Merge 5.14-rc5 into driver-core-next

We need the driver core fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

12 files changed, 96 insertions, 53 deletions

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index b07592ca92f0..0b38f944c6b6 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2016,6 +2016,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 
 static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
+	trace_kvm_hv_hypercall_done(result);
 	kvm_hv_hypercall_set_result(vcpu, result);
 	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
@@ -2139,6 +2140,7 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code)
 
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct kvm_hv_hcall hc;
 	u64 ret = HV_STATUS_SUCCESS;
 
@@ -2173,17 +2175,25 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
 	hc.rep = !!(hc.rep_cnt || hc.rep_idx);
 
-	if (hc.fast && is_xmm_fast_hypercall(&hc))
-		kvm_hv_hypercall_read_xmm(&hc);
-
 	trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx,
 			       hc.ingpa, hc.outgpa);
 
-	if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) {
+	if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
 		ret = HV_STATUS_ACCESS_DENIED;
 		goto hypercall_complete;
 	}
 
+	if (hc.fast && is_xmm_fast_hypercall(&hc)) {
+		if (unlikely(hv_vcpu->enforce_cpuid &&
+			     !(hv_vcpu->cpuid_cache.features_edx &
+			       HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+
+		kvm_hv_hypercall_read_xmm(&hc);
+	}
+
 	switch (hc.code) {
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
 		if (unlikely(hc.rep)) {
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 698969e18fe3..ff005fe738a4 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 660401700075..11e4065e1617 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -43,13 +43,13 @@ struct kvm_vcpu;
 
 struct dest_map {
 	/* vcpu bitmap where IRQ has been sent */
-	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
 
 	/*
 	 * Vector sent to a given vcpu, only valid when
 	 * the vcpu's bit in map is set
 	 */
-	u8 vectors[KVM_MAX_VCPU_ID];
+	u8 vectors[KVM_MAX_VCPU_ID + 1];
 };
 
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 66f7f5bc3482..c4f4fa23320e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1644,7 +1644,7 @@ static int is_empty_shadow_page(u64 *spt)
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 1d01da64c333..a8ad78a2faa1 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -646,7 +646,7 @@ out:
 void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *vmcb = svm->vmcb;
+	struct vmcb *vmcb = svm->vmcb01.ptr;
 	bool activated = kvm_vcpu_apicv_active(vcpu);
 
 	if (!enable_apicv)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3bd09c50c98b..61738ff8ef33 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -515,7 +515,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	 * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
 	 * avic_physical_id.
 	 */
-	WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK);
+	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
 
 	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
 	svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
@@ -702,8 +702,8 @@ out:
 }
 
 /* Copy state save area fields which are handled by VMRUN */
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
-			  struct vmcb_save_area *to_save)
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+			  struct vmcb_save_area *from_save)
 {
 	to_save->es = from_save->es;
 	to_save->cs = from_save->cs;
@@ -722,7 +722,7 @@ void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
 	to_save->cpl = 0;
 }
 
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 {
 	to_vmcb->save.fs = from_vmcb->save.fs;
 	to_vmcb->save.gs = from_vmcb->save.gs;
@@ -1385,7 +1385,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
 
-	svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save);
+	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
 	nested_load_control_from_vmcb12(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6710d9ee2e4b..7fbce342eec4 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -64,6 +64,7 @@ static DEFINE_MUTEX(sev_bitmap_lock);
 unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long sev_me_mask;
+static unsigned int nr_asids;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
 
@@ -78,11 +79,11 @@ struct enc_region {
 /* Called with the sev_bitmap_lock held, or on shutdown  */
 static int sev_flush_asids(int min_asid, int max_asid)
 {
-	int ret, pos, error = 0;
+	int ret, asid, error = 0;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
-	pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid);
-	if (pos >= max_asid)
+	asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
+	if (asid > max_asid)
 		return -EBUSY;
 
 	/*
@@ -115,15 +116,15 @@ static bool __sev_recycle_asids(int min_asid, int max_asid)
 
 	/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
 	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
-		   max_sev_asid);
-	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+		   nr_asids);
+	bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);
 
 	return true;
 }
 
 static int sev_asid_new(struct kvm_sev_info *sev)
 {
-	int pos, min_asid, max_asid, ret;
+	int asid, min_asid, max_asid, ret;
 	bool retry = true;
 	enum misc_res_type type;
 
@@ -143,11 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev)
 	 * 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 ? 0 : 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:
-	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
-	if (pos >= max_asid) {
+	asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
+	if (asid > max_asid) {
 		if (retry && __sev_recycle_asids(min_asid, max_asid)) {
 			retry = false;
 			goto again;
@@ -157,11 +158,11 @@ again:
 		goto e_uncharge;
 	}
 
-	__set_bit(pos, sev_asid_bitmap);
+	__set_bit(asid, sev_asid_bitmap);
 
 	mutex_unlock(&sev_bitmap_lock);
 
-	return pos + 1;
+	return asid;
 e_uncharge:
 	misc_cg_uncharge(type, sev->misc_cg, 1);
 	put_misc_cg(sev->misc_cg);
@@ -179,17 +180,16 @@ static int sev_get_asid(struct kvm *kvm)
 static void sev_asid_free(struct kvm_sev_info *sev)
 {
 	struct svm_cpu_data *sd;
-	int cpu, pos;
+	int cpu;
 	enum misc_res_type type;
 
 	mutex_lock(&sev_bitmap_lock);
 
