| Russell King | d111e8f | 2006-09-27 15:27:33 +0100 | [diff] [blame] | 1 | /* | 
|  | 2 | *  linux/arch/arm/mm/mmu.c | 
|  | 3 | * | 
|  | 4 | *  Copyright (C) 1995-2005 Russell King | 
|  | 5 | * | 
|  | 6 | * This program is free software; you can redistribute it and/or modify | 
|  | 7 | * it under the terms of the GNU General Public License version 2 as | 
|  | 8 | * published by the Free Software Foundation. | 
|  | 9 | */ | 
| Russell King | ae8f154 | 2006-09-27 15:38:34 +0100 | [diff] [blame] | 10 | #include <linux/module.h> | 
| Russell King | d111e8f | 2006-09-27 15:27:33 +0100 | [diff] [blame] | 11 | #include <linux/kernel.h> | 
|  | 12 | #include <linux/errno.h> | 
|  | 13 | #include <linux/init.h> | 
|  | 14 | #include <linux/bootmem.h> | 
|  | 15 | #include <linux/mman.h> | 
|  | 16 | #include <linux/nodemask.h> | 
|  | 17 |  | 
|  | 18 | #include <asm/mach-types.h> | 
|  | 19 | #include <asm/setup.h> | 
|  | 20 | #include <asm/sizes.h> | 
|  | 21 | #include <asm/tlb.h> | 
|  | 22 |  | 
|  | 23 | #include <asm/mach/arch.h> | 
|  | 24 | #include <asm/mach/map.h> | 
|  | 25 |  | 
|  | 26 | #include "mm.h" | 
|  | 27 |  | 
|  | 28 | DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); | 
|  | 29 |  | 
| Russell King | 6ae5a6e | 2006-09-30 10:50:05 +0100 | [diff] [blame] | 30 | extern void _stext, _etext, __data_start, _end; | 
| Russell King | d111e8f | 2006-09-27 15:27:33 +0100 | [diff] [blame] | 31 | extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; | 
|  | 32 |  | 
|  | 33 | /* | 
|  | 34 | * empty_zero_page is a special page that is used for | 
|  | 35 | * zero-initialized data and COW. | 
|  | 36 | */ | 
|  | 37 | struct page *empty_zero_page; | 
|  | 38 |  | 
|  | 39 | /* | 
|  | 40 | * The pmd table for the upper-most set of pages. | 
|  | 41 | */ | 
|  | 42 | pmd_t *top_pmd; | 
|  | 43 |  | 
| Russell King | ae8f154 | 2006-09-27 15:38:34 +0100 | [diff] [blame] | 44 | #define CPOLICY_UNCACHED	0 | 
|  | 45 | #define CPOLICY_BUFFERED	1 | 
|  | 46 | #define CPOLICY_WRITETHROUGH	2 | 
|  | 47 | #define CPOLICY_WRITEBACK	3 | 
|  | 48 | #define CPOLICY_WRITEALLOC	4 | 
|  | 49 |  | 
|  | 50 | static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK; | 
|  | 51 | static unsigned int ecc_mask __initdata = 0; | 
|  | 52 | pgprot_t pgprot_kernel; | 
|  | 53 |  | 
|  | 54 | EXPORT_SYMBOL(pgprot_kernel); | 
|  | 55 |  | 
|  | 56 | struct cachepolicy { | 
|  | 57 | const char	policy[16]; | 
|  | 58 | unsigned int	cr_mask; | 
|  | 59 | unsigned int	pmd; | 
|  | 60 | unsigned int	pte; | 
|  | 61 | }; | 
|  | 62 |  | 
|  | 63 | static struct cachepolicy cache_policies[] __initdata = { | 
|  | 64 | { | 
|  | 65 | .policy		= "uncached", | 
|  | 66 | .cr_mask	= CR_W|CR_C, | 
|  | 67 | .pmd		= PMD_SECT_UNCACHED, | 
|  | 68 | .pte		= 0, | 
|  | 69 | }, { | 
|  | 70 | .policy		= "buffered", | 
|  | 71 | .cr_mask	= CR_C, | 
|  | 72 | .pmd		= PMD_SECT_BUFFERED, | 
|  | 73 | .pte		= PTE_BUFFERABLE, | 
|  | 74 | }, { | 
|  | 75 | .policy		= "writethrough", | 
|  | 76 | .cr_mask	= 0, | 
|  | 77 | .pmd		= PMD_SECT_WT, | 
|  | 78 | .pte		= PTE_CACHEABLE, | 
|  | 79 | }, { | 
|  | 80 | .policy		= "writeback", | 
|  | 81 | .cr_mask	= 0, | 
|  | 82 | .pmd		= PMD_SECT_WB, | 
|  | 83 | .pte		= PTE_BUFFERABLE|PTE_CACHEABLE, | 
|  | 84 | }, { | 
|  | 85 | .policy		= "writealloc", | 
|  | 86 | .cr_mask	= 0, | 
|  | 87 | .pmd		= PMD_SECT_WBWA, | 
|  | 88 | .pte		= PTE_BUFFERABLE|PTE_CACHEABLE, | 
|  | 89 | } | 
|  | 90 | }; | 
|  | 91 |  | 
|  | 92 | /* | 
|  | 93 | * These are useful for identifing cache coherency | 
|  | 94 | * problems by allowing the cache or the cache and | 
|  | 95 | * writebuffer to be turned off.  (Note: the write | 
|  | 96 | * buffer should not be on and the cache off). | 
|  | 97 | */ | 
|  | 98 | static void __init early_cachepolicy(char **p) | 
