diff options
Diffstat (limited to 'arch/arm/mm')
-rw-r--r-- | arch/arm/mm/Kconfig | 46 | ||||
-rw-r--r-- | arch/arm/mm/alignment.c | 3 | ||||
-rw-r--r-- | arch/arm/mm/cache-b15-rac.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/cache-feroceon-l2.c | 5 | ||||
-rw-r--r-- | arch/arm/mm/cache-tauros2.c | 5 | ||||
-rw-r--r-- | arch/arm/mm/cache-v7.S | 40 | ||||
-rw-r--r-- | arch/arm/mm/context.c | 3 | ||||
-rw-r--r-- | arch/arm/mm/copypage-xsc3.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/dma-mapping.c | 675 | ||||
-rw-r--r-- | arch/arm/mm/dump.c | 10 | ||||
-rw-r--r-- | arch/arm/mm/fault.c | 22 | ||||
-rw-r--r-- | arch/arm/mm/fault.h | 9 | ||||
-rw-r--r-- | arch/arm/mm/init.c | 49 | ||||
-rw-r--r-- | arch/arm/mm/ioremap.c | 37 | ||||
-rw-r--r-- | arch/arm/mm/kasan_init.c | 15 | ||||
-rw-r--r-- | arch/arm/mm/mm.h | 4 | ||||
-rw-r--r-- | arch/arm/mm/mmu.c | 41 | ||||
-rw-r--r-- | arch/arm/mm/nommu.c | 28 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7-bugs.c | 208 |
19 files changed, 455 insertions, 749 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 58afba346729..fc439c2c16f8 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -386,6 +386,7 @@ config CPU_V6 select CPU_PABRT_V6 select CPU_THUMB_CAPABLE select CPU_TLB_V6 if MMU + select SMP_ON_UP if SMP # ARMv6k config CPU_V6K @@ -630,7 +631,11 @@ config CPU_USE_DOMAINS bool help This option enables or disables the use of domain switching - via the set_fs() function. + using the DACR (domain access control register) to protect memory + domains from each other. In Linux we use three domains: kernel, user + and IO. The domains are used to protect userspace from kernelspace + and to handle IO-space as a special type of memory by assigning + manager or client roles to running code (such as a process). config CPU_V7M_NUM_IRQ int "Number of external interrupts connected to the NVIC" @@ -737,15 +742,29 @@ config SWP_EMULATE If unsure, say Y. +choice + prompt "CPU Endianess" + default CPU_LITTLE_ENDIAN + +config CPU_LITTLE_ENDIAN + bool "Built little-endian kernel" + help + Say Y if you plan on running a kernel in little-endian mode. + This is the default and is used in practically all modern user + space builds. + config CPU_BIG_ENDIAN bool "Build big-endian kernel" - depends on ARCH_SUPPORTS_BIG_ENDIAN depends on !LD_IS_LLD help Say Y if you plan on running a kernel in big-endian mode. - Note that your board must be properly built and your board - port must properly enable any big-endian related features - of your chipset/board/processor. + This works on many machines using ARMv6 or newer processors + but requires big-endian user space. + + The only ARMv5 platform with big-endian support is + Intel IXP4xx. + +endchoice config CPU_ENDIAN_BE8 bool @@ -830,6 +849,7 @@ config CPU_BPREDICT_DISABLE config CPU_SPECTRE bool + select GENERIC_CPU_VULNERABILITIES config HARDEN_BRANCH_PREDICTOR bool "Harden the branch predictor against aliasing attacks" if EXPERT @@ -850,6 +870,16 @@ config HARDEN_BRANCH_PREDICTOR If unsure, say Y. +config HARDEN_BRANCH_HISTORY + bool "Harden Spectre style attacks against branch history" if EXPERT + depends on CPU_SPECTRE + default y + help + Speculation attacks against some high-performance processors can + make use of branch history to influence future speculation. When + taking an exception, a sequence of branches overwrites the branch + history, or branch history is invalidated. + config TLS_REG_EMUL bool select NEED_KUSER_HELPERS @@ -1110,12 +1140,6 @@ config ARM_DMA_MEM_BUFFERABLE config ARM_HEAVY_MB bool -config ARCH_SUPPORTS_BIG_ENDIAN - bool - help - This option specifies the architecture can support big endian - operation. - config DEBUG_ALIGN_RODATA bool "Make rodata strictly non-executable" depends on STRICT_KERNEL_RWX diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f499559d193..f8dd0b3cc8e0 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -935,6 +935,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (type == TYPE_LDST) do_alignment_finish_ldst(addr, instr, regs, offset); + if (thumb_mode(regs)) + regs->ARM_cpsr = it_advance(regs->ARM_cpsr); + return 0; bad_or_fault: diff --git a/arch/arm/mm/cache-b15-rac.c b/arch/arm/mm/cache-b15-rac.c index bdc07030997b..9c1172f26885 100644 --- a/arch/arm/mm/cache-b15-rac.c +++ b/arch/arm/mm/cache-b15-rac.c @@ -74,7 +74,7 @@ static inline void __b15_rac_flush(void) __raw_writel(FLUSH_RAC, b15_rac_base + rac_flush_offset); do { /* This dmb() is required to force the Bus Interface Unit - * to clean oustanding writes, and forces an idle cycle + * to clean outstanding writes, and forces an idle cycle * to be inserted. */ dmb(); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index 5c1b7a7b9af6..25dbd84a1aaf 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * arch/arm/mm/cache-feroceon-l2.c - Feroceon L2 cache controller support * * Copyright (C) 2008 Marvell Semiconductor * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * * References: * - Unified Layer 2 Cache for Feroceon CPU Cores, * Document ID MV-S104858-00, Rev. A, October 23 2007. diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c index 88255bea65e4..b1e1aba602f7 100644 --- a/arch/arm/mm/cache-tauros2.c +++ b/arch/arm/mm/cache-tauros2.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * arch/arm/mm/cache-tauros2.c - Tauros2 L2 cache controller support * * Copyright (C) 2008 Marvell Semiconductor * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * * References: * - PJ1 CPU Core Datasheet, * Document ID MV-S104837-01, Rev 0.7, January 24 2008. diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 830bbfb26ca5..7c9499b728c4 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -90,7 +90,7 @@ ENDPROC(v7_flush_icache_all) * * Flush the D-cache up to the Level of Unification Inner Shareable * - * Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode) + * Corrupted registers: r0-r6, r9-r10 */ ENTRY(v7_flush_dcache_louis) @@ -117,7 +117,7 @@ ENDPROC(v7_flush_dcache_louis) * * Flush the whole D-cache. * - * Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode) + * Corrupted registers: r0-r6, r9-r10 * * - mm - mm_struct describing address space */ @@ -149,22 +149,22 @@ flush_levels: movw r4, #0x3ff ands r4, r4, r1, lsr #3 @ find maximum number on the way size clz r5, r4 @ find bit position of way size increment - movw r7, #0x7fff - ands r7, r7, r1, lsr #13 @ extract max number of the index size + movw r6, #0x7fff + and r1, r6, r1, lsr #13 @ extract max number of the index size + mov r6, #1 + movne r4, r4, lsl r5 @ # of ways