-	pos = sev->asid - 1;
-	__set_bit(pos, sev_reclaim_asid_bitmap);
+	__set_bit(sev->asid, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
-		sd->sev_vmcbs[pos] = NULL;
+		sd->sev_vmcbs[sev->asid] = NULL;
 	}
 
 	mutex_unlock(&sev_bitmap_lock);
@@ -1857,12 +1857,17 @@ void __init sev_hardware_setup(void)
 	min_sev_asid = edx;
 	sev_me_mask = 1UL << (ebx & 0x3f);
 
-	/* Initialize SEV ASID bitmaps */
-	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	/*
+	 * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap,
+	 * even though it's never used, so that the bitmap is indexed by the
+	 * actual ASID.
+	 */
+	nr_asids = max_sev_asid + 1;
+	sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		goto out;
 
-	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
 	if (!sev_reclaim_asid_bitmap) {
 		bitmap_free(sev_asid_bitmap);
 		sev_asid_bitmap = NULL;
@@ -1907,7 +1912,7 @@ void sev_hardware_teardown(void)
 		return;
 
 	/* No need to take sev_bitmap_lock, all VMs have been destroyed. */
-	sev_flush_asids(0, max_sev_asid);
+	sev_flush_asids(1, max_sev_asid);
 
 	bitmap_free(sev_asid_bitmap);
 	bitmap_free(sev_reclaim_asid_bitmap);
@@ -1921,7 +1926,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
 	if (!sev_enabled)
 		return 0;
 
-	sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL);
+	sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL);
 	if (!sd->sev_vmcbs)
 		return -ENOMEM;
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 664d20f0689c..e8ccab50ebf6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1406,8 +1406,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		goto error_free_vmsa_page;
 	}
 
-	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
 	svm->vmcb01.ptr = page_address(vmcb01_page);
 	svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
 
@@ -1419,6 +1417,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	svm_switch_vmcb(svm, &svm->vmcb01);
 	init_vmcb(vcpu);
 
+	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
 	svm_init_osvw(vcpu);
 	vcpu->arch.microcode_version = 0x01000065;
 
@@ -1568,8 +1568,11 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control;
 
-	/* The following fields are ignored when AVIC is enabled */
-	WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
+	/*
+	 * The following fields are ignored when AVIC is enabled
+	 */
+	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+
 	svm_set_intercept(svm, INTERCEPT_VINTR);
 
 	/*
@@ -2147,11 +2150,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload)
 	ret = kvm_skip_emulated_instruction(vcpu);
 
 	if (vmload) {
-		nested_svm_vmloadsave(vmcb12, svm->vmcb);
+		svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
 		svm->sysenter_eip_hi = 0;
 		svm->sysenter_esp_hi = 0;
-	} else
-		nested_svm_vmloadsave(svm->vmcb, vmcb12);
+	} else {
+		svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
+	}
 
 	kvm_vcpu_unmap(vcpu, &map, true);
 
@@ -4344,8 +4348,8 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 
 		BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
 
-		svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
-				     map_save.hva + 0x400);
+		svm_copy_vmrun_state(map_save.hva + 0x400,
+				     &svm->vmcb01.ptr->save);
 
 		kvm_vcpu_unmap(vcpu, &map_save, true);
 	}
@@ -4393,8 +4397,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 					 &map_save) == -EINVAL)
 				return 1;
 
-			svm_copy_vmrun_state(map_save.hva + 0x400,
-					     &svm->vmcb01.ptr->save);
+			svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+					     map_save.hva + 0x400);
 
 			kvm_vcpu_unmap(vcpu, &map_save, true);
 		}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 7e2090752d8f..bd0fe94c2920 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -464,9 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct kvm_vcpu *vcpu);
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
-			  struct vmcb_save_area *to_save);
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+			  struct vmcb_save_area *from_save);
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
 int nested_svm_vmexit(struct vcpu_svm *svm);
 
 static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index 9b9a55abc29f..c53b8bf8d013 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments(
 	 * as we mark it dirty unconditionally towards end of vcpu
 	 * init phase.
 	 */
-	if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
+	if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
 	    hve->hv_enlightenments_control.msr_bitmap)
 		vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
 }
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index b484141ea15b..03ebe368333e 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -92,6 +92,21 @@ TRACE_EVENT(kvm_hv_hypercall,
 		  __entry->outgpa)
 );
 
+TRACE_EVENT(kvm_hv_hypercall_done,
+	TP_PROTO(u64 result),
+	TP_ARGS(result),
+
+	TP_STRUCT__entry(
+		__field(__u64, result)
+	),
+
+	TP_fast_assign(
+		__entry->result	= result;
+	),
+
+	TP_printk("result 0x%llx", __entry->result)
+);
+
 /*
  * Tracepoint for Xen hypercall.
  */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a4fd10604f72..e5d5c5ed7dd4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3407,7 +3407,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
-		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
 			return 1;
 		if (data & 0x1) {
 			vcpu->arch.apf.pageready_pending = false;
@@ -3746,7 +3746,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.apf.msr_int_val;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
-		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
 			return 1;
 
 		msr_info->data = 0;
@@ -4358,8 +4358,17 @@ static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
-	return kvm_arch_interrupt_allowed(vcpu) &&
-		kvm_cpu_accept_dm_intr(vcpu);
+	/*
+	 * Do not cause an interrupt window exit if an exception
+	 * is pending or an event needs reinjection; userspace
+	 * might want to inject the interrupt manually using KVM_SET_REGS
+	 * or KVM_SET_SREGS.  For that to work, we must be at an
+	 * instruction boundary and with no events half-injected.
+	 */
+	return (kvm_arch_interrupt_allowed(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu) &&
+		!kvm_event_needs_reinjection(vcpu) &&
+		!vcpu->arch.exception.pending);
 }
 
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,