ARCH_REQ(10)
#define KVM_REQ_PMI KVM_ARCH_REQ(11)
+#ifdef CONFIG_KVM_SMM
#define KVM_REQ_SMI KVM_ARCH_REQ(12)
+#endif
#define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13)
#define KVM_REQ_MCLOCK_INPROGRESS \
KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
@@ -204,6 +206,7 @@ typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
+union kvm_smram;
enum x86_intercept;
enum x86_intercept_stage;
@@ -253,16 +256,16 @@ enum x86_intercept_stage;
#define PFERR_GUEST_PAGE_BIT 33
#define PFERR_IMPLICIT_ACCESS_BIT 48
-#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
-#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
-#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
-#define PFERR_PK_MASK (1U << PFERR_PK_BIT)
-#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT)
-#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
-#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
-#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT)
+#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
+#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
+#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
+#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
+#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
@@ -488,17 +491,19 @@ enum pmc_type {
struct kvm_pmc {
enum pmc_type type;
u8 idx;
+ bool is_paused;
+ bool intr;
u64 counter;
+ u64 prev_counter;
u64 eventsel;
struct perf_event *perf_event;
struct kvm_vcpu *vcpu;
/*
+ * only for creating or reusing perf_event,
* eventsel value for general purpose counters,
* ctrl value for fixed counters.
*/
u64 current_config;
- bool is_paused;
- bool intr;
};
/* More counters may conflict with other existing Architectural MSRs */
@@ -524,7 +529,16 @@ struct kvm_pmu {
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
struct irq_work irq_work;
- DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+
+ /*
+ * Overlay the bitmap with a 64-bit atomic so that all bits can be
+ * set in a single access, e.g. to reprogram all counters when the PMU
+ * filter changes.
+ */
+ union {
+ DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+ atomic64_t __reprogram_pmi;
+ };
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
@@ -1156,7 +1170,18 @@ struct kvm_arch {
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
- struct list_head lpage_disallowed_mmu_pages;
+ /*
+ * A list of kvm_mmu_page structs that, if zapped, could possibly be
+ * replaced by an NX huge page. A shadow page is on this list if its
+ * existence disallows an NX huge page (nx_huge_page_disallowed is set)
+ * and there are no other conditions that prevent a huge page, e.g.
+ * the backing host page is huge, dirtly logging is not enabled for its
+ * memslot, etc... Note, zapping shadow pages on this list doesn't
+ * guarantee an NX huge page will be created in its stead, e.g. if the
+ * guest attempts to execute from the region then KVM obviously can't
+ * create an NX huge page (without hanging the guest).
+ */
+ struct list_head possible_nx_huge_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
/*
@@ -1272,7 +1297,7 @@ struct kvm_arch {
bool sgx_provisioning_allowed;
struct kvm_pmu_event_filter __rcu *pmu_event_filter;
- struct task_struct *nx_lpage_recovery_thread;
+ struct task_struct *nx_huge_page_recovery_thread;
#ifdef CONFIG_X86_64
/*
@@ -1284,6 +1309,9 @@ struct kvm_arch {
*/
bool tdp_mmu_enabled;
+ /* The number of TDP MMU pages across all roots. */
+ atomic64_t tdp_mmu_pages;
+
/*
* List of kvm_mmu_page structs being used as roots.
* All kvm_mmu_page structs in the list should have
@@ -1305,20 +1333,12 @@ struct kvm_arch {
struct list_head tdp_mmu_roots;
/*
- * List of kvm_mmu_page structs not being used as roots.
- * All kvm_mmu_page structs in the list should have
- * tdp_mmu_page set and a tdp_mmu_root_count of 0.
- */
- struct list_head tdp_mmu_pages;
-
- /*
* Protects accesses to the following fields when the MMU lock
* is held in read mode:
* - tdp_mmu_roots (above)
- * - tdp_mmu_pages (above)
* - the link field of kvm_mmu_page structs used by the TDP MMU
- * - lpage_disallowed_mmu_pages
- * - the lpage_disallowed_link field of kvm_mmu_page structs used
+ * - possible_nx_huge_pages;
+ * - the possible_nx_huge_page_link field of kvm_mmu_page structs used
* by the TDP MMU
* It is acceptable, but not necessary, to acquire this lock when
* the thread holds the MMU lock in write mode.
@@ -1612,10 +1632,12 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_KVM_SMM
int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
- int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
+ int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+ int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
+#endif
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@@ -1844,6 +1866,7 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);
int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
@@ -1909,8 +1932,6 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
-gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
- struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
@@ -1994,14 +2015,18 @@ enum {
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
+
+#ifdef CONFIG_KVM_SMM
#define HF_SMM_MASK (1 << 6)
#define HF_SMM_INSIDE_NMI_MASK (1 << 7)
-#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
-#define KVM_ADDRESS_SPACE_NUM 2
-
-#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
-#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+# define KVM_ADDRESS_SPACE_NUM 2
+# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+#else
+# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
+#endif
#define KVM_ARCH_WANT_MMU_NOTIFIER
@@ -2089,12 +2114,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#endif
}
-#define put_smstate(type, buf, offset, val) \
- *(type *)((buf) + (offset) - 0x7e00) = val
-
-#define GET_SMSTATE(type, buf, offset) \
- (*(type *)((buf) + (offset) - 0x7e00))
-
int kvm_cpu_dirty_log_size(void);
int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 9ac46dbe57d4..5d0f6891ae61 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -543,12 +543,12 @@ static inline void perf_check_microcode(void) { }
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
-extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
+extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
#else
struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
-static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+static inline void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
- return -1;
+ memset(lbr, 0, sizeof(*lbr));
}
#endif
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 0361626841bc..4352b46dd20c 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -293,12 +293,13 @@ struct vmcb_save_area {
struct vmcb_seg ldtr;
struct vmcb_seg idtr;
struct vmcb_seg tr;
- u8 reserved_1[42];
+ /* Reserved fields are named following their struct offset */
+ u8 reserved_0xa0[42];
u8 vmpl;
u8 cpl;
- u8 reserved_2[4];
+ u8 reserved_0xcc[4];
u64 efer;
- u8 reserved_3[112];
+ u8 reserved_0xd8[112];
u64 cr4;
u64 cr3;
u64 cr0;
@@ -306,7 +307,7 @@ struct vmcb_save_area {
u64 dr6;
u64 rflags;
u64 rip;
- u8 reserved_4[88];
+ u8 reserved_0x180[88];
u64 rsp;
u64 s_cet;
u64 ssp;
@@ -321,14 +322,14 @@ struct vmcb_save_area {
u64 sysenter_esp;
u64 sysenter_eip;
u64 cr2;
- u8 reserved_5[32];
+ u8 reserved_0x248[32];
u64 g_pat;
u64 dbgctl;
u64 br_from;
u64 br_to;
u64 last_excp_from;
u64 last_excp_to;
- u8 reserved_6[72];
+ u8 reserved_0x298[72];
u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
} __packed;
@@ -349,12 +350,12 @@ struct sev_es_save_area {
u64 vmpl2_ssp;
u64 vmpl3_ssp;
u64 u_cet;
- u8 reserved_1[2];
+ u8 reserved_0xc8[2];
u8 vmpl;
u8 cpl;
- u8 reserved_2[4];
+ u8 reserved_0xcc[4];
u64 efer;
- u8 reserved_3[104];
+ u8 reserved_0xd8[104];
u64 xss;
u64 cr4;
u64 cr3;
@@ -371,7 +372,7 @@ struct sev_es_save_area {
u64 dr1_addr_mask;
u64 dr2_addr_mask;
u64 dr3_addr_mask;
- u8 reserved_4[24];
+ u8 reserved_0x1c0[24];
u64 rsp;
u64 s_cet;
u64 ssp;
@@ -386,21 +387,21 @@ struct sev_es_save_area {
u64 sysenter_esp;
u64 sysenter_eip;
u64 cr2;
- u8 reserved_5[32];
+ u8 reserved_0x248[32];
u64 g_pat;
u64 dbgctl;
u64 br_from;
u64 br_to;
u64 last_excp_from;
u64 last_excp_to;
- u8 reserved_7[80];
+ u8 reserved_0x298[80];
u32 pkru;
- u8 reserved_8[20];
- u64 reserved_9; /* rax already available at 0x01f8 */
+ u32 tsc_aux;
+ u8 reserved_0x2f0[24];
u64 rcx;
u64 rdx;
u64 rbx;
- u64 reserved_10; /* rsp already available at 0x01d8 */
+ u64 reserved_0x320; /* rsp already available at 0x01d8 */
u64 rbp;
u64 rsi;
u64 rdi;
@@ -412,7 +413,7 @@ struct sev_es_save_area {
u64 r13;
u64 r14;
u64 r15;
- u8 reserved_11[16];
+ u8 reserved_0x380[16];
u64 guest_exit_info_1;
u64 guest_exit_info_2;
u64 guest_exit_int_info;
@@ -425,7 +426,7 @@ struct sev_es_save_area {
u64 pcpu_id;
u64 event_inj;
u64 xcr0;
- u8 reserved_12[16];
+ u8 reserved_0x3f0[16];
/* Floating point area */
u64 x87_dp;
@@ -443,23 +444,23 @@ struct sev_es_save_area {
} __packed;
struct ghcb_save_area {
- u8 reserved_1[203];
+ u8 reserved_0x0[203];
u8 cpl;
- u8 reserved_2[116];
+ u8 reserved_0xcc[116];
u64 xss;
- u8 reserved_3[24];
+ u8 reserved_0x148[24];
u64 dr7;
- u8 reserved_4[16];
+ u8 reserved_0x168[16];
u64 rip;
- u8 reserved_5[88];
+ u8 reserved_0x180[88];
u64 rsp;
- u8 reserved_6[24];
+ u8 reserved_0x1e0[24];
u64 rax;
- u8 reserved_7[264];
+ u8 reserved_0x200[264];
u64 rcx;
u64 rdx;
u64 rbx;
- u8 reserved_8[8];
+ u8 reserved_0x320[8];
u64 rbp;
u64 rsi;
u64 rdi;
@@ -471,12 +472,12 @@ struct ghcb_save_area {
u64 r13;
u64 r14;
u64 r15;
- u8 reserved_9[16];
+ u8 reserved_0x380[16];
u64 sw_exit_code;
u64 sw_exit_info_1;
u64 sw_exit_info_2;
u64 sw_scratch;
- u8 reserved_10[56];
+ u8 reserved_0x3b0[56];
u64 xcr0;
u8 valid_bitmap[16];
u64 x87_state_gpa;
@@ -490,7 +491,7 @@ struct ghcb {
u8 shared_buffer[GHCB_SHARED_BUF_SIZE];
- u8 reserved_1[10];
+ u8 reserved_0xff0[10];
u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */
u32 ghcb_usage;
} __packed;
@@ -502,6 +503,9 @@ struct ghcb {
#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024
#define EXPECTED_GHCB_SIZE PAGE_SIZE
+#define BUILD_BUG_RESERVED_OFFSET(x, y) \
+ ASSERT_STRUCT_OFFSET(struct x, reserved ## _ ## y, y)
+
static inline void __unused_size_checks(void)
{
BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE);
@@ -509,6 +513,39 @@ static inline void __unused_size_checks(void)
BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE);
+
+ /* Check offsets of reserved fields */
+
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298);
+
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xd8);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0);
+
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x0);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x148);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x168);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x180);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x1e0);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x200);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x320);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x380);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x3b0);
+
+ BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0);
}
struct vmcb {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 46de10a809ec..c6df6b16a088 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -214,6 +214,8 @@ struct kvm_msr_list {
struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_READ (1 << 0)
#define KVM_MSR_FILTER_WRITE (1 << 1)
+#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \
+ KVM_MSR_FILTER_WRITE)
__u32 flags;
__u32 nmsrs; /* number of msrs in bitmap */
__u32 base; /* MSR index the bitmap starts at */
@@ -222,8 +224,11 @@ struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_MAX_RANGES 16
struct kvm_msr_filter {
+#ifndef __KERNEL__
#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#endif
#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY)
__u32 flags;
struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
};
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d4e48b4a438b..cf886f86038a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -349,7 +349,7 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
static void kvm_guest_cpu_init(void)
{
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
- u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
+ u64 pa;
WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled));
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 67be7f217e37..fbeaa9ddef59 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -118,6 +118,17 @@ config KVM_AMD_SEV
Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
with Encrypted State (SEV-ES) on AMD processors.
+config KVM_SMM
+ bool "System Management Mode emulation"
+ default y
+ depends on KVM
+ help
+ Provides support for KVM to emulate System Management Mode (SMM)
+ in virtual machines. This can be used by the virtual machine
+ firmware to implement UEFI secure boot.