shifted into bits [31:...] + movne r6, r6, lsl r5 @ 1 shifted left by same amount loop1: - mov r9, r7 @ create working copy of max index + mov r9, r1 @ create working copy of max index loop2: - ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r4, r5 ) - THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r9, r2 ) - THUMB( orr r11, r11, r6 ) @ factor index number into r11 - mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way + mov r5, r9, lsl r2 @ factor set number into r5 + orr r5, r5, r4 @ factor way number into r5 + orr r5, r5, r10 @ factor cache level into r5 + mcr p15, 0, r5, c7, c14, 2 @ clean & invalidate by set/way subs r9, r9, #1 @ decrement the index bge loop2 - subs r4, r4, #1 @ decrement the way - bge loop1 + subs r4, r4, r6 @ decrement the way + bcs loop1 skip: add r10, r10, #2 @ increment cache number cmp r3, r10 @@ -192,14 +192,12 @@ ENDPROC(v7_flush_dcache_all) * */ ENTRY(v7_flush_kern_cache_all) - ARM( stmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( stmfd sp!, {r4-r7, r9-r11, lr} ) + stmfd sp!, {r4-r6, r9-r10, lr} bl v7_flush_dcache_all mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate - ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} ) + ldmfd sp!, {r4-r6, r9-r10, lr} ret lr ENDPROC(v7_flush_kern_cache_all) @@ -210,14 +208,12 @@ ENDPROC(v7_flush_kern_cache_all) * Invalidate the I-cache to the point of unification. */ ENTRY(v7_flush_kern_cache_louis) - ARM( stmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( stmfd sp!, {r4-r7, r9-r11, lr} ) + stmfd sp!, {r4-r6, r9-r10, lr} bl v7_flush_dcache_louis mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate - ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} ) + ldmfd sp!, {r4-r6, r9-r10, lr} ret lr ENDPROC(v7_flush_kern_cache_louis) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 48091870db89..4204ffa2d104 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -240,8 +240,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) unsigned int cpu = smp_processor_id(); u64 asid; - if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq)) - __check_vmalloc_seq(mm); + check_vmalloc_seq(mm); /* * We cannot update the pgd and the ASID atomicly with classic diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c index 6f0909dda2f9..c86e79677ff9 100644 --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -29,6 +29,7 @@ static void xsc3_mc_copy_user_page(void *kto, const void *kfrom) int tmp; asm volatile ("\ +.arch xscale \n\ pld [%1, #0] \n\ pld [%1, #32] \n\ 1: pld [%1, #64] \n\ @@ -80,6 +81,7 @@ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) { void *ptr, *kaddr = kmap_atomic(page); asm volatile ("\ +.arch xscale \n\ mov r1, %2 \n\ mov r2, #0 \n\ mov r3, #0 \n\ diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4b61541853ea..d7909091cf97 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -33,7 +33,7 @@ #include <asm/dma-iommu.h> #include <asm/mach/map.h> #include <asm/system_info.h> -#include <xen/swiotlb-xen.h> +#include <asm/xen/xen-ops.h> #include "dma.h" #include "mm.h" @@ -103,139 +103,6 @@ static struct arm_dma_buffer *arm_dma_buffer_find(void *virt) * before transfers and delay cache invalidation until transfer completion. * */ -static void __dma_page_cpu_to_dev(struct page *, unsigned long, - size_t, enum dma_data_direction); -static void __dma_page_dev_to_cpu(struct page *, unsigned long, - size_t, enum dma_data_direction); - -/** - * arm_dma_map_page - map a portion of a page for streaming DMA - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @page: page that buffer resides in - * @offset: offset into page for start of buffer - * @size: size of buffer to map - * @dir: DMA transfer direction - * - * Ensure that any data held in the cache is appropriately discarded - * or written back. - * - * The device owns this memory once this call has completed. The CPU - * can regain ownership by calling dma_unmap_page(). - */ -static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_cpu_to_dev(page, offset, size, dir); - return pfn_to_dma(dev, page_to_pfn(page)) + offset; -} - -static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return pfn_to_dma(dev, page_to_pfn(page)) + offset; -} - -/** - * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @handle: DMA address of buffer - * @size: size of buffer (same as passed to dma_map_page) - * @dir: DMA transfer direction (same as passed to dma_map_page) - * - * Unmap a page streaming mode DMA translation. The handle and size - * must match what was provided in the previous dma_map_page() call. - * All other usages are undefined. - * - * After this call, reads by the CPU to the buffer are guaranteed to see - * whatever the device wrote there. - */ -static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), - handle & ~PAGE_MASK, size, dir); -} - -static void arm_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_dev_to_cpu(page, offset, size, dir); -} - -static void arm_dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_cpu_to_dev(page, offset, size, dir); -} - -/* - * Return whether the given device DMA address mask can be supported - * properly. For example, if your device can only drive the low 24-bits - * during bus mastering, then you would pass 0x00ffffff as the mask - * to this function. - */ -static int arm_dma_supported(struct device *dev, u64 mask) -{ - unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit); - - /* - * Translate the device's DMA mask to a PFN limit. This - * PFN number includes the page which we can DMA to. - */ - return dma_to_pfn(dev, mask) >= max_dma_pfn; -} - -const struct dma_map_ops arm_dma_ops = { - .alloc = arm_dma_alloc, - .free = arm_dma_free, - .alloc_pages = dma_direct_alloc_pages, - .free_pages = dma_direct_free_pages, - .mmap = arm_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_dma_map_page, - .unmap_page = arm_dma_unmap_page, - .map_sg = arm_dma_map_sg, - .unmap_sg = arm_dma_unmap_sg, - .map_resource = dma_direct_map_resource, - .sync_single_for_cpu = arm_dma_sync_single_for_cpu, - .sync_single_for_device = arm_dma_sync_single_for_device, - .