summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/x86/include/asm/nmi.h37
-rw-r--r--arch/x86/include/asm/perf_event.h55
-rw-r--r--arch/x86/include/asm/reboot.h2
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c27
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c20
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c23
-rw-r--r--arch/x86/kernel/cpu/perf_event.c69
-rw-r--r--arch/x86/kernel/cpu/perf_event.h12
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c17
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c294
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c91
-rw-r--r--arch/x86/kernel/crash.c5
-rw-r--r--arch/x86/kernel/kgdb.c60
-rw-r--r--arch/x86/kernel/nmi.c433
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/reboot.c23
-rw-r--r--arch/x86/kernel/traps.c155
-rw-r--r--arch/x86/oprofile/nmi_int.c40
-rw-r--r--arch/x86/oprofile/nmi_timer_int.c28
-rw-r--r--arch/x86/oprofile/op_model_amd.c234
-rw-r--r--arch/x86/oprofile/op_x86_model.h1
-rw-r--r--drivers/acpi/apei/ghes.c22
-rw-r--r--drivers/char/ipmi/ipmi_watchdog.c33
-rw-r--r--drivers/watchdog/hpwdt.c25
-rw-r--r--include/linux/perf_event.h5
29 files changed, 1056 insertions, 683 deletions
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 4886a68f267..fd3f9f18cf3 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -22,27 +22,26 @@ void arch_trigger_all_cpu_backtrace(void);
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
#endif
-/*
- * Define some priorities for the nmi notifier call chain.
- *
- * Create a local nmi bit that has a higher priority than
- * external nmis, because the local ones are more frequent.
- *
- * Also setup some default high/normal/low settings for
- * subsystems to registers with. Using 4 bits to separate
- * the priorities. This can go a lot higher if needed be.
- */
-
-#define NMI_LOCAL_SHIFT 16 /* randomly picked */
-#define NMI_LOCAL_BIT (1ULL << NMI_LOCAL_SHIFT)
-#define NMI_HIGH_PRIOR (1ULL << 8)
-#define NMI_NORMAL_PRIOR (1ULL << 4)
-#define NMI_LOW_PRIOR (1ULL << 0)
-#define NMI_LOCAL_HIGH_PRIOR (NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
-#define NMI_LOCAL_NORMAL_PRIOR (NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
-#define NMI_LOCAL_LOW_PRIOR (NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+#define NMI_FLAG_FIRST 1
+
+enum {
+ NMI_LOCAL=0,
+ NMI_UNKNOWN,
+ NMI_MAX
+};
+
+#define NMI_DONE 0
+#define NMI_HANDLED 1
+
+typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
+
+int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long,
+ const char *);
+
+void unregister_nmi_handler(unsigned int, const char *);
void stop_nmi(void);
void restart_nmi(void);
+void local_touch_nmi(void);
#endif /* _ASM_X86_NMI_H */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 094fb30817a..f61c62f7d5d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,6 +29,9 @@
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
+#define AMD_PERFMON_EVENTSEL_GUESTONLY (1ULL << 40)
+#define AMD_PERFMON_EVENTSEL_HOSTONLY (1ULL << 41)
+
#define AMD64_EVENTSEL_EVENT \
(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
#define INTEL_ARCH_EVENT_MASK \
@@ -43,14 +46,17 @@
#define AMD64_RAW_EVENT_MASK \
(X86_RAW_EVENT_MASK | \
AMD64_EVENTSEL_EVENT)
+#define AMD64_NUM_COUNTERS 4
+#define AMD64_NUM_COUNTERS_F15H 6
+#define AMD64_NUM_COUNTERS_MAX AMD64_NUM_COUNTERS_F15H
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
+#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
/*
* Intel "Architectural Performance Monitoring" CPUID
@@ -110,6 +116,35 @@ union cpuid10_edx {
*/
#define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16)
+/*
+ * IBS cpuid feature detection
+ */
+
+#define IBS_CPUID_FEATURES 0x8000001b
+
+/*
+ * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
+ * bit 0 is used to indicate the existence of IBS.
+ */
+#define IBS_CAPS_AVAIL (1U<<0)
+#define IBS_CAPS_FETCHSAM (1U<<1)
+#define IBS_CAPS_OPSAM (1U<<2)
+#define IBS_CAPS_RDWROPCNT (1U<<3)
+#define IBS_CAPS_OPCNT (1U<<4)
+#define IBS_CAPS_BRNTRGT (1U<<5)
+#define IBS_CAPS_OPCNTEXT (1U<<6)
+
+#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
+ | IBS_CAPS_FETCHSAM \
+ | IBS_CAPS_OPSAM)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL 0x1cc
+#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK 0x0F
+
/* IbsFetchCtl bits/masks */
#define IBS_FETCH_RAND_EN (1ULL<<57)
#define IBS_FETCH_VAL (1ULL<<49)
@@ -124,6 +159,8 @@ union cpuid10_edx {
#define IBS_OP_MAX_CNT 0x0000FFFFULL
#define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */
+extern u32 get_ibs_caps(void);
+
#ifdef CONFIG_PERF_EVENTS
extern void perf_events_lapic_init(void);
@@ -159,7 +196,19 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
); \
}
+struct perf_guest_switch_msr {
+ unsigned msr;
+ u64 host, guest;
+};
+
+extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
#else
+static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+ *nr = 0;
+ return NULL;
+}
+
static inline void perf_events_lapic_init(void) { }
#endif
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 3250e3d605d..92f297069e8 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -23,7 +23,7 @@ void machine_real_restart(unsigned int type);
#define MRR_BIOS 0
#define MRR_APM 1
-typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
void nmi_shootdown_cpus(nmi_shootdown_cb callback);
#endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 82f2912155a..8baca3c4871 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -19,7 +19,7 @@ endif
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y += time.o ioport.o ldt.o dumpstack.o
+obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-y += probe_roms.o
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d5e57db0f7b..31cb9ae992b 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -60,22 +60,10 @@ void arch_trigger_all_cpu_backtrace(void)
}
static int __kprobes
-arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
- unsigned long cmd, void *__args)
+arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
{
- struct die_args *args = __args;
- struct pt_regs *regs;
int cpu;
- switch (cmd) {
- case DIE_NMI:
- break;
-
- default:
- return NOTIFY_DONE;
- }
-
- regs = args->regs;
cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
@@ -86,21 +74,16 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
show_regs(regs);
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
- return NOTIFY_DONE;
+ return NMI_DONE;
}
-static __read_mostly struct notifier_block backtrace_notifier = {
- .notifier_call = arch_trigger_all_cpu_backtrace_handler,
- .next = NULL,
- .priority = NMI_LOCAL_LOW_PRIOR,
-};
-
static int __init register_trigger_all_cpu_backtrace(void)
{
- register_die_notifier(&backtrace_notifier);
+ register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler,
+ 0, "arch_bt");
return 0;
}
early_initcall(register_trigger_all_cpu_backtrace);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 34b18594e72..75be00ecfff 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -672,18 +672,11 @@ void __cpuinit uv_cpu_init(void)
/*
* When NMI is received, print a stack trace.
