| b.liu | e958203 | 2025-04-17 19:18:16 +0800 | [diff] [blame] | 1 | // SPDX-License-Identifier: GPL-2.0-or-later | 
|  | 2 | /* | 
|  | 3 | * PowerPC64 SLB support. | 
|  | 4 | * | 
|  | 5 | * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM | 
|  | 6 | * Based on earlier code written by: | 
|  | 7 | * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com | 
|  | 8 | *    Copyright (c) 2001 Dave Engebretsen | 
|  | 9 | * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM | 
|  | 10 | */ | 
|  | 11 |  | 
|  | 12 | #include <asm/asm-prototypes.h> | 
|  | 13 | #include <asm/pgtable.h> | 
|  | 14 | #include <asm/mmu.h> | 
|  | 15 | #include <asm/mmu_context.h> | 
|  | 16 | #include <asm/paca.h> | 
|  | 17 | #include <asm/ppc-opcode.h> | 
|  | 18 | #include <asm/cputable.h> | 
|  | 19 | #include <asm/cacheflush.h> | 
|  | 20 | #include <asm/smp.h> | 
|  | 21 | #include <linux/compiler.h> | 
|  | 22 | #include <linux/context_tracking.h> | 
|  | 23 | #include <linux/mm_types.h> | 
|  | 24 |  | 
|  | 25 | #include <asm/udbg.h> | 
|  | 26 | #include <asm/code-patching.h> | 
|  | 27 |  | 
|  | 28 | enum slb_index { | 
|  | 29 | LINEAR_INDEX	= 0, /* Kernel linear map  (0xc000000000000000) */ | 
|  | 30 | KSTACK_INDEX	= 1, /* Kernel stack map */ | 
|  | 31 | }; | 
|  | 32 |  | 
|  | 33 | static long slb_allocate_user(struct mm_struct *mm, unsigned long ea); | 
|  | 34 |  | 
|  | 35 | #define slb_esid_mask(ssize)	\ | 
|  | 36 | (((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T) | 
|  | 37 |  | 
|  | 38 | static inline unsigned long mk_esid_data(unsigned long ea, int ssize, | 
|  | 39 | enum slb_index index) | 
|  | 40 | { | 
|  | 41 | return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index; | 
|  | 42 | } | 
|  | 43 |  | 
|  | 44 | static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize, | 
|  | 45 | unsigned long flags) | 
|  | 46 | { | 
|  | 47 | return (vsid << slb_vsid_shift(ssize)) | flags | | 
|  | 48 | ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT); | 
|  | 49 | } | 
|  | 50 |  | 
|  | 51 | static inline unsigned long mk_vsid_data(unsigned long ea, int ssize, | 
|  | 52 | unsigned long flags) | 
|  | 53 | { | 
|  | 54 | return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags); | 
|  | 55 | } | 
|  | 56 |  | 
|  | 57 | static void assert_slb_presence(bool present, unsigned long ea) | 
|  | 58 | { | 
|  | 59 | #ifdef CONFIG_DEBUG_VM | 
|  | 60 | unsigned long tmp; | 
|  | 61 |  | 
|  | 62 | WARN_ON_ONCE(mfmsr() & MSR_EE); | 
|  | 63 |  | 
|  | 64 | if (!cpu_has_feature(CPU_FTR_ARCH_206)) | 
|  | 65 | return; | 
|  | 66 |  | 
|  | 67 | /* | 
|  | 68 | * slbfee. requires bit 24 (PPC bit 39) be clear in RB. Hardware | 
|  | 69 | * ignores all other bits from 0-27, so just clear them all. | 
|  | 70 | */ | 
|  | 71 | ea &= ~((1UL << 28) - 1); | 
|  | 72 | asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0"); | 
|  | 73 |  | 
|  | 74 | WARN_ON(present == (tmp == 0)); | 
|  | 75 | #endif | 
|  | 76 | } | 
|  | 77 |  | 
|  | 78 | static inline void slb_shadow_update(unsigned long ea, int ssize, | 
|  | 79 | unsigned long flags, | 
|  | 80 | enum slb_index index) | 
|  | 81 | { | 
|  | 82 | struct slb_shadow *p = get_slb_shadow(); | 
|  | 83 |  | 
|  | 84 | /* | 
|  | 85 | * Clear the ESID first so the entry is not valid while we are | 
|  | 86 | * updating it.  No write barriers are needed here, provided | 
|  | 87 | * we only update the current CPU's SLB shadow buffer. | 
|  | 88 | */ | 
|  | 89 | WRITE_ONCE(p->save_area[index].esid, 0); | 
|  | 90 | WRITE_ONCE(p->save_area[index].vsid, cpu_to_be64(mk_vsid_data(ea, ssize, flags))); | 
|  | 91 | WRITE_ONCE(p->save_area[index].esid, cpu_to_be64(mk_esid_data(ea, ssize, index))); | 
|  | 92 | } | 
|  | 93 |  | 
|  | 94 | static inline void slb_shadow_clear(enum slb_index index) | 
|  | 95 | { | 
|  | 96 | WRITE_ONCE(get_slb_shadow()->save_area[index].esid, cpu_to_be64(index)); | 
|  | 97 | } | 
|  | 98 |  | 
|  | 99 | static inline void create_shadowed_slbe(unsigned long ea, int ssize, | 
