Re: [PATCH v5 08/15] KVM: arm64: Flush the HDBSS buffer on VM exit
From: Tian Zheng
Date: Fri Oct 30 2026 - 00:57:22 EST
On 10/28/2026 2:13 AM, Leonardo Bras wrote:
On Tue, Sep 29, 2026 at 06:36:48PM +0800, Tian Zheng wrote:
From: Eillon <yezhenyu2@xxxxxxxxxx>
HDBSS entries accumulate in the per-vCPU buffer while the guest runs,
and must be drained into the dirty bitmap or dirty ring before
userspace can observe them.
Drain the buffer at a single point: kvm_arch_vcpu_ioctl_run() flushes
it on every VM exit, before the exit reason is handled. Flushing
inside the run loop keeps the dirty-ring feedback timely: when a flush
pushes the ring past its soft limit, kvm_dirty_ring_push() raises
KVM_REQ_DIRTY_RING_SOFT_FULL, which check_vcpu_requests() observes at
the top of the next loop iteration, so the vCPU exits to userspace for
the harvest before re-entering the guest.
kvm_arch_sync_dirty_log() relies on the exit path to flush: it kicks
vCPUs out of guest mode, and the GET/CLEAR protocol tolerates
concurrent bitmap writes, so the snapshot is complete without extra
synchronization.
Signed-off-by: Eillon <yezhenyu2@xxxxxxxxxx>
Signed-off-by: Tian Zheng <zhengtian10@xxxxxxxxxx>
---
arch/arm64/include/asm/kvm_dirty_bit.h | 15 +++++++++
arch/arm64/kvm/arm.c | 20 ++++++++++++
arch/arm64/kvm/dirty_bit.c | 45 ++++++++++++++++++++++++++
3 files changed, 80 insertions(+)
diff --git a/arch/arm64/include/asm/kvm_dirty_bit.h b/arch/arm64/include/asm/kvm_dirty_bit.h
index fe703f02626b..d828e6b43fe9 100644
--- a/arch/arm64/include/asm/kvm_dirty_bit.h
+++ b/arch/arm64/include/asm/kvm_dirty_bit.h
@@ -13,6 +13,9 @@
#include <asm/sysreg.h>
#include <linux/sizes.h>
+#define HDBSS_ENTRY_VALID BIT(0)
+#define HDBSS_ENTRY_IPA GENMASK_ULL(55, 12)
+
#define KVM_ARM_HDBSS_DEFAULT_SIZE PAGE_SIZE
#define KVM_ARM_HDBSS_MAX_SIZE SZ_2M
@@ -22,7 +25,19 @@ static inline u32 kvm_hdbss_buffer_size(struct kvm *kvm)
return kvm->arch.hdbss_buffer_size ?: KVM_ARM_HDBSS_DEFAULT_SIZE;
}
+static inline bool kvm_hdbss_enabled(struct kvm *kvm)
+{
+ return kvm->arch.mmu.vtcr & VTCR_EL2_HDBSS;
+}
+
+static inline bool vcpu_hdbss_enabled(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.hw_mmu &&
+ (vcpu->arch.hw_mmu->vtcr & VTCR_EL2_HDBSS);
+}
+
IIUC, arch.mmu is always the canonical s2_mmu, while hw_mmu can be the
nested s2_mmu, if enabled.
Was that your intend here?
If not, we could use only kvm* version, which can be called with vcpu->kvm.
If it was, then I would like to understand the logic here, as IIUC the
buffer is accessible only for the non-nested guest, as it's
allocated in a per-vcpu structure. (vcpu->arch)
Hi leo,
Yes, that was the intent. The shadow MMU never carries VTCR_EL2.HDBSS,
so the flush is naturally skipped when running nested.
int kvm_arm_vcpu_alloc_hdbss(struct kvm_vcpu *vcpu);
void kvm_arm_vcpu_free_hdbss(struct kvm_vcpu *vcpu);
+void kvm_flush_hdbss_buffer(struct kvm_vcpu *vcpu);
#endif /* __ARM64_KVM_DIRTY_BIT_H__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 5ea4ac26995e..9d7bdece149a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1430,6 +1430,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+ /*
+ * Drain the HDBSS buffer before the exit is handled, so
+ * entries pushed to the dirty ring are accounted for by
+ * dirty_ring_check_request() on the next iteration.
+ */
+ if (vcpu_hdbss_enabled(vcpu))
+ kvm_flush_hdbss_buffer(vcpu);
+
/* Exit types that need handling before we can be preempted */
handle_exit_early(vcpu, ret);
looks the correct place, haven't looked too much on that, though.
Thanks!
@@ -2017,7 +2025,19 @@ 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)
{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+ if (!kvm_hdbss_enabled(kvm))
+ return;
+
+ /*
+ * The buffer is drained on every VM exit, so kicking running
+ * vCPUs is enough to flush them; the dirty-log GET/CLEAR
+ * protocol tolerates bits set concurrently with the snapshot.
+ */
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vcpu_kick(vcpu);
}
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 f9aeb9f34ad0..be0d12555c84 100644
--- a/arch/arm64/kvm/dirty_bit.c
+++ b/arch/arm64/kvm/dirty_bit.c
@@ -13,6 +13,7 @@
#include <linux/kconfig.h>
#include <linux/log2.h>
#include <linux/mm.h>
+#include <linux/srcu.h>
Out of curiosity, could you please explain you reasoning on selecting srcu
as locking here?
(Like, what are you protecting against, and why srcu is a good choice)
kvm_vcpu_mark_page_dirty() resolves the memslot under SRCU
(kvm_vcpu_gfn_to_memslot), and the flush loop calls it for each entry,
so the whole loop needs the read lock held.
int kvm_arm_vcpu_alloc_hdbss(struct kvm_vcpu *vcpu)
{
@@ -53,3 +54,47 @@ void kvm_arm_vcpu_free_hdbss(struct kvm_vcpu *vcpu)
vcpu->arch.hdbss.hdbss_pg = NULL;
vcpu->arch.hdbss.hdbssbr_el2 = 0;
}
+
+void kvm_flush_hdbss_buffer(struct kvm_vcpu *vcpu)
+{
+ int idx, curr_idx;
+ u64 prod;
+ u32 entries;
+ u64 *hdbss_buf;
+ struct kvm *kvm = vcpu->kvm;
+ int srcu_idx;
+
+ if (!vcpu_hdbss_enabled(vcpu))
+ return;
You test this before calling, is it really necessary to test it again, just
after calling?
You're right, I've removed it.
Thanks,
Tian
+
+ prod = read_sysreg_s(SYS_HDBSSPROD_EL2);
+ curr_idx = HDBSSPROD_IDX(prod);
+
+ if (curr_idx == 0 || !vcpu->arch.hdbss.hdbss_pg)
+ return;
+
+ hdbss_buf = page_address(vcpu->arch.hdbss.hdbss_pg);
+ if (!hdbss_buf)
+ return;
+
+ entries = kvm_hdbss_buffer_size(kvm) / sizeof(u64);
+
+ /* kvm_vcpu_mark_page_dirty() resolves the memslot under SRCU. */
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ for (idx = 0; idx < min_t(u32, curr_idx, entries); 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);
+ }
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ prod &= ~HDBSSPROD_EL2_INDEX_MASK;
+ write_sysreg_s(prod, SYS_HDBSSPROD_EL2);
+ vcpu->arch.hdbss.hdbssprod_el2 = prod;
+ isb();
+}
--
2.43.0
Thanks!
Leo