diff options
Diffstat (limited to 'arch/arm64/mm')
-rw-r--r-- | arch/arm64/mm/dma-mapping.c | 442 | ||||
-rw-r--r-- | arch/arm64/mm/dump.c | 24 | ||||
-rw-r--r-- | arch/arm64/mm/fault.c | 186 | ||||
-rw-r--r-- | arch/arm64/mm/flush.c | 3 | ||||
-rw-r--r-- | arch/arm64/mm/hugetlbpage.c | 12 | ||||
-rw-r--r-- | arch/arm64/mm/init.c | 40 | ||||
-rw-r--r-- | arch/arm64/mm/ioremap.c | 4 | ||||
-rw-r--r-- | arch/arm64/mm/kasan_init.c | 9 | ||||
-rw-r--r-- | arch/arm64/mm/mmap.c | 72 | ||||
-rw-r--r-- | arch/arm64/mm/mmu.c | 66 | ||||
-rw-r--r-- | arch/arm64/mm/numa.c | 2 | ||||
-rw-r--r-- | arch/arm64/mm/pageattr.c | 53 | ||||
-rw-r--r-- | arch/arm64/mm/pgd.c | 8 | ||||
-rw-r--r-- | arch/arm64/mm/proc.S | 20 |
14 files changed, 294 insertions, 647 deletions
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 5992eb9a9a08..9239416e93d4 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -1,35 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * SWIOTLB-based DMA API implementation - * * Copyright (C) 2012 ARM Ltd. * Author: Catalin Marinas <catalin.marinas@arm.com> */ #include <linux/gfp.h> -#include <linux/acpi.h> -#include <linux/memblock.h> #include <linux/cache.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <linux/genalloc.h> -#include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> -#include <linux/dma-contiguous.h> -#include <linux/vmalloc.h> -#include <linux/swiotlb.h> -#include <linux/pci.h> +#include <linux/dma-iommu.h> +#include <xen/xen.h> +#include <xen/swiotlb-xen.h> #include <asm/cacheflush.h> -pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, - unsigned long attrs) -{ - if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE)) - return pgprot_writecombine(prot); - return prot; -} - void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { @@ -48,424 +31,29 @@ void arch_dma_prep_coherent(struct page *page, size_t size) } #ifdef CONFIG_IOMMU_DMA -static int __swiotlb_get_sgtable_page(struct sg_table *sgt, - struct page *page, size_t size) -{ - int ret = sg_alloc_table(sgt, 1, GFP_KERNEL); - - if (!ret) - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); - - return ret; -} - -static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, - unsigned long pfn, size_t size) -{ - int ret = -ENXIO; - unsigned long nr_vma_pages = vma_pages(vma); - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned long off = vma->vm_pgoff; - - if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) { - ret = remap_pfn_range(vma, vma->vm_start, - pfn + off, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); - } - - return ret; -} -#endif /* CONFIG_IOMMU_DMA */ - -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 dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); -} -arch_initcall(arm64_dma_init); - -#ifdef CONFIG_IOMMU_DMA -#include <linux/dma-iommu.h> -#include <linux/platform_device.h> -#include <linux/amba/bus.h> - -/* Thankfully, all cache ops are by VA so we can ignore phys here */ -static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) -{ - __dma_flush_area(virt, PAGE_SIZE); -} - -static void *__iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, - unsigned long attrs) -{ - bool coherent = dev_is_dma_coherent(dev); - int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); - size_t iosize = size; - void *addr; - - if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) - return NULL; - - size = PAGE_ALIGN(size); - - /* - * Some drivers rely on this, and we probably don't want the - * possibility of stale kernel data being read by devices anyway. - */ - gfp |= __GFP_ZERO; - - if (!gfpflags_allow_blocking(gfp)) { - struct page *page; - /* - * In atomic context we can't remap anything, so we'll only - * get the virtually contiguous buffer we need by way of a - * physically contiguous allocation. - */ - if (coherent) { - page = alloc_pages(gfp, get_order(size)); - addr = page ? page_address(page) : NULL; - } else { - addr = dma_alloc_from_pool(size, &page, gfp); - } - if (!addr) - return NULL; - - *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (*handle == DMA_MAPPING_ERROR) { - if (coherent) - __free_pages(page, get_order(size)); - else - dma_free_from_pool(addr, size); - addr = NULL; - } - } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); - struct page *page; - - page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, - get_order(size), gfp & __GFP_NOWARN); - if (!page) - return NULL; - - *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (*handle == DMA_MAPPING_ERROR) { - dma_release_from_contiguous(dev, page, - size >> PAGE_SHIFT); - return NULL; - } - addr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, - __builtin_return_address(0)); - if (addr) { - 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, - size >> PAGE_SHIFT); - } - } else { - pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs); - struct page **pages; - - pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot, - handle, flush_page); - if (!pages) - return NULL; - - addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, - __builtin_return_address(0)); - if (!addr) - iommu_dma_free(dev, pages, iosize, handle); - } - return addr; -} - -static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - size_t iosize = size; - - size = PAGE_ALIGN(size); - /* - * @cpu_addr will be one of 4 things depending on how it was allocated: - * - A remapped array of pages for contiguous allocations. - * - A remapped array of pages from iommu_dma_alloc(), for all - * non-atomic allocations. - * - A non-cacheable alias from the atomic pool, for atomic - * allocations by non-coherent devices. - * - A normal lowmem address, for atomic allocations by - * coherent devices. - * Hence how dodgy the below logic looks... - */ - if (dma_in_atomic_pool(cpu_addr, size)) { - iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - dma_free_from_pool(cpu_addr, size); - } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { - struct page *page = vmalloc_to_page(cpu_addr); - - iommu_dma_unmap_page(dev, handle, iosize, 0, attrs); - dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); - dma_common_free_remap(cpu_addr, size, VM_USERMAP); - } else if (is_vmalloc_addr(cpu_addr)){ - struct vm_struct *area = find_vm_area(cpu_addr); - - if (WARN_ON(!area || !area->pages)) - return; - iommu_dma_free(dev, area->pages, iosize, &handle); - dma_common_free_remap(cpu_addr, size, VM_USERMAP); - } else { - iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - __free_pages(virt_to_page(cpu_addr), get_order(size)); - } -} - -static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - struct vm_struct *area; - int ret; - - vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); - - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) - return ret; - - if (!is_vmalloc_addr(cpu_addr)) { - unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr)); - return __swiotlb_mmap_pfn(vma, pfn, size); - } - - if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { - /* - * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, - * hence in the vmalloc space. - */ - unsigned long pfn = vmalloc_to_pfn(cpu_addr); - return __swiotlb_mmap_pfn(vma, pfn, size); - } - - area = find_vm_area(cpu_addr); - if (WARN_ON(!area || !area->pages)) - return -ENXIO; - - return iommu_dma_mmap(area->pages, size, vma); -} - -static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, - size_t size, unsigned long attrs) -{ - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct vm_struct *area = find_vm_area(cpu_addr); - - if (!is_vmalloc_addr(cpu_addr)) { - struct page *page = virt_to_page(cpu_addr); - return __swiotlb_get_sgtable_page(sgt, page, size); - } - - if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { - /* - * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, - * hence in the vmalloc space. - */ - struct page *page = vmalloc_to_page(cpu_addr); - return __swiotlb_get_sgtable_page(sgt, page, size); - } - - if (WARN_ON(!area || !area->pages)) - return -ENXIO; - - return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size, - GFP_KERNEL); -} - -static void __iommu_sync_single_for_cpu(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ - phys_addr_t phys; - - if (dev_is_dma_coherent(dev)) - return; - - phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr); - arch_sync_dma_for_cpu(dev, phys, size, dir); -} - -static void __iommu_sync_single_for_device(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ - phys_addr_t phys; - - if (dev_is_dma_coherent(dev)) - return; - - phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr); - arch_sync_dma_for_device(dev, phys, size, dir); -} - -static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - bool coherent = dev_is_dma_coherent(dev); - int prot = dma_info_to_prot(dir, coherent, attrs); - dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); - - if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - dev_addr != DMA_MAPPING_ERROR) - __dma_map_area(page_address(page) + offset, size, dir); - - return dev_addr; -} - -static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __iommu_sync_single_for_cpu(dev, dev_addr, size, dir); - - iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs); -} - -static void __iommu_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - if (dev_is_dma_coherent(dev)) - return; - - for_each_sg(sgl, sg, nelems, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); -} - -static void __iommu_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - if (dev_is_dma_coherent(dev)) - return; - - for_each_sg(sgl, sg, nelems, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); -} - -static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - bool