Re: [PATCH v4 5/6] KVM: arm64: Add HDBSS fault handling and buffer flush

[Tian Zheng <zhengtian10@huawei.com>]

On 7/14/2026 10:19 PM, Leonardo Bras wrote:
> On Tue, Jul 14, 2026 at 09:27:15PM +0800, Tian Zheng wrote:
>> On 7/14/2026 6:50 PM, Leonardo Bras wrote:
>>> On Tue, Jul 14, 2026 at 03:38:39PM +0800, Tian Zheng wrote:
>>>> On 7/13/2026 10:06 PM, Leonardo Bras wrote:
>>>>> On Thu, Jul 09, 2026 at 06:40:25PM +0800, Tian Zheng wrote:
>>>>>> From: eillon <yezhenyu2@huawei.com>
>>>>>>
>>>>>> Add HDBSS fault handling for buffer full, external abort, and general
>>>>>> protection fault (GPF) events. When the HDBSS buffer becomes full,
>>>>>> the hardware traps to EL2 with an HDBSSF event, which is handled by
>>>>>> setting a flush request.
>>>>>>
>>>>>> Add kvm_flush_hdbss_buffer() to consume HDBSS buffer entries and
>>>>>> propagate dirty information into the userspace-visible dirty bitmap.
>>>>>> Flush is triggered on vcpu_put, check_vcpu_requests, and
>>>>>> sync_dirty_log.
>>>>>>
>>>>>> Add esr_iss2_is_hdbssf() helper for HDBSS fault detection in guest
>>>>>> abort handling.
>>>>>>
>>>>>> Signed-off-by: Eillon <yezhenyu2@huawei.com>
>>>>>> Signed-off-by: Tian Zheng <zhengtian10@huawei.com>
>>>>>> ---
>>>>>>     arch/arm64/include/asm/esr.h           |  5 +++
>>>>>>     arch/arm64/include/asm/kvm_dirty_bit.h | 11 +++++
>>>>>>     arch/arm64/include/asm/kvm_host.h      |  1 +
>>>>>>     arch/arm64/kvm/arm.c                   | 14 ++++++
>>>>>>     arch/arm64/kvm/dirty_bit.c             | 62 ++++++++++++++++++++++++++
>>>>>>     arch/arm64/kvm/mmu.c                   |  4 ++
>>>>>>     6 files changed, 97 insertions(+)
>>>>>>
>>>>>> diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
>>>>>> index 81c17320a588..2e6b679b5908 100644
>>>>>> --- a/arch/arm64/include/asm/esr.h
>>>>>> +++ b/arch/arm64/include/asm/esr.h
>>>>>> @@ -437,6 +437,11 @@
>>>>>>     #ifndef __ASSEMBLER__
>>>>>>     #include <asm/types.h>
>>>>>>
>>>>>> +static inline bool esr_iss2_is_hdbssf(unsigned long esr)
>>>>>> +{
>>>>>> +	return ESR_ELx_ISS2(esr) & ESR_ELx_HDBSSF;
>>>>> This will return a long, which will be casted as bool.
>>>>> In general, what I see in the kernel is something like:
>>>>>
>>>>> 	return !!(ESR_ELx_ISS2(esr) & ESR_ELx_HDBSSF)
>>>> ok!
>>>>
>>>>
>>>>>> +}
>>>>>> +
>>>>>>     static inline unsigned long esr_brk_comment(unsigned long esr)
>>>>>>     {
>>>>>>     	return esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
>>>>>> diff --git a/arch/arm64/include/asm/kvm_dirty_bit.h b/arch/arm64/include/asm/kvm_dirty_bit.h
>>>>>> index 84b12f0a10af..4b28000e972f 100644
>>>>>> --- a/arch/arm64/include/asm/kvm_dirty_bit.h
>>>>>> +++ b/arch/arm64/include/asm/kvm_dirty_bit.h
>>>>>> @@ -10,7 +10,18 @@
>>>>>>     #include <asm/kvm_pgtable.h>
>>>>>>     #include <asm/sysreg.h>
>>>>>>
>>>>>> +/* HDBSS entry field definitions */
>>>>>> +#define HDBSS_ENTRY_VALID	BIT(0)
>>>>>> +#define HDBSS_ENTRY_TTWL_SHIFT (1)
>>>>>> +#define HDBSS_ENTRY_TTWL_MASK (GENMASK(3, 1))
>>>>>> +#define HDBSS_ENTRY_TTWL(x) \
>>>>>> +	(((x) << HDBSS_ENTRY_TTWL_SHIFT) & HDBSS_ENTRY_TTWL_MASK)
>>>>>> +#define HDBSS_ENTRY_TTWL_RESV HDBSS_ENTRY_TTWL(-4)
>>>>>> +#define HDBSS_ENTRY_IPA	GENMASK_ULL(55, 12)
>>>>>> +
>>>>>>     int kvm_arm_vcpu_alloc_hdbss(struct kvm_vcpu *vcpu, unsigned int order);
>>>>>>     void kvm_arm_vcpu_free_hdbss(struct kvm_vcpu *vcpu);
>>>>>> +void kvm_flush_hdbss_buffer(struct kvm_vcpu *vcpu);
>>>>>> +int kvm_handle_hdbss_fault(struct kvm_vcpu *vcpu);
>>>>>>
>>>>>>     #endif /* __ARM64_KVM_DIRTY_BIT_H__ */
>>>>>> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
>>>>>> index c41ec6d9c45a..cecfb884a64f 100644
>>>>>> --- a/arch/arm64/include/asm/kvm_host.h
>>>>>> +++ b/arch/arm64/include/asm/kvm_host.h
>>>>>> @@ -55,6 +55,7 @@
>>>>>>     #define KVM_REQ_GUEST_HYP_IRQ_PENDING	KVM_ARCH_REQ(9)
>>>>>>     #define KVM_REQ_MAP_L1_VNCR_EL2		KVM_ARCH_REQ(10)
>>>>>>     #define KVM_REQ_VGIC_PROCESS_UPDATE	KVM_ARCH_REQ(11)
>>>>>> +#define KVM_REQ_FLUSH_HDBSS			KVM_ARCH_REQ(12)
>>>>>>
>>>>>>     #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
>>>>>>     				     KVM_DIRTY_LOG_INITIALLY_SET)
>>>>>> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
>>>>>> index bf6688245d83..566953a4e23a 100644
>>>>>> --- a/arch/arm64/kvm/arm.c
>>>>>> +++ b/arch/arm64/kvm/arm.c
>>>>>> @@ -755,6 +755,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>>>>>>     		kvm_vcpu_put_hw_mmu(vcpu);
>>>>>>     	kvm_arm_vmid_clear_active();
>>>>>>
>>>>>> +	if (vcpu->kvm->arch.enable_hdbss)
>>>>>> +		kvm_flush_hdbss_buffer(vcpu);
>>>>>> +
>>>>>>     	vcpu_clear_on_unsupported_cpu(vcpu);
>>>>>>     	vcpu->cpu = -1;
>>>>>>     }
>>>>>> @@ -1157,6 +1160,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
