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

Pull KVM updates from Paolo Bonzini:
 "ARM:

   - More progress on the protected VM front, now with the full fixed
     feature set as well as the limitation of some hypercalls after
     initialisation.

   - Cleanup of the RAZ/WI sysreg handling, which was pointlessly
     complicated

   - Fixes for the vgic placement in the IPA space, together with a
     bunch of selftests

   - More memcg accounting of the memory allocated on behalf of a guest

   - Timer and vgic selftests

   - Workarounds for the Apple M1 broken vgic implementation

   - KConfig cleanups

   - New kvmarm.mode=none option, for those who really dislike us

  RISC-V:

   - New KVM port.

  x86:

   - New API to control TSC offset from userspace

   - TSC scaling for nested hypervisors on SVM

   - Switch masterclock protection from raw_spin_lock to seqcount

   - Clean up function prototypes in the page fault code and avoid
     repeated memslot lookups

   - Convey the exit reason to userspace on emulation failure

   - Configure time between NX page recovery iterations

   - Expose Predictive Store Forwarding Disable CPUID leaf

   - Allocate page tracking data structures lazily (if the i915 KVM-GT
     functionality is not compiled in)

   - Cleanups, fixes and optimizations for the shadow MMU code

  s390:

   - SIGP Fixes

   - initial preparations for lazy destroy of secure VMs

   - storage key improvements/fixes

   - Log the guest CPNC

  Starting from this release, KVM-PPC patches will come from Michael
  Ellerman's PPC tree"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  RISC-V: KVM: fix boolreturn.cocci warnings
  RISC-V: KVM: remove unneeded semicolon
  RISC-V: KVM: Fix GPA passed to __kvm_riscv_hfence_gvma_xyz() functions
  RISC-V: KVM: Factor-out FP virtualization into separate sources
  KVM: s390: add debug statement for diag 318 CPNC data
  KVM: s390: pv: properly handle page flags for protected guests
  KVM: s390: Fix handle_sske page fault handling
  KVM: x86: SGX must obey the KVM_INTERNAL_ERROR_EMULATION protocol
  KVM: x86: On emulation failure, convey the exit reason, etc. to userspace
  KVM: x86: Get exit_reason as part of kvm_x86_ops.get_exit_info
  KVM: x86: Clarify the kvm_run.emulation_failure structure layout
  KVM: s390: Add a routine for setting userspace CPU state
  KVM: s390: Simplify SIGP Set Arch handling
  KVM: s390: pv: avoid stalls when making pages secure
  KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm
  KVM: s390: pv: avoid double free of sida page
  KVM: s390: pv: add macros for UVC CC values
  s390/mm: optimize reset_guest_reference_bit()
  s390/mm: optimize set_guest_storage_key()
  s390/mm: no need for pte_alloc_map_lock() if we know the pmd is present
  ...

1 files changed, 97 insertions, 138 deletions

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index d5a47b93ef9b..7a0af1d39303 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -8,6 +8,7 @@
 #define __ARM64_KVM_HYP_SWITCH_H__
 
 #include <hyp/adjust_pc.h>
+#include <hyp/fault.h>
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
@@ -137,78 +138,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
-	u64 par, tmp;
-
-	/*
-	 * Resolve the IPA the hard way using the guest VA.
-	 *
-	 * Stage-1 translation already validated the memory access
-	 * rights. As such, we can use the EL1 translation regime, and
-	 * don't have to distinguish between EL0 and EL1 access.
-	 *
-	 * We do need to save/restore PAR_EL1 though, as we haven't
-	 * saved the guest context yet, and we may return early...
-	 */
-	par = read_sysreg_par();
-	if (!__kvm_at("s1e1r", far))
-		tmp = read_sysreg_par();
-	else
-		tmp = SYS_PAR_EL1_F; /* back to the guest */
-	write_sysreg(par, par_el1);
-
-	if (unlikely(tmp & SYS_PAR_EL1_F))
-		return false; /* Translation failed, back to guest */
-
-	/* Convert PAR to HPFAR format */
-	*hpfar = PAR_TO_HPFAR(tmp);
-	return true;
-}
-
-static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
-{
-	u64 hpfar, far;
-
-	far = read_sysreg_el2(SYS_FAR);
-
-	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
-	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
-	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
-		hpfar = read_sysreg(hpfar_el2);
-	}
-
-	fault->far_el2 = far;
-	fault->hpfar_el2 = hpfar;
-	return true;
-}
-
 static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 {
-	u8 ec;
-	u64 esr;
-
-	esr = vcpu->arch.fault.esr_el2;
-	ec = ESR_ELx_EC(esr);
-
-	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
-		return true;
-
-	return __get_fault_info(esr, &vcpu->arch.fault);
+	return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
 }
 