|  | 99 | { | 
|  | 100 | int i; | 
|  | 101 |  | 
|  | 102 | for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { | 
|  | 103 | int len = strlen(cache_policies[i].policy); | 
|  | 104 |  | 
|  | 105 | if (memcmp(*p, cache_policies[i].policy, len) == 0) { | 
|  | 106 | cachepolicy = i; | 
|  | 107 | cr_alignment &= ~cache_policies[i].cr_mask; | 
|  | 108 | cr_no_alignment &= ~cache_policies[i].cr_mask; | 
|  | 109 | *p += len; | 
|  | 110 | break; | 
|  | 111 | } | 
|  | 112 | } | 
|  | 113 | if (i == ARRAY_SIZE(cache_policies)) | 
|  | 114 | printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n"); | 
|  | 115 | flush_cache_all(); | 
|  | 116 | set_cr(cr_alignment); | 
|  | 117 | } | 
|  | 118 | __early_param("cachepolicy=", early_cachepolicy); | 
|  | 119 |  | 
|  | 120 | static void __init early_nocache(char **__unused) | 
|  | 121 | { | 
|  | 122 | char *p = "buffered"; | 
|  | 123 | printk(KERN_WARNING "nocache is deprecated; use cachepolicy=%s\n", p); | 
|  | 124 | early_cachepolicy(&p); | 
|  | 125 | } | 
|  | 126 | __early_param("nocache", early_nocache); | 
|  | 127 |  | 
|  | 128 | static void __init early_nowrite(char **__unused) | 
|  | 129 | { | 
|  | 130 | char *p = "uncached"; | 
|  | 131 | printk(KERN_WARNING "nowb is deprecated; use cachepolicy=%s\n", p); | 
|  | 132 | early_cachepolicy(&p); | 
|  | 133 | } | 
|  | 134 | __early_param("nowb", early_nowrite); | 
|  | 135 |  | 
|  | 136 | static void __init early_ecc(char **p) | 
|  | 137 | { | 
|  | 138 | if (memcmp(*p, "on", 2) == 0) { | 
|  | 139 | ecc_mask = PMD_PROTECTION; | 
|  | 140 | *p += 2; | 
|  | 141 | } else if (memcmp(*p, "off", 3) == 0) { | 
|  | 142 | ecc_mask = 0; | 
|  | 143 | *p += 3; | 
|  | 144 | } | 
|  | 145 | } | 
|  | 146 | __early_param("ecc=", early_ecc); | 
|  | 147 |  | 
|  | 148 | static int __init noalign_setup(char *__unused) | 
|  | 149 | { | 
|  | 150 | cr_alignment &= ~CR_A; | 
|  | 151 | cr_no_alignment &= ~CR_A; | 
|  | 152 | set_cr(cr_alignment); | 
|  | 153 | return 1; | 
|  | 154 | } | 
|  | 155 | __setup("noalign", noalign_setup); | 
|  | 156 |  | 
|  | 157 | struct mem_types { | 
|  | 158 | unsigned int	prot_pte; | 
|  | 159 | unsigned int	prot_l1; | 
|  | 160 | unsigned int	prot_sect; | 
|  | 161 | unsigned int	domain; | 
|  | 162 | }; | 
|  | 163 |  | 
|  | 164 | static struct mem_types mem_types[] __initdata = { | 
|  | 165 | [MT_DEVICE] = { | 
|  | 166 | .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | | 
|  | 167 | L_PTE_WRITE, | 
|  | 168 | .prot_l1   = PMD_TYPE_TABLE, | 
|  | 169 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4 | PMD_SECT_UNCACHED | | 
|  | 170 | PMD_SECT_AP_WRITE, | 
|  | 171 | .domain    = DOMAIN_IO, | 
|  | 172 | }, | 
|  | 173 | [MT_CACHECLEAN] = { | 
|  | 174 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4, | 
|  | 175 | .domain    = DOMAIN_KERNEL, | 
|  | 176 | }, | 
|  | 177 | [MT_MINICLEAN] = { | 
|  | 178 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4 | PMD_SECT_MINICACHE, | 
|  | 179 | .domain    = DOMAIN_KERNEL, | 
|  | 180 | }, | 
|  | 181 | [MT_LOW_VECTORS] = { | 
|  | 182 | .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | | 
|  | 183 | L_PTE_EXEC, | 
|  | 184 | .prot_l1   = PMD_TYPE_TABLE, | 
|  | 185 | .domain    = DOMAIN_USER, | 
|  | 186 | }, | 
|  | 187 | [MT_HIGH_VECTORS] = { | 
|  | 188 | .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | | 
|  | 189 | L_PTE_USER | L_PTE_EXEC, | 
|  | 190 | .prot_l1   = PMD_TYPE_TABLE, | 
|  | 191 | .domain    = DOMAIN_USER, | 
|  | 192 | }, | 
|  | 193 | [MT_MEMORY] = { | 
|  | 194 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4 | PMD_SECT_AP_WRITE, | 
|  | 195 | .domain    = DOMAIN_KERNEL, | 
|  | 196 | }, | 
|  | 197 | [MT_ROM] = { | 
|  | 198 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4, | 
