[PATCH v14 3/3] trace,x86: Add irq vector tracepoints

From: Seiji Aguchi
Date: Thu Jun 06 2013 - 11:25:33 EST

[Purpose of this patch]

As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.

http://www.spinics.net/lists/mm-commits/msg85707.html

<snip>
The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled. They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.

There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers. Tracing such events gives
us the information about IRQ interaction with other system events.

The trace also tells where the system is spending its time. We want to
know which cores are handling interrupts and how they are affecting other
processes in the system. Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.
<snip>

On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.

I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.

[Patch Description]

Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.

This patch adds following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
- local_timer_vector
- reschedule_vector
- call_function_vector
- call_function_single_vector
- irq_work_entry_vector
- error_apic_vector
- thermal_apic_vector
- threshold_apic_vector
- spurious_apic_vector
- x86_platform_ipi_vector

It introduces a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
- Create non-trace and trace irq handlers with entering_irq()/exiting_irq().
- Create a new IDT, trace_idt_table, at boot time by adding a logic to
_set_gate(). It is just a copy of original idt table.
- Register the new handlers for tracpoints to the new IDT by introducing
macros to alloc_intr_gate() called at registering time of irq_vector handlers.
- When loading IDT in irq-vector trace on/off, NMI or debug on/off and cpu hotplug events,
load_current_idt(), which selects the IDT that we currently should be using, based on
the current state, is called.

Also, rename nmi_idt_descr, nmi_idt_table and debug_stack_use_ctr to debug_idt_descr,
debug_idt_table, and debug_idt_ctr to describe meaning of the variables precisely.

In addtion, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.

Signed-off-by: Seiji Aguchi <seiji.aguchi@xxxxxxx>
---
arch/x86/include/asm/desc.h | 119 ++++++++++++++++++++++++++++-
arch/x86/include/asm/entry_arch.h | 8 +-
arch/x86/include/asm/hw_irq.h | 17 ++++
arch/x86/include/asm/mshyperv.h | 1 +
arch/x86/include/asm/trace/irq_vectors.h | 104 ++++++++++++++++++++++++++
arch/x86/kernel/Makefile | 1 +
arch/x86/kernel/apic/Makefile | 1 +
arch/x86/kernel/apic/apic.c | 71 +++++++++++++++---
arch/x86/kernel/cpu/common.c | 18 ++--
arch/x86/kernel/cpu/mcheck/therm_throt.c | 24 +++++--
arch/x86/kernel/cpu/mcheck/threshold.c | 24 +++++--
arch/x86/kernel/entry_32.S | 12 +++-
arch/x86/kernel/entry_64.S | 31 ++++++--
arch/x86/kernel/head_64.S | 8 ++-
arch/x86/kernel/irq.c | 31 +++++---
arch/x86/kernel/irq_work.c | 24 ++++++-
arch/x86/kernel/smp.c | 65 ++++++++++++++--
arch/x86/kernel/tracepoint.c | 57 ++++++++++++++
arch/x86/kernel/traps.c | 2 +-
include/xen/events.h | 3 +
20 files changed, 550 insertions(+), 71 deletions(-)
create mode 100644 arch/x86/include/asm/trace/irq_vectors.h
create mode 100644 arch/x86/kernel/tracepoint.c

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 8bf1c06..df474f8 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -36,8 +36,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in

extern struct desc_ptr idt_descr;
extern gate_desc idt_table[];
-extern struct desc_ptr nmi_idt_descr;
-extern gate_desc nmi_idt_table[];
+extern struct desc_ptr debug_idt_descr;
+extern gate_desc debug_idt_table[];

struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
@@ -316,7 +316,20 @@ static inline void set_nmi_gate(int gate, void *addr)
gate_desc s;

pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS);
- write_idt_entry(nmi_idt_table, gate, &s);
+ write_idt_entry(debug_idt_table, gate, &s);
+}
+#endif
+
+#ifdef CONFIG_TRACING
+extern struct desc_ptr trace_idt_descr;
+extern gate_desc trace_idt_table[];
+static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
+{
+ write_idt_entry(trace_idt_table, entry, gate);
+}
+#else
+static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
+{
}
#endif

@@ -331,6 +344,7 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
* setup time
*/
write_idt_entry(idt_table, gate, &s);
+ write_trace_idt_entry(gate, &s);
}

