Merge tag 'kvm-x86-misc-6.10' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.10:

 - Advertise the max mappable GPA in the "guest MAXPHYADDR" CPUID field, which
   is unused by hardware, so that KVM can communicate its inability to map GPAs
   that set bits 51:48 due to lack of 5-level paging.  Guest firmware is
   expected to use the information to safely remap BARs in the uppermost GPA
   space, i.e to avoid placing a BAR at a legal, but unmappable, GPA.

 - Use vfree() instead of kvfree() for allocations that always use vcalloc()
   or __vcalloc().

 - Don't completely ignore same-value writes to immutable feature MSRs, as
   doing so results in KVM failing to reject accesses to MSR that aren't
   supposed to exist given the vCPU model and/or KVM configuration.

 - Don't mark APICv as being inhibited due to ABSENT if APICv is disabled
   KVM-wide to avoid confusing debuggers (KVM will never bother clearing the
   ABSENT inhibit, even if userspace enables in-kernel local APIC).

6 files changed, 52 insertions, 30 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 1851b3870a9c..f2f2be5d1141 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1232,9 +1232,22 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->eax = entry->ebx = entry->ecx = 0;
 		break;
 	case 0x80000008: {
-		unsigned g_phys_as = (entry->eax >> 16) & 0xff;
-		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
-		unsigned phys_as = entry->eax & 0xff;
+		/*
+		 * GuestPhysAddrSize (EAX[23:16]) is intended for software
+		 * use.
+		 *
+		 * KVM's ABI is to report the effective MAXPHYADDR for the
+		 * guest in PhysAddrSize (phys_as), and the maximum
+		 * *addressable* GPA in GuestPhysAddrSize (g_phys_as).
+		 *
+		 * GuestPhysAddrSize is valid if and only if TDP is enabled,
+		 * in which case the max GPA that can be addressed by KVM may
+		 * be less than the max GPA that can be legally generated by
+		 * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't
+		 * support 5-level TDP.
+		 */
+		unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U);
+		unsigned int phys_as, g_phys_as;
 
 		/*
 		 * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
@@ -1242,16 +1255,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		 * reductions in MAXPHYADDR for memory encryption affect shadow
 		 * paging, too.
 		 *
-		 * If TDP is enabled but an explicit guest MAXPHYADDR is not
-		 * provided, use the raw bare metal MAXPHYADDR as reductions to
-		 * the HPAs do not affect GPAs.
+		 * If TDP is enabled, use the raw bare metal MAXPHYADDR as
+		 * reductions to the HPAs do not affect GPAs.  The max
+		 * addressable GPA is the same as the max effective GPA, except
+		 * that it's capped at 48 bits if 5-level TDP isn't supported
+		 * (hardware processes bits 51:48 only when walking the fifth
+		 * level page table).
 		 */
-		if (!tdp_enabled)
-			g_phys_as = boot_cpu_data.x86_phys_bits;
-		else if (!g_phys_as)
+		if (!tdp_enabled) {
+			phys_as = boot_cpu_data.x86_phys_bits;
+			g_phys_as = 0;
+		} else {
+			phys_as = entry->eax & 0xff;
 			g_phys_as = phys_as;
+			if (kvm_mmu_get_max_tdp_level() < 5)
+				g_phys_as = min(g_phys_as, 48);
+		}
 
-		entry->eax = g_phys_as | (virt_as << 8);
+		entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16);
 		entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
 		entry->edx = 0;
 		cpuid_entry_override(entry, CPUID_8000_0008_EBX);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2343c9f00e31..2e454316f2a2 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -100,6 +100,8 @@ static inline u8 kvm_get_shadow_phys_bits(void)
 	return boot_cpu_data.x86_phys_bits;
 }
 
+u8 kvm_mmu_get_max_tdp_level(void);
+
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
 void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
 void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 99f7b2f3d82a..662f62dfb2aa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5316,6 +5316,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
 	return max_tdp_level;
 }
 
+u8 kvm_mmu_get_max_tdp_level(void)
+{
+	return tdp_root_level ? tdp_root_level : max_tdp_level;
+}
+
 static union kvm_mmu_page_role
 kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
 				union kvm_cpu_role cpu_role)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index f6448284c18e..561c331fd6ec 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -41,7 +41,7 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
 {
-	kvfree(slot->arch.gfn_write_track);
+	vfree(slot->arch.gfn_write_track);
 	slot->arch.gfn_write_track = NULL;
 }
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index c6b4b1728006..9d0b02ef307e 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1074,7 +1074,7 @@ TRACE_EVENT(kvm_smm_transition,
 );
 
 /*
- * Tracepoint for VT-d posted-interrupts.
+ * Tracepoint for VT-d posted-interrupts and AMD-Vi Guest Virtual APIC.
  */
 TRACE_EVENT(kvm_pi_irte_update,
 	TP_PROTO(unsigned int host_irq, unsigned int vcpu_id,
@@ -1100,7 +1100,7 @@ TRACE_EVENT(kvm_pi_irte_update,
 		__entry->set		= set;
 	),
 
-	TP_printk("VT-d PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
+	TP_printk("PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
 		  "gvec: 0x%x, pi_desc_addr: 0x%llx",
 		  __entry->set ? "enabled and being updated" : "disabled",
 		  __entry->host_irq,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fda22b3800a1..082ac6d95a3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2233,16 +2233,13 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	/*
 	 * Disallow writes to immutable feature MSRs after KVM_RUN.  KVM does
 	 * not support modifying the guest vCPU model on the fly, e.g. changing
-	 * the nVMX capabilities while L2 is running is nonsensical.  Ignore
+	 * the nVMX capabilities while L2 is running is nonsensical.  Allow
 	 * writes of the same value, e.g. to allow userspace to blindly stuff
 	 * all MSRs when emulating RESET.
 	 */
-	if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) {
-		if (do_get_msr(vcpu, index, &val) || *data != val)
-			return -EINVAL;
-
-		return 0;
-	}
+	if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) &&
+	    (do_get_msr(vcpu, index, &val) || *data != val))
+		return -EINVAL;
 
 	return kvm_set_msr_ignored_check(vcpu, index, *data, true);
 }
@@ -10031,15 +10028,12 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
 
 static void kvm_apicv_init(struct kvm *kvm)
 {
-	unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons;
+	enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT :
+						       APICV_INHIBIT_REASON_DISABLE;
 
-	init_rwsem(&kvm->arch.apicv_update_lock);
-
-	set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true);
+	set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true);
 
-	if (!enable_apicv)
-		set_or_clear_apicv_inhibit(inhibits,
-					   APICV_INHIBIT_REASON_DISABLE, true);
+	init_rwsem(&kvm->arch.apicv_update_lock);
 }
 
 static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
@@ -12805,7 +12799,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot)
 	int i;
 
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.rmap[i]);
+		vfree(slot->arch.rmap[i]);
 		slot->arch.rmap[i] = NULL;
 	}
 }
@@ -12817,7 +12811,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	memslot_rmap_free(slot);
 
 	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.lpage_info[i - 1]);
+		vfree(slot->arch.lpage_info[i - 1]);
 		slot->arch.lpage_info[i - 1] = NULL;
 	}
 
@@ -12909,7 +12903,7 @@ out_free:
 	memslot_rmap_free(slot);
 
 	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.lpage_info[i - 1]);
+		vfree(slot->arch.lpage_info[i - 1]);
 		slot->arch.lpage_info[i - 1] = NULL;
 	}
 	return -ENOMEM;