intel.c 20.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6
#include <linux/init.h>
#include <linux/kernel.h>

#include <linux/string.h>
#include <linux/bitops.h>
#include <linux/smp.h>
I
Ingo Molnar 已提交
7
#include <linux/sched.h>
L
Linus Torvalds 已提交
8
#include <linux/thread_info.h>
N
Nick Piggin 已提交
9
#include <linux/module.h>
A
Alan Cox 已提交
10
#include <linux/uaccess.h>
L
Linus Torvalds 已提交
11 12

#include <asm/processor.h>
13
#include <asm/pgtable.h>
L
Linus Torvalds 已提交
14
#include <asm/msr.h>
15
#include <asm/bugs.h>
16
#include <asm/cpu.h>
L
Linus Torvalds 已提交
17

18
#ifdef CONFIG_X86_64
A
Alan Cox 已提交
19
#include <linux/topology.h>
20 21
#endif

L
Linus Torvalds 已提交
22 23 24 25 26 27 28
#include "cpu.h"

#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
#endif

29
static void early_init_intel(struct cpuinfo_x86 *c)
L
Linus Torvalds 已提交
30
{
31 32
	u64 misc_enable;

33
	/* Unmask CPUID levels if masked: */
34
	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
35 36 37 38 39 40
		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);

		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
			c->cpuid_level = cpuid_eax(0);
41
			get_cpu_cap(c);
42
		}
43 44
	}

45 46 47
	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
		(c->x86 == 0x6 && c->x86_model >= 0x0e))
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
48

49 50 51 52 53 54 55 56 57
	if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) {
		unsigned lower_word;

		wrmsr(MSR_IA32_UCODE_REV, 0, 0);
		/* Required by the SDM */
		sync_core();
		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
	}

58 59 60 61 62 63 64 65
	/*
	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
	 *
	 * A race condition between speculative fetches and invalidating
	 * a large page.  This is worked around in microcode, but we
	 * need the microcode to have already been loaded... so if it is
	 * not, recommend a BIOS update and disable large pages.
	 */
66 67 68 69
	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
	    c->microcode < 0x20e) {
		printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
		clear_cpu_cap(c, X86_FEATURE_PSE);
70 71
	}

72 73 74 75 76 77 78
#ifdef CONFIG_X86_64
	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#else
	/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
	if (c->x86 == 15 && c->x86_cache_alignment == 64)
		c->x86_cache_alignment = 128;
#endif
79

80 81 82 83 84
	/* CPUID workaround for 0F33/0F34 CPU */
	if (c->x86 == 0xF && c->x86_model == 0x3
	    && (c->x86_mask == 0x3 || c->x86_mask == 0x4))
		c->x86_phys_bits = 36;

85 86
	/*
	 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
I
Ingo Molnar 已提交
87 88 89 90
	 * with P/T states and does not stop in deep C-states.
	 *
	 * It is also reliable across cores and sockets. (but not across
	 * cabinets - we turn it off in that case explicitly.)
91 92 93 94
	 */
	if (c->x86_power & (1 << 8)) {
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
95 96
		if (!check_tsc_unstable())
			sched_clock_stable = 1;
97 98
	}

99 100 101 102 103 104 105 106 107 108 109 110
	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
	if (c->x86 == 6) {
		switch (c->x86_model) {
		case 0x27:	/* Penwell */
		case 0x35:	/* Cloverview */
			set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
			break;
		default:
			break;
		}
	}

111 112 113 114 115 116 117 118 119 120 121 122
	/*
	 * There is a known erratum on Pentium III and Core Solo
	 * and Core Duo CPUs.
	 * " Page with PAT set to WC while associated MTRR is UC
	 *   may consolidate to UC "
	 * Because of this erratum, it is better to stick with
	 * setting WC in MTRR rather than using PAT on these CPUs.
	 *
	 * Enable PAT WC only on P4, Core 2 or later CPUs.
	 */
	if (c->x86 == 6 && c->x86_model < 15)
		clear_cpu_cap(c, X86_FEATURE_PAT);
V
Vegard Nossum 已提交
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143

#ifdef CONFIG_KMEMCHECK
	/*
	 * P4s have a "fast strings" feature which causes single-
	 * stepping REP instructions to only generate a #DB on
	 * cache-line boundaries.
	 *
	 * Ingo Molnar reported a Pentium D (model 6) and a Xeon
	 * (model 2) with the same problem.
	 */
	if (c->x86 == 15) {
		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);