coherent = dev_is_dma_coherent(dev); - - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __iommu_sync_sg_for_device(dev, sgl, nelems, dir); - - return iommu_dma_map_sg(dev, sgl, nelems, - dma_info_to_prot(dir, coherent, attrs)); -} - -static void __iommu_unmap_sg_attrs(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir); - - iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs); -} - -static const struct dma_map_ops iommu_dma_ops = { - .alloc = __iommu_alloc_attrs, - .free = __iommu_free_attrs, - .mmap = __iommu_mmap_attrs, - .get_sgtable = __iommu_get_sgtable, - .map_page = __iommu_map_page, - .unmap_page = __iommu_unmap_page, - .map_sg = __iommu_map_sg_attrs, - .unmap_sg = __iommu_unmap_sg_attrs, - .sync_single_for_cpu = __iommu_sync_single_for_cpu, - .sync_single_for_device = __iommu_sync_single_for_device, - .sync_sg_for_cpu = __iommu_sync_sg_for_cpu, - .sync_sg_for_device = __iommu_sync_sg_for_device, - .map_resource = iommu_dma_map_resource, - .unmap_resource = iommu_dma_unmap_resource, -}; - -static int __init __iommu_dma_init(void) -{ - return iommu_dma_init(); -} -arch_initcall(__iommu_dma_init); - -static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *ops) -{ - struct iommu_domain *domain; - - if (!ops) - return; - - /* - * The IOMMU core code allocates the default DMA domain, which the - * underlying IOMMU driver needs to support via the dma-iommu layer. - */ - domain = iommu_get_domain_for_dev(dev); - - if (!domain) - goto out_err; - - if (domain->type == IOMMU_DOMAIN_DMA) { - if (iommu_dma_init_domain(domain, dma_base, size, dev)) - goto out_err; - - dev->dma_ops = &iommu_dma_ops; - } - - return; - -out_err: - pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", - dev_name(dev)); -} - void arch_teardown_dma_ops(struct device *dev) { dev->dma_ops = NULL; } - -#else - -static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu) -{ } - -#endif /* CONFIG_IOMMU_DMA */ +#endif void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { + int cls = cache_line_size_of_cpu(); + + WARN_TAINT(!coherent && cls > ARCH_DMA_MINALIGN, + TAINT_CPU_OUT_OF_SPEC, + "%s %s: ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", + dev_driver_string(dev), dev_name(dev), + ARCH_DMA_MINALIGN, cls); + dev->dma_coherent = coherent; - __iommu_setup_dma_ops(dev, dma_base, size, iommu); + if (iommu) + iommu_setup_dma_ops(dev, dma_base, size); #ifdef CONFIG_XEN if (xen_initial_domain()) - dev->dma_ops = xen_dma_ops; + dev->dma_ops = &xen_swiotlb_dma_ops; #endif } diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 82b3a7fdb4a6..93f9f77582ae 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -25,9 +25,20 @@ #include <asm/pgtable-hwdef.h> #include <asm/ptdump.h> -static const struct addr_marker address_markers[] = { + +enum address_markers_idx { + PAGE_OFFSET_NR = 0, + PAGE_END_NR, #ifdef CONFIG_KASAN - { KASAN_SHADOW_START, "Kasan shadow start" }, + KASAN_START_NR, +#endif +}; + +static struct addr_marker address_markers[] = { + { PAGE_OFFSET, "Linear Mapping start" }, + { 0 /* PAGE_END */, "Linear Mapping end" }, +#ifdef CONFIG_KASAN + { 0 /* KASAN_SHADOW_START */, "Kasan shadow start" }, { KASAN_SHADOW_END, "Kasan shadow end" }, #endif { MODULES_VADDR, "Modules start" }, @@ -42,7 +53,6 @@ static const struct addr_marker address_markers[] = { { VMEMMAP_START, "vmemmap start" }, { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" }, #endif - { PAGE_OFFSET, "Linear mapping" }, { -1, NULL }, }; @@ -376,7 +386,7 @@ static void ptdump_initialize(void) static struct ptdump_info kernel_ptdump_info = { .mm = &init_mm, .markers = address_markers, - .base_addr = VA_START, + .base_addr = PAGE_OFFSET, }; void ptdump_check_wx(void) @@ -390,7 +400,7 @@ void ptdump_check_wx(void) .check_wx = true, }; - walk_pgd(&st, &init_mm, VA_START); + walk_pgd(&st, &init_mm, PAGE_OFFSET); note_page(&st, 0, 0, 0); if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", @@ -401,6 +411,10 @@ void ptdump_check_wx(void) static int ptdump_init(void) { + address_markers[PAGE_END_NR].start_address = PAGE_END; +#ifdef CONFIG_KASAN + address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START; +#endif ptdump_initialize(); ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); return 0; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2d115016feb4..115d7a0e4b08 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -8,6 +8,7 @@ */ #include <linux/acpi.h> +#include <linux/bitfield.h> #include <linux/extable.h> #include <linux/signal.h> #include <linux/mm.h> @@ -59,28 +60,6 @@ static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr) return debug_fault_info + DBG_ESR_EVT(esr); } -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) -{ - int