[PATCH v2] KVM: arm64: Work around C1-Pro erratum 4193714 for protected guests

Wed May 6 06:37:41 PDT 2026

On Tue, May 05, 2026 at 05:52:03PM +0100, Catalin Marinas wrote:
> From: James Morse <james.morse at arm.com>
> 
> C1-Pro cores with SME have an erratum where TLBI+DSB does not complete
> all outstanding SME accesses. Instead a DSB needs to be executed on the
> affected CPUs. The implication is that pages cannot be unmapped from the
> host Stage 2 and then provided to a protected guest or to the
> hypervisor. Host SME accesses may still complete after this point.
> 
> This erratum breaks pKVM's guarantees, and the workaround is hard to
> implement as EL2 and EL1 share a security state meaning EL1 can mask
> IPIs sent by EL2, leading to interrupt blackouts.
> 
> Instead, do this in EL3. This has the advantage of a separate security
> state, meaning lower EL cannot mask the IPI. It is also simpler for EL3
> to know about CPUs that are off or in PSCI's CPU_SUSPEND.
> 
> Add the needed hook to host_stage2_set_owner_metadata_locked(). This
> covers the cases where the host loses access to a page:
> 
>   __pkvm_host_donate_guest()
>   __pkvm_guest_unshare_host()
>   host_stage2_set_owner_locked() when owner_id == PKVM_ID_HYP
> 
> Since pKVM relies on the firmware call for correctness, check for the
> firmware counterpart during protected KVM initialisation and fail the
> pKVM initialisation if it is missing.
> 
> Signed-off-by: James Morse <james.morse at arm.com>
> Co-developed-by: Catalin Marinas <catalin.marinas at arm.com>
> Signed-off-by: Catalin Marinas <catalin.marinas at arm.com>
> Cc: Mark Rutland <mark.rutland at arm.com>
> Cc: Marc Zyngier <maz at kernel.org>
> Cc: Oliver Upton <oupton at kernel.org>
> Cc: Will Deacon <will at kernel.org>
> Cc: Vincent Donnefort <vdonnefort at google.com>
> Cc: Lorenzo Pieralisi <lpieralisi at kernel.org>
> Cc: Sudeep Holla <sudeep.holla at kernel.org>
> ---
> 
> Added the kvm-arm list this time, missed it in v1.
> 
> Changelog below but it's only probing if the firmware counterpart is
> present and disable the hypervisor. If that's too harsh, we can leave it
> as a warning and maybe add a static label/flag to avoid the unnecessary
> SMC call on page donation.

As the pKVM upstream support is currently experimental and the protection
incomplete (see Documentation/virt/kvm/arm/pkvm.rst) perhaps a simple WARN() is
enough?

> 
> Changes:
> 
> v2:
> 
> (v1: https://lore.kernel.org/r/20260430155911.628402-1-catalin.marinas@arm.com)
> 
> - Add a check in init_hyp_mode() if KVM is running in protected mode and
>   refuse initialising the hypervisor if the firmware does not provide
>   the workaround counterpart
> - Add 'Co-developed-by: me'
> 
> v1:
> 
> (pre-7.1-rc: https://lore.kernel.org/r/20260323162408.4163113-6-catalin.marinas@arm.com)
> 
> - Move the hook to host_stage2_set_owner_metadata_locked()
> - Use hyp_smccc_1_1_smc()
> 
>  arch/arm64/kvm/arm.c                  | 21 +++++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c | 24 +++++++++++++++++++++++-
>  include/linux/arm-smccc.h             |  6 ++++++
>  3 files changed, 50 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 176cbe8baad3..51b6db45a54f 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -4,6 +4,7 @@
>   * Author: Christoffer Dall <c.dall at virtualopensystems.com>
>   */
>  
> +#include <linux/arm-smccc.h>
>  #include <linux/bug.h>
>  #include <linux/cpu_pm.h>
>  #include <linux/errno.h>
> @@ -2634,6 +2635,22 @@ static int init_pkvm_host_sve_state(void)
>  	return 0;
>  }
>  
> +static int pkvm_check_sme_dvmsync_fw_call(void)
> +{
> +	struct arm_smccc_res res;
> +
> +	if (!cpus_have_final_cap(ARM64_WORKAROUND_4193714))
> +		return 0;
> +
> +	arm_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res);
> +	if (res.a0) {
> +		kvm_err("pKVM requires firmware support for C1-Pro erratum 4193714\n");
> +		return -ENODEV;
> +	}
> +
> +	return 0;
> +}
> +
>  /*
>   * Finalizes the initialization of hyp mode, once everything else is initialized
>   * and the initialziation process cannot fail.
> @@ -2834,6 +2851,10 @@ static int __init init_hyp_mode(void)
>  		if (err)
>  			goto out_err;
>  
> +		err = pkvm_check_sme_dvmsync_fw_call();
> +		if (err)
> +			goto out_err;
> +
>  		err = kvm_hyp_init_protection(hyp_va_bits);
>  		if (err) {
>  			kvm_err("Failed to init hyp memory protection\n");
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 28a471d1927c..7d59faa99fee 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -5,6 +5,8 @@
>   */
>  
>  #include <linux/kvm_host.h>
> +#include <linux/arm-smccc.h>
> +

nit: probably not necessary with the nvhe/arm-smccc.h include below.

>  #include <asm/kvm_emulate.h>
>  #include <asm/kvm_hyp.h>
>  #include <asm/kvm_mmu.h>
> @@ -14,6 +16,7 @@
>  
>  #include <hyp/fault.h>
>  
> +#include <nvhe/arm-smccc.h>
>  #include <nvhe/gfp.h>
>  #include <nvhe/memory.h>
>  #include <nvhe/mem_protect.h>
> @@ -29,6 +32,19 @@ static struct hyp_pool host_s2_pool;
>  static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm);
>  #define current_vm (*this_cpu_ptr(&__current_vm))
>  
> +static void pkvm_sme_dvmsync_fw_call(void)
> +{
> +	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) {
> +		struct arm_smccc_res res;
> +
> +		/*
> +		 * Ignore the return value. Probing for the workaround
> +		 * availability took place in init_hyp_mode().
> +		 */
> +		hyp_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res);
> +	}
> +}
> +
>  static void guest_lock_component(struct pkvm_hyp_vm *vm)
>  {
>  	hyp_spin_lock(&vm->lock);
> @@ -574,8 +590,14 @@ static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size,
>  	ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
>  			      addr, size, &host_s2_pool,
>  			      KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation);
> -	if (!ret)
> +	if (!ret) {
> +		/*
> +		 * After stage2 maintenance has happened, but before the page
> +		 * owner has changed.
> +		 */
> +		pkvm_sme_dvmsync_fw_call();
>  		__host_update_page_state(addr, size, PKVM_NOPAGE);
> +	}
>  
>  	return ret;
>  }
> diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
> index 50b47eba7d01..e7195750d21b 100644
> --- a/include/linux/arm-smccc.h
> +++ b/include/linux/arm-smccc.h
> @@ -105,6 +105,12 @@
>  			   ARM_SMCCC_SMC_32,				\
>  			   0, 0x3fff)
>  
> +/* C1-Pro erratum 4193714: SME DVMSync early acknowledgement */
> +#define ARM_SMCCC_CPU_WORKAROUND_4193714				\
> +	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
> +			   ARM_SMCCC_SMC_32,				\
> +			   ARM_SMCCC_OWNER_CPU, 0x10)
> +
>  #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID				\
>  	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
>  			   ARM_SMCCC_SMC_32,				\