		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
			printk(KERN_INFO "kmemcheck: Disabling fast string operations\n");

			misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
		}
	}
#endif
144 145 146 147 148 149 150 151 152 153 154 155 156

	/*
	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
	 * clear the fast string and enhanced fast string CPU capabilities.
	 */
	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
			printk(KERN_INFO "Disabled fast string operations\n");
			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
			setup_clear_cpu_cap(X86_FEATURE_ERMS);
		}
	}
L
Linus Torvalds 已提交
157 158
}

159
#ifdef CONFIG_X86_32
L
Linus Torvalds 已提交
160 161 162 163 164
/*
 *	Early probe support logic for ppro memory erratum #50
 *
 *	This is called before we do cpu ident work
 */
165

166
int ppro_with_ram_bug(void)
L
Linus Torvalds 已提交
167 168 169 170 171 172 173 174 175 176 177
{
	/* Uses data from early_cpu_detect now */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
	    boot_cpu_data.x86 == 6 &&
	    boot_cpu_data.x86_model == 1 &&
	    boot_cpu_data.x86_mask < 8) {
		printk(KERN_INFO "Pentium Pro with Errata#50 detected. Taking evasive action.\n");
		return 1;
	}
	return 0;
}
178

179
static void intel_smp_check(struct cpuinfo_x86 *c)
180 181
{
	/* calling is from identify_secondary_cpu() ? */
182
	if (!c->cpu_index)
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
		return;

	/*
	 * Mask B, Pentium, but not Pentium MMX
	 */
	if (c->x86 == 5 &&
	    c->x86_mask >= 1 && c->x86_mask <= 4 &&
	    c->x86_model <= 3) {
		/*
		 * Remember we have B step Pentia with bugs
		 */
		WARN_ONCE(1, "WARNING: SMP operation may be unreliable"
				    "with B stepping processors.\n");
	}
}

199
static void intel_workarounds(struct cpuinfo_x86 *c)
L
Linus Torvalds 已提交
200 201 202
{
	unsigned long lo, hi;

203 204 205
#ifdef CONFIG_X86_F00F_BUG
	/*
	 * All current models of Pentium and Pentium with MMX technology CPUs
A
Alan Cox 已提交
206
	 * have the F0 0F bug, which lets nonprivileged users lock up the
207
	 * system. Announce that the fault handler will be checking for it.
208
	 */
209
	clear_cpu_bug(c, X86_BUG_F00F);
210 211 212
	if (!paravirt_enabled() && c->x86 == 5) {
		static int f00f_workaround_enabled;

213
		set_cpu_bug(c, X86_BUG_F00F);
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
		if (!f00f_workaround_enabled) {
			printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
			f00f_workaround_enabled = 1;
		}
	}
#endif

	/*
	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
	 * model 3 mask 3
	 */
	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
		clear_cpu_cap(c, X86_FEATURE_SEP);

	/*
	 * P4 Xeon errata 037 workaround.
	 * Hardware prefetcher may cause stale data to be loaded into the cache.
	 */
L
Linus Torvalds 已提交
232
	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
233
		rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
234
		if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
L
Linus Torvalds 已提交
235 236
			printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
			printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
237
			lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
A
Alan Cox 已提交
238
			wrmsr(MSR_IA32_MISC_ENABLE, lo, hi);
L
Linus Torvalds 已提交
239 240 241
		}
	}

242 243 244 245 246 247 248 249 250
	/*
	 * See if we have a good local APIC by checking for buggy Pentia,
	 * i.e. all B steppings and the C2 stepping of P54C when using their
	 * integrated APIC (see 11AP erratum in "Pentium Processor
	 * Specification Update").
	 */
	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
		set_cpu_cap(c, X86_FEATURE_11AP);
251 252


253
#ifdef CONFIG_X86_INTEL_USERCOPY
254
	/*
255
	 * Set up the preferred alignment for movsl bulk memory moves
256
	 */
257 258 259 260 261 262 263 264 265 266 267 268
	switch (c->x86) {
	case 4:		/* 486: untested */
		break;
	case 5:		/* Old Pentia: untested */
		break;
	case 6:		/* PII/PIII only like movsl with 8-byte alignment */
		movsl_mask.mask = 7;
		break;
	case 15:	/* P4 is OK down to 8-byte alignment */
		movsl_mask.mask = 7;
		break;
	}
269
#endif
270 271 272 273

