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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - selftests improvements
   - large PUD support for HugeTLB
   - single-stepping fixes
   - improved tracing
   - various timer and vGIC fixes

  x86:
   - Processor Tracing virtualization
   - STIBP support
   - some correctness fixes
   - refactorings and splitting of vmx.c
   - use the Hyper-V range TLB flush hypercall
   - reduce order of vcpu struct
   - WBNOINVD support
   - do not use -ftrace for __noclone functions
   - nested guest support for PAUSE filtering on AMD
   - more Hyper-V enlightenments (direct mode for synthetic timers)

  PPC:
   -  nested VFIO

  s390:
   - bugfixes only this time"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits)
  KVM: x86: Add CPUID support for new instruction WBNOINVD
  kvm: selftests: ucall: fix exit mmio address guessing
  Revert "compiler-gcc: disable -ftracer for __noclone functions"
  KVM: VMX: Move VM-Enter + VM-Exit handling to non-inline sub-routines
  KVM: VMX: Explicitly reference RCX as the vmx_vcpu pointer in asm blobs
  KVM: x86: Use jmp to invoke kvm_spurious_fault() from .fixup
  MAINTAINERS: Add arch/x86/kvm sub-directories to existing KVM/x86 entry
  KVM/x86: Use SVM assembly instruction mnemonics instead of .byte streams
  KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()
  KVM/MMU: Flush tlb directly in kvm_set_pte_rmapp()
  KVM/MMU: Move tlb flush in kvm_set_pte_rmapp() to kvm_mmu_notifier_change_pte()
  KVM: Make kvm_set_spte_hva() return int
  KVM: Replace old tlb flush function with new one to flush a specified range.
  KVM/MMU: Add tlb flush with range helper function
  KVM/VMX: Add hv tlb range flush support
  x86/hyper-v: Add HvFlushGuestAddressList hypercall support
  KVM: Add tlb_remote_flush_with_range callback in kvm_x86_ops
  KVM: x86: Disable Intel PT when VMXON in L1 guest
  KVM: x86: Set intercept for Intel PT MSRs read/write
  KVM: x86: Implement Intel PT MSRs read/write emulation
  ...

7 files changed, 60 insertions, 81 deletions

diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 00d422336a45..f39801e4136c 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -236,24 +236,3 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 		}
 	}
 }
-
-
-/*
- * After successfully emulating an instruction, we might want to
- * return to user space with a KVM_EXIT_DEBUG. We can only do this
- * once the emulation is complete, though, so for userspace emulations
- * we have to wait until we have re-entered KVM before calling this
- * helper.
- *
- * Return true (and set exit_reason) to return to userspace or false
- * if no further action is required.
- */
-bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		run->exit_reason = KVM_EXIT_DEBUG;
-		run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
-		return true;
-	}
-	return false;
-}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index ab35929dcb3c..0b7983442071 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -247,13 +247,6 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		handled = exit_handler(vcpu, run);
 	}
 
-	/*
-	 * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
-	 * structure if we need to return to userspace.
-	 */
-	if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
-		handled = 0;
-
 	return handled;
 }
 
@@ -287,12 +280,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_IRQ:
 		return 1;
 	case ARM_EXCEPTION_EL1_SERROR:
-		/* We may still need to return for single-step */
-		if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
-			&& kvm_arm_handle_step_debug(vcpu, run))
-			return 0;
-		else
-			return 1;
+		return 1;
 	case ARM_EXCEPTION_TRAP:
 		return handle_trap_exceptions(vcpu, run);
 	case ARM_EXCEPTION_HYP_GONE:
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 63ac10ead3a8..b0b1478094b4 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -313,33 +313,6 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-/* Skip an instruction which has been emulated. Returns true if
- * execution can continue or false if we need to exit hyp mode because
- * single-step was in effect.
- */
-static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
-{
-	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
-
-	if (vcpu_mode_is_32bit(vcpu)) {
-		vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
-		kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-		write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
-	} else {
-		*vcpu_pc(vcpu) += 4;
-	}
-
-	write_sysreg_el2(*vcpu_pc(vcpu), elr);
-
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		vcpu->arch.fault.esr_el2 =
-			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
-		return false;
-	} else {
-		return true;
-	}
-}
-
 static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
 {
 	struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state;
@@ -428,20 +401,12 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
-			if (ret ==  1 && __skip_instr(vcpu))
+			if (ret == 1)
 				return true;
 
