| .. | .. |
|---|
| 1 | +// SPDX-License-Identifier: GPL-2.0-only |
|---|
| 1 | 2 | /* |
|---|
| 2 | | - * SWIOTLB-based DMA API implementation |
|---|
| 3 | | - * |
|---|
| 4 | 3 | * Copyright (C) 2012 ARM Ltd. |
|---|
| 5 | 4 | * Author: Catalin Marinas <catalin.marinas@arm.com> |
|---|
| 6 | | - * |
|---|
| 7 | | - * This program is free software; you can redistribute it and/or modify |
|---|
| 8 | | - * it under the terms of the GNU General Public License version 2 as |
|---|
| 9 | | - * published by the Free Software Foundation. |
|---|
| 10 | | - * |
|---|
| 11 | | - * This program is distributed in the hope that it will be useful, |
|---|
| 12 | | - * but WITHOUT ANY WARRANTY; without even the implied warranty of |
|---|
| 13 | | - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|---|
| 14 | | - * GNU General Public License for more details. |
|---|
| 15 | | - * |
|---|
| 16 | | - * You should have received a copy of the GNU General Public License |
|---|
| 17 | | - * along with this program. If not, see <http://www.gnu.org/licenses/>. |
|---|
| 18 | 5 | */ |
|---|
| 19 | 6 | |
|---|
| 20 | 7 | #include <linux/gfp.h> |
|---|
| 21 | | -#include <linux/acpi.h> |
|---|
| 22 | | -#include <linux/bootmem.h> |
|---|
| 23 | 8 | #include <linux/cache.h> |
|---|
| 24 | | -#include <linux/export.h> |
|---|
| 25 | | -#include <linux/slab.h> |
|---|
| 26 | | -#include <linux/genalloc.h> |
|---|
| 27 | | -#include <linux/dma-direct.h> |
|---|
| 28 | | -#include <linux/dma-contiguous.h> |
|---|
| 29 | | -#include <linux/mm.h> |
|---|
| 30 | | -#include <linux/iommu.h> |
|---|
| 31 | | -#include <linux/vmalloc.h> |
|---|
| 32 | | -#include <linux/swiotlb.h> |
|---|
| 33 | | -#include <linux/dma-removed.h> |
|---|
| 34 | | -#include <linux/pci.h> |
|---|
| 35 | | -#include <linux/io.h> |
|---|
| 9 | +#include <linux/dma-map-ops.h> |
|---|
| 10 | +#include <linux/dma-iommu.h> |
|---|
| 11 | +#include <xen/xen.h> |
|---|
| 12 | +#include <xen/swiotlb-xen.h> |
|---|
| 13 | +#include <trace/hooks/iommu.h> |
|---|
| 14 | +#include <trace/hooks/dma_noalias.h> |
|---|
| 36 | 15 | |
|---|
| 37 | 16 | #include <asm/cacheflush.h> |
|---|
| 38 | | -#include <asm/tlbflush.h> |
|---|
| 39 | | -#include <asm/dma-iommu.h> |
|---|
| 40 | | -#include <linux/of_address.h> |
|---|
| 41 | | -#include <linux/dma-mapping-fast.h> |
|---|
| 42 | 17 | |
|---|
| 43 | | -static int swiotlb __ro_after_init; |
|---|
| 44 | | - |
|---|
| 45 | | -static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot, |
|---|
| 46 | | - bool coherent) |
|---|
| 18 | +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, |
|---|
| 19 | + enum dma_data_direction dir) |
|---|
| 47 | 20 | { |
|---|
| 48 | | - if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE)) |
|---|
| 49 | | - return pgprot_writecombine(prot); |
|---|
| 50 | | - return prot; |
|---|
| 21 | + __dma_map_area(phys_to_virt(paddr), size, dir); |
|---|
| 51 | 22 | } |
|---|
| 52 | 23 | |
|---|
| 53 | | -static bool is_dma_coherent(struct device *dev, unsigned long attrs) |
|---|
| 24 | +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, |
|---|
| 25 | + enum dma_data_direction dir) |
|---|
| 54 | 26 | { |
|---|
| 55 | | - |
|---|
| 56 | | - if (attrs & DMA_ATTR_FORCE_COHERENT) |
|---|
| 57 | | - return true; |
|---|
| 58 | | - else if (attrs & DMA_ATTR_FORCE_NON_COHERENT) |
|---|
| 59 | | - return false; |
|---|
| 60 | | - else if (is_device_dma_coherent(dev)) |
|---|
| 61 | | - return true; |
|---|
| 62 | | - else |
|---|
| 63 | | - return false; |
|---|
| 64 | | -} |
|---|
| 65 | | -static struct gen_pool *atomic_pool __ro_after_init; |
|---|
| 66 | | - |
|---|
| 67 | | -#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K |
|---|
| 68 | | -static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; |
|---|
| 69 | | - |
|---|
| 70 | | -static int __init early_coherent_pool(char *p) |
|---|
| 71 | | -{ |
|---|
| 72 | | - atomic_pool_size = memparse(p, &p); |
|---|
| 73 | | - return 0; |
|---|
| 74 | | -} |
|---|
| 75 | | -early_param("coherent_pool", early_coherent_pool); |
|---|
| 76 | | - |
|---|
| 77 | | -static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) |
|---|
| 78 | | -{ |
|---|
| 79 | | - unsigned long val; |
|---|
| 80 | | - void *ptr = NULL; |
|---|
| 81 | | - |
|---|
| 82 | | - if (!atomic_pool) { |
|---|
| 83 | | - WARN(1, "coherent pool not initialised!\n"); |
|---|
| 84 | | - return NULL; |
|---|
| 85 | | - } |
|---|
| 86 | | - |
|---|
| 87 | | - val = gen_pool_alloc(atomic_pool, size); |
|---|
| 88 | | - if (val) { |
|---|
| 89 | | - phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); |
|---|
| 90 | | - |
|---|
| 91 | | - *ret_page = phys_to_page(phys); |
|---|
| 92 | | - ptr = (void *)val; |
|---|
| 93 | | - memset(ptr, 0, size); |
|---|
| 94 | | - } |
|---|
| 95 | | - |
|---|
| 96 | | - return ptr; |
|---|
| 27 | + __dma_unmap_area(phys_to_virt(paddr), size, dir); |
|---|
| 97 | 28 | } |
|---|
| 98 | 29 | |
|---|
| 99 | | -static bool __in_atomic_pool(void *start, size_t size) |
|---|
| 30 | +void arch_dma_prep_coherent(struct page *page, size_t size) |
|---|
| 100 | 31 | { |
|---|
| 101 | | - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); |
|---|
| 32 | + __dma_flush_area(page_address(page), size); |
|---|
| 102 | 33 | } |
|---|
| 103 | | - |
|---|
| 104 | | -static int __free_from_pool(void *start, size_t size) |
|---|
| 105 | | -{ |
|---|
| 106 | | - if (!__in_atomic_pool(start, size)) |
|---|
| 107 | | - return 0; |
|---|
| 108 | | - |
|---|
| 109 | | - gen_pool_free(atomic_pool, (unsigned long)start, size); |
|---|
| 110 | | - |
|---|
| 111 | | - return 1; |
|---|
| 112 | | -} |
|---|
| 113 | | - |
|---|
| 114 | | -static void *__dma_alloc(struct device *dev, size_t size, |
|---|
| 115 | | - dma_addr_t *dma_handle, gfp_t flags, |
|---|
| 116 | | - unsigned long attrs) |
|---|
| 117 | | -{ |
|---|
| 118 | | - struct page *page; |
|---|
| 119 | | - void *ptr, *coherent_ptr; |
|---|
| 120 | | - bool coherent = is_dma_coherent(dev, attrs); |
|---|
| 121 | | - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false); |
|---|
| 122 | | - |
|---|
| 123 | | - size = PAGE_ALIGN(size); |
|---|
| 124 | | - |
|---|
| 125 | | - if (!coherent && !gfpflags_allow_blocking(flags)) { |
|---|
| 126 | | - struct page *page = NULL; |
|---|
| 127 | | - void *addr = __alloc_from_pool(size, &page, flags); |
|---|
| 128 | | - |
|---|
| 129 | | - if (addr) |
|---|
| 130 | | - *dma_handle = phys_to_dma(dev, page_to_phys(page)); |
|---|
| 131 | | - |
|---|
| 132 | | - return addr; |
|---|
| 133 | | - } |
|---|