#ifdef CONFIG_X86_NUMAQ
	numaq_tsc_disable();
#endif
274 275

	intel_smp_check(c);
276 277
}
#else
278
static void intel_workarounds(struct cpuinfo_x86 *c)
279 280
{
}
281 282
#endif

283
static void srat_detect_node(struct cpuinfo_x86 *c)
284
{
285
#ifdef CONFIG_NUMA
286 287 288 289 290
	unsigned node;
	int cpu = smp_processor_id();

	/* Don't do the funky fallback heuristics the AMD version employs
	   for now. */
291
	node = numa_cpu_node(cpu);
292
	if (node == NUMA_NO_NODE || !node_online(node)) {
293 294 295
		/* reuse the value from init_cpu_to_node() */
		node = cpu_to_node(cpu);
	}
296 297 298 299
	numa_set_node(cpu, node);
#endif
}

300 301 302
/*
 * find out the number of processor cores on the die
 */
303
static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
304
{
Z
Zachary Amsden 已提交
305
	unsigned int eax, ebx, ecx, edx;
306 307 308 309

	if (c->cpuid_level < 4)
		return 1;

Z
Zachary Amsden 已提交
310 311
	/* Intel has a non-standard dependency on %ecx for this CPUID level. */
	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
312
	if (eax & 0x1f)
A
Alan Cox 已提交
313
		return (eax >> 26) + 1;
314 315 316 317
	else
		return 1;
}

318
static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
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
{
	/* Intel VMX MSR indicated features */
#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020

	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;

	clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
	clear_cpu_cap(c, X86_FEATURE_VNMI);
	clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
	clear_cpu_cap(c, X86_FEATURE_EPT);
	clear_cpu_cap(c, X86_FEATURE_VPID);

	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
	msr_ctl = vmx_msr_high | vmx_msr_low;
	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
		set_cpu_cap(c, X86_FEATURE_VNMI);
	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
		      vmx_msr_low, vmx_msr_high);
		msr_ctl2 = vmx_msr_high | vmx_msr_low;
		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
			set_cpu_cap(c, X86_FEATURE_EPT);
		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
			set_cpu_cap(c, X86_FEATURE_VPID);
	}
}

356
static void init_intel(struct cpuinfo_x86 *c)
L
Linus Torvalds 已提交
357 358 359
{
	unsigned int l2 = 0;

360 361
	early_init_intel(c);

362
	intel_workarounds(c);
L
Linus Torvalds 已提交
363

364 365 366 367 368 369 370
	/*
	 * Detect the extended topology information if available. This
	 * will reinitialise the initial_apicid which will be used
	 * in init_intel_cacheinfo()
	 */
	detect_extended_topology(c);

L
Linus Torvalds 已提交
371
	l2 = init_intel_cacheinfo(c);
372
	if (c->cpuid_level > 9) {
373 374 375
		unsigned eax = cpuid_eax(10);
		/* Check for version and the number of counters */
		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
376
			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
377
	}
L
Linus Torvalds 已提交
378

379 380 381 382 383 384 385 386 387 388
	if (cpu_has_xmm2)
		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
	if (cpu_has_ds) {
		unsigned int l1;
		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
		if (!(l1 & (1<<11)))
			set_cpu_cap(c, X86_FEATURE_BTS);
		if (!(l1 & (1<<12)))
			set_cpu_cap(c, X86_FEATURE_PEBS);
	}
L
Linus Torvalds 已提交
389

390 391
	if (c->x86 == 6 && cpu_has_clflush &&
	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
392 393
		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);

394 395 396 397 398 399
#ifdef CONFIG_X86_64
	if (c->x86 == 15)
		c->x86_cache_alignment = c->x86_clflush_size * 2;
	if (c->x86 == 6)
		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
#else
400 401 402 403 404
	/*
	 * Names for the Pentium II/Celeron processors
	 * detectable only by also checking the cache size.
	 * Dixon is NOT a Celeron.
	 */
L
Linus Torvalds 已提交
405
	if (c->x86 == 6) {
406 407
		char *p = NULL;

L
Linus Torvalds 已提交
408 409
		switch (c->x86_model) {
		case 5:
410 411 412 413
			if (l2 == 0)
				p = "Celeron (Covington)";
			else if (l2 == 256)
				p = "Mobile Pentium II (Dixon)";
L
Linus Torvalds 已提交
414
			break;
415