+
+ If unsure, say Y.
+
config KVM_XEN
bool "Support for Xen hypercall interface"
depends on KVM
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index f453a0f96e24..b8a494b6a5ec 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -20,6 +20,7 @@ endif
kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
kvm-$(CONFIG_KVM_XEN) += xen.o
+kvm-$(CONFIG_KVM_SMM) += smm.o
kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
vmx/evmcs.o vmx/nested.o vmx/posted_intr.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 62bc7a01cecc..6b5912578edd 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -62,7 +62,7 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
* This one is tied to SSB in the user API, and not
* visible in /proc/cpuinfo.
*/
-#define KVM_X86_FEATURE_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
+#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
#define F feature_bit
#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0)
@@ -694,7 +694,7 @@ void kvm_set_cpu_caps(void)
F(CLZERO) | F(XSAVEERPTR) |
F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) |
- __feature_bit(KVM_X86_FEATURE_PSFD)
+ __feature_bit(KVM_X86_FEATURE_AMD_PSFD)
);
/*
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4a43261d25a2..5cc3efa0e21c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -242,37 +242,6 @@ enum x86_transfer_type {
X86_TRANSFER_TASK_SWITCH,
};
-static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
- nr &= NR_EMULATOR_GPRS - 1;
-
- if (!(ctxt->regs_valid & (1 << nr))) {
- ctxt->regs_valid |= 1 << nr;
- ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
- }
- return ctxt->_regs[nr];
-}
-
-static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
- nr &= NR_EMULATOR_GPRS - 1;
-
- BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
- BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
-
- ctxt->regs_valid |= 1 << nr;
- ctxt->regs_dirty |= 1 << nr;
- return &ctxt->_regs[nr];
-}
-
-static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- reg_read(ctxt, nr);
- return reg_write(ctxt, nr);
-}
-
static void writeback_registers(struct x86_emulate_ctxt *ctxt)
{
unsigned long dirty = ctxt->regs_dirty;
@@ -2338,335 +2307,15 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
return rc;
}
-static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
-{
-#ifdef CONFIG_X86_64
- return ctxt->ops->guest_has_long_mode(ctxt);
-#else
- return false;
-#endif
-}
-
-static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
-{
- desc->g = (flags >> 23) & 1;
- desc->d = (flags >> 22) & 1;
- desc->l = (flags >> 21) & 1;
- desc->avl = (flags >> 20) & 1;
- desc->p = (flags >> 15) & 1;
- desc->dpl = (flags >> 13) & 3;
- desc->s = (flags >> 12) & 1;
- desc->type = (flags >> 8) & 15;
-}
-
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
-{
- struct desc_struct desc;
- int offset;
- u16 selector;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
- return X86EMUL_CONTINUE;
-}
-
-#ifdef CONFIG_X86_64
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
-{
- struct desc_struct desc;
- int offset;
- u16 selector;
- u32 base3;
-
- offset = 0x7e00 + n * 16;
-
- selector = GET_SMSTATE(u16, smstate, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- base3 = GET_SMSTATE(u32, smstate, offset + 12);
-
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
- return X86EMUL_CONTINUE;
-}
-#endif
-
-static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
- u64 cr0, u64 cr3, u64 cr4)
-{
- int bad;
- u64 pcid;
-
- /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
- pcid = 0;
- if (cr4 & X86_CR4_PCIDE) {
- pcid = cr3 & 0xfff;
- cr3 &= ~0xfff;
- }
-
- bad = ctxt->ops->set_cr(ctxt, 3, cr3);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- /*
- * First enable PAE, long mode needs it before CR0.PG = 1 is set.
- * Then enable protected mode. However, PCID cannot be enabled
- * if EFER.LMA=0, so set it separately.
- */
- bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- bad = ctxt->ops->set_cr(ctxt, 0, cr0);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- if (cr4 & X86_CR4_PCIDE) {
- bad = ctxt->ops->set_cr(ctxt, 4, cr4);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
- if (pcid) {
- bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
- }
-
- }
-
- return X86EMUL_CONTINUE;
-}
-
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
-{
- struct desc_struct desc;
- struct desc_ptr dt;
- u16 selector;
- u32 val, cr0, cr3, cr4;
- int i;
-
- cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
-
- for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
-
- val = GET_SMSTATE(u32, smstate, 0x7fcc);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
- return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u32, smstate, 0x7fc8);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
- return X86EMUL_UNHANDLEABLE;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
-
- selector = GET_SMSTATE(u32, smstate, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
-
- dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
- ctxt->ops->set_gdt(ctxt, &dt);
-
- dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
- ctxt->ops->set_idt(ctxt, &dt);
-
- for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
-
- cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
-
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
-
- return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
-}
-
-#ifdef CONFIG_X86_64
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
-{
- struct desc_struct desc;
- struct desc_ptr dt;
- u64 val, cr0, cr3, cr4;
- u32 base3;
- u16 selector;
- int i, r;
-
- for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
-
- ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
-
- val = GET_SMSTATE(u64, smstate, 0x7f68);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
- return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u64, smstate, 0x7f60);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
- return X86EMUL_UNHANDLEABLE;
-
- cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
- cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
- cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
- val = GET_SMSTATE(u64, smstate, 0x7ed0);
-
- if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
- return X86EMUL_UNHANDLEABLE;
-
- selector = GET_SMSTATE(u32, smstate, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
- base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
-
- dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
- ctxt->ops->set_idt(ctxt, &dt);
-
- selector = GET_SMSTATE(u32, smstate, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
- base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
-
- dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
- ctxt->ops->set_gdt(ctxt, &dt);
-
- r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
- if (r != X86EMUL_CONTINUE)
- return r;
-
- for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
-
- return X86EMUL_CONTINUE;
-}
-#endif
-
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
- unsigned long cr0, cr4, efer;
- char buf[512];
- u64 smbase;
- int ret;
-
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
- smbase = ctxt->ops->get_smbase(ctxt);
-
- ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
- if (ret != X86EMUL_CONTINUE)
- return X86EMUL_UNHANDLEABLE;
-
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
-
- ctxt->ops->exiting_smm(ctxt);
-
- /*
- * Get back to real mode, to prepare a safe state in which to load
- * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
- * supports long mode.
- */
- if (emulator_has_longmode(ctxt)) {
- struct desc_struct cs_desc;
-
- /* Zero CR4.PCIDE before CR0.PG. */
- cr4 = ctxt->ops->get_cr(ctxt, 4);
- if (cr4 & X86_CR4_PCIDE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
-
- /* A 32-bit code segment is required to clear EFER.LMA. */
- memset(&cs_desc, 0, sizeof(cs_desc));
- cs_desc.type = 0xb;
- cs_desc.s = cs_desc.g = cs_desc.p = 1;
- ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS);
- }
-
- /* For the 64-bit case, this will clear EFER.LMA. */
- cr0 = ctxt->ops->get_cr(ctxt, 0);
- if (cr0 & X86_CR0_PE)
- ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
-
- if (emulator_has_longmode(ctxt)) {
- /* Clear CR4.PAE before clearing EFER.LME. */
- cr4 = ctxt->ops->get_cr(ctxt, 4);
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
- }
-
- /*
- * Give leave_smm() a chance to make ISA-specific changes to the vCPU
- * state (e.g. enter guest mode) before loading state from the SMM
- * state-save area.
- */
- if (ctxt->ops->leave_smm(ctxt, buf))
- goto emulate_shutdown;
-
-#ifdef CONFIG_X86_64
- if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, buf);
- else
-#endif
- ret = rsm_load_state_32(ctxt, buf);
-
- if (ret != X86EMUL_CONTINUE)
- goto emulate_shutdown;
+ if (ctxt->ops->leave_smm(ctxt))
+ ctxt->ops->triple_fault(ctxt);
- /*
- * Note, the ctxt->ops callbacks are responsible for handling side
- * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID
- * runtime updates, etc... If that changes, e.g. this flow is moved
- * out of the emulator to make it look more like enter_smm(), then
- * those side effects need to be explicitly handled for both success
- * and shutdown.
- */
return emulator_recalc_and_set_mode(ctxt);
-
-emulate_shutdown:
- ctxt->ops->triple_fault(ctxt);
- return X86EMUL_CONTINUE;
}
static void
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index f371f1292ca3..d8d50558f165 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -165,3 +165,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
}
+
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return irqchip_in_kernel(kvm);
+}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 3febc342360c..c09174f73a34 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -200,9 +200,4 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu)
return vcpu->arch.hflags & HF_GUEST_MASK;
}
-static inline bool is_smm(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.hflags & HF_SMM_MASK;
-}
-
#endif
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 89246446d6aa..2d9662be8333 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -117,16 +117,6 @@ struct x86_emulate_ops {
struct x86_exception *fault, bool system);
/*
- * read_phys: Read bytes of standard (non-emulated/special) memory.
- * Used for descriptor reading.
- * @addr: [IN ] Physical address from which to read.
- * @val: [OUT] Value read from memory.
- * @bytes: [IN ] Number of bytes to read from memory.
- */
- int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr,
- void *val, unsigned int bytes);
-
- /*
* write_std: Write bytes of standard (non-emulated/special) memory.
* Used for descriptor writing.
* @addr: [IN ] Linear address to which to write.
@@ -209,11 +199,8 @@ struct x86_emulate_ops {
int (*cpl)(struct x86_emulate_ctxt *ctxt);
void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
- u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
- void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
- int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
@@ -234,8 +221,7 @@ struct x86_emulate_ops {
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
- void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
- int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate);
+ int (*leave_smm)(struct x86_emulate_ctxt *ctxt);
void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
};
@@ -292,7 +278,6 @@ enum x86emul_mode {
/* These match some of the HF_* flags defined in kvm_host.h */
#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
#define X86EMUL_SMM_MASK (1 << 6)
-#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7)
/*
* fastop functions are declared as taking a never-defined fastop parameter,
@@ -526,4 +511,35 @@ void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt);
+static inline ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+ nr &= NR_EMULATOR_GPRS - 1;
+
+ if (!(ctxt->regs_valid & (1 << nr))) {
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
+ }
+ return ctxt->_regs[nr];
+}
+
+static inline ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+ nr &= NR_EMULATOR_GPRS - 1;
+
+ BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+ BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->regs_dirty |= 1 << nr;
+ return &ctxt->_regs[nr];
+}
+
+static inline ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ reg_read(ctxt, nr);
+ return reg_write(ctxt, nr);
+}
+
#endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d7639d126e6c..1bb63746e991 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -42,6 +42,7 @@
#include "x86.h"
#include "cpuid.h"
#include "hyperv.h"
+#include "smm.h"
#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -1170,9 +1171,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
break;
case APIC_DM_SMI:
- result = 1;
- kvm_make_request(KVM_REQ_SMI, vcpu);
- kvm_vcpu_kick(vcpu);
+ if (!kvm_inject_smi(vcpu)) {
+ kvm_vcpu_kick(vcpu);
+ result = 1;
+ }
break;
case APIC_DM_NMI:
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index a5ac4a5a5179..28e3769066e2 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -7,7 +7,7 @@
#include <linux/kvm_host.h>
#include "hyperv.h"
-#include "kvm_cache_regs.h"
+#include "smm.h"
#define KVM_APIC_INIT 0
#define KVM_APIC_SIPI 1
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 6f81539061d6..cfff74685a25 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -22,6 +22,7 @@
#include "tdp_mmu.h"
#include "x86.h"
#include "kvm_cache_regs.h"
+#include "smm.h"
#include "kvm_emulate.h"
#include "cpuid.h"
#include "spte.h"
@@ -802,15 +803,31 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
}
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
- if (sp->lpage_disallowed)
+ /*
+ * If it's possible to replace the shadow page with an NX huge page,
+ * i.e. if the shadow page is the only thing currently preventing KVM
+ * from using a huge page, add the shadow page to the list of "to be
+ * zapped for NX recovery" pages. Note, the shadow page can already be
+ * on the list if KVM is reusing an existing shadow page, i.e. if KVM
+ * links a shadow page at multiple points.
