blob: 13c6ec81254582e69eae8b6c69b703370b25fb18 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001#include <linux/init.h>
2#include <linux/bitops.h>
Stephen Rothwell5cdd1742011-08-10 11:49:56 +10003#include <linux/elf.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -07004#include <linux/mm.h>
Yinghai Lu8d71a2e2008-09-07 17:58:53 -07005
Alan Cox8bdbd962009-07-04 00:35:45 +01006#include <linux/io.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -07007#include <asm/processor.h>
Andi Kleend3f7eae2007-08-10 22:31:07 +02008#include <asm/apic.h>
Yinghai Lu1f442d72009-03-07 23:46:26 -08009#include <asm/cpu.h>
Andreas Herrmann42937e82009-06-08 15:55:09 +020010#include <asm/pci-direct.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070011
Yinghai Lu8d71a2e2008-09-07 17:58:53 -070012#ifdef CONFIG_X86_64
13# include <asm/numa_64.h>
14# include <asm/mmconfig.h>
15# include <asm/cacheflush.h>
16#endif
17
Linus Torvalds1da177e2005-04-16 15:20:36 -070018#include "cpu.h"
19
Yinghai Lu6c62aa42008-09-07 17:58:54 -070020#ifdef CONFIG_X86_32
Linus Torvalds1da177e2005-04-16 15:20:36 -070021/*
22 * B step AMD K6 before B 9730xxxx have hardware bugs that can cause
23 * misexecution of code under Linux. Owners of such processors should
24 * contact AMD for precise details and a CPU swap.
25 *
26 * See http://www.multimania.com/poulot/k6bug.html
27 * http://www.amd.com/K6/k6docs/revgd.html
28 *
29 * The following test is erm.. interesting. AMD neglected to up
30 * the chip setting when fixing the bug but they also tweaked some
31 * performance at the same time..
32 */
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +010033
Linus Torvalds1da177e2005-04-16 15:20:36 -070034extern void vide(void);
35__asm__(".align 4\nvide: ret");
36
Yinghai Lu11fdd252008-09-07 17:58:50 -070037static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c)
38{
39/*
40 * General Systems BIOSen alias the cpu frequency registers
41 * of the Elan at 0x000df000. Unfortuantly, one of the Linux
42 * drivers subsequently pokes it, and changes the CPU speed.
43 * Workaround : Remove the unneeded alias.
44 */
45#define CBAR (0xfffc) /* Configuration Base Address (32-bit) */
46#define CBAR_ENB (0x80000000)
47#define CBAR_KEY (0X000000CB)
48 if (c->x86_model == 9 || c->x86_model == 10) {
Alan Cox8bdbd962009-07-04 00:35:45 +010049 if (inl(CBAR) & CBAR_ENB)
50 outl(0 | CBAR_KEY, CBAR);
Yinghai Lu11fdd252008-09-07 17:58:50 -070051 }
52}
53
54
55static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
56{
57 u32 l, h;
58 int mbytes = num_physpages >> (20-PAGE_SHIFT);
59
60 if (c->x86_model < 6) {
61 /* Based on AMD doc 20734R - June 2000 */
62 if (c->x86_model == 0) {
63 clear_cpu_cap(c, X86_FEATURE_APIC);
64 set_cpu_cap(c, X86_FEATURE_PGE);
65 }
66 return;
67 }
68
69 if (c->x86_model == 6 && c->x86_mask == 1) {
70 const int K6_BUG_LOOP = 1000000;
71 int n;
72 void (*f_vide)(void);
73 unsigned long d, d2;
74
75 printk(KERN_INFO "AMD K6 stepping B detected - ");
76
77 /*
78 * It looks like AMD fixed the 2.6.2 bug and improved indirect
79 * calls at the same time.
