Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 87 insertions, 51 deletions

diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h
index 02f4784b5..d3f8bfc05 100644
--- a/arch/x86/kvm/svm/hyperv.h
+++ b/arch/x86/kvm/svm/hyperv.h
@@ -11,6 +11,7 @@
 #include "../hyperv.h"
 #include "svm.h"
 
+#ifdef CONFIG_KVM_HYPERV
 static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
 }
 
 void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {}
+static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {}
+#endif /* CONFIG_KVM_HYPERV */
 
 #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 60891b9ce..dee62362a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm)
  */
 static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
-	struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
 	int i;
 
 	/*
@@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 * - Nested hypervisor (L1) is using Hyper-V emulation interface and
 	 * tells KVM (L0) there were no changes in MSR bitmap for L2.
 	 */
-	if (!svm->nested.force_msr_bitmap_recalc &&
-	    kvm_hv_hypercall_enabled(&svm->vcpu) &&
-	    hve->hv_enlightenments_control.msr_bitmap &&
-	    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
-		goto set_msrpm_base_pa;
+#ifdef CONFIG_KVM_HYPERV
+	if (!svm->nested.force_msr_bitmap_recalc) {
+		struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+
+		if (kvm_hv_hypercall_enabled(&svm->vcpu) &&
+		    hve->hv_enlightenments_control.msr_bitmap &&
+		    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
+			goto set_msrpm_base_pa;
+	}
+#endif
 
 	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
@@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 
 	svm->nested.force_msr_bitmap_recalc = false;
 
+#ifdef CONFIG_KVM_HYPERV
 set_msrpm_base_pa:
+#endif
 	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));
 
 	return true;
@@ -296,7 +302,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu,
 	if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) {
 		if (CC(!(save->cr4 & X86_CR4_PAE)) ||
 		    CC(!(save->cr0 & X86_CR0_PE)) ||
-		    CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3)))
+		    CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3)))
 			return false;
 	}
 
@@ -363,12 +369,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
 	to->msrpm_base_pa &= ~0x0fffULL;
 	to->iopm_base_pa  &= ~0x0fffULL;
 
+#ifdef CONFIG_KVM_HYPERV
 	/* Hyper-V extensions (Enlightened VMCB) */
 	if (kvm_hv_hypercall_enabled(vcpu)) {
 		to->clean = from->clean;
 		memcpy(&to->hv_enlightenments, &from->hv_enlightenments,
 		       sizeof(to->hv_enlightenments));
 	}
+#endif
 }
 
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
@@ -472,14 +480,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
 
 static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
-	 * L2's VP_ID upon request from the guest. Make sure we check for
-	 * pending entries in the right FIFO upon L1/L2 transition as these
-	 * requests are put by other vCPUs asynchronously.
-	 */
-	if (to_hv_vcpu(vcpu) && npt_enabled)
-		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+	/* Handle pending Hyper-V TLB flush requests */
+	kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled);
 
 	/*
 	 * TODO: optimize unconditional TLB flush/MMU sync.  A partial list of
@@ -505,7 +507,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 			       bool nested_npt, bool reload_pdptrs)
 {
-	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3)))
+	if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3)))
 		return -EINVAL;
 
 	if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) &&
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 3fd47de14..b6a7ad4d6 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -161,7 +161,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
 		pmc_write_counter(pmc, data);
-		pmc_update_sample_period(pmc);
 		return 0;
 	}
 	/* MSR_EVNTSELn */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 1226bb215..86088d125 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -84,9 +84,10 @@ struct enc_region {
 };
 
 /* Called with the sev_bitmap_lock held, or on shutdown  */
-static int sev_flush_asids(int min_asid, int max_asid)
+static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 {
-	int ret, asid, error = 0;
+	int ret, error = 0;
+	unsigned int asid;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
 	asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
@@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
 }
 
 /* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(int min_asid, int max_asid)
+static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
 {
 	if (sev_flush_asids(min_asid, max_asid))
 		return false;
@@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
 
 static int sev_asid_new(struct kvm_sev_info *sev)
 {
-	int asid, min_asid, max_asid, ret;
+	/*
+	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
+	 * Note: min ASID can end up larger than the max if basic SEV support is
+	 * effectively disabled by disallowing use of ASIDs for SEV guests.
+	 */
+	unsigned int min_asid = sev->es_active ? 1 : min_sev_asid;
+	unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
+	unsigned int asid;
 	bool retry = true;
+	int ret;
+
+	if (min_asid > max_asid)
+		return -ENOTTY;
 
 	WARN_ON(sev->misc_cg);
 	sev->misc_cg = get_current_misc_cg();
@@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev)
 
 	mutex_lock(&sev_bitmap_lock);
 
-	/*
-	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
-	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
-	 */
-	min_asid = sev->es_active ? 1 : min_sev_asid;
-	max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
 again:
 	asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
 	if (asid > max_asid) {
@@ -187,7 +194,7 @@ e_uncharge:
 	return ret;
 }
 
-static int sev_get_asid(struct kvm *kvm)
+static unsigned int sev_get_asid(struct kvm *kvm)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
@@ -284,8 +291,8 @@ e_no_asid:
 
 static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 {
+	unsigned int asid = sev_get_asid(kvm);
 	struct sev_data_activate activate;
-	int asid = sev_get_asid(kvm);
 	int ret;
 