|  | 199 | .domain    = DOMAIN_KERNEL, | 
|  | 200 | }, | 
|  | 201 | [MT_IXP2000_DEVICE] = { /* IXP2400 requires XCB=101 for on-chip I/O */ | 
|  | 202 | .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | | 
|  | 203 | L_PTE_WRITE, | 
|  | 204 | .prot_l1   = PMD_TYPE_TABLE, | 
|  | 205 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4 | PMD_SECT_UNCACHED | | 
|  | 206 | PMD_SECT_AP_WRITE | PMD_SECT_BUFFERABLE | | 
|  | 207 | PMD_SECT_TEX(1), | 
|  | 208 | .domain    = DOMAIN_IO, | 
|  | 209 | }, | 
|  | 210 | [MT_NONSHARED_DEVICE] = { | 
|  | 211 | .prot_l1   = PMD_TYPE_TABLE, | 
|  | 212 | .prot_sect = PMD_TYPE_SECT | PMD_BIT4 | PMD_SECT_NONSHARED_DEV | | 
|  | 213 | PMD_SECT_AP_WRITE, | 
|  | 214 | .domain    = DOMAIN_IO, | 
|  | 215 | } | 
|  | 216 | }; | 
|  | 217 |  | 
|  | 218 | /* | 
|  | 219 | * Adjust the PMD section entries according to the CPU in use. | 
|  | 220 | */ | 
|  | 221 | static void __init build_mem_type_table(void) | 
|  | 222 | { | 
|  | 223 | struct cachepolicy *cp; | 
|  | 224 | unsigned int cr = get_cr(); | 
|  | 225 | unsigned int user_pgprot, kern_pgprot; | 
|  | 226 | int cpu_arch = cpu_architecture(); | 
|  | 227 | int i; | 
|  | 228 |  | 
|  | 229 | #if defined(CONFIG_CPU_DCACHE_DISABLE) | 
|  | 230 | if (cachepolicy > CPOLICY_BUFFERED) | 
|  | 231 | cachepolicy = CPOLICY_BUFFERED; | 
|  | 232 | #elif defined(CONFIG_CPU_DCACHE_WRITETHROUGH) | 
|  | 233 | if (cachepolicy > CPOLICY_WRITETHROUGH) | 
|  | 234 | cachepolicy = CPOLICY_WRITETHROUGH; | 
|  | 235 | #endif | 
|  | 236 | if (cpu_arch < CPU_ARCH_ARMv5) { | 
|  | 237 | if (cachepolicy >= CPOLICY_WRITEALLOC) | 
|  | 238 | cachepolicy = CPOLICY_WRITEBACK; | 
|  | 239 | ecc_mask = 0; | 
|  | 240 | } | 
|  | 241 |  | 
|  | 242 | /* | 
|  | 243 | * Xscale must not have PMD bit 4 set for section mappings. | 
|  | 244 | */ | 
|  | 245 | if (cpu_is_xscale()) | 
|  | 246 | for (i = 0; i < ARRAY_SIZE(mem_types); i++) | 
|  | 247 | mem_types[i].prot_sect &= ~PMD_BIT4; | 
|  | 248 |  | 
|  | 249 | /* | 
|  | 250 | * ARMv5 and lower, excluding Xscale, bit 4 must be set for | 
|  | 251 | * page tables. | 
|  | 252 | */ | 
|  | 253 | if (cpu_arch < CPU_ARCH_ARMv6 && !cpu_is_xscale()) | 
|  | 254 | for (i = 0; i < ARRAY_SIZE(mem_types); i++) | 
|  | 255 | if (mem_types[i].prot_l1) | 
|  | 256 | mem_types[i].prot_l1 |= PMD_BIT4; | 
|  | 257 |  | 
|  | 258 | cp = &cache_policies[cachepolicy]; | 
|  | 259 | kern_pgprot = user_pgprot = cp->pte; | 
|  | 260 |  | 
|  | 261 | /* | 
|  | 262 | * Enable CPU-specific coherency if supported. | 
|  | 263 | * (Only available on XSC3 at the moment.) | 
|  | 264 | */ | 
|  | 265 | if (arch_is_coherent()) { | 
|  | 266 | if (cpu_is_xsc3()) { | 
|  | 267 | mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; | 
|  | 268 | mem_types[MT_MEMORY].prot_pte |= L_PTE_COHERENT; | 
|  | 269 | } | 
|  | 270 | } | 
|  | 271 |  | 
|  | 272 | /* | 
|  | 273 | * ARMv6 and above have extended page tables. | 
|  | 274 | */ | 
|  | 275 | if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) { | 
|  | 276 | /* | 
|  | 277 | * bit 4 becomes XN which we must clear for the | 
|  | 278 | * kernel memory mapping. | 
|  | 279 | */ | 
|  | 280 | mem_types[MT_MEMORY].prot_sect &= ~PMD_SECT_XN; | 
|  | 281 | mem_types[MT_ROM].prot_sect &= ~PMD_SECT_XN; | 
|  | 282 |  | 
|  | 283 | /* | 
|  | 284 | * Mark cache clean areas and XIP ROM read only | 
|  | 285 | * from SVC mode and no access from userspace. | 
|  | 286 | */ | 
|  | 287 | mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; | 
|  | 288 | mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; | 
|  | 289 | mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; | 
|  | 290 |  | 
|  | 291 | /* | 
|  | 292 | * Mark the device area as "shared device" | 
|  | 293 | */ | 
|  | 294 | mem_types[MT_DEVICE].prot_pte |= L_PTE_BUFFERABLE; | 
