Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Bugfixes, mostly for ARM and AMD, and more documentation.

  Slightly bigger than usual because I couldn't send out what was
  pending for rc4, but there is nothing worrisome going on. I have more
  fixes pending for guest debugging support (gdbstub) but I will send
  them next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (22 commits)
  KVM: X86: Declare KVM_CAP_SET_GUEST_DEBUG properly
  KVM: selftests: Fix build for evmcs.h
  kvm: x86: Use KVM CPU capabilities to determine CR4 reserved bits
  KVM: VMX: Explicitly clear RFLAGS.CF and RFLAGS.ZF in VM-Exit RSB path
  docs/virt/kvm: Document configuring and running nested guests
  KVM: s390: Remove false WARN_ON_ONCE for the PQAP instruction
  kvm: ioapic: Restrict lazy EOI update to edge-triggered interrupts
  KVM: x86: Fixes posted interrupt check for IRQs delivery modes
  KVM: SVM: fill in kvm_run->debug.arch.dr[67]
  KVM: nVMX: Replace a BUG_ON(1) with BUG() to squash clang warning
  KVM: arm64: Fix 32bit PC wrap-around
  KVM: arm64: vgic-v4: Initialize GICv4.1 even in the absence of a virtual ITS
  KVM: arm64: Save/restore sp_el0 as part of __guest_enter
  KVM: arm64: Delete duplicated label in invalid_vector
  KVM: arm64: vgic-its: Fix memory leak on the error path of vgic_add_lpi()
  KVM: arm64: vgic-v3: Retire all pending LPIs on vcpu destroy
  KVM: arm: vgic-v2: Only use the virtual state when userspace accesses pending bits
  KVM: arm: vgic: Only use the virtual state when userspace accesses enable bits
  KVM: arm: vgic: Synchronize the whole guest on GIC{D,R}_I{S,C}ACTIVER read
  KVM: arm64: PSCI: Forbid 64bit functions for 32bit guests
  ...

13 files changed, 57 insertions, 39 deletions

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 23ebe51410f0..50a279d3ddd7 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+
+	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+	}
 out:
 	return err;
 }
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index d22d0534dd60..90186cf6473e 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -18,6 +18,7 @@
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
 	.pushsection	.hyp.text, "ax"
@@ -47,6 +48,16 @@
 	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
 .endm
 
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
 /*
  * u64 __guest_enter(struct kvm_vcpu *vcpu,
  *		     struct kvm_cpu_context *host_ctxt);
@@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
+	// Save the host's sp_el0
+	save_sp_el0	x1, x2
+
 	// Now the host state is stored if we have a pending RAS SError it must
 	// affect the host. If any asynchronous exception is pending we defer
 	// the guest entry. The DSB isn't necessary before v8.2 as any SError
@@ -83,6 +97,9 @@ alternative_else_nop_endif
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_guest x29, x0, x1, x2
 
+	// Restore the guest's sp_el0
+	restore_sp_el0 x29, x0
+
 	// Restore guest regs x0-x17
 	ldp	x0, x1,   [x29, #CPU_XREG_OFFSET(0)]
 	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
@@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Store the guest regs x18-x29, lr
 	save_callee_saved_regs x1
 
+	// Store the guest's sp_el0
+	save_sp_el0	x1, x2
+
 	get_host_ctxt	x2, x3
 
 	// Macro ptrauth_switch_to_guest format:
@@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_host x1, x2, x3, x4, x5
 
+	// Restore the hosts's sp_el0
+	restore_sp_el0 x2, x3
+
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index c2a13ab3c471..9c5cfb04170e 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic)
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
 SYM_CODE_START(\label)
-\label:
 	b \target
 SYM_CODE_END(\label)
 .endm
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 75b1925763f1..6d2df9fe0b5d 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -15,8 +15,9 @@
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate,
- * which are handled as part of the el2 return state) on every switch.
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
  * tpidr_el0 and tpidrro_el0 only need to be switched when going
  * to host userspace or a different VCPU.  EL1 registers only need to be
  * switched when potentially going to run a different VCPU.  The latter two
@@ -26,12 +27,6 @@
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 }
 