*/
-int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
+int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
{
unsigned long real_uv_nmi;
int bid;
- if (reason != DIE_NMIUNKNOWN)
- return NOTIFY_OK;
-
- if (in_crash_kexec)
- /* do nothing if entering the crash kernel */
- return NOTIFY_OK;
-
/*
* Each blade has an MMR that indicates when an NMI has been sent
* to cpus on the blade. If an NMI is detected, atomically
@@ -704,7 +697,7 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
}
if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
- return NOTIFY_DONE;
+ return NMI_DONE;
__get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
@@ -717,17 +710,12 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
dump_stack();
spin_unlock(&uv_nmi_lock);
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
-static struct notifier_block uv_dump_stack_nmi_nb = {
- .notifier_call = uv_handle_nmi,
- .priority = NMI_LOCAL_LOW_PRIOR - 1,
-};
-
void uv_register_nmi_notifier(void)
{
- if (register_die_notifier(&uv_dump_stack_nmi_nb))
+ if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv"))
printk(KERN_WARNING "UV NMI handler failed to register\n");
}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 1044fd787db..fe6eb197f84 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,7 +36,7 @@ endif
obj-$(CONFIG_X86_MCE) += mcheck/
obj-$(CONFIG_MTRR) += mtrr/
-obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o
quiet_cmd_mkcapflags = MKCAP $@
cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 0ed633c5048..6199232161c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -78,27 +78,20 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
static cpumask_var_t mce_inject_cpumask;
-static int mce_raise_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
int cpu = smp_processor_id();
struct mce *m = &__get_cpu_var(injectm);
- if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
- return NOTIFY_DONE;
+ if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
+ return NMI_DONE;
cpumask_clear_cpu(cpu, mce_inject_cpumask);
if (m->inject_flags & MCJ_EXCEPTION)
- raise_exception(m, args->regs);
+ raise_exception(m, regs);
else if (m->status)
raise_poll(m);
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
-static struct notifier_block mce_raise_nb = {
- .notifier_call = mce_raise_notify,
- .priority = NMI_LOCAL_NORMAL_PRIOR,
-};
-
/* Inject mce on current CPU */
static int raise_local(void)
{
@@ -216,7 +209,8 @@ static int inject_init(void)
return -ENOMEM;
printk(KERN_INFO "Machine check injector initialized\n");
mce_chrdev_ops.write = mce_write;
- register_die_notifier(&mce_raise_nb);
+ register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
+ "mce_notify");
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 08363b04212..fce51ad1f36 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -908,9 +908,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
percpu_inc(mce_exception_count);
- if (notify_die(DIE_NMI, "machine check", regs, error_code,
- 18, SIGKILL) == NOTIFY_STOP)
- goto out;
if (!banks)
goto out;
@@ -1140,6 +1137,15 @@ static void mce_start_timer(unsigned long data)
add_timer_on(t, smp_processor_id());
}
+/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+static void mce_timer_delete_all(void)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ del_timer_sync(&per_cpu(mce_timer, cpu));
+}
+
static void mce_do_trigger(struct work_struct *work)
{
call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
@@ -1750,7 +1756,6 @@ static struct syscore_ops mce_syscore_ops = {
static void mce_cpu_restart(void *data)
{
- del_timer_sync(&__get_cpu_var(mce_timer));
if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
@@ -1760,16 +1765,15 @@ static void mce_cpu_restart(void *data)
/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
+ mce_timer_delete_all();
on_each_cpu(mce_cpu_restart, NULL, 1);
}
/* Toggle features for corrected errors */
-static void mce_disable_ce(void *all)
+static void mce_disable_cmci(void *data)
{
if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
- if (all)
- del_timer_sync(&__get_cpu_var(mce_timer));
cmci_clear();
}
@@ -1852,7 +1856,8 @@ static ssize_t set_ignore_ce(struct sys_device *s,
if (mce_ignore_ce ^ !!new) {
if (new) {
/* disable ce features */
- on_each_cpu(mce_disable_ce, (void *)1, 1);
+ mce_timer_delete_all();
+ on_each_cpu(mce_disable_cmci, NULL, 1);
mce_ignore_ce = 1;
} else {
/* enable ce features */
@@ -1875,7 +1880,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s,
if (mce_cmci_disabled ^ !!new) {
if (new) {
/* disable cmci */
- on_each_cpu(mce_disable_ce, NULL, 1);
+ on_each_cpu(mce_disable_cmci, NULL, 1);
mce_cmci_disabled = 1;
} else {
/* enable cmci */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8ab89112f93..640891014b2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1058,76 +1058,15 @@ void perf_events_lapic_init(void)
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
-struct pmu_nmi_state {
- unsigned int marked;
- int handled;
-};
-
-static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
-
static int __kprobes
-perf_event_nmi_handler(struct notifier_block *self,
- unsigned long cmd, void *__args)
+perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
- struct die_args *args = __args;
- unsigned int this_nmi;
- int handled;
-
if (!atomic_read(&active_events))
- return NOTIFY_DONE;
-
- switch (cmd) {
- case DIE_NMI:
- break;
- case DIE_NMIUNKNOWN:
- this_nmi = percpu_read(irq_stat.__nmi_count);
- if (this_nmi != __this_cpu_read(pmu_nmi.marked))
- /* let the kernel handle the unknown nmi */
- return NOTIFY_DONE;
- /*
- * This one is a PMU back-to-back nmi. Two events
- * trigger 'simultaneously' raising two back-to-back
- * NMIs. If the first NMI handles both, the latter
- * will be empty and daze the CPU. So, we drop it to
- * avoid false-positive 'unknown nmi' messages.
- */
- return NOTIFY_STOP;
- default:
- return NOTIFY_DONE;
- }
-
- handled = x86_pmu.handle_irq(args->regs);
- if (!handled)
- return NOTIFY_DONE;
+ return NMI_DONE;
- this_nmi = percpu_read(irq_stat.__nmi_count);
- if ((handled > 1) ||
- /* the next nmi could be a back-to-back nmi */
- ((__this_cpu_read(pmu_nmi.marked) == this_nmi) &&
- (__this_cpu_read(pmu_nmi.handled) > 1))) {
- /*
- * We could have two subsequent back-to-back nmis: The
- * first handles more than one counter, the 2nd
- * handles only one counter and the 3rd handles no
- * counter.
- *
- * This is the 2nd nmi because the previous was
- * handling more than one counter. We will mark the
- * next (3rd) and then drop it if unhandled.
- */
- __this_cpu_write(pmu_nmi.marked, this_nmi + 1);
- __this_cpu_write(pmu_nmi.handled, handled);
- }
-
- return NOTIFY_STOP;
+ return x86_pmu.handle_irq(regs);
}
-static __read_mostly struct notifier_block perf_event_nmi_notifier = {
- .notifier_call = perf_event_nmi_handler,
- .next = NULL,
- .priority = NMI_LOCAL_LOW_PRIOR,
-};
-
struct event_constraint emptyconstraint;
struct event_constraint unconstrained;
@@ -1232,7 +1171,7 @@ static int __init init_hw_perf_events(void)
((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
perf_events_lapic_init();
- register_die_notifier(&perf_event_nmi_notifier);
+ register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
unconstrained = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fb330b0a816..b9698d40ac4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -131,6 +131,13 @@ struct cpu_hw_events {
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
/*
+ * Intel host/guest exclude bits
+ */
+ u64 intel_ctrl_guest_mask;
+ u64 intel_ctrl_host_mask;
+ struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
+
+ /*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
*/
@@ -295,6 +302,11 @@ struct x86_pmu {
*/
struct extra_reg *extra_regs;
unsigned int er_flags;
+
+ /*
+ * Intel host/guest support (KVM)
+ */
+ struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
};
#define ERF_NO_HT_SHARING 1
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 384450d6712..aeefd45697a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -138,6 +138,19 @@ static int amd_pmu_hw_config(struct perf_event *event)
if (ret)
return ret;
+ if (event->attr.exclude_host && event->attr.exclude_guest)
+ /*
+ * When HO == GO == 1 the hardware treats that as GO == HO == 0
+ * and will count in both modes. We don't want to count in that
+ * case so we emulate no-counting by setting US = OS = 0.