/*
@@ -360,12 +374,39 @@ static inline void alloc_system_vector(int vector)
}
}

-static inline void alloc_intr_gate(unsigned int n, void *addr)
+#ifdef CONFIG_TRACING
+static inline void trace_set_intr_gate(unsigned int gate, void *addr)
+{
+ gate_desc s;
+
+ pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS);
+ write_idt_entry(trace_idt_table, gate, &s);
+}
+
+static inline void __trace_alloc_intr_gate(unsigned int n, void *addr)
+{
+ trace_set_intr_gate(n, addr);
+}
+#else
+static inline void trace_set_intr_gate(unsigned int gate, void *addr)
+{
+}
+
+#define __trace_alloc_intr_gate(n, addr)
+#endif
+
+static inline void __alloc_intr_gate(unsigned int n, void *addr)
{
- alloc_system_vector(n);
set_intr_gate(n, addr);
}

+#define alloc_intr_gate(n, addr) \
+ do { \
+ alloc_system_vector(n); \
+ __alloc_intr_gate(n, addr); \
+ __trace_alloc_intr_gate(n, trace_##addr); \
+ } while (0)
+
/*
* This routine sets up an interrupt gate at directory privilege level 3.
*/
@@ -405,4 +446,72 @@ static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
_set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
}

+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(u32, debug_idt_ctr);
+static inline bool is_debug_idt_enabled(void)
+{
+ if (this_cpu_read(debug_idt_ctr))
+ return true;
+
+ return false;
+}
+
+static inline void load_debug_idt(void)
+{
+ load_idt((const struct desc_ptr *)&debug_idt_descr);
+}
+#else
+static inline bool is_debug_idt_enabled(void)
+{
+ return false;
+}
+
+static inline void load_debug_idt(void)
+{
+}
+#endif
+
+#ifdef CONFIG_TRACING
+extern atomic_t trace_idt_ctr;
+static inline bool is_trace_idt_enabled(void)
+{
+ if (atomic_read(&trace_idt_ctr))
+ return true;
+
+ return false;
+}
+
+static inline void load_trace_idt(void)
+{
+ load_idt((const struct desc_ptr *)&trace_idt_descr);
+}
+#else
+static inline bool is_trace_idt_enabled(void)
+{
+ return false;
+}
+
+static inline void load_trace_idt(void)
+{
+}
+#endif
+
+/*
+ * the load_current_idt() is called with interrupt disabled by local_irq_save()
+ * to avoid races. That way the IDT will always be set back to the expected
+ * descriptor.
+ */
+static inline void load_current_idt(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (is_debug_idt_enabled())
+ load_debug_idt();
+ else if (is_trace_idt_enabled())
+ load_trace_idt();
+ else
+ load_idt((const struct desc_ptr *)&idt_descr);
+ local_irq_restore(flags);
+}
#endif /* _ASM_X86_DESC_H */
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 9bd4eca..dc5fa66 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -13,14 +13,16 @@
BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
-BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
-BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
+BUILD_INTERRUPT3(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR,
+ smp_irq_move_cleanup_interrupt)
+BUILD_INTERRUPT3(reboot_interrupt, REBOOT_VECTOR, smp_reboot_interrupt)
#endif

BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)

#ifdef CONFIG_HAVE_KVM
-BUILD_INTERRUPT(kvm_posted_intr_ipi, POSTED_INTR_VECTOR)
+BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
+ smp_kvm_posted_intr_ipi)
#endif

/*
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 1da97ef..e4ac559 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -77,6 +77,23 @@ extern void threshold_interrupt(void);
extern void call_function_interrupt(void);
extern void call_function_single_interrupt(void);

+#ifdef CONFIG_TRACING
+/* Interrupt handlers registered during init_IRQ */
+extern void trace_apic_timer_interrupt(void);
+extern void trace_x86_platform_ipi(void);
+extern void trace_error_interrupt(void);
+extern void trace_irq_work_interrupt(void);
+extern void trace_spurious_interrupt(void);
+extern void trace_thermal_interrupt(void);
+extern void trace_reschedule_interrupt(void);
+extern void trace_threshold_interrupt(void);
+extern void trace_call_function_interrupt(void);
+extern void trace_call_function_single_interrupt(void);
+#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt
+#define trace_reboot_interrupt reboot_interrupt
+#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#endif /* CONFIG_TRACING */
+
/* IOAPIC */
#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
extern unsigned long io_apic_irqs;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index c2934be..cc40e03 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -12,6 +12,7 @@ struct ms_hyperv_info {
extern struct ms_hyperv_info ms_hyperv;