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, - .sync_sg_for_device = arm_dma_sync_sg_for_device, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_dma_ops); - -static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs); -static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs); -static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); - -const struct dma_map_ops arm_coherent_dma_ops = { - .alloc = arm_coherent_dma_alloc, - .free = arm_coherent_dma_free, - .alloc_pages = dma_direct_alloc_pages, - .free_pages = dma_direct_free_pages, - .mmap = arm_coherent_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_coherent_dma_map_page, - .map_sg = arm_dma_map_sg, - .map_resource = dma_direct_map_resource, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_coherent_dma_ops); static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag) { @@ -381,6 +248,7 @@ out: */ postcore_initcall(atomic_pool_init); +#ifdef CONFIG_CMA_AREAS struct dma_contig_early_reserve { phys_addr_t base; unsigned long size; @@ -435,10 +303,11 @@ void __init dma_contiguous_remap(void) iotable_init(&map, 1); } } +#endif static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { - struct page *page = virt_to_page(addr); + struct page *page = virt_to_page((void *)addr); pgprot_t prot = *(pgprot_t *)data; set_pte_ext(pte, mk_pte(page, prot), 0); @@ -707,7 +576,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, *handle = DMA_MAPPING_ERROR; allowblock = gfpflags_allow_blocking(gfp); - cma = allowblock ? dev_get_cma_area(dev) : false; + cma = allowblock ? dev_get_cma_area(dev) : NULL; if (cma) buf->allocator = &cma_allocator; @@ -723,7 +592,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (page) { unsigned long flags; - *handle = pfn_to_dma(dev, page_to_pfn(page)); + *handle = phys_to_dma(dev, page_to_phys(page)); buf->virt = args.want_vaddr ? addr : page; spin_lock_irqsave(&arm_dma_bufs_lock, flags); @@ -737,74 +606,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, } /* - * Allocate DMA-coherent memory space and return both the kernel remapped - * virtual and bus address for that space. - */ -void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, unsigned long attrs) -{ - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); - - return __dma_alloc(dev, size, handle, gfp, prot, false, - attrs, __builtin_return_address(0)); -} - -static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true, - attrs, __builtin_return_address(0)); -} - -static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - int ret = -ENXIO; - unsigned long nr_vma_pages = vma_pages(vma); - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned long pfn = dma_to_pfn(dev, dma_addr); - unsigned long off = vma->vm_pgoff; - - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) - return ret; - - 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; -} - -/* - * Create userspace mapping for the DMA-coherent memory. - */ -static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -/* * Free a buffer as defined by the above mapping. */ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs, bool is_coherent) { - struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); + struct page *page = phys_to_page(dma_to_phys(dev, handle)); struct arm_dma_buffer *buf; struct arm_dma_free_args args = { .dev = dev, @@ -822,40 +630,6 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, kfree(buf); } -void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - __arm_dma_free(dev, size, cpu_addr, handle, attrs, false); -} - -static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); -} - -int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t handle, size_t size, - unsigned long attrs) -{ - unsigned long pfn = dma_to_pfn(dev, handle); - struct page *page; - int ret; - - /* If the PFN is not valid, we do not have a struct page */ - if (!pfn_valid(pfn)) - return -ENXIO; - - page = pfn_to_page(pfn); - - ret = sg_alloc_table(sgt, 1, GFP_KERNEL); - if (unlikely(ret)) - return ret; - - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); - return 0; -} - static void dma_cache_maint_page(struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, void (*op)(const void *, size_t, int)) @@ -905,8 +679,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, /* * Make an area consistent for devices. - * Note: Drivers should NOT use this function directly, as it will break - * platforms with CONFIG_DMABOUNCE. + * Note: Drivers should NOT use this function directly. * Use the driver DMA support - see dma-mapping.h (dma_sync_*) */ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, @@ -959,122 +732,6 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, } } -/** - * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction - * - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the dma_map_single interface. - * Here the scatter gather list elements are each tagged with the - * appropriate dma address and length. They are obtained via - * sg_dma_{address,length}. - * - * Device ownership issues as mentioned for dma_map_single are the same - * here. - */ -int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i, j, ret; - - for_each_sg(sg, s, nents, i) { -#ifdef CONFIG_NEED_SG_DMA_LENGTH - s->dma_length = s->length; -#endif - s->dma_address = ops->map_page(dev, sg_page(s), s->offset, - s->length, dir, attrs); - if (dma_mapping_error(dev, s->dma_address)) { - ret = -EIO; - goto bad_mapping; - } - } - return nents; - - bad_mapping: - for_each_sg(sg, s, i, j) - ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); - return ret; -} - -/** - * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - - int i; - - for_each_sg(sg, s, nents, i) - ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); -} - -/** - * arm_dma_sync_sg_for_cpu - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map (returned from dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - */ -void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) - ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length, - dir); -} - -/** - * arm_dma_sync_sg_for_device - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map (returned from dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - */ -void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) - ops->sync_single_for_device(dev, sg_dma_address(s), s->length, - dir); -} - -static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) -{ - /* - * When CONFIG_ARM_LPAE is set, physical address can extend above - * 32-bits, which then can't be addressed by devices that only support - * 32-bit DMA. - * Use the generic dma-direct / swiotlb ops code in that case, as that - * handles bounce buffering for us. - */ - if (IS_ENABLED(CONFIG_ARM_LPAE)) - return NULL; - return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; -} - #ifdef CONFIG_ARM_DMA_USE_IOMMU static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs) @@ -1421,13 +1078,13 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr, __free_from_pool(cpu_addr, size); } -static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs, - int