1/* SPDX-License-Identifier: GPL-2.0-or-later */ 2#ifndef _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ 3#define _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ 4/* 5 * PowerPC64 memory management structures 6 * 7 * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com> 8 * PPC64 rework. 9 */ 10 11#include <asm/page.h> 12#include <asm/bug.h> 13#include <asm/asm-const.h> 14 15/* 16 * This is necessary to get the definition of PGTABLE_RANGE which we 17 * need for various slices related matters. Note that this isn't the 18 * complete pgtable.h but only a portion of it. 19 */ 20#include <asm/book3s/64/pgtable.h> 21#include <asm/bug.h> 22#include <asm/task_size_64.h> 23#include <asm/cpu_has_feature.h> 24 25/* 26 * SLB 27 */ 28 29#define SLB_NUM_BOLTED 2 30#define SLB_CACHE_ENTRIES 8 31#define SLB_MIN_SIZE 32 32 33/* Bits in the SLB ESID word */ 34#define SLB_ESID_V ASM_CONST(0x0000000008000000) /* valid */ 35 36/* Bits in the SLB VSID word */ 37#define SLB_VSID_SHIFT 12 38#define SLB_VSID_SHIFT_256M SLB_VSID_SHIFT 39#define SLB_VSID_SHIFT_1T 24 40#define SLB_VSID_SSIZE_SHIFT 62 41#define SLB_VSID_B ASM_CONST(0xc000000000000000) 42#define SLB_VSID_B_256M ASM_CONST(0x0000000000000000) 43#define SLB_VSID_B_1T ASM_CONST(0x4000000000000000) 44#define SLB_VSID_KS ASM_CONST(0x0000000000000800) 45#define SLB_VSID_KP ASM_CONST(0x0000000000000400) 46#define SLB_VSID_N ASM_CONST(0x0000000000000200) /* no-execute */ 47#define SLB_VSID_L ASM_CONST(0x0000000000000100) 48#define SLB_VSID_C ASM_CONST(0x0000000000000080) /* class */ 49#define SLB_VSID_LP ASM_CONST(0x0000000000000030) 50#define SLB_VSID_LP_00 ASM_CONST(0x0000000000000000) 51#define SLB_VSID_LP_01 ASM_CONST(0x0000000000000010) 52#define SLB_VSID_LP_10 ASM_CONST(0x0000000000000020) 53#define SLB_VSID_LP_11 ASM_CONST(0x0000000000000030) 54#define SLB_VSID_LLP (SLB_VSID_L|SLB_VSID_LP) 55 56#define SLB_VSID_KERNEL (SLB_VSID_KP) 57#define SLB_VSID_USER (SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C) 58 59#define SLBIE_C (0x08000000) 60#define SLBIE_SSIZE_SHIFT 25 61 62/* 63 * Hash table 64 */ 65 66#define HPTES_PER_GROUP 8 67 68#define HPTE_V_SSIZE_SHIFT 62 69#define HPTE_V_AVPN_SHIFT 7 70#define HPTE_V_COMMON_BITS ASM_CONST(0x000fffffffffffff) 71#define HPTE_V_AVPN ASM_CONST(0x3fffffffffffff80) 72#define HPTE_V_AVPN_3_0 ASM_CONST(0x000fffffffffff80) 73#define HPTE_V_AVPN_VAL(x) (((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT) 74#define HPTE_V_COMPARE(x,y) (!(((x) ^ (y)) & 0xffffffffffffff80UL)) 75#define HPTE_V_BOLTED ASM_CONST(0x0000000000000010) 76#define HPTE_V_LOCK ASM_CONST(0x0000000000000008) 77#define HPTE_V_LARGE ASM_CONST(0x0000000000000004) 78#define HPTE_V_SECONDARY ASM_CONST(0x0000000000000002) 79#define HPTE_V_VALID ASM_CONST(0x0000000000000001) 80 81/* 82 * ISA 3.0 has a different HPTE format. 83 */ 84#define HPTE_R_3_0_SSIZE_SHIFT 58 85#define HPTE_R_3_0_SSIZE_MASK (3ull << HPTE_R_3_0_SSIZE_SHIFT) 86#define HPTE_R_PP0 ASM_CONST(0x8000000000000000) 87#define HPTE_R_TS ASM_CONST(0x4000000000000000) 88#define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) 89#define HPTE_R_KEY_BIT4 ASM_CONST(0x2000000000000000) 90#define HPTE_R_KEY_BIT3 ASM_CONST(0x1000000000000000) 91#define HPTE_R_RPN_SHIFT 12 92#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) 93#define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000) 94#define HPTE_R_PP ASM_CONST(0x0000000000000003) 95#define HPTE_R_PPP ASM_CONST(0x8000000000000003) 96#define HPTE_R_N ASM_CONST(0x0000000000000004) 97#define HPTE_R_G ASM_CONST(0x0000000000000008) 98#define HPTE_R_M ASM_CONST(0x0000000000000010) 99#define