diff options
Diffstat (limited to 'arch/arm64/mm')
| -rw-r--r-- | arch/arm64/mm/cache.S | 3 | ||||
| -rw-r--r-- | arch/arm64/mm/dma-mapping.c | 288 | ||||
| -rw-r--r-- | arch/arm64/mm/fault.c | 33 | ||||
| -rw-r--r-- | arch/arm64/mm/hugetlbpage.c | 33 | ||||
| -rw-r--r-- | arch/arm64/mm/init.c | 54 | ||||
| -rw-r--r-- | arch/arm64/mm/kasan_init.c | 57 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 48 | ||||
| -rw-r--r-- | arch/arm64/mm/numa.c | 10 | ||||
| -rw-r--r-- | arch/arm64/mm/pageattr.c | 21 | ||||
| -rw-r--r-- | arch/arm64/mm/proc.S | 22 |
10 files changed, 207 insertions, 362 deletions
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 0c22ede52f90..a194fd0e837f 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -212,6 +212,9 @@ ENDPROC(__dma_clean_area) * - size - size in question */ ENTRY(__clean_dcache_area_pop) + alternative_if_not ARM64_HAS_DCPOP + b __clean_dcache_area_poc + alternative_else_nop_endif dcache_by_line_op cvap, sy, x0, x1, x2, x3 ret ENDPIPROC(__clean_dcache_area_pop) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index a3ac26284845..fb0908456a1f 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -33,113 +33,6 @@ #include <asm/cacheflush.h> -static struct gen_pool *atomic_pool __ro_after_init; - -#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; - -static int __init early_coherent_pool(char *p) -{ - atomic_pool_size = memparse(p, &p); - return 0; -} -early_param("coherent_pool", early_coherent_pool); - -static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) -{ - unsigned long val; - void *ptr = NULL; - - if (!atomic_pool) { - WARN(1, "coherent pool not initialised!\n"); - return NULL; - } - - val = gen_pool_alloc(atomic_pool, size); - if (val) { - phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); - - *ret_page = phys_to_page(phys); - ptr = (void *)val; - memset(ptr, 0, size); - } - - return ptr; -} - -static bool __in_atomic_pool(void *start, size_t size) -{ - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); -} - -static int __free_from_pool(void *start, size_t size) -{ - if (!__in_atomic_pool(start, size)) - return 0; - - gen_pool_free(atomic_pool, (unsigned long)start, size); - - return 1; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs) -{ - struct page *page; - void *ptr, *coherent_ptr; - pgprot_t prot = pgprot_writecombine(PAGE_KERNEL); - - size = PAGE_ALIGN(size); - - if (!gfpflags_allow_blocking(flags)) { - struct page *page = NULL; - void *addr = __alloc_from_pool(size, &page, flags); - - if (addr) - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - - return addr; - } - - ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); - if (!ptr) - goto no_mem; - - /* remove any dirty cache lines on the kernel alias */ - __dma_flush_area(ptr, size); - - /* create a coherent mapping */ - page = virt_to_page(ptr); - coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, __builtin_return_address(0)); - if (!coherent_ptr) - goto no_map; - - return coherent_ptr; - -no_map: - dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); -no_mem: - return NULL; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) { - void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); - - vunmap(vaddr); - dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); - } -} - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_to_phys(dev, dma_addr)); -} - pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { @@ -160,6 +53,11 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_unmap_area(phys_to_virt(paddr), size, dir); } +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + __dma_flush_area(page_address(page), size); +} + #ifdef CONFIG_IOMMU_DMA static int __swiotlb_get_sgtable_page(struct sg_table *sgt, struct page *page, size_t size) @@ -191,167 +89,13 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -static int __init atomic_pool_init(void) -{ - pgprot_t prot = __pgprot(PROT_NORMAL_NC); - unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; - struct page *page; - void *addr; - unsigned int pool_size_order = get_order(atomic_pool_size); - - if (dev_get_cma_area(NULL)) - page = dma_alloc_from_contiguous(NULL, nr_pages, - pool_size_order, false); - else - page = alloc_pages(GFP_DMA32, pool_size_order); - - if (page) { - int ret; - void *page_addr = page_address(page); - - memset(page_addr, 0, atomic_pool_size); - __dma_flush_area(page_addr, atomic_pool_size); - - atomic_pool = gen_pool_create(PAGE_SHIFT, -1); - if (!atomic_pool) - goto free_page; - - addr = dma_common_contiguous_remap(page, atomic_pool_size, - VM_USERMAP, prot, atomic_pool_init); - - if (!addr) - goto destroy_genpool; - - ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, - page_to_phys(page), - atomic_pool_size, -1); - if (ret) - goto remove_mapping; - - gen_pool_set_algo(atomic_pool, - gen_pool_first_fit_order_align, - NULL); - - pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", - atomic_pool_size / 1024); - return 0; - } - goto out; - -remove_mapping: - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); -destroy_genpool: - gen_pool_destroy(atomic_pool); - atomic_pool = NULL; -free_page: - if (!dma_release_from_contiguous(NULL, page, nr_pages)) - __free_pages(page, pool_size_order); -out: - pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", - atomic_pool_size / 1024); - return -ENOMEM; -} - -/******************************************** - * The following APIs are for dummy DMA ops * - ********************************************/ - -static void *__dummy_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs) -{ - return NULL; -} - -static void __dummy_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ -} - -static int __dummy_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} - -static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static void __dummy_sync_single(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ -} - -static void __dummy_sync_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} - -static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return 1; -} - -static int __dummy_dma_supported(struct device *hwdev, u64 mask) -{ - return 0; -} - -const struct dma_map_ops dummy_dma_ops = { - .alloc = __dummy_alloc, - .free = __dummy_free, - .mmap = __dummy_mmap, - .map_page = __dummy_map_page, - .unmap_page = __dummy_unmap_page, - .map_sg = __dummy_map_sg, - .unmap_sg = __dummy_unmap_sg, - .sync_single_for_cpu = __dummy_sync_single, - .sync_single_for_device = __dummy_sync_single, - .sync_sg_for_cpu = __dummy_sync_sg, - .sync_sg_for_device = __dummy_sync_sg, - .mapping_error = __dummy_mapping_error, - .dma_supported = __dummy_dma_supported, -}; -EXPORT_SYMBOL(dummy_dma_ops); - static int __init arm64_dma_init(void) { WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(), TAINT_CPU_OUT_OF_SPEC, "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", ARCH_DMA_MINALIGN, cache_line_size()); - - return atomic_pool_init(); + return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); } arch_initcall(arm64_dma_init); @@ -397,17 +141,17 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, page = alloc_pages(gfp, get_order(size)); addr = page ? page_address(page) : NULL; } else { - addr = __alloc_from_pool(size, &page, gfp); + addr = dma_alloc_from_pool(size, &page, gfp); } if (!addr) return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { if (coherent) __free_pages(page, get_order(size)); else - __free_from_pool(addr, size); + dma_free_from_pool(addr, size); addr = NULL; } } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { @@ -420,7 +164,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); return NULL; @@ -429,9 +173,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, prot, __builtin_return_address(0)); if (addr) { - memset(addr, 0, size); if (!coherent) __dma_flush_area(page_to_virt(page), iosize); + memset(addr, 0, size); } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, @@ -471,9 +215,9 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * coherent devices. * Hence how dodgy the below logic looks... */ - if (__in_atomic_pool(cpu_addr, size)) { + if (dma_in_atomic_pool(cpu_addr, size)) { iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - __free_from_pool(cpu_addr, size); + dma_free_from_pool(cpu_addr, size); } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { struct page *page = vmalloc_to_page(cpu_addr); @@ -580,7 +324,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - !iommu_dma_mapping_error(dev, dev_addr)) + dev_addr != DMA_MAPPING_ERROR) __dma_map_area(page_address(page) + offset, size, dir); return dev_addr; @@ -663,7 +407,6 @@ static const struct dma_map_ops iommu_dma_ops = { .sync_sg_for_device = __iommu_sync_sg_for_device, .map_resource = iommu_dma_map_resource, .unmap_resource = iommu_dma_unmap_resource, - .mapping_error = iommu_dma_mapping_error, }; static int __init __iommu_dma_init(void) @@ -719,9 +462,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - if (!dev->dma_ops) - dev->dma_ops = &swiotlb_dma_ops; - dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 7d9571f4ae3d..efb7b2cbead5 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -40,6 +40,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> +#include <asm/kasan.