void hyperv_callback_vector(void);
+#define trace_hyperv_callback_vector hyperv_callback_vector
void hyperv_vector_handler(struct pt_regs *regs);
void hv_register_vmbus_handler(int irq, irq_handler_t handler);

diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
new file mode 100644
index 0000000..2874df2
--- /dev/null
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -0,0 +1,104 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq_vectors
+
+#if !defined(_TRACE_IRQ_VECTORS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_VECTORS_H
+
+#include <linux/tracepoint.h>
+
+extern void trace_irq_vector_regfunc(void);
+extern void trace_irq_vector_unregfunc(void);
+
+DECLARE_EVENT_CLASS(x86_irq_vector,
+
+ TP_PROTO(int vector),
+
+ TP_ARGS(vector),
+
+ TP_STRUCT__entry(
+ __field( int, vector )
+ ),
+
+ TP_fast_assign(
+ __entry->vector = vector;
+ ),
+
+ TP_printk("vector=%d", __entry->vector) );
+
+#define DEFINE_IRQ_VECTOR_EVENT(name) \
+DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \
+ TP_PROTO(int vector), \
+ TP_ARGS(vector), \
+ trace_irq_vector_regfunc, \
+ trace_irq_vector_unregfunc); \
+DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \
+ TP_PROTO(int vector), \
+ TP_ARGS(vector), \
+ trace_irq_vector_regfunc, \
+ trace_irq_vector_unregfunc);
+
+
+/*
+ * local_timer - called when entering/exiting a local timer interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(local_timer);
+
+/*
+ * reschedule - called when entering/exiting a reschedule vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(reschedule);
+
+/*
+ * spurious_apic - called when entering/exiting a spurious apic vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(spurious_apic);
+
+/*
+ * error_apic - called when entering/exiting an error apic vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(error_apic);
+
+/*
+ * x86_platform_ipi - called when entering/exiting a x86 platform ipi interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi);
+
+/*
+ * irq_work - called when entering/exiting a irq work interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(irq_work);
+
+/*
+ * call_function - called when entering/exiting a call function interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(call_function);
+
+/*
+ * call_function_single - called when entering/exiting a call function
+ * single interrupt vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(call_function_single);
+
+/*
+ * threshold_apic - called when entering/exiting a threshold apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
+
+/*
+ * thermal_apic - called when entering/exiting a thermal apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(thermal_apic);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE irq_vectors
+#endif /* _TRACE_IRQ_VECTORS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7bd3bd3..74b3891 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -102,6 +102,7 @@ obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o

obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+obj-$(CONFIG_TRACING) += tracepoint.o

###
# 64 bit specific files
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 0ae0323..5274c3a 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,6 +2,7 @@
# Makefile for local APIC drivers and for the IO-APIC code
#

+CFLAGS_apic.o := -I$(src)/../../include/asm/trace
obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o
obj-y += hw_nmi.o

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 904611b..61ced40 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -55,6 +55,9 @@
#include <asm/tsc.h>
#include <asm/hypervisor.h>

+#define CREATE_TRACE_POINTS
+#include <asm/trace/irq_vectors.h>
+
unsigned int num_processors;

unsigned disabled_cpus __cpuinitdata;
@@ -919,17 +922,35 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
/*
* NOTE! We'd better ACK the irq immediately,
* because timer handling can be slow.
+ *
+ * update_process_times() expects us to have done irq_enter().
+ * Besides, if we don't timer interrupts ignore the global
+ * interrupt lock, which is the WrongThing (tm) to do.
*/
- ack_APIC_irq();
+ entering_ack_irq();
+ local_apic_timer_interrupt();
+ exiting_irq();
+
+ set_irq_regs(old_regs);
+}
+
+void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
/*
+ * NOTE! We'd better ACK the irq immediately,
+ * because timer handling can be slow.
+ *
* update_process_times() expects us to have done irq_enter().
* Besides, if we don't timer interrupts ignore the global
* interrupt lock, which is the WrongThing (tm) to do.
*/
- irq_enter();
- exit_idle();
+ entering_ack_irq();
+ trace_local_timer_entry(LOCAL_TIMER_VECTOR);
local_apic_timer_interrupt();
- irq_exit();
+ trace_local_timer_exit(LOCAL_TIMER_VECTOR);
+ exiting_irq();

set_irq_regs(old_regs);
}
@@ -1907,12 +1928,10 @@ int __init APIC_init_uniprocessor(void)
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
-void smp_spurious_interrupt(struct pt_regs *regs)
+static inline void __smp_spurious_interrupt(void)
{
u32 v;