|  | 295 | mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED; | 
|  | 296 |  | 
|  | 297 | /* | 
|  | 298 | * User pages need to be mapped with the ASID | 
|  | 299 | * (iow, non-global) | 
|  | 300 | */ | 
|  | 301 | user_pgprot |= L_PTE_ASID; | 
|  | 302 |  | 
|  | 303 | #ifdef CONFIG_SMP | 
|  | 304 | /* | 
|  | 305 | * Mark memory with the "shared" attribute for SMP systems | 
|  | 306 | */ | 
|  | 307 | user_pgprot |= L_PTE_SHARED; | 
|  | 308 | kern_pgprot |= L_PTE_SHARED; | 
|  | 309 | mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; | 
|  | 310 | #endif | 
|  | 311 | } | 
|  | 312 |  | 
|  | 313 | for (i = 0; i < 16; i++) { | 
|  | 314 | unsigned long v = pgprot_val(protection_map[i]); | 
|  | 315 | v = (v & ~(L_PTE_BUFFERABLE|L_PTE_CACHEABLE)) | user_pgprot; | 
|  | 316 | protection_map[i] = __pgprot(v); | 
|  | 317 | } | 
|  | 318 |  | 
|  | 319 | mem_types[MT_LOW_VECTORS].prot_pte |= kern_pgprot; | 
|  | 320 | mem_types[MT_HIGH_VECTORS].prot_pte |= kern_pgprot; | 
|  | 321 |  | 
|  | 322 | if (cpu_arch >= CPU_ARCH_ARMv5) { | 
|  | 323 | #ifndef CONFIG_SMP | 
|  | 324 | /* | 
|  | 325 | * Only use write-through for non-SMP systems | 
|  | 326 | */ | 
|  | 327 | mem_types[MT_LOW_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE; | 
|  | 328 | mem_types[MT_HIGH_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE; | 
|  | 329 | #endif | 
|  | 330 | } else { | 
|  | 331 | mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1); | 
|  | 332 | } | 
|  | 333 |  | 
|  | 334 | pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | | 
|  | 335 | L_PTE_DIRTY | L_PTE_WRITE | | 
|  | 336 | L_PTE_EXEC | kern_pgprot); | 
|  | 337 |  | 
|  | 338 | mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; | 
|  | 339 | mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; | 
|  | 340 | mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; | 
|  | 341 | mem_types[MT_ROM].prot_sect |= cp->pmd; | 
|  | 342 |  | 
|  | 343 | switch (cp->pmd) { | 
|  | 344 | case PMD_SECT_WT: | 
|  | 345 | mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WT; | 
|  | 346 | break; | 
|  | 347 | case PMD_SECT_WB: | 
|  | 348 | case PMD_SECT_WBWA: | 
|  | 349 | mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WB; | 
|  | 350 | break; | 
|  | 351 | } | 
|  | 352 | printk("Memory policy: ECC %sabled, Data cache %s\n", | 
|  | 353 | ecc_mask ? "en" : "dis", cp->policy); | 
|  | 354 | } | 
|  | 355 |  | 
|  | 356 | #define vectors_base()	(vectors_high() ? 0xffff0000 : 0) | 
|  | 357 |  | 
|  | 358 | /* | 
|  | 359 | * Create a SECTION PGD between VIRT and PHYS in domain | 
|  | 360 | * DOMAIN with protection PROT.  This operates on half- | 
|  | 361 | * pgdir entry increments. | 
|  | 362 | */ | 
|  | 363 | static inline void | 
|  | 364 | alloc_init_section(unsigned long virt, unsigned long phys, int prot) | 
|  | 365 | { | 
|  | 366 | pmd_t *pmdp = pmd_off_k(virt); | 
|  | 367 |  | 
|  | 368 | if (virt & (1 << 20)) | 
|  | 369 | pmdp++; | 
|  | 370 |  | 
|  | 371 | *pmdp = __pmd(phys | prot); | 
|  | 372 | flush_pmd_entry(pmdp); | 
|  | 373 | } | 
|  | 374 |  | 
|  | 375 | /* | 
|  | 376 | * Create a SUPER SECTION PGD between VIRT and PHYS with protection PROT | 
|  | 377 | */ | 
|  | 378 | static inline void | 
|  | 379 | alloc_init_supersection(unsigned long virt, unsigned long phys, int prot) | 
|  | 380 | { | 
|  | 381 | int i; | 
|  | 382 |  | 
|  | 383 | for (i = 0; i < 16; i += 1) { | 
|  | 384 | alloc_init_section(virt, phys, prot | PMD_SECT_SUPER); | 
|  | 385 |  | 
|  | 386 | virt += (PGDIR_SIZE / 2); | 
|  | 387 | } | 
|  | 388 | } | 
|  | 389 |  | 
|  | 390 | /* | 
|  | 391 | * Add a PAGE mapping between VIRT and PHYS in domain | 
|  | 392 | * DOMAIN with protection PROT.  Note that due to the | 
|  | 393 | * way we map the PTEs, we must allocate two PTE_SIZE'd | 
