[PATCH v4 4/6] KVM: arm64: Add HDBSS per-vCPU buffer management
Tian Zheng
zhengtian10 at huawei.com
Tue Jul 14 00:15:03 PDT 2026
On 7/13/2026 9:39 PM, Leonardo Bras wrote:
> On Thu, Jul 09, 2026 at 06:40:24PM +0800, Tian Zheng wrote:
>> From: eillon <yezhenyu2 at huawei.com>
>>
>> Add HDBSS (Hardware Dirty Bit State Structure) per-vCPU buffer
>> management including allocation, freeing, and loading of HDBSS
>> registers during vCPU load.
>>
>> This patch creates the foundational infrastructure:
>> - struct vcpu_hdbss_state and enable_hdbss/hdbss_order in kvm_arch
>> - kvm_dirty_bit.h header with alloc/free declarations
>> - dirty_bit.c with alloc/free helpers
>> - __load_hdbss() in VHE switch for register loading
>> - vCPU create/destroy hooks for buffer lifecycle
>> - sysreg definitions for HDBSS register manipulation
>> - Makefile update for dirty_bit.o
>>
>> Signed-off-by: Eillon <yezhenyu2 at huawei.com>
>> Signed-off-by: Tian Zheng <zhengtian10 at huawei.com>
>> ---
>> arch/arm64/include/asm/kvm_dirty_bit.h | 16 ++++++++
>> arch/arm64/include/asm/kvm_host.h | 13 +++++++
>> arch/arm64/include/asm/sysreg.h | 11 ++++++
>> arch/arm64/kvm/Makefile | 1 +
>> arch/arm64/kvm/arm.c | 7 ++++
>> arch/arm64/kvm/dirty_bit.c | 52 ++++++++++++++++++++++++++
>> arch/arm64/kvm/hyp/vhe/switch.c | 15 ++++++++
>> arch/arm64/kvm/mmu.c | 1 +
>> arch/arm64/kvm/reset.c | 4 ++
>> 9 files changed, 120 insertions(+)
>> create mode 100644 arch/arm64/include/asm/kvm_dirty_bit.h
>> create mode 100644 arch/arm64/kvm/dirty_bit.c
>>
>> diff --git a/arch/arm64/include/asm/kvm_dirty_bit.h b/arch/arm64/include/asm/kvm_dirty_bit.h
>> new file mode 100644
>> index 000000000000..84b12f0a10af
>> --- /dev/null
>> +++ b/arch/arm64/include/asm/kvm_dirty_bit.h
>> @@ -0,0 +1,16 @@
>> +/* SPDX-License-Identifier: GPL-2.0-only */
>> +/*
>> + * Copyright (C) 2026 ARM Ltd.
>> + * Author: Leonardo Bras <leo.bras at arm.com>
> You are adding the file, so the copyright note should be yours, then?
I originally thought your earlier patchset had already created this
file, so I
kept your copyright and author info. I'll update it to mine in the next
version.
Thanks for pointing that out!
>
>> + */
>> +
>> +#ifndef __ARM64_KVM_DIRTY_BIT_H__
>> +#define __ARM64_KVM_DIRTY_BIT_H__
>> +
>> +#include <asm/kvm_pgtable.h>
>> +#include <asm/sysreg.h>
>> +
>> +int kvm_arm_vcpu_alloc_hdbss(struct kvm_vcpu *vcpu, unsigned int order);
>> +void kvm_arm_vcpu_free_hdbss(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 bae2c4f92ef5..c41ec6d9c45a 100644
>> --- a/arch/arm64/include/asm/kvm_host.h
>> +++ b/arch/arm64/include/asm/kvm_host.h
>> @@ -420,6 +420,10 @@ struct kvm_arch {
>> */
>> struct kvm_protected_vm pkvm;
>>
>> + /* HDBSS: per-VM dirty tracking state */
>> + bool enable_hdbss;
> Is there not a way of checking hdbss without adding this new member on the
> struct? Would not checking the vcpu_hdbss_state from current vcpu should be
> enough?
HDBSS is a VM-wide property, so I currently use a VM-level flag
(kvm->arch.enable_hdbss)
to track whether it's enabled. Paths like
kvm_arch_commit_memory_region() and VM teardown
don't have a vCPU context to query, so per-vCPU state wouldn't work there.