- irq_enter();
- exit_idle();
/*
* Check if this really is a spurious interrupt and ACK it
* if it is a vectored one. Just in case...
@@ -1927,13 +1946,28 @@ void smp_spurious_interrupt(struct pt_regs *regs)
/* see sw-dev-man vol 3, chapter 7.4.13.5 */
pr_info("spurious APIC interrupt on CPU#%d, "
"should never happen.\n", smp_processor_id());
- irq_exit();
+}
+
+void smp_spurious_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ __smp_spurious_interrupt();
+ exiting_irq();
+}
+
+void smp_trace_spurious_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
+ __smp_spurious_interrupt();
+ trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR);
+ exiting_irq();
}

/*
* This interrupt should never happen with our APIC/SMP architecture
*/
-void smp_error_interrupt(struct pt_regs *regs)
+static inline void __smp_error_interrupt(struct pt_regs *regs)
{
u32 v0, v1;
u32 i = 0;
@@ -1948,8 +1982,6 @@ void smp_error_interrupt(struct pt_regs *regs)
"Illegal register address", /* APIC Error Bit 7 */
};

- irq_enter();
- exit_idle();
/* First tickle the hardware, only then report what went on. -- REW */
v0 = apic_read(APIC_ESR);
apic_write(APIC_ESR, 0);
@@ -1970,7 +2002,22 @@ void smp_error_interrupt(struct pt_regs *regs)

apic_printk(APIC_DEBUG, KERN_CONT "\n");

- irq_exit();
+}
+
+void smp_error_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ __smp_error_interrupt(regs);
+ exiting_irq();
+}
+
+void smp_trace_error_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ trace_error_apic_entry(ERROR_APIC_VECTOR);
+ __smp_error_interrupt(regs);
+ trace_error_apic_exit(ERROR_APIC_VECTOR);
+ exiting_irq();
}

/**
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 22018f7..e94823d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1071,8 +1071,8 @@ __setup("clearcpuid=", setup_disablecpuid);

#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
-struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1,
- (unsigned long) nmi_idt_table };
+struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
+ (unsigned long) debug_idt_table };

DEFINE_PER_CPU_FIRST(union irq_stack_union,
irq_stack_union) __aligned(PAGE_SIZE);
@@ -1148,20 +1148,20 @@ int is_debug_stack(unsigned long addr)
addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
}

-static DEFINE_PER_CPU(u32, debug_stack_use_ctr);
+DEFINE_PER_CPU(u32, debug_idt_ctr);

void debug_stack_set_zero(void)
{
- this_cpu_inc(debug_stack_use_ctr);
- load_idt((const struct desc_ptr *)&nmi_idt_descr);
+ this_cpu_inc(debug_idt_ctr);
+ load_current_idt();
}

void debug_stack_reset(void)
{
- if (WARN_ON(!this_cpu_read(debug_stack_use_ctr)))
+ if (WARN_ON(!this_cpu_read(debug_idt_ctr)))
return;
- if (this_cpu_dec_return(debug_stack_use_ctr) == 0)
- load_idt((const struct desc_ptr *)&idt_descr);
+ if (this_cpu_dec_return(debug_idt_ctr) == 0)
+ load_current_idt();
}

#else /* CONFIG_X86_64 */
@@ -1257,7 +1257,7 @@ void __cpuinit cpu_init(void)
switch_to_new_gdt(cpu);
loadsegment(fs, 0);

- load_idt((const struct desc_ptr *)&idt_descr);
+ load_current_idt();

memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
syscall_init();
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 47a1870..2f3a799 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -29,6 +29,7 @@
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>

/* How long to wait between reporting thermal events */
#define CHECK_INTERVAL (300 * HZ)
@@ -378,15 +379,26 @@ static void unexpected_thermal_interrupt(void)

static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;

-asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+static inline void __smp_thermal_interrupt(void)
{
- irq_enter();
- exit_idle();
inc_irq_stat(irq_thermal_count);
smp_thermal_vector();
- irq_exit();
- /* Ack only at the end to avoid potential reentry */
- ack_APIC_irq();
+}
+
+asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ __smp_thermal_interrupt();
+ exiting_ack_irq();
+}
+
+asmlinkage void smp_trace_thermal_interrupt(struct pt_regs *regs)
+{
+ entering_irq();
+ trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
+ __smp_thermal_interrupt();
+ trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
+ exiting_ack_irq();
}

/* Thermal monitoring depends on APIC, ACPI and clock modulation */
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index aa578ca..fe6b1c8 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -8,6 +8,7 @@
#include <asm/apic.h>
#include <asm/idle.h>
#include <asm/mce.h>
+#include <asm/trace/irq_vectors.h>

static void default_threshold_interrupt(void)
{
@@ -17,13 +18,24 @@ static void default_threshold_interrupt(void)

void (*mce_threshold_vector)(void) = default_threshold_interrupt;

-asmlinkage void smp_threshold_interrupt(void)
+static inline void __smp_threshold_interrupt(void)
{
- irq_enter();
- exit_idle();
inc_irq_stat(irq_threshold_count);
mce_threshold_vector();
- irq_exit();
- /* Ack only at the end to avoid potential reentry */
- ack_APIC_irq();
+}
+
+asmlinkage void smp_threshold_interrupt(void)
+{
+ entering_irq();
+ __smp_threshold_interrupt();
+ exiting_ack_irq();
+}
+
+asmlinkage void smp_trace_threshold_interrupt(void)
+{
+ entering_irq();
+ trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
+ __smp_threshold_interrupt();
+ trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
+ exiting_ack_irq();
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8f3e2de..2cfbc3a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -801,7 +801,17 @@ ENTRY(name) \
CFI_ENDPROC; \
ENDPROC(name)

-#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name)
+
+#ifdef CONFIG_TRACING
+#define TRACE_BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+#define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(name, nr, smp_##name); \
+ TRACE_BUILD_INTERRUPT(name, nr)

/* The include is where all of the SMP etc. interrupts come from */
#include <asm/entry_arch.h>
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7272089..11eef43 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1138,7 +1138,7 @@ END(common_interrupt)
/*
* APIC interrupts.
*/
-.macro apicinterrupt num sym do_sym
+.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
INTR_FRAME
ASM_CLAC
@@ -1150,15 +1150,32 @@ ENTRY(\sym)
END(\sym)
.endm

+#ifdef CONFIG_TRACING
+#define trace(sym) trace_##sym
+#define smp_trace(sym) smp_trace_##sym
+
+.macro trace_apicinterrupt num sym
+apicinterrupt3 \num trace(\sym) smp_trace(\sym)
+.endm
+#else
+.macro trace_apicinterrupt num sym do_sym
+.endm
+#endif
+
+.macro apicinterrupt num sym do_sym
+apicinterrupt3 \num \sym \do_sym
+trace_apicinterrupt \num \sym
+.endm
+
#ifdef CONFIG_SMP
-apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt REBOOT_VECTOR \
+apicinterrupt3 REBOOT_VECTOR \
reboot_interrupt smp_reboot_interrupt
#endif

#ifdef CONFIG_X86_UV
-apicinterrupt UV_BAU_MESSAGE \
+apicinterrupt3 UV_BAU_MESSAGE \
uv_bau_message_intr1 uv_bau_message_interrupt
#endif
apicinterrupt LOCAL_TIMER_VECTOR \
@@ -1167,7 +1184,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
x86_platform_ipi smp_x86_platform_ipi

#ifdef CONFIG_HAVE_KVM
-apicinterrupt POSTED_INTR_VECTOR \
+apicinterrupt3 POSTED_INTR_VECTOR \
kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
#endif

@@ -1451,13 +1468,13 @@ ENTRY(xen_failsafe_callback)
CFI_ENDPROC
END(xen_failsafe_callback)

-apicinterrupt HYPERVISOR_CALLBACK_VECTOR \
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
xen_hvm_callback_vector xen_evtchn_do_upcall