|  | 394 | * blocks - one for the Linux pte table, and one for | 
|  | 395 | * the hardware pte table. | 
|  | 396 | */ | 
|  | 397 | static inline void | 
|  | 398 | alloc_init_page(unsigned long virt, unsigned long phys, unsigned int prot_l1, pgprot_t prot) | 
|  | 399 | { | 
|  | 400 | pmd_t *pmdp = pmd_off_k(virt); | 
|  | 401 | pte_t *ptep; | 
|  | 402 |  | 
|  | 403 | if (pmd_none(*pmdp)) { | 
|  | 404 | ptep = alloc_bootmem_low_pages(2 * PTRS_PER_PTE * | 
|  | 405 | sizeof(pte_t)); | 
|  | 406 |  | 
|  | 407 | __pmd_populate(pmdp, __pa(ptep) | prot_l1); | 
|  | 408 | } | 
|  | 409 | ptep = pte_offset_kernel(pmdp, virt); | 
|  | 410 |  | 
|  | 411 | set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot)); | 
|  | 412 | } | 
|  | 413 |  | 
|  | 414 | /* | 
|  | 415 | * Create the page directory entries and any necessary | 
|  | 416 | * page tables for the mapping specified by `md'.  We | 
|  | 417 | * are able to cope here with varying sizes and address | 
|  | 418 | * offsets, and we take full advantage of sections and | 
|  | 419 | * supersections. | 
|  | 420 | */ | 
|  | 421 | void __init create_mapping(struct map_desc *md) | 
|  | 422 | { | 
|  | 423 | unsigned long virt, length; | 
|  | 424 | int prot_sect, prot_l1, domain; | 
|  | 425 | pgprot_t prot_pte; | 
|  | 426 | unsigned long off = (u32)__pfn_to_phys(md->pfn); | 
|  | 427 |  | 
|  | 428 | if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) { | 
|  | 429 | printk(KERN_WARNING "BUG: not creating mapping for " | 
|  | 430 | "0x%08llx at 0x%08lx in user region\n", | 
|  | 431 | __pfn_to_phys((u64)md->pfn), md->virtual); | 
|  | 432 | return; | 
|  | 433 | } | 
|  | 434 |  | 
|  | 435 | if ((md->type == MT_DEVICE || md->type == MT_ROM) && | 
|  | 436 | md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) { | 
|  | 437 | printk(KERN_WARNING "BUG: mapping for 0x%08llx at 0x%08lx " | 
|  | 438 | "overlaps vmalloc space\n", | 
|  | 439 | __pfn_to_phys((u64)md->pfn), md->virtual); | 
|  | 440 | } | 
|  | 441 |  | 
|  | 442 | domain	  = mem_types[md->type].domain; | 
|  | 443 | prot_pte  = __pgprot(mem_types[md->type].prot_pte); | 
|  | 444 | prot_l1   = mem_types[md->type].prot_l1 | PMD_DOMAIN(domain); | 
|  | 445 | prot_sect = mem_types[md->type].prot_sect | PMD_DOMAIN(domain); | 
|  | 446 |  | 
|  | 447 | /* | 
|  | 448 | * Catch 36-bit addresses | 
|  | 449 | */ | 
|  | 450 | if(md->pfn >= 0x100000) { | 
|  | 451 | if(domain) { | 
|  | 452 | printk(KERN_ERR "MM: invalid domain in supersection " | 
|  | 453 | "mapping for 0x%08llx at 0x%08lx\n", | 
|  | 454 | __pfn_to_phys((u64)md->pfn), md->virtual); | 
|  | 455 | return; | 
|  | 456 | } | 
|  | 457 | if((md->virtual | md->length | __pfn_to_phys(md->pfn)) | 
|  | 458 | & ~SUPERSECTION_MASK) { | 
|  | 459 | printk(KERN_ERR "MM: cannot create mapping for " | 
|  | 460 | "0x%08llx at 0x%08lx invalid alignment\n", | 
|  | 461 | __pfn_to_phys((u64)md->pfn), md->virtual); | 
|  | 462 | return; | 
|  | 463 | } | 
|  | 464 |  | 
|  | 465 | /* | 
|  | 466 | * Shift bits [35:32] of address into bits [23:20] of PMD | 
|  | 467 | * (See ARMv6 spec). | 
|  | 468 | */ | 
|  | 469 | off |= (((md->pfn >> (32 - PAGE_SHIFT)) & 0xF) << 20); | 
|  | 470 | } | 
|  | 471 |  | 
|  | 472 | virt   = md->virtual; | 
|  | 473 | off   -= virt; | 
|  | 474 | length = md->length; | 
|  | 475 |  | 
|  | 476 | if (mem_types[md->type].prot_l1 == 0 && | 
|  | 477 | (virt & 0xfffff || (virt + off) & 0xfffff || (virt + length) & 0xfffff)) { | 
|  | 478 | printk(KERN_WARNING "BUG: map for 0x%08lx at 0x%08lx can not " | 
|  | 479 | "be mapped using pages, ignoring.\n", | 
|  | 480 | __pfn_to_phys(md->pfn), md->virtual); | 
|  | 481 | return; | 
|  | 482 | } | 
|  | 483 |  | 
|  | 484 | while ((virt & 0xfffff || (virt + off) & 0xfffff) && length >= PAGE_SIZE) { | 
