diff options
Diffstat (limited to 'arch/arm64/kvm/mmu.c')
| -rw-r--r-- | arch/arm64/kvm/mmu.c | 1314 |
1 files changed, 979 insertions, 335 deletions
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index a3ee3b605c9b..48d7c372a4cd 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -4,18 +4,20 @@ * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ +#include <linux/acpi.h> #include <linux/mman.h> #include <linux/kvm_host.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/sched/signal.h> #include <trace/events/kvm.h> +#include <asm/acpi.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> -#include <asm/kvm_ras.h> +#include <asm/kvm_pkvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/virt.h> @@ -25,20 +27,31 @@ static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); -static unsigned long hyp_idmap_start; -static unsigned long hyp_idmap_end; -static phys_addr_t hyp_idmap_vector; +static unsigned long __ro_after_init hyp_idmap_start; +static unsigned long __ro_after_init hyp_idmap_end; +static phys_addr_t __ro_after_init hyp_idmap_vector; -static unsigned long io_map_base; +u32 __ro_after_init __hyp_va_bits; -static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) +static unsigned long __ro_after_init io_map_base; + +#define KVM_PGT_FN(fn) (!is_protected_kvm_enabled() ? fn : p ## fn) + +static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end, + phys_addr_t size) { - phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); phys_addr_t boundary = ALIGN_DOWN(addr + size, size); return (boundary - 1 < end - 1) ? boundary : end; } +static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); + + return __stage2_range_addr_end(addr, end, size); +} + /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, * we may see kernel panics with CONFIG_DETECT_HUNG_TASK, @@ -46,16 +59,17 @@ static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ -static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, +static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { + struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { - struct kvm_pgtable *pgt = kvm->arch.mmu.pgt; + struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; @@ -71,8 +85,81 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, return ret; } -#define stage2_apply_range_resched(kvm, addr, end, fn) \ - stage2_apply_range(kvm, addr, end, fn, true) +#define stage2_apply_range_resched(mmu, addr, end, fn) \ + stage2_apply_range(mmu, addr, end, fn, true) + +/* + * Get the maximum number of page-tables pages needed to split a range + * of blocks into PAGE_SIZE PTEs. It assumes the range is already + * mapped at level 2, or at level 1 if allowed. + */ +static int kvm_mmu_split_nr_page_tables(u64 range) +{ + int n = 0; + + if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2) + n += DIV_ROUND_UP(range, PUD_SIZE); + n += DIV_ROUND_UP(range, PMD_SIZE); + return n; +} + +static bool need_split_memcache_topup_or_resched(struct kvm *kvm) +{ + struct kvm_mmu_memory_cache *cache; + u64 chunk_size, min; + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) + return true; + + chunk_size = kvm->arch.mmu.split_page_chunk_size; + min = kvm_mmu_split_nr_page_tables(chunk_size); + cache = &kvm->arch.mmu.split_page_cache; + return kvm_mmu_memory_cache_nr_free_objects(cache) < min; +} + +static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr, + phys_addr_t end) +{ + struct kvm_mmu_memory_cache *cache; + struct kvm_pgtable *pgt; + int ret, cache_capacity; + u64 next, chunk_size; + + lockdep_assert_held_write(&kvm->mmu_lock); + + chunk_size = kvm->arch.mmu.split_page_chunk_size; + cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size); + + if (chunk_size == 0) + return 0; + + cache = &kvm->arch.mmu.split_page_cache; + + do { + if (need_split_memcache_topup_or_resched(kvm)) { + write_unlock(&kvm->mmu_lock); + cond_resched(); + /* Eager page splitting is best-effort. */ + ret = __kvm_mmu_topup_memory_cache(cache, + cache_capacity, + cache_capacity); + write_lock(&kvm->mmu_lock); + if (ret) + break; + } + + pgt = kvm->arch.mmu.pgt; + if (!pgt) + return -EINVAL; + + next = __stage2_range_addr_end(addr, end, chunk_size); + ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache); + if (ret) + break; + } while (addr = next, addr != end); + + return ret; +} static bool memslot_is_logging(struct kvm_memory_slot *memslot) { @@ -80,20 +167,31 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot) } /** - * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8 + * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8 * @kvm: pointer to kvm structure. * * Interface to HYP function to flush all VM TLB entries */ -void kvm_flush_remote_tlbs(struct kvm *kvm) +int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { - ++kvm->stat.generic.remote_tlb_flush_requests; - kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); + if (is_protected_kvm_enabled()) + kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); + else + kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); + return 0; } -static bool kvm_is_device_pfn(unsigned long pfn) +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, + gfn_t gfn, u64 nr_pages) { - return !pfn_is_map_memory(pfn); + u64 size = nr_pages << PAGE_SHIFT; + u64 addr = gfn << PAGE_SHIFT; + + if (is_protected_kvm_enabled()) + kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); + else + kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size); + return 0; } static void *stage2_memcache_zalloc_page(void *arg) @@ -130,21 +228,21 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size) static struct kvm_pgtable_mm_ops kvm_s2_mm_ops; -static void stage2_free_removed_table_rcu_cb(struct rcu_head *head) +static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head) { struct page *page = container_of(head, struct page, rcu_head); void *pgtable = page_to_virt(page); - u32 level = page_private(page); + s8 level = page_private(page); - kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level); + KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level); } -static void stage2_free_removed_table(void *addr, u32 level) +static void stage2_free_unlinked_table(void *addr, s8 level) { struct page *page = virt_to_page(addr); set_page_private(page, (unsigned long)level); - call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb); + call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb); } static void kvm_host_get_page(void *addr) @@ -216,7 +314,7 @@ static void invalidate_icache_guest_page(void *va, size_t size) * does. */ /** - * unmap_stage2_range -- Clear stage2 page table entries to unmap a range + * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range * @mmu: The KVM stage-2 MMU pointer * @start: The intermediate physical base address of the range to