+ */
+ if (!list_empty(&sp->possible_nx_huge_page_link))
return;
++kvm->stat.nx_lpage_splits;
- list_add_tail(&sp->lpage_disallowed_link,
- &kvm->arch.lpage_disallowed_mmu_pages);
- sp->lpage_disallowed = true;
+ list_add_tail(&sp->possible_nx_huge_page_link,
+ &kvm->arch.possible_nx_huge_pages);
+}
+
+static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+ bool nx_huge_page_possible)
+{
+ sp->nx_huge_page_disallowed = true;
+
+ if (nx_huge_page_possible)
+ track_possible_nx_huge_page(kvm, sp);
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -830,11 +847,20 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
+ if (list_empty(&sp->possible_nx_huge_page_link))
+ return;
+
--kvm->stat.nx_lpage_splits;
- sp->lpage_disallowed = false;
- list_del(&sp->lpage_disallowed_link);
+ list_del_init(&sp->possible_nx_huge_page_link);
+}
+
+static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ sp->nx_huge_page_disallowed = false;
+
+ untrack_possible_nx_huge_page(kvm, sp);
}
static struct kvm_memory_slot *
@@ -1645,7 +1671,7 @@ static int is_empty_shadow_page(u64 *spt)
u64 *pos;
u64 *end;
- for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
+ for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++)
if (is_shadow_present_pte(*pos)) {
printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
@@ -1793,7 +1819,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
continue;
}
- child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(ent);
if (child->unsync_children) {
if (mmu_pages_add(pvec, child, i))
@@ -1894,7 +1920,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
if (sp->role.invalid)
return true;
- /* TDP MMU pages due not use the MMU generation. */
+ /* TDP MMU pages do not use the MMU generation. */
return !sp->tdp_mmu_page &&
unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
}
@@ -2129,6 +2155,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+ INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
/*
* active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
* depends on valid pages being added to the head of the list. See
@@ -2350,7 +2378,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
* so we should update the spte at this point to get
* a new sp with the correct access.
*/
- child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(*sptep);
if (child->role.access == direct_access)
return;
@@ -2371,7 +2399,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
if (is_last_spte(pte, sp->role.level)) {
drop_spte(kvm, spte);
} else {
- child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(pte);
drop_parent_pte(child, spte);
/*
@@ -2486,8 +2514,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
zapped_root = !is_obsolete_sp(kvm, sp);
}
- if (sp->lpage_disallowed)
- unaccount_huge_nx_page(kvm, sp);
+ if (sp->nx_huge_page_disallowed)
+ unaccount_nx_huge_page(kvm, sp);
sp->role.invalid = 1;
@@ -2810,7 +2838,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
struct kvm_mmu_page *child;
u64 pte = *sptep;
- child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(pte);
drop_parent_pte(child, sptep);
flush = true;
} else if (pfn != spte_to_pfn(*sptep)) {
@@ -3084,7 +3112,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
if (cur_level > PG_LEVEL_4K &&
cur_level == fault->goal_level &&
is_shadow_present_pte(spte) &&
- !is_large_pte(spte)) {
+ !is_large_pte(spte) &&
+ spte_to_child_sp(spte)->nx_huge_page_disallowed) {
/*
* A small SPTE exists for this pfn, but FNAME(fetch)
* and __direct_map would like to create a large PTE
@@ -3126,9 +3155,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
continue;
link_shadow_page(vcpu, it.sptep, sp);
- if (fault->is_tdp && fault->huge_page_disallowed &&
- fault->req_level >= it.level)
- account_huge_nx_page(vcpu->kvm, sp);
+ if (fault->huge_page_disallowed)
+ account_nx_huge_page(vcpu->kvm, sp,
+ fault->req_level >= it.level);
}
if (WARN_ON_ONCE(it.level != fault->goal_level))
@@ -3148,8 +3177,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
}
-static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
{
+ if (is_sigpending_pfn(pfn)) {
+ kvm_handle_signal_exit(vcpu);
+ return -EINTR;
+ }
+
/*
* Do not cache the mmio info caused by writing the readonly gfn
* into the spte otherwise read access on readonly gfn also can
@@ -3171,7 +3205,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau
{
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(fault->pfn)))
- return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
+ return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn);
if (unlikely(!fault->slot)) {
gva_t gva = fault->is_tdp ? 0 : fault->addr;
@@ -3422,7 +3456,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
if (!VALID_PAGE(*root_hpa))
return;
- sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK);
+ /*
+ * The "root" may be a special root, e.g. a PAE entry, treat it as a
+ * SPTE to ensure any non-PA bits are dropped.
+ */
+ sp = spte_to_child_sp(*root_hpa);
if (WARN_ON(!sp))
return;
@@ -3907,8 +3945,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
hpa_t root = vcpu->arch.mmu->pae_root[i];
if (IS_VALID_PAE_ROOT(root)) {
- root &= SPTE_BASE_ADDR_MASK;
- sp = to_shadow_page(root);
+ sp = spte_to_child_sp(root);
mmu_sync_children(vcpu, sp, true);
}
}
@@ -4169,7 +4206,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
async = false;
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
fault->write, &fault->map_writable,
&fault->hva);
if (!async)
@@ -4186,7 +4223,12 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
}
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL,
+ /*
+ * Allow gup to bail on pending non-fatal signals when it's also allowed
+ * to wait for IO. Note, gup always bails if it is unable to quickly
+ * get a page and a fatal signal, i.e. SIGKILL, is pending.
+ */
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
fault->write, &fault->map_writable,
&fault->hva);
return RET_PF_CONTINUE;
@@ -5971,7 +6013,7 @@ int kvm_mmu_init_vm(struct kvm *kvm)
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
- INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
r = kvm_mmu_init_tdp_mmu(kvm);
@@ -6656,7 +6698,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
kvm_mmu_zap_all_fast(kvm);
mutex_unlock(&kvm->slots_lock);
- wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
}
mutex_unlock(&kvm_lock);
}
@@ -6788,7 +6830,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
- wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
mutex_unlock(&kvm_lock);
}
@@ -6796,9 +6838,10 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
return err;
}
-static void kvm_recover_nx_lpages(struct kvm *kvm)
+static void kvm_recover_nx_huge_pages(struct kvm *kvm)
{
unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits;
+ struct kvm_memory_slot *slot;
int rcu_idx;
struct kvm_mmu_page *sp;
unsigned int ratio;
@@ -6819,24 +6862,39 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0;
for ( ; to_zap; --to_zap) {
- if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+ if (list_empty(&kvm->arch.possible_nx_huge_pages))
break;
/*
* We use a separate list instead of just using active_mmu_pages
- * because the number of lpage_disallowed pages is expected to
- * be relatively small compared to the total.
+ * because the number of shadow pages that be replaced with an
+ * NX huge page is expected to be relatively small compared to
+ * the total number of shadow pages. And because the TDP MMU
+ * doesn't use active_mmu_pages.
*/
- sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+ sp = list_first_entry(&kvm->arch.possible_nx_huge_pages,
struct kvm_mmu_page,
- lpage_disallowed_link);
- WARN_ON_ONCE(!sp->lpage_disallowed);
- if (is_tdp_mmu_page(sp)) {
+ possible_nx_huge_page_link);
+ WARN_ON_ONCE(!sp->nx_huge_page_disallowed);
+ WARN_ON_ONCE(!sp->role.direct);
+
+ slot = gfn_to_memslot(kvm, sp->gfn);
+ WARN_ON_ONCE(!slot);
+
+ /*
+ * Unaccount and do not attempt to recover any NX Huge Pages
+ * that are being dirty tracked, as they would just be faulted
+ * back in as 4KiB pages. The NX Huge Pages in this slot will be
+ * recovered, along with all the other huge pages in the slot,
+ * when dirty logging is disabled.
+ */
+ if (slot && kvm_slot_dirty_track_enabled(slot))
+ unaccount_nx_huge_page(kvm, sp);
+ else if (is_tdp_mmu_page(sp))
flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
- } else {
+ else
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
- WARN_ON_ONCE(sp->lpage_disallowed);
- }
+ WARN_ON_ONCE(sp->nx_huge_page_disallowed);
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
@@ -6856,7 +6914,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
srcu_read_unlock(&kvm->srcu, rcu_idx);
}
-static long get_nx_lpage_recovery_timeout(u64 start_time)
+static long get_nx_huge_page_recovery_timeout(u64 start_time)
{
bool enabled;
uint period;
@@ -6867,19 +6925,19 @@ static long get_nx_lpage_recovery_timeout(u64 start_time)
: MAX_SCHEDULE_TIMEOUT;
}
-static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data)
{
u64 start_time;
long remaining_time;
while (true) {
start_time = get_jiffies_64();
- remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ remaining_time = get_nx_huge_page_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop() && remaining_time > 0) {
schedule_timeout(remaining_time);
- remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ remaining_time = get_nx_huge_page_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
}
@@ -6888,7 +6946,7 @@ static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
if (kthread_should_stop())
return 0;
- kvm_recover_nx_lpages(kvm);
+ kvm_recover_nx_huge_pages(kvm);
}
}
@@ -6896,17 +6954,17 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
{
int err;
- err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+ err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0,
"kvm-nx-lpage-recovery",
- &kvm->arch.nx_lpage_recovery_thread);
+ &kvm->arch.nx_huge_page_recovery_thread);
if (!err)
- kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+ kthread_unpark(kvm->arch.nx_huge_page_recovery_thread);
return err;
}
void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
{
- if (kvm->arch.nx_lpage_recovery_thread)
- kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+ if (kvm->arch.nx_huge_page_recovery_thread)
+ kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 582def531d4d..dbaf6755c5a7 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -57,7 +57,13 @@ struct kvm_mmu_page {
bool tdp_mmu_page;
bool unsync;
u8 mmu_valid_gen;
- bool lpage_disallowed; /* Can't be replaced by an equiv large page */
+
+ /*
+ * The shadow page can't be replaced by an equivalent huge page
+ * because it is being used to map an executable page in the guest
+ * and the NX huge page mitigation is enabled.
+ */
+ bool nx_huge_page_disallowed;
/*
* The following two entries are used to key the shadow page in the
@@ -100,7 +106,14 @@ struct kvm_mmu_page {
};
};
- struct list_head lpage_disallowed_link;
+ /*
+ * Tracks shadow pages that, if zapped, would allow KVM to create an NX
+ * huge page. A shadow page will have nx_huge_page_disallowed set but
+ * not be on the list if a huge page is disallowed for other reasons,
+ * e.g. because KVM is shadowing a PTE at the same gfn, the memslot
+ * isn't properly aligned, etc...
+ */
+ struct list_head possible_nx_huge_page_link;
#ifdef CONFIG_X86_32
/*
* Used out of the mmu-lock to avoid reading spte values while an
@@ -120,18 +133,6 @@ struct kvm_mmu_page {
extern struct kmem_cache *mmu_page_header_cache;
-static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
-{
- struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
-
- return (struct kvm_mmu_page *)page_private(page);
-}
-
-static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
-{
- return to_shadow_page(__pa(sptep));
-}
-
static inline int kvm_mmu_role_as_id(union kvm_mmu_page_role role)
{
return role.smm ? 1 : 0;
@@ -315,7 +316,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5ab5f94dcb6f..0f6455072055 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -713,9 +713,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
continue;
link_shadow_page(vcpu, it.sptep, sp);
- if (fault->huge_page_disallowed &&
- fault->req_level >= it.level)
- account_huge_nx_page(vcpu->kvm, sp);
+ if (fault->huge_page_disallowed)
+ account_nx_huge_page(vcpu->kvm, sp,
+ fault->req_level >= it.level);
}
if (WARN_ON_ONCE(it.level != fault->goal_level))
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 2e08b2a45361..c0fd7e049b4e 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -161,6 +161,18 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (!prefetch)
spte |= spte_shadow_accessed_mask(spte);
+ /*
+ * For simplicity, enforce the NX huge page mitigation even if not
+ * strictly necessary. KVM could ignore the mitigation if paging is
+ * disabled in the guest, as the guest doesn't have an page tables to
+ * abuse. But to safely ignore the mitigation, KVM would have to
+ * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG
+ * is toggled on, and that's a net negative for performance when TDP is
+ * enabled. When TDP is disabled, KVM will always switch to a new MMU
+ * when CR0.PG is toggled, but leveraging that to ignore the mitigation
+ * would tie make_spte() further to vCPU/MMU state, and add complexity
+ * just to optimize a mode that is anything but performance critical.
+ */
if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
is_nx_huge_page_enabled(vcpu->kvm)) {
pte_access &= ~ACC_EXEC_MASK;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7670c13ce251..1f03701b943a 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -188,7 +188,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
* should not modify the SPTE.
*
* Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on
- * bot AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
+ * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
* vulnerability. Use only low bits to avoid 64-bit immediates.
*
* Only used by the TDP MMU.
