From: Eillon <yezhenyu2@huawei.com> 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@huawei.com> Signed-off-by: Tian Zheng <zhengtian10@huawei.com> --- 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); +} + 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); @@ -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> 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; + + 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