L
Linus Torvalds 已提交
416 417 418 419 420 421
		case 6:
			if (l2 == 128)
				p = "Celeron (Mendocino)";
			else if (c->x86_mask == 0 || c->x86_mask == 5)
				p = "Celeron-A";
			break;
422

L
Linus Torvalds 已提交
423 424 425 426 427 428
		case 8:
			if (l2 == 128)
				p = "Celeron (Coppermine)";
			break;
		}

429 430
		if (p)
			strcpy(c->x86_model_id, p);
L
Linus Torvalds 已提交
431 432
	}

433 434 435 436
	if (c->x86 == 15)
		set_cpu_cap(c, X86_FEATURE_P4);
	if (c->x86 == 6)
		set_cpu_cap(c, X86_FEATURE_P3);
437
#endif
438 439 440 441 442 443 444 445 446 447 448 449 450

	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
		/*
		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
		 * detection.
		 */
		c->x86_max_cores = intel_num_cpu_cores(c);
#ifdef CONFIG_X86_32
		detect_ht(c);
#endif
	}

	/* Work around errata */
451
	srat_detect_node(c);
452 453 454

	if (cpu_has(c, X86_FEATURE_VMX))
		detect_vmx_virtcap(c);
455 456 457 458 459 460 461 462 463

	/*
	 * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not.
	 * x86_energy_perf_policy(8) is available to change it at run-time
	 */
	if (cpu_has(c, X86_FEATURE_EPB)) {
		u64 epb;

		rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
464 465 466 467 468
		if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) {
			printk_once(KERN_WARNING "ENERGY_PERF_BIAS:"
				" Set to 'normal', was 'performance'\n"
				"ENERGY_PERF_BIAS: View and update with"
				" x86_energy_perf_policy(8)\n");
469 470 471 472
			epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
			wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
		}
	}
473
}
L
Linus Torvalds 已提交
474

475
#ifdef CONFIG_X86_32
476
static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
L
Linus Torvalds 已提交
477
{
478 479
	/*
	 * Intel PIII Tualatin. This comes in two flavours.
L
Linus Torvalds 已提交
480 481 482 483 484 485 486 487
	 * One has 256kb of cache, the other 512. We have no way
	 * to determine which, so we use a boottime override
	 * for the 512kb model, and assume 256 otherwise.
	 */
	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
		size = 256;
	return size;
}
488
#endif
L
Linus Torvalds 已提交
489

490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509
#define TLB_INST_4K	0x01
#define TLB_INST_4M	0x02
#define TLB_INST_2M_4M	0x03

#define TLB_INST_ALL	0x05
#define TLB_INST_1G	0x06

#define TLB_DATA_4K	0x11
#define TLB_DATA_4M	0x12
#define TLB_DATA_2M_4M	0x13
#define TLB_DATA_4K_4M	0x14

#define TLB_DATA_1G	0x16

#define TLB_DATA0_4K	0x21
#define TLB_DATA0_4M	0x22
#define TLB_DATA0_2M_4M	0x23

#define STLB_4K		0x41

510
static const struct _tlb_table intel_tlb_table[] = {
511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539
	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages */" },
	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
	{ 0x00, 0, 0 }
};

540
static void intel_tlb_lookup(const unsigned char desc)
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
{
	unsigned char k;
	if (desc == 0)
		return;

	/* look up this descriptor in the table */
	for (k = 0; intel_tlb_table[k].descriptor != desc && \
			intel_tlb_table[k].descriptor != 0; k++)
		;

	if (intel_tlb_table[k].tlb_type == 0)
		return;

	switch (intel_tlb_table[k].tlb_type) {
	case STLB_4K:
		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_INST_ALL:
		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_INST_4K:
		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_INST_4M:
		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_INST_2M_4M:
		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_DATA_4K:
	case TLB_DATA0_4K:
		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_DATA_4M:
	case TLB_DATA0_4M:
		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_DATA_2M_4M:
	case TLB_DATA0_2M_4M:
		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	case TLB_DATA_4K_4M:
		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
		break;
	}
}