@@ -219,6 +219,23 @@ static inline int spte_index(u64 *sptep)
*/
extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
+{
+ struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT);
+
+ return (struct kvm_mmu_page *)page_private(page);
+}
+
+static inline struct kvm_mmu_page *spte_to_child_sp(u64 spte)
+{
+ return to_shadow_page(spte & SPTE_BASE_ADDR_MASK);
+}
+
+static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
+{
+ return to_shadow_page(__pa(sptep));
+}
+
static inline bool is_mmio_spte(u64 spte)
{
return (spte & shadow_mmio_mask) == shadow_mmio_value &&
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 672f0432d777..771210ce5181 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -29,7 +29,6 @@ int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
kvm->arch.tdp_mmu_enabled = true;
INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
- INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
kvm->arch.tdp_mmu_zap_wq = wq;
return 1;
}
@@ -54,7 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
/* Also waits for any queued work items. */
destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
- WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
+ WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
@@ -284,6 +283,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep,
gfn_t gfn, union kvm_mmu_page_role role)
{
+ INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
sp->role = role;
@@ -375,11 +376,13 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, +1);
+ atomic64_inc(&kvm->arch.tdp_mmu_pages);
}
static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, -1);
+ atomic64_dec(&kvm->arch.tdp_mmu_pages);
}
/**
@@ -395,14 +398,17 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
bool shared)
{
tdp_unaccount_mmu_page(kvm, sp);
+
+ if (!sp->nx_huge_page_disallowed)
+ return;
+
if (shared)
spin_lock(&kvm->arch.tdp_mmu_pages_lock);
else
lockdep_assert_held_write(&kvm->mmu_lock);
- list_del(&sp->link);
- if (sp->lpage_disallowed)
- unaccount_huge_nx_page(kvm, sp);
+ sp->nx_huge_page_disallowed = false;
+ untrack_possible_nx_huge_page(kvm, sp);
if (shared)
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
@@ -1116,16 +1122,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
* @kvm: kvm instance
* @iter: a tdp_iter instance currently on the SPTE that should be set
* @sp: The new TDP page table to install.
- * @account_nx: True if this page table is being installed to split a
- * non-executable huge page.
* @shared: This operation is running under the MMU lock in read mode.
*
* Returns: 0 if the new page table was installed. Non-0 if the page table
* could not be installed (e.g. the atomic compare-exchange failed).
*/
static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
- struct kvm_mmu_page *sp, bool account_nx,
- bool shared)
+ struct kvm_mmu_page *sp, bool shared)
{
u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled());
int ret = 0;
@@ -1138,16 +1141,14 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
tdp_mmu_set_spte(kvm, iter, spte);
}
- spin_lock(&kvm->arch.tdp_mmu_pages_lock);
- list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
- if (account_nx)
- account_huge_nx_page(kvm, sp);
- spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
tdp_account_mmu_page(kvm, sp);
return 0;
}
+static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_mmu_page *sp, bool shared);
+
/*
* Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing
* page tables and SPTEs to translate the faulting guest physical address.
@@ -1155,9 +1156,10 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_mmu *mmu = vcpu->arch.mmu;
+ struct kvm *kvm = vcpu->kvm;
struct tdp_iter iter;
struct kvm_mmu_page *sp;
- int ret;
+ int ret = RET_PF_RETRY;
kvm_mmu_hugepage_adjust(vcpu, fault);
@@ -1166,6 +1168,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
rcu_read_lock();
tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) {
+ int r;
+
if (fault->nx_huge_page_workaround_enabled)
disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
@@ -1173,57 +1177,52 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
break;
/*
- * If there is an SPTE mapping a large page at a higher level
- * than the target, that SPTE must be cleared and replaced
- * with a non-leaf SPTE.
+ * If SPTE has been frozen by another thread, just give up and
+ * retry, avoiding unnecessary page table allocation and free.
*/
- if (is_shadow_present_pte(iter.old_spte) &&
- is_large_pte(iter.old_spte)) {
- if (tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter))
- break;
+ if (is_removed_spte(iter.old_spte))
+ goto retry;
- /*
- * The iter must explicitly re-read the spte here
- * because the new value informs the !present
- * path below.
- */
- iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
- }
+ /* Step down into the lower level page table if it exists. */
+ if (is_shadow_present_pte(iter.old_spte) &&
+ !is_large_pte(iter.old_spte))
+ continue;
- if (!is_shadow_present_pte(iter.old_spte)) {
- bool account_nx = fault->huge_page_disallowed &&
- fault->req_level >= iter.level;
+ /*
+ * The SPTE is either non-present or points to a huge page that
+ * needs to be split.
+ */
+ sp = tdp_mmu_alloc_sp(vcpu);
+ tdp_mmu_init_child_sp(sp, &iter);
- /*
- * If SPTE has been frozen by another thread, just
- * give up and retry, avoiding unnecessary page table
- * allocation and free.
- */
- if (is_removed_spte(iter.old_spte))
- break;
+ sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
- sp = tdp_mmu_alloc_sp(vcpu);
- tdp_mmu_init_child_sp(sp, &iter);
+ if (is_shadow_present_pte(iter.old_spte))
+ r = tdp_mmu_split_huge_page(kvm, &iter, sp, true);
+ else
+ r = tdp_mmu_link_sp(kvm, &iter, sp, true);
- if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) {
- tdp_mmu_free_sp(sp);
- break;
- }
+ /*
+ * Also force the guest to retry the access if the upper level SPTEs
+ * aren't in place.
+ */
+ if (r) {
+ tdp_mmu_free_sp(sp);
+ goto retry;
}
- }
- /*
- * Force the guest to retry the access if the upper level SPTEs aren't
- * in place, or if the target leaf SPTE is frozen by another CPU.
- */
- if (iter.level != fault->goal_level || is_removed_spte(iter.old_spte)) {
- rcu_read_unlock();
- return RET_PF_RETRY;
+ if (fault->huge_page_disallowed &&
+ fault->req_level >= iter.level) {
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ track_possible_nx_huge_page(kvm, sp);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ }
}
ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
- rcu_read_unlock();
+retry:
+ rcu_read_unlock();
return ret;
}
@@ -1472,6 +1471,7 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
return sp;
}
+/* Note, the caller is responsible for initializing @sp. */
static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
struct kvm_mmu_page *sp, bool shared)
{
@@ -1479,8 +1479,6 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
const int level = iter->level;
int ret, i;
- tdp_mmu_init_child_sp(sp, iter);
-
/*
* No need for atomics when writing to sp->spt since the page table has
* not been linked in yet and thus is not reachable from any other CPU.
@@ -1496,7 +1494,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
* correctness standpoint since the translation will be the same either
* way.
*/
- ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared);
+ ret = tdp_mmu_link_sp(kvm, iter, sp, shared);
if (ret)
goto out;
@@ -1556,6 +1554,8 @@ retry:
continue;
}
+ tdp_mmu_init_child_sp(sp, &iter);
+
if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared))
goto retry;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index c163f7cc23ca..d3714200b932 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -5,6 +5,8 @@
#include <linux/kvm_host.h>
+#include "spte.h"
+
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
__must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index de1fd7369736..684393c22105 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -101,10 +101,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
bool skip_pmi = false;
- /* Ignore counters that have been reprogrammed already. */
- if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi))
- return;
-
if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
if (!in_pmi) {
/*
@@ -122,7 +118,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
} else {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
}
- kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
if (!pmc->intr || skip_pmi)
return;
@@ -147,12 +142,22 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+ /*
+ * Ignore overflow events for counters that are scheduled to be
+ * reprogrammed, e.g. if a PMI for the previous event races with KVM's
+ * handling of a related guest WRMSR.
+ */
+ if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi))
+ return;
+
__kvm_perf_overflow(pmc, true);
+
+ kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
-static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
- u64 config, bool exclude_user,
- bool exclude_kernel, bool intr)
+static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
+ bool exclude_user, bool exclude_kernel,
+ bool intr)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
struct perf_event *event;
@@ -204,14 +209,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
if (IS_ERR(event)) {
pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
PTR_ERR(event), pmc->idx);
- return;
+ return PTR_ERR(event);
}
pmc->perf_event = event;
pmc_to_pmu(pmc)->event_count++;
- clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
pmc->is_paused = false;
pmc->intr = intr || pebs;
+ return 0;
}
static void pmc_pause_counter(struct kvm_pmc *pmc)
@@ -245,7 +250,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
perf_event_enable(pmc->perf_event);
pmc->is_paused = false;
- clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
return true;
}
@@ -293,7 +297,7 @@ out:
return allow_event;
}
-void reprogram_counter(struct kvm_pmc *pmc)
+static void reprogram_counter(struct kvm_pmc *pmc)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
u64 eventsel = pmc->eventsel;
@@ -303,10 +307,13 @@ void reprogram_counter(struct kvm_pmc *pmc)
pmc_pause_counter(pmc);
if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc))
- return;
+ goto reprogram_complete;
if (!check_pmu_event_filter(pmc))
- return;
+ goto reprogram_complete;
+
+ if (pmc->counter < pmc->prev_counter)
+ __kvm_perf_overflow(pmc, false);
if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
printk_once("kvm pmu: pin control bit is ignored\n");
@@ -324,18 +331,29 @@ void reprogram_counter(struct kvm_pmc *pmc)
}
if (pmc->current_config == new_config && pmc_resume_counter(pmc))
- return;
+ goto reprogram_complete;
pmc_release_perf_event(pmc);
pmc->current_config = new_config;
- pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
- (eventsel & pmu->raw_event_mask),
- !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
- !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT);
+
+ /*
+ * If reprogramming fails, e.g. due to contention, leave the counter's
+ * regprogram bit set, i.e. opportunistically try again on the next PMU
+ * refresh. Don't make a new request as doing so can stall the guest
+ * if reprogramming repeatedly fails.
