hash.h 19.5 KB
Newer Older
1 2
#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H
#define _ASM_POWERPC_BOOK3S_64_HASH_H
3 4
#ifdef __KERNEL__

5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/hash-64k.h>
#else
#include <asm/book3s/64/hash-4k.h>
#endif

/*
 * Size of EA range mapped by our pagetables.
 */
#define PGTABLE_EADDR_SIZE	(PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
				 PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
#define PGTABLE_RANGE		(ASM_CONST(1) << PGTABLE_EADDR_SIZE)

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
#else
#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
#endif
/*
 * Define the address range of the kernel non-linear virtual area
 */
#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
#define KERN_VIRT_SIZE	ASM_CONST(0x0000100000000000)

/*
 * The vmalloc space starts at the beginning of that region, and
 * occupies half of it on hash CPUs and a quarter of it on Book3E
 * (we keep a quarter for the virtual memmap)
 */
#define VMALLOC_START	KERN_VIRT_START
#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 1)
#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)

/*
 * Region IDs
 */
#define REGION_SHIFT		60UL
#define REGION_MASK		(0xfUL << REGION_SHIFT)
#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)

#define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
#define USER_REGION_ID		(0UL)

/*
 * Defines the address of the vmemap area, in its own region on
 * hash table CPUs.
 */
#define VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)

#ifdef CONFIG_PPC_MM_SLICES
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#endif /* CONFIG_PPC_MM_SLICES */
60 61 62 63
/*
 * Common bits between 4K and 64K pages in a linux-style PTE.
 * These match the bits in the (hardware-defined) PowerPC PTE as closely
 * as possible. Additional bits may be defined in pgtable-hash64-*.h
64 65 66 67 68 69 70
 *
 * Note: We only support user read/write permissions. Supervisor always
 * have full read/write to pages above PAGE_OFFSET (pages below that
 * always use the user access permissions).
 *
 * We could create separate kernel read-only if we used the 3 PP bits
 * combinations that newer processors provide but we currently don't.
71
 */
72 73
#define _PAGE_PRESENT		0x0001 /* software: pte contains a translation */
#define _PAGE_USER		0x0002 /* matches one of the PP bits */
74
#define _PAGE_BIT_SWAP_TYPE	2
75 76
#define _PAGE_EXEC		0x0004 /* No execute on POWER4 and newer (we invert) */
#define _PAGE_GUARDED		0x0008
77
/* We can derive Memory coherence from _PAGE_NO_CACHE */
78
#define _PAGE_COHERENT		0x0
79 80 81 82 83
#define _PAGE_NO_CACHE		0x0020 /* I: cache inhibit */
#define _PAGE_WRITETHRU		0x0040 /* W: cache write-through */
#define _PAGE_DIRTY		0x0080 /* C: page changed */
#define _PAGE_ACCESSED		0x0100 /* R: page referenced */
#define _PAGE_RW		0x0200 /* software: user write access allowed */
84
#define _PAGE_HASHPTE		0x0400 /* software: pte has an associated HPTE */
85
#define _PAGE_BUSY		0x0800 /* software: PTE & hash are busy */
86 87 88 89
#define _PAGE_F_GIX		0x7000 /* full page: hidx bits */
#define _PAGE_F_GIX_SHIFT	12
#define _PAGE_F_SECOND		0x8000 /* Whether to use secondary hash or not */
#define _PAGE_SPECIAL		0x10000 /* software: special page */
90 91 92 93

/* No separate kernel read-only */
#define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
#define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
94
#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
95 96

/* Strong Access Ordering */
97
#define _PAGE_SAO		(_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT)
98

99 100
/* No page size encoding in the linux PTE */
#define _PAGE_PSIZE		0
101 102 103 104 105

/* PTEIDX nibble */
#define _PTEIDX_SECONDARY	0x8
#define _PTEIDX_GROUP_IX	0x7

106 107
/* Hash table based platforms need atomic updates of the linux PTE */
#define PTE_ATOMIC_UPDATES	1
108

