[PATCH v14 24/44] KVM: arm64: Handle realm MMIO emulation

[Gavin Shan]

Hi Steve,

On 5/13/26 11:17 PM, Steven Price wrote:
> MMIO emulation for a realm cannot be done directly with the VM's
> registers as they are protected from the host. However, for emulatable
> data aborts, the RMM uses GPRS[0] to provide the read/written value.
> We can transfer this from/to the equivalent VCPU's register entry and
> then depend on the generic MMIO handling code in KVM.
> 
> For a MMIO read, the value is placed in the shared RecExit structure
> during kvm_handle_mmio_return() rather than in the VCPU's register
> entry.
> 
> Signed-off-by: Steven Price <steven.price at arm.com>
> Reviewed-by: Gavin Shan <gshan at redhat.com>
> Reviewed-by: Suzuki K Poulose <suzuki.poulose at arm.com>
> ---
> Changes since v7:
>   * New comment for rec_exit_sync_dabt() explaining the call to
>     vcpu_set_reg().
> Changes since v5:
>   * Inject SEA to the guest is an emulatable MMIO access triggers a data
>     abort.
>   * kvm_handle_mmio_return() - disable kvm_incr_pc() for a REC (as the PC
>     isn't under the host's control) and move the REC_ENTER_EMULATED_MMIO
>     flag setting to this location (as that tells the RMM to skip the
>     instruction).
> ---
>   arch/arm64/kvm/inject_fault.c |  4 +++-
>   arch/arm64/kvm/mmio.c         | 16 ++++++++++++----
>   arch/arm64/kvm/rmi-exit.c     | 14 ++++++++++++++
>   3 files changed, 29 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
> index 89982bd3345f..6492397b73d7 100644
> --- a/arch/arm64/kvm/inject_fault.c
> +++ b/arch/arm64/kvm/inject_fault.c
> @@ -228,7 +228,9 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
>   
>   static void __kvm_inject_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr)
>   {
> -	if (vcpu_el1_is_32bit(vcpu))
> +	if (unlikely(vcpu_is_rec(vcpu)))
> +		vcpu->arch.rec.run->enter.flags |= REC_ENTER_FLAG_INJECT_SEA;
> +	else if (vcpu_el1_is_32bit(vcpu))
>   		inject_abt32(vcpu, iabt, addr);
>   	else
>   		inject_abt64(vcpu, iabt, addr);
> diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
> index e2285ed8c91d..6a8cb927fcca 100644
> --- a/arch/arm64/kvm/mmio.c
> +++ b/arch/arm64/kvm/mmio.c
> @@ -6,6 +6,7 @@
>   
>   #include <linux/kvm_host.h>
>   #include <asm/kvm_emulate.h>
> +#include <asm/rmi_smc.h>
>   #include <trace/events/kvm.h>
>   
>   #include "trace.h"
> @@ -138,14 +139,21 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
>   		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
>   			       &data);
>   		data = vcpu_data_host_to_guest(vcpu, data, len);
> -		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
> +
> +		if (vcpu_is_rec(vcpu))
> +			vcpu->arch.rec.run->enter.gprs[0] = data;
> +		else
> +			vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
>   	}
>   
>   	/*
>   	 * The MMIO instruction is emulated and should not be re-executed
>   	 * in the guest.
>   	 */
> -	kvm_incr_pc(vcpu);
> +	if (vcpu_is_rec(vcpu))
> +		vcpu->arch.rec.run->enter.flags |= REC_ENTER_FLAG_EMULATED_MMIO;
> +	else
> +		kvm_incr_pc(vcpu);
>   
>   	return 1;
>   }
> @@ -167,14 +175,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
>   	 * No valid syndrome? Ask userspace for help if it has
>   	 * volunteered to do so, and bail out otherwise.
>   	 *
> -	 * In the protected VM case, there isn't much userspace can do
> +	 * In the protected/realm VM case, there isn't much userspace can do
>   	 * though, so directly deliver an exception to the guest.
>   	 */
>   	if (!kvm_vcpu_dabt_isvalid(vcpu)) {
>   		trace_kvm_mmio_nisv(*vcpu_pc(vcpu), esr,
>   				    kvm_vcpu_get_hfar(vcpu), fault_ipa);
>   
> -		if (vcpu_is_protected(vcpu))
> +		if (vcpu_is_protected(vcpu) || vcpu_is_rec(vcpu))
>   			return kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
>   
>   		if (test_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER,
> diff --git a/arch/arm64/kvm/rmi-exit.c b/arch/arm64/kvm/rmi-exit.c
> index e7c51b6cf6ce..8ec0d179eba2 100644
> --- a/arch/arm64/kvm/rmi-exit.c
> +++ b/arch/arm64/kvm/rmi-exit.c
> @@ -25,6 +25,20 @@ static int rec_exit_reason_notimpl(struct kvm_vcpu *vcpu)
>   
>   static int rec_exit_sync_dabt(struct kvm_vcpu *vcpu)
>   {
> +	struct realm_rec *rec = &vcpu->arch.rec;
> +
> +	/*
> +	 * In the case of a write, copy over gprs[0] to the target GPR,
> +	 * preparing to handle MMIO write fault. The content to be written has
> +	 * been saved to gprs[0] by the RMM (even if another register was used
> +	 * by the guest). In the case of normal memory access this is redundant
> +	 * (the guest will replay the instruction), but the overhead is
> +	 * minimal.
> +	 */
> +	if (kvm_vcpu_dabt_iswrite(vcpu) && kvm_vcpu_dabt_isvalid(vcpu))
> +		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu),
> +			     rec->run->exit.gprs[0]);
> +

{ } is needed here.

>   	return kvm_handle_guest_abort(vcpu);
>   }
>   

Thanks,
Gavin