3 files changed, 87 insertions, 9 deletions

diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 4ba5c9095d03..f5154ed3da6c 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -65,6 +65,66 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
+#define PMSCR_EL1		sys_reg(3, 0, 9, 9, 0)
+
+#define PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
+#define PMBLIMITR_EL1_E		BIT(0)
+
+#define PMBIDR_EL1		sys_reg(3, 0, 9, 10, 7)
+#define PMBIDR_EL1_P		BIT(4)
+
+#define psb_csync()		asm volatile("hint #17")
+
+static void __hyp_text __debug_save_spe_vhe(u64 *pmscr_el1)
+{
+	/* The vcpu can run. but it can't hide. */
+}
+
+static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
+{
+	u64 reg;
+
+	/* SPE present on this CPU? */
+	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
+						  ID_AA64DFR0_PMSVER_SHIFT))
+		return;
+
+	/* Yes; is it owned by EL3? */
+	reg = read_sysreg_s(PMBIDR_EL1);
+	if (reg & PMBIDR_EL1_P)
+		return;
+
+	/* No; is the host actually using the thing? */
+	reg = read_sysreg_s(PMBLIMITR_EL1);
+	if (!(reg & PMBLIMITR_EL1_E))
+		return;
+
+	/* Yes; save the control register and disable data generation */
+	*pmscr_el1 = read_sysreg_s(PMSCR_EL1);
+	write_sysreg_s(0, PMSCR_EL1);
+	isb();
+
+	/* Now drain all buffered data to memory */
+	psb_csync();
+	dsb(nsh);
+}
+
+static hyp_alternate_select(__debug_save_spe,
+			    __debug_save_spe_nvhe, __debug_save_spe_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+{
+	if (!pmscr_el1)
+		return;
+
+	/* The host page table is installed, but not yet synchronised */
+	isb();
+
+	/* Re-enable data generation */
+	write_sysreg_s(pmscr_el1, PMSCR_EL1);
+}
+
 void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 				   struct kvm_guest_debug_arch *dbg,
 				   struct kvm_cpu_context *ctxt)
@@ -118,13 +178,15 @@ void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu)
 	    (vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_MDE))
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 
-	__debug_save_state(vcpu, &vcpu->arch.host_debug_state,
+	__debug_save_state(vcpu, &vcpu->arch.host_debug_state.regs,
 			   kern_hyp_va(vcpu->arch.host_cpu_context));
+	__debug_save_spe()(&vcpu->arch.host_debug_state.pmscr_el1);
 }
 
 void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu)
 {
-	__debug_restore_state(vcpu, &vcpu->arch.host_debug_state,
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_restore_state(vcpu, &vcpu->arch.host_debug_state.regs,
 			      kern_hyp_va(vcpu->arch.host_cpu_context));
 
 	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 75e83dd40d43..aede1658aeda 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -103,7 +103,13 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 static void __hyp_text __deactivate_traps_vhe(void)
 {
 	extern char vectors[];	/* kernel exception vectors */
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+		    MDCR_EL2_TPMS;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
@@ -111,6 +117,12 @@ static void __hyp_text __deactivate_traps_vhe(void)
 
 static void __hyp_text __deactivate_traps_nvhe(void)
 {
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
+	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
 	write_sysreg(HCR_RW, hcr_el2);
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
@@ -132,7 +144,6 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps_arch()();
 	write_sysreg(0, hstr_el2);
-	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
 	write_sysreg(0, pmuserenr_el0);
 }
 
@@ -357,6 +368,10 @@ again:
 	}
 
 	__debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
+	/*
+	 * This must come after restoring the host sysregs, since a non-VHE
+	 * system may enable SPE here and make use of the TTBRs.
+	 */
 	__debug_cond_restore_host_state(vcpu);
 
 	return exit_code;
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 88e2f2b938f0..e8e7ba2bc11f 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -16,6 +16,7 @@
  */
 
 #include <asm/kvm_hyp.h>
+#include <asm/tlbflush.h>
 
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
@@ -32,7 +33,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	asm volatile("tlbi ipas2e1is, %0" : : "r" (ipa));
+	__tlbi(ipas2e1is, ipa);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
@@ -41,7 +42,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	 * the Stage-1 invalidation happened first.
 	 */
 	dsb(ish);
-	asm volatile("tlbi vmalle1is" : : );
+	__tlbi(vmalle1is);
 	dsb(ish);
 	isb();
 
@@ -57,7 +58,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 	write_sysreg(kvm->arch.vttbr, vttbr_el2);
 	isb();
 
-	asm volatile("tlbi vmalls12e1is" : : );
+	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
@@ -72,7 +73,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	write_sysreg(kvm->arch.vttbr, vttbr_el2);
 	isb();
 
-	asm volatile("tlbi vmalle1" : : );
+	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
@@ -82,7 +83,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 void __hyp_text __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
-	asm volatile("tlbi alle1is	\n"
-		     "ic ialluis	  ": : );
+	__tlbi(alle1is);
+	asm volatile("ic ialluis" : : );
 	dsb(ish);
 }