unmap * @size: The size of the area to unmap @@ -235,13 +333,19 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); - WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap, + WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap), may_block)); } -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, + u64 size, bool may_block) { - __unmap_stage2_range(mmu, start, size, true); + __unmap_stage2_range(mmu, start, size, may_block); +} + +void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) +{ + stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush)); } static void stage2_flush_memslot(struct kvm *kvm, @@ -250,7 +354,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush); + kvm_stage2_flush_range(&kvm->arch.mmu, addr, end); } /** @@ -273,6 +377,8 @@ static void stage2_flush_vm(struct kvm *kvm) kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); + kvm_nested_s2_flush(kvm); + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } @@ -280,7 +386,7 @@ static void stage2_flush_vm(struct kvm *kvm) /** * free_hyp_pgds - free Hyp-mode page tables */ -void free_hyp_pgds(void) +void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { @@ -511,6 +617,25 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) return 0; } +static int __hyp_alloc_private_va_range(unsigned long base) +{ + lockdep_assert_held(&kvm_hyp_pgd_mutex); + + if (!PAGE_ALIGNED(base)) + return -EINVAL; + + /* + * Verify that BIT(VA_BITS - 1) hasn't been flipped by + * allocating the new area, as it would indicate we've + * overflowed the idmap/IO address range. + */ + if ((base ^ io_map_base) & BIT(VA_BITS - 1)) + return -ENOMEM; + + io_map_base = base; + + return 0; +} /** * hyp_alloc_private_va_range - Allocates a private VA range. @@ -531,29 +656,22 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) /* * This assumes that we have enough space below the idmap - * page to allocate our VAs. If not, the check below will - * kick. A potential alternative would be to detect that - * overflow and switch to an allocation above the idmap. + * page to allocate our VAs. If not, the check in + * __hyp_alloc_private_va_range() will kick. A potential + * alternative would be to detect that overflow and switch + * to an allocation above the idmap. * * The allocated size is always a multiple of PAGE_SIZE. */ - base = io_map_base - PAGE_ALIGN(size); - - /* Align the allocation based on the order of its size */ - base = ALIGN_DOWN(base, PAGE_SIZE << get_order(size)); - - /* - * Verify that BIT(VA_BITS - 1) hasn't been flipped by - * allocating the new area, as it would indicate we've - * overflowed the idmap/IO address range. - */ - if ((base ^ io_map_base) & BIT(VA_BITS - 1)) - ret = -ENOMEM; - else - *haddr = io_map_base = base; + size = PAGE_ALIGN(size); + base = io_map_base - size; + ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); + if (!ret) + *haddr = base; + return ret; } @@ -587,6 +705,48 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, return ret; } +int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) +{ + unsigned long base; + size_t size; + int ret; + + mutex_lock(&kvm_hyp_pgd_mutex); + /* + * Efficient stack verification using the NVHE_STACK_SHIFT bit implies + * an alignment of our allocation on the order of the size. + */ + size = NVHE_STACK_SIZE * 2; + base = ALIGN_DOWN(io_map_base - size, size); + + ret = __hyp_alloc_private_va_range(base); + + mutex_unlock(&kvm_hyp_pgd_mutex); + + if (ret) { + kvm_err("Cannot allocate hyp stack guard page\n"); + return ret; + } + + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. + */ + ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE, + phys_addr, PAGE_HYP); + if (ret) + kvm_err("Cannot map hyp stack\n"); + + *haddr = base + size; + + return ret; +} + /** * create_hyp_io_mappings - Map IO into both kernel and HYP * @phys_addr: The physical start address which gets mapped @@ -661,18 +821,39 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr) struct kvm_pgtable pgt = { .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, - .start_level = (KVM_PGTABLE_MAX_LEVELS - - CONFIG_PGTABLE_LEVELS), + .start_level = (KVM_PGTABLE_LAST_LEVEL - + ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; + unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ - u32 level = ~0; + s8 level = S8_MAX; int ret; + /* + * Disable IRQs so that we hazard against a concurrent + * teardown of the userspace page tables (which relies on + * IPI-ing threads). + */ + local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); - VM_BUG_ON(ret); - VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS); - VM_BUG_ON(!(pte & PTE_VALID)); + local_irq_restore(flags); + + if (ret) + return ret; + + /* + * Not seeing an error, but not updating level? Something went + * deeply wrong... + */ + if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL)) + return -EFAULT; + if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL)) + return -EFAULT; + + /* Oops, the userspace PTs are gone... Replay the fault */ + if (!kvm_pte_valid(pte)) + return -EAGAIN; return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } @@ -681,7 +862,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, .free_pages_exact = kvm_s2_free_pages_exact, - .free_removed_table = stage2_free_removed_table, + .free_unlinked_table = stage2_free_unlinked_table, .get_page = kvm_host_get_page, .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, @@ -691,21 +872,9 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .icache_inval_pou = invalidate_icache_guest_page, }; -/** - * kvm_init_stage2_mmu - Initialise a S2 MMU structure - * @kvm: The pointer to the KVM structure - * @mmu: The pointer to the s2 MMU structure - * @type: The machine type of the virtual machine - * - * Allocates only the stage-2 HW PGD level table(s). - * Note we don't need locking here as this is only called when the VM is - * created, which can only be done once. - */ -int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) +static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) { u32 kvm_ipa_limit = get_kvm_ipa_limit(); - int cpu, err; - struct kvm_pgtable *pgt; u64 mmfr0, mmfr1; u32 phys_shift; @@ -730,22 +899,98 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); + mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); + + return 0; +} + +/* + * Assume that @pgt is valid and unlinked from the KVM MMU to free the + * page-table without taking the kvm_mmu_lock and without performing any + * TLB invalidations. + * + * Also, the range of addresses can be large enough to cause need_resched + * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke + * cond_resched() periodically to prevent hogging the CPU for a long time + * and schedule something else, if required. + */ +static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr, + phys_addr_t