 	/* activate ASID on the given handle */
@@ -2196,10 +2203,13 @@ void __init sev_hardware_setup(void)
 	/*
 	 * SEV must obviously be supported in hardware.  Sanity check that the
 	 * CPU supports decode assists, which is mandatory for SEV guests to
-	 * support instruction emulation.
+	 * support instruction emulation.  Ditto for flushing by ASID, as SEV
+	 * guests are bound to a single ASID, i.e. KVM can't rotate to a new
+	 * ASID to effect a TLB flush.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_SEV) ||
-	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)))
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) ||
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
 		goto out;
 
 	/* Retrieve SEV CPUID information */
@@ -2234,8 +2244,10 @@ void __init sev_hardware_setup(void)
 		goto out;
 	}
 
-	sev_asid_count = max_sev_asid - min_sev_asid + 1;
-	WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+	if (min_sev_asid <= max_sev_asid) {
+		sev_asid_count = max_sev_asid - min_sev_asid + 1;
+		WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+	}
 	sev_supported = true;
 
 	/* SEV-ES support requested? */
@@ -2266,7 +2278,9 @@ void __init sev_hardware_setup(void)
 out:
 	if (boot_cpu_has(X86_FEATURE_SEV))
 		pr_info("SEV %s (ASIDs %u - %u)\n",
-			sev_supported ? "enabled" : "disabled",
+			sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
+								       "unusable" :
+								       "disabled",
 			min_sev_asid, max_sev_asid);
 	if (boot_cpu_has(X86_FEATURE_SEV_ES))
 		pr_info("SEV-ES %s (ASIDs %u - %u)\n",
@@ -2314,7 +2328,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
  */
 static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 {
-	int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+	unsigned int asid = sev_get_asid(vcpu->kvm);
 
 	/*
 	 * Note!  The address must be a kernel address, as regular page walk
@@ -2632,7 +2646,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-	int asid = sev_get_asid(svm->vcpu.kvm);
+	unsigned int asid = sev_get_asid(svm->vcpu.kvm);
 
 	/* Assign the asid allocated with this SEV guest */
 	svm->asid = asid;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a8bd4e909..e90b429c8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3563,8 +3563,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 	if (svm->nmi_l1_to_l2)
 		return;
 
-	svm->nmi_masked = true;
-	svm_set_iret_intercept(svm);
+	/*
+	 * No need to manually track NMI masking when vNMI is enabled, hardware
+	 * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the
+	 * case where software directly injects an NMI.
+	 */
+	if (!is_vnmi_enabled(svm)) {
+		svm->nmi_masked = true;
+		svm_set_iret_intercept(svm);
+	}
 	++vcpu->stat.nmi_injections;
 }
 
@@ -4744,7 +4751,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * Emulation is possible for SEV guests if and only if a prefilled
 	 * buffer containing the bytes of the intercepted instruction is
 	 * available. SEV guest memory is encrypted with a guest specific key
-	 * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
+	 * and cannot be decrypted by KVM, i.e. KVM would read ciphertext and
 	 * decode garbage.
 	 *
 	 * If KVM is NOT trying to simply skip an instruction, inject #UD if
@@ -5079,6 +5086,13 @@ static __init void svm_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SVM);
 		kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN);
 
+		/*
+		 * KVM currently flushes TLBs on *every* nested SVM transition,
+		 * and so for all intents and purposes KVM supports flushing by
+		 * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush.
+		 */
+		kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID);
+
 		if (nrips)
 			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index c409f934c..8ef95139c 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -148,7 +148,9 @@ struct vmcb_ctrl_area_cached {
 	u64 virt_ext;
 	u32 clean;
 	union {
+#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
 		struct hv_vmcb_enlightenments hv_enlightenments;
+#endif
 		u8 reserved_sw[32];
 	};
 };
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 7af8422d3..3971b3ea5 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -18,18 +18,14 @@
 int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	struct hv_vmcb_enlightenments *hve;
-	struct hv_partition_assist_pg **p_hv_pa_pg =
-			&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
 
-	if (!*p_hv_pa_pg)
-		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL);
-
-	if (!*p_hv_pa_pg)
+	if (partition_assist_page == INVALID_PAGE)
 		return -ENOMEM;
 
 	hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
 
-	hve->partition_assist_page = __pa(*p_hv_pa_pg);
+	hve->partition_assist_page = partition_assist_page;
 	hve->hv_vm_id = (unsigned long)vcpu->kvm;
 	if (!hve->hv_enlightenments_control.nested_flush_hypercall) {
 		hve->hv_enlightenments_control.nested_flush_hypercall = 1;
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index ef2ebabb0..9499f9c6b 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-10:	cmpb $0, kvm_rebooting
+10:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2
-30:	cmpb $0, kvm_rebooting
+30:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 4b
 	ud2
-50:	cmpb $0, kvm_rebooting
+50:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 6b
 	ud2
-70:	cmpb $0, kvm_rebooting
+70:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 8b
 	ud2
 
@@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	RESTORE_GUEST_SPEC_CTRL_BODY
 	RESTORE_HOST_SPEC_CTRL_BODY
 
-3:	cmpb $0, kvm_rebooting
+3:	cmpb $0, _ASM_RIP(kvm_rebooting)
 	jne 2b
 	ud2