diff options
| -rw-r--r-- | arch/arm64/include/asm/kvm_host.h | 1 | ||||
| -rw-r--r-- | arch/arm64/include/asm/kvm_pgtable.h | 20 | ||||
| -rw-r--r-- | arch/arm64/kvm/hyp/pgtable.c | 39 | ||||
| -rw-r--r-- | arch/arm64/kvm/mmu.c | 45 | ||||
| -rw-r--r-- | arch/arm64/kvm/pmu-emul.c | 8 | ||||
| -rw-r--r-- | arch/arm64/kvm/sys_regs.c | 70 | ||||
| -rw-r--r-- | include/linux/kvm_host.h | 1 | ||||
| -rw-r--r-- | include/linux/page-flags.h | 37 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 19 |
9 files changed, 165 insertions, 75 deletions
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 26bbd84a02de..62ac4174e608 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -185,7 +185,6 @@ enum vcpu_sysreg { PMCNTENSET_EL0, /* Count Enable Set Register */ PMINTENSET_EL1, /* Interrupt Enable Set Register */ PMOVSSET_EL0, /* Overflow Flag Status Set Register */ - PMSWINC_EL0, /* Software Increment Register */ PMUSERENR_EL0, /* User Enable Register */ /* Pointer Authentication Registers in a strict increasing order. */ diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index f004c0115d89..e42b55bd50a2 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -433,6 +433,26 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker); /** + * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry + * with its level. + * @pgt: Page-table structure initialised by kvm_pgtable_*_init() + * or a similar initialiser. + * @addr: Input address for the start of the walk. + * @ptep: Pointer to storage for the retrieved PTE. + * @level: Pointer to storage for the level of the retrieved PTE. + * + * The offset of @addr within a page is ignored. + * + * The walker will walk the page-table entries corresponding to the input + * address specified, retrieving the leaf corresponding to this address. + * Invalid entries are treated as leaf entries. + * + * 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_pgtable_stage2_find_range() - Find a range of Intermediate Physical * Addresses with compatible permission * attributes. diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 05321f4165e3..78f36bd5df6c 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -326,6 +326,45 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, return _kvm_pgtable_walk(&walk_data); } +struct leaf_walk_data { + kvm_pte_t pte; + u32 level; +}; + +static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, + enum kvm_pgtable_walk_flags flag, void * const arg) +{ + struct leaf_walk_data *data = arg; + + data->pte = *ptep; + data->level = level; + + return 0; +} + +int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, + kvm_pte_t *ptep, u32 *level) +{ + struct leaf_walk_data data; + struct kvm_pgtable_walker walker = { + .cb = leaf_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &data, + }; + int ret; + + ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), + PAGE_SIZE, &walker); + if (!ret) { + if (ptep) + *ptep = data.pte; + if (level) + *level = data.level; + } + + return ret; +} + struct hyp_map_data { u64 phys; kvm_pte_t attr; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 2ca0a494a111..f446f55b6832 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -434,6 +434,32 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, return 0; } +static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { + /* We shouldn't need any other callback to walk the PT */ + .phys_to_virt = kvm_host_va, +}; + +static int get_user_mapping_size(struct kvm *kvm, u64 addr) +{ + struct kvm_pgtable pgt = { + .pgd = (kvm_pte_t *)kvm->mm->pgd, + .ia_bits = VA_BITS, + .start_level = (KVM_PGTABLE_MAX_LEVELS - + CONFIG_PGTABLE_LEVELS), + .mm_ops = &kvm_user_mm_ops, + }; + kvm_pte_t pte = 0; /* Keep GCC quiet... */ + u32 level = ~0; + int ret; + + 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)); + + return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); +} + static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_host_zalloc_pages_exact, @@ -781,7 +807,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, * Returns the size of the mapping. */ static unsigned long -transparent_hugepage_adjust(struct kvm_memory_slot *memslot, +transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) { @@ -792,8 +818,8 @@ transparent_hugepage_adjust(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 (kvm_is_transparent_hugepage(pfn) && - fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + 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 @@ -815,7 +841,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot, *ipap &= PMD_MASK; kvm_release_pfn_clean(pfn); pfn &= ~(PTRS_PER_PMD - 1); - kvm_get_pfn(pfn); + get_page(pfn_to_page(pfn)); *pfnp = pfn; return PMD_SIZE; @@ -1051,9 +1077,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * 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)) - vma_pagesize = transparent_hugepage_adjust(memslot, hva, - &pfn, &fault_ipa); + if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { + if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE) + vma_pagesize = fault_granule; + else + vma_pagesize = transparent_hugepage_adjust(kvm, memslot, + hva, &pfn, + &fault_ipa); + } if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new VM_SHARED VMA */ diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 60f89bdbeebb..f5065f23b413 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -373,7 +373,6 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); - reg &= kvm_pmu_valid_counter_mask(vcpu); } return reg; @@ -564,20 +563,21 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) */ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { - unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); int i; if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask); + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } else { - kvm_pmu_disable_counter_mask(vcpu, mask); + kvm_pmu_disable_counter_mask(vcpu, + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { + unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) kvm_pmu_set_counter_value(vcpu, i, 0); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f6f126eb6ac1..a1f5101f49a3 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -603,6 +603,41 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, return REG_HIDDEN; } +static void reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX); + + /* No PMU available, any PMU reg may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + + n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT; + n &= ARMV8_PMU_PMCR_N_MASK; + if (n) + mask |= GENMASK(n - 1, 0); + + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= mask; +} + +static void reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0); +} + +static void reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK; +} + +static void reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + reset_unknown(vcpu, r); + __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK; +} + static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; @@ -845,7 +880,7 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_disable_counter_mask(vcpu, val); } } else { - p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } return true; @@ -869,7 +904,7 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* accessing PMINTENCLR_EL1 */ __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val; } else { - p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1); } return true; @@ -891,7 +926,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* accessing PMOVSCLR_EL0 */ __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask); } else { - p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask; + p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); } return true; @@ -944,16 +979,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } #define PMU_SYS_REG(r) \ - SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility + SYS_DESC(r), .reset = reset_pmu_reg, .visibility = pmu_visibility /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ { PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \ + .reset = reset_pmevcntr, \ .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ { PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \ + .reset = reset_pmevtyper, \ .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, @@ -1249,6 +1286,20 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return __set_id_reg(vcpu, rd, uaddr, true); } +static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + int err; + u64 val; + + /* Perform the access even if we are going to ignore the value */ + err = reg_from_user(&val, uaddr, sys_reg_to_index(rd)); + if (err) + return err; + + return 0; +} + static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1592,16 +1643,21 @@ static const struct sys_reg_desc sys_reg_descs[] = { .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, { PMU_SYS_REG(SYS_PMOVSCLR_EL0), .access = access_pmovs, .reg = PMOVSSET_EL0 }, + /* + * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was + * previously (and pointlessly) advertised in the past... + */ { PMU_SYS_REG(SYS_PMSWINC_EL0), - .access = access_pmswinc, .reg = PMSWINC_EL0 }, + .get_user = get_raz_id_reg, .set_user = set_wi_reg, + .access = access_pmswinc, .reset = NULL }, { PMU_SYS_REG(SYS_PMSELR_EL0), - .access = access_pmselr, .reg = PMSELR_EL0 }, + .access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 }, { PMU_SYS_REG(SYS_PMCEID0_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(SYS_PMCEID1_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(SYS_PMCCNTR_EL0), - .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 }, + .access = access_pmu_evcntr, .reset = reset_unknown, .reg = PMCCNTR_EL0 }, { PMU_SYS_REG(SYS_PMXEVTYPER_EL0), .access = access_pmu_evtyper, .reset = NULL }, { PMU_SYS_REG(SYS_PMXEVCNTR_EL0), diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ae7735b490b4..9818d271c2a1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -824,7 +824,6 @@ void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_get_pfn(kvm_pfn_t pfn); void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5922031ffab6..1ace27c4a8e0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -633,43 +633,6 @@ static inline int PageTransCompound(struct page *page) } /* - * PageTransCompoundMap is the same as PageTransCompound, but it also - * guarantees the primary MMU has the entire compound page mapped - * through pmd_trans_huge, which in turn guarantees the secondary MMUs - * can also map the entire compound page. This allows the secondary - * MMUs to call get_user_pages() only once for each compound page and - * to immediately map the entire compound page with a single secondary - * MMU fault. If there will be a pmd split later, the secondary MMUs - * will get an update through the MMU notifier invalidation through - * split_huge_pmd(). - * - * Unlike PageTransCompound, this is safe to be called only while - * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount check false - * positives. - * - * We have to treat page cache THP differently since every subpage of it - * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE - * mapped in the current process so comparing subpage's _mapcount to - * compound_mapcount to filter out PTE mapped case. - */ -static inline int PageTransCompoundMap(struct page *page) -{ - struct page *head; - - if (!PageTransCompound(page)) - return 0; - - if (PageAnon(page)) - return atomic_read(&page->_mapcount) < 0; - - head = compound_head(page); - /* File THP is PMD mapped and not PTE mapped */ - return atomic_read(&page->_mapcount) == - atomic_read(compound_mapcount_ptr(head)); -} - -/* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d20fba0fc290..1d3a03c0fed3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -189,16 +189,6 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) return true; } -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn) -{ - struct page *page = pfn_to_page(pfn); - - if (!PageTransCompoundMap(page)) - return false; - - return is_transparent_hugepage(compound_head(page)); -} - /* * Switches to specified vcpu, until a matching vcpu_put() */ @@ -2225,7 +2215,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP - * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will + * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. @@ -2622,13 +2612,6 @@ void kvm_set_pfn_accessed(kvm_pfn_t pfn) } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(kvm_pfn_t pfn) -{ - if (!kvm_is_reserved_pfn(pfn)) - get_page(pfn_to_page(pfn)); -} -EXPORT_SYMBOL_GPL(kvm_get_pfn); - static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) |