But you're right, maybe we don't need a value to store it — we could
remove this flag and instead
check the VTCR_EL2_HDBSS bit directly from kvm->arch.mmu.vtcr:
```
static inline bool kvm_hdbss_enabled(const struct kvm *kvm)
{
return kvm->arch.mmu.vtcr & VTCR_EL2_HDBSS;
}
if (kvm_hdbss_enabled(kvm))
...
```
>
>> + unsigned int hdbss_order;
> Is that the order for hdbss buffer size?
> Haven't finished reading the series, but would that be bad if this was also
> in the per-vcpu state struct, instead?
>
> Also, here I suggest that we save a number, instead of the encoding for
> HDBSSBR_ELS_SZ, and convert it on hdbss setup. It could be either a
> shift, or size.
>
> Reason being that you used this to compare with HDBSS_MAX_ORDER at some
> point, and there is no guarantee that the encoding will always be in
> crescent form.
>
> Also, it's not clear where you set this value.
Yes, this is the HDBSS buffer order (2^order bytes per vCPU).
I put it in kvm->arch *to make sure all vCPUs in a VM have the same order*.
I agree we should store a plain order number rather than the raw SZ
encoding.
The assignment should happen in kvm_arm_enable_hdbss_global(), which I
missed in v4 and will add in v5.
>
>> +
>> #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
>> /* Nested virtualization info */
>> struct dentry *debugfs_nv_dentry;
>> @@ -838,6 +842,12 @@ struct vcpu_reset_state {
>> bool reset;
>> };
>>
>> +struct vcpu_hdbss_state {
>> + phys_addr_t base_phys; /* for memory free */
>> + u64 hdbssbr_el2; /* load directly */
>> + u64 hdbssprod_el2; /* save directly */
>> +};
>> +
>> struct vncr_tlb;
>>
>> struct kvm_vcpu_arch {
>> @@ -945,6 +955,9 @@ struct kvm_vcpu_arch {
>>
>> /* Hyp-readable copy of kvm_vcpu::pid */
>> pid_t pid;
>> +
>> + /* HDBSS registers info */
>> + struct vcpu_hdbss_state hdbss;/
>> };
>>
>> /*
>> diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
>> index 7aa08d59d494..1354a58c3316 100644
>> --- a/arch/arm64/include/asm/sysreg.h
>> +++ b/arch/arm64/include/asm/sysreg.h
>> @@ -1039,6 +1039,17 @@
>>
>> #define GCS_CAP(x) ((((unsigned long)x) & GCS_CAP_ADDR_MASK) | \
>> GCS_CAP_VALID_TOKEN)
>> +
>> +/*
>> + * Definitions for the HDBSS feature
>> + */
>> +#define HDBSS_MAX_ORDER HDBSSBR_EL2_SZ_2MB
>> +
> See above comment on using the encoding instead of an actual size/shift
> number.
You're right — I will fix this in the next version as follows:
First, HDBSS_MAX_ORDER will be defined as a plain order number. In v4 I
only considered the 4KB page
case and hard-coded it to 9. To make it work for any PAGE_SIZE
configuration (4KB, 16KB, or 64KB), I'll derive
it from HDBSSBR_EL2_SZ_2MB:
```
#define HDBSS_MAX_ORDER (12 + HDBSSBR_EL2_SZ_2MB - PAGE_SHIFT)
```
This evaluates to 9 on 4KB pages, and the correct value on 16KB/64KB
pages as well.
Second, I will add two conversion helpers in sysreg.h to bridge between
kernel semantics (alloc_pages order)
and hardware encoding (HDBSSBR_EL2.SZ):
```
/* Convert alloc_pages order to HDBSSBR_EL2.SZ encoding */
#define hdbss_order_to_sz(order) (PAGE_SHIFT + (order) - 12)
```
These helpers work for any PAGE_SIZE configuration (4KB, 16KB, or 64KB)
because they use PAGE_SHIFT directly.