 static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu)
@@ -229,8 +161,13 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+/*
+ * We trap the first access to the FP/SIMD to save the host context and
+ * restore the guest context lazily.
+ * If FP/SIMD is not implemented, handle the trap and inject an undefined
+ * instruction exception to the guest. Similarly for trapped SVE accesses.
+ */
+static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest, sve_host;
 	u8 esr_ec;
@@ -248,9 +185,6 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	}
 
 	esr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    esr_ec != ESR_ELx_EC_SVE)
-		return false;
 
 	/* Don't handle SVE traps for non-SVE vcpus here: */
 	if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD)
@@ -352,14 +286,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 
 static inline bool esr_is_ptrauth_trap(u32 esr)
 {
-	u32 ec = ESR_ELx_EC(esr);
-
-	if (ec == ESR_ELx_EC_PAC)
-		return true;
-
-	if (ec != ESR_ELx_EC_SYS64)
-		return false;
-
 	switch (esr_sys64_to_sysreg(esr)) {
 	case SYS_APIAKEYLO_EL1:
 	case SYS_APIAKEYHI_EL1:
@@ -388,13 +314,12 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
 
 DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 
-static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm_cpu_context *ctxt;
 	u64 val;
 
-	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+	if (!vcpu_has_ptrauth(vcpu))
 		return false;
 
 	ctxt = this_cpu_ptr(&kvm_hyp_ctxt);
@@ -413,6 +338,90 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
+		return true;
+
+	if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+		return kvm_hyp_handle_ptrauth(vcpu, exit_code);
+
+	return false;
+}
+
+static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
+		return true;
+
+	return false;
+}
+
+static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	return false;
+}
+
+static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+		bool valid;
+
+		valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+			kvm_vcpu_dabt_isvalid(vcpu) &&
+			!kvm_vcpu_abt_issea(vcpu) &&
+			!kvm_vcpu_abt_iss1tw(vcpu);
+
+		if (valid) {
+			int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+			if (ret == 1)
+				return true;
+
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
+		}
+	}
+
+	return false;
+}
+
+typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
+
+/*
+ * Allow the hypervisor to handle the exit with an exit handler if it has one.
+ *
+ * Returns true if the hypervisor handled the exit, and control should go back
+ * to the guest, or false if it hasn't.
+ */
+static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
+	exit_handler_fn fn;
+
+	fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
+
+	if (fn)
+		return fn(vcpu, exit_code);
+
+	return false;
+}
+
 /*
  * 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
@@ -447,59 +456,9 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
-	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
-	    handle_tx2_tvm(vcpu))
+	/* Check if there's an exit handler and allow it to handle the exit. */
+	if (kvm_hyp_handle_exit(vcpu, exit_code))
 		goto guest;
-
-	/*
-	 * We trap the first access to the FP/SIMD to save the host context
-	 * and restore the guest context lazily.
-	 * If FP/SIMD is not implemented, handle the trap and inject an
-	 * undefined instruction exception to the guest.
-	 * Similarly for trapped SVE accesses.
-	 */
-	if (__hyp_handle_fpsimd(vcpu))
-		goto guest;
-
-	if (__hyp_handle_ptrauth(vcpu))
-		goto guest;
-
-	if (!__populate_fault_info(vcpu))
-		goto guest;
-
-	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
-		bool valid;
-
-		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
-			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
-			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_abt_iss1tw(vcpu);
-
-		if (valid) {
-			int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
-			if (ret == 1)
-				goto guest;
-
-			/* Promote an illegal access to an SError.*/
-			if (ret == -1)
-				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-
-			goto exit;
-		}
-	}
-
-	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
-		int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
-		if (ret == 1)
-			goto guest;
-	}
-
 exit:
 	/* Return to the host kernel and handle the exit */
 	return false;