arm64/sve: KVM: Prevent guests from using SVE

Until KVM has full SVE support, guests must not be allowed to
execute SVE instructions.

This patch enables the necessary traps, and also ensures that the
traps are disabled again on exit from the guest so that the host
can still use SVE if it wants to.

On guest exit, high bits of the SVE Zn registers may have been
clobbered as a side-effect the execution of FPSIMD instructions in
the guest. The existing KVM host FPSIMD restore code is not
sufficient to restore these bits, so this patch explicitly marks
the CPU as not containing cached vector state for any task, thus
forcing a reload on the next return to userspace. This is an
interim measure, in advance of adding full SVE awareness to KVM.

This marking of cached vector state in the CPU as invalid is done
using __this_cpu_write(fpsimd_last_state, NULL) in fpsimd.c. Due
to the repeated use of this rather obscure operation, it makes
sense to factor it out as a separate helper with a clearer name.
This patch factors it out as fpsimd_flush_cpu_state(), and ports
all callers to use it.

As a side effect of this refactoring, a this_cpu_write() in
fpsimd_cpu_pm_notifier() is changed to __this_cpu_write(). This
should be fine, since cpu_pm_enter() is supposed to be called only
with interrupts disabled.

Signed-off-by: Dave Martin <[e-mail]>
Reviewed-by: Alex Bennée <[e-mail]>
Reviewed-by: Christoffer Dall <[e-mail]>
Acked-by: Catalin Marinas <[e-mail]>
Acked-by: Marc Zyngier <[e-mail]>
Cc: Ard Biesheuvel <[e-mail]>
Signed-off-by: Will Deacon <[e-mail]>

arch/arm/include/asm/kvm_host.h

···
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 
+/* All host FP/SIMD state is restored on guest exit, so nothing to save: */
+static inline void kvm_fpsimd_flush_cpu_state(void) {}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm64/include/asm/fpsimd.h

···
 extern void fpsimd_update_current_state(struct fpsimd_state *state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void sve_flush_cpu_state(void);
 
 /* Maximum VL that SVE VL-agnostic software can transparently support */
 #define SVE_VL_ARCH_MAX 0x100

arch/arm64/include/asm/kvm_arm.h

···
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
-#define CPTR_EL2_DEFAULT	0x000033ff
+#define CPTR_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 */
+#define CPTR_EL2_DEFAULT	CPTR_EL2_RES1
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TPMS		(1 << 14)
···
 
 #define CPACR_EL1_FPEN		(3 << 20)
 #define CPACR_EL1_TTA		(1 << 28)
+#define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
 
 #endif /* __ARM64_KVM_ARM_H__ */

arch/arm64/include/asm/kvm_host.h

···
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
···
 
 	WARN_ONCE(parange < 40,
 		  "PARange is %d bits, unsupported configuration!", parange);
+}
+
+/*
+ * All host FP/SIMD state is restored on guest exit, so nothing needs
+ * doing here except in the SVE case:
+*/
+static inline void kvm_fpsimd_flush_cpu_state(void)
+{
+	if (system_supports_sve())
+		sve_flush_cpu_state();
 }
 
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/kernel/fpsimd.c

···
 	t->thread.fpsimd_state.cpu = NR_CPUS;
 }
 
+static inline void fpsimd_flush_cpu_state(void)
+{
+	__this_cpu_write(fpsimd_last_state, NULL);
+}
+
+/*
+ * Invalidate any task SVE state currently held in this CPU's regs.
+ *
+ * This is used to prevent the kernel from trying to reuse SVE register data
+ * that is detroyed by KVM guest enter/exit.  This function should go away when
+ * KVM SVE support is implemented.  Don't use it for anything else.
+ */
+#ifdef CONFIG_ARM64_SVE
+void sve_flush_cpu_state(void)
+{
+	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
+	struct task_struct *tsk;
+
+	if (!fpstate)
+		return;
+
+	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
+	if (test_tsk_thread_flag(tsk, TIF_SVE))
+		fpsimd_flush_cpu_state();
+}
+#endif /* CONFIG_ARM64_SVE */
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
 DEFINE_PER_CPU(bool, kernel_neon_busy);
···
 	}
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
-	__this_cpu_write(fpsimd_last_state, NULL);
+	fpsimd_flush_cpu_state();
 
 	preempt_disable();
 
···
 	case CPU_PM_ENTER:
 		if (current->mm)
 			task_fpsimd_save();
-		this_cpu_write(fpsimd_last_state, NULL);
+		fpsimd_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)

arch/arm64/kvm/hyp/switch.c

···
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~CPACR_EL1_FPEN;
+	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__kvm_hyp_vector, vbar_el1);
···
 	u64 val;
 
 	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
 	write_sysreg(val, cptr_el2);
 }
 
···
 
 	write_sysreg(mdcr_el2, mdcr_el2);
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-	write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
+	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
 }
 

virt/kvm/arm/arm.c

···
 		 */
 		preempt_disable();
 
+		/* Flush FP/SIMD state that can't survive guest entry/exit */
+		kvm_fpsimd_flush_cpu_state();
+
 		kvm_pmu_flush_hwstate(vcpu);
 
 		kvm_timer_flush_hwstate(vcpu);