80 */
81
82 n = K6_BUG_LOOP;
83 f_vide = vide;
84 rdtscl(d);
85 while (n--)
86 f_vide();
87 rdtscl(d2);
88 d = d2-d;
89
90 if (d > 20*K6_BUG_LOOP)
Alan Cox8bdbd962009-07-04 00:35:45 +010091 printk(KERN_CONT
92 "system stability may be impaired when more than 32 MB are used.\n");
Yinghai Lu11fdd252008-09-07 17:58:50 -070093 else
Alan Cox8bdbd962009-07-04 00:35:45 +010094 printk(KERN_CONT "probably OK (after B9730xxxx).\n");
Yinghai Lu11fdd252008-09-07 17:58:50 -070095 printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
96 }
97
98 /* K6 with old style WHCR */
99 if (c->x86_model < 8 ||
100 (c->x86_model == 8 && c->x86_mask < 8)) {
101 /* We can only write allocate on the low 508Mb */
102 if (mbytes > 508)
103 mbytes = 508;
104
105 rdmsr(MSR_K6_WHCR, l, h);
106 if ((l&0x0000FFFF) == 0) {
107 unsigned long flags;
108 l = (1<<0)|((mbytes/4)<<1);
109 local_irq_save(flags);
110 wbinvd();
111 wrmsr(MSR_K6_WHCR, l, h);
112 local_irq_restore(flags);
113 printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
114 mbytes);
115 }
116 return;
117 }
118
119 if ((c->x86_model == 8 && c->x86_mask > 7) ||
120 c->x86_model == 9 || c->x86_model == 13) {
121 /* The more serious chips .. */
122
123 if (mbytes > 4092)
124 mbytes = 4092;
125
126 rdmsr(MSR_K6_WHCR, l, h);
127 if ((l&0xFFFF0000) == 0) {
128 unsigned long flags;
129 l = ((mbytes>>2)<<22)|(1<<16);
130 local_irq_save(flags);
131 wbinvd();
132 wrmsr(MSR_K6_WHCR, l, h);
133 local_irq_restore(flags);
134 printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
135 mbytes);
136 }
137
138 return;
139 }
140
141 if (c->x86_model == 10) {
142 /* AMD Geode LX is model 10 */
143 /* placeholder for any needed mods */
144 return;
145 }
146}
147
Yinghai Lu1f442d72009-03-07 23:46:26 -0800148static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
149{
150#ifdef CONFIG_SMP
151 /* calling is from identify_secondary_cpu() ? */
Robert Richterf6e9456c2010-07-21 19:03:58 +0200152 if (!c->cpu_index)
Yinghai Lu1f442d72009-03-07 23:46:26 -0800153 return;
154
155 /*
156 * Certain Athlons might work (for various values of 'work') in SMP
157 * but they are not certified as MP capable.
158 */
159 /* Athlon 660/661 is valid. */
160 if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
161 (c->x86_mask == 1)))
162 goto valid_k7;
163
164 /* Duron 670 is valid */
165 if ((c->x86_model == 7) && (c->x86_mask == 0))
166 goto valid_k7;
167
168 /*
169 * Athlon 662, Duron 671, and Athlon >model 7 have capability
170 * bit. It's worth noting that the A5 stepping (662) of some
171 * Athlon XP's have the MP bit set.
172 * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for
173 * more.
174 */
175 if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
176 ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
177 (c->x86_model > 7))
178 if (cpu_has_mp)
179 goto valid_k7;
180
181 /* If we get here, not a certified SMP capable AMD system. */
182
183 /*
184 * Don't taint if we are running SMP kernel on a single non-MP
185 * approved Athlon
186 */
187 WARN_ONCE(1, "WARNING: This combination of AMD"
Michael Tokarev7da8b6d2009-07-22 17:50:23 +0400188 " processors is not suitable for SMP.\n");
Yinghai Lu1f442d72009-03-07 23:46:26 -0800189 if (!test_taint(TAINT_UNSAFE_SMP))
190 add_taint(TAINT_UNSAFE_SMP);
191
192valid_k7:
193 ;
194#endif
195}
196
Yinghai Lu11fdd252008-09-07 17:58:50 -0700197static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
198{
199 u32 l, h;
200
201 /*
202 * Bit 15 of Athlon specific MSR 15, needs to be 0
203 * to enable SSE on Palomino/Morgan/Barton CPU's.
204 * If the BIOS didn't enable it already, enable it here.