#endif /* CONFIG_XEN */

#if IS_ENABLED(CONFIG_HYPERV)
-apicinterrupt HYPERVISOR_CALLBACK_VECTOR \
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
hyperv_callback_vector hyperv_vector_handler
#endif /* CONFIG_HYPERV */

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 321d65e..5e4d8a8 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -518,9 +518,15 @@ ENTRY(idt_table)
.skip IDT_ENTRIES * 16

.align L1_CACHE_BYTES
-ENTRY(nmi_idt_table)
+ENTRY(debug_idt_table)
.skip IDT_ENTRIES * 16

+#ifdef CONFIG_TRACING
+ .align L1_CACHE_BYTES
+ENTRY(trace_idt_table)
+ .skip IDT_ENTRIES * 16
+#endif
+
__PAGE_ALIGNED_BSS
NEXT_PAGE(empty_zero_page)
.skip PAGE_SIZE
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index ac0631d..06af119 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -17,6 +17,7 @@
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
+#include <asm/trace/irq_vectors.h>

atomic_t irq_err_count;

@@ -204,23 +205,21 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
/*
* Handler for X86_PLATFORM_IPI_VECTOR.
*/
-void smp_x86_platform_ipi(struct pt_regs *regs)
+void __smp_x86_platform_ipi(void)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- ack_APIC_irq();
-
- irq_enter();
-
- exit_idle();
-
inc_irq_stat(x86_platform_ipis);

if (x86_platform_ipi_callback)
x86_platform_ipi_callback();
+}

- irq_exit();
+void smp_x86_platform_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);

+ entering_ack_irq();
+ __smp_x86_platform_ipi();
+ exiting_irq();
set_irq_regs(old_regs);
}

@@ -246,6 +245,18 @@ void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
}
#endif

+void smp_trace_x86_platform_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ entering_ack_irq();
+ trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
+ __smp_x86_platform_ipi();
+ trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
+ exiting_irq();
+ set_irq_regs(old_regs);
+}
+
EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);

#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index ca8f703..636a55e 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -8,14 +8,34 @@
#include <linux/irq_work.h>
#include <linux/hardirq.h>
#include <asm/apic.h>
+#include <asm/trace/irq_vectors.h>

-void smp_irq_work_interrupt(struct pt_regs *regs)
+static inline void irq_work_entering_irq(void)
{
irq_enter();
ack_APIC_irq();
+}
+
+static inline void __smp_irq_work_interrupt(void)
+{
inc_irq_stat(apic_irq_work_irqs);
irq_work_run();
- irq_exit();
+}
+
+void smp_irq_work_interrupt(struct pt_regs *regs)
+{
+ irq_work_entering_irq();
+ __smp_irq_work_interrupt();
+ exiting_irq();
+}
+
+void smp_trace_irq_work_interrupt(struct pt_regs *regs)
+{
+ irq_work_entering_irq();
+ trace_irq_work_entry(IRQ_WORK_VECTOR);
+ __smp_irq_work_interrupt();
+ trace_irq_work_exit(IRQ_WORK_VECTOR);
+ exiting_irq();
}

void arch_irq_work_raise(void)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 48d2b7d..f4fe0b8 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -30,6 +30,7 @@
#include <asm/proto.h>
#include <asm/apic.h>
#include <asm/nmi.h>
+#include <asm/trace/irq_vectors.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
*
@@ -249,32 +250,80 @@ finish:
/*
* Reschedule call back.
*/
-void smp_reschedule_interrupt(struct pt_regs *regs)
+static inline void __smp_reschedule_interrupt(void)
{
- ack_APIC_irq();
inc_irq_stat(irq_resched_count);
scheduler_ipi();
+}
+
+void smp_reschedule_interrupt(struct pt_regs *regs)
+{
+ ack_APIC_irq();
+ __smp_reschedule_interrupt();
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
}

-void smp_call_function_interrupt(struct pt_regs *regs)
+void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+{
+ ack_APIC_irq();
+ trace_reschedule_entry(RESCHEDULE_VECTOR);
+ __smp_reschedule_interrupt();
+ trace_reschedule_exit(RESCHEDULE_VECTOR);
+ /*
+ * KVM uses this interrupt to force a cpu out of guest mode
+ */
+}
+
+static inline void call_function_entering_irq(void)
{
ack_APIC_irq();
irq_enter();
+}
+
+static inline void __smp_call_function_interrupt(void)
+{
generic_smp_call_function_interrupt();
inc_irq_stat(irq_call_count);
- irq_exit();
}