ret = 0; - - /* kprobe_running() needs smp_processor_id() */ - if (!user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, esr)) - ret = 1; - preempt_enable(); - } - - return ret; -} -#else -static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) -{ - return 0; -} -#endif - static void data_abort_decode(unsigned int esr) { pr_alert("Data abort info:\n"); @@ -108,8 +87,8 @@ static void mem_abort_decode(unsigned int esr) pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%08x\n", esr); - pr_alert(" Exception class = %s, IL = %u bits\n", - esr_get_class_string(esr), + pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", + ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, @@ -131,7 +110,7 @@ static inline bool is_ttbr0_addr(unsigned long addr) 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; + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } /* @@ -160,10 +139,9 @@ static void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp=%016lx\n", + pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - mm == &init_mm ? VA_BITS : (int)vabits_user, - (unsigned long)virt_to_phys(mm->pgd)); + vabits_actual, (unsigned long)virt_to_phys(mm->pgd)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -264,6 +242,34 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, return false; } +static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, + unsigned int esr, + struct pt_regs *regs) +{ + unsigned long flags; + u64 par, dfsc; + + if (ESR_ELx_EC(esr) != ESR_ELx_EC_DABT_CUR || + (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT) + return false; + + local_irq_save(flags); + asm volatile("at s1e1r, %0" :: "r" (addr)); + isb(); + par = read_sysreg(par_el1); + local_irq_restore(flags); + + if (!(par & SYS_PAR_EL1_F)) + return false; + + /* + * If we got a different type of fault from the AT instruction, + * treat the translation fault as spurious. + */ + dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par); + return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; +} + static void die_kernel_fault(const char *msg, unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -292,6 +298,10 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; + if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), + "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) + return; + if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; @@ -384,40 +394,31 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADACCESS 0x020000 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags, - struct task_struct *tsk) + unsigned int mm_flags, unsigned long vm_flags) { - struct vm_area_struct *vma; - vm_fault_t fault; + struct vm_area_struct *vma = find_vma(mm, addr); - vma = find_vma(mm, addr); - fault = VM_FAULT_BADMAP; if (unlikely(!vma)) - goto out; - if (unlikely(vma->vm_start > addr)) - goto check_stack; + return VM_FAULT_BADMAP; /* * Ok, we have a good vm_area for this memory access, so we can handle * it. */ -good_area: + if (unlikely(vma->vm_start > addr)) { + if (!(vma->vm_flags & VM_GROWSDOWN)) + return VM_FAULT_BADMAP; + if (expand_stack(vma, addr)) + return VM_FAULT_BADMAP; + } + /* * Check that the permissions on the VMA allow for the fault which * occurred. */ - if (!(vma->vm_flags & vm_flags)) { - fault = VM_FAULT_BADACCESS; - goto out; - } - + if (!(vma->vm_flags & vm_flags)) + return VM_FAULT_BADACCESS; return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags); - -check_stack: - if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) - goto good_area; -out: - return fault; } static bool is_el0_instruction_abort(unsigned int esr) @@ -425,22 +426,27 @@ static bool is_el0_instruction_abort(unsigned int esr) return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } +/* + * Note: not valid for EL1 DC IVAC, but we never use that such that it + * should fault. EL0 cannot issue DC IVAC (undef). + */ +static bool is_write_abort(unsigned int esr) +{ + return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); +} + static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf; - struct task_struct *tsk; - struct mm_struct *mm; + struct mm_struct *mm = current->mm; vm_fault_t fault, major = 0; unsigned long vm_flags = VM_READ | VM_WRITE; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; - if (notify_page_fault(regs, esr)) + if (kprobe_page_fault(regs, esr)) return 0; - tsk = current; - mm = tsk->mm; - /* * If we're in an interrupt or have no user context, we must not take * the fault. @@ -453,7 +459,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (is_el0_instruction_abort(esr)) { vm_flags = VM_EXEC; - } else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) { + mm_flags |= FAULT_FLAG_INSTRUCTION; + } else if (is_write_abort(esr)) { vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } @@ -492,12 +499,14 @@ retry: */ might_sleep(); #ifdef CONFIG_DEBUG_VM - if (!user_mode(regs) && !search_exception_tables(regs->pc)) + if (!user_mode(regs) && !search_exception_tables(regs->pc)) { + up_read(&mm->mmap_sem); goto no_context; + } #endif } - fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk); + fault = __do_page_fault(mm, addr, mm_flags, vm_flags); major |= fault & VM_FAULT_MAJOR; if (fault & VM_FAULT_RETRY) { @@ -537,11 +546,11 @@ retry: * that point. */ if (major) { - tsk->maj_flt++; + current->maj_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr); } else { - tsk->min_flt++; + current->min_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr); } @@ -800,6 +809,53 @@ void __init hook_debug_fault_code(int nr, debug_fault_info[nr].name = name; } +/* + * In debug exception context, we explicitly disable preemption despite + * having interrupts disabled. + * This serves two purposes: it makes it much less likely that we would + * accidentally schedule in exception context and it will force a warning + * if we somehow manage to schedule by accident. + */ +static void debug_exception_enter(struct pt_regs *regs) +{ + /* + * Tell lockdep we disabled irqs in entry.S. Do nothing if they were + * already disabled to preserve the last enabled/disabled addresses. + */ + if (interrupts_enabled(regs)) + trace_hardirqs_off(); + + if (user_mode(regs)) { + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + } else { + /* + * We might have interrupted pretty much anything. In + * fact, if we're a debug exception, we can even interrupt + * NMI processing. We don't want this code makes in_nmi() + * to return true, but we need to notify RCU. + */ + rcu_nmi_enter(); + } + + preempt_disable(); + + /* This code is a bit fragile. Test it. */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); +} +NOKPROBE_SYMBOL(debug_exception_enter); + +static void debug_exception_exit(struct pt_regs *regs) +{ + preempt_enable_no_resched(); + + if (!user_mode(regs)) + rcu_nmi_exit(); + + if (interrupts_enabled(regs)) + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(debug_exception_exit); + #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); @@ -840,12 +896,7 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, if (cortex_a76_erratum_1463225_debug_handler(regs)) return; - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); + debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); @@ -855,7 +906,6 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, inf->sig, inf->code, (void __user *)pc, esr); } - if (interrupts_enabled(regs)) - trace_hardirqs_on(); + debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index dc19300309d2..ac485163a4a7 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -56,8 +56,7 @@ void __sync_icache_dcache(pte_t pte) struct page *page = pte_page(pte); if (!test_and_set_bit(PG_dcache_clean, &page->flags)) - sync_icache_aliases(page_address(page), - PAGE_SIZE << compound_order(page)); + sync_icache_aliases(page_address(page), page_size(page)); } EXPORT_SYMBOL_GPL(__sync_icache_dcache); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index f475e54fbc43..bbeb6a5a6ba6 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -228,7 +228,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, if (sz == PUD_SIZE) { ptep = (pte_t *)pudp; - } else if (sz == (PAGE_SIZE * CONT_PTES)) { + } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); @@ -246,7 +246,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = huge_pmd_share(mm, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); - } else if (sz == (PMD_SIZE * CONT_PMDS)) { + } else if (sz == (CONT_PMD_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); return (pte_t *)pmdp; @@ -454,9 +454,9 @@ 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(CONT_PMD_SIZE); add_huge_page_size(PMD_SIZE); - add_huge_page_size(PAGE_SIZE * CONT_PTES); + add_huge_page_size(CONT_PTE_SIZE); return 0; } @@ -470,9 +470,9 @@ static __init int setup_hugepagesz(char *opt) #ifdef CONFIG_ARM64_4K_PAGES case PUD_SIZE: #endif - case PMD_SIZE * CONT_PMDS: + case CONT_PMD_SIZE: case PMD_SIZE: - case PAGE_SIZE * CONT_PTES: + case CONT_PTE_SIZE: add_huge_page_size(ps); return 1; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 749c9b269f08..45c00a54909c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -50,6 +50,12 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); +s64 physvirt_offset __ro_after_init; +EXPORT_SYMBOL(physvirt_offset); + +struct page *vmemmap __ro_after_init; +EXPORT_SYMBOL(vmemmap); + phys_addr_t arm64_dma_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE @@ -180,8 +186,9 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); +#ifdef CONFIG_ZONE_DMA32 + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); +#endif