205 */
206 if (c->x86_model >= 6 && c->x86_model <= 10) {
207 if (!cpu_has(c, X86_FEATURE_XMM)) {
208 printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
209 rdmsr(MSR_K7_HWCR, l, h);
210 l &= ~0x00008000;
211 wrmsr(MSR_K7_HWCR, l, h);
212 set_cpu_cap(c, X86_FEATURE_XMM);
213 }
214 }
215
216 /*
217 * It's been determined by AMD that Athlons since model 8 stepping 1
218 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
219 * As per AMD technical note 27212 0.2
220 */
221 if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
222 rdmsr(MSR_K7_CLK_CTL, l, h);
223 if ((l & 0xfff00000) != 0x20000000) {
Alan Cox8bdbd962009-07-04 00:35:45 +0100224 printk(KERN_INFO
225 "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
226 l, ((l & 0x000fffff)|0x20000000));
Yinghai Lu11fdd252008-09-07 17:58:50 -0700227 wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
228 }
229 }
230
231 set_cpu_cap(c, X86_FEATURE_K7);
Yinghai Lu1f442d72009-03-07 23:46:26 -0800232
233 amd_k7_smp_check(c);
Yinghai Lu11fdd252008-09-07 17:58:50 -0700234}
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700235#endif
236
Tejun Heo645a7912011-01-23 14:37:40 +0100237#ifdef CONFIG_NUMA
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100238/*
239 * To workaround broken NUMA config. Read the comment in
240 * srat_detect_node().
241 */
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700242static int __cpuinit nearby_node(int apicid)
243{
244 int i, node;
245
246 for (i = apicid - 1; i >= 0; i--) {
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100247 node = __apicid_to_node[i];
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700248 if (node != NUMA_NO_NODE && node_online(node))
249 return node;
250 }
251 for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100252 node = __apicid_to_node[i];
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700253 if (node != NUMA_NO_NODE && node_online(node))
254 return node;
255 }
256 return first_node(node_online_map); /* Shouldn't happen */
257}
258#endif
Yinghai Lu11fdd252008-09-07 17:58:50 -0700259
260/*
Andreas Herrmann23588c32010-09-30 14:36:28 +0200261 * Fixup core topology information for
262 * (1) AMD multi-node processors
263 * Assumption: Number of cores in each internal node is the same.
Andreas Herrmann6057b4d2010-09-30 14:38:57 +0200264 * (2) AMD processors supporting compute units
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200265 */
266#ifdef CONFIG_X86_HT
Andreas Herrmann23588c32010-09-30 14:36:28 +0200267static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200268{
Borislav Petkov9e815092011-02-14 18:14:51 +0100269 u32 nodes, cores_per_cu = 1;
Andreas Herrmann23588c32010-09-30 14:36:28 +0200270 u8 node_id;
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200271 int cpu = smp_processor_id();
272
Andreas Herrmann23588c32010-09-30 14:36:28 +0200273 /* get information required for multi-node processors */
274 if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
Andreas Herrmann6057b4d2010-09-30 14:38:57 +0200275 u32 eax, ebx, ecx, edx;
276
277 cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
278 nodes = ((ecx >> 8) & 7) + 1;
279 node_id = ecx & 7;
280
281 /* get compute unit information */
282 smp_num_siblings = ((ebx >> 8) & 3) + 1;
283 c->compute_unit_id = ebx & 0xff;
Borislav Petkov9e815092011-02-14 18:14:51 +0100284 cores_per_cu += ((ebx >> 8) & 3);
Andreas Herrmann23588c32010-09-30 14:36:28 +0200285 } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
Andreas Herrmann6057b4d2010-09-30 14:38:57 +0200286 u64 value;
287
Andreas Herrmann23588c32010-09-30 14:36:28 +0200288 rdmsrl(MSR_FAM10H_NODE_ID, value);
289 nodes = ((value >> 3) & 7) + 1;
290 node_id = value & 7;
291 } else
Andreas Herrmann9d260eb2009-12-16 15:43:55 +0100292 return;
293
Andreas Herrmann23588c32010-09-30 14:36:28 +0200294 /* fixup multi-node processor information */
295 if (nodes > 1) {
Andreas Herrmann6057b4d2010-09-30 14:38:57 +0200296 u32 cores_per_node;
Andreas Herrmannd5185732011-01-24 16:05:40 +0100297 u32 cus_per_node;
Andreas Herrmann6057b4d2010-09-30 14:38:57 +0200298
Andreas Herrmann23588c32010-09-30 14:36:28 +0200299 set_cpu_cap(c, X86_FEATURE_AMD_DCM);
300 cores_per_node = c->x86_max_cores / nodes;
Andreas Herrmannd5185732011-01-24 16:05:40 +0100301 cus_per_node = cores_per_node / cores_per_cu;
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200302
Andreas Herrmann23588c32010-09-30 14:36:28 +0200303 /* store NodeID, use llc_shared_map to store sibling info */
304 per_cpu(cpu_llc_id, cpu) = node_id;
Andreas Herrmann9d260eb2009-12-16 15:43:55 +0100305
Borislav Petkov9e815092011-02-14 18:14:51 +0100306 /* core id has to be in the [0 .. cores_per_node - 1] range */
Andreas Herrmannd5185732011-01-24 16:05:40 +0100307 c->cpu_core_id %= cores_per_node;
308 c->compute_unit_id %= cus_per_node;
Andreas Herrmann23588c32010-09-30 14:36:28 +0200309 }
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200310}
311#endif
312
313/*
Yinghai Lu11fdd252008-09-07 17:58:50 -0700314 * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
315 * Assumes number of cores is a power of two.
