x86, trace: Add irq vector tracepoints

[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.

So, add 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

Also, introduce 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 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.
 - Add checking, whether irq vector tracing is on/off, into load_current_idt().
   This has to be done below debug checking for these reasons.
   - Switching to debug IDT may be kicked while tracing is enabled.
   - On the other hands, switching to trace IDT is kicked only when debugging
     is disabled.

In addition, 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@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

13 files changed, 217 insertions, 10 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7bd3bd310106..74b3891afb9b 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 0ae0323b1f9c..5274c3a07e75 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 59ee76fe1c53..61ced40e9c2c 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;
@@ -931,6 +934,27 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
 	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.
+	 */
+	entering_ack_irq();
+	trace_local_timer_entry(LOCAL_TIMER_VECTOR);
+	local_apic_timer_interrupt();
+	trace_local_timer_exit(LOCAL_TIMER_VECTOR);
+	exiting_irq();
+
+	set_irq_regs(old_regs);
+}
+
 int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
@@ -1931,6 +1955,15 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 	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
  */
@@ -1978,6 +2011,15 @@ void smp_error_interrupt(struct pt_regs *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();
+}
+
 /**
  * connect_bsp_APIC - attach the APIC to the interrupt system
  */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8f6a0f909d6f..d9c8c0947ec2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -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();
@@ -1334,7 +1334,7 @@ void __cpuinit cpu_init(void)
 	if (cpu_has_vme || cpu_has_tsc || cpu_has_de)
 		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
-	load_idt(&idt_descr);
+	load_current_idt();
 	switch_to_new_gdt(cpu);
 
 	/*
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index f6b35f2a6a37..2f3a7995e56a 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)
@@ -391,6 +392,15 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 	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 */
 static int intel_thermal_supported(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index 610cd98d6ef9..fe6b1c86645b 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)
 {
@@ -29,3 +30,12 @@ asmlinkage void smp_threshold_interrupt(void)
 	__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 8f3e2dec1df3..2cfbc3a3a2dd 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 727208941030..11eef43f971f 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 84fb779d5b74..5e4d8a8a5c40 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -521,6 +521,12 @@ ENTRY(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 e3b8df1754cc..06af119743a6 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;
 
@@ -244,6 +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 074d46fdbd1f..636a55e4a13c 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -8,6 +8,7 @@
 #include <linux/irq_work.h>
 #include <linux/hardirq.h>
 #include <asm/apic.h>
+#include <asm/trace/irq_vectors.h>
 
 static inline void irq_work_entering_irq(void)
 {
@@ -28,6 +29,15 @@ void smp_irq_work_interrupt(struct pt_regs *regs)
 	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)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d85837574a79..f4fe0b8879e0 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:
  *
@@ -264,6 +265,17 @@ void smp_reschedule_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();
@@ -283,6 +295,15 @@ void smp_call_function_interrupt(struct pt_regs *regs)
 	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)
 {
 	generic_smp_call_function_single_interrupt();
@@ -296,6 +317,15 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 	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)
 {
 	smp_no_nmi_ipi = true;
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
new file mode 100644
index 000000000000..1423efe98fbc
--- /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@hds.com>
+ *
+ */
+#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);
+}