HPTE_R_I ASM_CONST(0x0000000000000020) 100#define HPTE_R_W ASM_CONST(0x0000000000000040) 101#define HPTE_R_WIMG ASM_CONST(0x0000000000000078) 102#define HPTE_R_C ASM_CONST(0x0000000000000080) 103#define HPTE_R_R ASM_CONST(0x0000000000000100) 104#define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) 105#define HPTE_R_KEY_BIT2 ASM_CONST(0x0000000000000800) 106#define HPTE_R_KEY_BIT1 ASM_CONST(0x0000000000000400) 107#define HPTE_R_KEY_BIT0 ASM_CONST(0x0000000000000200) 108#define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI) 109 110#define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) 111#define HPTE_V_VRMA_MASK ASM_CONST(0x4001ffffff000000) 112 113/* Values for PP (assumes Ks=0, Kp=1) */ 114#define PP_RWXX 0 /* Supervisor read/write, User none */ 115#define PP_RWRX 1 /* Supervisor read/write, User read */ 116#define PP_RWRW 2 /* Supervisor read/write, User read/write */ 117#define PP_RXRX 3 /* Supervisor read, User read */ 118#define PP_RXXX (HPTE_R_PP0 | 2) /* Supervisor read, user none */ 119 120/* Fields for tlbiel instruction in architecture 2.06 */ 121#define TLBIEL_INVAL_SEL_MASK 0xc00 /* invalidation selector */ 122#define TLBIEL_INVAL_PAGE 0x000 /* invalidate a single page */ 123#define TLBIEL_INVAL_SET_LPID 0x800 /* invalidate a set for current LPID */ 124#define TLBIEL_INVAL_SET 0xc00 /* invalidate a set for all LPIDs */ 125#define TLBIEL_INVAL_SET_MASK 0xfff000 /* set number to inval. */ 126#define TLBIEL_INVAL_SET_SHIFT 12 127 128#define POWER7_TLB_SETS 128 /* # sets in POWER7 TLB */ 129#define POWER8_TLB_SETS 512 /* # sets in POWER8 TLB */ 130#define POWER9_TLB_SETS_HASH 256 /* # sets in POWER9 TLB Hash mode */ 131#define POWER9_TLB_SETS_RADIX 128 /* # sets in POWER9 TLB Radix mode */ 132 133#ifndef __ASSEMBLY__ 134 135struct mmu_hash_ops { 136 void (*hpte_invalidate)(unsigned long slot, 137 unsigned long vpn, 138 int bpsize, int apsize, 139 int ssize, int local); 140 long (*hpte_updatepp)(unsigned long slot, 141 unsigned long newpp, 142 unsigned long vpn, 143 int bpsize, int apsize, 144 int ssize, unsigned long flags); 145 void (*hpte_updateboltedpp)(unsigned long newpp, 146 unsigned long ea, 147 int psize, int ssize); 148 long (*hpte_insert)(unsigned long hpte_group, 149 unsigned long vpn, 150 unsigned long prpn, 151 unsigned long rflags, 152 unsigned long vflags, 153 int psize, int apsize, 154 int ssize); 155 long (*hpte_remove)(unsigned long hpte_group); 156 int (*hpte_removebolted)(unsigned long ea, 157 int psize, int ssize); 158 void (*flush_hash_range)(unsigned long number, int local); 159 void (*hugepage_invalidate)(unsigned long vsid, 160 unsigned long addr, 161 unsigned char *hpte_slot_array, 162 int psize, int ssize, int local); 163 int (*resize_hpt)(unsigned long shift); 164 /* 165 * Special for kexec. 166 * To be called in real mode with interrupts disabled. No locks are 167 * taken as such, concurrent access on pre POWER5 hardware could result 168 * in a deadlock. 169 * The linear mapping is destroyed as well. 170 */ 171 void (*hpte_clear_all)(void); 172}; 173extern struct mmu_hash_ops mmu_hash_ops; 174 175struct hash_pte { 176 __be64 v; 177 __be64 r; 178}; 179 180extern struct hash_pte *htab_address; 181extern unsigned long htab_size_bytes; 182extern unsigned long htab_hash_mask; 183 184 185static inline int shift_to_mmu_psize(unsigned int shift) 186{ 187 int psize; 188 189 for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) 190 if (mmu_psize_defs[psize].shift == shift) 191 return psize; 192 return -1; 193} 194 195static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) 196{ 197 if (mmu_psize_defs[mmu_psize].shift) 