|  | 100 | unsigned long flags, | 
|  | 101 | enum slb_index index) | 
|  | 102 | { | 
|  | 103 | /* | 
|  | 104 | * Updating the shadow buffer before writing the SLB ensures | 
|  | 105 | * we don't get a stale entry here if we get preempted by PHYP | 
|  | 106 | * between these two statements. | 
|  | 107 | */ | 
|  | 108 | slb_shadow_update(ea, ssize, flags, index); | 
|  | 109 |  | 
|  | 110 | assert_slb_presence(false, ea); | 
|  | 111 | asm volatile("slbmte  %0,%1" : | 
|  | 112 | : "r" (mk_vsid_data(ea, ssize, flags)), | 
|  | 113 | "r" (mk_esid_data(ea, ssize, index)) | 
|  | 114 | : "memory" ); | 
|  | 115 | } | 
|  | 116 |  | 
|  | 117 | /* | 
|  | 118 | * Insert bolted entries into SLB (which may not be empty, so don't clear | 
|  | 119 | * slb_cache_ptr). | 
|  | 120 | */ | 
|  | 121 | void __slb_restore_bolted_realmode(void) | 
|  | 122 | { | 
|  | 123 | struct slb_shadow *p = get_slb_shadow(); | 
|  | 124 | enum slb_index index; | 
|  | 125 |  | 
|  | 126 | /* No isync needed because realmode. */ | 
|  | 127 | for (index = 0; index < SLB_NUM_BOLTED; index++) { | 
|  | 128 | asm volatile("slbmte  %0,%1" : | 
|  | 129 | : "r" (be64_to_cpu(p->save_area[index].vsid)), | 
|  | 130 | "r" (be64_to_cpu(p->save_area[index].esid))); | 
|  | 131 | } | 
|  | 132 |  | 
|  | 133 | assert_slb_presence(true, local_paca->kstack); | 
|  | 134 | } | 
|  | 135 |  | 
|  | 136 | /* | 
|  | 137 | * Insert the bolted entries into an empty SLB. | 
|  | 138 | */ | 
|  | 139 | void slb_restore_bolted_realmode(void) | 
|  | 140 | { | 
|  | 141 | __slb_restore_bolted_realmode(); | 
|  | 142 | get_paca()->slb_cache_ptr = 0; | 
|  | 143 |  | 
|  | 144 | get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1; | 
|  | 145 | get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap; | 
|  | 146 | } | 
|  | 147 |  | 
|  | 148 | /* | 
|  | 149 | * This flushes all SLB entries including 0, so it must be realmode. | 
|  | 150 | */ | 
|  | 151 | void slb_flush_all_realmode(void) | 
|  | 152 | { | 
|  | 153 | asm volatile("slbmte %0,%0; slbia" : : "r" (0)); | 
|  | 154 | } | 
|  | 155 |  | 
|  | 156 | /* | 
|  | 157 | * This flushes non-bolted entries, it can be run in virtual mode. Must | 
|  | 158 | * be called with interrupts disabled. | 
|  | 159 | */ | 
|  | 160 | void slb_flush_and_restore_bolted(void) | 
|  | 161 | { | 
|  | 162 | struct slb_shadow *p = get_slb_shadow(); | 
|  | 163 |  | 
|  | 164 | BUILD_BUG_ON(SLB_NUM_BOLTED != 2); | 
|  | 165 |  | 
|  | 166 | WARN_ON(!irqs_disabled()); | 
|  | 167 |  | 
|  | 168 | /* | 
|  | 169 | * We can't take a PMU exception in the following code, so hard | 
|  | 170 | * disable interrupts. | 
|  | 171 | */ | 
|  | 172 | hard_irq_disable(); | 
|  | 173 |  | 
|  | 174 | asm volatile("isync\n" | 
|  | 175 | "slbia\n" | 
|  | 176 | "slbmte  %0, %1\n" | 
|  | 177 | "isync\n" | 
|  | 178 | :: "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].vsid)), | 
|  | 179 | "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].esid)) | 
|  | 180 | : "memory"); | 
|  | 181 | assert_slb_presence(true, get_paca()->kstack); | 
|  | 182 |  | 
|  | 183 | get_paca()->slb_cache_ptr = 0; | 
|  | 184 |  | 
|  | 185 | get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1; | 
|  | 186 | get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap; | 
|  | 187 | } | 
|  | 188 |  | 
|  | 189 | void slb_save_contents(struct slb_entry *slb_ptr) | 
|  | 190 | { | 
|  | 191 | int i; | 
|  | 192 | unsigned long e, v; | 
|  | 193 |  | 
|  | 194 | /* Save slb_cache_ptr value. */ | 
|  | 195 | get_paca()->slb_save_cache_ptr = get_paca()->slb_cache_ptr; | 
|  | 196 |  | 
|  | 197 | if (!slb_ptr) | 
|  | 198 | return; | 
|  | 199 |  | 
|  | 200 | for (i = 0; i < mmu_slb_size; i++) { | 
|  | 201 | asm volatile("slbmfee  %0,%1" : "=r" (e) : "r" (i)); | 
|  | 202 | asm volatile("slbmfev  %0,%1" : "=r" (v) : "r" (i)); | 
|  | 203 | slb_ptr->esid = e; | 
|  | 204 | slb_ptr->vsid = v; | 
|  | 205 | slb_ptr++; | 
|  | 206 | } | 
|  | 207 | } | 
|  | 208 |  | 
