Add a new stage2 function, kvm_pgtable_stage2_split(), for splitting a
range of huge pages. This will be used for eager-splitting huge pages into
PAGE_SIZE pages. The goal is to avoid having to split huge pages on
write-protection faults, and instead use this function to do it ahead of
time for large ranges (e.g., all guest memory in 1G chunks at a time).
No functional change intended. This new function will be used in a
Signed-off-by: Ricardo Koller <ricarkol@xxxxxxxxxx>
---
arch/arm64/include/asm/kvm_pgtable.h | 29 +++++++++++
arch/arm64/kvm/hyp/pgtable.c | 74 ++++++++++++++++++++++++++++
2 files changed, 103 insertions(+)
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index d2e4a5032146..396ebb0949fb 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -594,6 +594,35 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
*/
int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+/**
+ * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing
+ * to PAGE_SIZE guest pages.
+ * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr: Intermediate physical address from which to split.
+ * @size: Size of the range.
+ * @mc: Cache of pre-allocated and zeroed memory from which to allocate
+ * page-table pages.
+ *
+ * @addr and the end (@addr + @size) are effectively aligned down and up to
+ * the top level huge-page block size. This is an exampe using 1GB
+ * huge-pages and 4KB granules.
+ *
+ * [---input range---]
+ * : :
+ * [--1G block pte--][--1G block pte--][--1G block pte--][--1G block pte--]
+ * : :
+ * [--2MB--][--2MB--][--2MB--][--2MB--]
+ * : :
+ * [ ][ ][:][ ][ ][ ][ ][ ][:][ ][ ][ ]
+ * : :
+ *
+ * Return: 0 on success, negative error code on failure. Note that
+ * kvm_pgtable_stage2_split() is best effort: it tries to break as many
+ * blocks in the input range as allowed by the size of the memcache. It
+ * will fail it wasn't able to break any block.
+ */
+int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc);
+
/**
* kvm_pgtable_walk() - Walk a page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_*_init().
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index d1f309128118..9c42eff6d42e 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1267,6 +1267,80 @@ static int stage2_create_removed(kvm_pte_t *ptep, u64 phys, u32 level,
return __kvm_pgtable_visit(&data, mm_ops, ptep, level);
}
+struct stage2_split_data {
+ struct kvm_s2_mmu *mmu;
+ void *memcache;
+ struct kvm_pgtable_mm_ops *mm_ops;
+};
+
+static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
+ enum kvm_pgtable_walk_flags visit)
+{
+ struct stage2_split_data *data = ctx->arg;
+ struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
+ kvm_pte_t pte = ctx->old, attr, new;
+ enum kvm_pgtable_prot prot;
+ void *mc = data->memcache;
+ u32 level = ctx->level;
+ u64 phys;
+
+ if (WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx)))
+ return -EINVAL;
+
+ /* Nothing to split at the last level */
+ if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+ return 0;
+
+ /* We only split valid block mappings */
+ if (!kvm_pte_valid(pte) || kvm_pte_table(pte, ctx->level))
+ return 0;
+
+ phys = kvm_pte_to_phys(pte);
+ prot = kvm_pgtable_stage2_pte_prot(pte);
+ stage2_set_prot_attr(data->mmu->pgt, prot, &attr);
+
+ /*
+ * Eager page splitting is best-effort, so we can ignore the error.
+ * The returned PTE (new) will be valid even if this call returns
+ * error: new will be a single (big) block PTE. The only issue is
+ * that it will affect dirty logging performance, as the huge-pages
+ * will have to be split on fault, and so we WARN.
+ */
+ WARN_ON(stage2_create_removed(&new, phys, level, attr, mc, mm_ops));
+
+ stage2_put_pte(ctx, data->mmu, mm_ops);
+
+ /*
+ * Note, the contents of the page table are guaranteed to be made
+ * visible before the new PTE is assigned because
+ * stage2_make__pte() writes the PTE using smp_store_release().
+ */
+ stage2_make_pte(ctx, new);
+ dsb(ishst);
+ return 0;
+}
+
+int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt,
+ u64 addr, u64 size, void *mc)
+{
+ int ret;
+
+ struct stage2_split_data split_data = {
+ .mmu = pgt->mmu,
+ .memcache = mc,
+ .mm_ops = pgt->mm_ops,
+ };
+
+ struct kvm_pgtable_walker walker = {
+ .cb = stage2_split_walker,
+ .flags = KVM_PGTABLE_WALK_POST,
+ .arg = &split_data,
+ };
+
+ ret = kvm_pgtable_walk(pgt, addr, size, &walker);
+ return ret;
+}
+
int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
struct kvm_pgtable_mm_ops *mm_ops,
enum kvm_pgtable_stage2_flags flags,
--
2.38.1.431.g37b22c650d-goog