198 return mmu_psize_defs[mmu_psize].shift; 199 BUG(); 200} 201 202static inline unsigned int ap_to_shift(unsigned long ap) 203{ 204 int psize; 205 206 for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { 207 if (mmu_psize_defs[psize].ap == ap) 208 return mmu_psize_defs[psize].shift; 209 } 210 211 return -1; 212} 213 214static inline unsigned long get_sllp_encoding(int psize) 215{ 216 unsigned long sllp; 217 218 sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) | 219 ((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4); 220 return sllp; 221} 222 223#endif /* __ASSEMBLY__ */ 224 225/* 226 * Segment sizes. 227 * These are the values used by hardware in the B field of 228 * SLB entries and the first dword of MMU hashtable entries. 229 * The B field is 2 bits; the values 2 and 3 are unused and reserved. 230 */ 231#define MMU_SEGSIZE_256M 0 232#define MMU_SEGSIZE_1T 1 233 234/* 235 * encode page number shift. 236 * in order to fit the 78 bit va in a 64 bit variable we shift the va by 237 * 12 bits. This enable us to address upto 76 bit va. 238 * For hpt hash from a va we can ignore the page size bits of va and for 239 * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure 240 * we work in all cases including 4k page size. 241 */ 242#define VPN_SHIFT 12 243 244/* 245 * HPTE Large Page (LP) details 246 */ 247#define LP_SHIFT 12 248#define LP_BITS 8 249#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT) 250 251#ifndef __ASSEMBLY__ 252 253static inline int slb_vsid_shift(int ssize) 254{ 255 if (ssize == MMU_SEGSIZE_256M) 256 return SLB_VSID_SHIFT; 257 return SLB_VSID_SHIFT_1T; 258} 259 260static inline int segment_shift(int ssize) 261{ 262 if (ssize == MMU_SEGSIZE_256M) 263 return SID_SHIFT; 264 return SID_SHIFT_1T; 265} 266 267/* 268 * This array is indexed by the LP field of the HPTE second dword. 269 * Since this field may contain some RPN bits, some entries are 270 * replicated so that we get the same value irrespective of RPN. 271 * The top 4 bits are the page size index (MMU_PAGE_*) for the 272 * actual page size, the bottom 4 bits are the base page size. 273 */ 274extern u8 hpte_page_sizes[1 << LP_BITS]; 275 276static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l, 277 bool is_base_size) 278{ 279 unsigned int i, lp; 280 281 if (!(h & HPTE_V_LARGE)) 282 return 1ul << 12; 283 284 /* Look at the 8 bit LP value */ 285 lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); 286 i = hpte_page_sizes[lp]; 287 if (!i) 288 return 0; 289 if (!is_base_size) 290 i >>= 4; 291 return 1ul << mmu_psize_defs[i & 0xf].shift; 292} 293 294static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) 295{ 296 return __hpte_page_size(h, l, 0); 297} 298 299static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l) 300{ 301 return __hpte_page_size(h, l, 1); 302} 303 304/* 305 * The current system page and segment sizes 306 */ 307extern int mmu_kernel_ssize; 308extern int mmu_highuser_ssize; 309extern u16 mmu_slb_size; 310extern unsigned long tce_alloc_start, tce_alloc_end; 311 312/* 313 * If the processor supports 64k normal pages but not 64k cache 314 * inhibited pages, we have to be prepared to switch processes 315 * to use 4k pages when they create cache-inhibited mappings. 316 * If this is the case, mmu_ci_restrictions will be set to 1. 