316 */
317static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
318{
319#ifdef CONFIG_X86_HT
320 unsigned bits;
Andreas Herrmann99bd0c02009-06-19 10:59:09 +0200321 int cpu = smp_processor_id();
Yinghai Lu11fdd252008-09-07 17:58:50 -0700322
323 bits = c->x86_coreid_bits;
Yinghai Lu11fdd252008-09-07 17:58:50 -0700324 /* Low order bits define the core id (index of core in socket) */
325 c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
326 /* Convert the initial APIC ID into the socket ID */
327 c->phys_proc_id = c->initial_apicid >> bits;
Andreas Herrmann99bd0c02009-06-19 10:59:09 +0200328 /* use socket ID also for last level cache */
329 per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
Andreas Herrmann23588c32010-09-30 14:36:28 +0200330 amd_get_topology(c);
Yinghai Lu11fdd252008-09-07 17:58:50 -0700331#endif
332}
333
Andreas Herrmann6a812692009-09-16 11:33:40 +0200334int amd_get_nb_id(int cpu)
335{
336 int id = 0;
337#ifdef CONFIG_SMP
338 id = per_cpu(cpu_llc_id, cpu);
339#endif
340 return id;
341}
342EXPORT_SYMBOL_GPL(amd_get_nb_id);
343
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700344static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
345{
Tejun Heo645a7912011-01-23 14:37:40 +0100346#ifdef CONFIG_NUMA
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700347 int cpu = smp_processor_id();
348 int node;
Yinghai Lu0d96b9f2009-08-29 13:17:14 -0700349 unsigned apicid = c->apicid;
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700350
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100351 node = numa_cpu_node(cpu);
352 if (node == NUMA_NO_NODE)
353 node = per_cpu(cpu_llc_id, cpu);
Andreas Herrmann4a376ec2009-09-03 09:40:21 +0200354
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700355 if (!node_online(node)) {
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100356 /*
357 * Two possibilities here:
358 *
359 * - The CPU is missing memory and no node was created. In
360 * that case try picking one from a nearby CPU.
361 *
362 * - The APIC IDs differ from the HyperTransport node IDs
363 * which the K8 northbridge parsing fills in. Assume
364 * they are all increased by a constant offset, but in
365 * the same order as the HT nodeids. If that doesn't
366 * result in a usable node fall back to the path for the
367 * previous case.
368 *
369 * This workaround operates directly on the mapping between
370 * APIC ID and NUMA node, assuming certain relationship
371 * between APIC ID, HT node ID and NUMA topology. As going
372 * through CPU mapping may alter the outcome, directly
373 * access __apicid_to_node[].