coherent_flag) +static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); struct page **pages; void *addr = NULL; + int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL; *handle = DMA_MAPPING_ERROR; size = PAGE_ALIGN(size); @@ -1470,19 +1127,7 @@ err_buffer: return NULL; } -static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL); -} - -static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT); -} - -static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, +static int arm_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) { @@ -1496,35 +1141,24 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma if (vma->vm_pgoff >= nr_pages) return -ENXIO; + if (!dev->dma_coherent) + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); + err = vm_map_pages(vma, pages, nr_pages); if (err) pr_err("Remapping memory failed: %d\n", err); return err; } -static int arm_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) -{ - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - - return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -static int arm_coherent_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) -{ - return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs); -} /* * free a page as defined by the above mapping. * Must not be called with IRQs disabled. */ -static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs, int coherent_flag) +static void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, unsigned long attrs) { + int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL; struct page **pages; size = PAGE_ALIGN(size); @@ -1546,19 +1180,6 @@ static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_ad __iommu_free_buffer(dev, pages, size, attrs); } -static void arm_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, - unsigned long attrs) -{ - __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL); -} - -static void arm_coherent_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, unsigned long attrs) -{ - __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT); -} - static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) @@ -1578,8 +1199,7 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, */ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, size_t size, dma_addr_t *handle, - enum dma_data_direction dir, unsigned long attrs, - bool is_coherent) + enum dma_data_direction dir, unsigned long attrs) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova, iova_base; @@ -1599,7 +1219,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); - if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); prot = __dma_info_to_prot(dir, attrs); @@ -1619,9 +1239,20 @@ fail: return ret; } -static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs, - bool is_coherent) +/** + * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map + * @dir: DMA transfer direction + * + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * The scatter gather list elements are merged together (if possible) and + * tagged with the appropriate dma address and length. They are obtained via + * sg_dma_{address,length}. + */ +static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s = sg, *dma = sg, *start = sg; int i, count = 0, ret; @@ -1636,8 +1267,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) { ret = __map_sg_chunk(dev, start, size, - &dma->dma_address, dir, attrs, - is_coherent); + &dma->dma_address, dir, attrs); if (ret < 0) goto bad_mapping; @@ -1651,8 +1281,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, } size += s->length; } - ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs, - is_coherent); + ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs); if (ret < 0) goto bad_mapping; @@ -1670,44 +1299,19 @@ bad_mapping: } /** - * arm_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction - * - * Map a set of i/o coherent buffers described by scatterlist in streaming - * mode for DMA. The scatter gather list elements are merged together (if - * possible) and tagged with the appropriate dma address and length. They are - * obtained via sg_dma_{address,length}. - */ -static int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - return __iommu_map_sg(dev, sg, nents, dir, attrs, true); -} - -/** - * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg * @dev: valid struct device pointer * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) * - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * The scatter gather list elements are merged together (if possible) and - * tagged with the appropriate dma address and length. They are obtained via - * sg_dma_{address,length}. + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). */ -static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - return __iommu_map_sg(dev, sg, nents, dir, attrs, false); -} - -static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs, bool is_coherent) +static void arm_iommu_unmap_sg(struct device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction dir, + unsigned long attrs) { struct scatterlist *s; int i; @@ -1716,48 +1320,13 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, if (sg_dma_len(s)) __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); - if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); } } /** - * arm_coherent_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -static void arm_coherent_iommu_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - __iommu_unmap_sg(dev, sg, nents, dir, attrs, true); -} - -/** - * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -static void arm_iommu_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir, - unsigned long attrs) -{ - __iommu_unmap_sg(dev, sg, nents, dir, attrs, false); -} - -/** * arm_iommu_sync_sg_for_cpu * @dev: valid struct device pointer * @sg: list of buffers @@ -1771,6 +1340,9 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *s; int i; + if (dev->dma_coherent) + return; + for_each_sg(sg, s, nents, i) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); @@ -1790,22 +1362,24 @@ static void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *s; int i; + if (dev->dma_coherent) + return; + for_each_sg(sg, s, nents, i) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); } - /** - * arm_coherent_iommu_map_page + * arm_iommu_map_page * @dev: valid struct device pointer * @page: page that buffer resides in * @offset: offset into page for start of buffer * @size: size of buffer to map * @dir: DMA transfer direction * - * Coherent IOMMU aware version