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
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
|
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* linux/arch/arm/mm/cache-v7m.S
*
* Based on linux/arch/arm/mm/cache-v7.S
*
* Copyright (C) 2001 Deep Blue Solutions Ltd.
* Copyright (C) 2005 ARM Ltd.
*
* This is the "shell" of the ARMv7M processor support.
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/assembler.h>
#include <asm/errno.h>
#include <asm/unwind.h>
#include <asm/v7m.h>
#include "proc-macros.S"
/* Generic V7M read/write macros for memory mapped cache operations */
.macro v7m_cache_read, rt, reg
movw \rt, #:lower16:BASEADDR_V7M_SCB + \reg
movt \rt, #:upper16:BASEADDR_V7M_SCB + \reg
ldr \rt, [\rt]
.endm
.macro v7m_cacheop, rt, tmp, op, c = al
movw\c \tmp, #:lower16:BASEADDR_V7M_SCB + \op
movt\c \tmp, #:upper16:BASEADDR_V7M_SCB + \op
str\c \rt, [\tmp]
.endm
.macro read_ccsidr, rt
v7m_cache_read \rt, V7M_SCB_CCSIDR
.endm
.macro read_clidr, rt
v7m_cache_read \rt, V7M_SCB_CLIDR
.endm
.macro write_csselr, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_CSSELR
.endm
/*
* dcisw: Invalidate data cache by set/way
*/
.macro dcisw, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCISW
.endm
/*
* dccisw: Clean and invalidate data cache by set/way
*/
.macro dccisw, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCCISW
.endm
/*
* dccimvac: Clean and invalidate data cache line by MVA to PoC.
*/
.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
.macro dccimvac\c, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCCIMVAC, \c
.endm
.endr
/*
* dcimvac: Invalidate data cache line by MVA to PoC
*/
.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
.macro dcimvac\c, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC, \c
.endm
.endr
/*
* dccmvau: Clean data cache line by MVA to PoU
*/
.macro dccmvau, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAU
.endm
/*
* dccmvac: Clean data cache line by MVA to PoC
*/
.macro dccmvac, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAC
.endm
/*
* icimvau: Invalidate instruction caches by MVA to PoU
*/
.macro icimvau, rt, tmp
v7m_cacheop \rt, \tmp, V7M_SCB_ICIMVAU
.endm
/*
* Invalidate the icache, inner shareable if SMP, invalidate BTB for UP.
* rt data ignored by ICIALLU(IS), so can be used for the address
*/
.macro invalidate_icache, rt
v7m_cacheop \rt, \rt, V7M_SCB_ICIALLU
mov \rt, #0
.endm
/*
* Invalidate the BTB, inner shareable if SMP.
* rt data ignored by BPIALL, so it can be used for the address
*/
.macro invalidate_bp, rt
v7m_cacheop \rt, \rt, V7M_SCB_BPIALL
mov \rt, #0
.endm
ENTRY(v7m_invalidate_l1)
mov r0, #0
write_csselr r0, r1
read_ccsidr r0
movw r1, #0x7fff
and r2, r1, r0, lsr #13
movw r1, #0x3ff
and r3, r1, r0, lsr #3 @ NumWays - 1
add r2, r2, #1 @ NumSets
and r0, r0, #0x7
add r0, r0, #4 @ SetShift
clz r1, r3 @ WayShift
add r4, r3, #1 @ NumWays
1: sub r2, r2, #1 @ NumSets--
mov r3, r4 @ Temp = NumWays
2: subs r3, r3, #1 @ Temp--
mov r5, r3, lsl r1
mov r6, r2, lsl r0
orr r5, r5, r6 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
dcisw r5, r6
bgt 2b
cmp r2, #0
bgt 1b
dsb st
isb
ret lr
ENDPROC(v7m_invalidate_l1)
/*
* v7m_flush_icache_all()
*
* Flush the whole I-cache.
*
* Registers:
* r0 - set to 0
*/
ENTRY(v7m_flush_icache_all)
invalidate_icache r0
ret lr
ENDPROC(v7m_flush_icache_all)
/*
* v7m_flush_dcache_all()
*
* Flush the whole D-cache.
*
* Corrupted registers: r0-r7, r9-r11
*/
ENTRY(v7m_flush_dcache_all)
dmb @ ensure ordering with previous memory accesses
read_clidr r0
mov r3, r0, lsr #23 @ move LoC into position
ands r3, r3, #7 << 1 @ extract LoC*2 from clidr
beq finished @ if loc is 0, then no need to clean
start_flush_levels:
mov r10, #0 @ start clean at cache level 0
flush_levels:
add r2, r10, r10, lsr #1 @ work out 3x current cache level
mov r1, r0, lsr r2 @ extract cache type bits from clidr
and r1, r1, #7 @ mask of the bits for current cache only
cmp r1, #2 @ see what cache we have at this level
blt skip @ skip if no cache, or just i-cache
#ifdef CONFIG_PREEMPTION
save_and_disable_irqs_notrace r9 @ make cssr&csidr read atomic
#endif
write_csselr r10, r1 @ set current cache level
isb @ isb to sych the new cssr&csidr
read_ccsidr r1 @ read the new csidr
#ifdef CONFIG_PREEMPTION
restore_irqs_notrace r9
#endif
and r2, r1, #7 @ extract the length of the cache lines
add r2, r2, #4 @ add 4 (line length offset)
movw r4, #0x3ff
ands r4, r4, r1, lsr #3 @ find maximum number on the way size
clz r5, r4 @ find bit position of way size increment
movw r7, #0x7fff
ands r7, r7, r1, lsr #13 @ extract max number of the index size
loop1:
mov r9, r7 @ create working copy of max index
loop2:
lsl r6, r4, r5
orr r11, r10, r6 @ factor way and cache number into r11
lsl r6, r9, r2
orr r11, r11, r6 @ factor index number into r11
dccisw r11, r6 @ clean/invalidate by set/way
subs r9, r9, #1 @ decrement the index
bge loop2
subs r4, r4, #1 @ decrement the way
bge loop1
skip:
add r10, r10, #2 @ increment cache number
cmp r3, r10
bgt flush_levels
finished:
mov r10, #0 @ switch back to cache level 0
write_csselr r10, r3 @ select current cache level in cssr
dsb st
isb
ret lr
ENDPROC(v7m_flush_dcache_all)
/*
* v7m_flush_cache_all()
*
* Flush the entire cache system.
* The data cache flush is now achieved using atomic clean / invalidates
* working outwards from L1 cache. This is done using Set/Way based cache
* maintenance instructions.
* The instruction cache can still be invalidated back to the point of
* unification in a single instruction.
*
*/
ENTRY(v7m_flush_kern_cache_all)
stmfd sp!, {r4-r7, r9-r11, lr}
bl v7m_flush_dcache_all
invalidate_icache r0
ldmfd sp!, {r4-r7, r9-r11, lr}
ret lr
ENDPROC(v7m_flush_kern_cache_all)
/*
* v7m_flush_cache_all()
*
* Flush all TLB entries in a particular address space
*
* - mm - mm_struct describing address space
*/
ENTRY(v7m_flush_user_cache_all)
/*FALLTHROUGH*/
/*
* v7m_flush_cache_range(start, end, flags)
*
* Flush a range of TLB entries in the specified address space.
*
* - start - start address (may not be aligned)
* - end - end address (exclusive, may not be aligned)
* - flags - vm_area_struct flags describing address space
*
* It is assumed that:
* - we have a VIPT cache.
*/
ENTRY(v7m_flush_user_cache_range)
ret lr
ENDPROC(v7m_flush_user_cache_all)
ENDPROC(v7m_flush_user_cache_range)
/*
* v7m_coherent_kern_range(start,end)
*
* Ensure that the I and D caches are coherent within specified
* region. This is typically used when code has been written to
* a memory region, and will be executed.
*
* - start - virtual start address of region
* - end - virtual end address of region
*
* It is assumed that:
* - the Icache does not read data from the write buffer
*/
ENTRY(v7m_coherent_kern_range)
/* FALLTHROUGH */
/*
* v7m_coherent_user_range(start,end)
*
* Ensure that the I and D caches are coherent within specified
* region. This is typically used when code has been written to
* a memory region, and will be executed.
*
* - start - virtual start address of region
* - end - virtual end address of region
*
* It is assumed that:
* - the Icache does not read data from the write buffer
*/
ENTRY(v7m_coherent_user_range)
UNWIND(.fnstart )
dcache_line_size r2, r3
sub r3, r2, #1
bic r12, r0, r3
1:
/*
* We use open coded version of dccmvau otherwise USER() would
* point at movw instruction.
*/
dccmvau r12, r3
add r12, r12, r2
cmp r12, r1
blo 1b
dsb ishst
icache_line_size r2, r3
sub r3, r2, #1
bic r12, r0, r3
2:
icimvau r12, r3
add r12, r12, r2
cmp r12, r1
blo 2b
invalidate_bp r0
dsb ishst
isb
ret lr
UNWIND(.fnend )
ENDPROC(v7m_coherent_kern_range)
ENDPROC(v7m_coherent_user_range)
/*
* v7m_flush_kern_dcache_area(void *addr, size_t size)
*
* Ensure that the data held in the page kaddr is written back
* to the page in question.
*
* - addr - kernel address
* - size - region size
*/
ENTRY(v7m_flush_kern_dcache_area)
dcache_line_size r2, r3
add r1, r0, r1
sub r3, r2, #1
bic r0, r0, r3
1:
dccimvac r0, r3 @ clean & invalidate D line / unified line
add r0, r0, r2
cmp r0, r1
blo 1b
dsb st
ret lr
ENDPROC(v7m_flush_kern_dcache_area)
/*
* v7m_dma_inv_range(start,end)
*
* Invalidate the data cache within the specified region; we will
* be performing a DMA operation in this region and we want to
* purge old data in the cache.
*
* - start - virtual start address of region
* - end - virtual end address of region
*/
v7m_dma_inv_range:
dcache_line_size r2, r3
sub r3, r2, #1
tst r0, r3
bic r0, r0, r3
dccimvacne r0, r3
addne r0, r0, r2
subne r3, r2, #1 @ restore r3, corrupted by v7m's dccimvac
tst r1, r3
bic r1, r1, r3
dccimvacne r1, r3
cmp r0, r1
1:
dcimvaclo r0, r3
addlo r0, r0, r2
cmplo r0, r1
blo 1b
dsb st
ret lr
ENDPROC(v7m_dma_inv_range)
/*
* v7m_dma_clean_range(start,end)
* - start - virtual start address of region
* - end - virtual end address of region
*/
v7m_dma_clean_range:
dcache_line_size r2, r3
sub r3, r2, #1
bic r0, r0, r3
1:
dccmvac r0, r3 @ clean D / U line
add r0, r0, r2
cmp r0, r1
blo 1b
dsb st
ret lr
ENDPROC(v7m_dma_clean_range)
/*
* v7m_dma_flush_range(start,end)
* - start - virtual start address of region
* - end - virtual end address of region
*/
ENTRY(v7m_dma_flush_range)
dcache_line_size r2, r3
sub r3, r2, #1
bic r0, r0, r3
1:
dccimvac r0, r3 @ clean & invalidate D / U line
add r0, r0, r2
cmp r0, r1
blo 1b
dsb st
ret lr
ENDPROC(v7m_dma_flush_range)
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v7m_dma_map_area)
add r1, r1, r0
teq r2, #DMA_FROM_DEVICE
beq v7m_dma_inv_range
b v7m_dma_clean_range
ENDPROC(v7m_dma_map_area)
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v7m_dma_unmap_area)
add r1, r1, r0
teq r2, #DMA_TO_DEVICE
bne v7m_dma_inv_range
ret lr
ENDPROC(v7m_dma_unmap_area)
.globl v7m_flush_kern_cache_louis
.equ v7m_flush_kern_cache_louis, v7m_flush_kern_cache_all
__INITDATA
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions v7m
|