+ */
+ event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
+ ARCH_PERFMON_EVENTSEL_OS);
+ else if (event->attr.exclude_host)
+ event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY;
+ else if (event->attr.exclude_guest)
+ event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY;
+
if (event->attr.type != PERF_TYPE_RAW)
return 0;
@@ -398,7 +411,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.perfctr = MSR_K7_PERFCTR0,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = 4,
+ .num_counters = AMD64_NUM_COUNTERS,
.cntval_bits = 48,
.cntval_mask = (1ULL << 48) - 1,
.apic = 1,
@@ -562,7 +575,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
.perfctr = MSR_F15H_PERF_CTR,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = 6,
+ .num_counters = AMD64_NUM_COUNTERS_F15H,
.cntval_bits = 48,
.cntval_mask = (1ULL << 48) - 1,
.apic = 1,
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
new file mode 100644
index 00000000000..ab6343d2182
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -0,0 +1,294 @@
+/*
+ * Performance events - AMD IBS
+ *
+ * Copyright (C) 2011 Advanced Micro Devices, Inc., Robert Richter
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/perf_event.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <asm/apic.h>
+
+static u32 ibs_caps;
+
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
+
+static struct pmu perf_ibs;
+
+static int perf_ibs_init(struct perf_event *event)
+{
+ if (perf_ibs.type != event->attr.type)
+ return -ENOENT;
+ return 0;
+}
+
+static int perf_ibs_add(struct perf_event *event, int flags)
+{
+ return 0;
+}
+
+static void perf_ibs_del(struct perf_event *event, int flags)
+{
+}
+
+static struct pmu perf_ibs = {
+ .event_init= perf_ibs_init,
+ .add= perf_ibs_add,
+ .del= perf_ibs_del,
+};
+
+static __init int perf_event_ibs_init(void)
+{
+ if (!ibs_caps)
+ return -ENODEV; /* ibs not supported by the cpu */
+
+ perf_pmu_register(&perf_ibs, "ibs", -1);
+ printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
+
+ return 0;
+}
+
+#else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */
+
+static __init int perf_event_ibs_init(void) { return 0; }
+
+#endif
+
+/* IBS - apic initialization, for perf and oprofile */
+
+static __init u32 __get_ibs_caps(void)
+{
+ u32 caps;
+ unsigned int max_level;
+
+ if (!boot_cpu_has(X86_FEATURE_IBS))
+ return 0;
+
+ /* check IBS cpuid feature flags */
+ max_level = cpuid_eax(0x80000000);
+ if (max_level < IBS_CPUID_FEATURES)
+ return IBS_CAPS_DEFAULT;
+
+ caps = cpuid_eax(IBS_CPUID_FEATURES);
+ if (!(caps & IBS_CAPS_AVAIL))
+ /* cpuid flags not valid */
+ return IBS_CAPS_DEFAULT;
+
+ return caps;
+}
+
+u32 get_ibs_caps(void)
+{
+ return ibs_caps;
+}
+
+EXPORT_SYMBOL(get_ibs_caps);
+
+static inline int get_eilvt(int offset)
+{
+ return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int put_eilvt(int offset)
+{
+ return !setup_APIC_eilvt(offset, 0, 0, 1);
+}
+
+/*
+ * Check and reserve APIC extended interrupt LVT offset for IBS if available.
+ */
+static inline int ibs_eilvt_valid(void)
+{
+ int offset;
+ u64 val;
+ int valid = 0;
+
+ preempt_disable();
+
+ rdmsrl(MSR_AMD64_IBSCTL, val);
+ offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+ if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
+ pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
+ smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
+ goto out;
+ }
+
+ if (!get_eilvt(offset)) {
+ pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
+ smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
+ goto out;
+ }
+
+ valid = 1;
+out:
+ preempt_enable();
+
+ return valid;
+}
+
+static int setup_ibs_ctl(int ibs_eilvt_off)
+{
+ struct pci_dev *cpu_cfg;
+ int nodes;
+ u32 value = 0;
+
+ nodes = 0;
+ cpu_cfg = NULL;
+ do {
+ cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD,
+ PCI_DEVICE_ID_AMD_10H_NB_MISC,
+ cpu_cfg);
+ if (!cpu_cfg)
+ break;
+ ++nodes;
+ pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
+ | IBSCTL_LVT_OFFSET_VALID);
+ pci_read_config_dword(cpu_cfg, IBSCTL, &value);
+ if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
+ pci_dev_put(cpu_cfg);
+ printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
+ "IBSCTL = 0x%08x\n", value);
+ return -EINVAL;
+ }
+ } while (1);
+
+ if (!nodes) {
+ printk(KERN_DEBUG "No CPU node configured for IBS\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+/*
+ * This runs only on the current cpu. We try to find an LVT offset and
+ * setup the local APIC. For this we must disable preemption. On
+ * success we initialize all nodes with this offset. This updates then
+ * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
+ * the IBS interrupt vector is handled by perf_ibs_cpu_notifier that
+ * is using the new offset.
+ */
+static int force_ibs_eilvt_setup(void)
+{
+ int offset;
+ int ret;
+
+ preempt_disable();
+ /* find the next free available EILVT entry, skip offset 0 */
+ for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
+ if (get_eilvt(offset))
+ break;
+ }
+ preempt_enable();
+
+ if (offset == APIC_EILVT_NR_MAX) {
+ printk(KERN_DEBUG "No EILVT entry available\n");
+ return -EBUSY;
+ }
+
+ ret = setup_ibs_ctl(offset);
+ if (ret)
+ goto out;
+
+ if (!ibs_eilvt_valid()) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
+ pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
+ return 0;
+out:
+ preempt_disable();
+ put_eilvt(offset);
+ preempt_enable();
+ return ret;
+}
+
+static inline int get_ibs_lvt_offset(void)
+{
+ u64 val;
+
+ rdmsrl(MSR_AMD64_IBSCTL, val);
+ if (!(val & IBSCTL_LVT_OFFSET_VALID))
+ return -EINVAL;
+
+ return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void *dummy)
+{
+ int offset;
+
+ offset = get_ibs_lvt_offset();
+ if (offset < 0)
+ goto failed;
+
+ if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+ return;
+failed:
+ pr_warn("perf: IBS APIC setup failed on cpu #%d\n",
+ smp_processor_id());
+}
+
+static void clear_APIC_ibs(void *dummy)
+{
+ int offset;
+
+ offset = get_ibs_lvt_offset();
+ if (offset >= 0)
+ setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
+static int __cpuinit
+perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_STARTING:
+ setup_APIC_ibs(NULL);
+ break;
+ case CPU_DYING:
+ clear_APIC_ibs(NULL);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static __init int amd_ibs_init(void)
+{
+ u32 caps;
+ int ret;
+
+ caps = __get_ibs_caps();
+ if (!caps)
+ return -ENODEV; /* ibs not supported by the cpu */
+
+ if (!ibs_eilvt_valid()) {
+ ret = force_ibs_eilvt_setup();
+ if (ret) {
+ pr_err("Failed to setup IBS, %d\n", ret);
+ return ret;
+ }
+ }
+
+ get_online_cpus();
+ ibs_caps = caps;
+ /* make ibs_caps visible to other cpus: */
+ smp_mb();
+ perf_cpu_notifier(perf_ibs_cpu_notifier);
+ smp_call_function(setup_APIC_ibs, NULL, 1);
+ put_online_cpus();
+
+ return perf_event_ibs_init();
+}
+
+/* Since we need the pci subsystem to init ibs we can't do this earlier: */
+device_initcall(amd_ibs_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61fa35750b9..e09ca20e86e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -749,7 +749,8 @@ static void intel_pmu_enable_all(int added)
intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all();
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+ wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
+ x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
struct perf_event *event =
@@ -872,6 +873,7 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
@@ -879,6 +881,9 @@ static void intel_pmu_disable_event(struct perf_event *event)
return;
}
+ cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
+ cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
@@ -924,6 +929,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
static void intel_pmu_enable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -933,6 +939,11 @@ static void intel_pmu_enable_event(struct perf_event *event)
return;
}
+ if (event->attr.exclude_host)
+ cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
+ if (event->attr.exclude_guest)
+ cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc);
return;
@@ -1302,12 +1313,84 @@ static int intel_pmu_hw_config(struct perf_event *event)
return 0;
}
+struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+ if (x86_pmu.guest_get_msrs)
+ return x86_pmu.guest_get_msrs(nr);
+ *nr = 0;
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
+
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+
+ arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
+ arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
+ arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+
+ *nr = 1;
+ return arr;
+}
+
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+ int idx;
+
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ struct perf_event *event = cpuc->events[idx];
+
+ arr[idx].msr = x86_pmu_config_addr(idx);
+ arr[idx].host = arr[idx].guest = 0;
+
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ arr[idx].host = arr[idx].guest =