end) +{ + u64 next; + do { + next = stage2_range_addr_end(addr, end); + KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr, + next - addr); + if (next != end) + cond_resched(); + } while (addr = next, addr != end); +} + +static void kvm_stage2_destroy(struct kvm_pgtable *pgt) +{ + unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr); + + stage2_destroy_range(pgt, 0, BIT(ia_bits)); + KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt); +} + +/** + * kvm_init_stage2_mmu - Initialise a S2 MMU structure + * @kvm: The pointer to the KVM structure + * @mmu: The pointer to the s2 MMU structure + * @type: The machine type of the virtual machine + * + * Allocates only the stage-2 HW PGD level table(s). + * Note we don't need locking here as this is only called in two cases: + * + * - when the VM is created, which can't race against anything + * + * - when secondary kvm_s2_mmu structures are initialised for NV + * guests, and the caller must hold kvm->lock as this is called on a + * per-vcpu basis. + */ +int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) +{ + int cpu, err; + struct kvm_pgtable *pgt; + + /* + * If we already have our page tables in place, and that the + * MMU context is the canonical one, we have a bug somewhere, + * as this is only supposed to ever happen once per VM. + * + * Otherwise, we're building nested page tables, and that's + * probably because userspace called KVM_ARM_VCPU_INIT more + * than once on the same vcpu. Since that's actually legal, + * don't kick a fuss and leave gracefully. + */ if (mmu->pgt != NULL) { + if (kvm_is_nested_s2_mmu(kvm, mmu)) + return 0; + kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } + err = kvm_init_ipa_range(mmu, type); + if (err) + return err; + pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT); if (!pgt) return -ENOMEM; mmu->arch = &kvm->arch; - err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops); + err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops); if (err) goto out_free_pgtable; + mmu->pgt = pgt; + if (is_protected_kvm_enabled()) + return 0; + mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); if (!mmu->last_vcpu_ran) { err = -ENOMEM; @@ -755,17 +1000,30 @@ 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->pgt = pgt; + /* The eager page splitting is disabled by default */ + mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; + mmu->split_page_cache.gfp_zero = __GFP_ZERO; + mmu->pgd_phys = __pa(pgt->pgd); + + if (kvm_is_nested_s2_mmu(kvm, mmu)) + kvm_init_nested_s2_mmu(mmu); + return 0; out_destroy_pgtable: - kvm_pgtable_stage2_destroy(pgt); + kvm_stage2_destroy(pgt); out_free_pgtable: kfree(pgt); return err; } +void kvm_uninit_stage2_mmu(struct kvm *kvm) +{ + kvm_free_stage2_pgd(&kvm->arch.mmu); + kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); +} + static void stage2_unmap_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { @@ -802,7 +1060,7 @@ static void stage2_unmap_memslot(struct kvm *kvm, if (!(vma->vm_flags & VM_PFNMAP)) { gpa_t gpa = addr + (vm_start - memslot->userspace_addr); - unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start); + kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true); } hva = vm_end; } while (hva < reg_end); @@ -829,6 +1087,8 @@ void stage2_unmap_vm(struct kvm *kvm) kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); + kvm_nested_s2_unmap(kvm, true); + write_unlock(&kvm->mmu_lock); mmap_read_unlock(current->mm); srcu_read_unlock(&kvm->srcu, idx); @@ -846,29 +1106,47 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } + + if (kvm_is_nested_s2_mmu(kvm, mmu)) + kvm_init_nested_s2_mmu(mmu); + write_unlock(&kvm->mmu_lock); if (pgt) { - kvm_pgtable_stage2_destroy(pgt); + kvm_stage2_destroy(pgt); kfree(pgt); } } -static void hyp_mc_free_fn(void *addr, void *unused) +static void hyp_mc_free_fn(void *addr, void *mc) { + struct kvm_hyp_memcache *memcache = mc; + + if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) + kvm_account_pgtable_pages(addr, -1); + free_page((unsigned long)addr); } -static void *hyp_mc_alloc_fn(void *unused) +static void *hyp_mc_alloc_fn(void *mc) { - return (void *)__get_free_page(GFP_KERNEL_ACCOUNT); + struct kvm_hyp_memcache *memcache = mc; + void *addr; + + addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); + if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) + kvm_account_pgtable_pages(addr, 1); + + return addr; } void free_hyp_memcache(struct kvm_hyp_memcache *mc) { - if (is_protected_kvm_enabled()) - __free_hyp_memcache(mc, hyp_mc_free_fn, - kvm_host_va, NULL); + if (!is_protected_kvm_enabled()) + return; + + kfree(mc->mapping); + __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) @@ -876,8 +1154,14 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) if (!is_protected_kvm_enabled()) return 0; + if (!mc->mapping) { + mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT); + if (!mc->mapping) + return -ENOMEM; + } + return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, - kvm_host_pa, NULL); + kvm_host_pa, mc); } /** @@ -895,7 +1179,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t addr; int ret = 0; struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; - struct kvm_pgtable *pgt = kvm->arch.mmu.pgt; + struct kvm_s2_mmu *mmu = &kvm->arch.mmu; + struct kvm_pgtable *pgt = mmu->pgt; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); @@ -908,13 +1193,13 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) { ret = kvm_mmu_topup_memory_cache(&cache, - kvm_mmu_cache_min_pages(kvm)); + kvm_mmu_cache_min_pages(mmu)); if (ret) break; write_lock(&kvm->mmu_lock); - ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot, - &cache, 0); + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE, + pa, prot, &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; @@ -927,15 +1212,14 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, } /** - * stage2_wp_range() - write protect stage2 memory region range + * kvm_stage2_wp_range() - write protect stage2 memory region range * @mmu: The KVM stage-2 MMU pointer * @addr: Start address of range * @end: End address of range */ -static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) +void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { - struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); - stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect); + stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect)); } /** @@ -964,45 +1248,75 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); - stage2_wp_range(&kvm->arch.mmu, start, end); + kvm_stage2_wp_range(&kvm->arch.mmu, start, end); + kvm_nested_s2_wp(kvm); write_unlock(&kvm->mmu_lock); - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_memslot(kvm, memslot); } /** - * kvm_mmu_write_protect_pt_masked() - write