374 */
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700375 int ht_nodeid = c->initial_apicid;
376
377 if (ht_nodeid >= 0 &&
Tejun Heobbc9e2f2011-01-23 14:37:39 +0100378 __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
379 node = __apicid_to_node[ht_nodeid];
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700380 /* Pick a nearby node */
381 if (!node_online(node))
382 node = nearby_node(apicid);
383 }
384 numa_set_node(cpu, node);
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700385#endif
386}
387
Yinghai Lu11fdd252008-09-07 17:58:50 -0700388static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
389{
390#ifdef CONFIG_X86_HT
391 unsigned bits, ecx;
392
393 /* Multi core CPU? */
394 if (c->extended_cpuid_level < 0x80000008)
395 return;
396
397 ecx = cpuid_ecx(0x80000008);
398
399 c->x86_max_cores = (ecx & 0xff) + 1;
400
401 /* CPU telling us the core id bits shift? */
402 bits = (ecx >> 12) & 0xF;
403
404 /* Otherwise recompute */
405 if (bits == 0) {
406 while ((1 << bits) < c->x86_max_cores)
407 bits++;
408 }
409
410 c->x86_coreid_bits = bits;
411#endif
412}
413
Borislav Petkov8fa8b032011-08-05 20:04:09 +0200414static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c)
415{
416 if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
417
418 if (c->x86 > 0x10 ||
419 (c->x86 == 0x10 && c->x86_model >= 0x2)) {
420 u64 val;
421
422 rdmsrl(MSR_K7_HWCR, val);
423 if (!(val & BIT(24)))
424 printk(KERN_WARNING FW_BUG "TSC doesn't count "
425 "with P0 frequency!\n");
426 }
427 }
428
429 if (c->x86 == 0x15) {
430 unsigned long upperbit;
431 u32 cpuid, assoc;
432
433 cpuid = cpuid_edx(0x80000005);
434 assoc = cpuid >> 16 & 0xff;
435 upperbit = ((cpuid >> 24) << 10) / assoc;
436
437 va_align.mask = (upperbit - 1) & PAGE_MASK;
438 va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
439 }
440}
441
Thomas Petazzoni03ae5762008-02-15 12:00:23 +0100442static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
Andi Kleen2b16a232008-01-30 13:32:40 +0100443{
Yinghai Lu11fdd252008-09-07 17:58:50 -0700444 early_init_amd_mc(c);
445
Venki Pallipadi40fb1712008-11-17 16:11:37 -0800446 /*
447 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
448 * with P/T states and does not stop in deep C-states
449 */
450 if (c->x86_power & (1 << 8)) {
Yinghai Lue3224232008-09-06 01:52:28 -0700451 set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
Venki Pallipadi40fb1712008-11-17 16:11:37 -0800452 set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
453 }
Yinghai Lu5fef55f2008-09-04 21:09:43 +0200454
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700455#ifdef CONFIG_X86_64
456 set_cpu_cap(c, X86_FEATURE_SYSCALL32);
457#else
Yinghai Lu5fef55f2008-09-04 21:09:43 +0200458 /* Set MTRR capability flag if appropriate */
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700459 if (c->x86 == 5)
460 if (c->x86_model == 13 || c->x86_model == 9 ||
461 (c->x86_model == 8 && c->x86_mask >= 8))
462 set_cpu_cap(c, X86_FEATURE_K6_MTRR);
463#endif
Andreas Herrmann42937e82009-06-08 15:55:09 +0200464#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
465 /* check CPU config space for extended APIC ID */
Jeremy Fitzhardinge2cb07862009-07-22 09:59:35 -0700466 if (cpu_has_apic && c->x86 >= 0xf) {
Andreas Herrmann42937e82009-06-08 15:55:09 +0200467 unsigned int val;
468 val = read_pci_config(0, 24, 0, 0x68);
469 if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
470 set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
471 }
472#endif
Andi Kleen2b16a232008-01-30 13:32:40 +0100473}
474
Magnus Dammb4af3f72006-09-26 10:52:36 +0200475static void __cpuinit init_amd(struct cpuinfo_x86 *c)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700476{
Andi Kleen7d318d72005-09-29 22:05:55 +0200477#ifdef CONFIG_SMP
Andi Kleen3c92c2b2005-10-11 01:28:33 +0200478 unsigned long long value;
Andi Kleen7d318d72005-09-29 22:05:55 +0200479
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100480 /*
481 * Disable TLB flush filter by setting HWCR.FFDIS on K8
Andi Kleen7d318d72005-09-29 22:05:55 +0200482 * bit 6 of msr C001_0015
483 *
484 * Errata 63 for SH-B3 steppings
485 * Errata 122 for all steppings (F+ have it disabled by default)
486 */
Yinghai Lu11fdd252008-09-07 17:58:50 -0700487 if (c->x86 == 0xf) {
Andi Kleen7d318d72005-09-29 22:05:55 +0200488 rdmsrl(MSR_K7_HWCR, value);
489 value |= 1 << 6;
490 wrmsrl(MSR_K7_HWCR, value);
491 }
492#endif
493
Andi Kleen2b16a232008-01-30 13:32:40 +0100494 early_init_amd(c);
495
Linus Torvalds1da177e2005-04-16 15:20:36 -0700496 /*
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100497 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
Ingo Molnar16282a82008-02-26 08:49:57 +0100498 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100499 */
Ingo Molnar16282a82008-02-26 08:49:57 +0100500 clear_cpu_cap(c, 0*32+31);
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100501
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700502#ifdef CONFIG_X86_64
503 /* On C+ stepping K8 rep microcode works well for copy/memset */
504 if (c->x86 == 0xf) {
505 u32 level;
506
507 level = cpuid_eax(1);
Alan Cox8bdbd962009-07-04 00:35:45 +0100508 if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700509 set_cpu_cap(c, X86_FEATURE_REP_GOOD);
Kevin Winchesterfbd8b182009-08-10 19:56:45 -0300510
511 /*
512 * Some BIOSes incorrectly force this feature, but only K8
513 * revision D (model = 0x14) and later actually support it.