+ event->hw.config | ARCH_PERFMON_EVENTSEL_ENABLE;
+
+ if (event->attr.exclude_host)
+ arr[idx].host &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+ else if (event->attr.exclude_guest)
+ arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+ }
+
+ *nr = x86_pmu.num_counters;
+ return arr;
+}
+
+static void core_pmu_enable_event(struct perf_event *event)
+{
+ if (!event->attr.exclude_host)
+ x86_pmu_enable_event(event);
+}
+
+static void core_pmu_enable_all(int added)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ int idx;
+
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+
+ if (!test_bit(idx, cpuc->active_mask) ||
+ cpuc->events[idx]->attr.exclude_host)
+ continue;
+
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+ }
+}
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
.disable_all = x86_pmu_disable_all,
- .enable_all = x86_pmu_enable_all,
- .enable = x86_pmu_enable_event,
+ .enable_all = core_pmu_enable_all,
+ .enable = core_pmu_enable_event,
.disable = x86_pmu_disable_event,
.hw_config = x86_pmu_hw_config,
.schedule_events = x86_schedule_events,
@@ -1325,6 +1408,7 @@ static __initconst const struct x86_pmu core_pmu = {
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
.event_constraints = intel_core_event_constraints,
+ .guest_get_msrs = core_guest_get_msrs,
};
struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1431,6 +1515,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
+ .guest_get_msrs = intel_guest_get_msrs,
};
static void intel_clovertown_quirks(void)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 764c7c2b181..13ad89971d4 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -32,15 +32,12 @@ int in_crash_kexec;
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
-static void kdump_nmi_callback(int cpu, struct die_args *args)
+static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
{
- struct pt_regs *regs;
#ifdef CONFIG_X86_32
struct pt_regs fixed_regs;
#endif
- regs = args->regs;
-
#ifdef CONFIG_X86_32
if (!user_mode_vm(regs)) {
crash_fixup_ss_esp(&fixed_regs, regs);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 00354d4919a..faba5771aca 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -511,28 +511,37 @@ single_step_cont(struct pt_regs *regs, struct die_args *args)
static int was_in_debug_nmi[NR_CPUS];
-static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
- struct pt_regs *regs = args->regs;
-
switch (cmd) {
- case DIE_NMI:
+ case NMI_LOCAL:
if (atomic_read(&kgdb_active) != -1) {
/* KGDB CPU roundup */
kgdb_nmicallback(raw_smp_processor_id(), regs);
was_in_debug_nmi[raw_smp_processor_id()] = 1;
touch_nmi_watchdog();
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
- return NOTIFY_DONE;
+ break;
- case DIE_NMIUNKNOWN:
+ case NMI_UNKNOWN:
if (was_in_debug_nmi[raw_smp_processor_id()]) {
was_in_debug_nmi[raw_smp_processor_id()] = 0;
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
- return NOTIFY_DONE;
+ break;
+ default:
+ /* do nothing */
+ break;
+ }
+ return NMI_DONE;
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+ struct pt_regs *regs = args->regs;
+ switch (cmd) {
case DIE_DEBUG:
if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
if (user_mode(regs))
@@ -590,11 +599,6 @@ kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
static struct notifier_block kgdb_notifier = {
.notifier_call = kgdb_notify,
-
- /*
- * Lowest-prio notifier priority, we want to be notified last:
- */
- .priority = NMI_LOCAL_LOW_PRIOR,
};
/**
@@ -605,7 +609,31 @@ static struct notifier_block kgdb_notifier = {
*/
int kgdb_arch_init(void)
{
- return register_die_notifier(&kgdb_notifier);
+ int retval;
+
+ retval = register_die_notifier(&kgdb_notifier);
+ if (retval)
+ goto out;
+
+ retval = register_nmi_handler(NMI_LOCAL, kgdb_nmi_handler,
+ 0, "kgdb");
+ if (retval)
+ goto out1;
+
+ retval = register_nmi_handler(NMI_UNKNOWN, kgdb_nmi_handler,
+ 0, "kgdb");
+
+ if (retval)
+ goto out2;
+
+ return retval;
+
+out2:
+ unregister_nmi_handler(NMI_LOCAL, "kgdb");
+out1:
+ unregister_die_notifier(&kgdb_notifier);
+out:
+ return retval;
}
static void kgdb_hw_overflow_handler(struct perf_event *event,
@@ -673,6 +701,8 @@ void kgdb_arch_exit(void)
breakinfo[i].pev = NULL;
}
}
+ unregister_nmi_handler(NMI_UNKNOWN, "kgdb");
+ unregister_nmi_handler(NMI_LOCAL, "kgdb");
unregister_die_notifier(&kgdb_notifier);
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
new file mode 100644
index 00000000000..7ec5bd140b8
--- /dev/null
+++ b/arch/x86/kernel/nmi.c
@@ -0,0 +1,433 @@
+/*
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ * Copyright (C) 2011 Don Zickus Red Hat, Inc.
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * Handle hardware traps and faults.
+ */
+#include <linux/spinlock.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <linux/slab.h>
+
+#include <linux/mca.h>
+
+#if defined(CONFIG_EDAC)
+#include <linux/edac.h>
+#endif
+
+#include <linux/atomic.h>
+#include <asm/traps.h>
+#include <asm/mach_traps.h>
+#include <asm/nmi.h>
+
+#define NMI_MAX_NAMELEN 16
+struct nmiaction {
+ struct list_head list;
+ nmi_handler_t handler;
+ unsigned int flags;
+ char *name;
+};
+
+struct nmi_desc {
+ spinlock_t lock;
+ struct list_head head;
+};
+
+static struct nmi_desc nmi_desc[NMI_MAX] =
+{
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[0].head),
+ },
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[1].head),
+ },
+
+};
+
+struct nmi_stats {
+ unsigned int normal;
+ unsigned int unknown;
+ unsigned int external;
+ unsigned int swallow;
+};
+
+static DEFINE_PER_CPU(struct nmi_stats, nmi_stats);
+
+static int ignore_nmis;
+
+int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
+
+static int __init setup_unknown_nmi_panic(char *str)
+{
+ unknown_nmi_panic = 1;
+ return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
+#define nmi_to_desc(type) (&nmi_desc[type])
+
+static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+{
+ struct nmi_desc *desc = nmi_to_desc(type);
+ struct nmiaction *a;
+ int handled=0;
+
+ rcu_read_lock();
+
+ /*
+ * NMIs are edge-triggered, which means if you have enough
+ * of them concurrently, you can lose some because only one
+ * can be latched at any given time. Walk the whole list
+ * to handle those situations.
+ */
+ list_for_each_entry_rcu(a, &desc->head, list)
+ handled += a->handler(type, regs);
+
+ rcu_read_unlock();
+
+ /* return total number of NMI events handled */
+ return handled;
+}
+
+static int __setup_nmi(unsigned int type, struct nmiaction *action)
+{
+ struct nmi_desc *desc = nmi_to_desc(type);
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+
+ /*
+ * most handlers of type NMI_UNKNOWN never return because
+ * they just assume the NMI is theirs. Just a sanity check
+ * to manage expectations
+ */
+ WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
+
+ /*
+ * some handlers need to be executed first otherwise a fake
+ * event confuses some handlers (kdump uses this flag)
+ */
+ if (action->flags & NMI_FLAG_FIRST)
+ list_add_rcu(&action->list, &desc->head);
+ else
+ list_add_tail_rcu(&action->list, &desc->head);
+
+ spin_unlock_irqrestore(&desc->lock, flags);
+ return 0;
+}
+
+static struct nmiaction *__free_nmi(unsigned int type, const char *name)
+{
+ struct nmi_desc *desc = nmi_to_desc(type);
+ struct nmiaction *n;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+
+ list_for_each_entry_rcu(n, &desc->head, list) {
+ /*
+ * the name passed in to describe the nmi handler
+ * is used as the lookup key
+ */
+ if (!strcmp(n->name, name)) {
+ WARN(in_nmi(),
+ "Trying to free NMI (%s) from NMI context!\n", n->name);
+ list_del_rcu(&n->list);
+ break;
+ }
+ }
+
+ spin_unlock_irqrestore(&desc->lock, flags);
+ synchronize_rcu();
+ return (n);
+}
+
+int register_nmi_handler(unsigned int type, nmi_handler_t handler,
+ unsigned long nmiflags, const char *devname)
+{
+ struct nmiaction *action;
+ int retval = -ENOMEM;
+
+ if (!handler)
+ return -EINVAL;
+
+ action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
+ if (!action)
+ goto fail_action;
+
+ action->handler = handler;
+ action->flags = nmiflags;
+ action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
+ if (!action->name)
+ goto fail_action_name;
+
+ retval = __setup_nmi(type, action);
+
+ if (retval)
+ goto fail_setup_nmi;
+
+ return retval;
+
+fail_setup_nmi:
+ kfree(action->name);
+fail_action_name:
+ kfree(action);
+fail_action:
+
+ return retval;
+}
+EXPORT_SYMBOL_GPL(register_nmi_handler);
+
+void unregister_nmi_handler(unsigned int type, const char *name)
+{
+ struct nmiaction *a;
+
+ a = __free_nmi(type, name);
+ if (a) {
+ kfree(a->name);
+ kfree(a);
+ }
+}
+
+EXPORT_SYMBOL_GPL(unregister_nmi_handler);
+
+static notrace __kprobes void
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
+{
+ pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
+
+ /*
+ * On some machines, PCI SERR line is used to report memory
+ * errors. EDAC makes use of it.