|  | 209 | void slb_dump_contents(struct slb_entry *slb_ptr) | 
|  | 210 | { | 
|  | 211 | int i, n; | 
|  | 212 | unsigned long e, v; | 
|  | 213 | unsigned long llp; | 
|  | 214 |  | 
|  | 215 | if (!slb_ptr) | 
|  | 216 | return; | 
|  | 217 |  | 
|  | 218 | pr_err("SLB contents of cpu 0x%x\n", smp_processor_id()); | 
|  | 219 | pr_err("Last SLB entry inserted at slot %d\n", get_paca()->stab_rr); | 
|  | 220 |  | 
|  | 221 | for (i = 0; i < mmu_slb_size; i++) { | 
|  | 222 | e = slb_ptr->esid; | 
|  | 223 | v = slb_ptr->vsid; | 
|  | 224 | slb_ptr++; | 
|  | 225 |  | 
|  | 226 | if (!e && !v) | 
|  | 227 | continue; | 
|  | 228 |  | 
|  | 229 | pr_err("%02d %016lx %016lx\n", i, e, v); | 
|  | 230 |  | 
|  | 231 | if (!(e & SLB_ESID_V)) { | 
|  | 232 | pr_err("\n"); | 
|  | 233 | continue; | 
|  | 234 | } | 
|  | 235 | llp = v & SLB_VSID_LLP; | 
|  | 236 | if (v & SLB_VSID_B_1T) { | 
|  | 237 | pr_err("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx\n", | 
|  | 238 | GET_ESID_1T(e), | 
|  | 239 | (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T, llp); | 
|  | 240 | } else { | 
|  | 241 | pr_err(" 256M ESID=%9lx  VSID=%13lx LLP:%3lx\n", | 
|  | 242 | GET_ESID(e), | 
|  | 243 | (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT, llp); | 
|  | 244 | } | 
|  | 245 | } | 
|  | 246 | pr_err("----------------------------------\n"); | 
|  | 247 |  | 
|  | 248 | /* Dump slb cache entires as well. */ | 
|  | 249 | pr_err("SLB cache ptr value = %d\n", get_paca()->slb_save_cache_ptr); | 
|  | 250 | pr_err("Valid SLB cache entries:\n"); | 
|  | 251 | n = min_t(int, get_paca()->slb_save_cache_ptr, SLB_CACHE_ENTRIES); | 
|  | 252 | for (i = 0; i < n; i++) | 
|  | 253 | pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]); | 
|  | 254 | pr_err("Rest of SLB cache entries:\n"); | 
|  | 255 | for (i = n; i < SLB_CACHE_ENTRIES; i++) | 
|  | 256 | pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]); | 
|  | 257 | } | 
|  | 258 |  | 
|  | 259 | void slb_vmalloc_update(void) | 
|  | 260 | { | 
|  | 261 | /* | 
|  | 262 | * vmalloc is not bolted, so just have to flush non-bolted. | 
|  | 263 | */ | 
|  | 264 | slb_flush_and_restore_bolted(); | 
|  | 265 | } | 
|  | 266 |  | 
|  | 267 | static bool preload_hit(struct thread_info *ti, unsigned long esid) | 
|  | 268 | { | 
|  | 269 | unsigned char i; | 
|  | 270 |  | 
|  | 271 | for (i = 0; i < ti->slb_preload_nr; i++) { | 
|  | 272 | unsigned char idx; | 
|  | 273 |  | 
|  | 274 | idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR; | 
|  | 275 | if (esid == ti->slb_preload_esid[idx]) | 
|  | 276 | return true; | 
|  | 277 | } | 
|  | 278 | return false; | 
|  | 279 | } | 
|  | 280 |  | 
|  | 281 | static bool preload_add(struct thread_info *ti, unsigned long ea) | 
|  | 282 | { | 
|  | 283 | unsigned char idx; | 
|  | 284 | unsigned long esid; | 
|  | 285 |  | 
|  | 286 | if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) { | 
|  | 287 | /* EAs are stored >> 28 so 256MB segments don't need clearing */ | 
|  | 288 | if (ea & ESID_MASK_1T) | 
|  | 289 | ea &= ESID_MASK_1T; | 
|  | 290 | } | 
|  | 291 |  | 
|  | 292 | esid = ea >> SID_SHIFT; | 
|  | 293 |  | 
|  | 294 | if (preload_hit(ti, esid)) | 
|  | 295 | return false; | 
|  | 296 |  | 
|  | 297 | idx = (ti->slb_preload_tail + ti->slb_preload_nr) % SLB_PRELOAD_NR; | 
|  | 298 | ti->slb_preload_esid[idx] = esid; | 
|  | 299 | if (ti->slb_preload_nr == SLB_PRELOAD_NR) | 
|  | 300 | ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR; | 
|  | 301 | else | 
|  | 302 | ti->slb_preload_nr++; | 
|  | 303 |  | 
|  | 304 | return true; | 
|  | 305 | } | 
|  | 306 |  | 
|  | 307 | static void preload_age(struct thread_info *ti) | 
|  | 308 | { | 
|  | 309 | if (!ti->slb_preload_nr) | 
|  | 310 | return; | 
|  | 311 | ti->slb_preload_nr--; | 
|  | 312 | ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR; | 
|  | 313 | } | 
|  | 314 |  | 
|  | 315 | void slb_setup_new_exec(void) | 
|  | 316 | { | 
|  | 317 | struct thread_info *ti = current_thread_info(); | 