>>>>>>     		if (kvm_dirty_ring_check_request(vcpu))
>>>>>>     			return 0;
>>>>>>
>>>>>> +		if (kvm_check_request(KVM_REQ_FLUSH_HDBSS, vcpu))
>>>>>> +			kvm_flush_hdbss_buffer(vcpu);
>>>>>> +
>>>>>>     		check_nested_vcpu_requests(vcpu);
>>>>>>     	}
>>>>>>
>>>>>> @@ -1971,7 +1977,15 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl,
>>>>>>
>>>>>>     void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
>>>>>>     {
>>>>>> +	/*
>>>>>> +	 * Flush all CPUs' dirty log buffers to the dirty_bitmap.  Called
>>>>>> +	 * before reporting dirty_bitmap to userspace. Send a request with
>>>>>> +	 * KVM_REQUEST_WAIT to flush buffer synchronously.
>>>>>> +	 */
>>>>>> +	if (!kvm->arch.enable_hdbss)
>>>>>> +		return;
>>>>>>
>>>>>> +	kvm_make_all_cpus_request(kvm, KVM_REQ_FLUSH_HDBSS | KVM_REQUEST_WAIT);
>>>>>>     }
>>>>>>
>>>>>>     static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
>>>>>> diff --git a/arch/arm64/kvm/dirty_bit.c b/arch/arm64/kvm/dirty_bit.c
>>>>>> index 6c7a6ef66b5a..002366337637 100644
>>>>>> --- a/arch/arm64/kvm/dirty_bit.c
>>>>>> +++ b/arch/arm64/kvm/dirty_bit.c
>>>>>> @@ -50,3 +50,65 @@ void kvm_arm_vcpu_free_hdbss(struct kvm_vcpu *vcpu)
>>>>>>
>>>>>>     	vcpu->arch.hdbss.hdbssbr_el2 = 0;
>>>>>>     }
>>>>>> +
>>>>>> +void kvm_flush_hdbss_buffer(struct kvm_vcpu *vcpu)
>>>>>> +{
>>>>>> +	int idx, curr_idx;
>>>>>> +	u64 *hdbss_buf;
>>>>>> +	struct kvm *kvm = vcpu->kvm;
>>>>>> +
>>>>>> +	if (!kvm->arch.enable_hdbss)
>>>>>> +		return;
>>>>>> +
>>>>>> +	curr_idx = HDBSSPROD_IDX(read_sysreg_s(SYS_HDBSSPROD_EL2));
>>>>>> +
>>>>>> +	/* Do nothing if HDBSS buffer is empty or br_el2 is NULL */
>>>>>> +	if (curr_idx == 0 || vcpu->arch.hdbss.hdbssbr_el2 == 0)
>>>>>> +		return;
>>>>>> +
>>>>>> +	hdbss_buf = page_address(phys_to_page(vcpu->arch.hdbss.base_phys));
>>>>>> +	if (!hdbss_buf)
>>>>>> +		return;
>>>>>> +
>>>>>> +	guard(write_lock_irqsave)(&vcpu->kvm->mmu_lock);
>>>>>> +	for (idx = 0; idx < curr_idx; idx++) {
>>>>>> +		u64 gpa;
>>>>>> +
>>>>>> +		gpa = hdbss_buf[idx];
>>>>>> +		if (!(gpa & HDBSS_ENTRY_VALID))
>>>>>> +			continue;
>>>>>> +
>>>>>> +		gpa &= HDBSS_ENTRY_IPA;
>>>>>> +		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
>>>>> You mention that it does not support dirty-ring, but above function will
>>>>> mark the page as dirty in the dirty-ring :/
>>>>>
>>>> In kvm_arm_enable_hdbss_global(), we explicitly check and reject HDBSS
>>>> enablement if dirty-ring is active:
>>>>
>>>> ```
>>>> if (kvm->dirty_ring_size)
>>>>       return 0;
>>>> ```
>>>>
>>>> So when kvm_flush_hdbss_buffer() runs (which requires enable_hdbss = true),
>>>> we know for certain that
>>>>
>>>> kvm->dirty_ring_size == 0. Therefore, kvm_vcpu_mark_page_dirty() will always
>>>> take the dirty_bitmap path,
>>>>
>>>> never the dirty-ring path.
>>>>
>>>> That said, I'll add a comment in kvm_flush_hdbss_buffer() before dirty ring
>>>> mode is supported, to make this explicit:
>>>>
>>>> ```
>>>> /*
>>>>    * HDBSS is mutually exclusive with dirty-ring mode (see
>>>>    * kvm_arm_enable_hdbss_global()), so kvm_vcpu_mark_page_dirty()
>>>>    * will update the dirty_bitmap, not the dirty-ring.
>>>>    */
>>>> ```
>>>>
>>> Got it :)
>>>
>>> Out of curiosity: which issues have you found on supporting dirty-ring at
>>> this point?
>>>
>>> Thanks!
>>> Leo
>>
>> I haven't looked deeply into dirty-ring yet — my main concern is that if
>> both the dirty
>>
>> ring and HDBSS buffer fill up, the flush path might get blocked or
>> complicated.
>>
>> For now, I'm planning to match the HDBSS buffer size to the dirty ring size
>> in v5 and test it.
>>
>> Ideally, the two buffers would be the same size, and the entire dirty
>> tracking path would use
>>
> Ah, I see the point.
>
> IIRC, when dirty-ring gets full, the kernel returns to userspace with
> run->exit_reason == KVM_EXIT_DIRTY_RING_FULL, which will warn the VMM to
> drain the dirty-ring, and that makes space for us draining HDBSS to the
> dirty-ring again.
>
> The best way to achieve that, as I remember, is to always drain
> HDBSS as much as possible at guest_exitting. That will make more space to
> newer HDBSS entries, and we can get userspace to drain the dirty-ring
> earlier.
>
> I would say to even make HDBSS buffer half (entries) the dirty-ring. Then
> we can generally fully drain to the dirty-ring and even report ring full
> if the ring is above a given threshold percentage full.
>   
>> HDBSS exclusively — no fallback to the legacy dirty bitmap path. If that
>> works, I think this approach should be fine.
>>
>> Let me know if you have any insights on dirty ring's full-buffer behavior —
>> that would be helpful.
>>
>>
> Will do!
>
> Thanks!
> Leo