+ */
+ if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
+ (eventsel & pmu->raw_event_mask),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+ eventsel & ARCH_PERFMON_EVENTSEL_INT))
+ return;
+
+reprogram_complete:
+ clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+ pmc->prev_counter = 0;
}
-EXPORT_SYMBOL_GPL(reprogram_counter);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
@@ -345,10 +363,11 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit);
- if (unlikely(!pmc || !pmc->perf_event)) {
+ if (unlikely(!pmc)) {
clear_bit(bit, pmu->reprogram_pmi);
continue;
}
+
reprogram_counter(pmc);
}
@@ -522,14 +541,9 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
{
- u64 prev_count;
-
- prev_count = pmc->counter;
+ pmc->prev_counter = pmc->counter;
pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc);
-
- reprogram_counter(pmc);
- if (pmc->counter < prev_count)
- __kvm_perf_overflow(pmc, false);
+ kvm_pmu_request_counter_reprogam(pmc);
}
static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
@@ -542,12 +556,15 @@ static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
static inline bool cpl_is_matched(struct kvm_pmc *pmc)
{
bool select_os, select_user;
- u64 config = pmc->current_config;
+ u64 config;
if (pmc_is_gp(pmc)) {
+ config = pmc->eventsel;
select_os = config & ARCH_PERFMON_EVENTSEL_OS;
select_user = config & ARCH_PERFMON_EVENTSEL_USR;
} else {
+ config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl,
+ pmc->idx - INTEL_PMC_IDX_FIXED);
select_os = config & 0x1;
select_user = config & 0x2;
}
@@ -577,6 +594,8 @@ EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);
int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
{
struct kvm_pmu_event_filter tmp, *filter;
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
size_t size;
int r;
@@ -613,9 +632,18 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
mutex_lock(&kvm->lock);
filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
mutex_is_locked(&kvm->lock));
+ synchronize_srcu_expedited(&kvm->srcu);
+
+ BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) >
+ sizeof(((struct kvm_pmu *)0)->__reprogram_pmi));
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ atomic64_set(&vcpu_to_pmu(vcpu)->__reprogram_pmi, -1ull);
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_PMU);
+
mutex_unlock(&kvm->lock);
- synchronize_srcu_expedited(&kvm->srcu);
r = 0;
cleanup:
kfree(filter);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 5cc5721f260b..85ff3c0588ba 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -183,7 +183,11 @@ static inline void kvm_init_pmu_capability(void)
KVM_PMC_MAX_FIXED);
}
-void reprogram_counter(struct kvm_pmc *pmc);
+static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc)
+{
+ set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+ kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+}
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
new file mode 100644
index 000000000000..a9c1c2af8d94
--- /dev/null
+++ b/arch/x86/kvm/smm.c
@@ -0,0 +1,649 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/kvm_host.h>
+#include "x86.h"
+#include "kvm_cache_regs.h"
+#include "kvm_emulate.h"
+#include "smm.h"
+#include "cpuid.h"
+#include "trace.h"
+
+#define CHECK_SMRAM32_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00)
+
+#define CHECK_SMRAM64_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00)
+
+static void check_smram_offsets(void)
+{
+ /* 32 bit SMRAM image */
+ CHECK_SMRAM32_OFFSET(reserved1, 0xFE00);
+ CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
+ CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
+ CHECK_SMRAM32_OFFSET(io_inst_restart, 0xFF00);
+ CHECK_SMRAM32_OFFSET(auto_hlt_restart, 0xFF02);
+ CHECK_SMRAM32_OFFSET(io_restart_rdi, 0xFF04);
+ CHECK_SMRAM32_OFFSET(io_restart_rcx, 0xFF08);
+ CHECK_SMRAM32_OFFSET(io_restart_rsi, 0xFF0C);
+ CHECK_SMRAM32_OFFSET(io_restart_rip, 0xFF10);
+ CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
+ CHECK_SMRAM32_OFFSET(reserved2, 0xFF18);
+ CHECK_SMRAM32_OFFSET(int_shadow, 0xFF1A);
+ CHECK_SMRAM32_OFFSET(reserved3, 0xFF1B);
+ CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
+ CHECK_SMRAM32_OFFSET(fs, 0xFF38);
+ CHECK_SMRAM32_OFFSET(gs, 0xFF44);
+ CHECK_SMRAM32_OFFSET(idtr, 0xFF50);
+ CHECK_SMRAM32_OFFSET(tr, 0xFF5C);
+ CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C);
+ CHECK_SMRAM32_OFFSET(ldtr, 0xFF78);
+ CHECK_SMRAM32_OFFSET(es, 0xFF84);
+ CHECK_SMRAM32_OFFSET(cs, 0xFF90);
+ CHECK_SMRAM32_OFFSET(ss, 0xFF9C);
+ CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8);
+ CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC);
+ CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0);
+ CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4);
+ CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8);
+ CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC);
+ CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0);
+ CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4);
+ CHECK_SMRAM32_OFFSET(dr7, 0xFFC8);
+ CHECK_SMRAM32_OFFSET(dr6, 0xFFCC);
+ CHECK_SMRAM32_OFFSET(gprs, 0xFFD0);
+ CHECK_SMRAM32_OFFSET(eip, 0xFFF0);
+ CHECK_SMRAM32_OFFSET(eflags, 0xFFF4);
+ CHECK_SMRAM32_OFFSET(cr3, 0xFFF8);
+ CHECK_SMRAM32_OFFSET(cr0, 0xFFFC);
+
+ /* 64 bit SMRAM image */
+ CHECK_SMRAM64_OFFSET(es, 0xFE00);
+ CHECK_SMRAM64_OFFSET(cs, 0xFE10);
+ CHECK_SMRAM64_OFFSET(ss, 0xFE20);
+ CHECK_SMRAM64_OFFSET(ds, 0xFE30);
+ CHECK_SMRAM64_OFFSET(fs, 0xFE40);
+ CHECK_SMRAM64_OFFSET(gs, 0xFE50);
+ CHECK_SMRAM64_OFFSET(gdtr, 0xFE60);
+ CHECK_SMRAM64_OFFSET(ldtr, 0xFE70);
+ CHECK_SMRAM64_OFFSET(idtr, 0xFE80);
+ CHECK_SMRAM64_OFFSET(tr, 0xFE90);
+ CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0);
+ CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8);
+ CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
+ CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
+ CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
+ CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
+ CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
+ CHECK_SMRAM64_OFFSET(amd_nmi_mask, 0xFECA);
+ CHECK_SMRAM64_OFFSET(int_shadow, 0xFECB);
+ CHECK_SMRAM64_OFFSET(reserved2, 0xFECC);
+ CHECK_SMRAM64_OFFSET(efer, 0xFED0);
+ CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8);
+ CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0);
+ CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8);
+ CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0);
+ CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC);
+ CHECK_SMRAM64_OFFSET(smbase, 0xFF00);
+ CHECK_SMRAM64_OFFSET(reserved4, 0xFF04);
+ CHECK_SMRAM64_OFFSET(ssp, 0xFF18);
+ CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20);
+ CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28);
+ CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30);
+ CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38);
+ CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40);
+ CHECK_SMRAM64_OFFSET(cr4, 0xFF48);
+ CHECK_SMRAM64_OFFSET(cr3, 0xFF50);
+ CHECK_SMRAM64_OFFSET(cr0, 0xFF58);
+ CHECK_SMRAM64_OFFSET(dr7, 0xFF60);
+ CHECK_SMRAM64_OFFSET(dr6, 0xFF68);
+ CHECK_SMRAM64_OFFSET(rflags, 0xFF70);
+ CHECK_SMRAM64_OFFSET(rip, 0xFF78);
+ CHECK_SMRAM64_OFFSET(gprs, 0xFF80);
+
+ BUILD_BUG_ON(sizeof(union kvm_smram) != 512);
+}
+
+#undef CHECK_SMRAM64_OFFSET
+#undef CHECK_SMRAM32_OFFSET
+
+
+void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
+{
+ BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
+
+ trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm);
+
+ if (entering_smm) {
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ } else {
+ vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK);
+
+ /* Process a latched INIT or SMI, if any. */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+ /*
+ * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+ * on SMM exit we still need to reload them from
+ * guest memory
+ */
+ vcpu->arch.pdptrs_from_userspace = false;
+ }
+
+ kvm_mmu_reset_context(vcpu);
+}
+
+void process_smi(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.smi_pending = true;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
+static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
+{
+ u32 flags = 0;
+ flags |= seg->g << 23;
+ flags |= seg->db << 22;
+ flags |= seg->l << 21;
+ flags |= seg->avl << 20;
+ flags |= seg->present << 15;
+ flags |= seg->dpl << 13;
+ flags |= seg->s << 12;
+ flags |= seg->type << 8;
+ return flags;
+}
+
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_32 *state,
+ u32 *selector, int n)
+{
+ struct kvm_segment seg;
+
+ kvm_get_segment(vcpu, &seg, n);
+ *selector = seg.selector;
+ state->base = seg.base;
+ state->limit = seg.limit;
+ state->flags = enter_smm_get_segment_flags(&seg);
+}
+
+#ifdef CONFIG_X86_64
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_64 *state,
+ int n)
+{
+ struct kvm_segment seg;
+
+ kvm_get_segment(vcpu, &seg, n);
+ state->selector = seg.selector;
+ state->attributes = enter_smm_get_segment_flags(&seg) >> 8;
+ state->limit = seg.limit;
+ state->base = seg.base;
+}
+#endif
+
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu,
+ struct kvm_smram_state_32 *smram)
+{
+ struct desc_ptr dt;
+ unsigned long val;
+ int i;
+
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->eflags = kvm_get_rflags(vcpu);
+ smram->eip = kvm_rip_read(vcpu);
+
+ for (i = 0; i < 8; i++)
+ smram->gprs[i] = kvm_register_read_raw(vcpu, i);
+
+ kvm_get_dr(vcpu, 6, &val);
+ smram->dr6 = (u32)val;
+ kvm_get_dr(vcpu, 7, &val);
+ smram->dr7 = (u32)val;
+
+ enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
+ enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
+
+ static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ smram->gdtr.base = dt.address;
+ smram->gdtr.limit = dt.size;
+
+ static_call(kvm_x86_get_idt)(vcpu, &dt);
+ smram->idtr.base = dt.address;
+ smram->idtr.limit = dt.size;
+
+ enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES);
+ enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS);
+ enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS);
+
+ enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS);
+ enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS);
+ enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS);
+
+ smram->cr4 = kvm_read_cr4(vcpu);
+ smram->smm_revision = 0x00020000;
+ smram->smbase = vcpu->arch.smbase;
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+}
+
+#ifdef CONFIG_X86_64
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu,
+ struct kvm_smram_state_64 *smram)
+{
+ struct desc_ptr dt;
+ unsigned long val;
+ int i;
+
+ for (i = 0; i < 16; i++)
+ smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i);
+
+ smram->rip = kvm_rip_read(vcpu);
+ smram->rflags = kvm_get_rflags(vcpu);
+
+
+ kvm_get_dr(vcpu, 6, &val);
+ smram->dr6 = val;
+ kvm_get_dr(vcpu, 7, &val);
+ smram->dr7 = val;
+
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->cr4 = kvm_read_cr4(vcpu);
+
+ smram->smbase = vcpu->arch.smbase;
+ smram->smm_revison = 0x00020064;
+
+ smram->efer = vcpu->arch.efer;
+
+ enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
+
+ static_call(kvm_x86_get_idt)(vcpu, &dt);
+ smram->idtr.limit = dt.size;
+ smram->idtr.base = dt.address;
+
+ enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
+
+ static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ smram->gdtr.limit = dt.size;
+ smram->gdtr.base = dt.address;
+
+ enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES);
+ enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS);
+ enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS);
+ enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+ enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+ enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+}
+#endif
+
+void enter_smm(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment cs, ds;
+ struct desc_ptr dt;
+ unsigned long cr0;
+ union kvm_smram smram;
+
+ check_smram_offsets();
+
+ memset(smram.bytes, 0, sizeof(smram.bytes));
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ enter_smm_save_state_64(vcpu, &smram.smram64);
+ else
+#endif
+ enter_smm_save_state_32(vcpu, &smram.smram32);
+
+ /*
+ * Give enter_smm() a chance to make ISA-specific changes to the vCPU
+ * state (e.g. leave guest mode) after we've saved the state into the
+ * SMM state-save area.
+ *
+ * Kill the VM in the unlikely case of failure, because the VM
+ * can be in undefined state in this case.
+ */
+ if (static_call(kvm_x86_enter_smm)(vcpu, &smram))
+ goto error;
+
+ kvm_smm_changed(vcpu, true);
+
+ if (kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram)))
+ goto error;
+
+ if (static_call(kvm_x86_get_nmi_mask)(vcpu))
+ vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+ else
+ static_call(kvm_x86_set_nmi_mask)(vcpu, true);
+
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ kvm_rip_write(vcpu, 0x8000);
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
+ cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
+ static_call(kvm_x86_set_cr0)(vcpu, cr0);
+ vcpu->arch.cr0 = cr0;
+
+ static_call(kvm_x86_set_cr4)(vcpu, 0);
+
+ /* Undocumented: IDT limit is set to zero on entry to SMM. */
+ dt.address = dt.size = 0;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ if (WARN_ON_ONCE(kvm_set_dr(vcpu, 7, DR7_FIXED_1)))
+ goto error;
+
+ cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
+ cs.base = vcpu->arch.smbase;
+
+ ds.selector = 0;
+ ds.base = 0;
+
+ cs.limit = ds.limit = 0xffffffff;
+ cs.type = ds.type = 0x3;
+ cs.dpl = ds.dpl = 0;
+ cs.db = ds.db = 0;
+ cs.s = ds.s = 1;
+ cs.l = ds.l = 0;
+ cs.g = ds.g = 1;
+ cs.avl = ds.avl = 0;
+ cs.present = ds.present = 1;
+ cs.unusable = ds.unusable = 0;
+ cs.padding = ds.padding = 0;
+
+ kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ if (static_call(kvm_x86_set_efer)(vcpu, 0))
+ goto error;
+#endif
+
+ kvm_update_cpuid_runtime(vcpu);
+ kvm_mmu_reset_context(vcpu);
+ return;
+error:
+ kvm_vm_dead(vcpu->kvm);
+}
+
+static void rsm_set_desc_flags(struct kvm_segment *desc, u32 flags)
+{
+ desc->g = (flags >> 23) & 1;
+ desc->db = (flags >> 22) & 1;
+ desc->l = (flags >> 21) & 1;
+ desc->avl = (flags >> 20) & 1;
+ desc->present = (flags >> 15) & 1;
+ desc->dpl = (flags >> 13) & 3;
+ desc->s = (flags >> 12) & 1;
+ desc->type = (flags >> 8) & 15;
+
+ desc->unusable = !desc->present;
+ desc->padding = 0;
+}
+
+static int rsm_load_seg_32(struct kvm_vcpu *vcpu,
+ const struct kvm_smm_seg_state_32 *state,
+ u16 selector, int n)
+{
+ struct kvm_segment desc;
+
+ desc.selector = selector;
+ desc.base = state->base;
+ desc.limit = state->limit;
+ rsm_set_desc_flags(&desc, state->flags);
+ kvm_set_segment(vcpu, &desc, n);
+ return X86EMUL_CONTINUE;
+}
+
+#ifdef CONFIG_X86_64
+
+static int rsm_load_seg_64(struct kvm_vcpu *vcpu,
+ const struct kvm_smm_seg_state_64 *state,
+ int n)
+{
+ struct kvm_segment desc;
+
+ desc.selector = state->selector;
+ rsm_set_desc_flags(&desc, state->attributes << 8);
+ desc.limit = state->limit;
+ desc.base = state->base;
+ kvm_set_segment(vcpu, &desc, n);
+ return X86EMUL_CONTINUE;
+}
+#endif
+
+static int rsm_enter_protected_mode(struct kvm_vcpu *vcpu,
+ u64 cr0, u64 cr3, u64 cr4)
+{
+ int bad;
+ u64 pcid;
+
+ /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
+ pcid = 0;
+ if (cr4 & X86_CR4_PCIDE) {
+ pcid = cr3 & 0xfff;
+ cr3 &= ~0xfff;
+ }
+
+ bad = kvm_set_cr3(vcpu, cr3);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ /*
+ * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+ * Then enable protected mode. However, PCID cannot be enabled
+ * if EFER.LMA=0, so set it separately.