of arm_dma_map_page() + * IOMMU aware version of arm_dma_map_page() */ -static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page, +static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -1813,6 +1387,9 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p dma_addr_t dma_addr; int ret, prot, len = PAGE_ALIGN(size + offset); + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_page_cpu_to_dev(page, offset, size, dir); + dma_addr = __alloc_iova(mapping, len); if (dma_addr == DMA_MAPPING_ERROR) return dma_addr; @@ -1830,50 +1407,6 @@ fail: } /** - * arm_iommu_map_page - * @dev: valid struct device pointer - * @page: page that buffer resides in - * @offset: offset into page for start of buffer - * @size: size of buffer to map - * @dir: DMA transfer direction - * - * IOMMU aware version of arm_dma_map_page() - */ -static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_cpu_to_dev(page, offset, size, dir); - - return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs); -} - -/** - * arm_coherent_iommu_unmap_page - * @dev: valid struct device pointer - * @handle: DMA address of buffer - * @size: size of buffer (same as passed to dma_map_page) - * @dir: DMA transfer direction (same as passed to dma_map_page) - * - * Coherent IOMMU aware version of arm_dma_unmap_page() - */ -static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); - dma_addr_t iova = handle & PAGE_MASK; - int offset = handle & ~PAGE_MASK; - int len = PAGE_ALIGN(size + offset); - - if (!iova) - return; - - iommu_unmap(mapping->domain, iova, len); - __free_iova(mapping, iova, len); -} - -/** * arm_iommu_unmap_page * @dev: valid struct device pointer * @handle: DMA address of buffer @@ -1887,15 +1420,17 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; int offset = handle & ~PAGE_MASK; int len = PAGE_ALIGN(size + offset); if (!iova) return; - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_dev_to_cpu(page, offset, size, dir); + } iommu_unmap(mapping->domain, iova, len); __free_iova(mapping, iova, len); @@ -1963,12 +1498,13 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; unsigned int offset = handle & ~PAGE_MASK; - if (!iova) + if (dev->dma_coherent || !iova) return; + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_dev_to_cpu(page, offset, size, dir); } @@ -1977,12 +1513,13 @@ static void arm_iommu_sync_single_for_device(struct device *dev, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; unsigned int offset = handle & ~PAGE_MASK; - if (!iova) + if (dev->dma_coherent || !iova) return; + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_cpu_to_dev(page, offset, size, dir); } @@ -2004,26 +1541,6 @@ static const struct dma_map_ops iommu_ops = { .map_resource = arm_iommu_map_resource, .unmap_resource = arm_iommu_unmap_resource, - - .dma_supported = arm_dma_supported, -}; - -static const struct dma_map_ops iommu_coherent_ops = { - .alloc = arm_coherent_iommu_alloc_attrs, - .free = arm_coherent_iommu_free_attrs, - .mmap = arm_coherent_iommu_mmap_attrs, - .get_sgtable = arm_iommu_get_sgtable, - - .map_page = arm_coherent_iommu_map_page, - .unmap_page = arm_coherent_iommu_unmap_page, - - .map_sg = arm_coherent_iommu_map_sg, - .unmap_sg = arm_coherent_iommu_unmap_sg, - - .map_resource = arm_iommu_map_resource, - .unmap_resource = arm_iommu_unmap_resource, - - .dma_supported = arm_dma_supported, }; /** @@ -2199,40 +1716,32 @@ void arm_iommu_detach_device(struct device *dev) iommu_detach_device(mapping->domain, dev); kref_put(&mapping->kref, release_iommu_mapping); to_dma_iommu_mapping(dev) = NULL; - set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent)); + set_dma_ops(dev, NULL); pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } EXPORT_SYMBOL_GPL(arm_iommu_detach_device); -static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent) -{ - return coherent ? &iommu_coherent_ops : &iommu_ops; -} - -static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu) +static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) { struct dma_iommu_mapping *mapping; - if (!iommu) - return false; - mapping = arm_iommu_create_mapping(dev->bus, dma_base, size); if (IS_ERR(mapping)) { pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n", size, dev_name(dev)); - return false; + return; } if (__arm_iommu_attach_device(dev, mapping)) { pr_warn("Failed to attached device %s to IOMMU_mapping\n", dev_name(dev)); arm_iommu_release_mapping(mapping); - return false; + return; } - return true; + set_dma_ops(dev, &iommu_ops); } static void arm_teardown_iommu_dma_ops(struct device *dev) @@ -2248,27 +1757,26 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) #else -static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu) +static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) { - return false; } static void arm_teardown_iommu_dma_ops(struct device *dev) { } -#define arm_get_iommu_dma_map_ops arm_get_dma_map_ops - #endif /* CONFIG_ARM_DMA_USE_IOMMU */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - const struct dma_map_ops *dma_ops; - - dev->archdata.dma_coherent = coherent; -#ifdef CONFIG_SWIOTLB - dev->dma_coherent = coherent; -#endif + /* + * Due to legacy code that sets the ->dma_coherent flag from a bus + * notifier we can't just assign coherent to the ->dma_coherent flag + * here, but instead have to make sure we only set but never clear it + * for now. + */ + if (coherent) + dev->dma_coherent = true; /* * Don't override the dma_ops if they have already been set. Ideally @@ -2278,17 +1786,10 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, if (dev->dma_ops) return; - if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu)) - dma_ops = arm_get_iommu_dma_map_ops(coherent); - else - dma_ops = arm_get_dma_map_ops(coherent); + if (iommu) + arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent); - set_dma_ops(dev, dma_ops); - -#ifdef CONFIG_XEN - if (xen_initial_domain()) - dev->dma_ops = &xen_swiotlb_dma_ops; -#endif + xen_setup_dma_ops(dev); dev->archdata.dma_ops_setup = true; } @@ -2302,7 +1803,6 @@ void arch_teardown_dma_ops(struct device *dev) set_dma_ops(dev, NULL); } -#ifdef CONFIG_SWIOTLB void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { @@ -2330,4 +1830,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, { __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false); } -#endif /* CONFIG_SWIOTLB */ diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c index fb688003d156..059eb4cdc9c2 100644 --- a/arch/arm/mm/dump.c +++ b/arch/arm/mm/dump.c @@ -26,7 +26,7 @@ static struct addr_marker address_markers[] = { { MODULES_VADDR, "Modules" }, { PAGE_OFFSET, "Kernel Mapping" }, { 0, "vmalloc() Area" }, - { VMALLOC_END, "vmalloc() End" }, + { FDT_FIXED_BASE, "FDT Area" }, { FIXADDR_START, "Fixmap Area" }, { VECTORS_BASE, "Vectors" }, { VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" }, @@ -200,6 +200,7 @@ static const struct prot_bits section_bits[] = { }; struct pg_level { + const char *name; const struct prot_bits *bits; size_t num; u64 mask; @@ -213,9 +214,11 @@ static struct pg_level pg_level[] = { }, { /* p4d */ }, { /* pud */ }, { /* pmd */ + .