summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/include/asm/book3s/64/hash.h
blob: f7b721bbf918bf055b5c5a0efa8cfc90de053384 (plain)
1
2
3
4
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
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
208
209
210
#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H
#define _ASM_POWERPC_BOOK3S_64_HASH_H
#ifdef __KERNEL__

/*
 * Common bits between 4K and 64K pages in a linux-style PTE.
 * Additional bits may be defined in pgtable-hash64-*.h
 *
 * 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.
 */
#define H_PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
#define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
#define H_PAGE_F_GIX_SHIFT	57
#define H_PAGE_F_GIX		(7ul << 57)	/* HPTE index within HPTEG */
#define H_PAGE_F_SECOND		(1ul << 60)	/* HPTE is in 2ndary HPTEG */
#define H_PAGE_HASHPTE		(1ul << 61)	/* PTE has associated HPTE */

#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 H_PGTABLE_EADDR_SIZE	(H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + \
				 H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT)
#define H_PGTABLE_RANGE		(ASM_CONST(1) << H_PGTABLE_EADDR_SIZE)

#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&  defined(CONFIG_PPC_64K_PAGES)
/*
 * only with hash 64k we need to use the second half of pmd page table
 * to store pointer to deposited pgtable_t
 */
#define H_PMD_CACHE_INDEX	(H_PMD_INDEX_SIZE + 1)
#else
#define H_PMD_CACHE_INDEX	H_PMD_INDEX_SIZE
#endif
/*
 * Define the address range of the kernel non-linear virtual area
 */
#define H_KERN_VIRT_START ASM_CONST(0xD000000000000000)
#define H_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 H_VMALLOC_START	H_KERN_VIRT_START
#define H_VMALLOC_SIZE	(H_KERN_VIRT_SIZE >> 1)
#define H_VMALLOC_END	(H_VMALLOC_START + H_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(H_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 H_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 */


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

#define H_PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
#define H_PUD_BAD_BITS		(PMD_TABLE_SIZE-1)

#ifndef __ASSEMBLY__
#define	hash__pmd_bad(pmd)		(pmd_val(pmd) & H_PMD_BAD_BITS)
#define	hash__pud_bad(pud)		(pud_val(pud) & H_PUD_BAD_BITS)
static inline int hash__pgd_bad(pgd_t pgd)
{
	return (pgd_val(pgd) == 0);
}

extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
			    pte_t *ptep, unsigned long pte, int huge);
extern unsigned long htab_convert_pte_flags(unsigned long pteflags);
/* Atomic PTE updates */
static inline unsigned long hash__pte_update(struct mm_struct *mm,
					 unsigned long addr,
					 pte_t *ptep, unsigned long clr,
					 unsigned long set,
					 int huge)
{
	__be64 old_be, tmp_be;
	unsigned long old;

	__asm__ __volatile__(
	"1:	ldarx	%0,0,%3		# pte_update\n\
	and.	%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_be), "=&r" (tmp_be), "=m" (*ptep)
	: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
	: "cc" );
	/* huge pages use the old page table lock */
	if (!huge)
		assert_pte_locked(mm, addr);

	old = be64_to_cpu(old_be);
	if (old & H_PAGE_HASHPTE)
		hpte_need_flush(mm, addr, ptep, old, huge);

	return old;
}

/* 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 hash__ptep_set_access_flags(pte_t *ptep, pte_t entry)
{
	__be64 old, tmp, val, mask;

	mask = cpu_to_be64(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_READ | _PAGE_WRITE |
			   _PAGE_EXEC | _PAGE_SOFT_DIRTY);

	val = pte_raw(entry) & mask;

	__asm__ __volatile__(
	"1:	ldarx	%0,0,%4\n\
		and.	%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" (val), "r" (ptep), "m" (*ptep), "r" (cpu_to_be64(H_PAGE_BUSY))
	:"cc");
}

static inline int hash__pte_same(pte_t pte_a, pte_t pte_b)
{
	return (((pte_raw(pte_a) ^ pte_raw(pte_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
}

static inline int hash__pte_none(pte_t pte)
{
	return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0;
}

/* 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 hash__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;
}

#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 */


extern int hash__map_kernel_page(unsigned long ea, unsigned long pa,
			     unsigned long flags);
extern int __meminit hash__vmemmap_create_mapping(unsigned long start,
					      unsigned long page_size,
					      unsigned long phys);
extern void hash__vmemmap_remove_mapping(unsigned long start,
				     unsigned long page_size);

int hash__create_section_mapping(unsigned long start, unsigned long end);
int hash__remove_section_mapping(unsigned long start, unsigned long end);

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