+ */
+ bad = kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ bad = kvm_set_cr0(vcpu, cr0);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ if (cr4 & X86_CR4_PCIDE) {
+ bad = kvm_set_cr4(vcpu, cr4);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ if (pcid) {
+ bad = kvm_set_cr3(vcpu, cr3 | pcid);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ }
+
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smram_state_32 *smstate)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct desc_ptr dt;
+ int i, r;
+
+ ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->eip;
+
+ for (i = 0; i < 8; i++)
+ *reg_write(ctxt, i) = smstate->gprs[i];
+
+ if (kvm_set_dr(vcpu, 6, smstate->dr6))
+ return X86EMUL_UNHANDLEABLE;
+ if (kvm_set_dr(vcpu, 7, smstate->dr7))
+ return X86EMUL_UNHANDLEABLE;
+
+ rsm_load_seg_32(vcpu, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR);
+ rsm_load_seg_32(vcpu, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR);
+
+ dt.address = smstate->gdtr.base;
+ dt.size = smstate->gdtr.limit;
+ static_call(kvm_x86_set_gdt)(vcpu, &dt);
+
+ dt.address = smstate->idtr.base;
+ dt.size = smstate->idtr.limit;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ rsm_load_seg_32(vcpu, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
+ rsm_load_seg_32(vcpu, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
+ rsm_load_seg_32(vcpu, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS);
+
+ rsm_load_seg_32(vcpu, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS);
+ rsm_load_seg_32(vcpu, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS);
+ rsm_load_seg_32(vcpu, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS);
+
+ vcpu->arch.smbase = smstate->smbase;
+
+ r = rsm_enter_protected_mode(vcpu, smstate->cr0,
+ smstate->cr3, smstate->cr4);
+
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return r;
+}
+
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smram_state_64 *smstate)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct desc_ptr dt;
+ int i, r;
+
+ for (i = 0; i < 16; i++)
+ *reg_write(ctxt, i) = smstate->gprs[15 - i];
+
+ ctxt->_eip = smstate->rip;
+ ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED;
+
+ if (kvm_set_dr(vcpu, 6, smstate->dr6))
+ return X86EMUL_UNHANDLEABLE;
+ if (kvm_set_dr(vcpu, 7, smstate->dr7))
+ return X86EMUL_UNHANDLEABLE;
+
+ vcpu->arch.smbase = smstate->smbase;
+
+ if (kvm_set_msr(vcpu, MSR_EFER, smstate->efer & ~EFER_LMA))
+ return X86EMUL_UNHANDLEABLE;
+
+ rsm_load_seg_64(vcpu, &smstate->tr, VCPU_SREG_TR);
+
+ dt.size = smstate->idtr.limit;
+ dt.address = smstate->idtr.base;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ rsm_load_seg_64(vcpu, &smstate->ldtr, VCPU_SREG_LDTR);
+
+ dt.size = smstate->gdtr.limit;
+ dt.address = smstate->gdtr.base;
+ static_call(kvm_x86_set_gdt)(vcpu, &dt);
+
+ r = rsm_enter_protected_mode(vcpu, smstate->cr0, smstate->cr3, smstate->cr4);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ rsm_load_seg_64(vcpu, &smstate->es, VCPU_SREG_ES);
+ rsm_load_seg_64(vcpu, &smstate->cs, VCPU_SREG_CS);
+ rsm_load_seg_64(vcpu, &smstate->ss, VCPU_SREG_SS);
+ rsm_load_seg_64(vcpu, &smstate->ds, VCPU_SREG_DS);
+ rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS);
+ rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS);
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return X86EMUL_CONTINUE;
+}
+#endif
+
+int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ unsigned long cr0;
+ union kvm_smram smram;
+ u64 smbase;
+ int ret;
+
+ smbase = vcpu->arch.smbase;
+
+ ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfe00, smram.bytes, sizeof(smram));
+ if (ret < 0)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK) == 0)
+ static_call(kvm_x86_set_nmi_mask)(vcpu, false);
+
+ kvm_smm_changed(vcpu, false);
+
+ /*
+ * Get back to real mode, to prepare a safe state in which to load
+ * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
+ * supports long mode.
+ */
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+ struct kvm_segment cs_desc;
+ unsigned long cr4;
+
+ /* Zero CR4.PCIDE before CR0.PG. */
+ cr4 = kvm_read_cr4(vcpu);
+ if (cr4 & X86_CR4_PCIDE)
+ kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE);
+
+ /* A 32-bit code segment is required to clear EFER.LMA. */
+ memset(&cs_desc, 0, sizeof(cs_desc));
+ cs_desc.type = 0xb;
+ cs_desc.s = cs_desc.g = cs_desc.present = 1;
+ kvm_set_segment(vcpu, &cs_desc, VCPU_SREG_CS);
+ }
+#endif
+
+ /* For the 64-bit case, this will clear EFER.LMA. */
+ cr0 = kvm_read_cr0(vcpu);
+ if (cr0 & X86_CR0_PE)
+ kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+ unsigned long cr4, efer;
+
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = kvm_read_cr4(vcpu);
+ if (cr4 & X86_CR4_PAE)
+ kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PAE);
+
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ kvm_set_msr(vcpu, MSR_EFER, efer);
+ }
+#endif
+
+ /*
+ * Give leave_smm() a chance to make ISA-specific changes to the vCPU
+ * state (e.g. enter guest mode) before loading state from the SMM
+ * state-save area.
+ */
+ if (static_call(kvm_x86_leave_smm)(vcpu, &smram))
+ return X86EMUL_UNHANDLEABLE;
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return rsm_load_state_64(ctxt, &smram.smram64);
+ else
+#endif
+ return rsm_load_state_32(ctxt, &smram.smram32);
+}
diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h
new file mode 100644
index 000000000000..a1cf2ac5bd78
--- /dev/null
+++ b/arch/x86/kvm/smm.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_KVM_SMM_H
+#define ASM_KVM_SMM_H
+
+#include <linux/build_bug.h>
+
+#ifdef CONFIG_KVM_SMM
+
+
+/*
+ * 32 bit KVM's emulated SMM layout. Based on Intel P6 layout
+ * (https://www.sandpile.org/x86/smm.htm).
+ */
+
+struct kvm_smm_seg_state_32 {
+ u32 flags;
+ u32 limit;
+ u32 base;
+} __packed;
+
+struct kvm_smram_state_32 {
+ u32 reserved1[62];
+ u32 smbase;
+ u32 smm_revision;
+ u16 io_inst_restart;
+ u16 auto_hlt_restart;
+ u32 io_restart_rdi;
+ u32 io_restart_rcx;
+ u32 io_restart_rsi;
+ u32 io_restart_rip;
+ u32 cr4;
+
+ /* A20M#, CPL, shutdown and other reserved/undocumented fields */
+ u16 reserved2;
+ u8 int_shadow; /* KVM extension */
+ u8 reserved3[17];
+
+ struct kvm_smm_seg_state_32 ds;
+ struct kvm_smm_seg_state_32 fs;
+ struct kvm_smm_seg_state_32 gs;
+ struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */
+ struct kvm_smm_seg_state_32 tr;
+ u32 reserved;
+ struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */
+ struct kvm_smm_seg_state_32 ldtr;
+ struct kvm_smm_seg_state_32 es;
+ struct kvm_smm_seg_state_32 cs;
+ struct kvm_smm_seg_state_32 ss;
+
+ u32 es_sel;
+ u32 cs_sel;
+ u32 ss_sel;
+ u32 ds_sel;
+ u32 fs_sel;
+ u32 gs_sel;
+ u32 ldtr_sel;
+ u32 tr_sel;
+
+ u32 dr7;
+ u32 dr6;
+ u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */
+ u32 eip;
+ u32 eflags;
+ u32 cr3;
+ u32 cr0;
+} __packed;
+
+
+/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */
+
+struct kvm_smm_seg_state_64 {
+ u16 selector;
+ u16 attributes;
+ u32 limit;
+ u64 base;
+};
+
+struct kvm_smram_state_64 {
+
+ struct kvm_smm_seg_state_64 es;
+ struct kvm_smm_seg_state_64 cs;
+ struct kvm_smm_seg_state_64 ss;
+ struct kvm_smm_seg_state_64 ds;
+ struct kvm_smm_seg_state_64 fs;
+ struct kvm_smm_seg_state_64 gs;
+ struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 ldtr;
+ struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 tr;
+
+ /* I/O restart and auto halt restart are not implemented by KVM */
+ u64 io_restart_rip;
+ u64 io_restart_rcx;
+ u64 io_restart_rsi;
+ u64 io_restart_rdi;
+ u32 io_restart_dword;
+ u32 reserved1;
+ u8 io_inst_restart;
+ u8 auto_hlt_restart;
+ u8 amd_nmi_mask; /* Documented in AMD BKDG as NMI mask, not used by KVM */
+ u8 int_shadow;
+ u32 reserved2;
+
+ u64 efer;
+
+ /*
+ * Two fields below are implemented on AMD only, to store
+ * SVM guest vmcb address if the #SMI was received while in the guest mode.
+ */
+ u64 svm_guest_flag;
+ u64 svm_guest_vmcb_gpa;
+ u64 svm_guest_virtual_int; /* unknown purpose, not implemented */
+
+ u32 reserved3[3];
+ u32 smm_revison;
+ u32 smbase;
+ u32 reserved4[5];
+
+ /* ssp and svm_* fields below are not implemented by KVM */
+ u64 ssp;
+ u64 svm_guest_pat;
+ u64 svm_host_efer;
+ u64 svm_host_cr4;
+ u64 svm_host_cr3;
+ u64 svm_host_cr0;
+
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+};
+
+union kvm_smram {
+ struct kvm_smram_state_64 smram64;
+ struct kvm_smram_state_32 smram32;
+ u8 bytes[512];
+};
+
+static inline int kvm_inject_smi(struct kvm_vcpu *vcpu)
+{
+ kvm_make_request(KVM_REQ_SMI, vcpu);
+ return 0;
+}
+
+static inline bool is_smm(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.hflags & HF_SMM_MASK;
+}
+
+void kvm_smm_changed(struct kvm_vcpu *vcpu, bool in_smm);
+void enter_smm(struct kvm_vcpu *vcpu);
+int emulator_leave_smm(struct x86_emulate_ctxt *ctxt);
+void process_smi(struct kvm_vcpu *vcpu);
+#else
+static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) { return -ENOTTY; }
+static inline bool is_smm(struct kvm_vcpu *vcpu) { return false; }
+
+/*
+ * emulator_leave_smm is used as a function pointer, so the
+ * stub is defined in x86.c.
