KVM: arm64: Convert translation level parameter to s8

With the introduction of FEAT_LPA2, the Arm ARM adds a new level of
translation, level -1, so levels can now be in the range [-1;3]. 3 is
always the last level and the first level is determined based on the
number of VA bits in use.

Convert level variables to use a signed type in preparation for
supporting this new level -1.

Since the last level is always anchored at 3, and the first level varies
to suit the number of VA/IPA bits, take the opportunity to replace
KVM_PGTABLE_MAX_LEVELS with the 2 macros KVM_PGTABLE_FIRST_LEVEL and
KVM_PGTABLE_LAST_LEVEL. This removes the assumption from the code that
levels run from 0 to KVM_PGTABLE_MAX_LEVELS - 1, which will soon no
longer be true.

Reviewed-by: Oliver Upton <[e-mail]>
Signed-off-by: Ryan Roberts <[e-mail]>
Signed-off-by: Marc Zyngier <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/arm64/include/asm/kvm_emulate.h

···
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+static __always_inline s8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
 }

arch/arm64/include/asm/kvm_pgtable.h

···
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 
-#define KVM_PGTABLE_MAX_LEVELS		4U
+#define KVM_PGTABLE_FIRST_LEVEL		0
+#define KVM_PGTABLE_LAST_LEVEL		3
 
 /*
  * The largest supported block sizes for KVM (no 52-bit PA support):
···
  *  - 64K (level 2):	512MB
  */
 #ifdef CONFIG_ARM64_4K_PAGES
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1
 #else
-#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2
 #endif
 
 #define kvm_lpa2_is_enabled()		system_supports_lpa2()
···
 	return __phys_to_pfn(kvm_pte_to_phys(pte));
 }
 
-static inline u64 kvm_granule_shift(u32 level)
+static inline u64 kvm_granule_shift(s8 level)
 {
-	/* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+	/* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */
 	return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
 }
 
-static inline u64 kvm_granule_size(u32 level)
+static inline u64 kvm_granule_size(s8 level)
 {
 	return BIT(kvm_granule_shift(level));
 }
 
-static inline bool kvm_level_supports_block_mapping(u32 level)
+static inline bool kvm_level_supports_block_mapping(s8 level)
 {
 	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
 static inline u32 kvm_supported_block_sizes(void)
 {
-	u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+	s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
 	u32 r = 0;
 
-	for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++)
 		r |= BIT(kvm_granule_shift(level));
 
 	return r;
···
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
-	void		(*free_unlinked_table)(void *addr, u32 level);
+	void		(*free_unlinked_table)(void *addr, s8 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
···
 	u64					start;
 	u64					addr;
 	u64					end;
-	u32					level;
+	s8					level;
 	enum kvm_pgtable_walk_flags		flags;
 };
 
···
  */
 struct kvm_pgtable {
 	u32					ia_bits;
-	u32					start_level;
+	s8					start_level;
 	kvm_pteref_t				pgd;
 	struct kvm_pgtable_mm_ops		*mm_ops;
 
···
  * The page-table is assumed to be unreachable by any hardware walkers prior to
  * freeing and therefore no TLB invalidation is performed.
  */
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
 
 /**
  * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
···
  * an ERR_PTR(error) on failure.
  */
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte);
 
···
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level);
+			 kvm_pte_t *ptep, s8 *level);
 
 /**
  * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a

arch/arm64/include/asm/kvm_pkvm.h

···
 
 static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
 {
-	unsigned long total = 0, i;
+	unsigned long total = 0;
+	int i;
 
 	/* Provision the worst case scenario */
-	for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+	for (i = KVM_PGTABLE_FIRST_LEVEL; i <= KVM_PGTABLE_LAST_LEVEL; i++) {
 		nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
 		total += nr_pages;
 	}

arch/arm64/kvm/hyp/nvhe/mem_protect.c

···
 	hyp_put_page(&host_s2_pool, addr);
 }
 
-static void host_s2_free_unlinked_table(void *addr, u32 level)
+static void host_s2_free_unlinked_table(void *addr, s8 level)
 {
 	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
 }
···
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
-	u32 level;
+	s8 level;
 	int ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
···
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
 		level++;
-	} while ((level < KVM_PGTABLE_MAX_LEVELS) &&
+	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
 			!(kvm_level_supports_block_mapping(level) &&
 			  range_included(&cur, range)));
 

arch/arm64/kvm/hyp/nvhe/mm.c

···
 	 * https://lore.kernel.org/kvm/[e-mail]/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03
 	 */
 	dsb(ishst);
-	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), (KVM_PGTABLE_MAX_LEVELS - 1));
+	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), KVM_PGTABLE_LAST_LEVEL);
 	dsb(ish);
 	isb();
 }
···
 {
 	struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg);
 
-	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_MAX_LEVELS - 1)
+	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	slot->addr = ctx->addr;

arch/arm64/kvm/hyp/nvhe/setup.c

···
 	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1))
+	if (ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	phys = kvm_pte_to_phys(ctx->old);

arch/arm64/kvm/hyp/pgtable.c

···
 	return IS_ALIGNED(ctx->addr, granule);
 }
 
-static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
+static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level)
 {
 	u64 shift = kvm_granule_shift(level);
 	u64 mask = BIT(PAGE_SHIFT - 3) - 1;
···
 	return (addr & mask) >> shift;
 }
 
-static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
+static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
 {
 	struct kvm_pgtable pgt = {
 		.ia_bits	= ia_bits,
···
 	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
 }
 
-static bool kvm_pte_table(kvm_pte_t pte, u32 level)
+static bool kvm_pte_table(kvm_pte_t pte, s8 level)
 {
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	if (!kvm_pte_valid(pte))
···
 	return pte;
 }
 
-static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
 {
 	kvm_pte_t pte = kvm_phys_to_pte(pa);
-	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
-							   KVM_PTE_TYPE_BLOCK;
+	u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE :
+						       KVM_PTE_TYPE_BLOCK;
 
 	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
···
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);
 
 static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 				      struct kvm_pgtable_mm_ops *mm_ops,
-				      kvm_pteref_t pteref, u32 level)
+				      kvm_pteref_t pteref, s8 level)
 {
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
 	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
···
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level)
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
 {
 	u32 idx;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL ||
+			 level > KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
···
 
 struct leaf_walk_data {
 	kvm_pte_t	pte;
-	u32		level;
+	s8		level;
 };
 
 static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
···
 }
 
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level)
+			 kvm_pte_t *ptep, s8 *level)
 {
 	struct leaf_walk_data data;
 	struct kvm_pgtable_walker walker = {
···
 	if (hyp_map_walker_try_leaf(ctx, data))
 		return 0;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
···
 int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 			 struct kvm_pgtable_mm_ops *mm_ops)
 {
-	u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits);
+	s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 -
+			 ARM64_HW_PGTABLE_LEVELS(va_bits);
+
+	if (start_level < KVM_PGTABLE_FIRST_LEVEL ||
+	    start_level > KVM_PGTABLE_LAST_LEVEL)
+		return -EINVAL;
 
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
 	pgt->ia_bits		= va_bits;
-	pgt->start_level	= KVM_PGTABLE_MAX_LEVELS - levels;
+	pgt->start_level	= start_level;
 	pgt->mm_ops		= mm_ops;
 	pgt->mmu		= NULL;
 	pgt->force_pte_cb	= NULL;
···
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 {
 	u64 vtcr = VTCR_EL2_FLAGS;
-	u8 lvls;
+	s8 lvls;
 
 	vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT;
 	vtcr |= VTCR_EL2_T0SZ(phys_shift);
···
 {
 	u64 phys = stage2_map_walker_phys_addr(ctx, data);
 
-	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	return kvm_block_mapping_supported(ctx, phys);
···
 	if (ret != -E2BIG)
 		return ret;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	if (!data->memcache)
···
 	kvm_pte_t			attr_set;
 	kvm_pte_t			attr_clr;
 	kvm_pte_t			pte;
-	u32				level;
+	s8				level;
 };
 
 static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
···
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level, enum kvm_pgtable_walk_flags flags)
+				    s8 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
···
 				   enum kvm_pgtable_prot prot)
 {
 	int ret;
-	u32 level;
+	s8 level;
 	kvm_pte_t set = 0, clr = 0;
 
 	if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
···
 }
 
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte)
 {
···
  * fully populated tree up to the PTE entries. Note that @level is
  * interpreted as in "level @level entry".
  */
-static int stage2_block_get_nr_page_tables(u32 level)
+static int stage2_block_get_nr_page_tables(s8 level)
 {
 	switch (level) {
 	case 1:
···
 		return 0;
 	default:
 		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
-			     level >= KVM_PGTABLE_MAX_LEVELS);
+			     level > KVM_PGTABLE_LAST_LEVEL);
 		return -EINVAL;
 	};
 }
···
 	struct kvm_s2_mmu *mmu;
 	kvm_pte_t pte = ctx->old, new, *childp;
 	enum kvm_pgtable_prot prot;
-	u32 level = ctx->level;
+	s8 level = ctx->level;
 	bool force_pte;
 	int nr_pages;
 	u64 phys;
 
 	/* No huge-pages exist at the last level */
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return 0;
 
 	/* We only split valid block mappings */
···
 	u64 vtcr = mmu->vtcr;
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
···
 {
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 }
···
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {

arch/arm64/kvm/mmu.c

···
 {
 	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_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_unlinked_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, s8 level)
 {
 	struct page *page = virt_to_page(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 -
+				   CONFIG_PGTABLE_LEVELS + 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;
 
 	/*
···
 	 * Not seeing an error, but not updating level? Something went
 	 * deeply wrong...
 	 */
-	if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS))
+	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 */
···
 	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);
+	s8 fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;