|  | 485 | alloc_init_page(virt, virt + off, prot_l1, prot_pte); | 
|  | 486 |  | 
|  | 487 | virt   += PAGE_SIZE; | 
|  | 488 | length -= PAGE_SIZE; | 
|  | 489 | } | 
|  | 490 |  | 
|  | 491 | /* N.B.	ARMv6 supersections are only defined to work with domain 0. | 
|  | 492 | *	Since domain assignments can in fact be arbitrary, the | 
|  | 493 | *	'domain == 0' check below is required to insure that ARMv6 | 
|  | 494 | *	supersections are only allocated for domain 0 regardless | 
|  | 495 | *	of the actual domain assignments in use. | 
|  | 496 | */ | 
|  | 497 | if ((cpu_architecture() >= CPU_ARCH_ARMv6 || cpu_is_xsc3()) | 
|  | 498 | && domain == 0) { | 
|  | 499 | /* | 
|  | 500 | * Align to supersection boundary if !high pages. | 
|  | 501 | * High pages have already been checked for proper | 
|  | 502 | * alignment above and they will fail the SUPSERSECTION_MASK | 
|  | 503 | * check because of the way the address is encoded into | 
|  | 504 | * offset. | 
|  | 505 | */ | 
|  | 506 | if (md->pfn <= 0x100000) { | 
|  | 507 | while ((virt & ~SUPERSECTION_MASK || | 
|  | 508 | (virt + off) & ~SUPERSECTION_MASK) && | 
|  | 509 | length >= (PGDIR_SIZE / 2)) { | 
|  | 510 | alloc_init_section(virt, virt + off, prot_sect); | 
|  | 511 |  | 
|  | 512 | virt   += (PGDIR_SIZE / 2); | 
|  | 513 | length -= (PGDIR_SIZE / 2); | 
|  | 514 | } | 
|  | 515 | } | 
|  | 516 |  | 
|  | 517 | while (length >= SUPERSECTION_SIZE) { | 
|  | 518 | alloc_init_supersection(virt, virt + off, prot_sect); | 
|  | 519 |  | 
|  | 520 | virt   += SUPERSECTION_SIZE; | 
|  | 521 | length -= SUPERSECTION_SIZE; | 
|  | 522 | } | 
|  | 523 | } | 
|  | 524 |  | 
|  | 525 | /* | 
|  | 526 | * A section mapping covers half a "pgdir" entry. | 
|  | 527 | */ | 
|  | 528 | while (length >= (PGDIR_SIZE / 2)) { | 
|  | 529 | alloc_init_section(virt, virt + off, prot_sect); | 
|  | 530 |  | 
|  | 531 | virt   += (PGDIR_SIZE / 2); | 
|  | 532 | length -= (PGDIR_SIZE / 2); | 
|  | 533 | } | 
|  | 534 |  | 
|  | 535 | while (length >= PAGE_SIZE) { | 
|  | 536 | alloc_init_page(virt, virt + off, prot_l1, prot_pte); | 
|  | 537 |  | 
|  | 538 | virt   += PAGE_SIZE; | 
|  | 539 | length -= PAGE_SIZE; | 
|  | 540 | } | 
|  | 541 | } | 
|  | 542 |  | 
|  | 543 | /* | 
|  | 544 | * Create the architecture specific mappings | 
|  | 545 | */ | 
|  | 546 | void __init iotable_init(struct map_desc *io_desc, int nr) | 
|  | 547 | { | 
|  | 548 | int i; | 
|  | 549 |  | 
|  | 550 | for (i = 0; i < nr; i++) | 
|  | 551 | create_mapping(io_desc + i); | 
|  | 552 | } | 
|  | 553 |  | 
| Russell King | d111e8f | 2006-09-27 15:27:33 +0100 | [diff] [blame] | 554 | static inline void prepare_page_table(struct meminfo *mi) | 
|  | 555 | { | 
|  | 556 | unsigned long addr; | 
|  | 557 |  | 
|  | 558 | /* | 
|  | 559 | * Clear out all the mappings below the kernel image. | 
|  | 560 | */ | 
|  | 561 | for (addr = 0; addr < MODULE_START; addr += PGDIR_SIZE) | 
|  | 562 | pmd_clear(pmd_off_k(addr)); | 
|  | 563 |  | 
|  | 564 | #ifdef CONFIG_XIP_KERNEL | 
|  | 565 | /* The XIP kernel is mapped in the module area -- skip over it */ | 
|  | 566 | addr = ((unsigned long)&_etext + PGDIR_SIZE - 1) & PGDIR_MASK; | 
|  | 567 | #endif | 
|  | 568 | for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE) | 
|  | 569 | pmd_clear(pmd_off_k(addr)); | 
|  | 570 |  | 
|  | 571 | /* | 
|  | 572 | * Clear out all the kernel space mappings, except for the first | 
|  | 573 | * memory bank, up to the end of the vmalloc region. | 
|  | 574 | */ | 
|  | 575 | for (addr = __phys_to_virt(mi->bank[0].start + mi->bank[0].size); | 
|  | 576 | addr < VMALLOC_END; addr += PGDIR_SIZE) | 
|  | 577 | pmd_clear(pmd_off_k(addr)); | 
|  | 578 | } | 
|  | 579 |  | 
|  | 580 | /* | 
|  | 581 | * Reserve the various regions of node 0 | 
