Add a capability for userspace to specify the eager split chunk size.
The chunk size specifies how many pages to break at a time, using a
single allocation. Bigger the chunk size, more pages need to be
allocated ahead of time.
Suggested-by: Oliver Upton <oliver.upton@xxxxxxxxx>
Signed-off-by: Ricardo Koller <ricarkol@xxxxxxxxxx>
---
Documentation/virt/kvm/api.rst | 26 ++++++++++++++++++++++++++
arch/arm64/include/asm/kvm_host.h | 19 +++++++++++++++++++
arch/arm64/kvm/arm.c | 22 ++++++++++++++++++++++
arch/arm64/kvm/mmu.c | 3 +++
include/uapi/linux/kvm.h | 1 +
5 files changed, 71 insertions(+)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9807b05a1b57..a9332e331cce 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8284,6 +8284,32 @@ structure.
When getting the Modified Change Topology Report value, the attr->addr
must point to a byte where the value will be stored or retrieved from.
+8.40 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+---------------------------------------
+
+:Capability: KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+:Architectures: arm64
+:Type: vm
+:Parameters: arg[0] is the new chunk size.
+:Returns: 0 on success, -EINVAL if any memslot has been created.
+
+This capability sets the chunk size used in Eager Page Splitting.
+
+Eager Page Splitting improves the performance of dirty-logging (used
+in live migrations) when guest memory is backed by huge-pages. This
+optimization is enabled by default on arm64. It avoids splitting
+huge-pages (into PAGE_SIZE pages) on fault, by doing it eagerly when
+enabling dirty logging (with the KVM_MEM_LOG_DIRTY_PAGES flag for a
+memory region), or when using KVM_CLEAR_DIRTY_LOG.
+
+The chunk size specifies how many pages to break at a time, using a
+single allocation for each chunk. Bigger the chunk size, more pages
+need to be allocated ahead of time. A good heuristic is to pick the
+size of the huge-pages as the chunk size.
+
+If the chunk size (arg[0]) is zero, then no eager page splitting is
+performed. The default value PMD size (e.g., 2M when PAGE_SIZE is 4K).
+
9. Known KVM API problems
=========================
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 35a159d131b5..1445cbf6295e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -153,6 +153,25 @@ struct kvm_s2_mmu {
/* The last vcpu id that ran on each physical CPU */
int __percpu *last_vcpu_ran;
+#define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT PMD_SIZE
+ /*
+ * Memory cache used to split
+ * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It
+ * is used to allocate stage2 page tables while splitting huge
+ * pages. Note that the choice of EAGER_PAGE_SPLIT_CHUNK_SIZE
+ * influences both the capacity of the split page cache, and
+ * how often KVM reschedules. Be wary of raising CHUNK_SIZE
+ * too high.
+ *
+ * A good heuristic to pick CHUNK_SIZE is that it should be
+ * the size of the huge-pages backing guest memory. If not
+ * known, the PMD size (usually 2M) is a good guess.
+ *
+ * Protected by kvm->slots_lock.
+ */
+ struct kvm_mmu_memory_cache split_page_cache;
+ uint64_t split_page_chunk_size;
+
struct kvm_arch *arch;
};
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9c5573bc4614..c80617ced599 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -101,6 +101,22 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
r = 0;
set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags);
break;
+ case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
+ mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->slots_lock);
+ /*
+ * To keep things simple, allow changing the chunk
+ * size only if there are no memslots created.
+ */
+ if (!kvm_are_all_memslots_empty(kvm)) {
+ r = -EINVAL;
+ } else {
+ r = 0;
+ kvm->arch.mmu.split_page_chunk_size = cap->args[0];
+ }
+ mutex_unlock(&kvm->slots_lock);
+ mutex_unlock(&kvm->lock);
+ break;
default:
r = -EINVAL;
break;
@@ -298,6 +314,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_ARM_PTRAUTH_GENERIC:
r = system_has_full_ptr_auth();
break;
+ case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
+ if (kvm)
+ r = kvm->arch.mmu.split_page_chunk_size;
+ else
+ r = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
+ break;
default:
r = 0;
}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 812633a75e74..e2ada6588017 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -755,6 +755,9 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
for_each_possible_cpu(cpu)
*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
+ mmu->split_page_cache.gfp_zero = __GFP_ZERO;
+ mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
+
mmu->pgt = pgt;
mmu->pgd_phys = __pa(pgt->pgd);
return 0;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 55155e262646..02e05f7918e2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1175,6 +1175,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 226
#ifdef KVM_CAP_IRQ_ROUTING
--
2.39.2.637.g21b0678d19-goog