+ */
+#endif
+
+#endif
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 995bc0f90759..3aa9184d1e4e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -25,6 +25,7 @@
#include "trace.h"
#include "mmu.h"
#include "x86.h"
+#include "smm.h"
#include "cpuid.h"
#include "lapic.h"
#include "svm.h"
@@ -1383,6 +1384,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
return 0;
}
+#ifdef CONFIG_KVM_SMM
if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) {
if (block_nested_events)
return -EBUSY;
@@ -1391,6 +1393,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
nested_svm_simple_vmexit(svm, SVM_EXIT_SMI);
return 0;
}
+#endif
if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) {
if (block_nested_events)
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 9d65cd095691..0e313fbae055 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -159,7 +159,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
data &= ~pmu->reserved_bits;
if (data != pmc->eventsel) {
pmc->eventsel = data;
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
return 0;
}
@@ -212,7 +212,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)
struct kvm_pmc *pmc = &pmu->gp_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = pmc->eventsel = 0;
+ pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
}
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index efaaef2b7ae1..69dbf17f0d6a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2648,7 +2648,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
ghcb_scratch_beg = control->ghcb_gpa +
offsetof(struct ghcb, shared_buffer);
ghcb_scratch_end = control->ghcb_gpa +
- offsetof(struct ghcb, reserved_1);
+ offsetof(struct ghcb, reserved_0xff0);
/*
* If the scratch area begins within the GHCB, it must be
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c0950ae86b2b..7efc4fdaa446 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -6,6 +6,7 @@
#include "mmu.h"
#include "kvm_cache_regs.h"
#include "x86.h"
+#include "smm.h"
#include "cpuid.h"
#include "pmu.h"
@@ -2708,8 +2709,6 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
break;
- case MSR_IA32_PERF_CAPABILITIES:
- return 0;
default:
return KVM_MSR_RET_INVALID;
}
@@ -4102,6 +4101,8 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
return false;
case MSR_IA32_SMBASE:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ return false;
/* SEV-ES guests do not support SMM, so report false */
if (kvm && sev_es_guest(kvm))
return false;
@@ -4358,6 +4359,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu)
vcpu->arch.mcg_cap &= 0x1ff;
}
+#ifdef CONFIG_KVM_SMM
bool svm_smi_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -4385,7 +4387,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return 1;
}
-static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map_save;
@@ -4394,10 +4396,16 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
if (!is_guest_mode(vcpu))
return 0;
- /* FED8h - SVM Guest */
- put_smstate(u64, smstate, 0x7ed8, 1);
- /* FEE0h - SVM Guest VMCB Physical Address */
- put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+ /*
+ * 32-bit SMRAM format doesn't preserve EFER and SVM state. Userspace is
+ * responsible for ensuring nested SVM and SMIs are mutually exclusive.
+ */
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return 1;
+
+ smram->smram64.svm_guest_flag = 1;
+ smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
@@ -4419,8 +4427,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
* that, see svm_prepare_switch_to_guest()) which must be
* preserved.
*/
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
- &map_save) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save))
return 1;
BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
@@ -4432,34 +4439,33 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
- u64 saved_efer, vmcb12_gpa;
struct vmcb *vmcb12;
int ret;
+ const struct kvm_smram_state_64 *smram64 = &smram->smram64;
+
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
/* Non-zero if SMI arrived while vCPU was in guest mode. */
- if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+ if (!smram64->svm_guest_flag)
return 0;
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return 1;
- saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
- if (!(saved_efer & EFER_SVME))
+ if (!(smram64->efer & EFER_SVME))
return 1;
- vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram64->svm_guest_vmcb_gpa), &map))
return 1;
ret = 1;
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save))
goto unmap_map;
if (svm_allocate_nested(svm))
@@ -4481,7 +4487,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
vmcb12 = map.hva;
nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+ ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
if (ret)
goto unmap_save;
@@ -4507,6 +4513,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
/* We must be in SMM; RSM will cause a vmexit anyway. */
}
}
+#endif
static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
void *insn, int insn_len)
@@ -4782,10 +4789,12 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.pi_update_irte = avic_pi_update_irte,
.setup_mce = svm_setup_mce,
+#ifdef CONFIG_KVM_SMM
.smi_allowed = svm_smi_allowed,
.enter_smm = svm_enter_smm,
.leave_smm = svm_leave_smm,
.enable_smi_window = svm_enable_smi_window,
+#endif
.mem_enc_ioctl = sev_mem_enc_ioctl,
.mem_enc_register_region = sev_mem_enc_register_region,
@@ -4851,6 +4860,7 @@ static __init void svm_set_cpu_caps(void)
{
kvm_set_cpu_caps();
+ kvm_caps.supported_perf_cap = 0;
kvm_caps.supported_xss = 0;
/* CPUID 0x80000001 and 0x8000000A (SVM features) */
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 07254314f3dd..cd2ac9536c99 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -395,30 +395,6 @@ static inline bool vmx_pebs_supported(void)
return boot_cpu_has(X86_FEATURE_PEBS) && kvm_pmu_cap.pebs_ept;
}
-static inline u64 vmx_get_perf_capabilities(void)
-{
- u64 perf_cap = PMU_CAP_FW_WRITES;
- struct x86_pmu_lbr lbr;
- u64 host_perf_cap = 0;
-
- if (!enable_pmu)
- return 0;
-
- if (boot_cpu_has(X86_FEATURE_PDCM))
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
-
- if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr)
- perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
-
- if (vmx_pebs_supported()) {
- perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
- if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
- perf_cap &= ~PERF_CAP_PEBS_BASELINE;
- }
-
- return perf_cap;
-}
-
static inline bool cpu_has_notify_vmexit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5b0d4859e4b7..7924dea93678 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -16,6 +16,7 @@
#include "trace.h"
#include "vmx.h"
#include "x86.h"
+#include "smm.h"
static bool __read_mostly enable_shadow_vmcs = 1;
module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 10b33da9bd05..e5cec07ca8d9 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -52,7 +52,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
}
@@ -76,7 +76,7 @@ static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
pmc = intel_pmc_idx_to_pmc(pmu, bit);
if (pmc)
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
}
@@ -477,7 +477,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
if (!(data & reserved_bits)) {
pmc->eventsel = data;
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
return 0;
}
} else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false))
@@ -631,7 +631,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
pmu->fixed_counters[i].current_config = 0;
}
- vcpu->arch.perf_capabilities = vmx_get_perf_capabilities();
lbr_desc->records.nr = 0;
lbr_desc->event = NULL;
lbr_desc->msr_passthrough = false;
@@ -647,14 +646,14 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
pmc = &pmu->gp_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = pmc->eventsel = 0;
+ pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
}
for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
pmc = &pmu->fixed_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = 0;
+ pmc->counter = pmc->prev_counter = 0;
}
pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 746129ddd5ae..01936013428b 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -208,9 +208,8 @@ struct __packed vmcs12 {
/*
* For save/restore compatibility, the vmcs12 field offsets must not change.
*/
-#define CHECK_OFFSET(field, loc) \
- BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \
- "Offset of " #field " in struct vmcs12 has changed.")
+#define CHECK_OFFSET(field, loc) \
+ ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
static inline void vmx_check_vmcs12_offsets(void)
{
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 63247c57c72c..aca88524fd1e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -66,6 +66,7 @@
#include "vmcs12.h"
#include "vmx.h"
#include "x86.h"
+#include "smm.h"
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -1849,9 +1850,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
if (!nested)
return 1;
return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
- case MSR_IA32_PERF_CAPABILITIES:
- msr->data = vmx_get_perf_capabilities();
- return 0;
default:
return KVM_MSR_RET_INVALID;
}
@@ -2029,7 +2027,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
(host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
- if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) &&
+ if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) &&
(host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
@@ -2342,14 +2340,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
if (data & PMU_CAP_LBR_FMT) {
if ((data & PMU_CAP_LBR_FMT) !=
- (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT))
+ (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT))
return 1;
if (!cpuid_model_is_consistent(vcpu))
return 1;
}
if (data & PERF_CAP_PEBS_FORMAT) {
if ((data & PERF_CAP_PEBS_MASK) !=
- (vmx_get_perf_capabilities() & PERF_CAP_PEBS_MASK))
+ (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK))
return 1;
if (!guest_cpuid_has(vcpu, X86_FEATURE_DS))
return 1;
@@ -6844,6 +6842,8 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
{
switch (index) {
case MSR_IA32_SMBASE:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ return false;
/*
* We cannot do SMM unless we can run the guest in big
* real mode.
@@ -7669,6 +7669,31 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vmx_update_exception_bitmap(vcpu);
}
+static u64 vmx_get_perf_capabilities(void)
+{
+ u64 perf_cap = PMU_CAP_FW_WRITES;
+ struct x86_pmu_lbr lbr;
+ u64 host_perf_cap = 0;
+
+ if (!enable_pmu)
+ return 0;
+
+ if (boot_cpu_has(X86_FEATURE_PDCM))
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+
+ x86_perf_get_lbr(&lbr);
+ if (lbr.nr)
+ perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+
+ if (vmx_pebs_supported()) {
+ perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
+ if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
+ perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+ }
+
+ return perf_cap;
+}
+
static __init void vmx_set_cpu_caps(void)
{
kvm_set_cpu_caps();
@@ -7691,6 +7716,7 @@ static __init void vmx_set_cpu_caps(void)
if (!enable_pmu)
kvm_cpu_cap_clear(X86_FEATURE_PDCM);
+ kvm_caps.supported_perf_cap = vmx_get_perf_capabilities();
if (!enable_sgx) {
kvm_cpu_cap_clear(X86_FEATURE_SGX);
@@ -7906,6 +7932,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
~FEAT_CTL_LMCE_ENABLED;
}
+#ifdef CONFIG_KVM_SMM
static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
/* we need a nested vmexit to enter SMM, postpone if run is pending */
@@ -7914,7 +7941,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !is_smm(vcpu);
}
-static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7935,7 +7962,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7960,6 +7987,7 @@ static void vmx_enable_smi_window(struct kvm_vcpu *vcpu)
{
/* RSM will cause a vmexit anyway. */
}
+#endif
static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
{
@@ -8127,10 +8155,12 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.setup_mce = vmx_setup_mce,
+#ifdef CONFIG_KVM_SMM
.smi_allowed = vmx_smi_allowed,
.enter_smm = vmx_enter_smm,
.leave_smm = vmx_leave_smm,
.enable_smi_window = vmx_enable_smi_window,
+#endif
.can_emulate_instruction = vmx_can_emulate_instruction,
.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5384c567f68f..404325a13dc2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -30,6 +30,7 @@
#include "hyperv.h"
#include "lapic.h"
#include "xen.h"
+#include "smm.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
@@ -119,8 +120,6 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
-static void process_smi(struct kvm_vcpu *vcpu);
-static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
static void store_regs(struct kvm_vcpu *vcpu);
static int sync_regs(struct kvm_vcpu *vcpu);
@@ -1654,6 +1653,9 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
case MSR_IA32_ARCH_CAPABILITIES:
msr->data = kvm_get_arch_capabilities();
break;
+ case MSR_IA32_PERF_CAPABILITIES:
+ msr->data = kvm_caps.supported_perf_cap;
+ break;
case MSR_IA32_UCODE_REV:
rdmsrl_safe(msr->index, &msr->data);
break;
@@ -3566,20 +3568,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vcpu->arch.arch_capabilities = data;
break;
- case MSR_IA32_PERF_CAPABILITIES: {
- struct kvm_msr_entry msr_ent = {.index = msr, .data = 0};
-
+ case MSR_IA32_PERF_CAPABILITIES:
if (!msr_info->host_initiated)
return 1;
- if (kvm_get_msr_feature(&msr_ent))
- return 1;
- if (data & ~msr_ent.data)
+ if (data & ~kvm_caps.supported_perf_cap)
return 1;
vcpu->arch.perf_capabilities = data;
kvm_pmu_refresh(vcpu);
return 0;
- }
case MSR_EFER:
return set_efer(vcpu, msr_info);
case MSR_K7_HWCR:
@@ -3651,7 +3648,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
}
case MSR_IA32_SMBASE:
- if (!msr_info->host_initiated)
+ if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
return 1;
vcpu->arch.smbase = data;
break;
@@ -4067,7 +4064,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.ia32_misc_enable_msr;
break;
case MSR_IA32_SMBASE:
- if (!msr_info->host_initiated)
+ if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
return 1;
msr_info->data = vcpu->arch.smbase;
break;
@@ -4441,6 +4438,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r |= KVM_X86_DISABLE_EXITS_MWAIT;
break;
case KVM_CAP_X86_SMM:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ break;
+
/* SMBASE is usually relocated above 1M on modern chipsets,
* and SMM handlers might indeed rely on 4G segment limits,
* so do not report SMM to be available if real mode is
@@ -4897,13 +4897,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
return 0;
}
-static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu)
-{
- kvm_make_request(KVM_REQ_SMI, vcpu);
-
- return 0;
-}
-
static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
struct kvm_tpr_access_ctl *tac)
{
@@ -5039,8 +5032,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
process_nmi(vcpu);
+#ifdef CONFIG_KVM_SMM
if (kvm_check_request(KVM_REQ_SMI, vcpu))
process_smi(vcpu);
+#endif
/*
* KVM's ABI only allows for one exception to be migrated. Luckily,
@@ -5068,16 +5063,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
ex->pending && ex->has_payload)
kvm_deliver_exception_payload(vcpu, ex);
+ memset(events, 0, sizeof(*events));
+
/*
* The API doesn't provide the instruction length for software
* exceptions, so don't report them. As long as the guest RIP
* isn't advanced, we should expect to encounter the exception
* again.
