diff options
Diffstat (limited to 'arch/arm64/mm')
| -rw-r--r-- | arch/arm64/mm/contpte.c | 3 | ||||
| -rw-r--r-- | arch/arm64/mm/fault.c | 29 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 331 | ||||
| -rw-r--r-- | arch/arm64/mm/pageattr.c | 12 | ||||
| -rw-r--r-- | arch/arm64/mm/pgd.c | 2 | ||||
| -rw-r--r-- | arch/arm64/mm/proc.S | 36 |
6 files changed, 274 insertions, 139 deletions
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index c0557945939c..589bcf878938 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -622,8 +622,7 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma, __ptep_set_access_flags(vma, addr, ptep, entry, 0); if (dirty) - __flush_tlb_range(vma, start_addr, addr, - PAGE_SIZE, true, 3); + local_flush_tlb_contpte(vma, start_addr); } else { __contpte_try_unfold(vma->vm_mm, addr, ptep, orig_pte); __ptep_set_access_flags(vma, addr, ptep, entry, dirty); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d816ff44faff..be9dab2c7d6a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -233,9 +233,13 @@ int __ptep_set_access_flags(struct vm_area_struct *vma, pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); - /* Invalidate a stale read-only entry */ + /* + * Invalidate the local stale read-only entry. Remote stale entries + * may still cause page faults and be invalidated via + * flush_tlb_fix_spurious_fault(). + */ if (dirty) - flush_tlb_page(vma, address); + local_flush_tlb_page(vma, address); return 1; } @@ -967,10 +971,21 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, return vma_alloc_folio(flags, 0, vma, vaddr); } -void tag_clear_highpage(struct page *page) +bool tag_clear_highpages(struct page *page, int numpages) { - /* Newly allocated page, shouldn't have been tagged yet */ - WARN_ON_ONCE(!try_page_mte_tagging(page)); - mte_zero_clear_page_tags(page_address(page)); - set_page_mte_tagged(page); + /* + * Check if MTE is supported and fall back to clear_highpage(). + * get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and + * post_alloc_hook() will invoke tag_clear_highpages(). + */ + if (!system_supports_mte()) + return false; + + /* Newly allocated pages, shouldn't have been tagged yet */ + for (int i = 0; i < numpages; i++, page++) { + WARN_ON_ONCE(!try_page_mte_tagging(page)); + mte_zero_clear_page_tags(page_address(page)); + set_page_mte_tagged(page); + } + return true; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b8d37eb037fc..c8d24b7cdd62 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -49,6 +49,8 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ +#define INVALID_PHYS_ADDR (-1ULL) + DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); u64 kimage_voffset __ro_after_init; @@ -194,11 +196,11 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end, } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { unsigned long next; pmd_t pmd = READ_ONCE(*pmdp); @@ -213,6 +215,8 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, pmdval |= PMD_TABLE_PXN; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(TABLE_PTE); + if (pte_phys == INVALID_PHYS_ADDR) + return -ENOMEM; ptep = pte_set_fixmap(pte_phys); init_clear_pgtable(ptep); ptep += pte_index(addr); @@ -244,11 +248,13 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, * walker. */ pte_clear_fixmap(); + + return 0; } -static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags) +static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags) { unsigned long next; @@ -269,22 +275,29 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmdp, addr, next, phys, prot, - pgtable_alloc, flags); + int ret; + + ret = alloc_init_cont_pte(pmdp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + return ret; BUG_ON(pmd_val(old_pmd) != 0 && pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; } while (pmdp++, addr = next, addr != end); + + return 0; } -static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; @@ -301,6 +314,8 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, pudval |= PUD_TABLE_PXN; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(TABLE_PMD); + if (pmd_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pmdp = pmd_set_fixmap(pmd_phys); init_clear_pgtable(pmdp); pmdp += pmd_index(addr); @@ -320,20 +335,26 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + ret = init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + if (ret) + goto out; pmdp += pmd_index(next) - pmd_index(addr); phys += next - addr; } while (addr = next, addr != end); +out: pmd_clear_fixmap(); + + return ret; } -static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret = 0; unsigned long next; p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; @@ -346,6 +367,8 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, p4dval |= P4D_TABLE_PXN; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(TABLE_PUD); + if (pud_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pudp = pud_set_fixmap(pud_phys); init_clear_pgtable(pudp); pudp += pud_index(addr); @@ -375,8 +398,10 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pudp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_cont_pmd(pudp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(pud_val(old_pud) != 0 && pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); @@ -384,14 +409,18 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys += next - addr; } while (pudp++, addr = next, addr != end); +out: pud_clear_fixmap(); + + return ret; } -static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pgd_t pgd = READ_ONCE(*pgdp); p4d_t *p4dp; @@ -404,6 +433,8 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, pgdval |= PGD_TABLE_PXN; BUG_ON(!pgtable_alloc); p4d_phys = pgtable_alloc(TABLE_P4D); + if (p4d_phys == INVALID_PHYS_ADDR) + return -ENOMEM; p4dp = p4d_set_fixmap(p4d_phys); init_clear_pgtable(p4dp); p4dp += p4d_index(addr); @@ -418,8 +449,10 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, next = p4d_addr_end(addr, end); - alloc_init_pud(p4dp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_pud(p4dp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(p4d_val(old_p4d) != 0 && p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); @@ -427,15 +460,19 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, phys += next - addr; } while (p4dp++, addr = next, addr != end); +out: p4d_clear_fixmap(); + + return ret; } -static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_pgd(pgdir, virt); @@ -444,7 +481,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, * within a page, we cannot map the region as the caller expects. */ if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) - return; + return -EINVAL; phys &= PAGE_MASK; addr = virt & PAGE_MASK; @@ -452,25 +489,45 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, do { next = pgd_addr_end(addr, end); - alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, - flags); + ret = alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, + flags); + if (ret) + return ret; phys += next - addr; } while (pgdp++, addr = next, addr != end); + + return 0; } -static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; + mutex_lock(&fixmap_lock); - __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, - pgtable_alloc, flags); + ret = __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, + pgtable_alloc, flags); mutex_unlock(&fixmap_lock); + + return ret; } -#define INVALID_PHYS_ADDR (-1ULL) +static void early_create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) +{ + int ret; + + ret = __create_pgd_mapping(pgdir, phys, virt, size, prot, pgtable_alloc, + flags); + if (ret) + panic("Failed to create page tables\n"); +} static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp, enum pgtable_type pgtable_type) @@ -503,7 +560,7 @@ static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp, } static phys_addr_t -try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type, gfp_t gfp) +pgd_pgtable_alloc_init_mm_gfp(enum pgtable_type pgtable_type, gfp_t gfp) { return __pgd_pgtable_alloc(&init_mm, gfp, pgtable_type); } @@ -511,21 +568,13 @@ try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type, gfp_t gfp) static phys_addr_t __maybe_unused pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type) { - phys_addr_t pa; - - pa = __pgd_pgtable_alloc(&init_mm, GFP_PGTABLE_KERNEL, pgtable_type); - BUG_ON(pa == INVALID_PHYS_ADDR); - return pa; + return pgd_pgtable_alloc_init_mm_gfp(pgtable_type, GFP_PGTABLE_KERNEL); } static phys_addr_t pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type) { - phys_addr_t pa; - - pa = __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type); - BUG_ON(pa == INVALID_PHYS_ADDR); - return pa; + return __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type); } static void split_contpte(pte_t *ptep) @@ -546,7 +595,7 @@ static int split_pmd(pmd_t *pmdp, pmd_t pmd, gfp_t gfp, bool to_cont) pte_t *ptep; int