+ */
+#if defined(CONFIG_EDAC)
+ if (edac_handler_set()) {
+ edac_atomic_assert_error();
+ return;
+ }
+#endif
+
+ if (panic_on_unrecovered_nmi)
+ panic("NMI: Not continuing");
+
+ pr_emerg("Dazed and confused, but trying to continue\n");
+
+ /* Clear and disable the PCI SERR error line. */
+ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+ outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+io_check_error(unsigned char reason, struct pt_regs *regs)
+{
+ unsigned long i;
+
+ pr_emerg(
+ "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
+ show_registers(regs);
+
+ if (panic_on_io_nmi)
+ panic("NMI IOCK error: Not continuing");
+
+ /* Re-enable the IOCK line, wait for a few seconds */
+ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+ outb(reason, NMI_REASON_PORT);
+
+ i = 20000;
+ while (--i) {
+ touch_nmi_watchdog();
+ udelay(100);
+ }
+
+ reason &= ~NMI_REASON_CLEAR_IOCHK;
+ outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
+{
+ int handled;
+
+ /*
+ * Use 'false' as back-to-back NMIs are dealt with one level up.
+ * Of course this makes having multiple 'unknown' handlers useless
+ * as only the first one is ever run (unless it can actually determine
+ * if it caused the NMI)
+ */
+ handled = nmi_handle(NMI_UNKNOWN, regs, false);
+ if (handled) {
+ __this_cpu_add(nmi_stats.unknown, handled);
+ return;
+ }
+
+ __this_cpu_add(nmi_stats.unknown, 1);
+
+#ifdef CONFIG_MCA
+ /*
+ * Might actually be able to figure out what the guilty party
+ * is:
+ */
+ if (MCA_bus) {
+ mca_handle_nmi();
+ return;
+ }
+#endif
+ pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
+
+ pr_emerg("Do you have a strange power saving mode enabled?\n");
+ if (unknown_nmi_panic || panic_on_unrecovered_nmi)
+ panic("NMI: Not continuing");
+
+ pr_emerg("Dazed and confused, but trying to continue\n");
+}
+
+static DEFINE_PER_CPU(bool, swallow_nmi);
+static DEFINE_PER_CPU(unsigned long, last_nmi_rip);
+
+static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+{
+ unsigned char reason = 0;
+ int handled;
+ bool b2b = false;
+
+ /*
+ * CPU-specific NMI must be processed before non-CPU-specific
+ * NMI, otherwise we may lose it, because the CPU-specific
+ * NMI can not be detected/processed on other CPUs.
+ */
+
+ /*
+ * Back-to-back NMIs are interesting because they can either
+ * be two NMI or more than two NMIs (any thing over two is dropped
+ * due to NMI being edge-triggered). If this is the second half
+ * of the back-to-back NMI, assume we dropped things and process
+ * more handlers. Otherwise reset the 'swallow' NMI behaviour
+ */
+ if (regs->ip == __this_cpu_read(last_nmi_rip))
+ b2b = true;
+ else
+ __this_cpu_write(swallow_nmi, false);
+
+ __this_cpu_write(last_nmi_rip, regs->ip);
+
+ handled = nmi_handle(NMI_LOCAL, regs, b2b);
+ __this_cpu_add(nmi_stats.normal, handled);
+ if (handled) {
+ /*
+ * There are cases when a NMI handler handles multiple
+ * events in the current NMI. One of these events may
+ * be queued for in the next NMI. Because the event is
+ * already handled, the next NMI will result in an unknown
+ * NMI. Instead lets flag this for a potential NMI to
+ * swallow.
+ */
+ if (handled > 1)
+ __this_cpu_write(swallow_nmi, true);
+ return;
+ }
+
+ /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+ raw_spin_lock(&nmi_reason_lock);
+ reason = get_nmi_reason();
+
+ if (reason & NMI_REASON_MASK) {
+ if (reason & NMI_REASON_SERR)
+ pci_serr_error(reason, regs);
+ else if (reason & NMI_REASON_IOCHK)
+ io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+ /*
+ * Reassert NMI in case it became active
+ * meanwhile as it's edge-triggered:
+ */
+ reassert_nmi();
+#endif
+ __this_cpu_add(nmi_stats.external, 1);
+ raw_spin_unlock(&nmi_reason_lock);
+ return;
+ }
+ raw_spin_unlock(&nmi_reason_lock);
+
+ /*
+ * Only one NMI can be latched at a time. To handle
+ * this we may process multiple nmi handlers at once to
+ * cover the case where an NMI is dropped. The downside
+ * to this approach is we may process an NMI prematurely,
+ * while its real NMI is sitting latched. This will cause
+ * an unknown NMI on the next run of the NMI processing.
+ *
+ * We tried to flag that condition above, by setting the
+ * swallow_nmi flag when we process more than one event.
+ * This condition is also only present on the second half
+ * of a back-to-back NMI, so we flag that condition too.
+ *
+ * If both are true, we assume we already processed this
+ * NMI previously and we swallow it. Otherwise we reset
+ * the logic.
+ *
+ * There are scenarios where we may accidentally swallow
+ * a 'real' unknown NMI. For example, while processing
+ * a perf NMI another perf NMI comes in along with a
+ * 'real' unknown NMI. These two NMIs get combined into
+ * one (as descibed above). When the next NMI gets
+ * processed, it will be flagged by perf as handled, but
+ * noone will know that there was a 'real' unknown NMI sent
+ * also. As a result it gets swallowed. Or if the first
+ * perf NMI returns two events handled then the second
+ * NMI will get eaten by the logic below, again losing a
+ * 'real' unknown NMI. But this is the best we can do
+ * for now.
+ */
+ if (b2b && __this_cpu_read(swallow_nmi))
+ __this_cpu_add(nmi_stats.swallow, 1);
+ else
+ unknown_nmi_error(reason, regs);
+}
+
+dotraplinkage notrace __kprobes void
+do_nmi(struct pt_regs *regs, long error_code)
+{
+ nmi_enter();
+
+ inc_irq_stat(__nmi_count);
+
+ if (!ignore_nmis)
+ default_do_nmi(regs);
+
+ nmi_exit();
+}
+
+void stop_nmi(void)
+{
+ ignore_nmis++;
+}
+
+void restart_nmi(void)
+{
+ ignore_nmis--;
+}
+
+/* reset the back-to-back NMI logic */
+void local_touch_nmi(void)
+{
+ __this_cpu_write(last_nmi_rip, 0);
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7a3b65107a2..46ff054ebaa 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -57,6 +57,7 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
+#include <asm/nmi.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -107,6 +108,7 @@ void cpu_idle(void)
if (cpu_is_offline(cpu))
play_dead();
+ local_touch_nmi();
local_irq_disable();
/* Don't trace irqs off for idle */
stop_critical_timings();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f693e44e1bf..3bd7e6eebf3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -51,6 +51,7 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
+#include <asm/nmi.h>
asmlinkage extern void ret_from_fork(void);
@@ -133,6 +134,7 @@ void cpu_idle(void)
* from here on, until they go to idle.
* Otherwise, idle callbacks can misfire.
*/
+ local_touch_nmi();
local_irq_disable();
enter_idle();
/* Don't trace irqs off for idle */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9242436e993..e334be1182b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,7 +464,7 @@ static inline void kb_wait(void)
}
}
-static void vmxoff_nmi(int cpu, struct die_args *args)
+static void vmxoff_nmi(int cpu, struct pt_regs *regs)
{
cpu_emergency_vmxoff();
}
@@ -736,14 +736,10 @@ static nmi_shootdown_cb shootdown_callback;
static atomic_t waiting_for_crash_ipi;
-static int crash_nmi_callback(struct notifier_block *self,
- unsigned long val, void *data)
+static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
{
int cpu;
- if (val != DIE_NMI)
- return NOTIFY_OK;
-
cpu = raw_smp_processor_id();
/* Don't do anything if this handler is invoked on crashing cpu.