max_zone_pfns[ZONE_NORMAL] = max; free_area_init_nodes(max_zone_pfns); @@ -300,7 +307,7 @@ static void __init fdt_enforce_memory_region(void) void __init arm64_memblock_init(void) { - const s64 linear_region_size = -(s64)PAGE_OFFSET; + const s64 linear_region_size = BIT(vabits_actual - 1); /* Handle linux,usable-memory-range property */ fdt_enforce_memory_region(); @@ -309,18 +316,25 @@ void __init arm64_memblock_init(void) memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX); /* - * Ensure that the linear region takes up exactly half of the kernel - * virtual address space. This way, we can distinguish a linear address - * from a kernel/module/vmalloc address by testing a single bit. - */ - BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1)); - - /* * Select a suitable value for the base of physical memory. */ memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); + physvirt_offset = PHYS_OFFSET - PAGE_OFFSET; + + vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)); + + /* + * If we are running with a 52-bit kernel VA config on a system that + * does not support it, we have to offset our vmemmap and physvirt_offset + * s.t. we avoid the 52-bit portion of the direct linear map + */ + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) { + vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT; + physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48); + } + /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be @@ -569,8 +583,12 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { + unsigned long aligned_start, aligned_end; + + aligned_start = __virt_to_phys(start) & PAGE_MASK; + aligned_end = PAGE_ALIGN(__virt_to_phys(end)); + memblock_free(aligned_start, aligned_end - aligned_start); free_reserved_area((void *)start, (void *)end, 0, "initrd"); - memblock_free(__virt_to_phys(start), end - start); } #endif diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index fdb595a5d65f..9be71bee902c 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -69,7 +69,7 @@ void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot) } EXPORT_SYMBOL(__ioremap); -void __iounmap(volatile void __iomem *io_addr) +void iounmap(volatile void __iomem *io_addr) { unsigned long addr = (unsigned long)io_addr & PAGE_MASK; @@ -80,7 +80,7 @@ void __iounmap(volatile void __iomem *io_addr) if (is_vmalloc_addr((void *)addr)) vunmap((void *)addr); } -EXPORT_SYMBOL(__iounmap); +EXPORT_SYMBOL(iounmap); void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size) { diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6cf97b904ebb..f87a32484ea8 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -156,7 +156,8 @@ asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true); @@ -225,10 +226,10 @@ 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_early_shadow((void *)KASAN_SHADOW_START, - (void *)mod_shadow_start); + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)PAGE_END), + (void *)mod_shadow_start); kasan_populate_early_shadow((void *)kimg_shadow_end, - kasan_mem_to_shadow((void *)PAGE_OFFSET)); + (void *)KASAN_SHADOW_END); if (kimg_shadow_start > mod_shadow_end) kasan_populate_early_shadow((void *)mod_shadow_end, diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index b050641b5139..3028bacbc4e9 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -21,78 +21,6 @@ #include <asm/cputype.h> /* - * Leave enough space between the mmap area and the stack to honour ulimit in - * the face of randomisation. - */ -#define MIN_GAP (SZ_128M) -#define MAX_GAP (STACK_TOP/6*5) - -static int mmap_is_legacy(struct rlimit *rlim_stack) -{ - if (current->personality & ADDR_COMPAT_LAYOUT) - return 1; - - if (rlim_stack->rlim_cur == RLIM_INFINITY) - return 1; - - return sysctl_legacy_va_layout; -} - -unsigned long arch_mmap_rnd(void) -{ - unsigned long rnd; - -#ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_32BIT)) - rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); - else -#endif - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); - return rnd << PAGE_SHIFT; -} - -static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) -{ - unsigned long gap = rlim_stack->rlim_cur; - unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap; - - /* Values close to RLIM_INFINITY can overflow. */ - if (gap + pad > gap) - gap += pad; - - if (gap < MIN_GAP) - gap = MIN_GAP; - else if (gap > MAX_GAP) - gap = MAX_GAP; - - return PAGE_ALIGN(STACK_TOP - gap - rnd); -} - -/* - * This function, called very early during the creation of a new process VM - * image, sets up which VM layout function to use: - */ -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) -{ - unsigned long random_factor = 0UL; - - if (current->flags & PF_RANDOMIZE) - random_factor = arch_mmap_rnd(); - - /* - * Fall back to the standard layout if the personality bit