|  | 318 | struct mm_struct *mm = current->mm; | 
|  | 319 | unsigned long exec = 0x10000000; | 
|  | 320 |  | 
|  | 321 | WARN_ON(irqs_disabled()); | 
|  | 322 |  | 
|  | 323 | /* | 
|  | 324 | * preload cache can only be used to determine whether a SLB | 
|  | 325 | * entry exists if it does not start to overflow. | 
|  | 326 | */ | 
|  | 327 | if (ti->slb_preload_nr + 2 > SLB_PRELOAD_NR) | 
|  | 328 | return; | 
|  | 329 |  | 
|  | 330 | hard_irq_disable(); | 
|  | 331 |  | 
|  | 332 | /* | 
|  | 333 | * We have no good place to clear the slb preload cache on exec, | 
|  | 334 | * flush_thread is about the earliest arch hook but that happens | 
|  | 335 | * after we switch to the mm and have aleady preloaded the SLBEs. | 
|  | 336 | * | 
|  | 337 | * For the most part that's probably okay to use entries from the | 
|  | 338 | * previous exec, they will age out if unused. It may turn out to | 
|  | 339 | * be an advantage to clear the cache before switching to it, | 
|  | 340 | * however. | 
|  | 341 | */ | 
|  | 342 |  | 
|  | 343 | /* | 
|  | 344 | * preload some userspace segments into the SLB. | 
|  | 345 | * Almost all 32 and 64bit PowerPC executables are linked at | 
|  | 346 | * 0x10000000 so it makes sense to preload this segment. | 
|  | 347 | */ | 
|  | 348 | if (!is_kernel_addr(exec)) { | 
|  | 349 | if (preload_add(ti, exec)) | 
|  | 350 | slb_allocate_user(mm, exec); | 
|  | 351 | } | 
|  | 352 |  | 
|  | 353 | /* Libraries and mmaps. */ | 
|  | 354 | if (!is_kernel_addr(mm->mmap_base)) { | 
|  | 355 | if (preload_add(ti, mm->mmap_base)) | 
|  | 356 | slb_allocate_user(mm, mm->mmap_base); | 
|  | 357 | } | 
|  | 358 |  | 
|  | 359 | /* see switch_slb */ | 
|  | 360 | asm volatile("isync" : : : "memory"); | 
|  | 361 |  | 
|  | 362 | local_irq_enable(); | 
|  | 363 | } | 
|  | 364 |  | 
|  | 365 | void preload_new_slb_context(unsigned long start, unsigned long sp) | 
|  | 366 | { | 
|  | 367 | struct thread_info *ti = current_thread_info(); | 
|  | 368 | struct mm_struct *mm = current->mm; | 
|  | 369 | unsigned long heap = mm->start_brk; | 
|  | 370 |  | 
|  | 371 | WARN_ON(irqs_disabled()); | 
|  | 372 |  | 
|  | 373 | /* see above */ | 
|  | 374 | if (ti->slb_preload_nr + 3 > SLB_PRELOAD_NR) | 
|  | 375 | return; | 
|  | 376 |  | 
|  | 377 | hard_irq_disable(); | 
|  | 378 |  | 
|  | 379 | /* Userspace entry address. */ | 
|  | 380 | if (!is_kernel_addr(start)) { | 
|  | 381 | if (preload_add(ti, start)) | 
|  | 382 | slb_allocate_user(mm, start); | 
|  | 383 | } | 
|  | 384 |  | 
|  | 385 | /* Top of stack, grows down. */ | 
|  | 386 | if (!is_kernel_addr(sp)) { | 
|  | 387 | if (preload_add(ti, sp)) | 
|  | 388 | slb_allocate_user(mm, sp); | 
|  | 389 | } | 
|  | 390 |  | 
|  | 391 | /* Bottom of heap, grows up. */ | 
|  | 392 | if (heap && !is_kernel_addr(heap)) { | 
|  | 393 | if (preload_add(ti, heap)) | 
|  | 394 | slb_allocate_user(mm, heap); | 
|  | 395 | } | 
|  | 396 |  | 
|  | 397 | /* see switch_slb */ | 
|  | 398 | asm volatile("isync" : : : "memory"); | 
|  | 399 |  | 
|  | 400 | local_irq_enable(); | 
|  | 401 | } | 
|  | 402 |  | 
|  | 403 |  | 
|  | 404 | /* Flush all user entries from the segment table of the current processor. */ | 
|  | 405 | void switch_slb(struct task_struct *tsk, struct mm_struct *mm) | 
|  | 406 | { | 
|  | 407 | struct thread_info *ti = task_thread_info(tsk); | 
|  | 408 | unsigned char i; | 
|  | 409 |  | 
|  | 410 | /* | 
|  | 411 | * We need interrupts hard-disabled here, not just soft-disabled, | 
|  | 412 | * so that a PMU interrupt can't occur, which might try to access | 
|  | 413 | * user memory (to get a stack trace) and possible cause an SLB miss | 
|  | 414 | * which would update the slb_cache/slb_cache_ptr fields in the PACA. | 
|  | 415 | */ | 
|  | 416 | hard_irq_disable(); | 
|  | 417 | asm volatile("isync" : : : "memory"); | 
|  | 418 | if (cpu_has_feature(CPU_FTR_ARCH_300)) { | 
|  | 419 | /* | 
|  | 420 | * SLBIA IH=3 invalidates all Class=1 SLBEs and their | 
|  | 421 | * associated lookaside structures, which matches what | 