Borislav Petkov6b0f43d2009-08-31 09:50:11 +0200514 * (AMD Erratum #110, docId: 25759).
Kevin Winchesterfbd8b182009-08-10 19:56:45 -0300515 */
Borislav Petkov6b0f43d2009-08-31 09:50:11 +0200516 if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
517 u64 val;
518
Kevin Winchesterfbd8b182009-08-10 19:56:45 -0300519 clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
Borislav Petkov6b0f43d2009-08-31 09:50:11 +0200520 if (!rdmsrl_amd_safe(0xc001100d, &val)) {
521 val &= ~(1ULL << 32);
522 wrmsrl_amd_safe(0xc001100d, val);
523 }
524 }
525
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700526 }
Borislav Petkov12d8a962010-06-02 20:29:21 +0200527 if (c->x86 >= 0x10)
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700528 set_cpu_cap(c, X86_FEATURE_REP_GOOD);
Yinghai Lu0d96b9f2009-08-29 13:17:14 -0700529
530 /* get apicid instead of initial apic id from cpuid */
531 c->apicid = hard_smp_processor_id();
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700532#else
533
534 /*
535 * FIXME: We should handle the K5 here. Set up the write
536 * range and also turn on MSR 83 bits 4 and 31 (write alloc,
537 * no bus pipeline)
538 */
539
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100540 switch (c->x86) {
541 case 4:
Yinghai Lu11fdd252008-09-07 17:58:50 -0700542 init_amd_k5(c);
543 break;
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100544 case 5:
Yinghai Lu11fdd252008-09-07 17:58:50 -0700545 init_amd_k6(c);
546 break;
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100547 case 6: /* An Athlon/Duron */
Yinghai Lu11fdd252008-09-07 17:58:50 -0700548 init_amd_k7(c);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700549 break;
Andi Kleen67cddd92007-07-21 17:10:03 +0200550 }
Andi Kleen3556ddf2007-04-02 12:14:12 +0200551
Andi Kleenc12ceb72007-05-21 14:31:47 +0200552 /* K6s reports MCEs but don't actually have all the MSRs */
553 if (c->x86 < 6)
Ingo Molnar16282a82008-02-26 08:49:57 +0100554 clear_cpu_cap(c, X86_FEATURE_MCE);
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700555#endif
Andi Kleende421862008-01-30 13:32:37 +0100556
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700557 /* Enable workaround for FXSAVE leak */
Yinghai Lu11fdd252008-09-07 17:58:50 -0700558 if (c->x86 >= 6)
559 set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
560
561 if (!c->x86_model_id[0]) {
562 switch (c->x86) {
563 case 0xf:
564 /* Should distinguish Models here, but this is only
565 a fallback anyways. */
566 strcpy(c->x86_model_id, "Hammer");
567 break;
568 }
569 }
570
Borislav Petkov27c13ec2009-11-21 14:01:45 +0100571 cpu_detect_cache_sizes(c);
Yinghai Lu11fdd252008-09-07 17:58:50 -0700572
573 /* Multi core CPU? */
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700574 if (c->extended_cpuid_level >= 0x80000008) {
Yinghai Lu11fdd252008-09-07 17:58:50 -0700575 amd_detect_cmp(c);
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700576 srat_detect_node(c);
577 }
Yinghai Lu11fdd252008-09-07 17:58:50 -0700578
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700579#ifdef CONFIG_X86_32
Yinghai Lu11fdd252008-09-07 17:58:50 -0700580 detect_ht(c);
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700581#endif
Yinghai Lu11fdd252008-09-07 17:58:50 -0700582
583 if (c->extended_cpuid_level >= 0x80000006) {
Andreas Herrmannd9fadd72010-09-02 15:37:10 +0200584 if (cpuid_edx(0x80000006) & 0xf000)
Yinghai Lu11fdd252008-09-07 17:58:50 -0700585 num_cache_leaves = 4;
586 else
587 num_cache_leaves = 3;
588 }
589
Borislav Petkov12d8a962010-06-02 20:29:21 +0200590 if (c->x86 >= 0xf)
Yinghai Lu11fdd252008-09-07 17:58:50 -0700591 set_cpu_cap(c, X86_FEATURE_K8);
592
593 if (cpu_has_xmm2) {
594 /* MFENCE stops RDTSC speculation */
Ingo Molnar16282a82008-02-26 08:49:57 +0100595 set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
Yinghai Lu11fdd252008-09-07 17:58:50 -0700596 }
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700597
598#ifdef CONFIG_X86_64
599 if (c->x86 == 0x10) {
600 /* do this for boot cpu */
601 if (c == &boot_cpu_data)
602 check_enable_amd_mmconf_dmi();
603
604 fam10h_check_enable_mmcfg();
605 }
606
Borislav Petkov12d8a962010-06-02 20:29:21 +0200607 if (c == &boot_cpu_data && c->x86 >= 0xf) {
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700608 unsigned long long tseg;
609
610 /*
611 * Split up direct mapping around the TSEG SMM area.
