[PATCH v4 4/4] Add page fault tracepoints

[Seiji Aguchi <seiji.aguchi@hds.com>]

This patch introduces page fault tracepoints to x86 architecture
by switching IDT.

  Two events, for user and kernel spaces, are introduced at the beginning
  of page fault handler for tracing.

  - User space event
    There is a request of page fault event for user space as below.

    https://lkml.kernel.org/r/1368079520-11015-2-git-send-email-fdeslaur+()+gmail+!+com
    https://lkml.kernel.org/r/1368079520-11015-1-git-send-email-fdeslaur+()+gmail+!+com

  - Kernel space event:
    When we meature an overhead in kernel space for investigating performance
    issues, we can check if it comes from the page fault events.

Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
---
 arch/x86/include/asm/trace/exceptions.h | 52 +++++++++++++++++++++++++++++++++
 arch/x86/mm/Makefile                    |  2 ++
 arch/x86/mm/fault.c                     | 13 +++++++++
 3 files changed, 67 insertions(+)
 create mode 100644 arch/x86/include/asm/trace/exceptions.h

diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
new file mode 100644
index 0000000..86540c0
--- /dev/null
+++ b/arch/x86/include/asm/trace/exceptions.h
@@ -0,0 +1,52 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM exceptions
+
+#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PAGE_FAULT_H
+
+#include <linux/tracepoint.h>
+
+extern void trace_irq_vector_regfunc(void);
+extern void trace_irq_vector_unregfunc(void);
+
+DECLARE_EVENT_CLASS(x86_exceptions,
+
+	TP_PROTO(unsigned long address, struct pt_regs *regs,
+		 unsigned long error_code),
+
+	TP_ARGS(address, regs, error_code),
+
+	TP_STRUCT__entry(
+		__field(		unsigned long, address	)
+		__field(		unsigned long, ip	)
+		__field(		unsigned long, error_code )
+	),
+
+	TP_fast_assign(
+		__entry->address = address;
+		__entry->ip = regs->ip;
+		__entry->error_code = error_code;
+	),
+
+	TP_printk("address=%pf ip=%pf error_code=0x%lx",
+		  (void *)__entry->address, (void *)__entry->ip,
+		  __entry->error_code) );
+
+#define DEFINE_PAGE_FAULT_EVENT(name)				\
+DEFINE_EVENT_FN(x86_exceptions, name,				\
+	TP_PROTO(unsigned long address,	struct pt_regs *regs,	\
+		 unsigned long error_code),			\
+	TP_ARGS(address, regs, error_code),			\
+	trace_irq_vector_regfunc,				\
+	trace_irq_vector_unregfunc);
+
+DEFINE_PAGE_FAULT_EVENT(user_page_fault);
+DEFINE_PAGE_FAULT_EVENT(kernel_page_fault);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE exceptions
+#endif /*  _TRACE_PAGE_FAULT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 23d8e5f..6a19ad9 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -6,6 +6,8 @@ nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_physaddr.o		:= $(nostackp)
 CFLAGS_setup_nx.o		:= $(nostackp)
 
+CFLAGS_fault.o := -I$(src)/../include/asm/trace
+
 obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
 obj-$(CONFIG_SMP)		+= tlb.o
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fd3e281..f2730cbc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,9 @@
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
 
+#define CREATE_TRACE_POINTS
+#include <asm/trace/exceptions.h>
+
 /*
  * Page fault error code bits:
  *
@@ -1232,12 +1235,22 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	exception_exit(prev_state);
 }
 
+static void trace_page_fault_entries(struct pt_regs *regs,
+				     unsigned long error_code)
+{
+	if (user_mode(regs))
+		trace_user_page_fault(read_cr2(), regs, error_code);
+	else
+		trace_kernel_page_fault(read_cr2(), regs, error_code);
+}
+
 dotraplinkage void __kprobes
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	trace_page_fault_entries(regs, error_code);
 	__do_page_fault(regs, error_code);
 	exception_exit(prev_state);
 }
-- 
1.8.3.1