317 */ 318extern int mmu_ci_restrictions; 319 320/* 321 * This computes the AVPN and B fields of the first dword of a HPTE, 322 * for use when we want to match an existing PTE. The bottom 7 bits 323 * of the returned value are zero. 324 */ 325static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize, 326 int ssize) 327{ 328 unsigned long v; 329 /* 330 * The AVA field omits the low-order 23 bits of the 78 bits VA. 331 * These bits are not needed in the PTE, because the 332 * low-order b of these bits are part of the byte offset 333 * into the virtual page and, if b < 23, the high-order 334 * 23-b of these bits are always used in selecting the 335 * PTEGs to be searched 336 */ 337 v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm); 338 v <<= HPTE_V_AVPN_SHIFT; 339 v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT; 340 return v; 341} 342 343/* 344 * ISA v3.0 defines a new HPTE format, which differs from the old 345 * format in having smaller AVPN and ARPN fields, and the B field 346 * in the second dword instead of the first. 347 */ 348static inline unsigned long hpte_old_to_new_v(unsigned long v) 349{ 350 /* trim AVPN, drop B */ 351 return v & HPTE_V_COMMON_BITS; 352} 353 354static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r) 355{ 356 /* move B field from 1st to 2nd dword, trim ARPN */ 357 return (r & ~HPTE_R_3_0_SSIZE_MASK) | 358 (((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT); 359} 360 361static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r) 362{ 363 /* insert B field */ 364 return (v & HPTE_V_COMMON_BITS) | 365 ((r & HPTE_R_3_0_SSIZE_MASK) << 366 (HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT)); 367} 368 369static inline unsigned long hpte_new_to_old_r(unsigned long r) 370{ 371 /* clear out B field */ 372 return r & ~HPTE_R_3_0_SSIZE_MASK; 373} 374 375static inline unsigned long hpte_get_old_v(struct hash_pte *hptep) 376{ 377 unsigned long hpte_v; 378 379 hpte_v = be64_to_cpu(hptep->v); 380 if (cpu_has_feature(CPU_FTR_ARCH_300)) 381 hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); 382 return hpte_v; 383} 384 385/* 386 * This function sets the AVPN and L fields of the HPTE appropriately 387 * using the base page size and actual page size. 388 */ 389static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize, 390 int actual_psize, int ssize) 391{ 392 unsigned long v; 393 v = hpte_encode_avpn(vpn, base_psize, ssize); 394 if (actual_psize != MMU_PAGE_4K) 395 v |= HPTE_V_LARGE; 396 return v; 397} 398 399/* 400 * This function sets the ARPN, and LP fields of the HPTE appropriately 401 * for the page size. We assume the pa is already "clean" that is properly 402 * aligned for the requested page size 403 */ 404static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize, 405 int actual_psize) 406{ 407 /* A 4K page needs no special encoding */ 408 if (actual_psize == MMU_PAGE_4K) 409 return pa & HPTE_R_RPN; 410 else { 411 unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize]; 412 unsigned int shift = mmu_psize_defs[actual_psize].shift; 413 return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT); 414 } 415} 416 417/* 418 * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size. 419 */ 420static inline unsigned long hpt_vpn(unsigned long ea, 421 unsigned long vsid, int ssize) 422{ 423 unsigned long mask; 424 int s_shift = segment_shift(ssize); 425 426 mask = (1ul << (s_shift - VPN_SHIFT)) - 1; 427 return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask); 428} 429 430/* 431 * This hashes a virtual address 432 */ 433static inline unsigned long hpt_hash(unsigned long vpn, 434 unsigned int shift, int ssize) 435{ 436 unsigned long mask; 437 unsigned long hash, vsid; 438 439 /* VPN_SHIFT can be atmost 12 */ 440 if (ssize == MMU_SEGSIZE_256M) { 441 mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1; 442 hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^ 443 ((vpn & mask) >> (shift - VPN_SHIFT)); 444 } else { 