612 * Don't do it for gbpages because there seems very little
613 * benefit in doing so.
614 */
615 if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
Alan Cox8bdbd962009-07-04 00:35:45 +0100616 printk(KERN_DEBUG "tseg: %010llx\n", tseg);
617 if ((tseg>>PMD_SHIFT) <
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700618 (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
Alan Cox8bdbd962009-07-04 00:35:45 +0100619 ((tseg>>PMD_SHIFT) <
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700620 (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
Alan Cox8bdbd962009-07-04 00:35:45 +0100621 (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
622 set_memory_4k((unsigned long)__va(tseg), 1);
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700623 }
624 }
625#endif
Boris Ostrovskyb87cf802011-03-15 12:13:44 -0400626
Boris Ostrovskye9cdd342011-05-26 11:19:52 -0400627 /*
628 * Family 0x12 and above processors have APIC timer
629 * running in deep C states.
630 */
631 if (c->x86 > 0x11)
Boris Ostrovskyb87cf802011-03-15 12:13:44 -0400632 set_cpu_cap(c, X86_FEATURE_ARAT);
Joerg Roedel5bbc0972011-04-15 14:47:40 +0200633
634 /*
635 * Disable GART TLB Walk Errors on Fam10h. We do this here
636 * because this is always needed when GART is enabled, even in a
637 * kernel which has no MCE support built in.
638 */
639 if (c->x86 == 0x10) {
640 /*
641 * BIOS should disable GartTlbWlk Errors themself. If
642 * it doesn't do it here as suggested by the BKDG.
643 *
644 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
645 */
646 u64 mask;
Roedel, Joergd47cc0d2011-05-19 11:13:39 +0200647 int err;
Joerg Roedel5bbc0972011-04-15 14:47:40 +0200648
Roedel, Joergd47cc0d2011-05-19 11:13:39 +0200649 err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
650 if (err == 0) {
651 mask |= (1 << 10);
652 checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
653 }
Joerg Roedel5bbc0972011-04-15 14:47:40 +0200654 }
Linus Torvalds1da177e2005-04-16 15:20:36 -0700655}
656
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700657#ifdef CONFIG_X86_32
Alan Cox8bdbd962009-07-04 00:35:45 +0100658static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
659 unsigned int size)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700660{
661 /* AMD errata T13 (order #21922) */
662 if ((c->x86 == 6)) {
Alan Cox8bdbd962009-07-04 00:35:45 +0100663 /* Duron Rev A0 */
664 if (c->x86_model == 3 && c->x86_mask == 0)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700665 size = 64;
Alan Cox8bdbd962009-07-04 00:35:45 +0100666 /* Tbird rev A1/A2 */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700667 if (c->x86_model == 4 &&
Alan Cox8bdbd962009-07-04 00:35:45 +0100668 (c->x86_mask == 0 || c->x86_mask == 1))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700669 size = 256;
670 }
671 return size;
672}
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700673#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700674
Jan Beulich02dde8b2009-03-12 12:08:49 +0000675static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700676 .c_vendor = "AMD",
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100677 .c_ident = { "AuthenticAMD" },
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700678#ifdef CONFIG_X86_32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700679 .c_models = {
680 { .vendor = X86_VENDOR_AMD, .family = 4, .model_names =
681 {
682 [3] = "486 DX/2",
683 [7] = "486 DX/2-WB",
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100684 [8] = "486 DX/4",
685 [9] = "486 DX/4-WB",
Linus Torvalds1da177e2005-04-16 15:20:36 -0700686 [14] = "Am5x86-WT",
