summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kvm')
-rw-r--r--arch/arm64/kvm/arm.c5
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/fault.h2
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-init.S4
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c6
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mm.c4
-rw-r--r--arch/arm64/kvm/hyp/nvhe/setup.c2
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c90
-rw-r--r--arch/arm64/kvm/mmu.c49
-rw-r--r--arch/arm64/kvm/reset.c9
10 files changed, 99 insertions, 74 deletions
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f1085..c4bbc224549b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1837,6 +1837,7 @@ static int kvm_init_vector_slots(void)
static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
{
struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
+ u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
unsigned long tcr;
/*
@@ -1859,6 +1860,10 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
}
tcr &= ~TCR_T0SZ_MASK;
tcr |= TCR_T0SZ(hyp_va_bits);
+ tcr &= ~TCR_EL2_PS_MASK;
+ tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0));
+ if (kvm_lpa2_is_enabled())
+ tcr |= TCR_EL2_DS;
params->tcr_el2 = tcr;
params->pgd_pa = kvm_mmu_get_httbr();
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 9ddcfe2c3e57..9e13c1bc2ad5 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
*/
if (!(esr & ESR_ELx_S1PTW) &&
(cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
+ esr_fsc_is_permission_fault(esr))) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index d56fef44dc31..a038320cdb08 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -622,7 +622,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
- valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
+ valid = kvm_vcpu_trap_is_translation_fault(vcpu) &&
kvm_vcpu_dabt_isvalid(vcpu) &&
!kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 1cc06e6797bd..f62a7d360285 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -122,11 +122,7 @@ alternative_if ARM64_HAS_CNP
alternative_else_nop_endif
msr ttbr0_el2, x2
- /*
- * Set the PS bits in TCR_EL2.
- */
ldr x0, [x0, #NVHE_INIT_TCR_EL2]
- tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
msr tcr_el2, x0
isb
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 8d0a5834e883..861c76021a25 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -91,7 +91,7 @@ static void host_s2_put_page(void *addr)
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);
}
@@ -443,7 +443,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
{
struct kvm_mem_range cur;
kvm_pte_t pte;
- u32 level;
+ s8 level;
int ret;
hyp_assert_lock_held(&host_mmu.lock);
@@ -462,7 +462,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
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)));
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 65a7a186d7b2..b01a3d1078a8 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -260,7 +260,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
* https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/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();
}
@@ -275,7 +275,7 @@ static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx,
{
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;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 0d5e0a89ddce..bc58d1b515af 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -181,7 +181,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
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);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1966fdee740e..c651df904fe3 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;
@@ -902,7 +926,7 @@ 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 +1005,7 @@ 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 +1175,7 @@ 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 +1218,7 @@ 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 +1320,7 @@ 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 +1373,7 @@ 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)
{
@@ -1407,7 +1431,7 @@ 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 +1442,7 @@ 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 +1455,13 @@ 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 */
@@ -1514,7 +1538,7 @@ 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 +1561,7 @@ 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 +1597,7 @@ 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 = {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d87c8fcc4c24..d14504821b79 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -223,12 +223,12 @@ 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_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);
@@ -804,13 +804,13 @@ 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 -
+ 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;
/*
@@ -829,7 +829,9 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
* 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 */
@@ -1374,7 +1376,7 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
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;
@@ -1388,17 +1390,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
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);
long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
struct kvm_pgtable *pgt;
- 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);
- if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
+ if (fault_is_perm && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
@@ -1409,8 +1411,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* 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.
*/
- if (fault_status != ESR_ELx_FSC_PERM ||
- (logging_active && write_fault)) {
+ if (!fault_is_perm || (logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
if (ret)
@@ -1527,8 +1528,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* 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 (fault_is_perm && fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1541,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
}
}
- if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
+ if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (mte_allowed) {
sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1567,7 +1567,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* 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)
+ if (fault_is_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,
@@ -1618,7 +1618,7 @@ 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;
+ unsigned long esr;
phys_addr_t fault_ipa;
struct kvm_memory_slot *memslot;
unsigned long hva;
@@ -1626,12 +1626,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
gfn_t gfn;
int ret, idx;
- fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+ esr = kvm_vcpu_get_esr(vcpu);
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_permission_fault(esr)) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
@@ -1666,9 +1666,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *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),
@@ -1730,13 +1730,14 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_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);
+ ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+ esr_fsc_is_permission_fault(esr));
if (ret == 0)
ret = 1;
out:
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 5bb4de162cab..68d1d05672bd 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -280,12 +280,11 @@ int __init kvm_set_ipa_limit(void)
parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_PARANGE_SHIFT);
/*
- * IPA size beyond 48 bits could not be supported
- * on either 4K or 16K page size. Hence let's cap
- * it to 48 bits, in case it's reported as larger
- * on the system.
+ * IPA size beyond 48 bits for 4K and 16K page size is only supported
+ * when LPA2 is available. So if we have LPA2, enable it, else cap to 48
+ * bits, in case it's reported as larger on the system.
*/
- if (PAGE_SIZE != SZ_64K)
+ if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K)
parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
/*
generated by cgit (git 2.34.1) at 2024-06-11 20:08:56 +0000