summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/ppc_mmu_32.c
blob: 6aa12081377531594bea592b94915da93904be78 (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
211
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
/*
 * This file contains the routines for handling the MMU on those
 * PowerPC implementations where the MMU substantially follows the
 * architecture specification.  This includes the 6xx, 7xx, 7xxx,
 * 8260, and POWER3 implementations but excludes the 8xx and 4xx.
 *  -- paulus
 *
 *  Derived from arch/ppc/mm/init.c:
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
 *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
 *    Copyright (C) 1996 Paul Mackerras
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 *
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/lmb.h>

#include <asm/prom.h>
#include <asm/mmu.h>
#include <asm/machdep.h>

#include "mmu_decl.h"

struct hash_pte *Hash, *Hash_end;
unsigned long Hash_size, Hash_mask;
unsigned long _SDR1;

struct ppc_bat BATS[8][2];	/* 8 pairs of IBAT, DBAT */

struct batrange {		/* stores address ranges mapped by BATs */
	unsigned long start;
	unsigned long limit;
	phys_addr_t phys;
} bat_addrs[8];

/*
 * Return PA for this VA if it is mapped by a BAT, or 0
 */
phys_addr_t v_mapped_by_bats(unsigned long va)
{
	int b;
	for (b = 0; b < 4; ++b)
		if (va >= bat_addrs[b].start && va < bat_addrs[b].limit)
			return bat_addrs[b].phys + (va - bat_addrs[b].start);
	return 0;
}

/*
 * Return VA for a given PA or 0 if not mapped
 */
unsigned long p_mapped_by_bats(phys_addr_t pa)
{
	int b;
	for (b = 0; b < 4; ++b)
		if (pa >= bat_addrs[b].phys
	    	    && pa < (bat_addrs[b].limit-bat_addrs[b].start)
		              +bat_addrs[b].phys)
			return bat_addrs[b].start+(pa-bat_addrs[b].phys);
	return 0;
}

unsigned long __init mmu_mapin_ram(void)
{
#ifdef CONFIG_POWER4
	return 0;
#else
	unsigned long tot, bl, done;
	unsigned long max_size = (256<<20);

	if (__map_without_bats) {
		printk(KERN_DEBUG "RAM mapped without BATs\n");
		return 0;
	}

	/* Set up BAT2 and if necessary BAT3 to cover RAM. */

	/* Make sure we don't map a block larger than the
	   smallest alignment of the physical address. */
	tot = total_lowmem;
	for (bl = 128<<10; bl < max_size; bl <<= 1) {
		if (bl * 2 > tot)
			break;
	}

	setbat(2, KERNELBASE, 0, bl, _PAGE_RAM);
	done = (unsigned long)bat_addrs[2].limit - KERNELBASE + 1;
	if ((done < tot) && !bat_addrs[3].limit) {
		/* use BAT3 to cover a bit more */
		tot -= done;
		for (bl = 128<<10; bl < max_size; bl <<= 1)
			if (bl * 2 > tot)
				break;
		setbat(3, KERNELBASE+done, done, bl, _PAGE_RAM);
		done = (unsigned long)bat_addrs[3].limit - KERNELBASE + 1;
	}

	return done;
#endif
}

/*
 * Set up one of the I/D BAT (block address translation) register pairs.
 * The parameters are not checked; in particular size must be a power
 * of 2 between 128k and 256M.
 */
void __init setbat(int index, unsigned long virt, phys_addr_t phys,
		   unsigned int size, int flags)
{
	unsigned int bl;
	int wimgxpp;
	struct ppc_bat *bat = BATS[index];

	if (((flags & _PAGE_NO_CACHE) == 0) &&
	    cpu_has_feature(CPU_FTR_NEED_COHERENT))
		flags |= _PAGE_COHERENT;

	bl = (size >> 17) - 1;
	if (PVR_VER(mfspr(SPRN_PVR)) != 1) {
		/* 603, 604, etc. */
		/* Do DBAT first */
		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
				   | _PAGE_COHERENT | _PAGE_GUARDED);
		wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX;
		bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
		bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
#ifndef CONFIG_KGDB /* want user access for breakpoints */
		if (flags & _PAGE_USER)
#endif
			bat[1].batu |= 1; 	/* Vp = 1 */
		if (flags & _PAGE_GUARDED) {
			/* G bit must be zero in IBATs */
			bat[0].batu = bat[0].batl = 0;
		} else {
			/* make IBAT same as DBAT */
			bat[0] = bat[1];
		}
	} else {
		/* 601 cpu */
		if (bl > BL_8M)
			bl = BL_8M;
		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
				   | _PAGE_COHERENT);
		wimgxpp |= (flags & _PAGE_RW)?
			((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX;
		bat->batu = virt | wimgxpp | 4;	/* Ks=0, Ku=1 */
		bat->batl = phys | bl | 0x40;	/* V=1 */
	}

	bat_addrs[index].start = virt;
	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
	bat_addrs[index].phys = phys;
}

/*
 * Preload a translation in the hash table
 */
void hash_preload(struct mm_struct *mm, unsigned long ea,
		  unsigned long access, unsigned long trap)
{
	pmd_t *pmd;

	if (Hash == 0)
		return;
	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
	if (!pmd_none(*pmd))
		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
}

/*
 * Initialize the hash table and patch the instructions in hashtable.S.
 */
void __init MMU_init_hw(void)
{
	unsigned int hmask, mb, mb2;
	unsigned int n_hpteg, lg_n_hpteg;

	extern unsigned int hash_page_patch_A[];
	extern unsigned int hash_page_patch_B[], hash_page_patch_C[];
	extern unsigned int hash_page[];
	extern unsigned int flush_hash_patch_A[], flush_hash_patch_B[];

	if (!cpu_has_feature(CPU_FTR_HPTE_TABLE)) {
		/*
		 * Put a blr (procedure return) instruction at the
		 * start of hash_page, since we can still get DSI
		 * exceptions on a 603.
		 */
		hash_page[0] = 0x4e800020;
		flush_icache_range((unsigned long) &hash_page[0],
				   (unsigned long) &hash_page[1]);
		return;
	}

	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);

#define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
#define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
#define MIN_N_HPTEG	1024		/* min 64kB hash table */

	/*
	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
	 * This is less than the recommended amount, but then
	 * Linux ain't AIX.
	 */
	n_hpteg = total_memory / (PAGE_SIZE * 8);
	if (n_hpteg < MIN_N_HPTEG)
		n_hpteg = MIN_N_HPTEG;
	lg_n_hpteg = __ilog2(n_hpteg);
	if (n_hpteg & (n_hpteg - 1)) {
		++lg_n_hpteg;		/* round up if not power of 2 */
		n_hpteg = 1 << lg_n_hpteg;
	}
	Hash_size = n_hpteg << LG_HPTEG_SIZE;

	/*
	 * Find some memory for the hash table.
	 */
	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
	Hash = __va(lmb_alloc_base(Hash_size, Hash_size,
				   __initial_memory_limit_addr));
	cacheable_memzero(Hash, Hash_size);
	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;

	Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size);

	printk("Total memory = %lldMB; using %ldkB for hash table (at %p)\n",
	       (unsigned long long)(total_memory >> 20), Hash_size >> 10, Hash);


	/*
	 * Patch up the instructions in hashtable.S:create_hpte
	 */
	if ( ppc_md.progress ) ppc_md.progress("hash:patch", 0x345);
	Hash_mask = n_hpteg - 1;
	hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
	mb2 = mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
	if (lg_n_hpteg > 16)
		mb2 = 16 - LG_HPTEG_SIZE;

	hash_page_patch_A[0] = (hash_page_patch_A[0] & ~0xffff)
		| ((unsigned int)(Hash) >> 16);
	hash_page_patch_A[1] = (hash_page_patch_A[1] & ~0x7c0) | (mb << 6);
	hash_page_patch_A[2] = (hash_page_patch_A[2] & ~0x7c0) | (mb2 << 6);
	hash_page_patch_B[0] = (hash_page_patch_B[0] & ~0xffff) | hmask;
	hash_page_patch_C[0] = (hash_page_patch_C[0] & ~0xffff) | hmask;

	/*
	 * Ensure that the locations we've patched have been written
	 * out from the data cache and invalidated in the instruction
	 * cache, on those machines with split caches.
	 */
	flush_icache_range((unsigned long) &hash_page_patch_A[0],
			   (unsigned long) &hash_page_patch_C[1]);

	/*
	 * Patch up the instructions in hashtable.S:flush_hash_page
	 */
	flush_hash_patch_A[0] = (flush_hash_patch_A[0] & ~0xffff)
		| ((unsigned int)(Hash) >> 16);
	flush_hash_patch_A[1] = (flush_hash_patch_A[1] & ~0x7c0) | (mb << 6);
	flush_hash_patch_A[2] = (flush_hash_patch_A[2] & ~0x7c0) | (mb2 << 6);
	flush_hash_patch_B[0] = (flush_hash_patch_B[0] & ~0xffff) | hmask;
	flush_icache_range((unsigned long) &flush_hash_patch_A[0],
			   (unsigned long) &flush_hash_patch_B[1]);

	if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
}