445 mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1; 446 vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT); 447 hash = vsid ^ (vsid << 25) ^ 448 ((vpn & mask) >> (shift - VPN_SHIFT)) ; 449 } 450 return hash & 0x7fffffffffUL; 451} 452 453#define HPTE_LOCAL_UPDATE 0x1 454#define HPTE_NOHPTE_UPDATE 0x2 455 456extern int __hash_page_4K(unsigned long ea, unsigned long access, 457 unsigned long vsid, pte_t *ptep, unsigned long trap, 458 unsigned long flags, int ssize, int subpage_prot); 459extern int __hash_page_64K(unsigned long ea, unsigned long access, 460 unsigned long vsid, pte_t *ptep, unsigned long trap, 461 unsigned long flags, int ssize); 462struct mm_struct; 463unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap); 464extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, 465 unsigned long access, unsigned long trap, 466 unsigned long flags); 467extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap, 468 unsigned long dsisr); 469int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, 470 pte_t *ptep, unsigned long trap, unsigned long flags, 471 int ssize, unsigned int shift, unsigned int mmu_psize); 472#ifdef CONFIG_TRANSPARENT_HUGEPAGE 473extern int __hash_page_thp(unsigned long ea, unsigned long access, 474 unsigned long vsid, pmd_t *pmdp, unsigned long trap, 475 unsigned long flags, int ssize, unsigned int psize); 476#else 477static inline int __hash_page_thp(unsigned long ea, unsigned long access, 478 unsigned long vsid, pmd_t *pmdp, 479 unsigned long trap, unsigned long flags, 480 int ssize, unsigned int psize) 481{ 482 BUG(); 483 return -1; 484} 485#endif 486extern void hash_failure_debug(unsigned long ea, unsigned long access, 487 unsigned long vsid, unsigned long trap, 488 int ssize, int psize, int lpsize, 489 unsigned long pte); 490extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend, 491 unsigned long pstart, unsigned long prot, 492 int psize, int ssize); 493int htab_remove_mapping(unsigned long vstart, unsigned long vend, 494 int psize, int ssize); 495extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages); 496extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr); 497 498extern void hash__setup_new_exec(void); 499 500#ifdef CONFIG_PPC_PSERIES 501void hpte_init_pseries(void); 502#else 503static inline void hpte_init_pseries(void) { } 504#endif 505 506extern void hpte_init_native(void); 507 508struct slb_entry { 509 u64 esid; 510 u64 vsid; 511}; 512 513extern void slb_initialize(void); 514void slb_flush_and_restore_bolted(void); 515void slb_flush_all_realmode(void); 516void __slb_restore_bolted_realmode(void); 517void slb_restore_bolted_realmode(void); 518void slb_save_contents(struct slb_entry *slb_ptr); 519void slb_dump_contents(struct slb_entry *slb_ptr); 520 521extern void slb_vmalloc_update(void); 522extern void slb_set_size(u16 size); 523#endif /* __ASSEMBLY__ */ 524 525/* 526 * VSID allocation (256MB segment) 527 * 528 * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated 529 * from mmu context id and effective segment id of the address. 530 * 531 * For user processes max context id is limited to MAX_USER_CONTEXT. 532 * more details in get_user_context 533 * 534 * For kernel space get_kernel_context 535 * 536 * The proto-VSIDs are then scrambled into real VSIDs with the 537 * multiplicative hash: 538 * 539 * VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS 540 * 541 * VSID_MULTIPLIER is prime, so in particular it is 542 * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. 