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", .bits = section_bits, .num = ARRAY_SIZE(section_bits), }, { /* pte */ + .name = "PTE", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, @@ -282,7 +285,8 @@ static void note_page(struct pg_state *st, unsigned long addr, delta >>= 10; unit++; } - pt_dump_seq_printf(st->seq, "%9lu%c", delta, *unit); + pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); if (st->current_domain) pt_dump_seq_printf(st->seq, " %s", st->current_domain); @@ -346,7 +350,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) addr = start + i * PMD_SIZE; domain = get_domain_name(pmd); if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd)) - note_page(st, addr, 3, pmd_val(*pmd), domain); + note_page(st, addr, 4, pmd_val(*pmd), domain); else walk_pte(st, pmd, addr, domain); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..de988cba9a4b 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -105,6 +105,19 @@ static inline bool is_write_fault(unsigned int fsr) return (fsr & FSR_WRITE) && !(fsr & FSR_CM); } +static inline bool is_translation_fault(unsigned int fsr) +{ + int fs = fsr_fs(fsr); +#ifdef CONFIG_ARM_LPAE + if ((fs & FS_MMU_NOLL_MASK) == FS_TRANS_NOLL) + return true; +#else + if (fs == FS_L1_TRANS || fs == FS_L2_TRANS) + return true; +#endif + return false; +} + static void die_kernel_fault(const char *msg, struct mm_struct *mm, unsigned long addr, unsigned int fsr, struct pt_regs *regs) @@ -140,7 +153,8 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) + if (is_translation_fault(fsr) && + kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) return; msg = "paging request"; @@ -208,7 +222,7 @@ static inline bool is_permission_fault(unsigned int fsr) { int fs = fsr_fs(fsr); #ifdef CONFIG_ARM_LPAE - if ((fs & FS_PERM_NOLL_MASK) == FS_PERM_NOLL) + if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL) return true; #else if (fs == FS_L1_PERM || fs == FS_L2_PERM) @@ -322,6 +336,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 83b5ab32d7a4..54927ba1fa6e 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -14,8 +14,9 @@ #ifdef CONFIG_ARM_LPAE #define FSR_FS_AEA 17 +#define FS_TRANS_NOLL 0x4 #define FS_PERM_NOLL 0xC -#define FS_PERM_NOLL_MASK 0x3C +#define FS_MMU_NOLL_MASK 0x3C static inline int fsr_fs(unsigned int fsr) { @@ -23,8 +24,10 @@ static inline int fsr_fs(unsigned int fsr) } #else #define FSR_FS_AEA 22 -#define FS_L1_PERM 0xD -#define FS_L2_PERM 0xF +#define FS_L1_TRANS 0x5 +#define FS_L2_TRANS 0x7 +#define FS_L1_PERM 0xD +#define FS_L2_PERM 0xF static inline int fsr_fs(unsigned int fsr) { diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 6d0cb0f7bc54..ce64bdb55a16 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -164,47 +164,6 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) return phys; } -static void __init arm_initrd_init(void) -{ -#ifdef CONFIG_BLK_DEV_INITRD - phys_addr_t start; - unsigned long size; - - initrd_start = initrd_end = 0; - - if (!phys_initrd_size) - return; - - /* - * Round the memory region to page boundaries as per free_initrd_mem() - * This allows us to detect whether the pages overlapping the initrd - * are in use, but more importantly, reserves the entire set of pages - * as we don't want these pages allocated for other purposes. - */ - start = round_down(phys_initrd_start, PAGE_SIZE); - size = phys_initrd_size + (phys_initrd_start - start); - size = round_up(size, PAGE_SIZE); - - if (!memblock_is_region_memory(start, size)) { - pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n", - (u64)start, size); - return; - } - - if (memblock_is_region_reserved(start, size)) { - pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n", - (u64)start, size); - return; - } - - memblock_reserve(start, size); - - /* Now convert initrd to virtual addresses */ - initrd_start = __phys_to_virt(phys_initrd_start); - initrd_end = initrd_start + phys_initrd_size; -#endif -} - #ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND void check_cpu_icache_size(int cpuid) { @@ -226,7 +185,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc) /* Register the kernel text, kernel data and initrd with memblock. */ memblock_reserve(__pa(KERNEL_START), KERNEL_END - KERNEL_START); - arm_initrd_init(); + reserve_initrd_mem(); arm_mm_memblock_reserve(); @@ -312,11 +271,7 @@ static void __init free_highpages(void) void __init mem_init(void) { #ifdef CONFIG_ARM_LPAE - if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > arm_dma_pfn_limit) - swiotlb_init(1); - else - swiotlb_force = SWIOTLB_NO_FORCE; + swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE); #endif set_max_mapnr(pfn_to_page(max_pfn) - mem_map); diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 197f8eb3a775..2129070065c3 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -117,16 +117,21 @@ EXPORT_SYMBOL(ioremap_page); void __check_vmalloc_seq(struct mm_struct *mm) { - unsigned int seq; + int seq; do { - seq = init_mm.context.vmalloc_seq; + seq = atomic_read(&init_mm.context.vmalloc_seq); memcpy(pgd_offset(mm, VMALLOC_START), pgd_offset_k(VMALLOC_START), sizeof(pgd_t) * (pgd_index(VMALLOC_END) - pgd_index(VMALLOC_START))); - mm->context.vmalloc_seq = seq; - } while (seq != init_mm.context.vmalloc_seq); + /* + * Use a store-release so that other CPUs that observe the + * counter's new value are guaranteed to see the results of the + * memcpy as well. + */ + atomic_set_release(&mm->context.vmalloc_seq, seq); + } while (seq != atomic_read(&init_mm.context.vmalloc_seq)); } #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) @@ -157,7 +162,7 @@ static void unmap_area_sections(unsigned long virt, unsigned long size) * Note: this is still racy on SMP machines. */ pmd_clear(pmdp); - init_mm.context.vmalloc_seq++; + atomic_inc_return_release(&init_mm.context.vmalloc_seq); /* * Free the page table, if there was one. @@ -174,8 +179,7 @@ static void unmap_area_sections(unsigned long virt, unsigned long size) * Ensure that the active_mm is up to date - we