Paolo Ciarrocchifb87a292008-02-22 23:10:33 +0100687 [15] = "Am5x86-WB"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700688 }
689 },
690 },
Yinghai Lu6c62aa42008-09-07 17:58:54 -0700691 .c_size_cache = amd_size_cache,
692#endif
Thomas Petazzoni03ae5762008-02-15 12:00:23 +0100693 .c_early_init = early_init_amd,
Borislav Petkov8fa8b032011-08-05 20:04:09 +0200694 .c_bsp_init = bsp_init_amd,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700695 .c_init = init_amd,
Yinghai Lu10a434f2008-09-04 21:09:45 +0200696 .c_x86_vendor = X86_VENDOR_AMD,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700697};
698
Yinghai Lu10a434f2008-09-04 21:09:45 +0200699cpu_dev_register(amd_cpu_dev);
Hans Rosenfeldd78d6712010-07-28 19:09:30 +0200700
701/*
702 * AMD errata checking
703 *
704 * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
705 * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
706 * have an OSVW id assigned, which it takes as first argument. Both take a
707 * variable number of family-specific model-stepping ranges created by
708 * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const
709 * int[] in arch/x86/include/asm/processor.h.
710 *
711 * Example:
712 *
713 * const int amd_erratum_319[] =
714 * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
715 * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
716 * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
717 */
718
Hans Rosenfeld9d8888c2010-07-28 19:09:31 +0200719const int amd_erratum_400[] =
Borislav Petkov328935e2011-05-17 14:55:18 +0200720 AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
Hans Rosenfeld9d8888c2010-07-28 19:09:31 +0200721 AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
H. Peter Anvina5b91602010-07-28 16:23:20 -0700722EXPORT_SYMBOL_GPL(amd_erratum_400);
Hans Rosenfeld9d8888c2010-07-28 19:09:31 +0200723
Hans Rosenfeld1be85a62010-07-28 19:09:32 +0200724const int amd_erratum_383[] =
725 AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
H. Peter Anvina5b91602010-07-28 16:23:20 -0700726EXPORT_SYMBOL_GPL(amd_erratum_383);
Hans Rosenfeld9d8888c2010-07-28 19:09:31 +0200727
Hans Rosenfeldd78d6712010-07-28 19:09:30 +0200728bool cpu_has_amd_erratum(const int *erratum)
729{
Tejun Heo7b543a52010-12-18 16:30:05 +0100730 struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
Hans Rosenfeldd78d6712010-07-28 19:09:30 +0200731 int osvw_id = *erratum++;
732 u32 range;
733 u32 ms;
734
735 /*
736 * If called early enough that current_cpu_data hasn't been initialized
737 * yet, fall back to boot_cpu_data.
738 */
739 if (cpu->x86 == 0)
740 cpu = &boot_cpu_data;
741
742 if (cpu->x86_vendor != X86_VENDOR_AMD)
743 return false;
744
745 if (osvw_id >= 0 && osvw_id < 65536 &&
746 cpu_has(cpu, X86_FEATURE_OSVW)) {
747 u64 osvw_len;
748
749 rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
750 if (osvw_id < osvw_len) {
751 u64 osvw_bits;
752
753 rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
754 osvw_bits);
755 return osvw_bits & (1ULL << (osvw_id & 0x3f));
756 }
757 }
758
759 /* OSVW unavailable or ID unknown, match family-model-stepping range */
Hans Rosenfeld07a77952010-08-18 16:19:50 +0200760 ms = (cpu->x86_model << 4) | cpu->x86_mask;
Hans Rosenfeldd78d6712010-07-28 19:09:30 +0200761 while ((range = *erratum++))
762 if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
763 (ms >= AMD_MODEL_RANGE_START(range)) &&
764 (ms <= AMD_MODEL_RANGE_END(range)))
765 return true;
766
767 return false;
768}
H. Peter Anvina5b91602010-07-28 16:23:20 -0700769
770EXPORT_SYMBOL_GPL(cpu_has_amd_erratum);