| 134 | | - |
|---|
| 135 | | - ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs); |
|---|
| 136 | | - |
|---|
| 137 | | - if (!ptr) |
|---|
| 138 | | - goto no_mem; |
|---|
| 139 | | - |
|---|
| 140 | | - /* no need for non-cacheable mapping if coherent */ |
|---|
| 141 | | - if (coherent) |
|---|
| 142 | | - return ptr; |
|---|
| 143 | | - |
|---|
| 144 | | - /* remove any dirty cache lines on the kernel alias */ |
|---|
| 145 | | - __dma_flush_area(ptr, size); |
|---|
| 146 | | - |
|---|
| 147 | | - /* create a coherent mapping */ |
|---|
| 148 | | - page = virt_to_page(ptr); |
|---|
| 149 | | - coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, |
|---|
| 150 | | - prot, __builtin_return_address(0)); |
|---|
| 151 | | - if (!coherent_ptr) |
|---|
| 152 | | - goto no_map; |
|---|
| 153 | | - |
|---|
| 154 | | - return coherent_ptr; |
|---|
| 155 | | - |
|---|
| 156 | | -no_map: |
|---|
| 157 | | - swiotlb_free(dev, size, ptr, *dma_handle, attrs); |
|---|
| 158 | | -no_mem: |
|---|
| 159 | | - return NULL; |
|---|
| 160 | | -} |
|---|
| 161 | | - |
|---|
| 162 | | -static void __dma_free(struct device *dev, size_t size, |
|---|
| 163 | | - void *vaddr, dma_addr_t dma_handle, |
|---|
| 164 | | - unsigned long attrs) |
|---|
| 165 | | -{ |
|---|
| 166 | | - void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); |
|---|
| 167 | | - |
|---|
| 168 | | - size = PAGE_ALIGN(size); |
|---|
| 169 | | - |
|---|
| 170 | | - if (!is_device_dma_coherent(dev)) { |
|---|
| 171 | | - if (__free_from_pool(vaddr, size)) |
|---|
| 172 | | - return; |
|---|
| 173 | | - vunmap(vaddr); |
|---|
| 174 | | - } |
|---|
| 175 | | - swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs); |
|---|
| 176 | | -} |
|---|
| 177 | | - |
|---|
| 178 | | -static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, |
|---|
| 179 | | - unsigned long offset, size_t size, |
|---|
| 180 | | - enum dma_data_direction dir, |
|---|
| 181 | | - unsigned long attrs) |
|---|
| 182 | | -{ |
|---|
| 183 | | - dma_addr_t dev_addr; |
|---|
| 184 | | - |
|---|
| 185 | | - dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs); |
|---|
| 186 | | - if (!is_dma_coherent(dev, attrs) && |
|---|
| 187 | | - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 188 | | - __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); |
|---|
| 189 | | - |
|---|
| 190 | | - return dev_addr; |
|---|
| 191 | | -} |
|---|
| 192 | | - |
|---|
| 193 | | - |
|---|
| 194 | | -static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr, |
|---|
| 195 | | - size_t size, enum dma_data_direction dir, |
|---|
| 196 | | - unsigned long attrs) |
|---|
| 197 | | -{ |
|---|
| 198 | | - if (!is_dma_coherent(dev, attrs) && |
|---|
| 199 | | - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 200 | | - __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); |
|---|
| 201 | | - swiotlb_unmap_page(dev, dev_addr, size, dir, attrs); |
|---|
| 202 | | -} |
|---|
| 203 | | - |
|---|
| 204 | | -static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, |
|---|
| 205 | | - int nelems, enum dma_data_direction dir, |
|---|
| 206 | | - unsigned long attrs) |
|---|
| 207 | | -{ |
|---|
| 208 | | - struct scatterlist *sg; |
|---|
| 209 | | - int i, ret; |
|---|
| 210 | | - |
|---|
| 211 | | - ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs); |
|---|
| 212 | | - if (!is_dma_coherent(dev, attrs) && |
|---|
| 213 | | - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 214 | | - for_each_sg(sgl, sg, ret, i) |
|---|
| 215 | | - __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), |
|---|
| 216 | | - sg->length, dir); |
|---|
| 217 | | - |
|---|
| 218 | | - return ret; |
|---|
| 219 | | -} |
|---|
| 220 | | - |
|---|
| 221 | | -static void __swiotlb_unmap_sg_attrs(struct device *dev, |
|---|
| 222 | | - struct scatterlist *sgl, int nelems, |
|---|
| 223 | | - enum dma_data_direction dir, |
|---|
| 224 | | - unsigned long attrs) |
|---|
| 225 | | -{ |
|---|
| 226 | | - struct scatterlist *sg; |
|---|
| 227 | | - int i; |
|---|
| 228 | | - |
|---|
| 229 | | - if (!is_dma_coherent(dev, attrs) && |
|---|
| 230 | | - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 231 | | - for_each_sg(sgl, sg, nelems, i) |
|---|
| 232 | | - __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), |
|---|
| 233 | | - sg->length, dir); |
|---|
| 234 | | - swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs); |
|---|
| 235 | | -} |
|---|
| 236 | | - |
|---|
| 237 | | -static void __swiotlb_sync_single_for_cpu(struct device *dev, |
|---|
| 238 | | - dma_addr_t dev_addr, size_t size, |
|---|
| 239 | | - enum dma_data_direction dir) |
|---|
| 240 | | -{ |
|---|
| 241 | | - if (!is_device_dma_coherent(dev)) |
|---|
| 242 | | - __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); |
|---|
| 243 | | - swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir); |
|---|
| 244 | | -} |
|---|
| 245 | | - |
|---|
| 246 | | -static void __swiotlb_sync_single_for_device(struct device *dev, |
|---|
| 247 | | - dma_addr_t dev_addr, size_t size, |
|---|
| 248 | | - enum dma_data_direction dir) |
|---|
| 249 | | -{ |
|---|
| 250 | | - swiotlb_sync_single_for_device(dev, dev_addr, size, dir); |
|---|
| 251 | | - if (!is_device_dma_coherent(dev)) |
|---|
| 252 | | - __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); |
|---|
| 253 | | -} |
|---|
| 254 | | - |
|---|
| 255 | | -static void __swiotlb_sync_sg_for_cpu(struct device *dev, |
|---|
| 256 | | - struct scatterlist *sgl, int nelems, |
|---|
| 257 | | - enum dma_data_direction dir) |
|---|
| 258 | | -{ |
|---|
| 259 | | - struct scatterlist *sg; |
|---|
| 260 | | - int i; |
|---|
| 261 | | - |
|---|
| 262 | | - if (!is_device_dma_coherent(dev)) |
|---|
| 263 | | - for_each_sg(sgl, sg, nelems, i) |
|---|
| 264 | | - __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), |
|---|
| 265 | | - sg->length, dir); |
|---|
| 266 | | - swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir); |
|---|
| 267 | | -} |
|---|
| 268 | | - |
|---|
| 269 | | -static void __swiotlb_sync_sg_for_device(struct device *dev, |
|---|
| 270 | | - struct scatterlist *sgl, int nelems, |
|---|
| 271 | | - enum dma_data_direction dir) |
|---|
| 272 | | -{ |
|---|
| 273 | | - struct scatterlist *sg; |
|---|
| 274 | | - int i; |
|---|
| 275 | | - |
|---|
| 276 | | - swiotlb_sync_sg_for_device(dev, sgl, nelems, dir); |
|---|
| 277 | | - if (!is_device_dma_coherent(dev)) |
|---|
| 278 | | - for_each_sg(sgl, sg, nelems, i) |
|---|
| 279 | | - __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), |
|---|