109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
/*
 * THP pages can't be special. So use the _PAGE_SPECIAL
 */
#define _PAGE_SPLITTING _PAGE_SPECIAL

/*
 * We need to differentiate between explicit huge page and THP huge
 * page, since THP huge page also need to track real subpage details
 */
#define _PAGE_THP_HUGE  _PAGE_4K_PFN

/*
 * set of bits not changed in pmd_modify.
 */
#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |		\
			 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
			 _PAGE_THP_HUGE)
#define _PTE_NONE_MASK	_PAGE_HPTEFLAGS
/*
 * The mask convered by the RPN must be a ULL on 32-bit platforms with
 * 64-bit PTEs
 */
#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
/*
 * _PAGE_CHG_MASK masks of bits that are to be preserved across
 * pgprot changes
 */
#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
			 _PAGE_ACCESSED | _PAGE_SPECIAL)
/*
 * Mask of bits returned by pte_pgprot()
 */
#define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
			 _PAGE_WRITETHRU | _PAGE_4K_PFN | \
			 _PAGE_USER | _PAGE_ACCESSED |  \
			 _PAGE_RW |  _PAGE_DIRTY | _PAGE_EXEC)
/*
 * We define 2 sets of base prot bits, one for basic pages (ie,
 * cacheable kernel and user pages) and one for non cacheable
 * pages. We always set _PAGE_COHERENT when SMP is enabled or
 * the processor might need it for DMA coherency.
 */
#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)

/* Permission masks used to generate the __P and __S table,
 *
 * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
 *
 * Write permissions imply read permissions for now (we could make write-only
 * pages on BookE but we don't bother for now). Execute permission control is
 * possible on platforms that define _PAGE_EXEC
 *
 * Note due to the way vm flags are laid out, the bits are XWR
 */
#define PAGE_NONE	__pgprot(_PAGE_BASE)
#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \
				 _PAGE_EXEC)
#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER )
#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER )
#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)

#define __P000	PAGE_NONE
#define __P001	PAGE_READONLY
#define __P010	PAGE_COPY
#define __P011	PAGE_COPY
#define __P100	PAGE_READONLY_X
#define __P101	PAGE_READONLY_X
#define __P110	PAGE_COPY_X
#define __P111	PAGE_COPY_X

#define __S000	PAGE_NONE
#define __S001	PAGE_READONLY
#define __S010	PAGE_SHARED
#define __S011	PAGE_SHARED
#define __S100	PAGE_READONLY_X
#define __S101	PAGE_READONLY_X
#define __S110	PAGE_SHARED_X
#define __S111	PAGE_SHARED_X

/* Permission masks used for kernel mappings */
#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
#define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
				 _PAGE_NO_CACHE)
#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
				 _PAGE_NO_CACHE | _PAGE_GUARDED)
#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)

/* Protection used for kernel text. We want the debuggers to be able to
 * set breakpoints anywhere, so don't write protect the kernel text
 * on platforms where such control is possible.
 */
#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
#define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
208
#else
209
#define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
210 211
#endif

212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
/* Make modules code happy. We don't set RO yet */
#define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
#define PAGE_AGP		(PAGE_KERNEL_NC)

#define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
#define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)

#ifndef __ASSEMBLY__
#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
				 || (pmd_val(pmd) & PMD_BAD_BITS))
#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)

#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
				 || (pud_val(pud) & PUD_BAD_BITS))
#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)

#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))

extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
			    pte_t *ptep, unsigned long pte, int huge);
extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
					 unsigned long addr,
					 pmd_t *pmdp,
					 unsigned long clr,
					 unsigned long set);
/* Atomic PTE updates */
static inline unsigned long pte_update(struct mm_struct *mm,
				       unsigned long addr,
				       pte_t *ptep, unsigned long clr,
				       unsigned long set,
				       int huge)
{
	unsigned long old, tmp;