Thanks for the insights — reusing PML's reservation mechanism makes sense.

I think we can*keep the HDBSS buffer at 512 entries* (matching 
PML_LOG_NR_ENTRIES)

for now, and *not expose any ioctl for userspace to configure it*. Since 
the kernel

auto-enables HDBSS, a userspace size knob would be confusing.


The reservation logic would be:

- Implement kvm_cpu_dirty_log_size() on arm64 to return the HDBSS buffer 
entry

count (512, or 0 if HDBSS is not enabled)

- Reuse kvm_dirty_ring_get_rsvd_entries() to reserve space for one full 
flush:

KVM_DIRTY_RING_RSVD_ENTRIES + hdbss_entries

- So soft_limit = dirty_ring_size - (KVM_DIRTY_RING_RSVD_ENTRIES + 
hdbss_entries),

guaranteeing a full flush always fits

kvm_flush_hdbss_buffer() at guest_exit pushes via 
mark_page_dirty_in_slot() ->

kvm_dirty_ring_push() -> kvm_dirty_ring_soft_full, which triggers

KVM_EXIT_DIRTY_RING_FULL when needed.

If soft_limit is hit, KVM_REQ_DIRTY_RING_FULL is set and the next 
vcpu_run exits

to userspace for QEMU to drain the ring.

*One more thing: *when userspace sets the dirty ring size via

KVM_VM_IOCTL_ENABLE_DIRTY_LOG_RING, we already enforce that

size >= kvm_dirty_ring_get_rsvd_entries(kvm) * sizeof(struct kvm_dirty_gfn)

or size < PAGE_SIZE. With HDBSS, kvm_dirty_ring_get_rsvd_entries() will 
include the

HDBSS entries via kvm_cpu_dirty_log_size(), so the same check will 
automatically guarantee

the ring is large enough to accommodate the HDBSS buffer. No additional 
validation is needed.

Thanks,
Tian