Third, I will update the HDBSSBR_EL2 register construction in
kvm_arm_vcpu_alloc_hdbss()：
```
/* before */
.hdbssbr_el2 = HDBSSBR_EL2(page_to_phys(hdbss_pg), order),
/* after */
.hdbssbr_el2 = HDBSSBR_EL2(page_to_phys(hdbss_pg),
hdbss_order_to_sz(order)),
```
And I will also update the __free_pages() call to use
vcpu->kvm->arch.hdbss_order directly, since that field
stores the plain order number and avoids decoding the SZ encoding at
free time:
```
/* before */
__free_pages(hdbss_pg,
FIELD_GET(HDBSSBR_EL2_SZ_MASK,
vcpu->arch.hdbss.hdbssbr_el2));
/* after */
__free_pages(hdbss_pg,
vcpu->kvm->arch.hdbss_order);
```
>
>> +#define HDBSSBR_EL2(baddr, sz) (((baddr) & HDBSSBR_EL2_BADDR_MASK) | \
>> + FIELD_PREP(HDBSSBR_EL2_SZ_MASK, sz))
>> +
>> +#define HDBSSPROD_IDX(prod) FIELD_GET(HDBSSPROD_EL2_INDEX_MASK, prod)
>> +
>> /*
>> * Definitions for GICv5 instructions
>> */
>> diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
>> index 59612d2f277c..ec2749af64fa 100644
>> --- a/arch/arm64/kvm/Makefile
>> +++ b/arch/arm64/kvm/Makefile
>> @@ -18,6 +18,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
>> guest.o debug.o reset.o sys_regs.o stacktrace.o \
>> vgic-sys-reg-v3.o fpsimd.o pkvm.o \
>> arch_timer.o trng.o vmid.o emulate-nested.o nested.o at.o \
>> + dirty_bit.o \
>> vgic/vgic.o vgic/vgic-init.o \
>> vgic/vgic-irqfd.o vgic/vgic-v2.o \
>> vgic/vgic-v3.o vgic/vgic-v4.o \
>> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
>> index 50adfff75be8..bf6688245d83 100644
>> --- a/arch/arm64/kvm/arm.c
>> +++ b/arch/arm64/kvm/arm.c
>> @@ -38,6 +38,7 @@
>> #include <asm/kvm_asm.h>
>> #include <asm/kvm_emulate.h>
>> #include <asm/kvm_hyp.h>
>> +#include <asm/kvm_dirty_bit.h>
>> #include <asm/kvm_mmu.h>
>> #include <asm/kvm_nested.h>
>> #include <asm/kvm_pkvm.h>
>> @@ -565,6 +566,12 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
>> if (err)
>> kvm_vgic_vcpu_destroy(vcpu);
>>
>> + if (vcpu->kvm->arch.enable_hdbss) {
>> + err = kvm_arm_vcpu_alloc_hdbss(vcpu, vcpu->kvm->arch.hdbss_order);
>> + if (err)
>> + kvm_vgic_vcpu_destroy(vcpu);
>> + }
>> +
>> return err;
>> }
>>
>> diff --git a/arch/arm64/kvm/dirty_bit.c b/arch/arm64/kvm/dirty_bit.c
>> new file mode 100644
>> index 000000000000..6c7a6ef66b5a
>> --- /dev/null
>> +++ b/arch/arm64/kvm/dirty_bit.c
>> @@ -0,0 +1,52 @@
>> +// SPDX-License-Identifier: GPL-2.0-only
>> +/*
>> + * Copyright (C) 2026 ARM Ltd.