|  | 422 | * switch_slb wants. So ARCH_300 does not use the slb | 
|  | 423 | * cache. | 
|  | 424 | */ | 
|  | 425 | asm volatile(PPC_SLBIA(3)); | 
|  | 426 | } else { | 
|  | 427 | unsigned long offset = get_paca()->slb_cache_ptr; | 
|  | 428 |  | 
|  | 429 | if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) && | 
|  | 430 | offset <= SLB_CACHE_ENTRIES) { | 
|  | 431 | unsigned long slbie_data = 0; | 
|  | 432 |  | 
|  | 433 | for (i = 0; i < offset; i++) { | 
|  | 434 | unsigned long ea; | 
|  | 435 |  | 
|  | 436 | ea = (unsigned long) | 
|  | 437 | get_paca()->slb_cache[i] << SID_SHIFT; | 
|  | 438 | /* | 
|  | 439 | * Could assert_slb_presence(true) here, but | 
|  | 440 | * hypervisor or machine check could have come | 
|  | 441 | * in and removed the entry at this point. | 
|  | 442 | */ | 
|  | 443 |  | 
|  | 444 | slbie_data = ea; | 
|  | 445 | slbie_data |= user_segment_size(slbie_data) | 
|  | 446 | << SLBIE_SSIZE_SHIFT; | 
|  | 447 | slbie_data |= SLBIE_C; /* user slbs have C=1 */ | 
|  | 448 | asm volatile("slbie %0" : : "r" (slbie_data)); | 
|  | 449 | } | 
|  | 450 |  | 
|  | 451 | /* Workaround POWER5 < DD2.1 issue */ | 
|  | 452 | if (!cpu_has_feature(CPU_FTR_ARCH_207S) && offset == 1) | 
|  | 453 | asm volatile("slbie %0" : : "r" (slbie_data)); | 
|  | 454 |  | 
|  | 455 | } else { | 
|  | 456 | struct slb_shadow *p = get_slb_shadow(); | 
|  | 457 | unsigned long ksp_esid_data = | 
|  | 458 | be64_to_cpu(p->save_area[KSTACK_INDEX].esid); | 
|  | 459 | unsigned long ksp_vsid_data = | 
|  | 460 | be64_to_cpu(p->save_area[KSTACK_INDEX].vsid); | 
|  | 461 |  | 
|  | 462 | asm volatile(PPC_SLBIA(1) "\n" | 
|  | 463 | "slbmte	%0,%1\n" | 
|  | 464 | "isync" | 
|  | 465 | :: "r"(ksp_vsid_data), | 
|  | 466 | "r"(ksp_esid_data)); | 
|  | 467 |  | 
|  | 468 | get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1; | 
|  | 469 | } | 
|  | 470 |  | 
|  | 471 | get_paca()->slb_cache_ptr = 0; | 
|  | 472 | } | 
|  | 473 | get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap; | 
|  | 474 |  | 
|  | 475 | copy_mm_to_paca(mm); | 
|  | 476 |  | 
|  | 477 | /* | 
|  | 478 | * We gradually age out SLBs after a number of context switches to | 
|  | 479 | * reduce reload overhead of unused entries (like we do with FP/VEC | 
|  | 480 | * reload). Each time we wrap 256 switches, take an entry out of the | 
|  | 481 | * SLB preload cache. | 
|  | 482 | */ | 
|  | 483 | tsk->thread.load_slb++; | 
|  | 484 | if (!tsk->thread.load_slb) { | 
|  | 485 | unsigned long pc = KSTK_EIP(tsk); | 
|  | 486 |  | 
|  | 487 | preload_age(ti); | 
|  | 488 | preload_add(ti, pc); | 
|  | 489 | } | 
|  | 490 |  | 
|  | 491 | for (i = 0; i < ti->slb_preload_nr; i++) { | 
|  | 492 | unsigned char idx; | 
|  | 493 | unsigned long ea; | 
|  | 494 |  | 
|  | 495 | idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR; | 
|  | 496 | ea = (unsigned long)ti->slb_preload_esid[idx] << SID_SHIFT; | 
|  | 497 |  | 
|  | 498 | slb_allocate_user(mm, ea); | 
|  | 499 | } | 
|  | 500 |  | 
|  | 501 | /* | 
|  | 502 | * Synchronize slbmte preloads with possible subsequent user memory | 
|  | 503 | * address accesses by the kernel (user mode won't happen until | 
|  | 504 | * rfid, which is safe). | 
|  | 505 | */ | 
|  | 506 | asm volatile("isync" : : : "memory"); | 
|  | 507 | } | 
|  | 508 |  | 
|  | 509 | void slb_set_size(u16 size) | 
|  | 510 | { | 
|  | 511 | mmu_slb_size = size; | 
|  | 512 | } | 
|  | 513 |  | 
|  | 514 | void slb_initialize(void) | 
|  | 515 | { | 
|  | 516 | unsigned long linear_llp, vmalloc_llp, io_llp; | 
|  | 517 | unsigned long lflags; | 
|  | 518 | static int slb_encoding_inited; | 
|  | 519 | #ifdef CONFIG_SPARSEMEM_VMEMMAP | 
|  | 520 | unsigned long vmemmap_llp; | 
|  | 521 | #endif | 
|  | 522 |  | 
|  | 523 | /* Prepare our SLB miss handler based on our page size */ | 
|  | 524 | linear_llp = mmu_psize_defs[mmu_linear_psize].sllp; | 
|  | 525 | io_llp = mmu_psize_defs[mmu_io_psize].sllp; | 
|  | 526 | vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp; | 