	__asm__ __volatile__(
	"1:	ldarx	%0,0,%3		# pte_update\n\
	andi.	%1,%0,%6\n\
	bne-	1b \n\
	andc	%1,%0,%4 \n\
	or	%1,%1,%7\n\
	stdcx.	%1,0,%3 \n\
	bne-	1b"
	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
	: "cc" );
	/* huge pages use the old page table lock */
	if (!huge)
		assert_pte_locked(mm, addr);

	if (old & _PAGE_HASHPTE)
		hpte_need_flush(mm, addr, ptep, old, huge);

	return old;
}

static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
					      unsigned long addr, pte_t *ptep)
{
	unsigned long old;

	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
		return 0;
	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
	return (old & _PAGE_ACCESSED) != 0;
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
({									   \
	int __r;							   \
	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
	__r;								   \
})

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
				      pte_t *ptep)
{

	if ((pte_val(*ptep) & _PAGE_RW) == 0)
		return;

	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
}

static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
					   unsigned long addr, pte_t *ptep)
{
	if ((pte_val(*ptep) & _PAGE_RW) == 0)
		return;

	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
}

/*
 * We currently remove entries from the hashtable regardless of whether
 * the entry was young or dirty. The generic routines only flush if the
 * entry was young or dirty which is not good enough.
 *
 * We should be more intelligent about this but for the moment we override
 * these functions and force a tlb flush unconditionally
 */
#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
#define ptep_clear_flush_young(__vma, __address, __ptep)		\
({									\
	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
						  __ptep);		\
	__young;							\
})

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long addr, pte_t *ptep)
{
	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
	return __pte(old);
}

static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
			     pte_t * ptep)
{
	pte_update(mm, addr, ptep, ~0UL, 0, 0);
}


/* Set the dirty and/or accessed bits atomically in a linux PTE, this
 * function doesn't need to flush the hash entry
 */
static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
{
	unsigned long bits = pte_val(entry) &
		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);

	unsigned long old, tmp;

	__asm__ __volatile__(
	"1:	ldarx	%0,0,%4\n\
		andi.	%1,%0,%6\n\
		bne-	1b \n\
		or	%0,%3,%0\n\
		stdcx.	%0,0,%4\n\
		bne-	1b"
	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
	:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
	:"cc");
}

#define __HAVE_ARCH_PTE_SAME
#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)

static inline char *get_hpte_slot_array(pmd_t *pmdp)
{
	/*
	 * The hpte hindex is stored in the pgtable whose address is in the
	 * second half of the PMD
	 *
	 * Order this load with the test for pmd_trans_huge in the caller
	 */
	smp_rmb();
	return *(char **)(pmdp + PTRS_PER_PMD);


}
/*
 * The linux hugepage PMD now include the pmd entries followed by the address
 * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
 * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
 * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
 * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
 *
 * The last three bits are intentionally left to zero. This memory location
 * are also used as normal page PTE pointers. So if we have any pointers
 * left around while we collapse a hugepage, we need to make sure
 * _PAGE_PRESENT bit of that is zero when we look at them
 */
static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
{
	return (hpte_slot_array[index] >> 3) & 0x1;
}

static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
					   int index)
{
	return hpte_slot_array[index] >> 4;
}

static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
					unsigned int index, unsigned int hidx)
{
	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 *
 * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs
 * page. The hugetlbfs page table walking and mangling paths are totally
 * separated form the core VM paths and they're differentiated by
 *  VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run.
 *
 * pmd_trans_huge() is defined as false at build time if
 * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build
 * time in such case.
 *
 * For ppc64 we need to differntiate from explicit hugepages from THP, because
 * for THP we also track the subpage details at the pmd level. We don't do
 * that for explicit huge pages.
 *
 */
static inline int pmd_trans_huge(pmd_t pmd)
{
	/*
	 * leaf pte for huge page, bottom two bits != 00
	 */
	return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE);
}

static inline int pmd_trans_splitting(pmd_t pmd)
{
	if (pmd_trans_huge(pmd))
		return pmd_val(pmd) & _PAGE_SPLITTING;
	return 0;
}