@@ -751,10 +747,10 @@ static int crash_nmi_callback(struct notifier_block *self,
* an NMI if system was initially booted with nmi_watchdog parameter.
*/
if (cpu == crashing_cpu)
- return NOTIFY_STOP;
+ return NMI_HANDLED;
local_irq_disable();
- shootdown_callback(cpu, (struct die_args *)data);
+ shootdown_callback(cpu, regs);
atomic_dec(&waiting_for_crash_ipi);
/* Assume hlt works */
@@ -762,7 +758,7 @@ static int crash_nmi_callback(struct notifier_block *self,
for (;;)
cpu_relax();
- return 1;
+ return NMI_HANDLED;
}
static void smp_send_nmi_allbutself(void)
@@ -770,12 +766,6 @@ static void smp_send_nmi_allbutself(void)
apic->send_IPI_allbutself(NMI_VECTOR);
}
-static struct notifier_block crash_nmi_nb = {
- .notifier_call = crash_nmi_callback,
- /* we want to be the first one called */
- .priority = NMI_LOCAL_HIGH_PRIOR+1,
-};
-
/* Halt all other CPUs, calling the specified function on each of them
*
* This function can be used to halt all other CPUs on crash
@@ -794,7 +784,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
/* Would it be better to replace the trap vector here? */
- if (register_die_notifier(&crash_nmi_nb))
+ if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
+ NMI_FLAG_FIRST, "crash"))
return; /* return what? */
/* Ensure the new callback function is set before sending
* out the NMI
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 6913369c234..a8e3eb83466 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -81,15 +81,6 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, };
DECLARE_BITMAP(used_vectors, NR_VECTORS);
EXPORT_SYMBOL_GPL(used_vectors);
-static int ignore_nmis;
-
-int unknown_nmi_panic;
-/*
- * Prevent NMI reason port (0x61) being accessed simultaneously, can
- * only be used in NMI handler.
- */
-static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
-
static inline void conditional_sti(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
@@ -307,152 +298,6 @@ gp_in_kernel:
die("general protection fault", regs, error_code);
}
-static int __init setup_unknown_nmi_panic(char *str)
-{
- unknown_nmi_panic = 1;
- return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static notrace __kprobes void
-pci_serr_error(unsigned char reason, struct pt_regs *regs)
-{
- pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
- reason, smp_processor_id());
-
- /*
- * On some machines, PCI SERR line is used to report memory
- * errors. EDAC makes use of it.
- */
-#if defined(CONFIG_EDAC)
- if (edac_handler_set()) {
- edac_atomic_assert_error();
- return;
- }
-#endif
-
- if (panic_on_unrecovered_nmi)
- panic("NMI: Not continuing");
-
- pr_emerg("Dazed and confused, but trying to continue\n");
-
- /* Clear and disable the PCI SERR error line. */
- reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
- outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-io_check_error(unsigned char reason, struct pt_regs *regs)
-{
- unsigned long i;
-
- pr_emerg(
- "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
- reason, smp_processor_id());
- show_registers(regs);
-
- if (panic_on_io_nmi)
- panic("NMI IOCK error: Not continuing");
-
- /* Re-enable the IOCK line, wait for a few seconds */
- reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
- outb(reason, NMI_REASON_PORT);
-
- i = 20000;
- while (--i) {
- touch_nmi_watchdog();
- udelay(100);
- }
-
- reason &= ~NMI_REASON_CLEAR_IOCHK;
- outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
-{
- if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
- NOTIFY_STOP)
- return;
-#ifdef CONFIG_MCA
- /*
- * Might actually be able to figure out what the guilty party
- * is:
- */
- if (MCA_bus) {
- mca_handle_nmi();
- return;
- }
-#endif
- pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
- reason, smp_processor_id());
-
- pr_emerg("Do you have a strange power saving mode enabled?\n");
- if (unknown_nmi_panic || panic_on_unrecovered_nmi)
- panic("NMI: Not continuing");
-
- pr_emerg("Dazed and confused, but trying to continue\n");
-}
-
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
-{
- unsigned char reason = 0;
-
- /*
- * CPU-specific NMI must be processed before non-CPU-specific
- * NMI, otherwise we may lose it, because the CPU-specific
- * NMI can not be detected/processed on other CPUs.
- */
- if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
- return;
-
- /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
- raw_spin_lock(&nmi_reason_lock);
- reason = get_nmi_reason();
-
- if (reason & NMI_REASON_MASK) {
- if (reason & NMI_REASON_SERR)
- pci_serr_error(reason, regs);
- else if (reason & NMI_REASON_IOCHK)
- io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
- /*
- * Reassert NMI in case it became active
- * meanwhile as it's edge-triggered:
- */
- reassert_nmi();
-#endif
- raw_spin_unlock(&nmi_reason_lock);
- return;
- }
- raw_spin_unlock(&nmi_reason_lock);
-
- unknown_nmi_error(reason, regs);
-}
-
-dotraplinkage notrace __kprobes void
-do_nmi(struct pt_regs *regs, long error_code)
-{
- nmi_enter();
-
- inc_irq_stat(__nmi_count);
-
- if (!ignore_nmis)
- default_do_nmi(regs);
-
- nmi_exit();
-}
-
-void stop_nmi(void)
-{
- ignore_nmis++;
-}
-
-void restart_nmi(void)
-{
- ignore_nmis--;
-}
-
/* May run on IST stack. */
dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
{
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 68894fdc034..c04dc145a4b 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -61,26 +61,15 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
}
-static int profile_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
- int ret = NOTIFY_DONE;
-
- switch (val) {
- case DIE_NMI:
- if (ctr_running)
- model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
- else if (!nmi_enabled)
- break;
- else
- model->stop(&__get_cpu_var(cpu_msrs));
- ret = NOTIFY_STOP;
- break;
- default:
- break;
- }
- return ret;
+ if (ctr_running)
+ model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+ else if (!nmi_enabled)
+ return NMI_DONE;
+ else
+ model->stop(&__get_cpu_var(cpu_msrs));
+ return NMI_HANDLED;
}
static void nmi_cpu_save_registers(struct op_msrs *msrs)
@@ -363,12 +352,6 @@ static void nmi_cpu_setup(void *dummy)
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
-static struct notifier_block profile_exceptions_nb = {
- .notifier_call = profile_exceptions_notify,
- .next = NULL,
- .priority = NMI_LOCAL_LOW_PRIOR,
-};
-
static void nmi_cpu_restore_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
@@ -402,8 +385,6 @@ static void nmi_cpu_shutdown(void *dummy)
apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
apic_write(APIC_LVTERR, v);
nmi_cpu_restore_registers(msrs);
- if (model->cpu_down)
- model->cpu_down();
}
static void nmi_cpu_up(void *dummy)
@@ -508,7 +489,8 @@ static int nmi_setup(void)
ctr_running = 0;
/* make variables visible to the nmi handler: */
smp_mb();
- err = register_die_notifier(&profile_exceptions_nb);
+ err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify,
+ 0, "oprofile");
if (err)
goto fail;
@@ -538,7 +520,7 @@ static void nmi_shutdown(void)
put_online_cpus();
/* make variables visible to the nmi handler: */
smp_mb();
- unregister_die_notifier(&profile_exceptions_nb);
+ unregister_nmi_handler(NMI_LOCAL, "oprofile");
msrs = &get_cpu_var(cpu_msrs);
model->shutdown(msrs);
free_msrs();
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index 720bf5a53c5..7f8052cd662 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -18,32 +18,16 @@
#include <asm/apic.h>
#include <asm/ptrace.h>
-static int profile_timer_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int profile_timer_exceptions_notify(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
- int ret = NOTIFY_DONE;
-
- switch (val) {
- case DIE_NMI:
- oprofile_add_sample(args->regs, 0);
- ret = NOTIFY_STOP;
- break;
- default:
- break;
- }
- return ret;
+ oprofile_add_sample(regs, 0);
+ return NMI_HANDLED;
}
-static struct notifier_block profile_timer_exceptions_nb = {
- .notifier_call = profile_timer_exceptions_notify,
- .next = NULL,
- .priority = NMI_LOW_PRIOR,
-};
-
static int timer_start(void)
{
- if (register_die_notifier(&profile_timer_exceptions_nb))
+ if (register_nmi_handler(NMI_LOCAL, profile_timer_exceptions_notify,
+ 0, "oprofile-timer"))
return 1;
return 0;
}
@@ -51,7 +35,7 @@ static int timer_start(void)
static void timer_stop(void)
{
- unregister_die_notifier(&profile_timer_exceptions_nb);
+ unregister_nmi_handler(NMI_LOCAL, "oprofile-timer");
synchronize_sched(); /* Allow already-started NMIs to complete. */
}
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 9cbb710dc94..303f0863782 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -29,8 +29,6 @@
#include "op_x86_model.h"
#include "op_counter.h"
-#define NUM_COUNTERS 4
-#define NUM_COUNTERS_F15H 6
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
#define NUM_VIRT_COUNTERS 32
#else
@@ -70,62 +68,12 @@ static struct ibs_config ibs_config;
static struct ibs_state ibs_state;
/*
- * IBS cpuid feature detection
- */
-
-#define IBS_CPUID_FEATURES 0x8000001b
-
-/*
- * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
- * bit 0 is used to indicate the existence of IBS.
