KVM: arm64: Eagerly switch ZCR_EL{1,2}

In non-protected KVM modes, while the guest FPSIMD/SVE/SME state is live on the
CPU, the host's active SVE VL may differ from the guest's maximum SVE VL:

* For VHE hosts, when a VM uses NV, ZCR_EL2 contains a value constrained
  by the guest hypervisor, which may be less than or equal to that
  guest's maximum VL.

  Note: in this case the value of ZCR_EL1 is immaterial due to E2H.

* For nVHE/hVHE hosts, ZCR_EL1 contains a value written by the guest,
  which may be less than or greater than the guest's maximum VL.

  Note: in this case hyp code traps host SVE usage and lazily restores
  ZCR_EL2 to the host's maximum VL, which may be greater than the
  guest's maximum VL.

This can be the case between exiting a guest and kvm_arch_vcpu_put_fp().
If a softirq is taken during this period and the softirq handler tries
to use kernel-mode NEON, then the kernel will fail to save the guest's
FPSIMD/SVE state, and will pend a SIGKILL for the current thread.

This happens because kvm_arch_vcpu_ctxsync_fp() binds the guest's live
FPSIMD/SVE state with the guest's maximum SVE VL, and
fpsimd_save_user_state() verifies that the live SVE VL is as expected
before attempting to save the register state:

| if (WARN_ON(sve_get_vl() != vl)) {
|         force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
|         return;
| }

Fix this and make this a bit easier to reason about by always eagerly
switching ZCR_EL{1,2} at hyp during guest<->host transitions. With this
happening, there's no need to trap host SVE usage, and the nVHE/nVHE
__deactivate_cptr_traps() logic can be simplified to enable host access
to all present FPSIMD/SVE/SME features.

In protected nVHE/hVHE modes, the host's state is always saved/restored
by hyp, and the guest's state is saved prior to exit to the host, so
from the host's PoV the guest never has live FPSIMD/SVE/SME state, and
the host's ZCR_EL1 is never clobbered by hyp.

Fixes: 8c8010d ("KVM: arm64: Save/restore SVE state for nVHE")
Fixes: 2e3cf82 ("KVM: arm64: nv: Ensure correct VL is loaded before saving SVE state")
Signed-off-by: Mark Rutland <[email protected]>
Reviewed-by: Mark Brown <[email protected]>
Tested-by: Mark Brown <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Fuad Tabba <[email protected]>
Cc: Marc Zyngier <[email protected]>
Cc: Oliver Upton <[email protected]>
Cc: Will Deacon <[email protected]>
Reviewed-by: Oliver Upton <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Marc Zyngier <[email protected]>

Author: mrutland-arm

arch/arm64/kvm/fpsimd.c

@@ -136,36 +136,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	local_irq_save(flags);
 
 	if (guest_owns_fp_regs()) {
-		if (vcpu_has_sve(vcpu)) {
-			u64 zcr = read_sysreg_el1(SYS_ZCR);
-
-			/*
-			 * If the vCPU is in the hyp context then ZCR_EL1 is
-			 * loaded with its vEL2 counterpart.
-			 */
-			__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
-
-			/*
-			 * Restore the VL that was saved when bound to the CPU,
-			 * which is the maximum VL for the guest. Because the
-			 * layout of the data when saving the sve state depends
-			 * on the VL, we need to use a consistent (i.e., the
-			 * maximum) VL.
-			 * Note that this means that at guest exit ZCR_EL1 is
-			 * not necessarily the same as on guest entry.
-			 *
-			 * ZCR_EL2 holds the guest hypervisor's VL when running
-			 * a nested guest, which could be smaller than the
-			 * max for the vCPU. Similar to above, we first need to
-			 * switch to a VL consistent with the layout of the
-			 * vCPU's SVE state. KVM support for NV implies VHE, so
-			 * using the ZCR_EL1 alias is safe.
-			 */
-			if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
-				sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
-						       SYS_ZCR_EL1);
-		}
-
 		/*
 		 * Flush (save and invalidate) the fpsimd/sve state so that if
 		 * the host tries to use fpsimd/sve, it's not using stale data

arch/arm64/kvm/hyp/entry.S

@@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN
 alternative_else_nop_endif
 	mrs	x1, isr_el1
 	cbz	x1,  1f
+
+	// Ensure that __guest_enter() always provides a context
+	// synchronization event so that callers don't need ISBs for anything
+	// that would usually be synchonized by the ERET.
+	isb
 	mov	x0, #ARM_EXCEPTION_IRQ
 	ret
 