 static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
@@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
 static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 }
 
 static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index e15166b0a16d..ad2f172c26a6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5dcf9ff12828..d05bb040fd42 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS:
 	case KVM_CAP_S390_AIS_MIGRATION:
 	case KVM_CAP_S390_VCPU_RESETS:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_S390_HPAGE_1M:
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 69a824f9ef0b..893893642415 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	 * available for the guest are AQIC and TAPQ with the t bit set
 	 * since we do not set IC.3 (FIII) we currently will only intercept
 	 * the AQIC function code.
+	 * Note: running nested under z/VM can result in intercepts for other
+	 * function codes, e.g. PQAP(QCI). We do not support this and bail out.
 	 */
 	reg0 = vcpu->run->s.regs.gprs[0];
 	fc = (reg0 >> 24) & 0xff;
-	if (WARN_ON_ONCE(fc != 0x03))
+	if (fc != 0x03)
 		return -EOPNOTSUPP;
 
 	/* PQAP instruction is allowed for guest kernel only */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 42a2d0d3984a..0dea9f122bb9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
 {
 	/* We can only post Fixed and LowPrio IRQs */
-	return (irq->delivery_mode == dest_Fixed ||
-		irq->delivery_mode == dest_LowestPrio);
+	return (irq->delivery_mode == APIC_DM_FIXED ||
+		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 750ff0b29404..d057376bd3d3 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 	}
 
 	/*
-	 * AMD SVM AVIC accelerate EOI write and do not trap,
-	 * in-kernel IOAPIC will not be able to receive the EOI.
-	 * In this case, we do lazy update of the pending EOI when
-	 * trying to set IOAPIC irq.
+	 * AMD SVM AVIC accelerate EOI write iff the interrupt is edge
+	 * triggered, in which case the in-kernel IOAPIC will not be able
+	 * to receive the EOI.  In this case, we do a lazy update of the
+	 * pending EOI when trying to set IOAPIC irq.
 	 */
-	if (kvm_apicv_activated(ioapic->kvm))
+	if (edge && kvm_apicv_activated(ioapic->kvm))
 		ioapic_lazy_update_eoi(ioapic, irq);
 
 	/*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2f379bacbb26..38f6aeefeb55 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1752,6 +1752,8 @@ static int db_interception(struct vcpu_svm *svm)
 	if (svm->vcpu.guest_debug &
 	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6;
+		kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7;
 		kvm_run->debug.arch.pc =
 			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
 		kvm_run->debug.arch.exception = DB_VECTOR;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index fd78ffbde644..e44f33c82332 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	 */
 		break;
 	default:
-		BUG_ON(1);
+		BUG();
 		break;
 	}
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 87f3f24fef37..51d1a82742fd 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit)
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 
+	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
+	or $1, %_ASM_AX
+
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c5835f9cb9ad..d786c7d27ce5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -926,19 +926,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 	__reserved_bits;				\
 })
 
-static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
-{
-	u64 reserved_bits = __cr4_reserved_bits(cpu_has, c);
-
-	if (kvm_cpu_cap_has(X86_FEATURE_LA57))
-		reserved_bits &= ~X86_CR4_LA57;
-
-	if (kvm_cpu_cap_has(X86_FEATURE_UMIP))
-		reserved_bits &= ~X86_CR4_UMIP;
-
-	return reserved_bits;
-}
-
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
@@ -3385,6 +3372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -9675,7 +9663,9 @@ int kvm_arch_hardware_setup(void *opaque)
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		supported_xss = 0;
 
-	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f)
+	cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_);
+#undef __kvm_cpu_cap_has
 
 	if (kvm_has_tsc_control) {
 		/*
@@ -9707,7 +9697,8 @@ int kvm_arch_check_processor_compat(void *opaque)
 
 	WARN_ON(!irqs_disabled());
 
-	if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits)
+	if (__cr4_reserved_bits(cpu_has, c) !=
+	    __cr4_reserved_bits(cpu_has, &boot_cpu_data))
 		return -EIO;
 
 	return ops->check_processor_compatibility();