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 subsequent commit. Signed-off-by: Ricardo Koller <ricarkol@xxxxxxxxxx> --- arch/arm64/include/asm/kvm_pgtable.h | 30 ++++++++ arch/arm64/kvm/hyp/pgtable.c | 105 +++++++++++++++++++++++++++ 2 files changed, 135 insertions(+) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 2ea397ad3e63..b28489aa0994 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -658,6 +658,36 @@ 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. + * @mc_capacity: Number of pages in @mc. + * + * @addr and the end (@addr + @size) are effectively aligned down and up to + * the top level huge-page block size. This is an example 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 @mc_capacity. + */ +int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + void *mc, u64 mc_capacity); + /** * 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 fed314f2b320..e2fb78398b3d 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1229,6 +1229,111 @@ int kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, return 0; } +struct stage2_split_data { + struct kvm_s2_mmu *mmu; + void *memcache; + u64 mc_capacity; +}; + +/* + * Get the number of page-tables needed to replace a bock with a fully + * populated tree, up to the PTE level, at particular level. + */ +static inline u32 stage2_block_get_nr_page_tables(u32 level) +{ + switch (level) { + /* There are no blocks at level 0 */ + case 1: return 1 + PTRS_PER_PTE; + case 2: return 1; + case 3: return 0; + default: + WARN_ON_ONCE(1); + return ~0; + } +} + +static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + struct stage2_split_data *data = ctx->arg; + kvm_pte_t pte = ctx->old, new, *childp; + enum kvm_pgtable_prot prot; + void *mc = data->memcache; + u32 level = ctx->level; + u64 phys, nr_pages; + bool force_pte; + int ret; + + /* No huge-pages exist at the last level */ + if (level == KVM_PGTABLE_MAX_LEVELS - 1) + return 0; + + /* We only split valid block mappings */ + if (!kvm_pte_valid(pte)) + return 0; + + nr_pages = stage2_block_get_nr_page_tables(level); + if (data->mc_capacity >= nr_pages) { + /* Build a tree mapped down to the PTE granularity. */ + force_pte = true; + } else { + /* + * Don't force PTEs. This requires a single page of PMDs at the + * PUD level, or a single page of PTEs at the PMD level. If we + * are at the PUD level, the PTEs will be created recursively. + */ + force_pte = false; + nr_pages = 1; + } + + if (data->mc_capacity < nr_pages) + return -ENOMEM; + + phys = kvm_pte_to_phys(pte); + prot = kvm_pgtable_stage2_pte_prot(pte); + + ret = kvm_pgtable_stage2_create_unlinked(data->mmu->pgt, &new, phys, + level, prot, mc, force_pte); + if (ret) + return ret; + + if (!stage2_try_break_pte(ctx, data->mmu)) { + childp = kvm_pte_follow(new, mm_ops); + kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); + mm_ops->put_page(childp); + return -EAGAIN; + } + + /* + * 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); + data->mc_capacity -= nr_pages; + return 0; +} + +int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + void *mc, u64 mc_capacity) +{ + struct stage2_split_data split_data = { + .mmu = pgt->mmu, + .memcache = mc, + .mc_capacity = mc_capacity, + }; + + struct kvm_pgtable_walker walker = { + .cb = stage2_split_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &split_data, + }; + + return kvm_pgtable_walk(pgt, addr, size, &walker); +} + 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, -- 2.39.1.637.g21b0678d19-goog