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

@@ -375,6 +375,65 @@ static inline void __hyp_sve_save_host(void)
 			 true);
 }
 
+static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	u64 zcr_el1, zcr_el2;
+
+	if (!guest_owns_fp_regs())
+		return;
+
+	if (vcpu_has_sve(vcpu)) {
+		/* A guest hypervisor may restrict the effective max VL. */
+		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+			zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2);
+		else
+			zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+
+		write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+		zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu));
+		write_sysreg_el1(zcr_el1, SYS_ZCR);
+	}
+}
+
+static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	u64 zcr_el1, zcr_el2;
+
+	if (!guest_owns_fp_regs())
+		return;
+
+	/*
+	 * When the guest owns the FP regs, we know that guest+hyp traps for
+	 * any FPSIMD/SVE/SME features exposed to the guest have been disabled
+	 * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
+	 * prior to __guest_entry(). As __guest_entry() guarantees a context
+	 * synchronization event, we don't need an ISB here to avoid taking
+	 * traps for anything that was exposed to the guest.
+	 */
+	if (vcpu_has_sve(vcpu)) {
+		zcr_el1 = read_sysreg_el1(SYS_ZCR);
+		__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
+
+		/*
+		 * The guest's state is always saved using the guest's max VL.
+		 * Ensure that the host has the guest's max VL active such that
+		 * the host can save the guest's state lazily, but don't
+		 * artificially restrict the host to the guest's max VL.
+		 */
+		if (has_vhe()) {
+			zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+			write_sysreg_el2(zcr_el2, SYS_ZCR);
+		} else {
+			zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1;
+			write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+			zcr_el1 = vcpu_sve_max_vq(vcpu) - 1;
+			write_sysreg_el1(zcr_el1, SYS_ZCR);
+		}
+	}
+}
+
 static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 {
 	/*

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -5,6 +5,7 @@
  */
 
 #include <hyp/adjust_pc.h>
+#include <hyp/switch.h>
 
 #include <asm/pgtable-types.h>
 #include <asm/kvm_asm.h>
@@ -224,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 
 		sync_hyp_vcpu(hyp_vcpu);
 	} else {
+		struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu);
+
 		/* The host is fully trusted, run its vCPU directly. */
-		ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
+		fpsimd_lazy_switch_to_guest(vcpu);
+		ret = __kvm_vcpu_run(vcpu);
+		fpsimd_lazy_switch_to_host(vcpu);
 	}
 out:
 	cpu_reg(host_ctxt, 1) =  ret;
@@ -675,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 	case ESR_ELx_EC_SMC64:
 		handle_host_smc(host_ctxt);
 		break;
-	case ESR_ELx_EC_SVE:
-		cpacr_clear_set(0, CPACR_EL1_ZEN);
-		isb();
-		sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1,
-				       SYS_ZCR_EL2);
-		break;
 	case ESR_ELx_EC_IABT_LOW:
 	case ESR_ELx_EC_DABT_LOW:
 		handle_host_mem_abort(host_ctxt);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -73,12 +73,10 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 
 static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-
 	if (has_hvhe()) {
 		u64 val = CPACR_EL1_FPEN;
 
-		if (!kvm_has_sve(kvm) || !guest_owns_fp_regs())
+		if (cpus_have_final_cap(ARM64_SVE))
 			val |= CPACR_EL1_ZEN;
 		if (cpus_have_final_cap(ARM64_SME))
 			val |= CPACR_EL1_SMEN;
@@ -87,7 +85,7 @@ static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
 	} else {
 		u64 val = CPTR_NVHE_EL2_RES1;
 
-		if (kvm_has_sve(kvm) && guest_owns_fp_regs())
+		if (!cpus_have_final_cap(ARM64_SVE))
 			val |= CPTR_EL2_TZ;
 		if (!cpus_have_final_cap(ARM64_SME))
 			val |= CPTR_EL2_TSM;

arch/arm64/kvm/hyp/vhe/switch.c

@@ -579,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	sysreg_save_host_state_vhe(host_ctxt);
 
+	fpsimd_lazy_switch_to_guest(vcpu);
+
 	/*
 	 * Note that ARM erratum 1165522 requires us to configure both stage 1
 	 * and stage 2 translation for the guest context before we clear
@@ -603,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps(vcpu);
 
+	fpsimd_lazy_switch_to_host(vcpu);
+
 	sysreg_restore_host_state_vhe(host_ctxt);
 
 	if (guest_owns_fp_regs())