-			if (ret == -1) {
-				/* Promote an illegal access to an
-				 * SError. If we would be returning
-				 * due to single-step clear the SS
-				 * bit so handle_exit knows what to
-				 * do after dealing with the error.
-				 */
-				if (!__skip_instr(vcpu))
-					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
 				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-			}
 
 			goto exit;
 		}
@@ -452,7 +417,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
-		if (ret == 1 && __skip_instr(vcpu))
+		if (ret == 1)
 			return true;
 	}
 
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 215c7c0eb3b0..9cbdd034a563 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -41,7 +41,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
  * Returns:
  *  1: GICV access successfully performed
  *  0: Not a GICV access
- * -1: Illegal GICV access
+ * -1: Illegal GICV access successfully performed
  */
 int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
@@ -61,12 +61,16 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 		return 0;
 
 	/* Reject anything but a 32bit access */
-	if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32))
+	if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) {
+		__kvm_skip_instr(vcpu);
 		return -1;
+	}
 
 	/* Not aligned? Don't bother */
-	if (fault_ipa & 3)
+	if (fault_ipa & 3) {
+		__kvm_skip_instr(vcpu);
 		return -1;
+	}
 
 	rd = kvm_vcpu_dabt_get_rd(vcpu);
 	addr  = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va;
@@ -88,5 +92,7 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 		vcpu_set_reg(vcpu, rd, data);
 	}
 
+	__kvm_skip_instr(vcpu);
+
 	return 1;
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1ca592d38c3c..e3e37228ae4e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -76,7 +76,7 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	if (!vcpu->arch.sysregs_loaded_on_cpu)
 		goto immediate_read;
@@ -1858,6 +1858,8 @@ static void perform_access(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *params,
 			   const struct sys_reg_desc *r)
 {
+	trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
+
 	/*
 	 * Not having an accessor means that we have configured a trap
 	 * that we don't know how to handle. This certainly qualifies
@@ -1920,8 +1922,8 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 	}
 
-	kvm_err("Unsupported guest CP%d access at: %08lx\n",
-		cp, *vcpu_pc(vcpu));
+	kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n",
+		cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 }
@@ -2071,8 +2073,8 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 	if (likely(r)) {
 		perform_access(vcpu, params, r);
 	} else {
-		kvm_err("Unsupported guest sys_reg access at: %lx\n",
-			*vcpu_pc(vcpu));
+		kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n",
+			*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
 		print_sys_reg_instr(params);
 		kvm_inject_undefined(vcpu);
 	}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index cd710f8b63e0..3b1bc7f01d0b 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -35,6 +35,9 @@ struct sys_reg_params {
 };
 
 struct sys_reg_desc {
+	/* Sysreg string for debug */
+	const char *name;
+
 	/* MRS/MSR instruction which accesses it. */
 	u8	Op0;
 	u8	Op1;
@@ -130,6 +133,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 #define Op2(_x) 	.Op2 = _x
 
 #define SYS_DESC(reg)					\
+	.name = #reg,					\
 	Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)),	\
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h
index 3b82fb1ddd09..eab91ad0effb 100644
--- a/arch/arm64/kvm/trace.h
+++ b/arch/arm64/kvm/trace.h
@@ -3,6 +3,7 @@
 #define _TRACE_ARM64_KVM_H
 
 #include <linux/tracepoint.h>
+#include "sys_regs.h"
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
@@ -152,6 +153,40 @@ TRACE_EVENT(kvm_handle_sys_reg,
 	TP_printk("HSR 0x%08lx", __entry->hsr)
 );
 
+TRACE_EVENT(kvm_sys_access,
+	TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg),
+	TP_ARGS(vcpu_pc, params, reg),
+
+	TP_STRUCT__entry(
+		__field(unsigned long,			vcpu_pc)
+		__field(bool,				is_write)
+		__field(const char *,			name)
+		__field(u8,				Op0)
+		__field(u8,				Op1)
+		__field(u8,				CRn)
+		__field(u8,				CRm)
+		__field(u8,				Op2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->is_write = params->is_write;
+		__entry->name = reg->name;
+		__entry->Op0 = reg->Op0;
+		__entry->Op0 = reg->Op0;
+		__entry->Op1 = reg->Op1;
+		__entry->CRn = reg->CRn;
+		__entry->CRm = reg->CRm;
+		__entry->Op2 = reg->Op2;
+	),
+
+	TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s",
+		  __entry->vcpu_pc, __entry->name ?: "UNKN",
+		  __entry->Op0, __entry->Op1, __entry->CRn,
+		  __entry->CRm, __entry->Op2,
+		  __entry->is_write ? "write" : "read")
+);
+
 TRACE_EVENT(kvm_set_guest_debug,
 	TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
 	TP_ARGS(vcpu, guest_debug),