|  | 527 | get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp; | 
|  | 528 | #ifdef CONFIG_SPARSEMEM_VMEMMAP | 
|  | 529 | vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp; | 
|  | 530 | #endif | 
|  | 531 | if (!slb_encoding_inited) { | 
|  | 532 | slb_encoding_inited = 1; | 
|  | 533 | pr_devel("SLB: linear  LLP = %04lx\n", linear_llp); | 
|  | 534 | pr_devel("SLB: io      LLP = %04lx\n", io_llp); | 
|  | 535 | #ifdef CONFIG_SPARSEMEM_VMEMMAP | 
|  | 536 | pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp); | 
|  | 537 | #endif | 
|  | 538 | } | 
|  | 539 |  | 
|  | 540 | get_paca()->stab_rr = SLB_NUM_BOLTED - 1; | 
|  | 541 | get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1; | 
|  | 542 | get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap; | 
|  | 543 |  | 
|  | 544 | lflags = SLB_VSID_KERNEL | linear_llp; | 
|  | 545 |  | 
|  | 546 | /* Invalidate the entire SLB (even entry 0) & all the ERATS */ | 
|  | 547 | asm volatile("isync":::"memory"); | 
|  | 548 | asm volatile("slbmte  %0,%0"::"r" (0) : "memory"); | 
|  | 549 | asm volatile("isync; slbia; isync":::"memory"); | 
|  | 550 | create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX); | 
|  | 551 |  | 
|  | 552 | /* | 
|  | 553 | * For the boot cpu, we're running on the stack in init_thread_union, | 
|  | 554 | * which is in the first segment of the linear mapping, and also | 
|  | 555 | * get_paca()->kstack hasn't been initialized yet. | 
|  | 556 | * For secondary cpus, we need to bolt the kernel stack entry now. | 
|  | 557 | */ | 
|  | 558 | slb_shadow_clear(KSTACK_INDEX); | 
|  | 559 | if (raw_smp_processor_id() != boot_cpuid && | 
|  | 560 | (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET) | 
|  | 561 | create_shadowed_slbe(get_paca()->kstack, | 
|  | 562 | mmu_kernel_ssize, lflags, KSTACK_INDEX); | 
|  | 563 |  | 
|  | 564 | asm volatile("isync":::"memory"); | 
|  | 565 | } | 
|  | 566 |  | 
|  | 567 | static void slb_cache_update(unsigned long esid_data) | 
|  | 568 | { | 
|  | 569 | int slb_cache_index; | 
|  | 570 |  | 
|  | 571 | if (cpu_has_feature(CPU_FTR_ARCH_300)) | 
|  | 572 | return; /* ISAv3.0B and later does not use slb_cache */ | 
|  | 573 |  | 
|  | 574 | /* | 
|  | 575 | * Now update slb cache entries | 
|  | 576 | */ | 
|  | 577 | slb_cache_index = local_paca->slb_cache_ptr; | 
|  | 578 | if (slb_cache_index < SLB_CACHE_ENTRIES) { | 
|  | 579 | /* | 
|  | 580 | * We have space in slb cache for optimized switch_slb(). | 
|  | 581 | * Top 36 bits from esid_data as per ISA | 
|  | 582 | */ | 
|  | 583 | local_paca->slb_cache[slb_cache_index++] = esid_data >> 28; | 
|  | 584 | local_paca->slb_cache_ptr++; | 
|  | 585 | } else { | 
|  | 586 | /* | 
|  | 587 | * Our cache is full and the current cache content strictly | 
|  | 588 | * doesn't indicate the active SLB conents. Bump the ptr | 
|  | 589 | * so that switch_slb() will ignore the cache. | 
|  | 590 | */ | 
|  | 591 | local_paca->slb_cache_ptr = SLB_CACHE_ENTRIES + 1; | 
|  | 592 | } | 
|  | 593 | } | 
|  | 594 |  | 
|  | 595 | static enum slb_index alloc_slb_index(bool kernel) | 
|  | 596 | { | 
|  | 597 | enum slb_index index; | 
|  | 598 |  | 
|  | 599 | /* | 
|  | 600 | * The allocation bitmaps can become out of synch with the SLB | 
|  | 601 | * when the _switch code does slbie when bolting a new stack | 
|  | 602 | * segment and it must not be anywhere else in the SLB. This leaves | 
|  | 603 | * a kernel allocated entry that is unused in the SLB. With very | 
|  | 604 | * large systems or small segment sizes, the bitmaps could slowly | 
|  | 605 | * fill with these entries. They will eventually be cleared out | 
|  | 606 | * by the round robin allocator in that case, so it's probably not | 
|  | 607 | * worth accounting for. | 
|  | 608 | */ | 
|  | 609 |  | 
|  | 610 | /* | 
|  | 611 | * SLBs beyond 32 entries are allocated with stab_rr only | 
|  | 612 | * POWER7/8/9 have 32 SLB entries, this could be expanded if a | 
|  | 613 | * future CPU has more. | 