i; - pte_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PTE, gfp); + pte_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PTE, gfp); if (pte_phys == INVALID_PHYS_ADDR) return -ENOMEM; ptep = (pte_t *)phys_to_virt(pte_phys); @@ -591,7 +640,7 @@ static int split_pud(pud_t *pudp, pud_t pud, gfp_t gfp, bool to_cont) pmd_t *pmdp; int i; - pmd_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PMD, gfp); + pmd_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PMD, gfp); if (pmd_phys == INVALID_PHYS_ADDR) return -ENOMEM; pmdp = (pmd_t *)phys_to_virt(pmd_phys); @@ -708,6 +757,30 @@ out: return ret; } +static inline bool force_pte_mapping(void) +{ + const bool bbml2 = system_capabilities_finalized() ? + system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); + + if (debug_pagealloc_enabled()) + return true; + if (bbml2) + return false; + return rodata_full || arm64_kfence_can_set_direct_map() || is_realm_world(); +} + +static inline bool split_leaf_mapping_possible(void) +{ + /* + * !BBML2_NOABORT systems should never run into scenarios where we would + * have to split. So exit early and let calling code detect it and raise + * a warning. + */ + if (!system_supports_bbml2_noabort()) + return false; + return !force_pte_mapping(); +} + static DEFINE_MUTEX(pgtable_split_lock); int split_kernel_leaf_mapping(unsigned long start, unsigned long end) @@ -715,12 +788,11 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) int ret; /* - * !BBML2_NOABORT systems should not be trying to change permissions on - * anything that is not pte-mapped in the first place. Just return early - * and let the permission change code raise a warning if not already - * pte-mapped. + * Exit early if the region is within a pte-mapped area or if we can't + * split. For the latter case, the permission change code will raise a + * warning if not already pte-mapped. */ - if (!system_supports_bbml2_noabort()) + if (!split_leaf_mapping_possible() || is_kfence_address((void *)start)) return 0; /* @@ -758,30 +830,30 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) return ret; } -static int __init split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pud_t pud = pudp_get(pudp); int ret = 0; if (pud_leaf(pud)) - ret = split_pud(pudp, pud, GFP_ATOMIC, false); + ret = split_pud(pudp, pud, gfp, false); return ret; } -static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pmd_t pmd = pmdp_get(pmdp); int ret = 0; if (pmd_leaf(pmd)) { if (pmd_cont(pmd)) split_contpmd(pmdp); - ret = split_pmd(pmdp, pmd, GFP_ATOMIC, false); + ret = split_pmd(pmdp, pmd, gfp, false); /* * We have split the pmd directly to ptes so there is no need to @@ -793,9 +865,8 @@ static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, return ret; } -static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) { pte_t pte = __ptep_get(ptep); @@ -805,12 +876,24 @@ static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, return 0; } -static const struct mm_walk_ops split_to_ptes_ops __initconst = { +static const struct mm_walk_ops split_to_ptes_ops = { .pud_entry = split_to_ptes_pud_entry, .pmd_entry = split_to_ptes_pmd_entry, .pte_entry = split_to_ptes_pte_entry, }; +static int range_split_to_ptes(unsigned long start, unsigned long end, gfp_t gfp) +{ + int ret; + + arch_enter_lazy_mmu_mode(); + ret = walk_kernel_page_table_range_lockless(start, end, + &split_to_ptes_ops, NULL, &gfp); + arch_leave_lazy_mmu_mode(); + + return ret; +} + static bool linear_map_requires_bbml2 __initdata; u32 idmap_kpti_bbml2_flag; @@ -847,11 +930,9 @@ static int __init linear_map_split_to_ptes(void *__unused) * PTE. The kernel alias remains static throughout runtime so * can continue to be safely mapped with large mappings. */ - ret = walk_kernel_page_table_range_lockless(lstart, kstart, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(lstart, kstart, GFP_ATOMIC); if (!ret) - ret = walk_kernel_page_table_range_lockless(kend, lend, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(kend, lend, GFP_ATOMIC); if (ret) panic("Failed to split linear map\n"); flush_tlb_kernel_range(lstart, lend); @@ -903,8 +984,8 @@ void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, @@ -918,8 +999,8 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, if (page_mappings_only) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - pgd_pgtable_alloc_special_mm, flags); + early_create_pgd_mapping(mm->pgd, phys, virt, size, prot, + pgd_pgtable_alloc_special_mm, flags); } static void