|  | 582 | */ | 
|  | 583 | void __init reserve_node_zero(pg_data_t *pgdat) | 
|  | 584 | { | 
|  | 585 | unsigned long res_size = 0; | 
|  | 586 |  | 
|  | 587 | /* | 
|  | 588 | * Register the kernel text and data with bootmem. | 
|  | 589 | * Note that this can only be in node 0. | 
|  | 590 | */ | 
|  | 591 | #ifdef CONFIG_XIP_KERNEL | 
|  | 592 | reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start); | 
|  | 593 | #else | 
|  | 594 | reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext); | 
|  | 595 | #endif | 
|  | 596 |  | 
|  | 597 | /* | 
|  | 598 | * Reserve the page tables.  These are already in use, | 
|  | 599 | * and can only be in node 0. | 
|  | 600 | */ | 
|  | 601 | reserve_bootmem_node(pgdat, __pa(swapper_pg_dir), | 
|  | 602 | PTRS_PER_PGD * sizeof(pgd_t)); | 
|  | 603 |  | 
|  | 604 | /* | 
|  | 605 | * Hmm... This should go elsewhere, but we really really need to | 
|  | 606 | * stop things allocating the low memory; ideally we need a better | 
|  | 607 | * implementation of GFP_DMA which does not assume that DMA-able | 
|  | 608 | * memory starts at zero. | 
|  | 609 | */ | 
|  | 610 | if (machine_is_integrator() || machine_is_cintegrator()) | 
|  | 611 | res_size = __pa(swapper_pg_dir) - PHYS_OFFSET; | 
|  | 612 |  | 
|  | 613 | /* | 
|  | 614 | * These should likewise go elsewhere.  They pre-reserve the | 
|  | 615 | * screen memory region at the start of main system memory. | 
|  | 616 | */ | 
|  | 617 | if (machine_is_edb7211()) | 
|  | 618 | res_size = 0x00020000; | 
|  | 619 | if (machine_is_p720t()) | 
|  | 620 | res_size = 0x00014000; | 
|  | 621 |  | 
|  | 622 | #ifdef CONFIG_SA1111 | 
|  | 623 | /* | 
|  | 624 | * Because of the SA1111 DMA bug, we want to preserve our | 
|  | 625 | * precious DMA-able memory... | 
|  | 626 | */ | 
|  | 627 | res_size = __pa(swapper_pg_dir) - PHYS_OFFSET; | 
|  | 628 | #endif | 
|  | 629 | if (res_size) | 
|  | 630 | reserve_bootmem_node(pgdat, PHYS_OFFSET, res_size); | 
|  | 631 | } | 
|  | 632 |  | 
|  | 633 | /* | 
|  | 634 | * Set up device the mappings.  Since we clear out the page tables for all | 
|  | 635 | * mappings above VMALLOC_END, we will remove any debug device mappings. | 
|  | 636 | * This means you have to be careful how you debug this function, or any | 
|  | 637 | * called function.  This means you can't use any function or debugging | 
|  | 638 | * method which may touch any device, otherwise the kernel _will_ crash. | 
|  | 639 | */ | 
|  | 640 | static void __init devicemaps_init(struct machine_desc *mdesc) | 
|  | 641 | { | 
|  | 642 | struct map_desc map; | 
|  | 643 | unsigned long addr; | 
|  | 644 | void *vectors; | 
|  | 645 |  | 
|  | 646 | /* | 
|  | 647 | * Allocate the vector page early. | 
|  | 648 | */ | 
|  | 649 | vectors = alloc_bootmem_low_pages(PAGE_SIZE); | 
|  | 650 | BUG_ON(!vectors); | 
|  | 651 |  | 
|  | 652 | for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE) | 
|  | 653 | pmd_clear(pmd_off_k(addr)); | 
|  | 654 |  | 
|  | 655 | /* | 
|  | 656 | * Map the kernel if it is XIP. | 
|  | 657 | * It is always first in the modulearea. | 
|  | 658 | */ | 
|  | 659 | #ifdef CONFIG_XIP_KERNEL | 
|  | 660 | map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK); | 
|  | 661 | map.virtual = MODULE_START; | 
|  | 662 | map.length = ((unsigned long)&_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK; | 
|  | 663 | map.type = MT_ROM; | 
|  | 664 | create_mapping(&map); | 
|  | 665 | #endif | 
|  | 666 |  | 
|  | 667 | /* | 
|  | 668 | * Map the cache flushing regions. | 
|  | 669 | */ | 
|  | 670 | #ifdef FLUSH_BASE | 
|  | 671 | map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS); | 
|  | 672 | map.virtual = FLUSH_BASE; | 
|  | 673 | map.length = SZ_1M; | 
|  | 674 | map.type = MT_CACHECLEAN; | 
|  | 675 | create_mapping(&map); | 