-void smp_call_function_single_interrupt(struct pt_regs *regs)
+void smp_call_function_interrupt(struct pt_regs *regs)
+{
+ call_function_entering_irq();
+ __smp_call_function_interrupt();
+ exiting_irq();
+}
+
+void smp_trace_call_function_interrupt(struct pt_regs *regs)
+{
+ call_function_entering_irq();
+ trace_call_function_entry(CALL_FUNCTION_VECTOR);
+ __smp_call_function_interrupt();
+ trace_call_function_exit(CALL_FUNCTION_VECTOR);
+ exiting_irq();
+}
+
+static inline void __smp_call_function_single_interrupt(void)
{
- ack_APIC_irq();
- irq_enter();
generic_smp_call_function_single_interrupt();
inc_irq_stat(irq_call_count);
- irq_exit();
+}
+
+void smp_call_function_single_interrupt(struct pt_regs *regs)
+{
+ call_function_entering_irq();
+ __smp_call_function_single_interrupt();
+ exiting_irq();
+}
+
+void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+{
+ call_function_entering_irq();
+ trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
+ __smp_call_function_single_interrupt();
+ trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
+ exiting_irq();
}

static int __init nonmi_ipi_setup(char *str)
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
new file mode 100644
index 0000000..1423efe
--- /dev/null
+++ b/arch/x86/kernel/tracepoint.c
@@ -0,0 +1,57 @@
+/*
+ * Code for supporting irq vector tracepoints.
+ *
+ * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@xxxxxxx>
+ *
+ */
+#include <asm/hw_irq.h>
+#include <asm/desc.h>
+#include <linux/atomic.h>
+
+atomic_t trace_idt_ctr = ATOMIC_INIT(0);
+struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1,
+ (unsigned long) trace_idt_table };
+
+#ifndef CONFIG_X86_64
+gate_desc trace_idt_table[NR_VECTORS] __page_aligned_data
+ = { { { { 0, 0 } } }, };
+#endif
+
+static int trace_irq_vector_refcount;
+static DEFINE_MUTEX(irq_vector_mutex);
+
+static void set_trace_idt_ctr(int val)
+{
+ atomic_set(&trace_idt_ctr, val);
+ /* Ensure the trace_idt_ctr is set before sending IPI */
+ wmb();
+}
+
+static void switch_idt(void *arg)
+{
+ load_current_idt();
+}
+
+void trace_irq_vector_regfunc(void)
+{
+ mutex_lock(&irq_vector_mutex);
+ if (!trace_irq_vector_refcount) {
+ set_trace_idt_ctr(1);
+ smp_call_function(switch_idt, NULL, 0);
+ switch_idt(NULL);
+ }
+ trace_irq_vector_refcount++;
+ mutex_unlock(&irq_vector_mutex);
+}
+
+void trace_irq_vector_unregfunc(void)
+{
+ mutex_lock(&irq_vector_mutex);
+ trace_irq_vector_refcount--;
+ if (!trace_irq_vector_refcount) {
+ set_trace_idt_ctr(0);
+ smp_call_function(switch_idt, NULL, 0);
+ switch_idt(NULL);
+ }
+ mutex_unlock(&irq_vector_mutex);
+}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 772e2a8..d27182d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -785,7 +785,7 @@ void __init trap_init(void)
x86_init.irqs.trap_init();

#ifdef CONFIG_X86_64
- memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
+ memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16);
set_nmi_gate(X86_TRAP_DB, &debug);
set_nmi_gate(X86_TRAP_BP, &int3);
#endif
diff --git a/include/xen/events.h b/include/xen/events.h
index b2b27c6..c9ea10e 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -76,6 +76,9 @@ unsigned irq_from_evtchn(unsigned int evtchn);

/* Xen HVM evtchn vector callback */
void xen_hvm_callback_vector(void);
+#ifdef CONFIG_TRACING
+#define trace_xen_hvm_callback_vector xen_hvm_callback_vector
+#endif
extern int xen_have_vector_callback;
int xen_set_callback_via(uint64_t via);
void xen_evtchn_do_upcall(struct pt_regs *regs);
--
1.7.1


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/