aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/slb.c
blob: a685652effeb05cd303b75a7a2a07e796d1a9a89 (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
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
/*
 * PowerPC64 SLB support.
 *
 * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
 * Based on earlier code written by:
 * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
 *    Copyright (c) 2001 Dave Engebretsen
 * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
 *
 *
 *      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 <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/paca.h>
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <asm/smp.h>
#include <asm/firmware.h>
#include <linux/compiler.h>
#include <asm/udbg.h>


extern void slb_allocate_realmode(unsigned long ea);
extern void slb_allocate_user(unsigned long ea);

static void slb_allocate(unsigned long ea)
{
	/* Currently, we do real mode for all SLBs including user, but
	 * that will change if we bring back dynamic VSIDs
	 */
	slb_allocate_realmode(ea);
}

#define slb_esid_mask(ssize)	\
	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)

static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
					 unsigned long slot)
{
	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
}

#define slb_vsid_shift(ssize)	\
	((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T)

static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
					 unsigned long flags)
{
	return (get_kernel_vsid(ea, ssize) << slb_vsid_shift(ssize)) | flags |
		((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
}

static inline void slb_shadow_update(unsigned long ea, int ssize,
				     unsigned long flags,
				     unsigned long entry)
{
	/*
	 * Clear the ESID first so the entry is not valid while we are
	 * updating it.  No write barriers are needed here, provided
	 * we only update the current CPU's SLB shadow buffer.
	 */
	get_slb_shadow()->save_area[entry].esid = 0;
	get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, ssize, flags);
	get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, ssize, entry);
}

static inline void slb_shadow_clear(unsigned long entry)
{
	get_slb_shadow()->save_area[entry].esid = 0;
}

static inline void create_shadowed_slbe(unsigned long ea, int ssize,
					unsigned long flags,
					unsigned long entry)
{
	/*
	 * Updating the shadow buffer before writing the SLB ensures
	 * we don't get a stale entry here if we get preempted by PHYP
	 * between these two statements.
	 */
	slb_shadow_update(ea, ssize, flags, entry);

	asm volatile("slbmte  %0,%1" :
		     : "r" (mk_vsid_data(ea, ssize, flags)),
		       "r" (mk_esid_data(ea, ssize, entry))
		     : "memory" );
}

static void __slb_flush_and_rebolt(void)
{
	/* If you change this make sure you change SLB_NUM_BOLTED
	 * appropriately too. */
	unsigned long linear_llp, vmalloc_llp, lflags, vflags;
	unsigned long ksp_esid_data, ksp_vsid_data;

	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
	lflags = SLB_VSID_KERNEL | linear_llp;
	vflags = SLB_VSID_KERNEL | vmalloc_llp;

	ksp_esid_data = mk_esid_data(get_paca()->kstack, mmu_kernel_ssize, 2);
	if ((ksp_esid_data & ~0xfffffffUL) <= PAGE_OFFSET) {
		ksp_esid_data &= ~SLB_ESID_V;
		ksp_vsid_data = 0;
		slb_shadow_clear(2);
	} else {
		/* Update stack entry; others don't change */
		slb_shadow_update(get_paca()->kstack, mmu_kernel_ssize, lflags, 2);
		ksp_vsid_data = get_slb_shadow()->save_area[2].vsid;
	}

	/* We need to do this all in asm, so we're sure we don't touch
	 * the stack between the slbia and rebolting it. */
	asm volatile("isync\n"
		     "slbia\n"
		     /* Slot 1 - first VMALLOC segment */
		     "slbmte	%0,%1\n"
		     /* Slot 2 - kernel stack */
		     "slbmte	%2,%3\n"
		     "isync"
		     :: "r"(mk_vsid_data(VMALLOC_START, mmu_kernel_ssize, vflags)),
		        "r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, 1)),
		        "r"(ksp_vsid_data),
		        "r"(ksp_esid_data)
		     : "memory");
}

void slb_flush_and_rebolt(void)
{

	WARN_ON(!irqs_disabled());

	/*
	 * We can't take a PMU exception in the following code, so hard
	 * disable interrupts.
	 */
	hard_irq_disable();

	__slb_flush_and_rebolt();
	get_paca()->slb_cache_ptr = 0;
}

void slb_vmalloc_update(void)
{
	unsigned long vflags;

	vflags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmalloc_psize].sllp;
	slb_shadow_update(VMALLOC_START, mmu_kernel_ssize, vflags, 1);
	slb_flush_and_rebolt();
}

/* Helper function to compare esids.  There are four cases to handle.
 * 1. The system is not 1T segment size capable.  Use the GET_ESID compare.
 * 2. The system is 1T capable, both addresses are < 1T, use the GET_ESID compare.
 * 3. The system is 1T capable, only one of the two addresses is > 1T.  This is not a match.
 * 4. The system is 1T capable, both addresses are > 1T, use the GET_ESID_1T macro to compare.
 */
static inline int esids_match(unsigned long addr1, unsigned long addr2)
{
	int esid_1t_count;

	/* System is not 1T segment size capable. */
	if (!cpu_has_feature(CPU_FTR_1T_SEGMENT))
		return (GET_ESID(addr1) == GET_ESID(addr2));

	esid_1t_count = (((addr1 >> SID_SHIFT_1T) != 0) +
				((addr2 >> SID_SHIFT_1T) != 0));

	/* both addresses are < 1T */
	if (esid_1t_count == 0)
		return (GET_ESID(addr1) == GET_ESID(addr2));

	/* One address < 1T, the other > 1T.  Not a match */
	if (esid_1t_count == 1)
		return 0;

	/* Both addresses are > 1T. */
	return (GET_ESID_1T(addr1) == GET_ESID_1T(addr2));
}

/* Flush all user entries from the segment table of the current processor. */
void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
{
	unsigned long offset;
	unsigned long slbie_data = 0;
	unsigned long pc = KSTK_EIP(tsk);
	unsigned long stack = KSTK_ESP(tsk);
	unsigned long unmapped_base;

	/*
	 * We need interrupts hard-disabled here, not just soft-disabled,
	 * so that a PMU interrupt can't occur, which might try to access
	 * user memory (to get a stack trace) and possible cause an SLB miss
	 * which would update the slb_cache/slb_cache_ptr fields in the PACA.
	 */
	hard_irq_disable();
	offset = get_paca()->slb_cache_ptr;
	if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B) &&
	    offset <= SLB_CACHE_ENTRIES) {
		int i;
		asm volatile("isync" : : : "memory");
		for (i = 0; i < offset; i++) {
			slbie_data = (unsigned long)get_paca()->slb_cache[i]
				<< SID_SHIFT; /* EA */
			slbie_data |= user_segment_size(slbie_data)
				<< SLBIE_SSIZE_SHIFT;
			slbie_data |= SLBIE_C; /* C set for user addresses */
			asm volatile("slbie %0" : : "r" (slbie_data));
		}
		asm volatile("isync" : : : "memory");
	} else {
		__slb_flush_and_rebolt();
	}

	/* Workaround POWER5 < DD2.1 issue */
	if (offset == 1 || offset > SLB_CACHE_ENTRIES)
		asm volatile("slbie %0" : : "r" (slbie_data));

	get_paca()->slb_cache_ptr = 0;
	get_paca()->context = mm->context;

	/*
	 * preload some userspace segments into the SLB.
	 */
	if (test_tsk_thread_flag(tsk, TIF_32BIT))
		unmapped_base = TASK_UNMAPPED_BASE_USER32;
	else
		unmapped_base = TASK_UNMAPPED_BASE_USER64;

	if (is_kernel_addr(pc))
		return;
	slb_allocate(pc);

	if (esids_match(pc,stack))
		return;

	if (is_kernel_addr(stack))
		return;
	slb_allocate(stack);

	if (esids_match(pc,unmapped_base) || esids_match(stack,unmapped_base))
		return;

	if (is_kernel_addr(unmapped_base))
		return;
	slb_allocate(unmapped_base);
}

static inline void patch_slb_encoding(unsigned int *insn_addr,
				      unsigned int immed)
{
	/* Assume the instruction had a "0" immediate value, just
	 * "or" in the new value
	 */
	*insn_addr |= immed;
	flush_icache_range((unsigned long)insn_addr, 4+
			   (unsigned long)insn_addr);
}

void slb_initialize(void)
{
	unsigned long linear_llp, vmalloc_llp, io_llp;
	unsigned long lflags, vflags;
	static int slb_encoding_inited;
	extern unsigned int *slb_miss_kernel_load_linear;
	extern unsigned int *slb_miss_kernel_load_io;
	extern unsigned int *slb_compare_rr_to_size;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	extern unsigned int *slb_miss_kernel_load_vmemmap;
	unsigned long vmemmap_llp;
#endif

	/* Prepare our SLB miss handler based on our page size */
	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp;
#endif
	if (!slb_encoding_inited) {
		slb_encoding_inited = 1;
		patch_slb_encoding(slb_miss_kernel_load_linear,
				   SLB_VSID_KERNEL | linear_llp);
		patch_slb_encoding(slb_miss_kernel_load_io,
				   SLB_VSID_KERNEL | io_llp);
		patch_slb_encoding(slb_compare_rr_to_size,
				   mmu_slb_size);

		pr_devel("SLB: linear  LLP = %04lx\n", linear_llp);
		pr_devel("SLB: io      LLP = %04lx\n", io_llp);

#ifdef CONFIG_SPARSEMEM_VMEMMAP
		patch_slb_encoding(slb_miss_kernel_load_vmemmap,
				   SLB_VSID_KERNEL | vmemmap_llp);
		pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
#endif
	}

	get_paca()->stab_rr = SLB_NUM_BOLTED;

	/* On iSeries the bolted entries have already been set up by
	 * the hypervisor from the lparMap data in head.S */
	if (firmware_has_feature(FW_FEATURE_ISERIES))
		return;

	lflags = SLB_VSID_KERNEL | linear_llp;
	vflags = SLB_VSID_KERNEL | vmalloc_llp;

	/* Invalidate the entire SLB (even slot 0) & all the ERATS */
	asm volatile("isync":::"memory");
	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
	asm volatile("isync; slbia; isync":::"memory");
	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, 0);

	create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1);

	/* For the boot cpu, we're running on the stack in init_thread_union,
	 * which is in the first segment of the linear mapping, and also
	 * get_paca()->kstack hasn't been initialized yet.
	 * For secondary cpus, we need to bolt the kernel stack entry now.
	 */
	slb_shadow_clear(2);
	if (raw_smp_processor_id() != boot_cpuid &&
	    (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET)
		create_shadowed_slbe(get_paca()->kstack,
				     mmu_kernel_ssize, lflags, 2);

	asm volatile("isync":::"memory");
}