|  | 676 | #endif | 
|  | 677 | #ifdef FLUSH_BASE_MINICACHE | 
|  | 678 | map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS + SZ_1M); | 
|  | 679 | map.virtual = FLUSH_BASE_MINICACHE; | 
|  | 680 | map.length = SZ_1M; | 
|  | 681 | map.type = MT_MINICLEAN; | 
|  | 682 | create_mapping(&map); | 
|  | 683 | #endif | 
|  | 684 |  | 
|  | 685 | /* | 
|  | 686 | * Create a mapping for the machine vectors at the high-vectors | 
|  | 687 | * location (0xffff0000).  If we aren't using high-vectors, also | 
|  | 688 | * create a mapping at the low-vectors virtual address. | 
|  | 689 | */ | 
|  | 690 | map.pfn = __phys_to_pfn(virt_to_phys(vectors)); | 
|  | 691 | map.virtual = 0xffff0000; | 
|  | 692 | map.length = PAGE_SIZE; | 
|  | 693 | map.type = MT_HIGH_VECTORS; | 
|  | 694 | create_mapping(&map); | 
|  | 695 |  | 
|  | 696 | if (!vectors_high()) { | 
|  | 697 | map.virtual = 0; | 
|  | 698 | map.type = MT_LOW_VECTORS; | 
|  | 699 | create_mapping(&map); | 
|  | 700 | } | 
|  | 701 |  | 
|  | 702 | /* | 
|  | 703 | * Ask the machine support to map in the statically mapped devices. | 
|  | 704 | */ | 
|  | 705 | if (mdesc->map_io) | 
|  | 706 | mdesc->map_io(); | 
|  | 707 |  | 
|  | 708 | /* | 
|  | 709 | * Finally flush the caches and tlb to ensure that we're in a | 
|  | 710 | * consistent state wrt the writebuffer.  This also ensures that | 
|  | 711 | * any write-allocated cache lines in the vector page are written | 
|  | 712 | * back.  After this point, we can start to touch devices again. | 
|  | 713 | */ | 
|  | 714 | local_flush_tlb_all(); | 
|  | 715 | flush_cache_all(); | 
|  | 716 | } | 
|  | 717 |  | 
|  | 718 | /* | 
|  | 719 | * paging_init() sets up the page tables, initialises the zone memory | 
|  | 720 | * maps, and sets up the zero page, bad page and bad page tables. | 
|  | 721 | */ | 
|  | 722 | void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc) | 
|  | 723 | { | 
|  | 724 | void *zero_page; | 
|  | 725 |  | 
|  | 726 | build_mem_type_table(); | 
|  | 727 | prepare_page_table(mi); | 
|  | 728 | bootmem_init(mi); | 
|  | 729 | devicemaps_init(mdesc); | 
|  | 730 |  | 
|  | 731 | top_pmd = pmd_off_k(0xffff0000); | 
|  | 732 |  | 
|  | 733 | /* | 
|  | 734 | * allocate the zero page.  Note that we count on this going ok. | 
|  | 735 | */ | 
|  | 736 | zero_page = alloc_bootmem_low_pages(PAGE_SIZE); | 
|  | 737 | memzero(zero_page, PAGE_SIZE); | 
|  | 738 | empty_zero_page = virt_to_page(zero_page); | 
|  | 739 | flush_dcache_page(empty_zero_page); | 
|  | 740 | } | 
| Russell King | ae8f154 | 2006-09-27 15:38:34 +0100 | [diff] [blame] | 741 |  | 
|  | 742 | /* | 
|  | 743 | * In order to soft-boot, we need to insert a 1:1 mapping in place of | 
|  | 744 | * the user-mode pages.  This will then ensure that we have predictable | 
|  | 745 | * results when turning the mmu off | 
|  | 746 | */ | 
|  | 747 | void setup_mm_for_reboot(char mode) | 
|  | 748 | { | 
|  | 749 | unsigned long base_pmdval; | 
|  | 750 | pgd_t *pgd; | 
|  | 751 | int i; | 
|  | 752 |  | 
|  | 753 | if (current->mm && current->mm->pgd) | 
|  | 754 | pgd = current->mm->pgd; | 
|  | 755 | else | 
|  | 756 | pgd = init_mm.pgd; | 
|  | 757 |  | 
|  | 758 | base_pmdval = PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT; | 
|  | 759 | if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale()) | 
|  | 760 | base_pmdval |= PMD_BIT4; | 
|  | 761 |  | 
|  | 762 | for (i = 0; i < FIRST_USER_PGD_NR + USER_PTRS_PER_PGD; i++, pgd++) { | 
|  | 763 | unsigned long pmdval = (i << PGDIR_SHIFT) | base_pmdval; | 
|  | 764 | pmd_t *pmd; | 
|  | 765 |  | 
|  | 766 | pmd = pmd_off(pgd, i << PGDIR_SHIFT); | 
|  | 767 | pmd[0] = __pmd(pmdval); | 
|  | 768 | pmd[1] = __pmd(pmdval + (1 << (PGDIR_SHIFT - 1))); | 
|  | 769 | flush_pmd_entry(pmd); | 
|  | 770 | } | 
|  | 771 | } |