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -132,6 +133,18 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= VA_START; +} + /* * Dump out the page tables associated with 'addr' in the currently active mm. */ @@ -141,7 +154,7 @@ void show_pte(unsigned long addr) pgd_t *pgdp; pgd_t pgd; - if (addr < TASK_SIZE) { + if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { @@ -149,7 +162,7 @@ void show_pte(unsigned long addr) addr); return; } - } else if (addr >= VA_START) { + } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { @@ -160,7 +173,7 @@ void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - VA_BITS, mm->pgd); + mm == &init_mm ? VA_BITS : (int) vabits_user, mm->pgd); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -254,7 +267,7 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, if (fsc_type == ESR_ELx_FSC_PERM) return true; - if (addr < TASK_SIZE && system_uses_ttbr0_pan()) + if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return fsc_type == ESR_ELx_FSC_FAULT && (regs->pstate & PSR_PAN_BIT); @@ -319,7 +332,7 @@ static void set_thread_esr(unsigned long address, unsigned int esr) * type", so we ignore this wrinkle and just return the translation * fault.) */ - if (current->thread.fault_address >= TASK_SIZE) { + if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* @@ -455,7 +468,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - if (addr < TASK_SIZE && is_el1_permission_fault(addr, esr, regs)) { + if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { /* regs->orig_addr_limit may be 0 if we entered from EL0 */ if (regs->orig_addr_limit == KERNEL_DS) die_kernel_fault("access to user memory with fs=KERNEL_DS", @@ -603,7 +616,7 @@ static int __kprobes do_translation_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (addr < TASK_SIZE) + if (is_ttbr0_addr(addr)) return do_page_fault(addr, esr, regs); do_bad_area(addr, esr, regs); @@ -758,7 +771,7 @@ asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, * re-enabled IRQs. If the address is a kernel address, apply * BP hardening prior to enabling IRQs and pre-emption. */ - if (addr > TASK_SIZE) + if (!is_ttbr0_addr(addr)) arm64_apply_bp_hardening(); local_daif_restore(DAIF_PROCCTX); @@ -771,7 +784,7 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr, struct pt_regs *regs) { if (user_mode(regs)) { - if (instruction_pointer(regs) > TASK_SIZE) + if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); local_daif_restore(DAIF_PROCCTX); } @@ -825,7 +838,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, if (interrupts_enabled(regs)) trace_hardirqs_off(); - if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE) + if (user_mode(regs) && !is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); if (!inf->fn(addr, esr, regs)) { diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index f58ea503ad01..28cbc22d7e30 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -429,6 +429,27 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); } +static void __init add_huge_page_size(unsigned long size) +{ + if (size_to_hstate(size)) + return; + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); +} + +static int __init hugetlbpage_init(void) +{ +#ifdef CONFIG_ARM64_4K_PAGES + add_huge_page_size(PUD_SIZE); +#endif + add_huge_page_size(PMD_SIZE * CONT_PMDS); + add_huge_page_size(PMD_SIZE); + add_huge_page_size(PAGE_SIZE * CONT_PTES); + + return 0; +} +arch_initcall(hugetlbpage_init); + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); @@ -440,7 +461,7 @@ static __init int setup_hugepagesz(char *opt) case PMD_SIZE * CONT_PMDS: case PMD_SIZE: case PAGE_SIZE * CONT_PTES: - hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); + add_huge_page_size(ps); return 1; } @@ -449,13 +470,3 @@ static __init int setup_hugepagesz(char *opt) return 0; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PTE_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9b432d9fcada..a8f2e4792ef9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -59,25 +59,9 @@ * that cannot be mistaken for a real physical address. */ s64 memstart_addr __ro_after_init = -1; -phys_addr_t arm64_dma_phys_limit __ro_after_init; - -#ifdef CONFIG_BLK_DEV_INITRD -static int __init early_initrd(char *p) -{ - unsigned long start, size; - char *endp; - - start = memparse(p, &endp); - if (*endp == ',') { - size = memparse(endp + 1, NULL); +EXPORT_SYMBOL(memstart_addr); - initrd_start = start; - initrd_end = start + size; - } - return 0; -} -early_param("initrd", early_initrd); -#endif +phys_addr_t arm64_dma_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -289,6 +273,14 @@ int pfn_valid(unsigned long pfn) if ((addr >> PAGE_SHIFT) != pfn) return 0; + +#ifdef CONFIG_SPARSEMEM + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) + return 0; + + if (!valid_section(__nr_to_section(pfn_to_section_nr(pfn)))) + return 0; +#endif return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_valid); @@ -407,14 +399,14 @@ void __init arm64_memblock_init(void) memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } - if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) { + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* * Add back the memory we just removed if it results in the * initrd to become inaccessible via the linear mapping. * Otherwise, this is a no-op */ - u64 base = initrd_start & PAGE_MASK; - u64 size = PAGE_ALIGN(initrd_end) - base; + u64 base = phys_initrd_start & PAGE_MASK; + u64 size = PAGE_ALIGN(phys_initrd_size); /* * We can only add back the initrd memory if we don't end up @@ -458,15 +450,11 @@ void __init arm64_memblock_init(void) * pagetables with memblock. */ memblock_reserve(__pa_symbol(_text), _end - _text); -#ifdef CONFIG_BLK_DEV_INITRD - if (initrd_start) { - memblock_reserve(initrd_start, initrd_end - initrd_start); - + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ - initrd_start = __phys_to_virt(initrd_start); - initrd_end = __phys_to_virt(initrd_end); + initrd_start = __phys_to_virt(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; } -#endif early_init_fdt_scan_reserved_mem(); @@ -607,15 +595,7 @@ void __init mem_init(void) * detected at build time already. */ #ifdef CONFIG_COMPAT - BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); -#endif - -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* - * Make sure we chose the upper bound of sizeof(struct page) - * correctly when sizing the VMEMMAP array. - */ - BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); + BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64); #endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 63527e585aac..4b55b15707a3 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -39,7 +39,15 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) { void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, node); + MEMBLOCK_ALLOC_KASAN, node); + return __pa(p); +} + +static phys_addr_t __init kasan_alloc_raw_page(int node) +{ + void *p = memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE, + __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_KASAN, node); return __pa(p); } @@ -47,8 +55,9 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { if (pmd_none(READ_ONCE(*pmdp))) { - phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) - : kasan_alloc_zeroed_page(node); + phys_addr_t pte_phys = early ? + __pa_symbol(kasan_early_shadow_pte) + : kasan_alloc_zeroed_page(node); __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } @@ -60,8 +69,9 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { if (pud_none(READ_ONCE(*pudp))) { - phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) - : kasan_alloc_zeroed_page(node); + phys_addr_t pmd_phys = early ? + __pa_symbol(kasan_early_shadow_pmd) + : kasan_alloc_zeroed_page(node); __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } @@ -72,8 +82,9 @@ static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { if (pgd_none(READ_ONCE(*pgdp))) { - phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) - : kasan_alloc_zeroed_page(node); + phys_addr_t pud_phys = early ? + __pa_symbol(kasan_early_shadow_pud) + : kasan_alloc_zeroed_page(node); __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } @@ -87,8 +98,11 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { - phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) - : kasan_alloc_zeroed_page(node); + phys_addr_t page_phys = early ? + __pa_symbol(kasan_early_shadow_page) + : kasan_alloc_raw_page(node); + if (!early) + memset(__va(page_phys), KASAN_SHADOW_INIT, PAGE_SIZE); next = addr + PAGE_SIZE; set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); @@ -205,14 +219,14 @@ void __init kasan_init(void) kasan_map_populate(kimg_shadow_start, kimg_shadow_end, early_pfn_to_nid(virt_to_pfn(lm_alias(_text)))); - kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, - (void *)mod_shadow_start); - kasan_populate_zero_shadow((void *)kimg_shadow_end, - kasan_mem_to_shadow((void *)PAGE_OFFSET)); + kasan_populate_early_shadow((void *)KASAN_SHADOW_START, + (void *)mod_shadow_start); + kasan_populate_early_shadow((void *)kimg_shadow_end, + kasan_mem_to_shadow((void *)PAGE_OFFSET)); if (kimg_shadow_start > mod_shadow_end) - kasan_populate_zero_shadow((void *)mod_shadow_end, - (void *)kimg_shadow_start); + kasan_populate_early_shadow((void *)mod_shadow_end, + (void *)kimg_shadow_start); for_each_memblock(memory, reg) { void *start = (void *)__phys_to_virt(reg->base); @@ -227,16 +241,19 @@ void __init kasan_init(void) } /* - * KAsan may reuse the contents of kasan_zero_pte directly, so we - * should make sure that it maps the zero page read-only. + * KAsan may reuse the contents of kasan_early_shadow_pte directly, + * so we should make sure that it maps the zero page read-only. */ for (i = 0; i < PTRS_PER_PTE; i++) - set_pte(&kasan_zero_pte[i], - pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + set_pte(&kasan_early_shadow_pte[i], + pfn_pte(sym_to_pfn(kasan_early_shadow_page), + PAGE_KERNEL_RO)); - memset(kasan_zero_page, 0, PAGE_SIZE); + memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); + kasan_init_tags(); + /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; pr_info("KernelAddressSanitizer initialized\n"); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d1d6601b385d..b6f5aa52ac67 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -52,6 +52,8 