update_mapping_prot(phys_addr_t phys, unsigned long virt, @@ -931,8 +1012,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); /* flush the TLBs after updating live kernel mappings */ flush_tlb_kernel_range(virt, virt + size); @@ -941,8 +1022,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, - prot, early_pgtable_alloc, flags); + early_create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, + prot, early_pgtable_alloc, flags); } void __init mark_linear_text_alias_ro(void) @@ -1002,6 +1083,33 @@ static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); __kfence_pool = phys_to_virt(kfence_pool); } + +bool arch_kfence_init_pool(void) +{ + unsigned long start = (unsigned long)__kfence_pool; + unsigned long end = start + KFENCE_POOL_SIZE; + int ret; + + /* Exit early if we know the linear map is already pte-mapped. */ + if (!split_leaf_mapping_possible()) + return true; + + /* Kfence pool is already pte-mapped for the early init case. */ + if (kfence_early_init) + return true; + + mutex_lock(&pgtable_split_lock); + ret = range_split_to_ptes(start, end, GFP_PGTABLE_KERNEL); + mutex_unlock(&pgtable_split_lock); + + /* + * Since the system supports bbml2_noabort, tlb invalidation is not + * required here; the pgtable mappings have been split to pte but larger + * entries may safely linger in the TLB. + */ + + return !ret; +} #else /* CONFIG_KFENCE */ static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; } @@ -1009,16 +1117,6 @@ static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { #endif /* CONFIG_KFENCE */ -static inline bool force_pte_mapping(void) -{ - bool bbml2 = system_capabilities_finalized() ? - system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); - - return (!bbml2 && (rodata_full || arm64_kfence_can_set_direct_map() || - is_realm_world())) || - debug_pagealloc_enabled(); -} - static void __init map_mem(pgd_t *pgdp) { static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN); @@ -1158,6 +1256,8 @@ static int __init __kpti_install_ng_mappings(void *__unused) remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { + int ret; + alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE); kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd); @@ -1178,9 +1278,11 @@ static int __init __kpti_install_ng_mappings(void *__unused) // covers the PTE[] page itself, the remaining entries are free // to be used as a ad-hoc fixmap. // - __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc), - KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, - kpti_ng_pgd_alloc, 0); + ret = __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc), + KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, + kpti_ng_pgd_alloc, 0); + if (ret) + panic("Failed to create page tables\n"); } cpu_install_idmap(); @@ -1233,9 +1335,9 @@ static int __init map_entry_trampoline(void) /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); - __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, - entry_tramp_text_size(), prot, - pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS); + early_create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) @@ -1877,23 +1979,28 @@ int arch_add_memory(int nid, u64 start, u64 size, if (force_pte_mapping()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), - size, params->pgprot, pgd_pgtable_alloc_init_mm, - flags); + ret = __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), + size, params->pgprot, pgd_pgtable_alloc_init_mm, + flags); + if (ret) + goto err; memblock_clear_nomap(start, size); ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); if (ret) - __remove_pgd_mapping(swapper_pg_dir, - __phys_to_virt(start), size); - else { - /* Address of hotplugged memory can be smaller */ - max_pfn = max(max_pfn, PFN_UP(start + size)); - max_low_pfn = max_pfn; - } + goto err; + + /* Address of hotplugged memory can be smaller */ + max_pfn = max(max_pfn, PFN_UP(start + size)); + max_low_pfn = max_pfn; + + return 0; +err: + __remove_pgd_mapping(swapper_pg_dir, + __phys_to_virt(start), size); return ret; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 5135f2d66958..f0e784b963e6 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -148,7 +148,7 @@ static int change_memory_common(unsigned long addr, int numpages, unsigned long size = PAGE_SIZE * numpages; unsigned long end = start + size; struct vm_struct *area; - int i; + int ret; if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; @@ -184,9 +184,13 @@ static int change_memory_common(unsigned long addr, int numpages, */ if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || pgprot_val(clear_mask) == PTE_RDONLY)) { - for (i = 0; i < area->nr_pages; i++) { - __change_memory_common((u64)page_address(area->pages[i]), - PAGE_SIZE, set_mask, clear_mask); + unsigned long idx = (start - (unsigned long)kasan_reset_tag(area->addr)) + >> PAGE_SHIFT; + for (; numpages; idx++, numpages--) { + ret = __change_memory_common((u64)page_address(area->pages[idx]), + PAGE_SIZE, set_mask, clear_mask); + if (ret) + return ret; } } diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 8160cff35089..bf5110b91e2f 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -56,7 +56,7 @@ void __init pgtable_cache_init(void) * With 52-bit physical addresses, the architecture requires the * top-level table to be aligned to at least 64 bytes. */ - BUILD_BUG_ON(PGD_SIZE < 64); + BUILD_BUG_ON(!IS_ALIGNED(PGD_SIZE, 64)); #endif /* diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 86818511962b..01e868116448 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -23,15 +23,18 @@ #include <asm/sysreg.h> #ifdef CONFIG_ARM64_64K_PAGES -#define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_64K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_64K << TCR_EL1_TG1_SHIFT)) #elif defined(CONFIG_ARM64_16K_PAGES) -#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_16K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_16K << TCR_EL1_TG1_SHIFT)) #else /* CONFIG_ARM64_4K_PAGES */ -#define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_4K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_4K << TCR_EL1_TG1_SHIFT)) #endif #ifdef CONFIG_RANDOMIZE_BASE -#define TCR_KASLR_FLAGS TCR_NFD1 +#define TCR_KASLR_FLAGS TCR_EL1_NFD1 #else #define TCR_KASLR_FLAGS 0 #endif @@ -40,23 +43,30 @@ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA #ifdef CONFIG_KASAN_SW_TAGS -#define TCR_KASAN_SW_FLAGS TCR_TBI1 | TCR_TBID1 +#define TCR_KASAN_SW_FLAGS TCR_EL1_TBI1 | TCR_EL1_TBID1 #else #define TCR_KASAN_SW_FLAGS 0 #endif #ifdef CONFIG_KASAN_HW_TAGS -#define TCR_MTE_FLAGS TCR_TCMA1 | TCR_TBI1 | TCR_TBID1 +#define TCR_MTE_FLAGS TCR_EL1_TCMA1 | TCR_EL1_TBI1 | TCR_EL1_TBID1 #elif defined(CONFIG_ARM64_MTE) /* * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on * TBI being enabled at EL1. */ -#define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1 +#define TCR_MTE_FLAGS TCR_EL1_TBI1 | TCR_EL1_TBID1 #else #define TCR_MTE_FLAGS 0 #endif +#define TCR_IRGN_WBWA ((TCR_EL1_IRGN0_WBWA << TCR_EL1_IRGN0_SHIFT) |\ + (TCR_EL1_IRGN1_WBWA << TCR_EL1_IRGN1_SHIFT)) +#define TCR_ORGN_WBWA ((TCR_EL1_ORGN0_WBWA << TCR_EL1_ORGN0_SHIFT) |\ + (TCR_EL1_ORGN1_WBWA << TCR_EL1_ORGN1_SHIFT)) +#define TCR_SHARED ((TCR_EL1_SH0_INNER << TCR_EL1_SH0_SHIFT) |\ + (TCR_EL1_SH1_INNER << TCR_EL1_SH1_SHIFT)) + /* * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and * changed during mte_cpu_setup to Normal Tagged if the system supports MTE. @@ -129,7 +139,7 @@ SYM_FUNC_START(cpu_do_resume) /* Don't change t0sz here, mask those bits when restoring */ mrs x7, tcr_el1 - bfi x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH + bfi x8, x7, TCR_EL1_T0SZ_SHIFT, TCR_EL1_T0SZ_WIDTH msr tcr_el1, x8 msr vbar_el1, x9 @@ -481,8 +491,8 @@ SYM_FUNC_START(__cpu_setup) tcr2 .req x15 mov_q mair, MAIR_EL1_SET mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ - TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_EL1_AS | \ + TCR_EL1_TBI0 | TCR_EL1_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS mov tcr2, xzr tcr_clear_errata_bits tcr, x9, x5 @@ -492,7 +502,7 @@ SYM_FUNC_START(__cpu_setup) alternative_if ARM64_HAS_VA52 tcr_set_t1sz tcr, x9 #ifdef CONFIG_ARM64_LPA2 - orr tcr, tcr, #TCR_DS + orr tcr, tcr, #TCR_EL1_DS #endif alternative_else_nop_endif #endif @@ -500,7 +510,7 @@ alternative_else_nop_endif /* * Set the IPS bits in TCR_EL1. */ - tcr_compute_pa_size tcr, #TCR_IPS_SHIFT, x5, x6 + tcr_compute_pa_size tcr, #TCR_EL1_IPS_SHIFT, x5, x6 #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable hardware update of the Access Flags bit. @@ -510,7 +520,7 @@ alternative_else_nop_endif mrs x9, ID_AA64MMFR1_EL1 ubfx x9, x9, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, #4 cbz x9, 1f - orr tcr, tcr, #TCR_HA // hardware Access flag update + orr tcr, tcr, #TCR_EL1_HA // hardware Access flag update #ifdef CONFIG_ARM64_HAFT cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT b.lt 1f |