| 280 | | - sg->length, dir); |
|---|
| 281 | | -} |
|---|
| 282 | | - |
|---|
| 283 | | -static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, |
|---|
| 284 | | - unsigned long pfn, size_t size) |
|---|
| 285 | | -{ |
|---|
| 286 | | - int ret = -ENXIO; |
|---|
| 287 | | - unsigned long nr_vma_pages = vma_pages(vma); |
|---|
| 288 | | - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; |
|---|
| 289 | | - unsigned long off = vma->vm_pgoff; |
|---|
| 290 | | - |
|---|
| 291 | | - if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) { |
|---|
| 292 | | - ret = remap_pfn_range(vma, vma->vm_start, |
|---|
| 293 | | - pfn + off, |
|---|
| 294 | | - vma->vm_end - vma->vm_start, |
|---|
| 295 | | - vma->vm_page_prot); |
|---|
| 296 | | - } |
|---|
| 297 | | - |
|---|
| 298 | | - return ret; |
|---|
| 299 | | -} |
|---|
| 300 | | - |
|---|
| 301 | | -static int __swiotlb_mmap(struct device *dev, |
|---|
| 302 | | - struct vm_area_struct *vma, |
|---|
| 303 | | - void *cpu_addr, dma_addr_t dma_addr, size_t size, |
|---|
| 304 | | - unsigned long attrs) |
|---|
| 305 | | -{ |
|---|
| 306 | | - int ret = -ENXIO; |
|---|
| 307 | | - unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT; |
|---|
| 308 | | - |
|---|
| 309 | | - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, |
|---|
| 310 | | - is_dma_coherent(dev, attrs)); |
|---|
| 311 | | - |
|---|
| 312 | | - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) |
|---|
| 313 | | - return ret; |
|---|
| 314 | | - |
|---|
| 315 | | - return __swiotlb_mmap_pfn(vma, pfn, size); |
|---|
| 316 | | -} |
|---|
| 317 | | - |
|---|
| 318 | | -static int __swiotlb_get_sgtable_page(struct sg_table *sgt, |
|---|
| 319 | | - struct page *page, size_t size) |
|---|
| 320 | | -{ |
|---|
| 321 | | - int ret = sg_alloc_table(sgt, 1, GFP_KERNEL); |
|---|
| 322 | | - |
|---|
| 323 | | - if (!ret) |
|---|
| 324 | | - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); |
|---|
| 325 | | - |
|---|
| 326 | | - return ret; |
|---|
| 327 | | -} |
|---|
| 328 | | - |
|---|
| 329 | | -static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, |
|---|
| 330 | | - void *cpu_addr, dma_addr_t handle, size_t size, |
|---|
| 331 | | - unsigned long attrs) |
|---|
| 332 | | -{ |
|---|
| 333 | | - struct page *page = phys_to_page(dma_to_phys(dev, handle)); |
|---|
| 334 | | - |
|---|
| 335 | | - return __swiotlb_get_sgtable_page(sgt, page, size); |
|---|
| 336 | | -} |
|---|
| 337 | | - |
|---|
| 338 | | -static int __swiotlb_dma_supported(struct device *hwdev, u64 mask) |
|---|
| 339 | | -{ |
|---|
| 340 | | - if (swiotlb) |
|---|
| 341 | | - return swiotlb_dma_supported(hwdev, mask); |
|---|
| 342 | | - return 1; |
|---|
| 343 | | -} |
|---|
| 344 | | - |
|---|
| 345 | | -static void *arm64_dma_remap(struct device *dev, void *cpu_addr, |
|---|
| 346 | | - dma_addr_t handle, size_t size, |
|---|
| 347 | | - unsigned long attrs) |
|---|
| 348 | | -{ |
|---|
| 349 | | - struct page *page = phys_to_page(dma_to_phys(dev, handle)); |
|---|
| 350 | | - bool coherent = is_device_dma_coherent(dev); |
|---|
| 351 | | - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); |
|---|
| 352 | | - unsigned long offset = handle & ~PAGE_MASK; |
|---|
| 353 | | - struct vm_struct *area; |
|---|
| 354 | | - unsigned long addr; |
|---|
| 355 | | - |
|---|
| 356 | | - size = PAGE_ALIGN(size + offset); |
|---|
| 357 | | - |
|---|
| 358 | | - /* |
|---|
| 359 | | - * DMA allocation can be mapped to user space, so lets |
|---|
| 360 | | - * set VM_USERMAP flags too. |
|---|
| 361 | | - */ |
|---|
| 362 | | - area = get_vm_area(size, VM_USERMAP); |
|---|
| 363 | | - if (!area) |
|---|
| 364 | | - return NULL; |
|---|
| 365 | | - |
|---|
| 366 | | - addr = (unsigned long)area->addr; |
|---|
| 367 | | - area->phys_addr = __pfn_to_phys(page_to_pfn(page)); |
|---|
| 368 | | - |
|---|
| 369 | | - if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) { |
|---|
| 370 | | - vunmap((void *)addr); |
|---|
| 371 | | - return NULL; |
|---|
| 372 | | - } |
|---|
| 373 | | - return (void *)addr + offset; |
|---|
| 374 | | -} |
|---|
| 375 | | - |
|---|
| 376 | | -static void arm64_dma_unremap(struct device *dev, void *remapped_addr, |
|---|
| 377 | | - size_t size) |
|---|
| 378 | | -{ |
|---|
| 379 | | - struct vm_struct *area; |
|---|
| 380 | | - |
|---|
| 381 | | - size = PAGE_ALIGN(size); |
|---|
| 382 | | - remapped_addr = (void *)((unsigned long)remapped_addr & PAGE_MASK); |
|---|
| 383 | | - |
|---|
| 384 | | - area = find_vm_area(remapped_addr); |
|---|
| 385 | | - if (!area) { |
|---|
| 386 | | - WARN(1, "trying to free invalid coherent area: %pK\n", |
|---|
| 387 | | - remapped_addr); |
|---|
| 388 | | - return; |
|---|
| 389 | | - } |
|---|
| 390 | | - vunmap(remapped_addr); |
|---|
| 391 | | - flush_tlb_kernel_range((unsigned long)remapped_addr, |
|---|
| 392 | | - (unsigned long)(remapped_addr + size)); |
|---|
| 393 | | -} |
|---|
| 394 | | - |
|---|
| 395 | | -static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr) |
|---|
| 396 | | -{ |
|---|
| 397 | | - if (swiotlb) |
|---|
| 398 | | - return swiotlb_dma_mapping_error(hwdev, addr); |
|---|
| 399 | | - return 0; |
|---|
| 400 | | -} |
|---|
| 401 | | - |
|---|
| 402 | | -static const struct dma_map_ops arm64_swiotlb_dma_ops = { |
|---|
| 403 | | - .alloc = __dma_alloc, |
|---|
| 404 | | - .free = __dma_free, |
|---|
| 405 | | - .mmap = __swiotlb_mmap, |
|---|
| 406 | | - .get_sgtable = __swiotlb_get_sgtable, |
|---|
| 407 | | - .map_page = __swiotlb_map_page, |
|---|
| 408 | | - .unmap_page = __swiotlb_unmap_page, |
|---|
| 409 | | - .map_sg = __swiotlb_map_sg_attrs, |
|---|
| 410 | | - .unmap_sg = __swiotlb_unmap_sg_attrs, |
|---|
| 411 | | - .sync_single_for_cpu = __swiotlb_sync_single_for_cpu, |
|---|
| 412 | | - .sync_single_for_device = __swiotlb_sync_single_for_device, |
|---|
| 413 | | - .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu, |
|---|
| 414 | | - .sync_sg_for_device = __swiotlb_sync_sg_for_device, |
|---|
| 415 | | - .dma_supported = __swiotlb_dma_supported, |
|---|
| 416 | | - .mapping_error = __swiotlb_dma_mapping_error, |
|---|
| 417 | | - .remap = arm64_dma_remap, |
|---|
| 418 | | - .unremap = arm64_dma_unremap, |
|---|
| 419 | | -}; |
|---|
| 420 | | - |
|---|
| 421 | | -static int __init atomic_pool_init(void) |
|---|
| 422 | | -{ |
|---|
| 423 | | - pgprot_t prot = __pgprot(PROT_NORMAL_NC); |
|---|
| 424 | | - unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; |
|---|
| 425 | | - struct page *page; |
|---|
| 426 | | - void *addr; |
|---|