is set, or - * if the expected stack growth is unlimited: - */ - if (mmap_is_legacy(rlim_stack)) { - mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; - } else { - mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; - } -} - -/* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e5ae8663f230..60c929f3683b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -40,8 +40,9 @@ 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 __section(".mmuoff.data.write") vabits_actual; +EXPORT_SYMBOL(vabits_actual); u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -362,7 +363,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, static phys_addr_t __pgd_pgtable_alloc(int shift) { - void *ptr = (void *)__get_free_page(PGALLOC_GFP); + void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL); BUG_ON(!ptr); /* Ensure the zeroed page is visible to the page table walker */ @@ -383,7 +384,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) * folded, and if so pgtable_pmd_page_ctor() becomes nop. */ if (shift == PAGE_SHIFT) - BUG_ON(!pgtable_page_ctor(phys_to_page(pa))); + BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa))); else if (shift == PMD_SHIFT) BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa))); @@ -398,7 +399,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if (virt < VMALLOC_START) { + if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -425,7 +426,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, static void update_mapping_prot(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if (virt < VMALLOC_START) { + if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -646,6 +647,8 @@ static void __init map_kernel(pgd_t *pgdp) set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { + pgd_t *bm_pgdp; + pud_t *bm_pudp; /* * The fixmap shares its top level pgd entry with the kernel * mapping. This can really only occur when we are running @@ -653,9 +656,9 @@ static void __init map_kernel(pgd_t *pgdp) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, - pud_set_fixmap_offset(pgdp, FIXADDR_START), - lm_alias(bm_pmd)); + bm_pgdp = pgd_offset_raw(pgdp, FIXADDR_START); + bm_pudp = pud_set_fixmap_offset(bm_pgdp, FIXADDR_START); + pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); @@ -765,7 +768,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return 0; } -#endif /* CONFIG_ARM64_64K_PAGES */ +#endif /* !ARM64_SWAPPER_USES_SECTION_MAPS */ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { @@ -876,7 +879,7 @@ void __set_fixmap(enum fixed_addresses idx, } } -void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) +void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); int offset; @@ -929,17 +932,9 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } -void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +int __init arch_ioremap_p4d_supported(void) { - void *dt_virt; - int size; - - dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); - if (!dt_virt) - return NULL; - - memblock_reserve(dt_phys, size); - return dt_virt; + return 0; } int __init arch_ioremap_pud_supported(void) @@ -960,32 +955,28 @@ int __init arch_ioremap_pmd_supported(void) int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { - pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | - pgprot_val(mk_sect_prot(prot))); - pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot); + pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot)); /* Only allow permission changes for now */ if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)), pud_val(new_pud))) return 0; - BUG_ON(phys & ~PUD_MASK); + VM_BUG_ON(phys & ~PUD_MASK); set_pud(pudp, new_pud); return 1; } int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { - pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | - pgprot_val(mk_sect_prot(prot))); - pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot); + pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot)); /* Only allow permission changes for now */ if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)), pmd_val(new_pmd))) return 0; - BUG_ON(phys & ~PMD_MASK); + VM_BUG_ON(phys & ~PMD_MASK); set_pmd(pmdp, new_pmd); return 1; } @@ -1073,4 +1064,21 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, restrictions); } +void arch_remove_memory(int nid, u64 start, u64 size, + struct vmem_altmap *altmap) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + /* + * FIXME: Cleanup page tables (also in arch_add_memory() in case + * adding fails). Until then, this function should only be used + * during memory hotplug (adding memory), not for memory + * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be + * unlocked yet. + */ + zone = page_zone(pfn_to_page(start_pfn)); + __remove_pages(zone, start_pfn, nr_pages, altmap); +} #endif diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 