543 * Because the modulus is 2^n-1 we can compute it efficiently without 544 * a divide or extra multiply (see below). The scramble function gives 545 * robust scattering in the hash table (at least based on some initial 546 * results). 547 * 548 * We use VSID 0 to indicate an invalid VSID. The means we can't use context id 549 * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which 550 * will produce a VSID of 0. 551 * 552 * We also need to avoid the last segment of the last context, because that 553 * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 554 * because of the modulo operation in vsid scramble. 555 */ 556 557/* 558 * Max Va bits we support as of now is 68 bits. We want 19 bit 559 * context ID. 560 * Restrictions: 561 * GPU has restrictions of not able to access beyond 128TB 562 * (47 bit effective address). We also cannot do more than 20bit PID. 563 * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS 564 * to 16 bits (ie, we can only have 2^16 pids at the same time). 565 */ 566#define VA_BITS 68 567#define CONTEXT_BITS 19 568#define ESID_BITS (VA_BITS - (SID_SHIFT + CONTEXT_BITS)) 569#define ESID_BITS_1T (VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS)) 570 571#define ESID_BITS_MASK ((1 << ESID_BITS) - 1) 572#define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1) 573 574/* 575 * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need 576 * to use more than one context for linear mapping the kernel. 577 * For vmalloc and memmap, we use just one context with 512TB. With 64 byte 578 * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). 579 */ 580#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) 581#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) 582#else 583#define MAX_KERNEL_CTX_CNT 1 584#endif 585 586#define MAX_VMALLOC_CTX_CNT 1 587#define MAX_IO_CTX_CNT 1 588#define MAX_VMEMMAP_CTX_CNT 1 589 590/* 591 * 256MB segment 592 * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments 593 * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts 594 * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each 595 * context maps 2^49 bytes (512TB). 596 * 597 * We also need to avoid the last segment of the last context, because that 598 * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 599 * because of the modulo operation in vsid scramble. 600 * 601 */ 602#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) 603 604// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel 605#define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ 606 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) 607 608/* 609 * For platforms that support on 65bit VA we limit the context bits 610 */ 611#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2) 612 613/* 614 * This should be computed such that protovosid * vsid_mulitplier 615 * doesn't overflow 64 bits. The vsid_mutliplier should also be 616 * co-prime to vsid_modulus. We also need to make sure that number 617 * of bits in multiplied result (dividend) is less than twice the number of 618 * protovsid bits for our modulus optmization to work. 619 * 620 * The below table shows the current values used. 621 * |-------+------------+----------------------+------------+-------------------| 622 * | | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS | 623 * |-------+------------+----------------------+------------+-------------------| 624 * | 1T | 24 | 25 | 49 | 50 | 625 * |-------+------------+----------------------+------------+-------------------| 626 * | 256MB | 24 | 37 | 61 | 74 | 627 * |-------+------------+----------------------+------------+-------------------| 628 * 629 * |-------+------------+----------------------+------------+--------------------| 630 * | | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS | 631 * |-------+------------+----------------------+------------+--------------------| 632 * | 1T | 24 | 28 | 52 | 56 | 633 * |-------+------------+----------------------+------------+--------------------| 634 * | 256MB | 24 | 40 | 64 | 80 | 635 * |-------+------------+----------------------+------------+--------------------| 636 * 637 */ 638#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ 639#define VSID_BITS_256M (VA_BITS - SID_SHIFT) 640#define VSID_BITS_65_256M (65 - SID_SHIFT) 641/* 642 * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS 643 */ 644#define VSID_MULINV_256M ASM_CONST(665548017062) 645 646#define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ 647#define VSID_BITS_1T (VA_BITS - SID_SHIFT_1T) 648#define VSID_BITS_65_1T (65 - SID_SHIFT_1T) 649#define VSID_MULINV_1T ASM_CONST(209034062) 650 651/* 1TB VSID reserved for VRMA */ 652#define VRMA_VSID 0x1ffffffUL 653#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) 654 655/* 4 bits per slice and we have one slice per 1TB */ 656#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41) 657#define LOW_SLICE_ARRAY_SZ (BITS_PER_LONG / BITS_PER_BYTE) 658#define TASK_SLICE_ARRAY_SZ(x) ((x)->hash_context->slb_addr_limit >> 41) 659#ifndef __ASSEMBLY__ 660 661#ifdef CONFIG_PPC_SUBPAGE_PROT 662/* 663 * For the sub-page protection option, we extend the PGD with one of 664 * these. Basically we have a 3-level tree, with the top level being 665 * the protptrs array. To optimize speed and memory consumption when 666 * only addresses < 4GB are being protected, pointers to the first 667 * four pages of sub-page protection words are stored in the low_prot 668 * array. 669 * Each page of sub-page protection words protects 1GB (4 bytes 670 * protects 64k). For the 3-level tree, each page of pointers then 671 * protects 8TB. 672 */ 673struct subpage_prot_table { 674 unsigned long maxaddr; /* only addresses < this are protected */ 675 unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)]; 676 unsigned int *low_prot[4]; 677}; 678 679#define SBP_L1_BITS (PAGE_SHIFT - 2) 680#define SBP_L2_BITS (PAGE_SHIFT - 3) 681#define SBP_L1_COUNT (1 << SBP_L1_BITS) 682#define SBP_L2_COUNT (1 << SBP_L2_BITS) 683#define SBP_L2_SHIFT (PAGE_SHIFT + SBP_L1_BITS) 684#define SBP_L3_SHIFT (SBP_L2_SHIFT + SBP_L2_BITS) 685 686extern void subpage_prot_free(struct mm_struct *mm); 687#else 688static inline void subpage_prot_free(struct mm_struct *mm) {} 689#endif /* CONFIG_PPC_SUBPAGE_PROT */ 690 691/* 692 * One bit per slice. We have lower slices which cover 256MB segments 693 * upto 4G range. That gets us 16 low slices. For the rest we track slices 694 * in 1TB size. 695 */ 696struct slice_mask { 697 u64 low_slices; 698 DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH); 699}; 700 701struct hash_mm_context { 702 u16 user_psize; /* page size index */ 703 704 /* SLB page size encodings*/ 705 unsigned char low_slices_psize[LOW_SLICE_ARRAY_SZ]; 706 unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; 707 unsigned long slb_addr_limit; 708#ifdef CONFIG_PPC_64K_PAGES 709 struct slice_mask mask_64k; 710#endif 711 struct slice_mask mask_4k; 712#ifdef CONFIG_HUGETLB_PAGE 713 struct slice_mask mask_16m; 714 struct slice_mask mask_16g; 715#endif 716 717#ifdef CONFIG_PPC_SUBPAGE_PROT 718 struct subpage_prot_table *spt; 719#endif /* CONFIG_PPC_SUBPAGE_PROT */ 720}; 721 722#if 0 723/* 724 * The code below is equivalent to this function for arguments 725 * < 2^VSID_BITS, which is all this should ever be called 726 * with. However gcc is not clever enough to compute the 727 * modulus (2^n-1) without a second multiply. 