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS); u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; +u64 vabits_user __ro_after_init; +EXPORT_SYMBOL(vabits_user); u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -451,7 +453,7 @@ static void __init map_mem(pgd_t *pgdp) struct memblock_region *reg; int flags = 0; - if (debug_pagealloc_enabled()) + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* @@ -552,7 +554,19 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, static int __init parse_rodata(char *arg) { - return strtobool(arg, &rodata_enabled); + int ret = strtobool(arg, &rodata_enabled); + if (!ret) { + rodata_full = false; + return 0; + } + + /* permit 'full' in addition to boolean options */ + if (strcmp(arg, "full")) + return -EINVAL; + + rodata_enabled = true; + rodata_full = true; + return 0; } early_param("rodata", parse_rodata); @@ -989,10 +1003,8 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - if (!pmd_present(pmd)) - return 1; if (!pmd_table(pmd)) { - VM_WARN_ON(!pmd_table(pmd)); + VM_WARN_ON(1); return 1; } @@ -1012,10 +1024,8 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - if (!pud_present(pud)) - return 1; if (!pud_table(pud)) { - VM_WARN_ON(!pud_table(pud)); + VM_WARN_ON(1); return 1; } @@ -1032,3 +1042,25 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pmd_free(NULL, table); return 1; } + +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; /* Don't attempt a block mapping */ +} + +#ifdef CONFIG_MEMORY_HOTPLUG +int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, + bool want_memblock) +{ + int flags = 0; + + if (rodata_full || debug_pagealloc_enabled()) + flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; + + __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), + size, PAGE_KERNEL, pgd_pgtable_alloc, flags); + + return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, + altmap, want_memblock); +} +#endif diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 27a31efd9e8e..ae34e3a1cef1 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -466,3 +466,13 @@ void __init arm64_numa_init(void) numa_init(dummy_numa_init); } + +/* + * We hope that we will be hotplugging memory on nodes we already know about, + * such that acpi_get_node() succeeds and we never fall back to this... + */ +int memory_add_physaddr_to_nid(u64 addr) +{ + pr_warn("Unknown node for memory at 0x%llx, assuming node 0\n", addr); + return 0; +} diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a56359373d8b..6cd645edcf35 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -25,6 +25,8 @@ struct page_change_data { pgprot_t clear_mask; }; +bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED); + static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { @@ -64,6 +66,7 @@ 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; if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; @@ -93,6 +96,24 @@ static int change_memory_common(unsigned long addr, int numpages, if (!numpages) return 0; + /* + * If we are manipulating read-only permissions, apply the same + * change to the linear mapping of the pages that back this VM area. + */ + 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); + } + } + + /* + * Get rid of potentially aliasing lazily unmapped vm areas that may + * have permissions set that deviate from the ones we are setting here. + */ + vm_unmap_aliases(); + return __change_memory_common(start, size, set_mask, clear_mask); } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 2c75b0b903ae..73886a5f1f30 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -47,6 +47,12 @@ /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA +#ifdef CONFIG_KASAN_SW_TAGS +#define TCR_KASAN_FLAGS TCR_TBI1 +#else +#define TCR_KASAN_FLAGS 0 +#endif + #define MAIR(attr, mt) ((attr) << ((mt) * 8)) /* @@ -182,6 +188,7 @@ ENDPROC(cpu_do_switch_mm) .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 adrp \tmp1, empty_zero_page phys_to_ttbr \tmp2, \tmp1 + offset_ttbr1 \tmp2 msr ttbr1_el1, \tmp2 isb tlbi vmalle1 @@ -200,6 +207,7 @@ ENTRY(idmap_cpu_replace_ttbr1) __idmap_cpu_set_reserved_ttbr1 x1, x3 + offset_ttbr1 x0 msr ttbr1_el1, x0 isb @@ -254,6 +262,7 @@ ENTRY(idmap_kpti_install_ng_mappings) pte .req x16 mrs swapper_ttb, ttbr1_el1 + restore_ttbr1 swapper_ttb adr flag_ptr, __idmap_kpti_flag cbnz cpu, __idmap_kpti_secondary @@ -373,6 +382,7 @@ __idmap_kpti_secondary: cbnz w18, 1b /* All done, act like nothing happened */ + offset_ttbr1 swapper_ttb msr ttbr1_el1, swapper_ttb isb ret @@ -445,8 +455,16 @@ ENTRY(__cpu_setup) */ ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 - tcr_set_idmap_t0sz x10, x9 + TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS + +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + ldr_l x9, vabits_user + sub x9, xzr, x9 + add x9, x9, #64 +#else + ldr_l x9, idmap_t0sz +#endif + tcr_set_t0sz x10, x9 /* * Set the IPS bits in TCR_EL1. |