#endif
static inline int pmd_large(pmd_t pmd)
{
	/*
	 * leaf pte for huge page, bottom two bits != 00
	 */
	return ((pmd_val(pmd) & 0x3) != 0x0);
}

static inline pmd_t pmd_mknotpresent(pmd_t pmd)
{
	return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT);
}

static inline pmd_t pmd_mksplitting(pmd_t pmd)
{
	return __pmd(pmd_val(pmd) | _PAGE_SPLITTING);
}

#define __HAVE_ARCH_PMD_SAME
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
}

static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
					      unsigned long addr, pmd_t *pmdp)
{
	unsigned long old;

	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
		return 0;
	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
	return ((old & _PAGE_ACCESSED) != 0);
}

#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
				      pmd_t *pmdp)
{

	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
		return;

	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
}

484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
/* Generic accessors to PTE bits */
static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }

#ifdef CONFIG_NUMA_BALANCING
/*
 * These work without NUMA balancing but the kernel does not care. See the
 * comment in include/asm-generic/pgtable.h . On powerpc, this will only
 * work for user pages and always return true for kernel pages.
 */
static inline int pte_protnone(pte_t pte)
{
	return (pte_val(pte) &
		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
}
#endif /* CONFIG_NUMA_BALANCING */

static inline int pte_present(pte_t pte)
{
	return pte_val(pte) & _PAGE_PRESENT;
}

/* Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 *
 * Even if PTEs can be unsigned long long, a PFN is always an unsigned
 * long for now.
 */
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
{
	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
		     pgprot_val(pgprot));
}

static inline unsigned long pte_pfn(pte_t pte)
{
	return pte_val(pte) >> PTE_RPN_SHIFT;
}

/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_RW);
}

static inline pte_t pte_mkclean(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_RW);
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_DIRTY);
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_ACCESSED);
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SPECIAL);
}

static inline pte_t pte_mkhuge(pte_t pte)
{
	return pte;
}

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
}

/* This low level function performs the actual PTE insertion
 * Setting the PTE depends on the MMU type and other factors. It's
 * an horrible mess that I'm not going to try to clean up now but
 * I'm keeping it in one place rather than spread around
 */
static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
				pte_t *ptep, pte_t pte, int percpu)
{
	/*
	 * Anything else just stores the PTE normally. That covers all 64-bit
	 * cases, and 32-bit non-hash with 32-bit PTEs.
	 */
	*ptep = pte;
}

/*
 * Macro to mark a page protection value as "uncacheable".
 */

#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
			 _PAGE_WRITETHRU)

#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_NO_CACHE | _PAGE_GUARDED);
}

#define pgprot_noncached_wc pgprot_noncached_wc
static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_NO_CACHE);
}

#define pgprot_cached pgprot_cached
static inline pgprot_t pgprot_cached(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_COHERENT);
}

#define pgprot_cached_wthru pgprot_cached_wthru
static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_COHERENT | _PAGE_WRITETHRU);
}

#define pgprot_cached_noncoherent pgprot_cached_noncoherent
static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
{
	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
}

#define pgprot_writecombine pgprot_writecombine
static inline pgprot_t pgprot_writecombine(pgprot_t prot)
{
	return pgprot_noncached_wc(prot);
}

635 636 637 638 639 640 641 642 643 644 645 646 647
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
				   pmd_t *pmdp, unsigned long old_pmd);
#else
static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
					  unsigned long addr, pmd_t *pmdp,
					  unsigned long old_pmd)
{
	WARN(1, "%s called with THP disabled\n", __func__);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#endif /* !__ASSEMBLY__ */
648
#endif /* __KERNEL__ */
649
#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */