summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel/cpu/mtrr/generic.c
blob: 169ac8e0db689e069cc5b02b044458c1142468b7 (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
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
/* This only handles 32bit MTRR on 32bit hosts. This is strictly wrong
   because MTRRs can span upto 40 bits (36bits on most modern x86) */ 
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <asm/io.h>
#include <asm/mtrr.h>
#include <asm/msr.h>
#include <asm/system.h>
#include <asm/cpufeature.h>
#include <asm/tlbflush.h>
#include "mtrr.h"

struct mtrr_state {
	struct mtrr_var_range *var_ranges;
	mtrr_type fixed_ranges[NUM_FIXED_RANGES];
	unsigned char enabled;
	mtrr_type def_type;
};

static unsigned long smp_changes_mask;
static struct mtrr_state mtrr_state = {};

/*  Get the MSR pair relating to a var range  */
static void __init
get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
{
	rdmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi);
	rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
}

static void __init
get_fixed_ranges(mtrr_type * frs)
{
	unsigned int *p = (unsigned int *) frs;
	int i;

	rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]);

	for (i = 0; i < 2; i++)
		rdmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], p[3 + i * 2]);
	for (i = 0; i < 8; i++)
		rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
}

/*  Grab all of the MTRR state for this CPU into *state  */
void __init get_mtrr_state(void)
{
	unsigned int i;
	struct mtrr_var_range *vrs;
	unsigned lo, dummy;

	if (!mtrr_state.var_ranges) {
		mtrr_state.var_ranges = kmalloc(num_var_ranges * sizeof (struct mtrr_var_range), 
						GFP_KERNEL);
		if (!mtrr_state.var_ranges)
			return;
	} 
	vrs = mtrr_state.var_ranges;

	for (i = 0; i < num_var_ranges; i++)
		get_mtrr_var_range(i, &vrs[i]);
	get_fixed_ranges(mtrr_state.fixed_ranges);

	rdmsr(MTRRdefType_MSR, lo, dummy);
	mtrr_state.def_type = (lo & 0xff);
	mtrr_state.enabled = (lo & 0xc00) >> 10;
}

/*  Some BIOS's are fucked and don't set all MTRRs the same!  */
void __init mtrr_state_warn(void)
{
	unsigned long mask = smp_changes_mask;

	if (!mask)
		return;
	if (mask & MTRR_CHANGE_MASK_FIXED)
		printk(KERN_WARNING "mtrr: your CPUs had inconsistent fixed MTRR settings\n");
	if (mask & MTRR_CHANGE_MASK_VARIABLE)
		printk(KERN_WARNING "mtrr: your CPUs had inconsistent variable MTRR settings\n");
	if (mask & MTRR_CHANGE_MASK_DEFTYPE)
		printk(KERN_WARNING "mtrr: your CPUs had inconsistent MTRRdefType settings\n");
	printk(KERN_INFO "mtrr: probably your BIOS does not setup all CPUs.\n");
	printk(KERN_INFO "mtrr: corrected configuration.\n");
}

/* Doesn't attempt to pass an error out to MTRR users
   because it's quite complicated in some cases and probably not
   worth it because the best error handling is to ignore it. */
void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b)
{
	if (wrmsr_safe(msr, a, b) < 0)
		printk(KERN_ERR
			"MTRR: CPU %u: Writing MSR %x to %x:%x failed\n",
			smp_processor_id(), msr, a, b);
}

int generic_get_free_region(unsigned long base, unsigned long size)
/*  [SUMMARY] Get a free MTRR.
    <base> The starting (base) address of the region.
    <size> The size (in bytes) of the region.
    [RETURNS] The index of the region on success, else -1 on error.
*/
{
	int i, max;
	mtrr_type ltype;
	unsigned long lbase;
	unsigned lsize;

	max = num_var_ranges;
	for (i = 0; i < max; ++i) {
		mtrr_if->get(i, &lbase, &lsize, &ltype);
		if (lsize == 0)
			return i;
	}
	return -ENOSPC;
}

static void generic_get_mtrr(unsigned int reg, unsigned long *base,
			     unsigned int *size, mtrr_type * type)
{
	unsigned int mask_lo, mask_hi, base_lo, base_hi;

	rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi);
	if ((mask_lo & 0x800) == 0) {
		/*  Invalid (i.e. free) range  */
		*base = 0;
		*size = 0;
		*type = 0;
		return;
	}

	rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi);

	/* Work out the shifted address mask. */
	mask_lo = size_or_mask | mask_hi << (32 - PAGE_SHIFT)
	    | mask_lo >> PAGE_SHIFT;

	/* This works correctly if size is a power of two, i.e. a
	   contiguous range. */
	*size = -mask_lo;
	*base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
	*type = base_lo & 0xff;
}

static int set_fixed_ranges(mtrr_type * frs)
{
	unsigned int *p = (unsigned int *) frs;
	int changed = FALSE;
	int i;
	unsigned int lo, hi;

	rdmsr(MTRRfix64K_00000_MSR, lo, hi);
	if (p[0] != lo || p[1] != hi) {
		mtrr_wrmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
		changed = TRUE;
	}

	for (i = 0; i < 2; i++) {
		rdmsr(MTRRfix16K_80000_MSR + i, lo, hi);
		if (p[2 + i * 2] != lo || p[3 + i * 2] != hi) {
			mtrr_wrmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2],
			      p[3 + i * 2]);
			changed = TRUE;
		}
	}

	for (i = 0; i < 8; i++) {
		rdmsr(MTRRfix4K_C0000_MSR + i, lo, hi);
		if (p[6 + i * 2] != lo || p[7 + i * 2] != hi) {
			mtrr_wrmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2],
			      p[7 + i * 2]);
			changed = TRUE;
		}
	}
	return changed;
}

/*  Set the MSR pair relating to a var range. Returns TRUE if
    changes are made  */
static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
{
	unsigned int lo, hi;
	int changed = FALSE;

	rdmsr(MTRRphysBase_MSR(index), lo, hi);
	if ((vr->base_lo & 0xfffff0ffUL) != (lo & 0xfffff0ffUL)
	    || (vr->base_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
		(hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
		mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi);
		changed = TRUE;
	}

	rdmsr(MTRRphysMask_MSR(index), lo, hi);

	if ((vr->mask_lo & 0xfffff800UL) != (lo & 0xfffff800UL)
	    || (vr->mask_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
		(hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
		mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
		changed = TRUE;
	}
	return changed;
}

static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi)
/*  [SUMMARY] Set the MTRR state for this CPU.
    <state> The MTRR state information to read.
    <ctxt> Some relevant CPU context.
    [NOTE] The CPU must already be in a safe state for MTRR changes.
    [RETURNS] 0 if no changes made, else a mask indication what was changed.
*/
{
	unsigned int i;
	unsigned long change_mask = 0;

	for (i = 0; i < num_var_ranges; i++)
		if (set_mtrr_var_ranges(i, &mtrr_state.var_ranges[i]))
			change_mask |= MTRR_CHANGE_MASK_VARIABLE;

	if (set_fixed_ranges(mtrr_state.fixed_ranges))
		change_mask |= MTRR_CHANGE_MASK_FIXED;

	/*  Set_mtrr_restore restores the old value of MTRRdefType,
	   so to set it we fiddle with the saved value  */
	if ((deftype_lo & 0xff) != mtrr_state.def_type
	    || ((deftype_lo & 0xc00) >> 10) != mtrr_state.enabled) {
		deftype_lo |= (mtrr_state.def_type | mtrr_state.enabled << 10);
		change_mask |= MTRR_CHANGE_MASK_DEFTYPE;
	}

	return change_mask;
}


static unsigned long cr4 = 0;
static u32 deftype_lo, deftype_hi;
static DEFINE_SPINLOCK(set_atomicity_lock);

/*
 * Since we are disabling the cache don't allow any interrupts - they
 * would run extremely slow and would only increase the pain.  The caller must
 * ensure that local interrupts are disabled and are reenabled after post_set()
 * has been called.
 */

static void prepare_set(void)
{
	unsigned long cr0;

	/*  Note that this is not ideal, since the cache is only flushed/disabled
	   for this CPU while the MTRRs are changed, but changing this requires
	   more invasive changes to the way the kernel boots  */

	spin_lock(&set_atomicity_lock);

	/*  Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
	cr0 = read_cr0() | 0x40000000;	/* set CD flag */
	write_cr0(cr0);
	wbinvd();

	/*  Save value of CR4 and clear Page Global Enable (bit 7)  */
	if ( cpu_has_pge ) {
		cr4 = read_cr4();
		write_cr4(cr4 & ~X86_CR4_PGE);
	}

	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
	__flush_tlb();

	/*  Save MTRR state */
	rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);

