On Mon, Feb 6, 2023 at 8:58 AM Ricardo Koller <ricarkol@xxxxxxxxxx> wrote:
>
> Add a stage2 helper, kvm_pgtable_stage2_create_unlinked(), for creating
> unlinked tables (the opposite of kvm_pgtable_stage2_free_unlinked()).
> Creating an unlinked table is useful for splitting block PTEs into
> subtrees of 4K PTEs. For example, a 1G block PTE can be split into 4K
> PTEs by first creating a fully populated tree, and then use it to
> replace the 1G PTE in a single step. This will be used in a
> subsequent commit for eager huge-page splitting (a dirty-logging
> optimization).
>
> No functional change intended. This new function will be used in a
> subsequent commit.
>
> Signed-off-by: Ricardo Koller <ricarkol@xxxxxxxxxx>
> ---
> arch/arm64/include/asm/kvm_pgtable.h | 29 +++++++++++++++++
> arch/arm64/kvm/hyp/pgtable.c | 47 ++++++++++++++++++++++++++++
> 2 files changed, 76 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index 7c45082e6c23..e94c92988745 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -460,6 +460,35 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
> */
> void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
>
> +/**
> + * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
> + * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
> + * @new: Unlinked stage-2 paging structure to be created.
> + * @phys: Physical address of the memory to map.
> + * @level: Level of the stage-2 paging structure to be created.
> + * @prot: Permissions and attributes for the mapping.
> + * @mc: Cache of pre-allocated and zeroed memory from which to allocate
> + * page-table pages.
> + * @force_pte: Force mappings to PAGE_SIZE granularity.
> + *
> + * Create an unlinked page-table tree under @new. If @force_pte is
> + * true and @level is the PMD level, then the tree is mapped up to the
typo: this should be: "if @force_pte is true OR @level is the PMD, then
the tree is mapped up to the PAGE_SIZE leaf PTE"
> + * PAGE_SIZE leaf PTE; the tree is mapped up one level otherwise. This
> + * new page-table tree is not reachable (i.e., it is removed) from the
> + * root pgd and it's therefore unreachableby the hardware page-table
> + * walker. No TLB invalidation or CMOs are performed.
> + *
> + * If device attributes are not explicitly requested in @prot, then the
> + * mapping will be normal, cacheable.
> + *
> + * Return: 0 only if a fully populated tree was created (all memory
> + * under @level is mapped), negative error code on failure.
> + */
> +int kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
> + kvm_pte_t *new, u64 phys, u32 level,
> + enum kvm_pgtable_prot prot, void *mc,
> + bool force_pte);
> +
> /**
> * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
> * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 0a5ef9288371..fed314f2b320 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -1181,6 +1181,53 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
> return kvm_pgtable_walk(pgt, addr, size, &walker);
> }
>
> +int kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
> + kvm_pte_t *new, u64 phys, u32 level,
> + enum kvm_pgtable_prot prot, void *mc,
> + bool force_pte)
> +{
> + struct stage2_map_data map_data = {
> + .phys = phys,
> + .mmu = pgt->mmu,
> + .memcache = mc,
> + .force_pte = force_pte,
> + };
> + struct kvm_pgtable_walker walker = {
> + .cb = stage2_map_walker,
> + .flags = KVM_PGTABLE_WALK_LEAF |
> + KVM_PGTABLE_WALK_SKIP_BBM |
> + KVM_PGTABLE_WALK_SKIP_CMO,
> + .arg = &map_data,
> + };
> + /* .addr (the IPA) is irrelevant for a removed table */
> + struct kvm_pgtable_walk_data data = {
> + .walker = &walker,
> + .addr = 0,
> + .end = kvm_granule_size(level),
> + };
> + struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
> + kvm_pte_t *pgtable;
> + int ret;
> +
> + ret = stage2_set_prot_attr(pgt, prot, &map_data.attr);
> + if (ret)
> + return ret;
> +
> + pgtable = mm_ops->zalloc_page(mc);
> + if (!pgtable)
> + return -ENOMEM;
> +
> + ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable,
> + level + 1);
> + if (ret) {
> + kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
> + mm_ops->put_page(pgtable);
> + return ret;
> + }
> +
> + *new = kvm_init_table_pte(pgtable, mm_ops);
> + return 0;
> +}
>
> int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
> struct kvm_pgtable_mm_ops *mm_ops,
> --
> 2.39.1.519.gcb327c4b5f-goog
>
