summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/mcheck/p4.c
blob: f70753a443bb295ad59f6a1cee968e2380734a7b (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
/*
 * P4 specific Machine Check Exception Reporting
 */

#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/smp.h>

#include <asm/therm_throt.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/apic.h>
#include <asm/msr.h>

#include "mce.h"

/* as supported by the P4/Xeon family */
struct intel_mce_extended_msrs {
	u32 eax;
	u32 ebx;
	u32 ecx;
	u32 edx;
	u32 esi;
	u32 edi;
	u32 ebp;
	u32 esp;
	u32 eflags;
	u32 eip;
	/* u32 *reserved[]; */
};

static int mce_num_extended_msrs;


#ifdef CONFIG_X86_MCE_P4THERMAL

static void unexpected_thermal_interrupt(struct pt_regs *regs)
{
	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
			smp_processor_id());
	add_taint(TAINT_MACHINE_CHECK);
}

/* P4/Xeon Thermal transition interrupt handler: */
static void intel_thermal_interrupt(struct pt_regs *regs)
{
	__u64 msr_val;

	ack_APIC_irq();

	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
	therm_throt_process(msr_val & 0x1);
}

/* Thermal interrupt handler for this CPU setup: */
static void (*vendor_thermal_interrupt)(struct pt_regs *regs) =
						unexpected_thermal_interrupt;

void smp_thermal_interrupt(struct pt_regs *regs)
{
	irq_enter();
	vendor_thermal_interrupt(regs);
	__get_cpu_var(irq_stat).irq_thermal_count++;
	irq_exit();
}

static void intel_set_thermal_handler(void)
{
	vendor_thermal_interrupt = intel_thermal_interrupt;
}

/* P4/Xeon Thermal regulation detect and init: */
static void intel_init_thermal(struct cpuinfo_x86 *c)
{
	unsigned int cpu = smp_processor_id();
	int tm2 = 0;
	u32 l, h;

	/* Thermal monitoring depends on ACPI and clock modulation*/
	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
		return;

	/*
	 * First check if its enabled already, in which case there might
	 * be some SMM goo which handles it, so we can't even put a handler
	 * since it might be delivered via SMI already:
	 */
	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
	h = apic_read(APIC_LVTTHMR);
	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
		printk(KERN_DEBUG
		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);
		return;
	}

	if (cpu_has(c, X86_FEATURE_TM2) && (l & MSR_IA32_MISC_ENABLE_TM2))
		tm2 = 1;

	/* Check whether a vector already exists */
	if (h & APIC_VECTOR_MASK) {
		printk(KERN_DEBUG
		       "CPU%d: Thermal LVT vector (%#x) already installed\n",
		       cpu, (h & APIC_VECTOR_MASK));
		return;
	}

	/* We'll mask the thermal vector in the lapic till we're ready: */
	h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED;
	apic_write(APIC_LVTTHMR, h);

	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
	wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03, h);

	intel_set_thermal_handler();

	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
	wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);

	/* Unmask the thermal vector: */
	l = apic_read(APIC_LVTTHMR);
	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);

	printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n",
	       cpu, tm2 ? "TM2" : "TM1");

	/* enable thermal throttle processing */
	atomic_set(&therm_throt_en, 1);
}
#endif /* CONFIG_X86_MCE_P4THERMAL */

/* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */
static void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
{
	u32 h;

	rdmsr(MSR_IA32_MCG_EAX, r->eax, h);
	rdmsr(MSR_IA32_MCG_EBX, r->ebx, h);
	rdmsr(MSR_IA32_MCG_ECX, r->ecx, h);
	rdmsr(MSR_IA32_MCG_EDX, r->edx, h);
	rdmsr(MSR_IA32_MCG_ESI, r->esi, h);
	rdmsr(MSR_IA32_MCG_EDI, r->edi, h);
	rdmsr(MSR_IA32_MCG_EBP, r->ebp, h);
	rdmsr(MSR_IA32_MCG_ESP, r->esp, h);
	rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h);
	rdmsr(MSR_IA32_MCG_EIP, r->eip, h);
}

static void intel_machine_check(struct pt_regs *regs, long error_code)
{
	u32 alow, ahigh, high, low;
	u32 mcgstl, mcgsth;
	int recover = 1;
	int i;

	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
	if (mcgstl & (1<<0))	/* Recoverable ? */
		recover = 0;

	printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
		smp_processor_id(), mcgsth, mcgstl);

	if (mce_num_extended_msrs > 0) {
		struct intel_mce_extended_msrs dbg;

		intel_get_extended_msrs(&dbg);

		printk(KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n"
			"\teax: %08x ebx: %08x ecx: %08x edx: %08x\n"
			"\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
			smp_processor_id(), dbg.eip, dbg.eflags,
			dbg.eax, dbg.ebx, dbg.ecx, dbg.edx,
			dbg.esi, dbg.edi, dbg.ebp, dbg.esp);
	}

	for (i = 0; i < nr_mce_banks; i++) {
		rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
		if (high & (1<<31)) {
			char misc[20];
			char addr[24];

			misc[0] = addr[0] = '\0';
			if (high & (1<<29))
				recover |= 1;
			if (high & (1<<25))
				recover |= 2;
			high &= ~(1<<31);
			if (high & (1<<27)) {
				rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
				snprintf(misc, 20, "[%08x%08x]", ahigh, alow);
			}
			if (high & (1<<26)) {
				rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
				snprintf(addr, 24, " at %08x%08x", ahigh, alow);
			}
			printk(KERN_EMERG "CPU %d: Bank %d: %08x%08x%s%s\n",
				smp_processor_id(), i, high, low, misc, addr);
		}
	}

	if (recover & 2)
		panic("CPU context corrupt");
	if (recover & 1)
		panic("Unable to continue");

	printk(KERN_EMERG "Attempting to continue.\n");

	/*
	 * Do not clear the MSR_IA32_MCi_STATUS if the error is not
	 * recoverable/continuable.This will allow BIOS to look at the MSRs
	 * for errors if the OS could not log the error.
	 */
	for (i = 0; i < nr_mce_banks; i++) {
		u32 msr;
		msr = MSR_IA32_MC0_STATUS+i*4;
		rdmsr(msr, low, high);
		if (high&(1<<31)) {
			/* Clear it */
			wrmsr(msr, 0UL, 0UL);
			/* Serialize */
			wmb();
			add_taint(TAINT_MACHINE_CHECK);
		}
	}
	mcgstl &= ~(1<<2);
	wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
}

void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
{
	u32 l, h;
	int i;

	machine_check_vector = intel_machine_check;
	wmb();

	printk(KERN_INFO "Intel machine check architecture supported.\n");
	rdmsr(MSR_IA32_MCG_CAP, l, h);
	if (l & (1<<8))	/* Control register present ? */
		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
	nr_mce_banks = l & 0xff;

	for (i = 0; i < nr_mce_banks; i++) {
		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
	}

	set_in_cr4(X86_CR4_MCE);
	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
		smp_processor_id());

	/* Check for P4/Xeon extended MCE MSRs */
	rdmsr(MSR_IA32_MCG_CAP, l, h);
	if (l & (1<<9))	{/* MCG_EXT_P */
		mce_num_extended_msrs = (l >> 16) & 0xff;
		printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
				" available\n",
			smp_processor_id(), mce_num_extended_msrs);

#ifdef CONFIG_X86_MCE_P4THERMAL
		/* Check for P4/Xeon Thermal monitor */
		intel_init_thermal(c);
#endif
	}
}
OpenPOWER on IntegriCloud