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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - A couple of fixes when handling an exception while a SError has
     been delivered

   - Workaround for Cortex-A510's single-step erratum

  RISC-V:

   - Make CY, TM, and IR counters accessible in VU mode

   - Fix SBI implementation version

  x86:

   - Report deprecation of x87 features in supported CPUID

   - Preparation for fixing an interrupt delivery race on AMD hardware

   - Sparse fix

  All except POWER and s390:

   - Rework guest entry code to correctly mark noinstr areas and fix
     vtime' accounting (for x86, this was already mostly correct but not
     entirely; for ARM, MIPS and RISC-V it wasn't)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Use ERR_PTR_USR() to return -EFAULT as a __user pointer
  KVM: x86: Report deprecated x87 features in supported CPUID
  KVM: arm64: Workaround Cortex-A510's single-step and PAC trap errata
  KVM: arm64: Stop handle_exit() from handling HVC twice when an SError occurs
  KVM: arm64: Avoid consuming a stale esr value when SError occur
  RISC-V: KVM: Fix SBI implementation version
  RISC-V: KVM: make CY, TM, and IR counters accessible in VU mode
  kvm/riscv: rework guest entry logic
  kvm/arm64: rework guest entry logic
  kvm/x86: rework guest entry logic
  kvm/mips: rework guest entry logic
  kvm: add guest_state_{enter,exit}_irqoff()
  KVM: x86: Move delivery of non-APICv interrupt into vendor code
  kvm: Move KVM_GET_XSAVE2 IOCTL definition at the end of kvm.h

Author: torvalds

Documentation/arm64/silicon-errata.rst

@@ -100,6 +100,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2051678        | ARM64_ERRATUM_2051678       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2077057        | ARM64_ERRATUM_2077057       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2054223        | ARM64_ERRATUM_2054223       |

arch/arm64/Kconfig

@@ -680,6 +680,22 @@ config ARM64_ERRATUM_2051678
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2077057
+	bool "Cortex-A510: 2077057: workaround software-step corrupting SPSR_EL2"
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2077057.
+	  Affected Cortex-A510 may corrupt SPSR_EL2 when the a step exception is
+	  expected, but a Pointer Authentication trap is taken instead. The
+	  erratum causes SPSR_EL1 to be copied to SPSR_EL2, which could allow
+	  EL1 to cause a return to EL2 with a guest controlled ELR_EL2.
+
+	  This can only happen when EL2 is stepping EL1.
+
+	  When these conditions occur, the SPSR_EL2 value is unchanged from the
+	  previous guest entry, and can be restored from the in-memory copy.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_2119858
 	bool "Cortex-A710/X2: 2119858: workaround TRBE overwriting trace data in FILL mode"
 	default y

arch/arm64/kernel/cpu_errata.c

@@ -600,6 +600,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2077057
+	{
+		.desc = "ARM erratum 2077057",
+		.capability = ARM64_WORKAROUND_2077057,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2064142
 	{
 		.desc = "ARM erratum 2064142",

arch/arm64/kvm/arm.c

@@ -797,6 +797,24 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
 			xfer_to_guest_mode_work_pending();
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_enter_irqoff();
+	ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+	guest_state_exit_irqoff();
+
+	return ret;
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -881,9 +899,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		guest_enter_irqoff();
+		guest_timing_enter_irqoff();
 
-		ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+		ret = kvm_arm_vcpu_enter_exit(vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -918,26 +936,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
 		/*
-		 * We may have taken a host interrupt in HYP mode (ie
-		 * while executing the guest). This interrupt is still
-		 * pending, as we haven't serviced it yet!
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
 		 *
-		 * We're now back in SVC mode, with interrupts
-		 * disabled.  Enabling the interrupts now will have
-		 * the effect of taking the interrupt again, in SVC
-		 * mode this time.
+		 * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other
+		 * context synchronization event) is necessary to ensure that
+		 * pending interrupts are taken.
 		 */
 		local_irq_enable();
+		isb();
+		local_irq_disable();
+
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
 
-		/*
-		 * We do local_irq_enable() before calling guest_exit() so
-		 * that if a timer interrupt hits while running the guest we
-		 * account that tick as being spent in the guest.  We enable
-		 * preemption after calling guest_exit() so that if we get
-		 * preempted we make sure ticks after that is not counted as
-		 * guest time.
-		 */
-		guest_exit();
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/* Exit types that need handling before we can be preempted */

arch/arm64/kvm/handle_exit.c

@@ -228,6 +228,14 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 {
 	struct kvm_run *run = vcpu->run;
 
+	if (ARM_SERROR_PENDING(exception_index)) {
+		/*
+		 * The SError is handled by handle_exit_early(). If the guest
+		 * survives it will re-execute the original instruction.
+		 */
+		return 1;
+	}
+
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	switch (exception_index) {

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -402,6 +402,24 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
+static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/*
+	 * Check for the conditions of Cortex-A510's #2077057. When these occur
+	 * SPSR_EL2 can't be trusted, but isn't needed either as it is
+	 * unchanged from the value in vcpu_gp_regs(vcpu)->pstate.
+	 * Are we single-stepping the guest, and took a PAC exception from the
+	 * active-not-pending state?
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_2077057)		&&
+	    vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP			&&
+	    *vcpu_cpsr(vcpu) & DBG_SPSR_SS				&&
+	    ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC)
+		write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -413,7 +431,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	 * Save PSTATE early so that we can evaluate the vcpu mode
 	 * early on.
 	 */
-	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+	synchronize_vcpu_pstate(vcpu, exit_code);
 