protect dirty pages + * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE + * pages for memory slot * @kvm: The KVM pointer - * @slot: The memory slot associated with mask - * @gfn_offset: The gfn offset in memory slot - * @mask: The mask of dirty pages at offset 'gfn_offset' in this memory - * slot to be write protected + * @slot: The memory slot to split * - * Walks bits set in mask write protects the associated pte's. Caller must - * acquire kvm_mmu_lock. + * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired, + * serializing operations for VM memory regions. */ -static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask) +static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot) { - phys_addr_t base_gfn = slot->base_gfn + gfn_offset; - phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; - phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + phys_addr_t start, end; + + lockdep_assert_held(&kvm->slots_lock); - stage2_wp_range(&kvm->arch.mmu, start, end); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, slot); + + start = memslot->base_gfn << PAGE_SHIFT; + end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + + write_lock(&kvm->mmu_lock); + kvm_mmu_split_huge_pages(kvm, start, end); + write_unlock(&kvm->mmu_lock); } /* - * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected - * dirty pages. + * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages. + * @kvm: The KVM pointer + * @slot: The memory slot associated with mask + * @gfn_offset: The gfn offset in memory slot + * @mask: The mask of pages at offset 'gfn_offset' in this memory + * slot to enable dirty logging on * - * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to - * enable dirty logging for them. + * Writes protect selected pages to enable dirty logging, and then + * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); + phys_addr_t base_gfn = slot->base_gfn + gfn_offset; + phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; + phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + + lockdep_assert_held_write(&kvm->mmu_lock); + + kvm_stage2_wp_range(&kvm->arch.mmu, start, end); + + /* + * Eager-splitting is done when manual-protect is set. We + * also check for initially-all-set because we can avoid + * eager-splitting if initially-all-set is false. + * Initially-all-set equal false implies that huge-pages were + * already split when enabling dirty logging: no need to do it + * again. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + kvm_mmu_split_huge_pages(kvm, start, end); + + kvm_nested_s2_wp(kvm); } static void kvm_send_hwpoison_signal(unsigned long address, short lsb) @@ -1022,6 +1336,10 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, if (map_size == PAGE_SIZE) return true; + /* pKVM only supports PMD_SIZE huge-mappings */ + if (is_protected_kvm_enabled() && map_size != PMD_SIZE) + return false; + size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; @@ -1079,7 +1397,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, * * Returns the size of the mapping. */ -static unsigned long +static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) @@ -1091,30 +1409,17 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ - if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) && - get_user_mapping_size(kvm, hva) >= PMD_SIZE) { - /* - * The address we faulted on is backed by a transparent huge - * page. However, because we map the compound huge page and - * not the individual tail page, we need to transfer the - * refcount to the head page. We have to be careful that the - * THP doesn't start to split while we are adjusting the - * refcounts. - * - * We are sure this doesn't happen, because mmu_invalidate_retry - * was successful and we are holding the mmu_lock, so if this - * THP is trying to split, it will be blocked in the mmu - * notifier before touching any of the pages, specifically - * before being able to call __split_huge_page_refcount(). - * - * We can therefore safely transfer the refcount from PG_tail - * to PG_head and switch the pfn from a tail page to the head - * page accordingly. - */ + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + int sz = get_user_mapping_size(kvm, hva); + + if (sz < 0) + return sz; + + if (sz < PMD_SIZE) + return PAGE_SIZE; + *ipap &= PMD_MASK; - kvm_release_pfn_clean(pfn); pfn &= ~(PTRS_PER_PMD - 1); - get_page(pfn_to_page(pfn)); *pfnp = pfn; return PMD_SIZE; @@ -1158,21 +1463,29 @@ static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) * able to see the page's tags and therefore they must be initialised first. If * PG_mte_tagged is set, tags have already been initialised. * - * The race in the test/set of the PG_mte_tagged flag is handled by: - * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs - * racing to santise the same page - * - mmap_lock protects between a VM faulting a page in and the VMM performing - * an mprotect() to add VM_MTE + * Must be called with kvm->mmu_lock held to ensure the memory remains mapped + * while the tags are zeroed. */ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, unsigned long size) { unsigned long i, nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(pfn); + struct folio *folio = page_folio(page); if (!kvm_has_mte(kvm)) return; + if (folio_test_hugetlb(folio)) { + /* Hugetlb has MTE flags set on head page only */ + if (folio_try_hugetlb_mte_tagging(folio)) { + for (i = 0; i < nr_pages; i++, page++) + mte_clear_page_tags(page_address(page)); + folio_set_hugetlb_mte_tagged(folio); + } + return; + } + for (i = 0; i < nr_pages; i++, page++) { if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); @@ -1186,36 +1499,190 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma) return vma->vm_flags & VM_MTE_ALLOWED; } +static bool kvm_vma_is_cacheable(struct vm_area_struct *vma) +{ + switch (FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot))) { + case MT_NORMAL_NC: + case MT_DEVICE_nGnRnE: + case MT_DEVICE_nGnRE: + return false; + default: + return true; + } +} + +static int prepare_mmu_memcache(struct kvm_vcpu *vcpu, bool topup_memcache, + void **memcache) +{ + int min_pages; + + if (!is_protected_kvm_enabled()) + *memcache = &vcpu->arch.mmu_page_cache; + else + *memcache = &vcpu->arch.pkvm_memcache; + + if (!topup_memcache) + return 0; + + min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); + + if (!is_protected_kvm_enabled()) + return kvm_mmu_topup_memory_cache(*memcache, min_pages); + + return topup_hyp_memcache(*memcache, min_pages); +} + +/* + * Potentially reduce shadow S2 permissions to match the guest's own S2. For + * exec faults, we'd only reach this point if the guest actually allowed it (see + * kvm_s2_handle_perm_fault). + * + * Also encode the level of the original translation in the SW bits