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>

1 files changed, 70 insertions, 2 deletions

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index af290b8f124a..1377ecb29d8d 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -320,6 +320,19 @@ static inline void set_nmi_gate(int gate, void *addr)
 }
 #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
+
 static inline void _set_gate(int gate, unsigned type, void *addr,
 			     unsigned dpl, unsigned ist, unsigned seg)
 {
@@ -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.
  */
@@ -430,6 +471,31 @@ 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
@@ -442,6 +508,8 @@ static inline void load_current_idt(void)
 	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);