*/
- if (kvm_exception_is_soft(ex->vector)) {
- events->exception.injected = 0;
- events->exception.pending = 0;
- } else {
+ if (!kvm_exception_is_soft(ex->vector)) {
events->exception.injected = ex->injected;
events->exception.pending = ex->pending;
/*
@@ -5097,20 +5091,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
- events->interrupt.soft = 0;
events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending != 0;
events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu);
- events->nmi.pad = 0;
- events->sipi_vector = 0; /* never valid when reporting to user space */
+ /* events->sipi_vector is never valid when reporting to user space */
+#ifdef CONFIG_KVM_SMM
events->smi.smm = is_smm(vcpu);
events->smi.pending = vcpu->arch.smi_pending;
events->smi.smm_inside_nmi =
!!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
+#endif
events->smi.latched_init = kvm_lapic_latched_init(vcpu);
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
@@ -5122,12 +5116,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
}
-
- memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm);
-
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
@@ -5200,6 +5190,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+#ifdef CONFIG_KVM_SMM
if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
kvm_leave_nested(vcpu);
kvm_smm_changed(vcpu, events->smi.smm);
@@ -5214,6 +5205,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
}
+#else
+ if (events->smi.smm || events->smi.pending ||
+ events->smi.smm_inside_nmi)
+ return -EINVAL;
+#endif
+
if (lapic_in_kernel(vcpu)) {
if (events->smi.latched_init)
set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
@@ -5580,7 +5577,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
case KVM_SMI: {
- r = kvm_vcpu_ioctl_smi(vcpu);
+ r = kvm_inject_smi(vcpu);
break;
}
case KVM_SET_CPUID: {
@@ -6239,9 +6236,7 @@ split_irqchip_unlock:
break;
case KVM_CAP_X86_USER_SPACE_MSR:
r = -EINVAL;
- if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL |
- KVM_MSR_EXIT_REASON_UNKNOWN |
- KVM_MSR_EXIT_REASON_FILTER))
+ if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK)
break;
kvm->arch.user_space_msr_mask = cap->args[0];
r = 0;
@@ -6418,7 +6413,7 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
if (!user_range->nmsrs)
return 0;
- if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE))
+ if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK)
return -EINVAL;
if (!user_range->flags)
@@ -6452,7 +6447,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
int r = 0;
u32 i;
- if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+ if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK)
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
@@ -7125,8 +7120,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
return handled;
}
-static void kvm_set_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
+void kvm_set_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
{
static_call(kvm_x86_set_segment)(vcpu, var, seg);
}
@@ -7162,16 +7157,6 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
- gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
- struct x86_exception *exception)
-{
- struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
- access |= PFERR_FETCH_MASK;
- return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
-}
-
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception)
{
@@ -7284,15 +7269,6 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
}
-static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
- unsigned long addr, void *val, unsigned int bytes)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes);
-
- return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
-}
-
static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
struct kvm_vcpu *vcpu, u64 access,
struct x86_exception *exception)
@@ -8084,26 +8060,6 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
}
-static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
- u32 msr_index, u64 data)
-{
- return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
-}
-
-static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- return vcpu->arch.smbase;
-}
-
-static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- vcpu->arch.smbase = smbase;
-}
-
static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
u32 pmc)
{
@@ -8178,18 +8134,13 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
return emul_to_vcpu(ctxt)->arch.hflags;
}
-static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
+#ifndef CONFIG_KVM_SMM
+static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- kvm_smm_changed(vcpu, false);
-}
-
-static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
-{
- return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+ WARN_ON_ONCE(1);
+ return X86EMUL_UNHANDLEABLE;
}
+#endif
static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
{
@@ -8215,7 +8166,6 @@ static const struct x86_emulate_ops emulate_ops = {
.write_gpr = emulator_write_gpr,
.read_std = emulator_read_std,
.write_std = emulator_write_std,
- .read_phys = kvm_read_guest_phys_system,
.fetch = kvm_fetch_guest_virt,
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
@@ -8235,11 +8185,8 @@ static const struct x86_emulate_ops emulate_ops = {
.cpl = emulator_get_cpl,
.get_dr = emulator_get_dr,
.set_dr = emulator_set_dr,
- .get_smbase = emulator_get_smbase,
- .set_smbase = emulator_set_smbase,
.set_msr_with_filter = emulator_set_msr_with_filter,
.get_msr_with_filter = emulator_get_msr_with_filter,
- .set_msr = emulator_set_msr,
.get_msr = emulator_get_msr,
.check_pmc = emulator_check_pmc,
.read_pmc = emulator_read_pmc,
@@ -8254,7 +8201,6 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
.get_hflags = emulator_get_hflags,
- .exiting_smm = emulator_exiting_smm,
.leave_smm = emulator_leave_smm,
.triple_fault = emulator_triple_fault,
.set_xcr = emulator_set_xcr,
@@ -8327,8 +8273,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
cs_db ? X86EMUL_MODE_PROT32 :
X86EMUL_MODE_PROT16;
BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
- BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
- BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
ctxt->interruptibility = 0;
ctxt->have_exception = false;
@@ -8587,29 +8531,6 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
static int complete_emulated_pio(struct kvm_vcpu *vcpu);
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
-{
- trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm);
-
- if (entering_smm) {
- vcpu->arch.hflags |= HF_SMM_MASK;
- } else {
- vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK);
-
- /* Process a latched INIT or SMI, if any. */
- kvm_make_request(KVM_REQ_EVENT, vcpu);
-
- /*
- * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
- * on SMM exit we still need to reload them from
- * guest memory
- */
- vcpu->arch.pdptrs_from_userspace = false;
- }
-
- kvm_mmu_reset_context(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -9999,6 +9920,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
* in order to make progress and get back here for another iteration.
* The kvm_x86_ops hooks communicate this by returning -EBUSY.
*/
+#ifdef CONFIG_KVM_SMM
if (vcpu->arch.smi_pending) {
r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY;
if (r < 0)
@@ -10011,6 +9933,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
} else
static_call(kvm_x86_enable_smi_window)(vcpu);
}
+#endif
if (vcpu->arch.nmi_pending) {
r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY;
@@ -10086,246 +10009,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
-static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
-{
- u32 flags = 0;
- flags |= seg->g << 23;
- flags |= seg->db << 22;
- flags |= seg->l << 21;
- flags |= seg->avl << 20;
- flags |= seg->present << 15;
- flags |= seg->dpl << 13;
- flags |= seg->s << 12;
- flags |= seg->type << 8;
- return flags;
-}
-
-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
-{
- struct kvm_segment seg;
- int offset;
-
- kvm_get_segment(vcpu, &seg, n);
- put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- put_smstate(u32, buf, offset + 8, seg.base);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
-{
- struct kvm_segment seg;
- int offset;
- u16 flags;
-
- kvm_get_segment(vcpu, &seg, n);
- offset = 0x7e00 + n * 16;
-
- flags = enter_smm_get_segment_flags(&seg) >> 8;
- put_smstate(u16, buf, offset, seg.selector);
- put_smstate(u16, buf, offset + 2, flags);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u64, buf, offset + 8, seg.base);
-}
-#endif
-
-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
-{
- struct desc_ptr dt;
- struct kvm_segment seg;
- unsigned long val;
- int i;
-
- put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
- put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
- put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
- put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
-
- for (i = 0; i < 8; i++)
- put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
-
- kvm_get_dr(vcpu, 6, &val);
- put_smstate(u32, buf, 0x7fcc, (u32)val);
- kvm_get_dr(vcpu, 7, &val);
- put_smstate(u32, buf, 0x7fc8, (u32)val);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u32, buf, 0x7fc4, seg.selector);
- put_smstate(u32, buf, 0x7f64, seg.base);
- put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u32, buf, 0x7fc0, seg.selector);
- put_smstate(u32, buf, 0x7f80, seg.base);
- put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
-
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f74, dt.address);
- put_smstate(u32, buf, 0x7f70, dt.size);
-
- static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f58, dt.address);
- put_smstate(u32, buf, 0x7f54, dt.size);
-
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_32(vcpu, buf, i);
-
- put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
-
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020000);
- put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
-{
- struct desc_ptr dt;
- struct kvm_segment seg;
- unsigned long val;
- int i;
-
- for (i = 0; i < 16; i++)
- put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
-
- put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
- put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
-
- kvm_get_dr(vcpu, 6, &val);
- put_smstate(u64, buf, 0x7f68, val);
- kvm_get_dr(vcpu, 7, &val);
- put_smstate(u64, buf, 0x7f60, val);
-
- put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
- put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
- put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
-
- put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
-
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020064);
-
- put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e94, seg.limit);
- put_smstate(u64, buf, 0x7e98, seg.base);
-
- static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e84, dt.size);
- put_smstate(u64, buf, 0x7e88, dt.address);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e74, seg.limit);
- put_smstate(u64, buf, 0x7e78, seg.base);
-
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e64, dt.size);
- put_smstate(u64, buf, 0x7e68, dt.address);
-
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_64(vcpu, buf, i);
-}
-#endif
-
-static void enter_smm(struct kvm_vcpu *vcpu)
-{
- struct kvm_segment cs, ds;
- struct desc_ptr dt;
- unsigned long cr0;
- char buf[512];
-
- memset(buf, 0, 512);
-#ifdef CONFIG_X86_64
- if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, buf);
- else
-#endif
- enter_smm_save_state_32(vcpu, buf);
-
- /*
- * Give enter_smm() a chance to make ISA-specific changes to the vCPU
- * state (e.g. leave guest mode) after we've saved the state into the
- * SMM state-save area.
- */
- static_call(kvm_x86_enter_smm)(vcpu, buf);
-
- kvm_smm_changed(vcpu, true);
- kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
-
- if (static_call(kvm_x86_get_nmi_mask)(vcpu))
- vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
- else
- static_call(kvm_x86_set_nmi_mask)(vcpu, true);
-
- kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
- kvm_rip_write(vcpu, 0x8000);
-
- cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
- static_call(kvm_x86_set_cr0)(vcpu, cr0);
- vcpu->arch.cr0 = cr0;
-
- static_call(kvm_x86_set_cr4)(vcpu, 0);
-
- /* Undocumented: IDT limit is set to zero on entry to SMM. */
- dt.address = dt.size = 0;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
-
- kvm_set_dr(vcpu, 7, DR7_FIXED_1);
-
- cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
- cs.base = vcpu->arch.smbase;
-
- ds.selector = 0;
- ds.base = 0;
-
- cs.limit = ds.limit = 0xffffffff;
- cs.type = ds.type = 0x3;
- cs.dpl = ds.dpl = 0;
- cs.db = ds.db = 0;
- cs.s = ds.s = 1;
- cs.l = ds.l = 0;
- cs.g = ds.g = 1;
- cs.avl = ds.avl = 0;
- cs.present = ds.present = 1;
- cs.unusable = ds.unusable = 0;
- cs.padding = ds.padding = 0;
-
- kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
-
-#ifdef CONFIG_X86_64
- if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- static_call(kvm_x86_set_efer)(vcpu, 0);
-#endif
-
- kvm_update_cpuid_runtime(vcpu);
- kvm_mmu_reset_context(vcpu);
-}
-
-static void process_smi(struct kvm_vcpu *vcpu)
-{
- vcpu->arch.smi_pending = true;
- kvm_make_request(KVM_REQ_EVENT, vcpu);
-}
-
void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
unsigned long *vcpu_bitmap)
{
@@ -10585,8 +10268,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
}
if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
record_steal_time(vcpu);
+#ifdef CONFIG_KVM_SMM
if (kvm_check_request(KVM_REQ_SMI, vcpu))
process_smi(vcpu);
+#endif
if (kvm_check_request(KVM_REQ_NMI, vcpu))
process_nmi(vcpu);
if (kvm_check_request(KVM_REQ_PMU, vcpu))
@@ -11900,6 +11585,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
kvm_async_pf_hash_reset(vcpu);
+
+ vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
kvm_pmu_init(vcpu);
vcpu->arch.pending_external_vector = -1;
@@ -12909,10 +12596,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
static_call(kvm_x86_nmi_allowed)(vcpu, false)))
return true;
+#ifdef CONFIG_KVM_SMM
if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
(vcpu->arch.smi_pending &&
static_call(kvm_x86_smi_allowed)(vcpu, false)))
return true;
+#endif
if (kvm_arch_interrupt_allowed(vcpu) &&
(kvm_cpu_has_interrupt(vcpu) ||
@@ -12953,7 +12642,9 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
return true;
if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+#ifdef CONFIG_KVM_SMM
kvm_test_request(KVM_REQ_SMI, vcpu) ||
+#endif
kvm_test_request(KVM_REQ_EVENT, vcpu))
return true;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 829d3134c1eb..9de72586f406 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -27,6 +27,7 @@ struct kvm_caps {
u64 supported_mce_cap;
u64 supported_xcr0;
u64 supported_xss;
+ u64 supported_perf_cap;
};
void kvm_spurious_fault(void);