of the leaf + * entry as a proxy for the span of that translation. This will be retrieved on + * TLB invalidation from the guest and used to limit the invalidation scope if a + * TTL hint or a range isn't provided. + */ +static void adjust_nested_fault_perms(struct kvm_s2_trans *nested, + enum kvm_pgtable_prot *prot, + bool *writable) +{ + *writable &= kvm_s2_trans_writable(nested); + if (!kvm_s2_trans_readable(nested)) + *prot &= ~KVM_PGTABLE_PROT_R; + + *prot |= kvm_encode_nested_level(nested); +} + +static void adjust_nested_exec_perms(struct kvm *kvm, + struct kvm_s2_trans *nested, + enum kvm_pgtable_prot *prot) +{ + if (!kvm_s2_trans_exec_el0(kvm, nested)) + *prot &= ~KVM_PGTABLE_PROT_UX; + if (!kvm_s2_trans_exec_el1(kvm, nested)) + *prot &= ~KVM_PGTABLE_PROT_PX; +} + +#define KVM_PGTABLE_WALK_MEMABORT_FLAGS (KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED) + +static int gmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, + struct kvm_s2_trans *nested, + struct kvm_memory_slot *memslot, bool is_perm) +{ + bool write_fault, exec_fault, writable; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS; + enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; + struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt; + unsigned long mmu_seq; + struct page *page; + struct kvm *kvm = vcpu->kvm; + void *memcache; + kvm_pfn_t pfn; + gfn_t gfn; + int ret; + + ret = prepare_mmu_memcache(vcpu, true, &memcache); + if (ret) + return ret; + + if (nested) + gfn = kvm_s2_trans_output(nested) >> PAGE_SHIFT; + else + gfn = fault_ipa >> PAGE_SHIFT; + + write_fault = kvm_is_write_fault(vcpu); + exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); + + VM_WARN_ON_ONCE(write_fault && exec_fault); + + mmu_seq = kvm->mmu_invalidate_seq; + /* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */ + smp_rmb(); + + ret = kvm_gmem_get_pfn(kvm, memslot, gfn, &pfn, &page, NULL); + if (ret) { + kvm_prepare_memory_fault_exit(vcpu, fault_ipa, PAGE_SIZE, + write_fault, exec_fault, false); + return ret; + } + + writable = !(memslot->flags & KVM_MEM_READONLY); + + if (nested) + adjust_nested_fault_perms(nested, &prot, &writable); + + if (writable) + prot |= KVM_PGTABLE_PROT_W; + + if (exec_fault || cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) + prot |= KVM_PGTABLE_PROT_X; + + if (nested) + adjust_nested_exec_perms(kvm, nested, &prot); + + kvm_fault_lock(kvm); + if (mmu_invalidate_retry(kvm, mmu_seq)) { + ret = -EAGAIN; + goto out_unlock; + } + + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, PAGE_SIZE, + __pfn_to_phys(pfn), prot, + memcache, flags); + +out_unlock: + kvm_release_faultin_page(kvm, page, !!ret, writable); + kvm_fault_unlock(kvm); + + if (writable && !ret) + mark_page_dirty_in_slot(kvm, memslot, gfn); + + return ret != -EAGAIN ? ret : 0; +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, + struct kvm_s2_trans *nested, struct kvm_memory_slot *memslot, unsigned long hva, - unsigned long fault_status) + bool fault_is_perm) { int ret = 0; - bool write_fault, writable, force_pte = false; - bool exec_fault; - bool device = false; + bool topup_memcache; + bool write_fault, writable; + bool exec_fault, mte_allowed, is_vma_cacheable; + bool s2_force_noncacheable = false, vfio_allow_any_uc = false; unsigned long mmu_seq; + phys_addr_t ipa = fault_ipa; struct kvm *kvm = vcpu->kvm; - struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; short vma_shift; + void *memcache; gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); - unsigned long vma_pagesize, fault_granule; + bool force_pte = logging_active; + long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; + struct page *page; + vm_flags_t vm_flags; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_MEMABORT_FLAGS; - fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level); + if (fault_is_perm) + fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); - VM_BUG_ON(write_fault && exec_fault); + VM_WARN_ON_ONCE(write_fault && exec_fault); - if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) { - kvm_err("Unexpected L2 read permission error\n"); - return -EFAULT; - } + /* + * Permission faults just need to update the existing leaf entry, + * and so normally don't require allocations from the memcache. The + * only exception to this is when dirty logging is enabled at runtime + * and a write fault needs to collapse a block entry into a table. + */ + topup_memcache = !fault_is_perm || (logging_active && write_fault); + ret = prepare_mmu_memcache(vcpu, topup_memcache, &memcache); + if (ret) + return ret; /* * Let's check if we will get back a huge page backed by hugetlbfs, or @@ -1229,16 +1696,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - /* - * logging_active is guaranteed to never be true for VM_PFNMAP - * memslots. - */ - if (logging_active) { - force_pte = true; + if (force_pte) vma_shift = PAGE_SHIFT; - } else { + else vma_shift = get_vma_page_shift(vma, hva); - } switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED @@ -1265,44 +1726,69 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } vma_pagesize = 1UL << vma_shift; - if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) - fault_ipa &= ~(vma_pagesize - 1); - gfn = fault_ipa >> PAGE_SHIFT; - mmap_read_unlock(current->mm); + if (nested) { + unsigned long max_map_size; + + max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE; + + ipa = kvm_s2_trans_output(nested); + + /* + * If we're about to create a shadow stage 2 entry, then we + * can only create a block mapping if the guest stage 2 page + * table uses at least as big a mapping. + */ + max_map_size = min(kvm_s2_trans_size(nested), max_map_size); + + /* + * Be careful that if the mapping size falls between + * two host sizes, take the smallest of the two. + */ + if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE) + max_map_size = PMD_SIZE; + else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE) + max_map_size = PAGE_SIZE; + + force_pte = (max_map_size == PAGE_SIZE); + vma_pagesize = min_t(long, vma_pagesize, max_map_size); + } /* - * Permission faults just need to update the existing leaf entry, - * and so normally don't require allocations from the memcache. The - * only exception to this is when dirty logging is enabled at runtime - * and a write fault needs to collapse a block entry into a table. + * Both the canonical IPA and fault IPA must be hugepage-aligned to + * ensure we find the right PFN and lay down the mapping in the right + * place. */ - if (fault_status != ESR_ELx_FSC_PERM || - (logging_active && write_fault)) { - ret = kvm_mmu_topup_memory_cache(memcache, - kvm_mmu_cache_min_pages(kvm)); - if (ret) - return ret; + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { + fault_ipa &= ~(vma_pagesize - 1); + ipa &= ~(vma_pagesize - 