|  | 614 | */ | 
|  | 615 | if (local_paca->slb_used_bitmap != U32_MAX) { | 
|  | 616 | index = ffz(local_paca->slb_used_bitmap); | 
|  | 617 | local_paca->slb_used_bitmap |= 1U << index; | 
|  | 618 | if (kernel) | 
|  | 619 | local_paca->slb_kern_bitmap |= 1U << index; | 
|  | 620 | } else { | 
|  | 621 | /* round-robin replacement of slb starting at SLB_NUM_BOLTED. */ | 
|  | 622 | index = local_paca->stab_rr; | 
|  | 623 | if (index < (mmu_slb_size - 1)) | 
|  | 624 | index++; | 
|  | 625 | else | 
|  | 626 | index = SLB_NUM_BOLTED; | 
|  | 627 | local_paca->stab_rr = index; | 
|  | 628 | if (index < 32) { | 
|  | 629 | if (kernel) | 
|  | 630 | local_paca->slb_kern_bitmap |= 1U << index; | 
|  | 631 | else | 
|  | 632 | local_paca->slb_kern_bitmap &= ~(1U << index); | 
|  | 633 | } | 
|  | 634 | } | 
|  | 635 | BUG_ON(index < SLB_NUM_BOLTED); | 
|  | 636 |  | 
|  | 637 | return index; | 
|  | 638 | } | 
|  | 639 |  | 
|  | 640 | static long slb_insert_entry(unsigned long ea, unsigned long context, | 
|  | 641 | unsigned long flags, int ssize, bool kernel) | 
|  | 642 | { | 
|  | 643 | unsigned long vsid; | 
|  | 644 | unsigned long vsid_data, esid_data; | 
|  | 645 | enum slb_index index; | 
|  | 646 |  | 
|  | 647 | vsid = get_vsid(context, ea, ssize); | 
|  | 648 | if (!vsid) | 
|  | 649 | return -EFAULT; | 
|  | 650 |  | 
|  | 651 | /* | 
|  | 652 | * There must not be a kernel SLB fault in alloc_slb_index or before | 
|  | 653 | * slbmte here or the allocation bitmaps could get out of whack with | 
|  | 654 | * the SLB. | 
|  | 655 | * | 
|  | 656 | * User SLB faults or preloads take this path which might get inlined | 
|  | 657 | * into the caller, so add compiler barriers here to ensure unsafe | 
|  | 658 | * memory accesses do not come between. | 
|  | 659 | */ | 
|  | 660 | barrier(); | 
|  | 661 |  | 
|  | 662 | index = alloc_slb_index(kernel); | 
|  | 663 |  | 
|  | 664 | vsid_data = __mk_vsid_data(vsid, ssize, flags); | 
|  | 665 | esid_data = mk_esid_data(ea, ssize, index); | 
|  | 666 |  | 
|  | 667 | /* | 
|  | 668 | * No need for an isync before or after this slbmte. The exception | 
|  | 669 | * we enter with and the rfid we exit with are context synchronizing. | 
|  | 670 | * User preloads should add isync afterwards in case the kernel | 
|  | 671 | * accesses user memory before it returns to userspace with rfid. | 
|  | 672 | */ | 
|  | 673 | assert_slb_presence(false, ea); | 
|  | 674 | asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)); | 
|  | 675 |  | 
|  | 676 | barrier(); | 
|  | 677 |  | 
|  | 678 | if (!kernel) | 
|  | 679 | slb_cache_update(esid_data); | 
|  | 680 |  | 
|  | 681 | return 0; | 
|  | 682 | } | 
|  | 683 |  | 
|  | 684 | static long slb_allocate_kernel(unsigned long ea, unsigned long id) | 
|  | 685 | { | 
|  | 686 | unsigned long context; | 
|  | 687 | unsigned long flags; | 
|  | 688 | int ssize; | 
|  | 689 |  | 
|  | 690 | if (id == LINEAR_MAP_REGION_ID) { | 
|  | 691 |  | 
|  | 692 | /* We only support upto MAX_PHYSMEM_BITS */ | 
|  | 693 | if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS)) | 
|  | 694 | return -EFAULT; | 
|  | 695 |  | 
|  | 696 | flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp; | 
|  | 697 |  | 
|  | 698 | #ifdef CONFIG_SPARSEMEM_VMEMMAP | 
|  | 699 | } else if (id == VMEMMAP_REGION_ID) { | 
|  | 700 |  | 
|  | 701 | if (ea >= H_VMEMMAP_END) | 
|  | 702 | return -EFAULT; | 
|  | 703 |  | 
|  | 704 | flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp; | 
|  | 705 | #endif | 
|  | 706 | } else if (id == VMALLOC_REGION_ID) { | 
|  | 707 |  | 
|  | 708 | if (ea >= H_VMALLOC_END) | 
|  | 709 | return -EFAULT; | 
|  | 710 |  | 
|  | 711 | flags = local_paca->vmalloc_sllp; | 
|  | 712 |  | 
|  | 713 | } else if (id == IO_REGION_ID) { | 
|  | 714 |  | 
|  | 715 | if (ea >= H_KERN_IO_END) | 
|  | 716 | return -EFAULT; | 
|  | 717 |  | 
|  | 718 | flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp; | 
|  | 719 |  | 
|  | 720 | } else { | 
|  | 721 | return -EFAULT; | 
|  | 722 | } | 