- */
-#define IBS_CAPS_AVAIL (1U<<0)
-#define IBS_CAPS_FETCHSAM (1U<<1)
-#define IBS_CAPS_OPSAM (1U<<2)
-#define IBS_CAPS_RDWROPCNT (1U<<3)
-#define IBS_CAPS_OPCNT (1U<<4)
-#define IBS_CAPS_BRNTRGT (1U<<5)
-#define IBS_CAPS_OPCNTEXT (1U<<6)
-
-#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
- | IBS_CAPS_FETCHSAM \
- | IBS_CAPS_OPSAM)
-
-/*
- * IBS APIC setup
- */
-#define IBSCTL 0x1cc
-#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
-#define IBSCTL_LVT_OFFSET_MASK 0x0F
-
-/*
* IBS randomization macros
*/
#define IBS_RANDOM_BITS 12
#define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1)
#define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5))
-static u32 get_ibs_caps(void)
-{
- u32 ibs_caps;
- unsigned int max_level;
-
- if (!boot_cpu_has(X86_FEATURE_IBS))
- return 0;
-
- /* check IBS cpuid feature flags */
- max_level = cpuid_eax(0x80000000);
- if (max_level < IBS_CPUID_FEATURES)
- return IBS_CAPS_DEFAULT;
-
- ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
- if (!(ibs_caps & IBS_CAPS_AVAIL))
- /* cpuid flags not valid */
- return IBS_CAPS_DEFAULT;
-
- return ibs_caps;
-}
-
/*
* 16-bit Linear Feedback Shift Register (LFSR)
*
@@ -316,81 +264,6 @@ static void op_amd_stop_ibs(void)
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
-static inline int get_eilvt(int offset)
-{
- return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
-}
-
-static inline int put_eilvt(int offset)
-{
- return !setup_APIC_eilvt(offset, 0, 0, 1);
-}
-
-static inline int ibs_eilvt_valid(void)
-{
- int offset;
- u64 val;
- int valid = 0;
-
- preempt_disable();
-
- rdmsrl(MSR_AMD64_IBSCTL, val);
- offset = val & IBSCTL_LVT_OFFSET_MASK;
-
- if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
- pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
- smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- goto out;
- }
-
- if (!get_eilvt(offset)) {
- pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
- smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- goto out;
- }
-
- valid = 1;
-out:
- preempt_enable();
-
- return valid;
-}
-
-static inline int get_ibs_offset(void)
-{
- u64 val;
-
- rdmsrl(MSR_AMD64_IBSCTL, val);
- if (!(val & IBSCTL_LVT_OFFSET_VALID))
- return -EINVAL;
-
- return val & IBSCTL_LVT_OFFSET_MASK;
-}
-
-static void setup_APIC_ibs(void)
-{
- int offset;
-
- offset = get_ibs_offset();
- if (offset < 0)
- goto failed;
-
- if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
- return;
-failed:
- pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
- smp_processor_id());
-}
-
-static void clear_APIC_ibs(void)
-{
- int offset;
-
- offset = get_ibs_offset();
- if (offset >= 0)
- setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
-}
-
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -439,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
goto fail;
}
/* both registers must be reserved */
- if (num_counters == NUM_COUNTERS_F15H) {
+ if (num_counters == AMD64_NUM_COUNTERS_F15H) {
msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
} else {
@@ -504,15 +377,6 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
val |= op_x86_get_ctrl(model, &counter_config[virt]);
wrmsrl(msrs->controls[i].addr, val);
}
-
- if (ibs_caps)
- setup_APIC_ibs();
-}
-
-static void op_amd_cpu_shutdown(void)
-{
- if (ibs_caps)
- clear_APIC_ibs();
}
static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -575,86 +439,6 @@ static void op_amd_stop(struct op_msrs const * const msrs)
op_amd_stop_ibs();
}
-static int setup_ibs_ctl(int ibs_eilvt_off)
-{
- struct pci_dev *cpu_cfg;
- int nodes;
- u32 value = 0;
-
- nodes = 0;
- cpu_cfg = NULL;
- do {
- cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD,
- PCI_DEVICE_ID_AMD_10H_NB_MISC,
- cpu_cfg);
- if (!cpu_cfg)
- break;
- ++nodes;
- pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
- | IBSCTL_LVT_OFFSET_VALID);
- pci_read_config_dword(cpu_cfg, IBSCTL, &value);
- if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
- pci_dev_put(cpu_cfg);
- printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
- "IBSCTL = 0x%08x\n", value);
- return -EINVAL;
- }
- } while (1);
-
- if (!nodes) {
- printk(KERN_DEBUG "No CPU node configured for IBS\n");
- return -ENODEV;
- }
-
- return 0;
-}
-
-/*
- * This runs only on the current cpu. We try to find an LVT offset and
- * setup the local APIC. For this we must disable preemption. On
- * success we initialize all nodes with this offset. This updates then
- * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
- * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
- * amd_cpu_shutdown() using the new offset.