1); } - mmu_seq = vcpu->kvm->mmu_invalidate_seq; + gfn = ipa >> PAGE_SHIFT; + mte_allowed = kvm_vma_mte_allowed(vma); + + vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED; + + vm_flags = vma->vm_flags; + + is_vma_cacheable = kvm_vma_is_cacheable(vma); + + /* Don't use the VMA after the unlock -- it may have vanished */ + vma = NULL; + /* - * Ensure the read of mmu_invalidate_seq happens before we call - * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk - * the page we just got a reference to gets unmapped before we have a - * chance to grab the mmu_lock, which ensure that if the page gets - * unmapped afterwards, the call to kvm_unmap_gfn will take it away - * from us again properly. This smp_rmb() interacts with the smp_wmb() - * in kvm_mmu_notifier_invalidate_<page|range_end>. + * Read mmu_invalidate_seq so that KVM can detect if the results of + * vma_lookup() or __kvm_faultin_pfn() become stale prior to + * acquiring kvm->mmu_lock. * - * Besides, __gfn_to_pfn_memslot() instead of gfn_to_pfn_prot() is - * used to avoid unnecessary overhead introduced to locate the memory - * slot because it's always fixed even @gfn is adjusted for huge pages. + * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs + * with the smp_wmb() in kvm_mmu_invalidate_end(). */ - smp_rmb(); + mmu_seq = kvm->mmu_invalidate_seq; + mmap_read_unlock(current->mm); - pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, - write_fault, &writable, NULL); + pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, + &writable, &page); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); return 0; @@ -1310,18 +1796,39 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (is_error_noslot_pfn(pfn)) return -EFAULT; - if (kvm_is_device_pfn(pfn)) { - /* - * If the page was identified as device early by looking at - * the VMA flags, vma_pagesize is already representing the - * largest quantity we can map. If instead it was mapped - * via gfn_to_pfn_prot(), vma_pagesize is set to PAGE_SIZE - * and must not be upgraded. - * - * In both cases, we don't let transparent_hugepage_adjust() - * change things at the last minute. - */ - device = true; + /* + * Check if this is non-struct page memory PFN, and cannot support + * CMOs. It could potentially be unsafe to access as cacheable. + */ + if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP) && !pfn_is_map_memory(pfn)) { + if (is_vma_cacheable) { + /* + * Whilst the VMA owner expects cacheable mapping to this + * PFN, hardware also has to support the FWB and CACHE DIC + * features. + * + * ARM64 KVM relies on kernel VA mapping to the PFN to + * perform cache maintenance as the CMO instructions work on + * virtual addresses. VM_PFNMAP region are not necessarily + * mapped to a KVA and hence the presence of hardware features + * S2FWB and CACHE DIC are mandatory to avoid the need for + * cache maintenance. + */ + if (!kvm_supports_cacheable_pfnmap()) + ret = -EFAULT; + } else { + /* + * If the page was identified as device early by looking at + * the VMA flags, vma_pagesize is already representing the + * largest quantity we can map. If instead it was mapped + * via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE + * and must not be upgraded. + * + * In both cases, we don't let transparent_hugepage_adjust() + * change things at the last minute. + */ + s2_force_noncacheable = true; + } } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write @@ -1330,31 +1837,45 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, writable = false; } - if (exec_fault && device) - return -ENOEXEC; + if (exec_fault && s2_force_noncacheable) + ret = -ENOEXEC; - read_lock(&kvm->mmu_lock); + if (ret) { + kvm_release_page_unused(page); + return ret; + } + + if (nested) + adjust_nested_fault_perms(nested, &prot, &writable); + + kvm_fault_lock(kvm); pgt = vcpu->arch.hw_mmu->pgt; - if (mmu_invalidate_retry(kvm, mmu_seq)) + if (mmu_invalidate_retry(kvm, mmu_seq)) { + ret = -EAGAIN; goto out_unlock; + } /* * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ - if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { - if (fault_status == ESR_ELx_FSC_PERM && - fault_granule > PAGE_SIZE) + if (vma_pagesize == PAGE_SIZE && !(force_pte || s2_force_noncacheable)) { + if (fault_is_perm && fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); + + if (vma_pagesize < 0) { + ret = vma_pagesize; + goto out_unlock; + } } - if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) { + if (!fault_is_perm && !s2_force_noncacheable && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ - if (kvm_vma_mte_allowed(vma)) { + if (mte_allowed) { sanitise_mte_tags(kvm, pfn, vma_pagesize); } else { ret = -EFAULT; @@ -1368,53 +1889,138 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (exec_fault) prot |= KVM_PGTABLE_PROT_X; - if (device) - prot |= KVM_PGTABLE_PROT_DEVICE; - else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) + if (s2_force_noncacheable) { + if (vfio_allow_any_uc) + prot |= KVM_PGTABLE_PROT_NORMAL_NC; + else + prot |= KVM_PGTABLE_PROT_DEVICE; + } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) { prot |= KVM_PGTABLE_PROT_X; + } + + if (nested) + adjust_nested_exec_perms(kvm, nested, &prot); /* * Under the premise of getting a FSC_PERM fault, we just need to relax * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ - if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule) - ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); - else - ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, + if (fault_is_perm && vma_pagesize == fault_granule) { + /* + * Drop the SW bits in favour of those stored in the + * PTE, which will be preserved. + */ + prot &= ~KVM_NV_GUEST_MAP_SZ; + ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags); + } else { + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, - memcache, KVM_PGTABLE_WALK_SHARED); + memcache, flags); + } + +out_unlock: + kvm_release_faultin_page(kvm, page, !!ret, writable); + kvm_fault_unlock(kvm); /* Mark the page dirty only if the fault is handled successfully */ - if (writable && !ret) { - kvm_set_pfn_dirty(pfn); + if (writable && !ret) mark_page_dirty_in_slot(kvm, memslot, gfn); - } -out_unlock: - read_unlock(&kvm->mmu_lock); - kvm_set_pfn_accessed(pfn); - kvm_release_pfn_clean(pfn); return ret != -EAGAIN ? ret : 0; } /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { - pte_t pte; - kvm_pte_t kpte; + enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); - write_lock(&vcpu->kvm->mmu_lock); + read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; - kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); - write_unlock(&vcpu->kvm->mmu_lock); + KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags); + read_unlock(&vcpu->kvm->mmu_lock); +} - pte = __pte(kpte); - if (pte_valid(pte)) - kvm_set_pfn_accessed(pte_pfn(pte)); +/* + * Returns true if the SEA should be handled locally within KVM if the abort + * is caused by a kernel memory allocation (e.g. stage-2 table memory). + */ +static bool host_owns_sea(struct kvm_vcpu *vcpu, u64 esr) +{ + /* + * Without FEAT_RAS HCR_EL2.TEA is RES0, meaning any external abort + * taken from a guest EL to EL2 is due to a host-imposed access (e.g. + * stage-2 PTW). + */ + if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + return true; + + /* KVM owns the VNCR when the vCPU isn't in a nested context. */ + if (is_hyp_ctxt(vcpu) && !kvm_vcpu_trap_is_iabt(vcpu) && (esr & ESR_ELx_VNCR)) + return true; + + /* + * Determining if an external abort during a table walk happened at + * stage-2 is only possible with S1PTW is set. Otherwise, since KVM + * sets HCR_EL2.TEA, SEAs due to a stage-1 walk (i.e. accessing the + * PA of the stage-1 descriptor) can reach here and are reported + * with a TTW ESR value. + */ + return (esr_fsc_is_sea_ttw(esr) && (esr & ESR_ELx_S1PTW)); +} + +int kvm_handle_guest_sea(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_run *run = vcpu->run; + u64 esr = kvm_vcpu_get_esr(vcpu); + u64 esr_mask = ESR_ELx_EC_MASK | + ESR_ELx_IL | + ESR_ELx_FnV | + ESR_ELx_EA | + ESR_ELx_CM | + ESR_ELx_WNR | + ESR_ELx_FSC; + u64 ipa; + + /* + * Give APEI the opportunity to claim the abort before handling it + * within KVM. apei_claim_sea() expects to be called with IRQs enabled. + */ + lockdep_assert_irqs_enabled(); + if (apei_claim_sea(NULL) == 0) + return 1; + + if (host_owns_sea(vcpu, esr) || + !test_bit(KVM_ARCH_FLAG_EXIT_SEA, &vcpu->kvm->arch.flags)) + return kvm_inject_serror(vcpu); + + /* ESR_ELx.SET is RES0 when FEAT_RAS isn't implemented. */ + if (kvm_has_ras(kvm)) + esr_mask |= ESR_ELx_SET_MASK; + + /* + * Exit to userspace, and provide faulting guest virtual and physical + * addresses in case userspace wants to emulate SEA to guest by + * writing to FAR_ELx and HPFAR_ELx registers. + */ + memset(&run->arm_sea, 0, sizeof(run->arm_sea)); + run->exit_reason = KVM_EXIT_ARM_SEA; + run->arm_sea.esr = esr & esr_mask; + + if (!(esr & ESR_ELx_FnV)) + run->arm_sea.gva = kvm_vcpu_get_hfar(vcpu); + + ipa = kvm_vcpu_get_fault_ipa(vcpu); + if (ipa != INVALID_GPA) { + run->arm_sea.flags |= KVM_EXIT_ARM_SEA_FLAG_GPA_VALID; + run->arm_sea.gpa = ipa; + } + + return 0; } /** @@ -1430,20 +2036,32 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) { - unsigned long fault_status; - phys_addr_t fault_ipa; + struct kvm_s2_trans nested_trans, *nested = NULL; + unsigned long esr; + phys_addr_t fault_ipa; /* The address we faulted on */ + phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */ struct kvm_memory_slot *memslot; unsigned long hva; bool is_iabt, write_fault, writable; gfn_t gfn; int ret, idx; - fault_status = kvm_vcpu_trap_get_fault_type(vcpu); + if (kvm_vcpu_abt_issea(vcpu)) + return kvm_handle_guest_sea(vcpu); + + esr = kvm_vcpu_get_esr(vcpu); + + /* + * The fault IPA should be reliable at this point as we're not dealing + * with an SEA. + */ + ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm)) + return -EFAULT; - fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); - if (fault_status == ESR_ELx_FSC_FAULT) { + if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); @@ -1451,36 +2069,20 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) } /* Falls between the IPA range and the PARange? */ - if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) { fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); - if (is_iabt) - kvm_inject_pabt(vcpu, fault_ipa); - else - kvm_inject_dabt(vcpu, fault_ipa); - return 1; + return kvm_inject_sea(vcpu, is_iabt, fault_ipa); } } - /* Synchronous External Abort? */ - if (kvm_vcpu_abt_issea(vcpu)) { - /* - * For RAS the host kernel may handle this abort. - * There is no need to pass the error into the guest. - */ - if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu))) - kvm_inject_vabt(vcpu); - - return 1; - } - trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - if (fault_status != ESR_ELx_FSC_FAULT && - fault_status != ESR_ELx_FSC_PERM && - fault_status != ESR_ELx_FSC_ACCESS) { + if (!esr_fsc_is_translation_fault(esr) && + !esr_fsc_is_permission_fault(esr) && + !esr_fsc_is_access_flag_fault(esr)) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1490,7 +2092,47 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) idx = srcu_read_lock(&vcpu->kvm->srcu); - gfn = fault_ipa >> PAGE_SHIFT; + /* + * We may have faulted on a shadow stage 2 page table if we are + * running a nested guest. In this case, we have to resolve the L2 + * IPA to the L1 IPA first, before knowing what kind of memory should + * back the L1 IPA. + * + * If the shadow stage 2 page table walk faults, then we simply inject + * this to the guest and carry on. + * + * If there are no shadow S2 PTs because S2 is disabled, there is + * nothing to walk and we treat it as a 1:1 before going through the + * canonical translation. + */ + if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) && + vcpu->arch.hw_mmu->nested_stage2_enabled) { + u32 esr; + + ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans); + if (ret == -EAGAIN) { + ret = 1; + goto out_unlock; + } + + if (ret) { + esr = kvm_s2_trans_esr(&nested_trans); + kvm_inject_s2_fault(vcpu, esr); + goto out_unlock; + } + + ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans); + if (ret) { + esr = kvm_s2_trans_esr(&nested_trans); + kvm_inject_s2_fault(vcpu, esr); + goto out_unlock; + } + + ipa = kvm_s2_trans_output(&nested_trans); + nested = &nested_trans; + } + + gfn = ipa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); write_fault = kvm_is_write_fault(vcpu); @@ -1507,8 +2149,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) } if (kvm_vcpu_abt_iss1tw(vcpu)) { - kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; + ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); goto out_unlock; } @@ -1534,28 +2175,34 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) * faulting VA. This is always 12 bits, irrespective * of the page size. */ - fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1); - ret = io_mem_abort(vcpu, fault_ipa); + ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + ret = io_mem_abort(vcpu, ipa); goto out_unlock; } /* Userspace should not be able to register out-of-bounds IPAs */ - VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm)); + VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu)); - if (fault_status == ESR_ELx_FSC_ACCESS) { + if (esr_fsc_is_access_flag_fault(esr)) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; } - ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); + VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) && + !write_fault && !kvm_vcpu_trap_is_exec_fault(vcpu)); + + if (kvm_slot_has_gmem(memslot)) + ret = gmem_abort(vcpu, fault_ipa, nested, memslot, + esr_fsc_is_permission_fault(esr)); + else + ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva, + esr_fsc_is_permission_fault(esr)); if (ret == 0) ret = 1; out: - if (ret == -ENOEXEC) { - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; - } + if (ret == -ENOEXEC) + ret = kvm_inject_sea_iabt(vcpu, kvm_vcpu_get_hfar(vcpu)); out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; @@ -1570,67 +2217,36 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) (range->end - range->start) << PAGE_SHIFT, range->may_block); + kvm_nested_s2_unmap(kvm, range->may_block); return false; } -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - kvm_pfn_t pfn = pte_pfn(range->pte); + u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; - WARN_ON(range->end - range->start != 1); - + return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, + range->start << PAGE_SHIFT, + size, true); /* - * If the page isn't tagged, defer to user_mem_abort() for sanitising - * the MTE tags. The S2 pte should have been unmapped by - * mmu_notifier_invalidate_range_end(). + * TODO: Handle nested_mmu structures here using the reverse mapping in + * a later version of patch series. */ - if (kvm_has_mte(kvm) && !page_mte_tagged(pfn_to_page(pfn))) - return false; - - /* - * We've moved a page around, probably through CoW, so let's treat - * it just like a translation fault and the map handler will clean - * the cache to the PoC. - * - * The MMU notifiers will have unmapped a huge PMD before calling - * ->change_pte() (which in turn calls kvm_set_spte_gfn()) and - * therefore we never need to clear out a huge PMD through this - * calling path and a memcache is not required. - */ - kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, - PAGE_SIZE, __pfn_to_phys(pfn), - KVM_PGTABLE_PROT_R, NULL, 0); - - return false; } -bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; - kvm_pte_t kpte; - pte_t pte; if (!kvm->arch.mmu.pgt) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); - - kpte = kvm_pgtable_stage2_mkold(kvm->arch.mmu.pgt, - range->start << PAGE_SHIFT); - pte = __pte(kpte); - return pte_valid(pte) && pte_young(pte); -} - -bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) -{ - if (!kvm->arch.mmu.pgt) - return false; - - return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, - range->start << PAGE_SHIFT); + return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, + range->start << PAGE_SHIFT, + size, false); } phys_addr_t kvm_mmu_get_httbr(void) @@ -1668,7 +2284,7 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .virt_to_phys = kvm_host_pa, }; -int kvm_mmu_init(u32 *hyp_va_bits) +int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; @@ -1687,16 +2303,9 @@ int kvm_mmu_init(u32 *hyp_va_bits) BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* - * The ID map may be configured to use an extended virtual address - * range. This is only the case if system RAM is out of range for the - * currently configured page size and VA_BITS_MIN, in which case we will - * also need the extended virtual range for the HYP ID map, or we won't - * be able to enable the EL2 MMU. - * - * However, in some cases the ID map may be configured for fewer than - * the number of VA bits used by the regular kernel stage 1. This - * happens when VA_BITS=52 and the kernel image is placed in PA space - * below 48 bits. + * The ID map is always configured for 48 bits of translation, which + * may be fewer than the number of VA bits used by the regular kernel + * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom @@ -1707,7 +2316,7 @@ int kvm_mmu_init(u32 *hyp_va_bits) * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ - idmap_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET); + idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); @@ -1745,6 +2354,7 @@ int kvm_mmu_init(u32 *hyp_va_bits) goto out_destroy_pgtable; io_map_base = hyp_idmap_start; + __hyp_va_bits = *hyp_va_bits; return 0; out_destroy_pgtable: @@ -1761,20 +2371,42 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { + bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES; + /* * At this point memslot has been committed and there is an * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ - if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (log_dirty_pages) { + + if (change == KVM_MR_DELETE) + return; + /* - * If we're with initial-all-set, we don't need to write - * protect any pages because they're all reported as dirty. - * Huge pages and normal pages will be write protect gradually. + * Huge and normal pages are write-protected and split + * on either of these two cases: + * + * 1. with initial-all-set: gradually with CLEAR ioctls, */ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) { - kvm_mmu_wp_memory_region(kvm, new->id); - } + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; + /* + * or + * 2. without initial-all-set: all in one shot when + * enabling dirty logging. + */ + kvm_mmu_wp_memory_region(kvm, new->id); + kvm_mmu_split_memory_region(kvm, new->id); + } else { + /* + * Free any leftovers from the eager page splitting cache. Do + * this when deleting, moving, disabling dirty logging, or + * creating the memslot (a nop). Doing it for deletes makes + * sure we don't leak memory, and there's no need to keep the + * cache around for any of the other cases. + */ + kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } } @@ -1794,9 +2426,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT)) return -EFAULT; + /* + * Only support guest_memfd backed memslots with mappable memory, since + * there aren't any CoCo VMs that support only private memory on arm64. + */ + if (kvm_slot_has_gmem(new) && !kvm_memslot_is_gmem_only(new)) + return -EINVAL; + hva = new->userspace_addr; reg_end = hva + (new->npages << PAGE_SHIFT); @@ -1830,6 +2469,15 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, ret = -EINVAL; break; } + + /* + * Cacheable PFNMAP is allowed only if the hardware + * supports it. + */ + if (kvm_vma_is_cacheable(vma) && !kvm_supports_cacheable_pfnmap()) { + ret = -EINVAL; + break; + } } hva = min(reg_end, vma->vm_end); } while (hva < reg_end); @@ -1846,11 +2494,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } -void kvm_arch_flush_shadow_all(struct kvm *kvm) -{ - kvm_free_stage2_pgd(&kvm->arch.mmu); -} - void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { @@ -1858,7 +2501,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, phys_addr_t size = slot->npages << PAGE_SHIFT; write_lock(&kvm->mmu_lock); - unmap_stage2_range(&kvm->arch.mmu, gpa, size); + kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true); + kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); } |