| 427 | | - unsigned int pool_size_order = get_order(atomic_pool_size); |
|---|
| 428 | | - |
|---|
| 429 | | - if (dev_get_cma_area(NULL)) |
|---|
| 430 | | - page = dma_alloc_from_contiguous(NULL, nr_pages, |
|---|
| 431 | | - pool_size_order, false); |
|---|
| 432 | | - else |
|---|
| 433 | | - page = alloc_pages(GFP_DMA32, pool_size_order); |
|---|
| 434 | | - |
|---|
| 435 | | - if (page) { |
|---|
| 436 | | - int ret; |
|---|
| 437 | | - void *page_addr = page_address(page); |
|---|
| 438 | | - |
|---|
| 439 | | - memset(page_addr, 0, atomic_pool_size); |
|---|
| 440 | | - __dma_flush_area(page_addr, atomic_pool_size); |
|---|
| 441 | | - |
|---|
| 442 | | - atomic_pool = gen_pool_create(PAGE_SHIFT, -1); |
|---|
| 443 | | - if (!atomic_pool) |
|---|
| 444 | | - goto free_page; |
|---|
| 445 | | - |
|---|
| 446 | | - addr = dma_common_contiguous_remap(page, atomic_pool_size, |
|---|
| 447 | | - VM_USERMAP, prot, atomic_pool_init); |
|---|
| 448 | | - |
|---|
| 449 | | - if (!addr) |
|---|
| 450 | | - goto destroy_genpool; |
|---|
| 451 | | - |
|---|
| 452 | | - ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, |
|---|
| 453 | | - page_to_phys(page), |
|---|
| 454 | | - atomic_pool_size, -1); |
|---|
| 455 | | - if (ret) |
|---|
| 456 | | - goto remove_mapping; |
|---|
| 457 | | - |
|---|
| 458 | | - gen_pool_set_algo(atomic_pool, |
|---|
| 459 | | - gen_pool_first_fit_order_align, |
|---|
| 460 | | - NULL); |
|---|
| 461 | | - |
|---|
| 462 | | - pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", |
|---|
| 463 | | - atomic_pool_size / 1024); |
|---|
| 464 | | - return 0; |
|---|
| 465 | | - } |
|---|
| 466 | | - goto out; |
|---|
| 467 | | - |
|---|
| 468 | | -remove_mapping: |
|---|
| 469 | | - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP, false); |
|---|
| 470 | | -destroy_genpool: |
|---|
| 471 | | - gen_pool_destroy(atomic_pool); |
|---|
| 472 | | - atomic_pool = NULL; |
|---|
| 473 | | -free_page: |
|---|
| 474 | | - if (!dma_release_from_contiguous(NULL, page, nr_pages)) |
|---|
| 475 | | - __free_pages(page, pool_size_order); |
|---|
| 476 | | -out: |
|---|
| 477 | | - pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", |
|---|
| 478 | | - atomic_pool_size / 1024); |
|---|
| 479 | | - return -ENOMEM; |
|---|
| 480 | | -} |
|---|
| 481 | | - |
|---|
| 482 | | -/******************************************** |
|---|
| 483 | | - * The following APIs are for dummy DMA ops * |
|---|
| 484 | | - ********************************************/ |
|---|
| 485 | | - |
|---|
| 486 | | -static void *__dummy_alloc(struct device *dev, size_t size, |
|---|
| 487 | | - dma_addr_t *dma_handle, gfp_t flags, |
|---|
| 488 | | - unsigned long attrs) |
|---|
| 489 | | -{ |
|---|
| 490 | | - WARN(1, "dma alloc failure, device may be missing a call to arch_setup_dma_ops"); |
|---|
| 491 | | - return NULL; |
|---|
| 492 | | -} |
|---|
| 493 | | - |
|---|
| 494 | | -static void __dummy_free(struct device *dev, size_t size, |
|---|
| 495 | | - void *vaddr, dma_addr_t dma_handle, |
|---|
| 496 | | - unsigned long attrs) |
|---|
| 497 | | -{ |
|---|
| 498 | | -} |
|---|
| 499 | | - |
|---|
| 500 | | -static int __dummy_mmap(struct device *dev, |
|---|
| 501 | | - struct vm_area_struct *vma, |
|---|
| 502 | | - void *cpu_addr, dma_addr_t dma_addr, size_t size, |
|---|
| 503 | | - unsigned long attrs) |
|---|
| 504 | | -{ |
|---|
| 505 | | - return -ENXIO; |
|---|
| 506 | | -} |
|---|
| 507 | | - |
|---|
| 508 | | -static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, |
|---|
| 509 | | - unsigned long offset, size_t size, |
|---|
| 510 | | - enum dma_data_direction dir, |
|---|
| 511 | | - unsigned long attrs) |
|---|
| 512 | | -{ |
|---|
| 513 | | - return 0; |
|---|
| 514 | | -} |
|---|
| 515 | | - |
|---|
| 516 | | -static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, |
|---|
| 517 | | - size_t size, enum dma_data_direction dir, |
|---|
| 518 | | - unsigned long attrs) |
|---|
| 519 | | -{ |
|---|
| 520 | | -} |
|---|
| 521 | | - |
|---|
| 522 | | -static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, |
|---|
| 523 | | - int nelems, enum dma_data_direction dir, |
|---|
| 524 | | - unsigned long attrs) |
|---|
| 525 | | -{ |
|---|
| 526 | | - return 0; |
|---|
| 527 | | -} |
|---|
| 528 | | - |
|---|
| 529 | | -static void __dummy_unmap_sg(struct device *dev, |
|---|
| 530 | | - struct scatterlist *sgl, int nelems, |
|---|
| 531 | | - enum dma_data_direction dir, |
|---|
| 532 | | - unsigned long attrs) |
|---|
| 533 | | -{ |
|---|
| 534 | | -} |
|---|
| 535 | | - |
|---|
| 536 | | -static void __dummy_sync_single(struct device *dev, |
|---|
| 537 | | - dma_addr_t dev_addr, size_t size, |
|---|
| 538 | | - enum dma_data_direction dir) |
|---|
| 539 | | -{ |
|---|
| 540 | | -} |
|---|
| 541 | | - |
|---|
| 542 | | -static void __dummy_sync_sg(struct device *dev, |
|---|
| 543 | | - struct scatterlist *sgl, int nelems, |
|---|
| 544 | | - enum dma_data_direction dir) |
|---|
| 545 | | -{ |
|---|
| 546 | | -} |
|---|
| 547 | | - |
|---|
| 548 | | -static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) |
|---|
| 549 | | -{ |
|---|
| 550 | | - return 1; |
|---|
| 551 | | -} |
|---|
| 552 | | - |
|---|
| 553 | | -static int __dummy_dma_supported(struct device *hwdev, u64 mask) |
|---|
| 554 | | -{ |
|---|
| 555 | | - return 0; |
|---|
| 556 | | -} |
|---|
| 557 | | - |
|---|
| 558 | | -const struct dma_map_ops dummy_dma_ops = { |
|---|
| 559 | | - .alloc = __dummy_alloc, |
|---|
| 560 | | - .free = __dummy_free, |
|---|
| 561 | | - .mmap = __dummy_mmap, |
|---|
| 562 | | - .map_page = __dummy_map_page, |
|---|
| 563 | | - .unmap_page = __dummy_unmap_page, |
|---|
| 564 | | - .map_sg = __dummy_map_sg, |
|---|
| 565 | | - .unmap_sg = __dummy_unmap_sg, |
|---|
| 566 | | - .sync_single_for_cpu = __dummy_sync_single, |
|---|
| 567 | | - .sync_single_for_device = __dummy_sync_single, |
|---|
| 568 | | - .sync_sg_for_cpu = __dummy_sync_sg, |
|---|
| 569 | | - .sync_sg_for_device = __dummy_sync_sg, |
|---|
| 570 | | - .mapping_error = __dummy_mapping_error, |
|---|
| 571 | | - .dma_supported = __dummy_dma_supported, |
|---|
| 572 | | -}; |
|---|
| 573 | | -EXPORT_SYMBOL(dummy_dma_ops); |
|---|
| 574 | | - |
|---|
| 575 | | -static int __init arm64_dma_init(void) |
|---|
| 576 | | -{ |
|---|
| 577 | | - if (swiotlb_force == SWIOTLB_FORCE || |
|---|
| 578 | | - max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) |
|---|
| 579 | | - swiotlb = 1; |
|---|
| 580 | | - |
|---|
| 581 | | - WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(), |
|---|
| 582 | | - TAINT_CPU_OUT_OF_SPEC, |
|---|
| 583 | | - "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", |
|---|
| 584 | | - ARCH_DMA_MINALIGN, cache_line_size()); |
|---|
| 585 | | - |
|---|
| 586 | | - return atomic_pool_init(); |
|---|
| 587 | | -} |
|---|
| 588 | | -arch_initcall(arm64_dma_init); |
|---|
| 589 | 34 | |
|---|
| 590 | 35 | #ifdef CONFIG_IOMMU_DMA |
|---|
| 591 | | -#include <linux/dma-iommu.h> |
|---|
| 592 | | -#include <linux/platform_device.h> |
|---|
| 593 | | -#include <linux/amba/bus.h> |
|---|
| 594 | | - |
|---|
| 595 | | -/* Thankfully, all cache ops are by VA so we can ignore phys here */ |
|---|
| 596 | | -static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) |
|---|
| 597 | | -{ |
|---|
| 598 | | - __dma_flush_area(virt, PAGE_SIZE); |
|---|
| 599 | | -} |
|---|
| 600 | | - |
|---|
| 601 | | -static void *__iommu_alloc_attrs(struct device *dev, size_t size, |
|---|
| 602 | | - dma_addr_t *handle, gfp_t gfp, |
|---|
| 603 | | - unsigned long attrs) |
|---|
| 604 | | -{ |
|---|
| 605 | | - bool coherent = is_dma_coherent(dev, attrs); |
|---|
| 606 | | - int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs); |
|---|
| 607 | | - size_t iosize = size; |
|---|
| 608 | | - void *addr; |
|---|
| 609 | | - |
|---|
| 610 | | - if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) |
|---|
| 611 | | - return NULL; |
|---|
| 612 | | - |
|---|
| 613 | | - size = PAGE_ALIGN(size); |
|---|
| 614 | | - |
|---|
| 615 | | - /* |
|---|
| 616 | | - * Some drivers rely on this, and we probably don't want the |
|---|
| 617 | | - * possibility of stale kernel data being read by devices anyway. |
|---|
| 618 | | - */ |
|---|
| 619 | | - if (!(attrs & DMA_ATTR_SKIP_ZEROING)) |
|---|
| 620 | | - gfp |= __GFP_ZERO; |
|---|
| 621 | | - |
|---|
| 622 | | - if (!gfpflags_allow_blocking(gfp)) { |
|---|
| 623 | | - struct page *page; |
|---|
| 624 | | - /* |
|---|
| 625 | | - * In atomic context we can't remap anything, so we'll only |
|---|
| 626 | | - * get the virtually contiguous buffer we need by way of a |
|---|
| 627 | | - * physically contiguous allocation. |
|---|
| 628 | | - */ |
|---|
| 629 | | - if (coherent) { |
|---|
| 630 | | - page = alloc_pages(gfp, get_order(size)); |
|---|
| 631 | | - addr = page ? page_address(page) : NULL; |
|---|
| 632 | | - } else { |
|---|
| 633 | | - addr = __alloc_from_pool(size, &page, gfp); |
|---|
| 634 | | - } |
|---|
| 635 | | - if (!addr) |
|---|
| 636 | | - return NULL; |
|---|
| 637 | | - |
|---|
| 638 | | - *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); |
|---|
| 639 | | - if (iommu_dma_mapping_error(dev, *handle)) { |
|---|
| 640 | | - if (coherent) |
|---|
| 641 | | - __free_pages(page, get_order(size)); |
|---|
| 642 | | - else |
|---|
| 643 | | - __free_from_pool(addr, size); |
|---|
| 644 | | - addr = NULL; |
|---|
| 645 | | - } |
|---|
| 646 | | - } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { |
|---|
| 647 | | - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); |
|---|
| 648 | | - struct page *page; |
|---|
| 649 | | - |
|---|
| 650 | | - page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, |
|---|
| 651 | | - get_order(size), gfp & __GFP_NOWARN); |
|---|
| 652 | | - if (!page) |
|---|
| 653 | | - return NULL; |
|---|
| 654 | | - |
|---|
| 655 | | - *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); |
|---|
| 656 | | - if (iommu_dma_mapping_error(dev, *handle)) { |
|---|
| 657 | | - dma_release_from_contiguous(dev, page, |
|---|
| 658 | | - size >> PAGE_SHIFT); |
|---|
| 659 | | - return NULL; |
|---|
| 660 | | - } |
|---|
| 661 | | - addr = dma_common_contiguous_remap(page, size, VM_USERMAP, |
|---|
| 662 | | - prot, |
|---|
| 663 | | - __builtin_return_address(0)); |
|---|
| 664 | | - if (addr) { |
|---|
| 665 | | - if (!coherent) |
|---|
| 666 | | - __dma_flush_area(page_to_virt(page), iosize); |
|---|
| 667 | | - memset(addr, 0, size); |
|---|
| 668 | | - } else { |
|---|
| 669 | | - iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); |
|---|
| 670 | | - dma_release_from_contiguous(dev, page, |
|---|
| 671 | | - size >> PAGE_SHIFT); |
|---|
| 672 | | - } |
|---|
| 673 | | - } else { |
|---|
| 674 | | - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); |
|---|
| 675 | | - struct page **pages; |
|---|
| 676 | | - |
|---|
| 677 | | - pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot, |
|---|
| 678 | | - handle, flush_page); |
|---|
| 679 | | - if (!pages) |
|---|
| 680 | | - return NULL; |
|---|
| 681 | | - |
|---|
| 682 | | - addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, |
|---|
| 683 | | - __builtin_return_address(0)); |
|---|
| 684 | | - if (!addr) |
|---|
| 685 | | - iommu_dma_free(dev, pages, iosize, handle); |
|---|
| 686 | | - } |
|---|
| 687 | | - return addr; |
|---|
| 688 | | -} |
|---|
| 689 | | - |
|---|
| 690 | | -static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, |
|---|
| 691 | | - dma_addr_t handle, unsigned long attrs) |
|---|
| 692 | | -{ |
|---|
| 693 | | - size_t iosize = size; |
|---|
| 694 | | - |
|---|
| 695 | | - size = PAGE_ALIGN(size); |
|---|
| 696 | | - /* |
|---|
| 697 | | - * @cpu_addr will be one of 4 things depending on how it was allocated: |
|---|
| 698 | | - * - A remapped array of pages for contiguous allocations. |
|---|
| 699 | | - * - A remapped array of pages from iommu_dma_alloc(), for all |
|---|
| 700 | | - * non-atomic allocations. |
|---|
| 701 | | - * - A non-cacheable alias from the atomic pool, for atomic |
|---|
| 702 | | - * allocations by non-coherent devices. |
|---|
| 703 | | - * - A normal lowmem address, for atomic allocations by |
|---|
| 704 | | - * coherent devices. |
|---|
| 705 | | - * Hence how dodgy the below logic looks... |
|---|
| 706 | | - */ |
|---|
| 707 | | - if (__in_atomic_pool(cpu_addr, size)) { |
|---|
| 708 | | - iommu_dma_unmap_page(dev, handle, iosize, 0, 0); |
|---|
| 709 | | - __free_from_pool(cpu_addr, size); |
|---|
| 710 | | - } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { |
|---|
| 711 | | - struct page *page = vmalloc_to_page(cpu_addr); |
|---|
| 712 | | - iommu_dma_unmap_page(dev, handle, iosize, 0, attrs); |
|---|
| 713 | | - dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); |
|---|
| 714 | | - dma_common_free_remap(cpu_addr, size, VM_USERMAP, false); |
|---|
| 715 | | - } else if (is_vmalloc_addr(cpu_addr)) { |
|---|
| 716 | | - struct vm_struct *area = find_vm_area(cpu_addr); |
|---|
| 717 | | - |
|---|
| 718 | | - if (WARN_ON(!area || !area->pages)) |
|---|
| 719 | | - return; |
|---|
| 720 | | - iommu_dma_free(dev, area->pages, iosize, &handle); |
|---|
| 721 | | - dma_common_free_remap(cpu_addr, size, VM_USERMAP, false); |
|---|
| 722 | | - } else { |
|---|
| 723 | | - iommu_dma_unmap_page(dev, handle, iosize, 0, 0); |
|---|
| 724 | | - __free_pages(virt_to_page(cpu_addr), get_order(size)); |
|---|
| 725 | | - } |
|---|
| 726 | | -} |
|---|
| 727 | | - |
|---|
| 728 | | -static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, |
|---|
| 729 | | - void *cpu_addr, dma_addr_t dma_addr, size_t size, |
|---|
| 730 | | - unsigned long attrs) |
|---|
| 731 | | -{ |
|---|
| 732 | | - struct vm_struct *area; |
|---|
| 733 | | - int ret; |
|---|
| 734 | | - unsigned long pfn = 0; |
|---|
| 735 | | - |
|---|
| 736 | | - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, |
|---|
| 737 | | - is_dma_coherent(dev, attrs)); |
|---|
| 738 | | - |
|---|
| 739 | | - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) |
|---|
| 740 | | - return ret; |
|---|
| 741 | | - |
|---|
| 742 | | - area = find_vm_area(cpu_addr); |
|---|
| 743 | | - |
|---|
| 744 | | - if (area && area->pages) |
|---|
| 745 | | - return iommu_dma_mmap(area->pages, size, vma); |
|---|
| 746 | | - else if (!is_vmalloc_addr(cpu_addr)) |
|---|
| 747 | | - pfn = page_to_pfn(virt_to_page(cpu_addr)); |
|---|
| 748 | | - else if (is_vmalloc_addr(cpu_addr)) |
|---|
| 749 | | - /* |
|---|
| 750 | | - * DMA_ATTR_FORCE_CONTIGUOUS and atomic pool allocations are |
|---|
| 751 | | - * always remapped, hence in the vmalloc space. |
|---|
| 752 | | - */ |
|---|
| 753 | | - pfn = vmalloc_to_pfn(cpu_addr); |
|---|
| 754 | | - |
|---|
| 755 | | - if (pfn) |
|---|
| 756 | | - return __swiotlb_mmap_pfn(vma, pfn, size); |
|---|
| 757 | | - |
|---|
| 758 | | - return -ENXIO; |
|---|
| 759 | | -} |
|---|
| 760 | | - |
|---|
| 761 | | -static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, |
|---|
| 762 | | - void *cpu_addr, dma_addr_t dma_addr, |
|---|
| 763 | | - size_t size, unsigned long attrs) |
|---|
| 764 | | -{ |
|---|
| 765 | | - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; |
|---|
| 766 | | - struct page *page = NULL; |
|---|
| 767 | | - struct vm_struct *area = find_vm_area(cpu_addr); |
|---|
| 768 | | - |
|---|
| 769 | | - if (area && area->pages) |
|---|
| 770 | | - return sg_alloc_table_from_pages(sgt, area->pages, count, 0, |
|---|
| 771 | | - size, GFP_KERNEL); |
|---|
| 772 | | - else if (!is_vmalloc_addr(cpu_addr)) |
|---|
| 773 | | - page = virt_to_page(cpu_addr); |
|---|
| 774 | | - else if (is_vmalloc_addr(cpu_addr)) |
|---|
| 775 | | - /* |
|---|
| 776 | | - * DMA_ATTR_FORCE_CONTIGUOUS and atomic pool allocations |
|---|
| 777 | | - * are always remapped, hence in the vmalloc space. |
|---|
| 778 | | - */ |
|---|
| 779 | | - page = vmalloc_to_page(cpu_addr); |
|---|
| 780 | | - |
|---|
| 781 | | - if (page) |
|---|
| 782 | | - return __swiotlb_get_sgtable_page(sgt, page, size); |
|---|
| 783 | | - return -ENXIO; |
|---|
| 784 | | -} |
|---|
| 785 | | - |
|---|
| 786 | | -static void __iommu_sync_single_for_cpu(struct device *dev, |
|---|
| 787 | | - dma_addr_t dev_addr, size_t size, |
|---|
| 788 | | - enum dma_data_direction dir) |
|---|
| 789 | | -{ |
|---|
| 790 | | - phys_addr_t phys; |
|---|
| 791 | | - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); |
|---|
| 792 | | - |
|---|
| 793 | | - if (!domain || iommu_is_iova_coherent(domain, dev_addr)) |
|---|
| 794 | | - return; |
|---|
| 795 | | - if (is_device_dma_coherent(dev)) |
|---|
| 796 | | - return; |
|---|
| 797 | | - phys = iommu_iova_to_phys(domain, dev_addr); |
|---|
| 798 | | - __dma_unmap_area(phys_to_virt(phys), size, dir); |
|---|
| 799 | | -} |
|---|
| 800 | | - |
|---|
| 801 | | -static void __iommu_sync_single_for_device(struct device *dev, |
|---|
| 802 | | - dma_addr_t dev_addr, size_t size, |
|---|
| 803 | | - enum dma_data_direction dir) |
|---|
| 804 | | -{ |
|---|
| 805 | | - phys_addr_t phys; |
|---|
| 806 | | - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); |
|---|
| 807 | | - |
|---|
| 808 | | - if (!domain || iommu_is_iova_coherent(domain, dev_addr)) |
|---|
| 809 | | - return; |
|---|
| 810 | | - if (is_device_dma_coherent(dev)) |
|---|
| 811 | | - return; |
|---|
| 812 | | - phys = iommu_iova_to_phys(domain, dev_addr); |
|---|
| 813 | | - __dma_map_area(phys_to_virt(phys), size, dir); |
|---|
| 814 | | -} |
|---|
| 815 | | - |
|---|
| 816 | | -static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, |
|---|
| 817 | | - unsigned long offset, size_t size, |
|---|
| 818 | | - enum dma_data_direction dir, |
|---|
| 819 | | - unsigned long attrs) |
|---|
| 820 | | -{ |
|---|
| 821 | | - bool coherent = is_dma_coherent(dev, attrs); |
|---|
| 822 | | - int prot = dma_info_to_prot(dir, coherent, attrs); |
|---|
| 823 | | - dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); |
|---|
| 824 | | - |
|---|
| 825 | | - if (!iommu_dma_mapping_error(dev, dev_addr) && |
|---|
| 826 | | - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 827 | | - __iommu_sync_single_for_device(dev, dev_addr, size, dir); |
|---|
| 828 | | - |
|---|
| 829 | | - return dev_addr; |
|---|
| 830 | | -} |
|---|
| 831 | | - |
|---|
| 832 | | -static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr, |
|---|
| 833 | | - size_t size, enum dma_data_direction dir, |
|---|
| 834 | | - unsigned long attrs) |
|---|
| 835 | | -{ |
|---|
| 836 | | - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 837 | | - __iommu_sync_single_for_cpu(dev, dev_addr, size, dir); |
|---|
| 838 | | - |
|---|
| 839 | | - iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs); |
|---|
| 840 | | -} |
|---|
| 841 | | - |
|---|
| 842 | | -static void __iommu_sync_sg_for_cpu(struct device *dev, |
|---|
| 843 | | - struct scatterlist *sgl, int nelems, |
|---|
| 844 | | - enum dma_data_direction dir) |
|---|
| 845 | | -{ |
|---|
| 846 | | - struct scatterlist *sg; |
|---|
| 847 | | - dma_addr_t iova = sg_dma_address(sgl); |
|---|
| 848 | | - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); |
|---|
| 849 | | - int i; |
|---|
| 850 | | - |
|---|
| 851 | | - if (!domain || iommu_is_iova_coherent(domain, iova)) |
|---|
| 852 | | - return; |
|---|
| 853 | | - if (is_device_dma_coherent(dev)) |
|---|
| 854 | | - return; |
|---|
| 855 | | - for_each_sg(sgl, sg, nelems, i) |
|---|
| 856 | | - __dma_unmap_area(sg_virt(sg), sg->length, dir); |
|---|
| 857 | | -} |
|---|
| 858 | | - |
|---|
| 859 | | -static void __iommu_sync_sg_for_device(struct device *dev, |
|---|
| 860 | | - struct scatterlist *sgl, int nelems, |
|---|
| 861 | | - enum dma_data_direction dir) |
|---|
| 862 | | -{ |
|---|
| 863 | | - struct scatterlist *sg; |
|---|
| 864 | | - dma_addr_t iova = sg_dma_address(sgl); |
|---|
| 865 | | - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); |
|---|
| 866 | | - int i; |
|---|
| 867 | | - |
|---|
| 868 | | - if (!domain || iommu_is_iova_coherent(domain, iova)) |
|---|
| 869 | | - return; |
|---|
| 870 | | - if (is_device_dma_coherent(dev)) |
|---|
| 871 | | - return; |
|---|
| 872 | | - for_each_sg(sgl, sg, nelems, i) |
|---|
| 873 | | - __dma_map_area(sg_virt(sg), sg->length, dir); |
|---|
| 874 | | -} |
|---|
| 875 | | - |
|---|
| 876 | | -static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, |
|---|
| 877 | | - int nelems, enum dma_data_direction dir, |
|---|
| 878 | | - unsigned long attrs) |
|---|
| 879 | | -{ |
|---|
| 880 | | - bool coherent = is_device_dma_coherent(dev); |
|---|
| 881 | | - |
|---|
| 882 | | - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 883 | | - __iommu_sync_sg_for_device(dev, sgl, nelems, dir); |
|---|
| 884 | | - |
|---|
| 885 | | - return iommu_dma_map_sg(dev, sgl, nelems, |
|---|
| 886 | | - dma_info_to_prot(dir, coherent, attrs)); |
|---|
| 887 | | -} |
|---|
| 888 | | - |
|---|
| 889 | | -static void __iommu_unmap_sg_attrs(struct device *dev, |
|---|
| 890 | | - struct scatterlist *sgl, int nelems, |
|---|
| 891 | | - enum dma_data_direction dir, |
|---|
| 892 | | - unsigned long attrs) |
|---|
| 893 | | -{ |
|---|
| 894 | | - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) |
|---|
| 895 | | - __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir); |
|---|
| 896 | | - |
|---|
| 897 | | - iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs); |
|---|
| 898 | | -} |
|---|
| 899 | | - |
|---|
| 900 | | -static const struct dma_map_ops iommu_dma_ops = { |
|---|
| 901 | | - .alloc = __iommu_alloc_attrs, |
|---|
| 902 | | - .free = __iommu_free_attrs, |
|---|
| 903 | | - .mmap = __iommu_mmap_attrs, |
|---|
| 904 | | - .get_sgtable = __iommu_get_sgtable, |
|---|
| 905 | | - .map_page = __iommu_map_page, |
|---|
| 906 | | - .unmap_page = __iommu_unmap_page, |
|---|
| 907 | | - .map_sg = __iommu_map_sg_attrs, |
|---|
| 908 | | - .unmap_sg = __iommu_unmap_sg_attrs, |
|---|
| 909 | | - .sync_single_for_cpu = __iommu_sync_single_for_cpu, |
|---|
| 910 | | - .sync_single_for_device = __iommu_sync_single_for_device, |
|---|
| 911 | | - .sync_sg_for_cpu = __iommu_sync_sg_for_cpu, |
|---|
| 912 | | - .sync_sg_for_device = __iommu_sync_sg_for_device, |
|---|
| 913 | | - .map_resource = iommu_dma_map_resource, |
|---|
| 914 | | - .unmap_resource = iommu_dma_unmap_resource, |
|---|
| 915 | | - .mapping_error = iommu_dma_mapping_error, |
|---|
| 916 | | -}; |
|---|
| 917 | | - |
|---|
| 918 | | -static int __init __iommu_dma_init(void) |
|---|
| 919 | | -{ |
|---|
| 920 | | - return iommu_dma_init(); |
|---|
| 921 | | -} |
|---|
| 922 | | -arch_initcall(__iommu_dma_init); |
|---|
| 923 | | - |
|---|
| 924 | | -static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, |
|---|
| 925 | | - const struct iommu_ops *ops) |
|---|
| 926 | | -{ |
|---|
| 927 | | - struct iommu_domain *domain; |
|---|
| 928 | | - |
|---|
| 929 | | - if (!ops) |
|---|
| 930 | | - return; |
|---|
| 931 | | - |
|---|
| 932 | | - /* |
|---|
| 933 | | - * The IOMMU core code allocates the default DMA domain, which the |
|---|
| 934 | | - * underlying IOMMU driver needs to support via the dma-iommu layer. |
|---|
| 935 | | - */ |
|---|
| 936 | | - domain = iommu_get_domain_for_dev(dev); |
|---|
| 937 | | - |
|---|
| 938 | | - if (!domain) |
|---|
| 939 | | - goto out_err; |
|---|
| 940 | | - |
|---|
| 941 | | - if (domain->type == IOMMU_DOMAIN_DMA) { |
|---|
| 942 | | - if (iommu_dma_init_domain(domain, dma_base, size, dev)) |
|---|
| 943 | | - goto out_err; |
|---|
| 944 | | - |
|---|
| 945 | | - dev->dma_ops = &iommu_dma_ops; |
|---|
| 946 | | - } |
|---|
| 947 | | - |
|---|
| 948 | | - return; |
|---|
| 949 | | - |
|---|
| 950 | | -out_err: |
|---|
| 951 | | - pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", |
|---|
| 952 | | - dev_name(dev)); |
|---|
| 953 | | -} |
|---|
| 954 | | - |
|---|
| 955 | 36 | void arch_teardown_dma_ops(struct device *dev) |
|---|
| 956 | 37 | { |
|---|
| 957 | 38 | dev->dma_ops = NULL; |
|---|
| 958 | 39 | } |
|---|
| 959 | | - |
|---|
| 960 | | -#else |
|---|
| 961 | | - |
|---|
| 962 | | -static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, |
|---|
| 963 | | - const struct iommu_ops *iommu) |
|---|
| 964 | | -{ } |
|---|
| 965 | | - |
|---|
| 966 | | -#endif /* CONFIG_IOMMU_DMA */ |
|---|
| 967 | | - |
|---|
| 968 | | -static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size); |
|---|
| 40 | +#endif |
|---|
| 969 | 41 | |
|---|
| 970 | 42 | void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, |
|---|
| 971 | 43 | const struct iommu_ops *iommu, bool coherent) |
|---|
| 972 | 44 | { |
|---|
| 973 | | - if (!dev->dma_ops) { |
|---|
| 974 | | - if (dev->removed_mem) |
|---|
| 975 | | - set_dma_ops(dev, &removed_dma_ops); |
|---|
| 976 | | - else |
|---|
| 977 | | - dev->dma_ops = &arm64_swiotlb_dma_ops; |
|---|
| 45 | + int cls = cache_line_size_of_cpu(); |
|---|
| 46 | + |
|---|
| 47 | + WARN_TAINT(!coherent && cls > ARCH_DMA_MINALIGN, |
|---|
| 48 | + TAINT_CPU_OUT_OF_SPEC, |
|---|
| 49 | + "%s %s: ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", |
|---|
| 50 | + dev_driver_string(dev), dev_name(dev), |
|---|
| 51 | + ARCH_DMA_MINALIGN, cls); |
|---|
| 52 | + |
|---|
| 53 | + dev->dma_coherent = coherent; |
|---|
| 54 | + if (iommu) { |
|---|
| 55 | + iommu_setup_dma_ops(dev, dma_base, size); |
|---|
| 56 | + trace_android_vh_iommu_setup_dma_ops(dev, dma_base, size); |
|---|
| 57 | + trace_android_rvh_iommu_setup_dma_ops(dev, dma_base, size); |
|---|
| 978 | 58 | } |
|---|
| 979 | 59 | |
|---|
| 980 | | - dev->archdata.dma_coherent = coherent; |
|---|
| 981 | | - if (of_parse_phandle(dev->of_node, "qcom,iommu-group", 0)) |
|---|
| 982 | | - arm_iommu_setup_dma_ops(dev, dma_base, size); |
|---|
| 983 | | - else |
|---|
| 984 | | - __iommu_setup_dma_ops(dev, dma_base, size, iommu); |
|---|
| 60 | + /* Allow vendor modules to opt-in for the 2454944 erratum workaround */ |
|---|
| 61 | + trace_android_rvh_setup_dma_ops(dev); |
|---|
| 985 | 62 | |
|---|
| 986 | 63 | #ifdef CONFIG_XEN |
|---|
| 987 | | - if (xen_initial_domain()) { |
|---|
| 988 | | - dev->archdata.dev_dma_ops = dev->dma_ops; |
|---|
| 989 | | - dev->dma_ops = xen_dma_ops; |
|---|
| 990 | | - } |
|---|
| 64 | + if (xen_initial_domain()) |
|---|
| 65 | + dev->dma_ops = &xen_swiotlb_dma_ops; |
|---|
| 991 | 66 | #endif |
|---|
| 992 | 67 | } |
|---|
| 993 | | -EXPORT_SYMBOL_GPL(arch_setup_dma_ops); |
|---|
| 994 | 68 | |
|---|
| 995 | | -#ifdef CONFIG_ARM64_DMA_USE_IOMMU |
|---|
| 996 | | - |
|---|
| 997 | | -/* guards initialization of default_domain->iova_cookie */ |
|---|
| 998 | | -static DEFINE_MUTEX(iommu_dma_init_mutex); |
|---|
| 999 | | - |
|---|
| 1000 | | -static int |
|---|
| 1001 | | -iommu_init_mapping(struct device *dev, struct dma_iommu_mapping *mapping) |
|---|
| 1002 | | -{ |
|---|
| 1003 | | - struct iommu_domain *domain = mapping->domain; |
|---|
| 1004 | | - dma_addr_t dma_base = mapping->base; |
|---|
| 1005 | | - u64 size = mapping->bits << PAGE_SHIFT; |
|---|
| 1006 | | - int ret; |
|---|
| 1007 | | - bool own_cookie; |
|---|
| 1008 | | - |
|---|
| 1009 | | - /* |
|---|
| 1010 | | - * if own_cookie is false, then we are sharing the iova_cookie with |
|---|
| 1011 | | - * another driver, and should not free it on error. Cleanup will be |
|---|
| 1012 | | - * done when the iommu_domain is freed. |
|---|
| 1013 | | - */ |
|---|
| 1014 | | - own_cookie = !domain->iova_cookie; |
|---|
| 1015 | | - |
|---|
| 1016 | | - if (own_cookie) { |
|---|
| 1017 | | - ret = iommu_get_dma_cookie(domain); |
|---|
| 1018 | | - if (ret) { |
|---|
| 1019 | | - dev_err(dev, "iommu_get_dma_cookie failed: %d\n", ret); |
|---|
| 1020 | | - return ret; |
|---|
| 1021 | | - } |
|---|
| 1022 | | - } |
|---|
| 1023 | | - |
|---|
| 1024 | | - ret = iommu_dma_init_domain(domain, dma_base, size, dev); |
|---|
| 1025 | | - if (ret) { |
|---|
| 1026 | | - dev_err(dev, "iommu_dma_init_domain failed: %d\n", ret); |
|---|
| 1027 | | - if (own_cookie) |
|---|
| 1028 | | - iommu_put_dma_cookie(domain); |
|---|
| 1029 | | - return ret; |
|---|
| 1030 | | - } |
|---|
| 1031 | | - |
|---|
| 1032 | | - mapping->ops = &iommu_dma_ops; |
|---|
| 1033 | | - return 0; |
|---|
| 1034 | | -} |
|---|
| 1035 | | - |
|---|
| 1036 | | -static int arm_iommu_get_dma_cookie(struct device *dev, |
|---|
| 1037 | | - struct dma_iommu_mapping *mapping) |
|---|
| 1038 | | -{ |
|---|
| 1039 | | - int s1_bypass = 0, is_fast = 0; |
|---|
| 1040 | | - int err = 0; |
|---|
| 1041 | | - |
|---|
| 1042 | | - mutex_lock(&iommu_dma_init_mutex); |
|---|
| 1043 | | - |
|---|
| 1044 | | - iommu_domain_get_attr(mapping->domain, DOMAIN_ATTR_S1_BYPASS, |
|---|
| 1045 | | - &s1_bypass); |
|---|
| 1046 | | - iommu_domain_get_attr(mapping->domain, DOMAIN_ATTR_FAST, &is_fast); |
|---|
| 1047 | | - |
|---|
| 1048 | | - if (s1_bypass) |
|---|
| 1049 | | - mapping->ops = &arm64_swiotlb_dma_ops; |
|---|
| 1050 | | - else if (is_fast) |
|---|
| 1051 | | - err = fast_smmu_init_mapping(dev, mapping); |
|---|
| 1052 | | - else |
|---|
| 1053 | | - err = iommu_init_mapping(dev, mapping); |
|---|
| 1054 | | - |
|---|
| 1055 | | - mutex_unlock(&iommu_dma_init_mutex); |
|---|
| 1056 | | - return err; |
|---|
| 1057 | | -} |
|---|
| 1058 | | - |
|---|
| 1059 | | -/* |
|---|
| 1060 | | - * Checks for "qcom,iommu-dma-addr-pool" property. |
|---|
| 1061 | | - * If not present, leaves dma_addr and dma_size unmodified. |
|---|
| 1062 | | - */ |
|---|
| 1063 | | -static void arm_iommu_get_dma_window(struct device *dev, u64 *dma_addr, |
|---|
| 1064 | | - u64 *dma_size) |
|---|
| 1065 | | -{ |
|---|
| 1066 | | - struct device_node *np; |
|---|
| 1067 | | - int naddr, nsize, len; |
|---|
| 1068 | | - const __be32 *ranges; |
|---|
| 1069 | | - |
|---|
| 1070 | | - if (!dev->of_node) |
|---|
| 1071 | | - return; |
|---|
| 1072 | | - |
|---|
| 1073 | | - np = of_parse_phandle(dev->of_node, "qcom,iommu-group", 0); |
|---|
| 1074 | | - if (!np) |
|---|
| 1075 | | - np = dev->of_node; |
|---|
| 1076 | | - |
|---|
| 1077 | | - ranges = of_get_property(np, "qcom,iommu-dma-addr-pool", &len); |
|---|
| 1078 | | - if (!ranges) |
|---|
| 1079 | | - return; |
|---|
| 1080 | | - |
|---|
| 1081 | | - len /= sizeof(u32); |
|---|
| 1082 | | - naddr = of_n_addr_cells(np); |
|---|
| 1083 | | - nsize = of_n_size_cells(np); |
|---|
| 1084 | | - if (len < naddr + nsize) { |
|---|
| 1085 | | - dev_err(dev, "Invalid length for qcom,iommu-dma-addr-pool, expected %d cells\n", |
|---|
| 1086 | | - naddr + nsize); |
|---|
| 1087 | | - return; |
|---|
| 1088 | | - } |
|---|
| 1089 | | - if (naddr == 0 || nsize == 0) { |
|---|
| 1090 | | - dev_err(dev, "Invalid #address-cells %d or #size-cells %d\n", |
|---|
| 1091 | | - naddr, nsize); |
|---|
| 1092 | | - return; |
|---|
| 1093 | | - } |
|---|
| 1094 | | - |
|---|
| 1095 | | - *dma_addr = of_read_number(ranges, naddr); |
|---|
| 1096 | | - *dma_size = of_read_number(ranges + naddr, nsize); |
|---|
| 1097 | | -} |
|---|
| 1098 | | - |
|---|
| 1099 | | -static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size) |
|---|
| 1100 | | -{ |
|---|
| 1101 | | - struct iommu_domain *domain; |
|---|
| 1102 | | - struct iommu_group *group; |
|---|
| 1103 | | - struct dma_iommu_mapping mapping = {0}; |
|---|
| 1104 | | - |
|---|
| 1105 | | - group = dev->iommu_group; |
|---|
| 1106 | | - if (!group) |
|---|
| 1107 | | - return; |
|---|
| 1108 | | - |
|---|
| 1109 | | - arm_iommu_get_dma_window(dev, &dma_base, &size); |
|---|
| 1110 | | - |
|---|
| 1111 | | - domain = iommu_get_domain_for_dev(dev); |
|---|
| 1112 | | - if (!domain) |
|---|
| 1113 | | - return; |
|---|
| 1114 | | - |
|---|
| 1115 | | - /* Allow iommu-debug to call arch_setup_dma_ops to reconfigure itself */ |
|---|
| 1116 | | - if (domain->type != IOMMU_DOMAIN_DMA && |
|---|
| 1117 | | - !of_device_is_compatible(dev->of_node, "iommu-debug-test")) { |
|---|
| 1118 | | - dev_err(dev, "Invalid iommu domain type!\n"); |
|---|
| 1119 | | - return; |
|---|
| 1120 | | - } |
|---|
| 1121 | | - |
|---|
| 1122 | | - mapping.base = dma_base; |
|---|
| 1123 | | - mapping.bits = size >> PAGE_SHIFT; |
|---|
| 1124 | | - mapping.domain = domain; |
|---|
| 1125 | | - |
|---|
| 1126 | | - if (arm_iommu_get_dma_cookie(dev, &mapping)) { |
|---|
| 1127 | | - dev_err(dev, "Failed to get dma cookie\n"); |
|---|
| 1128 | | - return; |
|---|
| 1129 | | - } |
|---|
| 1130 | | - |
|---|
| 1131 | | - set_dma_ops(dev, mapping.ops); |
|---|
| 1132 | | -} |
|---|
| 1133 | | - |
|---|
| 1134 | | -#else /*!CONFIG_ARM64_DMA_USE_IOMMU */ |
|---|
| 1135 | | - |
|---|
| 1136 | | -static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size) |
|---|
| 1137 | | -{ |
|---|
| 1138 | | -} |
|---|
| 69 | +#ifdef CONFIG_NO_GKI |
|---|
| 70 | +EXPORT_SYMBOL(__dma_map_area); |
|---|
| 71 | +EXPORT_SYMBOL(__dma_unmap_area); |
|---|
| 1139 | 72 | #endif |
|---|