diff options
Diffstat (limited to 'arch/arm64/mm')
| -rw-r--r-- | arch/arm64/mm/copypage.c | 7 | ||||
| -rw-r--r-- | arch/arm64/mm/dma-mapping.c | 17 | ||||
| -rw-r--r-- | arch/arm64/mm/fault.c | 12 | ||||
| -rw-r--r-- | arch/arm64/mm/hugetlbpage.c | 21 | ||||
| -rw-r--r-- | arch/arm64/mm/init.c | 25 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 125 | ||||
| -rw-r--r-- | arch/arm64/mm/mteswap.c | 16 | ||||
| -rw-r--r-- | arch/arm64/mm/pageattr.c | 3 | ||||
| -rw-r--r-- | arch/arm64/mm/proc.S | 4 |
9 files changed, 118 insertions, 112 deletions
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 24913271e898..8dd5a8fe64b4 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,12 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); - if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) { - set_bit(PG_mte_tagged, &to->flags); + if (system_supports_mte() && page_mte_tagged(from)) { + page_kasan_tag_reset(to); + /* It's a new page, shouldn't have been tagged yet */ + WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); + set_page_mte_tagged(to); } } EXPORT_SYMBOL(copy_highpage); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..5240f6acad64 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -36,7 +36,22 @@ void arch_dma_prep_coherent(struct page *page, size_t size) { unsigned long start = (unsigned long)page_address(page); - dcache_clean_poc(start, start + size); + /* + * The architecture only requires a clean to the PoC here in order to + * meet the requirements of the DMA API. However, some vendors (i.e. + * Qualcomm) abuse the DMA API for transferring buffers from the + * non-secure to the secure world, resetting the system if a non-secure + * access shows up after the buffer has been transferred: + * + * https://lore.kernel.org/r/20221114110329.68413-1-manivannan.sadhasivam@linaro.org + * + * Using clean+invalidate appears to make this issue less likely, but + * the drivers themselves still need fixing as the CPU could issue a + * speculative read from the buffer via the linear mapping irrespective + * of the cache maintenance we use. Once the drivers are fixed, we can + * relax this to a clean operation. + */ + dcache_clean_inval_poc(start, start + size); } #ifdef CONFIG_IOMMU_DMA diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3e9cf9826417..596f46dabe4e 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -354,6 +354,11 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) return false; } +static bool is_translation_fault(unsigned long esr) +{ + return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; +} + static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { @@ -386,7 +391,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) + if (is_translation_fault(esr) && + kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; @@ -937,6 +943,8 @@ struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, void tag_clear_highpage(struct page *page) { + /* 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_bit(PG_mte_tagged, &page->flags); + set_page_mte_tagged(page); } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..cd8d96e1fa1a 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return huge_ptep_clear_flush(vma, addr, ptep); + } + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 4b4651ee47f2..58a0bb2c17f1 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -96,6 +96,8 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1; #define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit #define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) + static int __init reserve_crashkernel_low(unsigned long long low_size) { unsigned long long low_base; @@ -130,6 +132,7 @@ static void __init reserve_crashkernel(void) unsigned long long crash_max = CRASH_ADDR_LOW_MAX; char *cmdline = boot_command_line; int ret; + bool fixed_base = false; if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; @@ -147,7 +150,9 @@ static void __init reserve_crashkernel(void) * is not allowed. */ ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); - if (ret && (ret != -ENOENT)) + if (ret == -ENOENT) + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + else if (ret) return; crash_max = CRASH_ADDR_HIGH_MAX; @@ -159,18 +164,32 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); /* User specifies base address explicitly. */ - if (crash_base) + if (crash_base) { + fixed_base = true; crash_max = crash_base + crash_size; + } +retry: crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_max); if (!crash_base) { + /* + * If the first attempt was for low memory, fall back to + * high memory, the minimum required low memory will be + * reserved later. + */ + if (!fixed_base && (crash_max == CRASH_ADDR_LOW_MAX)) { + crash_max = CRASH_ADDR_HIGH_MAX; + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + goto retry; + } + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", crash_size); return; } - if ((crash_base >= CRASH_ADDR_LOW_MAX) && + if ((crash_base > CRASH_ADDR_LOW_MAX - crash_low_size) && crash_low_size && reserve_crashkernel_low(crash_low_size)) { memblock_phys_free(crash_base, crash_size); return; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9a7c38965154..12915f379c22 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -814,53 +814,6 @@ void __init paging_init(void) create_idmap(); } -/* - * Check whether a kernel address is valid (derived from arch/x86/). - */ -int kern_addr_valid(unsigned long addr) -{ - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp, pud; - pmd_t *pmdp, pmd; - pte_t *ptep, pte; - - addr = arch_kasan_reset_tag(addr); - if ((((long)addr) >> VA_BITS) != -1UL) - return 0; - - pgdp = pgd_offset_k(addr); - if (pgd_none(READ_ONCE(*pgdp))) - return 0; - - p4dp = p4d_offset(pgdp, addr); - if (p4d_none(READ_ONCE(*p4dp))) - return 0; - - pudp = pud_offset(p4dp, addr); - pud = READ_ONCE(*pudp); - if (pud_none(pud)) - return 0; - - if (pud_sect(pud)) - return pfn_valid(pud_pfn(pud)); - - pmdp = pmd_offset(pudp, addr); - pmd = READ_ONCE(*pmdp); - if (pmd_none(pmd)) - return 0; - - if (pmd_sect(pmd)) - return pfn_valid(pmd_pfn(pmd)); - - ptep = pte_offset_kernel(pmdp, addr); - pte = READ_ONCE(*ptep); - if (pte_none(pte)) - return 0; - - return pfn_valid(pte_pfn(pte)); -} - #ifdef CONFIG_MEMORY_HOTPLUG static void free_hotplug_page_range(struct page *page, size_t size, struct vmem_altmap *altmap) @@ -1184,53 +1137,28 @@ static void free_empty_tables(unsigned long addr, unsigned long end, } #endif +void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, + unsigned long addr, unsigned long next) +{ + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); +} + +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + vmemmap_verify((pte_t *)pmdp, node, addr, next); + return 1; +} + int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - unsigned long addr = start; - unsigned long next; - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp; - pmd_t *pmdp; - WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); - if (!ARM64_KERNEL_USES_PMD_MAPS) + if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) return vmemmap_populate_basepages(start, end, node, altmap); - - do { - next = pmd_addr_end(addr, end); - - pgdp = vmemmap_pgd_populate(addr, node); - if (!pgdp) - return -ENOMEM; - - p4dp = vmemmap_p4d_populate(pgdp, addr, node); - if (!p4dp) - return -ENOMEM; - - pudp = vmemmap_pud_populate(p4dp, addr, node); - if (!pudp) - return -ENOMEM; - - pmdp = pmd_offset(pudp, addr); - if (pmd_none(READ_ONCE(*pmdp))) { - void *p = NULL; - - p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (!p) { - if (vmemmap_populate_basepages(addr, next, node, altmap)) - return -ENOMEM; - continue; - } - - pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); - } else - vmemmap_verify((pte_t *)pmdp, node, addr, next); - } while (addr = next, addr != end); - - return 0; + else + return vmemmap_populate_hugepages(start, end, node, altmap); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -1702,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void) } early_initcall(prevent_bootmem_remove_init); #endif + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); + } + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index bed803d8e158..cd508ba80ab1 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -24,7 +24,7 @@ int mte_save_tags(struct page *page) { void *tag_storage, *ret; - if (!test_bit(PG_mte_tagged, &page->flags)) + if (!page_mte_tagged(page)) return 0; tag_storage = mte_allocate_tag_storage(); @@ -46,21 +46,17 @@ int mte_save_tags(struct page *page) return 0; } -bool mte_restore_tags(swp_entry_t entry, struct page *page) +void mte_restore_tags(swp_entry_t entry, struct page *page) { void *tags = xa_load(&mte_pages, entry.val); if (!tags) - return false; + return; - /* - * Test PG_mte_tagged again in case it was racing with another - * set_pte_at(). - */ - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (try_page_mte_tagging(page)) { mte_restore_page_tags(page_address(page), tags); - - return true; + set_page_mte_tagged(page); + } } void mte_invalidate_tags(int type, pgoff_t offset) diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 5922178d7a06..79dd201c59d8 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -202,8 +202,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) /* * This function is used to determine if a linear map page has been marked as - * not-valid. Walk the page table and check the PTE_VALID bit. This is based - * on kern_addr_valid(), which almost does what we need. + * not-valid. Walk the page table and check the PTE_VALID bit. * * Because this is only called on the kernel linear map, p?d_sect() implies * p?d_present(). When debug_pagealloc is enabled, sections mappings are diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b9ecbbae1e1a..066fa60b93d2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -189,16 +189,12 @@ SYM_FUNC_END(cpu_do_resume) * called by anything else. It can only be executed from a TTBR0 mapping. */ SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1) - save_and_disable_daif flags=x2 - __idmap_cpu_set_reserved_ttbr1 x1, x3 offset_ttbr1 x0, x3 msr ttbr1_el1, x0 isb - restore_daif x2 - ret SYM_FUNC_END(idmap_cpu_replace_ttbr1) .popsection |