 	/*
 	 * Check whether we want to repaint the state one way or
@@ -424,7 +442,8 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
-	if (ARM_SERROR_PENDING(*exit_code)) {
+	if (ARM_SERROR_PENDING(*exit_code) &&
+	    ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) {
 		u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
 
 		/*

arch/arm64/tools/cpucaps

@@ -55,9 +55,10 @@ WORKAROUND_1418040
 WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
-WORKAROUND_2064142
-WORKAROUND_2038923
 WORKAROUND_1902691
+WORKAROUND_2038923
+WORKAROUND_2064142
+WORKAROUND_2077057
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_TRBE_WRITE_OUT_OF_RANGE

arch/mips/kvm/mips.c

@@ -414,6 +414,24 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -ENOIOCTLCMD;
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static int noinstr kvm_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_enter_irqoff();
+	ret = kvm_mips_callbacks->vcpu_run(vcpu);
+	guest_state_exit_irqoff();
+
+	return ret;
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	int r = -EINTR;
@@ -434,7 +452,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	lose_fpu(1);
 
 	local_irq_disable();
-	guest_enter_irqoff();
+	guest_timing_enter_irqoff();
 	trace_kvm_enter(vcpu);
 
 	/*
@@ -445,10 +463,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	 */
 	smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 
-	r = kvm_mips_callbacks->vcpu_run(vcpu);
+	r = kvm_mips_vcpu_enter_exit(vcpu);
+
+	/*
+	 * We must ensure that any pending interrupts are taken before
+	 * we exit guest timing so that timer ticks are accounted as
+	 * guest time. Transiently unmask interrupts so that any
+	 * pending interrupts are taken.
+	 *
+	 * TODO: is there a barrier which ensures that pending interrupts are
+	 * recognised? Currently this just hopes that the CPU takes any pending
+	 * interrupts between the enable and disable.
+	 */
+	local_irq_enable();
+	local_irq_disable();
 
 	trace_kvm_out(vcpu);
-	guest_exit_irqoff();
+	guest_timing_exit_irqoff();
 	local_irq_enable();
 
 out:
@@ -1168,7 +1199,7 @@ static void kvm_mips_set_c0_status(void)
 /*
  * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
  */
-int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+static int __kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 cause = vcpu->arch.host_cp0_cause;
@@ -1357,6 +1388,17 @@ int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+int noinstr kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_exit_irqoff();
+	ret = __kvm_mips_handle_exit(vcpu);
+	guest_state_enter_irqoff();
+
+	return ret;
+}
+
 /* Enable FPU for guest and restore context */
 void kvm_own_fpu(struct kvm_vcpu *vcpu)
 {

arch/riscv/kvm/vcpu.c

@@ -90,6 +90,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *cntx;
+	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 
 	/* Mark this VCPU never ran */
 	vcpu->arch.ran_atleast_once = false;
@@ -106,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SPVP;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	/* By default, make CY, TM, and IR counters accessible in VU mode */
+	reset_csr->scounteren = 0x7;
+
 	/* Setup VCPU timer */
 	kvm_riscv_vcpu_timer_init(vcpu);
 
@@ -699,6 +703,20 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
 	csr_write(CSR_HVIP, csr->hvip);
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	guest_state_enter_irqoff();
+	__kvm_riscv_switch_to(&vcpu->arch);
+	guest_state_exit_irqoff();
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -790,9 +808,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		guest_enter_irqoff();
+		guest_timing_enter_irqoff();
 
-		__kvm_riscv_switch_to(&vcpu->arch);
+		kvm_riscv_vcpu_enter_exit(vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -812,25 +830,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_riscv_vcpu_sync_interrupts(vcpu);
 
 		/*
-		 * We may have taken a host interrupt in VS/VU-mode (i.e.
-		 * while executing the guest). This interrupt is still
-		 * pending, as we haven't serviced it yet!
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
 		 *
-		 * We're now back in HS-mode with interrupts disabled
-		 * so enabling the interrupts now will have the effect
-		 * of taking the interrupt again, in HS-mode this time.
+		 * There's no barrier which ensures that pending interrupts are
+		 * recognised, so we just hope that the CPU takes any pending
+		 * interrupts between the enable and disable.
 		 */
 		local_irq_enable();
+		local_irq_disable();
 
-		/*
-		 * We do local_irq_enable() before calling guest_exit() so
-		 * that if a timer interrupt hits while running the guest
-		 * we account that tick as being spent in the guest. We
-		 * enable preemption after calling guest_exit() so that if
-		 * we get preempted we make sure ticks after that is not
-		 * counted as guest time.
-		 */
-		guest_exit();
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
 
 		preempt_enable();
 

arch/riscv/kvm/vcpu_sbi_base.c

@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/version.h>
 #include <asm/csr.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_timer.h>
@@ -32,7 +33,7 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		*out_val = KVM_SBI_IMPID;
 		break;
 	case SBI_EXT_BASE_GET_IMP_VERSION:
-		*out_val = 0;
+		*out_val = LINUX_VERSION_CODE;
 		break;
 	case SBI_EXT_BASE_PROBE_EXT:
 		if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START &&