	/*  Disable MTRRs, and set the default type to uncached  */
	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & 0xf300UL, deftype_hi);
}

static void post_set(void)
{
	/*  Flush TLBs (no need to flush caches - they are disabled)  */
	__flush_tlb();

	/* Intel (P6) standard MTRRs */
	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
		
	/*  Enable caches  */
	write_cr0(read_cr0() & 0xbfffffff);

	/*  Restore value of CR4  */
	if ( cpu_has_pge )
		write_cr4(cr4);
	spin_unlock(&set_atomicity_lock);
}

static void generic_set_all(void)
{
	unsigned long mask, count;
	unsigned long flags;

	local_irq_save(flags);
	prepare_set();

	/* Actually set the state */
	mask = set_mtrr_state(deftype_lo,deftype_hi);

	post_set();
	local_irq_restore(flags);

	/*  Use the atomic bitops to update the global mask  */
	for (count = 0; count < sizeof mask * 8; ++count) {
		if (mask & 0x01)
			set_bit(count, &smp_changes_mask);
		mask >>= 1;
	}
	
}

static void generic_set_mtrr(unsigned int reg, unsigned long base,
			     unsigned long size, mtrr_type type)
/*  [SUMMARY] Set variable MTRR register on the local CPU.
    <reg> The register to set.
    <base> The base address of the region.
    <size> The size of the region. If this is 0 the region is disabled.
    <type> The type of the region.
    <do_safe> If TRUE, do the change safely. If FALSE, safety measures should
    be done externally.
    [RETURNS] Nothing.
*/
{
	unsigned long flags;
	struct mtrr_var_range *vr;

	vr = &mtrr_state.var_ranges[reg];

	local_irq_save(flags);
	prepare_set();

	if (size == 0) {
		/* The invalid bit is kept in the mask, so we simply clear the
		   relevant mask register to disable a range. */
		mtrr_wrmsr(MTRRphysMask_MSR(reg), 0, 0);
		memset(vr, 0, sizeof(struct mtrr_var_range));
	} else {
		vr->base_lo = base << PAGE_SHIFT | type;
		vr->base_hi = (base & size_and_mask) >> (32 - PAGE_SHIFT);
		vr->mask_lo = -size << PAGE_SHIFT | 0x800;
		vr->mask_hi = (-size & size_and_mask) >> (32 - PAGE_SHIFT);

		mtrr_wrmsr(MTRRphysBase_MSR(reg), vr->base_lo, vr->base_hi);
		mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi);
	}

	post_set();
	local_irq_restore(flags);
}

int generic_validate_add_page(unsigned long base, unsigned long size, unsigned int type)
{
	unsigned long lbase, last;

	/*  For Intel PPro stepping <= 7, must be 4 MiB aligned 
	    and not touch 0x70000000->0x7003FFFF */
	if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 &&
	    boot_cpu_data.x86_model == 1 &&
	    boot_cpu_data.x86_mask <= 7) {
		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
			printk(KERN_WARNING "mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
			return -EINVAL;
		}
		if (!(base + size < 0x70000000 || base > 0x7003FFFF) &&
		    (type == MTRR_TYPE_WRCOMB
		     || type == MTRR_TYPE_WRBACK)) {
			printk(KERN_WARNING "mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n");
			return -EINVAL;
		}
	}

	if (base + size < 0x100) {
		printk(KERN_WARNING "mtrr: cannot set region below 1 MiB (0x%lx000,0x%lx000)\n",
		       base, size);
		return -EINVAL;
	}
	/*  Check upper bits of base and last are equal and lower bits are 0
	    for base and 1 for last  */
	last = base + size - 1;
	for (lbase = base; !(lbase & 1) && (last & 1);
	     lbase = lbase >> 1, last = last >> 1) ;
	if (lbase != last) {
		printk(KERN_WARNING "mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n",
		       base, size);
		return -EINVAL;
	}
	return 0;
}


static int generic_have_wrcomb(void)
{
	unsigned long config, dummy;
	rdmsr(MTRRcap_MSR, config, dummy);
	return (config & (1 << 10));
}

int positive_have_wrcomb(void)
{
	return 1;
}

/* generic structure...
 */
struct mtrr_ops generic_mtrr_ops = {
	.use_intel_if      = 1,
	.set_all	   = generic_set_all,
	.get               = generic_get_mtrr,
	.get_free_region   = generic_get_free_region,
	.set               = generic_set_mtrr,
	.validate_add_page = generic_validate_add_page,
	.have_wrcomb       = generic_have_wrcomb,
};
OpenPOWER on IntegriCloud