Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 64 insertions, 39 deletions

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1966fdee74..ce5cef7d73 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -79,7 +79,10 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
 
 static bool kvm_phys_is_valid(u64 phys)
 {
-	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
+	u64 parange_max = kvm_get_parange_max();
+	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);
+
+	return phys < BIT(shift);
 }
 
 static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
@@ -98,7 +101,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx,
 	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;
@@ -114,7 +117,7 @@ static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 	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,
@@ -124,9 +127,9 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 	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))
@@ -154,11 +157,11 @@ static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops
 	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);
@@ -203,11 +206,11 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
 }
 
 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);
@@ -272,12 +275,13 @@ out:
 }
 
 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) {
@@ -340,7 +344,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 
 struct leaf_walk_data {
 	kvm_pte_t	pte;
-	u32		level;
+	s8		level;
 };
 
 static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -355,7 +359,7 @@ 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 = {
@@ -408,7 +412,8 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 	}
 
 	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
 	attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -467,7 +472,7 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	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);
@@ -563,14 +568,19 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 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;
@@ -624,7 +634,7 @@ struct stage2_map_data {
 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);
@@ -635,6 +645,15 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 	lvls = stage2_pgtable_levels(phys_shift);
 	if (lvls < 2)
 		lvls = 2;
+
+	/*
+	 * When LPA2 is enabled, the HW supports an extra level of translation
+	 * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2
+	 * to as an addition to SL0 to enable encoding this extra start level.
+	 * However, since we always use concatenated pages for the first level
+	 * lookup, we will never need this extra level and therefore do not need
+	 * to touch SL2.
+	 */
 	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
 
 #ifdef CONFIG_ARM64_HW_AFDBM
@@ -654,6 +673,9 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 		vtcr |= VTCR_EL2_HA;
 #endif /* CONFIG_ARM64_HW_AFDBM */
 
+	if (kvm_lpa2_is_enabled())
+		vtcr |= VTCR_EL2_DS;
+
 	/* Set the vmid bits */
 	vtcr |= (get_vmid_bits(mmfr1) == 16) ?
 		VTCR_EL2_VS_16BIT :
@@ -711,7 +733,9 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p
 	if (prot & KVM_PGTABLE_PROT_W)
 		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+
 	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -805,12 +829,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 		 * Perform the appropriate TLB invalidation based on the
 		 * evicted pte value (if any).
 		 */
-		if (kvm_pte_table(ctx->old, ctx->level))
-			kvm_tlb_flush_vmid_range(mmu, ctx->addr,
-						kvm_granule_size(ctx->level));
-		else if (kvm_pte_valid(ctx->old))
+		if (kvm_pte_table(ctx->old, ctx->level)) {
+			u64 size = kvm_granule_size(ctx->level);
+			u64 addr = ALIGN_DOWN(ctx->addr, size);
+
+			kvm_tlb_flush_vmid_range(mmu, addr, size);
+		} else if (kvm_pte_valid(ctx->old)) {
 			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
 				     ctx->addr, ctx->level);
+		}
 	}
 
 	if (stage2_pte_is_counted(ctx->old))
@@ -902,7 +929,7 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	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);
@@ -981,7 +1008,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	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)
@@ -1151,7 +1178,7 @@ struct stage2_attr_data {
 	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,
@@ -1194,7 +1221,7 @@ 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;
@@ -1296,7 +1323,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   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)
@@ -1349,7 +1376,7 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 }
 
 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)
 {
@@ -1395,7 +1422,6 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
 				 level + 1);
 	if (ret) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
-		mm_ops->put_page(pgtable);
 		return ERR_PTR(ret);
 	}
 
@@ -1407,7 +1433,7 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
  * 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:
@@ -1418,7 +1444,7 @@ static int stage2_block_get_nr_page_tables(u32 level)
 		return 0;
 	default:
 		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
-			     level >= KVM_PGTABLE_MAX_LEVELS);
+			     level > KVM_PGTABLE_LAST_LEVEL);
 		return -EINVAL;
 	};
 }
@@ -1431,13 +1457,13 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	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 */
@@ -1478,7 +1504,6 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 	if (!stage2_try_break_pte(ctx, mmu)) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
-		mm_ops->put_page(childp);
 		return -EAGAIN;
 	}
 
@@ -1514,7 +1539,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	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);
@@ -1537,7 +1562,7 @@ size_t kvm_pgtable_stage2_pgd_size(u64 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;
 
 	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 }
@@ -1573,7 +1598,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	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 = {