want to * catch any use-after-iounmap cases. */ - if (current->active_mm->context.vmalloc_seq != init_mm.context.vmalloc_seq) - __check_vmalloc_seq(current->active_mm); + check_vmalloc_seq(current->active_mm); flush_tlb_kernel_range(virt, end); } @@ -414,7 +418,7 @@ void *arch_memremap_wb(phys_addr_t phys_addr, size_t size) __builtin_return_address(0)); } -void __iounmap(volatile void __iomem *io_addr) +void iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); struct static_vm *svm; @@ -442,16 +446,9 @@ void __iounmap(volatile void __iomem *io_addr) vunmap(addr); } - -void (*arch_iounmap)(volatile void __iomem *) = __iounmap; - -void iounmap(volatile void __iomem *cookie) -{ - arch_iounmap(cookie); -} EXPORT_SYMBOL(iounmap); -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) || IS_ENABLED(CONFIG_PCMCIA) static int pci_ioremap_mem_type = MT_DEVICE; void pci_ioremap_set_mem_type(int mem_type) @@ -489,3 +486,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return memblock_is_map_memory(pfn); +} diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c index 5ad0d6c56d56..46d9f4a622cb 100644 --- a/arch/arm/mm/kasan_init.c +++ b/arch/arm/mm/kasan_init.c @@ -236,7 +236,11 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START), + if (!IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START), + kasan_mem_to_shadow((void *)VMALLOC_END)); + + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_END), kasan_mem_to_shadow((void *)-1UL) + 1); for_each_mem_range(i, &pa_start, &pa_end) { @@ -264,12 +268,17 @@ void __init kasan_init(void) /* * 1. The module global variables are in MODULES_VADDR ~ MODULES_END, - * so we need to map this area. + * so we need to map this area if CONFIG_KASAN_VMALLOC=n. With + * VMALLOC support KASAN will manage this region dynamically, + * refer to kasan_populate_vmalloc() and ARM's implementation of + * module_alloc(). * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR * ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't * use kasan_populate_zero_shadow. */ - create_mapping((void *)MODULES_VADDR, (void *)(PKMAP_BASE + PMD_SIZE)); + if (!IS_ENABLED(CONFIG_KASAN_VMALLOC) && IS_ENABLED(CONFIG_MODULES)) + create_mapping((void *)MODULES_VADDR, (void *)(MODULES_END)); + create_mapping((void *)PKMAP_BASE, (void *)(PKMAP_BASE + PMD_SIZE)); /* * KAsan may reuse the contents of kasan_early_shadow_pte directly, so diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 9ff683612f2a..d7ffccb7fea7 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -88,6 +88,10 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); +#ifdef CONFIG_CMA_AREAS void dma_contiguous_remap(void); +#else +static inline void dma_contiguous_remap(void) { } +#endif unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 274e4f73fd33..463fc2a8448f 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -212,12 +212,14 @@ early_param("ecc", early_ecc); static int __init early_cachepolicy(char *p) { pr_warn("cachepolicy kernel parameter not supported without cp15\n"); + return 0; } early_param("cachepolicy", early_cachepolicy); static int __init noalign_setup(char *__unused) { pr_warn("noalign kernel parameter not supported without cp15\n"); + return 1; } __setup("noalign", noalign_setup); @@ -294,6 +296,17 @@ static struct mem_type mem_types[] __ro_after_init = { .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_RO] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN | L_PTE_RDONLY, + .prot_l1 = PMD_TYPE_TABLE, +#ifdef CONFIG_ARM_LPAE + .prot_sect = PMD_TYPE_SECT | L_PMD_SECT_RDONLY | PMD_SECT_AP2, +#else + .prot_sect = PMD_TYPE_SECT, +#endif + .domain = DOMAIN_KERNEL, + }, [MT_ROM] = { .prot_sect = PMD_TYPE_SECT, .domain = DOMAIN_KERNEL, @@ -403,6 +416,26 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); } +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = __PAGE_NONE, + [VM_READ] = __PAGE_READONLY, + [VM_WRITE] = __PAGE_COPY, + [VM_WRITE | VM_READ] = __PAGE_COPY, + [VM_EXEC] = __PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = __PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = __PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = __PAGE_COPY_EXEC, + [VM_SHARED] = __PAGE_NONE, + [VM_SHARED | VM_READ] = __PAGE_READONLY, + [VM_SHARED | VM_WRITE] = __PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = __PAGE_SHARED, + [VM_SHARED | VM_EXEC] = __PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = __PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = __PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __PAGE_SHARED_EXEC +}; +DECLARE_VM_GET_PAGE_PROT + /* * Adjust the PMD section entries according to the CPU in use. */ @@ -487,6 +520,7 @@ static void __init build_mem_type_table(void) /* Also setup NX memory mapping */ mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_XN; } if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* @@ -566,6 +600,7 @@ static void __init build_mem_type_table(void) mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif /* @@ -585,6 +620,8 @@ static void __init build_mem_type_table(void) mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RO].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RO].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED; @@ -645,6 +682,8 @@ static void __init build_mem_type_table(void) mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd; mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RO].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RO].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; @@ -1358,7 +1397,7 @@ static void __init devicemaps_init(const struct machine_desc *mdesc) map.pfn = __phys_to_pfn(__atags_pointer & SECTION_MASK); map.virtual = FDT_FIXED_BASE; map.length = FDT_FIXED_SIZE; - map.type = MT_ROM; + map.type = MT_MEMORY_RO; create_mapping(&map); } diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 2658f52903da..c1494a4dee25 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -26,6 +26,13 @@ unsigned long vectors_base; +/* + * empty_zero_page is a special page that is used for + * zero-initialized data and COW. + */ +struct page *empty_zero_page; +EXPORT_SYMBOL(empty_zero_page); + #ifdef CONFIG_ARM_MPU struct mpu_rgn_info mpu_rgn_info; #endif @@ -148,9 +155,21 @@ void __init adjust_lowmem_bounds(void) */ void __init paging_init(const struct machine_desc *mdesc) { + void *zero_page; + early_trap_init((void *)vectors_base); mpu_setup(); + + /* allocate the zero page. */ + zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!zero_page) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); + bootmem_init(); + + empty_zero_page = virt_to_page(zero_page); + flush_dcache_page(empty_zero_page); } /* @@ -230,14 +249,7 @@ void *arch_memremap_wb(phys_addr_t phys_addr, size_t size) return (void *)phys_addr; } -void __iounmap(volatile void __iomem *addr) -{ -} -EXPORT_SYMBOL(__iounmap); - -void (*arch_iounmap)(volatile void __iomem *); - -void iounmap(volatile void __iomem *addr) +void iounmap(volatile void __iomem *io_addr) { } EXPORT_SYMBOL(iounmap); diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 114c05ab4dd9..8bc7a2d6d6c7 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -6,8 +6,35 @@ #include <asm/cp15.h> #include <asm/cputype.h> #include <asm/proc-fns.h> +#include <asm/spectre.h> #include <asm/system_misc.h> +#ifdef CONFIG_ARM_PSCI +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + + switch ((int)res.a0) { + case SMCCC_RET_SUCCESS: + return SPECTRE_MITIGATED; + + case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: + return SPECTRE_UNAFFECTED; + + default: + return SPECTRE_VULNERABLE; + } +} +#else +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + return SPECTRE_VULNERABLE; +} +#endif + #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn); @@ -36,13 +63,60 @@ static void __maybe_unused call_hvc_arch_workaround_1(void) arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } -static void cpu_v7_spectre_init(void) +static unsigned int spectre_v2_install_workaround(unsigned int method) { const char *spectre_v2_method = NULL; int cpu = smp_processor_id(); if (per_cpu(harden_branch_predictor_fn, cpu)) - return; + return SPECTRE_MITIGATED; + + switch (method) { + case SPECTRE_V2_METHOD_BPIALL: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_bpiall; + spectre_v2_method = "BPIALL"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_iciallu; + spectre_v2_method = "ICIALLU"; + break; + + case SPECTRE_V2_METHOD_HVC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_hvc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; + spectre_v2_method = "hypervisor"; + break; + + case SPECTRE_V2_METHOD_SMC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_smc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; + spectre_v2_method = "firmware"; + break; + } + + if (spectre_v2_method) + pr_info("CPU%u: Spectre v2: using %s workaround\n", + smp_processor_id(), spectre_v2_method); + + return SPECTRE_MITIGATED; +} +#else +static unsigned int spectre_v2_install_workaround(unsigned int method) +{ + pr_info_once("Spectre V2: workarounds disabled by configuration\n"); + + return SPECTRE_VULNERABLE; +} +#endif + +static void cpu_v7_spectre_v2_init(void) +{ + unsigned int state, method = 0; switch (read_cpuid_part()) { case ARM_CPU_PART_CORTEX_A8: @@ -51,69 +125,133 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_bpiall; - spectre_v2_method = "BPIALL"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; break; case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_iciallu; - spectre_v2_method = "ICIALLU"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_ICIALLU; break; -#ifdef CONFIG_ARM_PSCI case ARM_CPU_PART_BRAHMA_B53: /* Requires no workaround */ + state = SPECTRE_UNAFFECTED; break; + default: /* Other ARM CPUs require no workaround */ - if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) + if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) { + state = SPECTRE_UNAFFECTED; break; + } + fallthrough; - /* Cortex A57/A72 require firmware workaround */ - case ARM_CPU_PART_CORTEX_A57: - case ARM_CPU_PART_CORTEX_A72: { - struct arm_smccc_res res; - arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 != 0) - return; + /* Cortex A57/A72 require firmware workaround */ + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = spectre_v2_get_cpu_fw_mitigation_state(); + if (state != SPECTRE_MITIGATED) + break; switch (arm_smccc_1_1_get_conduit()) { case SMCCC_CONDUIT_HVC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_hvc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_hvc_switch_mm; - spectre_v2_method = "hypervisor"; + method = SPECTRE_V2_METHOD_HVC; break; case SMCCC_CONDUIT_SMC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_smc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_smc_switch_mm; - spectre_v2_method = "firmware"; + method = SPECTRE_V2_METHOD_SMC; break; default: + state = SPECTRE_VULNERABLE; break; } } -#endif + + if (state == SPECTRE_MITIGATED) + state = spectre_v2_install_workaround(method); + + spectre_v2_update_state(state, method); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +static int spectre_bhb_method; + +static const char *spectre_bhb_method_name(int method) +{ + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + return "loop"; + + case SPECTRE_V2_METHOD_BPIALL: + return "BPIALL"; + + default: + return "unknown"; } +} - if (spectre_v2_method) - pr_info("CPU%u: Spectre v2: using %s workaround\n", - smp_processor_id(), spectre_v2_method); +static int spectre_bhb_install_workaround(int method) +{ + if (spectre_bhb_method != method) { + if (spectre_bhb_method) { + pr_err("CPU%u: Spectre BHB: method disagreement, system vulnerable\n", + smp_processor_id()); + + return SPECTRE_VULNERABLE; + } + + if (spectre_bhb_update_vectors(method) == SPECTRE_VULNERABLE) + return SPECTRE_VULNERABLE; + + spectre_bhb_method = method; + + pr_info("CPU%u: Spectre BHB: enabling %s workaround for all CPUs\n", + smp_processor_id(), spectre_bhb_method_name(method)); + } + + return SPECTRE_MITIGATED; } #else -static void cpu_v7_spectre_init(void) +static int spectre_bhb_install_workaround(int method) { + return SPECTRE_VULNERABLE; } #endif +static void cpu_v7_spectre_bhb_init(void) +{ + unsigned int state, method = 0; + + switch (read_cpuid_part()) { + case ARM_CPU_PART_CORTEX_A15: + case ARM_CPU_PART_BRAHMA_B15: + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_LOOP8; + break; + + case ARM_CPU_PART_CORTEX_A73: + case ARM_CPU_PART_CORTEX_A75: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; + break; + + default: + state = SPECTRE_UNAFFECTED; + break; + } + + if (state == SPECTRE_MITIGATED) + state = spectre_bhb_install_workaround(method); + + spectre_v2_update_state(state, method); +} + static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned, u32 mask, const char *msg) { @@ -142,16 +280,18 @@ static bool check_spectre_auxcr(bool *warned, u32 bit) void cpu_v7_ca8_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); } void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } void cpu_v7_bugs_init(void) { - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } |