b.liu | e958203 | 2025-04-17 19:18:16 +0800 | [diff] [blame] | 1 | // SPDX-License-Identifier: GPL-2.0-only |
| 2 | /* |
| 3 | * VDSO implementations. |
| 4 | * |
| 5 | * Copyright (C) 2012 ARM Limited |
| 6 | * |
| 7 | * Author: Will Deacon <will.deacon@arm.com> |
| 8 | */ |
| 9 | |
| 10 | #include <linux/cache.h> |
| 11 | #include <linux/clocksource.h> |
| 12 | #include <linux/elf.h> |
| 13 | #include <linux/err.h> |
| 14 | #include <linux/errno.h> |
| 15 | #include <linux/gfp.h> |
| 16 | #include <linux/kernel.h> |
| 17 | #include <linux/mm.h> |
| 18 | #include <linux/sched.h> |
| 19 | #include <linux/signal.h> |
| 20 | #include <linux/slab.h> |
| 21 | #include <linux/timekeeper_internal.h> |
| 22 | #include <linux/vmalloc.h> |
| 23 | #include <vdso/datapage.h> |
| 24 | #include <vdso/helpers.h> |
| 25 | #include <vdso/vsyscall.h> |
| 26 | |
| 27 | #include <asm/cacheflush.h> |
| 28 | #include <asm/signal32.h> |
| 29 | #include <asm/vdso.h> |
| 30 | |
| 31 | extern char vdso_start[], vdso_end[]; |
| 32 | #ifdef CONFIG_COMPAT_VDSO |
| 33 | extern char vdso32_start[], vdso32_end[]; |
| 34 | #endif /* CONFIG_COMPAT_VDSO */ |
| 35 | |
| 36 | /* vdso_lookup arch_index */ |
| 37 | enum arch_vdso_type { |
| 38 | ARM64_VDSO = 0, |
| 39 | #ifdef CONFIG_COMPAT_VDSO |
| 40 | ARM64_VDSO32 = 1, |
| 41 | #endif /* CONFIG_COMPAT_VDSO */ |
| 42 | }; |
| 43 | #ifdef CONFIG_COMPAT_VDSO |
| 44 | #define VDSO_TYPES (ARM64_VDSO32 + 1) |
| 45 | #else |
| 46 | #define VDSO_TYPES (ARM64_VDSO + 1) |
| 47 | #endif /* CONFIG_COMPAT_VDSO */ |
| 48 | |
| 49 | struct __vdso_abi { |
| 50 | const char *name; |
| 51 | const char *vdso_code_start; |
| 52 | const char *vdso_code_end; |
| 53 | unsigned long vdso_pages; |
| 54 | /* Data Mapping */ |
| 55 | struct vm_special_mapping *dm; |
| 56 | /* Code Mapping */ |
| 57 | struct vm_special_mapping *cm; |
| 58 | }; |
| 59 | |
| 60 | static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = { |
| 61 | { |
| 62 | .name = "vdso", |
| 63 | .vdso_code_start = vdso_start, |
| 64 | .vdso_code_end = vdso_end, |
| 65 | }, |
| 66 | #ifdef CONFIG_COMPAT_VDSO |
| 67 | { |
| 68 | .name = "vdso32", |
| 69 | .vdso_code_start = vdso32_start, |
| 70 | .vdso_code_end = vdso32_end, |
| 71 | }, |
| 72 | #endif /* CONFIG_COMPAT_VDSO */ |
| 73 | }; |
| 74 | |
| 75 | /* |
| 76 | * The vDSO data page. |
| 77 | */ |
| 78 | static union { |
| 79 | struct vdso_data data[CS_BASES]; |
| 80 | u8 page[PAGE_SIZE]; |
| 81 | } vdso_data_store __page_aligned_data; |
| 82 | struct vdso_data *vdso_data = vdso_data_store.data; |
| 83 | |
| 84 | static int __vdso_remap(enum arch_vdso_type arch_index, |
| 85 | const struct vm_special_mapping *sm, |
| 86 | struct vm_area_struct *new_vma) |
| 87 | { |
| 88 | unsigned long new_size = new_vma->vm_end - new_vma->vm_start; |
| 89 | unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end - |
| 90 | vdso_lookup[arch_index].vdso_code_start; |
| 91 | |
| 92 | if (vdso_size != new_size) |
| 93 | return -EINVAL; |
| 94 | |
| 95 | current->mm->context.vdso = (void *)new_vma->vm_start; |
| 96 | |
| 97 | return 0; |
| 98 | } |
| 99 | |
| 100 | static int __vdso_init(enum arch_vdso_type arch_index) |
| 101 | { |
| 102 | int i; |
| 103 | struct page **vdso_pagelist; |
| 104 | unsigned long pfn; |
| 105 | |
| 106 | if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) { |
| 107 | pr_err("vDSO is not a valid ELF object!\n"); |
| 108 | return -EINVAL; |
| 109 | } |
| 110 | |
| 111 | vdso_lookup[arch_index].vdso_pages = ( |
| 112 | vdso_lookup[arch_index].vdso_code_end - |
| 113 | vdso_lookup[arch_index].vdso_code_start) >> |
| 114 | PAGE_SHIFT; |
| 115 | |
| 116 | /* Allocate the vDSO pagelist, plus a page for the data. */ |
| 117 | vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1, |
| 118 | sizeof(struct page *), |
| 119 | GFP_KERNEL); |
| 120 | if (vdso_pagelist == NULL) |
| 121 | return -ENOMEM; |
| 122 | |
| 123 | /* Grab the vDSO data page. */ |
| 124 | vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data)); |
| 125 | |
| 126 | |
| 127 | /* Grab the vDSO code pages. */ |
| 128 | pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start); |
| 129 | |
| 130 | for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++) |
| 131 | vdso_pagelist[i + 1] = pfn_to_page(pfn + i); |
| 132 | |
| 133 | vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0]; |
| 134 | vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1]; |
| 135 | |
| 136 | return 0; |
| 137 | } |
| 138 | |
| 139 | static int __setup_additional_pages(enum arch_vdso_type arch_index, |
| 140 | struct mm_struct *mm, |
| 141 | struct linux_binprm *bprm, |
| 142 | int uses_interp) |
| 143 | { |
| 144 | unsigned long vdso_base, vdso_text_len, vdso_mapping_len; |
| 145 | void *ret; |
| 146 | |
| 147 | vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT; |
| 148 | /* Be sure to map the data page */ |
| 149 | vdso_mapping_len = vdso_text_len + PAGE_SIZE; |
| 150 | |
| 151 | vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); |
| 152 | if (IS_ERR_VALUE(vdso_base)) { |
| 153 | ret = ERR_PTR(vdso_base); |
| 154 | goto up_fail; |
| 155 | } |
| 156 | |
| 157 | ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE, |
| 158 | VM_READ|VM_MAYREAD, |
| 159 | vdso_lookup[arch_index].dm); |
| 160 | if (IS_ERR(ret)) |
| 161 | goto up_fail; |
| 162 | |
| 163 | vdso_base += PAGE_SIZE; |
| 164 | mm->context.vdso = (void *)vdso_base; |
| 165 | ret = _install_special_mapping(mm, vdso_base, vdso_text_len, |
| 166 | VM_READ|VM_EXEC| |
| 167 | VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, |
| 168 | vdso_lookup[arch_index].cm); |
| 169 | if (IS_ERR(ret)) |
| 170 | goto up_fail; |
| 171 | |
| 172 | return 0; |
| 173 | |
| 174 | up_fail: |
| 175 | mm->context.vdso = NULL; |
| 176 | return PTR_ERR(ret); |
| 177 | } |
| 178 | |
| 179 | #ifdef CONFIG_COMPAT |
| 180 | /* |
| 181 | * Create and map the vectors page for AArch32 tasks. |
| 182 | */ |
| 183 | #ifdef CONFIG_COMPAT_VDSO |
| 184 | static int aarch32_vdso_mremap(const struct vm_special_mapping *sm, |
| 185 | struct vm_area_struct *new_vma) |
| 186 | { |
| 187 | return __vdso_remap(ARM64_VDSO32, sm, new_vma); |
| 188 | } |
| 189 | #endif /* CONFIG_COMPAT_VDSO */ |
| 190 | |
| 191 | /* |
| 192 | * aarch32_vdso_pages: |
| 193 | * 0 - kuser helpers |
| 194 | * 1 - sigreturn code |
| 195 | * or (CONFIG_COMPAT_VDSO): |
| 196 | * 0 - kuser helpers |
| 197 | * 1 - vdso data |
| 198 | * 2 - vdso code |
| 199 | */ |
| 200 | #define C_VECTORS 0 |
| 201 | #ifdef CONFIG_COMPAT_VDSO |
| 202 | #define C_VVAR 1 |
| 203 | #define C_VDSO 2 |
| 204 | #define C_PAGES (C_VDSO + 1) |
| 205 | #else |
| 206 | #define C_SIGPAGE 1 |
| 207 | #define C_PAGES (C_SIGPAGE + 1) |
| 208 | #endif /* CONFIG_COMPAT_VDSO */ |
| 209 | static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init; |
| 210 | static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = { |
| 211 | { |
| 212 | .name = "[vectors]", /* ABI */ |
| 213 | .pages = &aarch32_vdso_pages[C_VECTORS], |
| 214 | }, |
| 215 | #ifdef CONFIG_COMPAT_VDSO |
| 216 | { |
| 217 | .name = "[vvar]", |
| 218 | }, |
| 219 | { |
| 220 | .name = "[vdso]", |
| 221 | .mremap = aarch32_vdso_mremap, |
| 222 | }, |
| 223 | #else |
| 224 | { |
| 225 | .name = "[sigpage]", /* ABI */ |
| 226 | .pages = &aarch32_vdso_pages[C_SIGPAGE], |
| 227 | }, |
| 228 | #endif /* CONFIG_COMPAT_VDSO */ |
| 229 | }; |
| 230 | |
| 231 | static int aarch32_alloc_kuser_vdso_page(void) |
| 232 | { |
| 233 | extern char __kuser_helper_start[], __kuser_helper_end[]; |
| 234 | int kuser_sz = __kuser_helper_end - __kuser_helper_start; |
| 235 | unsigned long vdso_page; |
| 236 | |
| 237 | if (!IS_ENABLED(CONFIG_KUSER_HELPERS)) |
| 238 | return 0; |
| 239 | |
| 240 | vdso_page = get_zeroed_page(GFP_ATOMIC); |
| 241 | if (!vdso_page) |
| 242 | return -ENOMEM; |
| 243 | |
| 244 | memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, |
| 245 | kuser_sz); |
| 246 | aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page); |
| 247 | flush_dcache_page(aarch32_vdso_pages[C_VECTORS]); |
| 248 | return 0; |
| 249 | } |
| 250 | |
| 251 | #ifdef CONFIG_COMPAT_VDSO |
| 252 | static int __aarch32_alloc_vdso_pages(void) |
| 253 | { |
| 254 | int ret; |
| 255 | |
| 256 | vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR]; |
| 257 | vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO]; |
| 258 | |
| 259 | ret = __vdso_init(ARM64_VDSO32); |
| 260 | if (ret) |
| 261 | return ret; |
| 262 | |
| 263 | return aarch32_alloc_kuser_vdso_page(); |
| 264 | } |
| 265 | #else |
| 266 | static int __aarch32_alloc_vdso_pages(void) |
| 267 | { |
| 268 | extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; |
| 269 | int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; |
| 270 | unsigned long sigpage; |
| 271 | int ret; |
| 272 | |
| 273 | sigpage = get_zeroed_page(GFP_ATOMIC); |
| 274 | if (!sigpage) |
| 275 | return -ENOMEM; |
| 276 | |
| 277 | memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz); |
| 278 | aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage); |
| 279 | flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]); |
| 280 | |
| 281 | ret = aarch32_alloc_kuser_vdso_page(); |
| 282 | if (ret) |
| 283 | free_page(sigpage); |
| 284 | |
| 285 | return ret; |
| 286 | } |
| 287 | #endif /* CONFIG_COMPAT_VDSO */ |
| 288 | |
| 289 | static int __init aarch32_alloc_vdso_pages(void) |
| 290 | { |
| 291 | return __aarch32_alloc_vdso_pages(); |
| 292 | } |
| 293 | arch_initcall(aarch32_alloc_vdso_pages); |
| 294 | |
| 295 | static int aarch32_kuser_helpers_setup(struct mm_struct *mm) |
| 296 | { |
| 297 | void *ret; |
| 298 | |
| 299 | if (!IS_ENABLED(CONFIG_KUSER_HELPERS)) |
| 300 | return 0; |
| 301 | |
| 302 | /* |
| 303 | * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's |
| 304 | * not safe to CoW the page containing the CPU exception vectors. |
| 305 | */ |
| 306 | ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE, |
| 307 | VM_READ | VM_EXEC | |
| 308 | VM_MAYREAD | VM_MAYEXEC, |
| 309 | &aarch32_vdso_spec[C_VECTORS]); |
| 310 | |
| 311 | return PTR_ERR_OR_ZERO(ret); |
| 312 | } |
| 313 | |
| 314 | #ifndef CONFIG_COMPAT_VDSO |
| 315 | static int aarch32_sigreturn_setup(struct mm_struct *mm) |
| 316 | { |
| 317 | unsigned long addr; |
| 318 | void *ret; |
| 319 | |
| 320 | addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0); |
| 321 | if (IS_ERR_VALUE(addr)) { |
| 322 | ret = ERR_PTR(addr); |
| 323 | goto out; |
| 324 | } |
| 325 | |
| 326 | /* |
| 327 | * VM_MAYWRITE is required to allow gdb to Copy-on-Write and |
| 328 | * set breakpoints. |
| 329 | */ |
| 330 | ret = _install_special_mapping(mm, addr, PAGE_SIZE, |
| 331 | VM_READ | VM_EXEC | VM_MAYREAD | |
| 332 | VM_MAYWRITE | VM_MAYEXEC, |
| 333 | &aarch32_vdso_spec[C_SIGPAGE]); |
| 334 | if (IS_ERR(ret)) |
| 335 | goto out; |
| 336 | |
| 337 | mm->context.vdso = (void *)addr; |
| 338 | |
| 339 | out: |
| 340 | return PTR_ERR_OR_ZERO(ret); |
| 341 | } |
| 342 | #endif /* !CONFIG_COMPAT_VDSO */ |
| 343 | |
| 344 | int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) |
| 345 | { |
| 346 | struct mm_struct *mm = current->mm; |
| 347 | int ret; |
| 348 | |
| 349 | if (down_write_killable(&mm->mmap_sem)) |
| 350 | return -EINTR; |
| 351 | |
| 352 | ret = aarch32_kuser_helpers_setup(mm); |
| 353 | if (ret) |
| 354 | goto out; |
| 355 | |
| 356 | #ifdef CONFIG_COMPAT_VDSO |
| 357 | ret = __setup_additional_pages(ARM64_VDSO32, |
| 358 | mm, |
| 359 | bprm, |
| 360 | uses_interp); |
| 361 | #else |
| 362 | ret = aarch32_sigreturn_setup(mm); |
| 363 | #endif /* CONFIG_COMPAT_VDSO */ |
| 364 | |
| 365 | out: |
| 366 | up_write(&mm->mmap_sem); |
| 367 | return ret; |
| 368 | } |
| 369 | #endif /* CONFIG_COMPAT */ |
| 370 | |
| 371 | static int vdso_mremap(const struct vm_special_mapping *sm, |
| 372 | struct vm_area_struct *new_vma) |
| 373 | { |
| 374 | return __vdso_remap(ARM64_VDSO, sm, new_vma); |
| 375 | } |
| 376 | |
| 377 | /* |
| 378 | * aarch64_vdso_pages: |
| 379 | * 0 - vvar |
| 380 | * 1 - vdso |
| 381 | */ |
| 382 | #define A_VVAR 0 |
| 383 | #define A_VDSO 1 |
| 384 | #define A_PAGES (A_VDSO + 1) |
| 385 | static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = { |
| 386 | { |
| 387 | .name = "[vvar]", |
| 388 | }, |
| 389 | { |
| 390 | .name = "[vdso]", |
| 391 | .mremap = vdso_mremap, |
| 392 | }, |
| 393 | }; |
| 394 | |
| 395 | static int __init vdso_init(void) |
| 396 | { |
| 397 | vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR]; |
| 398 | vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO]; |
| 399 | |
| 400 | return __vdso_init(ARM64_VDSO); |
| 401 | } |
| 402 | arch_initcall(vdso_init); |
| 403 | |
| 404 | int arch_setup_additional_pages(struct linux_binprm *bprm, |
| 405 | int uses_interp) |
| 406 | { |
| 407 | struct mm_struct *mm = current->mm; |
| 408 | int ret; |
| 409 | |
| 410 | if (down_write_killable(&mm->mmap_sem)) |
| 411 | return -EINTR; |
| 412 | |
| 413 | ret = __setup_additional_pages(ARM64_VDSO, |
| 414 | mm, |
| 415 | bprm, |
| 416 | uses_interp); |
| 417 | |
| 418 | up_write(&mm->mmap_sem); |
| 419 | |
| 420 | return ret; |
| 421 | } |