4f241cc7cc3b..4decf1659700 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -29,7 +29,7 @@ static __init int numa_parse_early_param(char *opt) { if (!opt) return -EINVAL; - if (!strncmp(opt, "off", 3)) + if (str_has_prefix(opt, "off")) numa_off = true; return 0; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 47b057bfa803..9ce7bd9d4d9c 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -19,8 +19,7 @@ struct page_change_data { 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) +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) { struct page_change_data *cdata = data; pte_t pte = READ_ONCE(*ptep); @@ -129,7 +128,6 @@ int set_memory_nx(unsigned long addr, int numpages) __pgprot(PTE_PXN), __pgprot(0)); } -EXPORT_SYMBOL_GPL(set_memory_nx); int set_memory_x(unsigned long addr, int numpages) { @@ -137,7 +135,6 @@ int set_memory_x(unsigned long addr, int numpages) __pgprot(0), __pgprot(PTE_PXN)); } -EXPORT_SYMBOL_GPL(set_memory_x); int set_memory_valid(unsigned long addr, int numpages, int enable) { @@ -151,17 +148,48 @@ int set_memory_valid(unsigned long addr, int numpages, int enable) __pgprot(PTE_VALID)); } -#ifdef CONFIG_DEBUG_PAGEALLOC +int set_direct_map_invalid_noflush(struct page *page) +{ + struct page_change_data data = { + .set_mask = __pgprot(0), + .clear_mask = __pgprot(PTE_VALID), + }; + + if (!rodata_full) + return 0; + + return apply_to_page_range(&init_mm, + (unsigned long)page_address(page), + PAGE_SIZE, change_page_range, &data); +} + +int set_direct_map_default_noflush(struct page *page) +{ + struct page_change_data data = { + .set_mask = __pgprot(PTE_VALID | PTE_WRITE), + .clear_mask = __pgprot(PTE_RDONLY), + }; + + if (!rodata_full) + return 0; + + return apply_to_page_range(&init_mm, + (unsigned long)page_address(page), + PAGE_SIZE, change_page_range, &data); +} + void __kernel_map_pages(struct page *page, int numpages, int enable) { + if (!debug_pagealloc_enabled() && !rodata_full) + return; + set_memory_valid((unsigned long)page_address(page), numpages, enable); } -#ifdef CONFIG_HIBERNATION + /* - * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function - * is used to determine if a linear map page has been marked as not-valid by - * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit. - * This is based on kern_addr_valid(), which almost does what we need. + * 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. * * 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 @@ -175,6 +203,9 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); + if (!debug_pagealloc_enabled() && !rodata_full) + return true; + pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; @@ -196,5 +227,3 @@ bool kernel_page_present(struct page *page) ptep = pte_offset_kernel(pmdp, addr); return pte_valid(READ_ONCE(*ptep)); } -#endif /* CONFIG_HIBERNATION */ -#endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 9a0c7d5090d6..4a64089e5771 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -19,10 +19,12 @@ static struct kmem_cache *pgd_cache __ro_after_init; pgd_t *pgd_alloc(struct mm_struct *mm) { + gfp_t gfp = GFP_PGTABLE_USER; + if (PGD_SIZE == PAGE_SIZE) - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_page(gfp); else - return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cache, gfp); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -33,7 +35,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } -void __init pgd_cache_init(void) +void __init pgtable_cache_init(void) { if (PGD_SIZE == PAGE_SIZE) return; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 7dbf2be470f6..a1e0592d1fbc 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -168,7 +168,7 @@ 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 + offset_ttbr1 \tmp2, \tmp1 msr ttbr1_el1, \tmp2 isb tlbi vmalle1 @@ -187,7 +187,7 @@ ENTRY(idmap_cpu_replace_ttbr1) __idmap_cpu_set_reserved_ttbr1 x1, x3 - offset_ttbr1 x0 + offset_ttbr1 x0, x3 msr ttbr1_el1, x0 isb @@ -286,6 +286,15 @@ skip_pgd: msr sctlr_el1, x18 isb + /* + * Invalidate the local I-cache so that any instructions fetched + * speculatively from the PoC are discarded, since they may have + * been dynamically patched at the PoU. + */ + ic iallu + dsb nsh + isb + /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] ret @@ -362,7 +371,7 @@ __idmap_kpti_secondary: cbnz w18, 1b /* All done, act like nothing happened */ - offset_ttbr1 swapper_ttb + offset_ttbr1 swapper_ttb, x18 msr ttbr1_el1, swapper_ttb isb ret @@ -438,10 +447,11 @@ ENTRY(__cpu_setup) TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS tcr_clear_errata_bits x10, x9, x5 -#ifdef CONFIG_ARM64_USER_VA_BITS_52 - ldr_l x9, vabits_user +#ifdef CONFIG_ARM64_VA_BITS_52 + ldr_l x9, vabits_actual sub x9, xzr, x9 add x9, x9, #64 + tcr_set_t1sz x10, x9 #else ldr_l x9, idmap_t0sz #endif |