|  | 723 |  | 
|  | 724 | ssize = MMU_SEGSIZE_1T; | 
|  | 725 | if (!mmu_has_feature(MMU_FTR_1T_SEGMENT)) | 
|  | 726 | ssize = MMU_SEGSIZE_256M; | 
|  | 727 |  | 
|  | 728 | context = get_kernel_context(ea); | 
|  | 729 |  | 
|  | 730 | return slb_insert_entry(ea, context, flags, ssize, true); | 
|  | 731 | } | 
|  | 732 |  | 
|  | 733 | static long slb_allocate_user(struct mm_struct *mm, unsigned long ea) | 
|  | 734 | { | 
|  | 735 | unsigned long context; | 
|  | 736 | unsigned long flags; | 
|  | 737 | int bpsize; | 
|  | 738 | int ssize; | 
|  | 739 |  | 
|  | 740 | /* | 
|  | 741 | * consider this as bad access if we take a SLB miss | 
|  | 742 | * on an address above addr limit. | 
|  | 743 | */ | 
|  | 744 | if (ea >= mm_ctx_slb_addr_limit(&mm->context)) | 
|  | 745 | return -EFAULT; | 
|  | 746 |  | 
|  | 747 | context = get_user_context(&mm->context, ea); | 
|  | 748 | if (!context) | 
|  | 749 | return -EFAULT; | 
|  | 750 |  | 
|  | 751 | if (unlikely(ea >= H_PGTABLE_RANGE)) { | 
|  | 752 | WARN_ON(1); | 
|  | 753 | return -EFAULT; | 
|  | 754 | } | 
|  | 755 |  | 
|  | 756 | ssize = user_segment_size(ea); | 
|  | 757 |  | 
|  | 758 | bpsize = get_slice_psize(mm, ea); | 
|  | 759 | flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp; | 
|  | 760 |  | 
|  | 761 | return slb_insert_entry(ea, context, flags, ssize, false); | 
|  | 762 | } | 
|  | 763 |  | 
|  | 764 | long do_slb_fault(struct pt_regs *regs, unsigned long ea) | 
|  | 765 | { | 
|  | 766 | unsigned long id = get_region_id(ea); | 
|  | 767 |  | 
|  | 768 | /* IRQs are not reconciled here, so can't check irqs_disabled */ | 
|  | 769 | VM_WARN_ON(mfmsr() & MSR_EE); | 
|  | 770 |  | 
|  | 771 | if (unlikely(!(regs->msr & MSR_RI))) | 
|  | 772 | return -EINVAL; | 
|  | 773 |  | 
|  | 774 | /* | 
|  | 775 | * SLB kernel faults must be very careful not to touch anything | 
|  | 776 | * that is not bolted. E.g., PACA and global variables are okay, | 
|  | 777 | * mm->context stuff is not. | 
|  | 778 | * | 
|  | 779 | * SLB user faults can access all of kernel memory, but must be | 
|  | 780 | * careful not to touch things like IRQ state because it is not | 
|  | 781 | * "reconciled" here. The difficulty is that we must use | 
|  | 782 | * fast_exception_return to return from kernel SLB faults without | 
|  | 783 | * looking at possible non-bolted memory. We could test user vs | 
|  | 784 | * kernel faults in the interrupt handler asm and do a full fault, | 
|  | 785 | * reconcile, ret_from_except for user faults which would make them | 
|  | 786 | * first class kernel code. But for performance it's probably nicer | 
|  | 787 | * if they go via fast_exception_return too. | 
|  | 788 | */ | 
|  | 789 | if (id >= LINEAR_MAP_REGION_ID) { | 
|  | 790 | long err; | 
|  | 791 | #ifdef CONFIG_DEBUG_VM | 
|  | 792 | /* Catch recursive kernel SLB faults. */ | 
|  | 793 | BUG_ON(local_paca->in_kernel_slb_handler); | 
|  | 794 | local_paca->in_kernel_slb_handler = 1; | 
|  | 795 | #endif | 
|  | 796 | err = slb_allocate_kernel(ea, id); | 
|  | 797 | #ifdef CONFIG_DEBUG_VM | 
|  | 798 | local_paca->in_kernel_slb_handler = 0; | 
|  | 799 | #endif | 
|  | 800 | return err; | 
|  | 801 | } else { | 
|  | 802 | struct mm_struct *mm = current->mm; | 
|  | 803 | long err; | 
|  | 804 |  | 
|  | 805 | if (unlikely(!mm)) | 
|  | 806 | return -EFAULT; | 
|  | 807 |  | 
|  | 808 | err = slb_allocate_user(mm, ea); | 
|  | 809 | if (!err) | 
|  | 810 | preload_add(current_thread_info(), ea); | 
|  | 811 |  | 
|  | 812 | return err; | 
|  | 813 | } | 
|  | 814 | } | 
|  | 815 |  | 
|  | 816 | void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err) | 
|  | 817 | { | 
|  | 818 | if (err == -EFAULT) { | 
|  | 819 | if (user_mode(regs)) | 
|  | 820 | _exception(SIGSEGV, regs, SEGV_BNDERR, ea); | 
|  | 821 | else | 
|  | 822 | bad_page_fault(regs, ea, SIGSEGV); | 
|  | 823 | } else if (err == -EINVAL) { | 
|  | 824 | unrecoverable_exception(regs); | 
|  | 825 | } else { | 
|  | 826 | BUG(); | 
|  | 827 | } | 
|  | 828 | } |