>> + * Author: Leonardo Bras <leo.bras at arm.com>
>> + */
>> +
>> +#include <asm/kvm_dirty_bit.h>
>> +#include <asm/kvm_mmu.h>
>> +#include <asm/sysreg.h>
>> +#include <linux/gfp.h>
>> +#include <linux/kconfig.h>
>> +#include <linux/mm.h>
>> +
>> +int kvm_arm_vcpu_alloc_hdbss(struct kvm_vcpu *vcpu, unsigned int order)
>> +{
>> + struct page *hdbss_pg = NULL;
>> +
>> + if (vcpu->arch.hdbss.hdbssbr_el2 || !system_supports_hdbss())
>> + return 0;
>> +
>> + if (order > HDBSS_MAX_ORDER)
>> + return -EINVAL;
>> +
>> + hdbss_pg = alloc_pages(GFP_KERNEL_ACCOUNT, order);
>> + if (!hdbss_pg)
>> + return -ENOMEM;
>> +
>> + vcpu->arch.hdbss = (struct vcpu_hdbss_state) {
>> + .base_phys = page_to_phys(hdbss_pg),
>> + .hdbssbr_el2 = HDBSSBR_EL2(page_to_phys(hdbss_pg), order),
>> + .hdbssprod_el2 = 0,
>> + };
>> +
>> + return 0;
>> +}
>> +
>> +void kvm_arm_vcpu_free_hdbss(struct kvm_vcpu *vcpu)
>> +{
>> + struct page *hdbss_pg;
>> +
>> + if (!vcpu->arch.hdbss.hdbssbr_el2) {
>> + return;
>> + }
>> +
>> + hdbss_pg = phys_to_page(vcpu->arch.hdbss.base_phys);
>> + if (hdbss_pg)
>> + __free_pages(hdbss_pg,
>> + FIELD_GET(HDBSSBR_EL2_SZ_MASK,
>> + vcpu->arch.hdbss.hdbssbr_el2));
>> +
>> + vcpu->arch.hdbss.hdbssbr_el2 = 0;
>> +}
>> diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
>> index bbe9cebd3d9d..fe72944bfd3d 100644
>> --- a/arch/arm64/kvm/hyp/vhe/switch.c
>> +++ b/arch/arm64/kvm/hyp/vhe/switch.c
>> @@ -22,6 +22,7 @@
>> #include <asm/kvm_emulate.h>
>> #include <asm/kvm_hyp.h>
>> #include <asm/kvm_mmu.h>
>> +#include <asm/kvm_dirty_bit.h>
>> #include <asm/fpsimd.h>
>> #include <asm/debug-monitors.h>
>> #include <asm/processor.h>
>> @@ -213,6 +214,19 @@ static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
>> local_irq_restore(flags);
>> }
>>
>> +static void __load_hdbss(struct kvm_vcpu *vcpu)
>> +{
>> + struct kvm *kvm = vcpu->kvm;
>> +
>> + if (!kvm->arch.enable_hdbss)
>> + return;
>> +
>> + write_sysreg_s(vcpu->arch.hdbss.hdbssbr_el2, SYS_HDBSSBR_EL2);
>> + write_sysreg_s(vcpu->arch.hdbss.hdbssprod_el2, SYS_HDBSSPROD_EL2);
>> +
>> + isb();
>> +}
>> +
>> void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
>> {
>> host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu;
>> @@ -220,6 +234,7 @@ void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
>> __vcpu_load_switch_sysregs(vcpu);
>> __vcpu_load_activate_traps(vcpu);
>> __load_stage2(vcpu->arch.hw_mmu);
>> + __load_hdbss(vcpu);
>> }
>>
>> void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
>> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
>> index 346efed6e605..83251d95bf3f 100644
>> --- a/arch/arm64/kvm/mmu.c
>> +++ b/arch/arm64/kvm/mmu.c
>> @@ -16,6 +16,7 @@
>> #include <asm/cacheflush.h>
>> #include <asm/kvm_arm.h>
>> #include <asm/kvm_mmu.h>
>> +#include <asm/kvm_dirty_bit.h>
>> #include <asm/kvm_pgtable.h>
>> #include <asm/kvm_pkvm.h>
>> #include <asm/kvm_asm.h>
>> diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
>> index b963fd975aac..d8104bcbd9ff 100644
>> --- a/arch/arm64/kvm/reset.c
>> +++ b/arch/arm64/kvm/reset.c
>> @@ -27,6 +27,7 @@
>> #include <asm/kvm_asm.h>
>> #include <asm/kvm_emulate.h>
>> #include <asm/kvm_mmu.h>
>> +#include <asm/kvm_dirty_bit.h>
>> #include <asm/kvm_nested.h>
>> #include <asm/virt.h>
>>
>> @@ -161,6 +162,9 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
>> free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
>> kfree(vcpu->arch.vncr_tlb);
>> kfree(vcpu->arch.ccsidr);
>> +
>> + if (vcpu->kvm->arch.enable_hdbss)
>> + kvm_arm_vcpu_free_hdbss(vcpu);
>> }
>>
>> static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
>> --
>> 2.33.0
>>
More information about the linux-arm-kernel
mailing list