728 */ 729#define vsid_scramble(protovsid, size) \ 730 ((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size)) 731 732/* simplified form avoiding mod operation */ 733#define vsid_scramble(protovsid, size) \ 734 ({ \ 735 unsigned long x; \ 736 x = (protovsid) * VSID_MULTIPLIER_##size; \ 737 x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \ 738 (x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \ 739 }) 740 741#else /* 1 */ 742static inline unsigned long vsid_scramble(unsigned long protovsid, 743 unsigned long vsid_multiplier, int vsid_bits) 744{ 745 unsigned long vsid; 746 unsigned long vsid_modulus = ((1UL << vsid_bits) - 1); 747 /* 748 * We have same multipler for both 256 and 1T segements now 749 */ 750 vsid = protovsid * vsid_multiplier; 751 vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus); 752 return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus; 753} 754 755#endif /* 1 */ 756 757/* Returns the segment size indicator for a user address */ 758static inline int user_segment_size(unsigned long addr) 759{ 760 /* Use 1T segments if possible for addresses >= 1T */ 761 if (addr >= (1UL << SID_SHIFT_1T)) 762 return mmu_highuser_ssize; 763 return MMU_SEGSIZE_256M; 764} 765 766static inline unsigned long get_vsid(unsigned long context, unsigned long ea, 767 int ssize) 768{ 769 unsigned long va_bits = VA_BITS; 770 unsigned long vsid_bits; 771 unsigned long protovsid; 772 773 /* 774 * Bad address. We return VSID 0 for that 775 */ 776 if ((ea & EA_MASK) >= H_PGTABLE_RANGE) 777 return 0; 778 779 if (!mmu_has_feature(MMU_FTR_68_BIT_VA)) 780 va_bits = 65; 781 782 if (ssize == MMU_SEGSIZE_256M) { 783 vsid_bits = va_bits - SID_SHIFT; 784 protovsid = (context << ESID_BITS) | 785 ((ea >> SID_SHIFT) & ESID_BITS_MASK); 786 return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits); 787 } 788 /* 1T segment */ 789 vsid_bits = va_bits - SID_SHIFT_1T; 790 protovsid = (context << ESID_BITS_1T) | 791 ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK); 792 return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits); 793} 794 795/* 796 * For kernel space, we use context ids as 797 * below. Range is 512TB per context. 798 * 799 * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] 800 * 0x00002 - [ 0xc002000000000000 - 0xc003ffffffffffff] 801 * 0x00003 - [ 0xc004000000000000 - 0xc005ffffffffffff] 802 * 0x00004 - [ 0xc006000000000000 - 0xc007ffffffffffff] 803 * 804 * vmap, IO, vmemap 805 * 806 * 0x00005 - [ 0xc008000000000000 - 0xc009ffffffffffff] 807 * 0x00006 - [ 0xc00a000000000000 - 0xc00bffffffffffff] 808 * 0x00007 - [ 0xc00c000000000000 - 0xc00dffffffffffff] 809 * 810 */ 811static inline unsigned long get_kernel_context(unsigned long ea) 812{ 813 unsigned long region_id = get_region_id(ea); 814 unsigned long ctx; 815 /* 816 * Depending on Kernel config, kernel region can have one context 817 * or more. 818 */ 819 if (region_id == LINEAR_MAP_REGION_ID) { 820 /* 821 * We already verified ea to be not beyond the addr limit. 822 */ 823 ctx = 1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT); 824 } else 825 ctx = region_id + MAX_KERNEL_CTX_CNT - 1; 826 return ctx; 827} 828 829/* 830 * This is only valid for addresses >= PAGE_OFFSET 831 */ 832static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) 833{ 834 unsigned long context; 835 836 if (!is_kernel_addr(ea)) 837 return 0; 838 839 context = get_kernel_context(ea); 840 return get_vsid(context, ea, ssize); 841} 842 843unsigned htab_shift_for_mem_size(unsigned long mem_size); 844 845#endif /* __ASSEMBLY__ */ 846 847#endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */ 848