[PATCH v2 03/13] KVM: arm64: Support host MMIO trap handlers for unmapped devices
Fuad Tabba
fuad.tabba at linux.dev
Thu Sep 10 07:46:55 PDT 2026
Hi Seb,
On Fri, 7 Aug 2026 at 17:43, Sebastian Ene <sebastianene at google.com> wrote:
>
> Hook a handler to the host mem abort so that the hypervisor can
> intercept host accesses to unmapped memory regions.
> When a Stage-2 fault occurs on a registered device region, the
> hypervisor will look if there is any registered function that
> can handle the access. On the back of this, mediate host accesses
> to devices and emulate them in pKVM.
>
> Signed-off-by: Sebastian Ene <sebastianene at google.com>
> Signed-off-by: Bartłomiej Grzesik <bgrzesik at google.com>
Is this co-authored by Bartłomiej, or a stray tag?
> ---
> arch/arm64/include/asm/kvm_arm.h | 2 ++
> arch/arm64/include/asm/kvm_pkvm.h | 4 +++
> arch/arm64/kvm/hyp/nvhe/mem_protect.c | 49 +++++++++++++++++++++++++++
> arch/arm64/kvm/hyp/nvhe/setup.c | 3 ++
> 4 files changed, 58 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
> index 3f9233b5a130..6360c90f9855 100644
> --- a/arch/arm64/include/asm/kvm_arm.h
> +++ b/arch/arm64/include/asm/kvm_arm.h
> @@ -304,6 +304,8 @@
>
> /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
> #define HPFAR_MASK (~UL(0xf))
> +#define FAR_MASK GENMASK_ULL(11, 0)
FAR_TO_FIPA_OFFSET() a few lines further down is the same mask, and
mem_protect.c already uses it.
> +
> /*
> * We have
> * PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12]
> diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
> index ab26bec079d6..0a471564be00 100644
> --- a/arch/arm64/include/asm/kvm_pkvm.h
> +++ b/arch/arm64/include/asm/kvm_pkvm.h
> @@ -20,9 +20,13 @@
> /* The maximum number of hypervisor protected regions from the host */
> #define PKVM_PROTECTED_REGS_NUM 8
>
> +struct pkvm_protected_reg;
> +typedef void(pkvm_emulate_handler)(struct pkvm_protected_reg *region, u64 offset,
> + bool write, u64 *reg, u8 reg_size);
> struct pkvm_protected_reg {
> u64 pfn;
> u64 nr_pages;
> + pkvm_emulate_handler *cb;
> };
>
> extern struct pkvm_protected_reg kvm_nvhe_sym(pkvm_protected_regs)[];
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 500c18c2fd48..7e978e0c44b9 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -14,6 +14,7 @@
> #include <asm/stage2_pgtable.h>
>
> #include <hyp/fault.h>
> +#include <hyp/adjust_pc.h>
>
> #include <nvhe/arm-smccc.h>
> #include <nvhe/gfp.h>
> @@ -752,6 +753,50 @@ static void host_inject_mem_abort(struct kvm_cpu_context *host_ctxt)
> inject_host_exception(esr);
> }
>
> +static bool handle_host_mmio_trap(struct kvm_cpu_context *host_ctxt, u64 esr, u64 addr)
> +{
> + u64 offset, reg_value = 0, start, end;
> + u8 reg_size, reg_index;
> + bool write;
> + int i;
> +
> + for (i = 0; i < num_protected_reg; i++) {
> + if (!pkvm_protected_regs[i].pfn || !pkvm_protected_regs[i].nr_pages ||
> + !pkvm_protected_regs[i].cb)
> + continue;
> +
> + start = PFN_PHYS(pkvm_protected_regs[i].pfn);
> + end = start + PFN_PHYS(pkvm_protected_regs[i].nr_pages);
> + reg_size = BIT((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
> +
> + if (start > addr || addr + reg_size > end)
> + continue;
> +
> + reg_index = (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
> + write = (esr & ESR_ELx_WNR) == ESR_ELx_WNR;
> + offset = addr - start;
> +
> + if (write && reg_index != 31)
> + reg_value = host_ctxt->regs.regs[reg_index];
> +
> + pkvm_protected_regs[i].cb(&pkvm_protected_regs[i], offset, write,
> + ®_value, reg_size);
> +
> + if (!write && reg_index != 31)
> + host_ctxt->regs.regs[reg_index] = reg_value;
> +
> + kvm_skip_host_instr();
> + return true;
The callback returns void, so a rejection can't reach this code, and
both of the lines below it run anyway. On a read the host gets
reg_value, still the 0 it was initialised to, and the instruction is
skipped either way.
The later patches use the same callback, and their rejections are bare
returns: cwriter_write() drops a command that process_cmd() rejects,
ctlr_write() drops a GITS_CTLR enable, baser_write() drops a layout
change. That's invisible to the host, and to a test.
Could the callback return bool, and this return false on a rejection?
handle_host_mem_abort() then falls into host_stage2_idmap(), which
returns -EPERM for a donated page, so the case there already injects
the abort.
Cheers,
/fuad
> + }
> +
> + return false;
> +}
> +
> +static bool is_dabt(u64 esr)
> +{
> + return (ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_LOW) && (esr & ESR_ELx_ISV);
> +}
> +
> void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
> {
> struct kvm_vcpu_fault_info fault;
> @@ -774,6 +819,10 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
> BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
> addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
>
> + if (is_dabt(esr) && !addr_is_memory(addr) &&
> + handle_host_mmio_trap(host_ctxt, esr, addr | (fault.far_el2 & FAR_MASK)))
> + return;
> +
> switch (host_stage2_idmap(addr)) {
> case -EPERM:
> host_inject_mem_abort(host_ctxt);
> diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
> index 64c0290da888..4395595b7f7e 100644
> --- a/arch/arm64/kvm/hyp/nvhe/setup.c
> +++ b/arch/arm64/kvm/hyp/nvhe/setup.c
> @@ -294,6 +294,9 @@ static int donate_protected_mmio_regions(void)
> pkvm_protected_regs[i].nr_pages << PAGE_SHIFT);
> if (ret)
> goto err_setup;
> +
> + if (pkvm_protected_regs[i].cb)
> + pkvm_protected_regs[i].cb = kern_hyp_va(pkvm_protected_regs[i].cb);
> }
>
> return 0;
> --
> 2.55.0.654.g21b8a5bc05-goog
>
More information about the linux-arm-kernel
mailing list