- */
-static int force_ibs_eilvt_setup(void)
-{
- int offset;
- int ret;
-
- preempt_disable();
- /* find the next free available EILVT entry, skip offset 0 */
- for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
- if (get_eilvt(offset))
- break;
- }
- preempt_enable();
-
- if (offset == APIC_EILVT_NR_MAX) {
- printk(KERN_DEBUG "No EILVT entry available\n");
- return -EBUSY;
- }
-
- ret = setup_ibs_ctl(offset);
- if (ret)
- goto out;
-
- if (!ibs_eilvt_valid()) {
- ret = -EFAULT;
- goto out;
- }
-
- pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
- pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
-
- return 0;
-out:
- preempt_disable();
- put_eilvt(offset);
- preempt_enable();
- return ret;
-}
-
/*
* check and reserve APIC extended interrupt LVT offset for IBS if
* available
@@ -667,17 +451,6 @@ static void init_ibs(void)
if (!ibs_caps)
return;
- if (ibs_eilvt_valid())
- goto out;
-
- if (!force_ibs_eilvt_setup())
- goto out;
-
- /* Failed to setup ibs */
- ibs_caps = 0;
- return;
-
-out:
printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
}
@@ -741,9 +514,9 @@ static int op_amd_init(struct oprofile_operations *ops)
ops->create_files = setup_ibs_files;
if (boot_cpu_data.x86 == 0x15) {
- num_counters = NUM_COUNTERS_F15H;
+ num_counters = AMD64_NUM_COUNTERS_F15H;
} else {
- num_counters = NUM_COUNTERS;
+ num_counters = AMD64_NUM_COUNTERS;
}
op_amd_spec.num_counters = num_counters;
@@ -760,7 +533,6 @@ struct op_x86_model_spec op_amd_spec = {
.init = op_amd_init,
.fill_in_addresses = &op_amd_fill_in_addresses,
.setup_ctrs = &op_amd_setup_ctrs,
- .cpu_down = &op_amd_cpu_shutdown,
.check_ctrs = &op_amd_check_ctrs,
.start = &op_amd_start,
.stop = &op_amd_stop,
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 89017fa1fd6..71e8a67337e 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -43,7 +43,6 @@ struct op_x86_model_spec {
int (*fill_in_addresses)(struct op_msrs * const msrs);
void (*setup_ctrs)(struct op_x86_model_spec const *model,
struct op_msrs const * const msrs);
- void (*cpu_down)(void);
int (*check_ctrs)(struct pt_regs * const regs,
struct op_msrs const * const msrs);
void (*start)(struct op_msrs const * const msrs);
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0784f99a466..b8e08cb67a1 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -50,6 +50,7 @@
#include <acpi/hed.h>
#include <asm/mce.h>
#include <asm/tlbflush.h>
+#include <asm/nmi.h>
#include "apei-internal.h"
@@ -749,15 +750,11 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
}
}
-static int ghes_notify_nmi(struct notifier_block *this,
- unsigned long cmd, void *data)
+static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
{
struct ghes *ghes, *ghes_global = NULL;
int sev, sev_global = -1;
- int ret = NOTIFY_DONE;
-
- if (cmd != DIE_NMI)
- return ret;
+ int ret = NMI_DONE;
raw_spin_lock(&ghes_nmi_lock);
list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
@@ -770,10 +767,10 @@ static int ghes_notify_nmi(struct notifier_block *this,
sev_global = sev;
ghes_global = ghes;
}
- ret = NOTIFY_STOP;
+ ret = NMI_HANDLED;
}
- if (ret == NOTIFY_DONE)
+ if (ret == NMI_DONE)
goto out;
if (sev_global >= GHES_SEV_PANIC) {
@@ -825,10 +822,6 @@ static struct notifier_block ghes_notifier_sci = {
.notifier_call = ghes_notify_sci,
};
-static struct notifier_block ghes_notifier_nmi = {
- .notifier_call = ghes_notify_nmi,
-};
-
static unsigned long ghes_esource_prealloc_size(
const struct acpi_hest_generic *generic)
{
@@ -918,7 +911,8 @@ static int __devinit ghes_probe(struct platform_device *ghes_dev)
ghes_estatus_pool_expand(len);
mutex_lock(&ghes_list_mutex);
if (list_empty(&ghes_nmi))
- register_die_notifier(&ghes_notifier_nmi);
+ register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0,
+ "ghes");
list_add_rcu(&ghes->list, &ghes_nmi);
mutex_unlock(&ghes_list_mutex);
break;
@@ -964,7 +958,7 @@ static int __devexit ghes_remove(struct platform_device *ghes_dev)
mutex_lock(&ghes_list_mutex);
list_del_rcu(&ghes->list);
if (list_empty(&ghes_nmi))
- unregister_die_notifier(&ghes_notifier_nmi);
+ unregister_nmi_handler(NMI_LOCAL, "ghes");
mutex_unlock(&ghes_list_mutex);
/*
* To synchronize with NMI handler, ghes can only be
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 3302586655c..c2917ffad2c 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -65,6 +65,7 @@
* mechanism for it at that time.
*/
#include <asm/kdebug.h>
+#include <asm/nmi.h>
#define HAVE_DIE_NMI
#endif
@@ -1077,17 +1078,8 @@ static void ipmi_unregister_watchdog(int ipmi_intf)
#ifdef HAVE_DIE_NMI
static int
-ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
+ipmi_nmi(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = data;
-
- if (val != DIE_NMIUNKNOWN)
- return NOTIFY_OK;
-
- /* Hack, if it's a memory or I/O error, ignore it. */
- if (args->err & 0xc0)
- return NOTIFY_OK;
-
/*
* If we get here, it's an NMI that's not a memory or I/O
* error. We can't truly tell if it's from IPMI or not
@@ -1097,15 +1089,15 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
if (testing_nmi) {
testing_nmi = 2;
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
/* If we are not expecting a timeout, ignore it. */
if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
- return NOTIFY_OK;
+ return NMI_DONE;
if (preaction_val != WDOG_PRETIMEOUT_NMI)
- return NOTIFY_OK;
+ return NMI_DONE;
/*
* If no one else handled the NMI, we assume it was the IPMI
@@ -1120,12 +1112,8 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
panic(PFX "pre-timeout");
}
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
-
-static struct notifier_block ipmi_nmi_handler = {
- .notifier_call = ipmi_nmi
-};
#endif
static int wdog_reboot_handler(struct notifier_block *this,
@@ -1290,7 +1278,8 @@ static void check_parms(void)
}
}
if (do_nmi && !nmi_handler_registered) {
- rv = register_die_notifier(&ipmi_nmi_handler);
+ rv = register_nmi_handler(NMI_UNKNOWN, ipmi_nmi, 0,
+ "ipmi");
if (rv) {
printk(KERN_WARNING PFX
"Can't register nmi handler\n");
@@ -1298,7 +1287,7 @@ static void check_parms(void)
} else
nmi_handler_registered = 1;
} else if (!do_nmi && nmi_handler_registered) {
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
nmi_handler_registered = 0;
}
#endif
@@ -1336,7 +1325,7 @@ static int __init ipmi_wdog_init(void)
if (rv) {
#ifdef HAVE_DIE_NMI
if (nmi_handler_registered)
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
#endif
atomic_notifier_chain_unregister(&panic_notifier_list,
&wdog_panic_notifier);
@@ -1357,7 +1346,7 @@ static void __exit ipmi_wdog_exit(void)
#ifdef HAVE_DIE_NMI
if (nmi_handler_registered)
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
#endif
atomic_notifier_chain_unregister(&panic_notifier_list,
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 809cbda03d7..3774c9b8dac 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -35,6 +35,7 @@
#include <linux/notifier.h>
#include <asm/cacheflush.h>
#endif /* CONFIG_HPWDT_NMI_DECODING */
+#include <asm/nmi.h>
#define HPWDT_VERSION "1.3.0"
#define SECS_TO_TICKS(secs) ((secs) * 1000 / 128)
@@ -477,15 +478,11 @@ static int hpwdt_time_left(void)
/*
* NMI Handler
*/
-static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
- void *data)
+static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs)
{
unsigned long rom_pl;
static int die_nmi_called;
- if (ulReason != DIE_NMIUNKNOWN)
- goto out;
-
if (!hpwdt_nmi_decoding)
goto out;
@@ -508,7 +505,7 @@ static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
"Management Log for details.\n");
out:
- return NOTIFY_OK;
+ return NMI_DONE;
}
#endif /* CONFIG_HPWDT_NMI_DECODING */
@@ -648,13 +645,6 @@ static struct miscdevice hpwdt_miscdev = {
.fops = &hpwdt_fops,
};
-#ifdef CONFIG_HPWDT_NMI_DECODING
-static struct notifier_block die_notifier = {
- .notifier_call = hpwdt_pretimeout,
- .priority = 0,
-};
-#endif /* CONFIG_HPWDT_NMI_DECODING */
-
/*
* Init & Exit
*/
@@ -740,10 +730,9 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
* die notify list to handle a critical NMI. The default is to
* be last so other users of the NMI signal can function.
*/
- if (priority)
- die_notifier.priority = 0x7FFFFFFF;
-
- retval = register_die_notifier(&die_notifier);
+ retval = register_nmi_handler(NMI_UNKNOWN, hpwdt_pretimeout,
+ (priority) ? NMI_FLAG_FIRST : 0,
+ "hpwdt");
if (retval != 0) {
dev_warn(&dev->dev,
"Unable to register a die notifier (err=%d).\n",
@@ -763,7 +752,7 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
static void hpwdt_exit_nmi_decoding(void)
{
- unregister_die_notifier(&die_notifier);
+ unregister_nmi_handler(NMI_UNKNOWN, "hpwdt");
if (cru_rom_addr)
iounmap(cru_rom_addr);
}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c816075c01c..1e9ebe5e009 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -220,7 +220,10 @@ struct perf_event_attr {
mmap_data : 1, /* non-exec mmap data */
sample_id_all : 1, /* sample_type all events */
- __reserved_1 : 45;
+ exclude_host : 1, /* don't count in host */
+ exclude_guest : 1, /* don't count in guest */
+
+ __reserved_1 : 43;
union {
__u32 wakeup_events; /* wakeup every n events */