609
static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637
{
	switch ((c->x86 << 8) + c->x86_model) {
	case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
	case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
	case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
		tlb_flushall_shift = -1;
		break;
	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
	case 0x625: /* 32 nm nehalem, "Clarkdale" */
	case 0x62c: /* 32 nm nehalem, "Gulftown" */
	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
	case 0x62f: /* 32 nm Xeon E7 */
		tlb_flushall_shift = 6;
		break;
	case 0x62a: /* SandyBridge */
	case 0x62d: /* SandyBridge, "Romely-EP" */
		tlb_flushall_shift = 5;
		break;
	case 0x63a: /* Ivybridge */
		tlb_flushall_shift = 1;
		break;
	default:
		tlb_flushall_shift = 6;
	}
}

638
static void intel_detect_tlb(struct cpuinfo_x86 *c)
639 640 641 642
{
	int i, j, n;
	unsigned int regs[4];
	unsigned char *desc = (unsigned char *)regs;
643 644 645 646

	if (c->cpuid_level < 2)
		return;

647 648 649 650 651 652 653 654 655 656 657 658 659 660 661
	/* Number of times to iterate */
	n = cpuid_eax(2) & 0xFF;

	for (i = 0 ; i < n ; i++) {
		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);

		/* If bit 31 is set, this is an unknown format */
		for (j = 0 ; j < 3 ; j++)
			if (regs[j] & (1 << 31))
				regs[j] = 0;

		/* Byte 0 is level count, not a descriptor */
		for (j = 1 ; j < 16 ; j++)
			intel_tlb_lookup(desc[j]);
	}
662
	intel_tlb_flushall_shift_set(c);
663 664
}

665
static const struct cpu_dev intel_cpu_dev = {
L
Linus Torvalds 已提交
666
	.c_vendor	= "Intel",
667
	.c_ident	= { "GenuineIntel" },
668
#ifdef CONFIG_X86_32
669 670
	.legacy_models = {
		{ .family = 4, .model_names =
671 672 673 674 675 676 677 678 679
		  {
			  [0] = "486 DX-25/33",
			  [1] = "486 DX-50",
			  [2] = "486 SX",
			  [3] = "486 DX/2",
			  [4] = "486 SL",
			  [5] = "486 SX/2",
			  [7] = "486 DX/2-WB",
			  [8] = "486 DX/4",
L
Linus Torvalds 已提交
680 681 682
			  [9] = "486 DX/4-WB"
		  }
		},
683
		{ .family = 5, .model_names =
684 685 686
		  {
			  [0] = "Pentium 60/66 A-step",
			  [1] = "Pentium 60/66",
L
Linus Torvalds 已提交
687
			  [2] = "Pentium 75 - 200",
688
			  [3] = "OverDrive PODP5V83",
L
Linus Torvalds 已提交
689
			  [4] = "Pentium MMX",
690
			  [7] = "Mobile Pentium 75 - 200",
L
Linus Torvalds 已提交
691 692 693
			  [8] = "Mobile Pentium MMX"
		  }
		},
694
		{ .family = 6, .model_names =
695
		  {
L
Linus Torvalds 已提交
696
			  [0] = "Pentium Pro A-step",
697 698 699 700
			  [1] = "Pentium Pro",
			  [3] = "Pentium II (Klamath)",
			  [4] = "Pentium II (Deschutes)",
			  [5] = "Pentium II (Deschutes)",
L
Linus Torvalds 已提交
701
			  [6] = "Mobile Pentium II",
702 703
			  [7] = "Pentium III (Katmai)",
			  [8] = "Pentium III (Coppermine)",
L
Linus Torvalds 已提交
704 705 706 707
			  [10] = "Pentium III (Cascades)",
			  [11] = "Pentium III (Tualatin)",
		  }
		},
708
		{ .family = 15, .model_names =
L
Linus Torvalds 已提交
709 710 711 712 713 714 715 716 717
		  {
			  [0] = "Pentium 4 (Unknown)",
			  [1] = "Pentium 4 (Willamette)",
			  [2] = "Pentium 4 (Northwood)",
			  [4] = "Pentium 4 (Foster)",
			  [5] = "Pentium 4 (Foster)",
		  }
		},
	},
718
	.legacy_cache_size = intel_size_cache,
719
#endif
720
	.c_detect_tlb	= intel_detect_tlb,
721
	.c_early_init   = early_init_intel,
L
Linus Torvalds 已提交
722
	.c_init		= init_intel,
Y
Yinghai Lu 已提交
723
	.c_x86_vendor	= X86_VENDOR_INTEL,
L
Linus Torvalds 已提交
724 725
};

Y
Yinghai Lu 已提交
726
cpu_dev_register(intel_cpu_dev);
L
Linus Torvalds 已提交
727