7 files changed, 108 insertions, 29 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e49a4fd718fe..0842b1127684 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,7 +29,7 @@ config X86
         select HAVE_FTRACE_MCOUNT_RECORD
         select HAVE_DYNAMIC_FTRACE
         select HAVE_FUNCTION_TRACER
-        select HAVE_FUNCTION_RET_TRACER if X86_32
+        select HAVE_FUNCTION_GRAPH_TRACER if X86_32
         select HAVE_FUNCTION_TRACE_MCOUNT_TEST
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 754a3e082f94..7e61b4ceb9a4 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -28,7 +28,7 @@ struct dyn_arch_ftrace {
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifndef __ASSEMBLY__
 
@@ -51,6 +51,6 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 #endif /* __ASSEMBLY__ */
-#endif /* CONFIG_FUNCTION_RET_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index af2bc36ca1c4..64939a0c3986 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -14,7 +14,7 @@ CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
-ifdef CONFIG_FUNCTION_RET_TRACER
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # Don't trace __switch_to() but let it for function tracer
 CFLAGS_REMOVE_process_32.o = -pg
 endif
@@ -70,7 +70,7 @@ obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
 obj-$(CONFIG_X86_IO_APIC)       += io_apic.o
 obj-$(CONFIG_X86_REBOOTFIXUPS)  += reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
-obj-$(CONFIG_FUNCTION_RET_TRACER)       += ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)     += ftrace.o
 obj-$(CONFIG_KEXEC)             += machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)             += relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)        += crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 8e48c5d4467d..88ea02dcb622 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,6 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
+#include <linux/ftrace.h>
 
 #include <linux/acpi.h>
 #include <acpi/processor.h>
@@ -391,6 +392,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
         unsigned int next_perf_state = 0; /* Index into perf table */
         unsigned int i;
         int result = 0;
+        struct power_trace it;
 
         dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
 
@@ -427,6 +429,8 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
                 }
         }
 
+        trace_power_mark(&it, POWER_PSTATE, next_perf_state);
+
         switch (data->cpu_feature) {
         case SYSTEM_INTEL_MSR_CAPABLE:
                 cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 74defe21ba42..958af86186c4 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1174,6 +1174,11 @@ ftrace_call:
         popl %edx
         popl %ecx
         popl %eax
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+        jmp ftrace_stub
+#endif
 
 .globl ftrace_stub
 ftrace_stub:
@@ -1188,9 +1193,9 @@ ENTRY(mcount)
 
         cmpl $ftrace_stub, ftrace_trace_function
         jnz trace
-#ifdef CONFIG_FUNCTION_RET_TRACER
-        cmpl $ftrace_stub, ftrace_function_return
-        jnz ftrace_return_caller
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        cmpl $ftrace_stub, ftrace_graph_return
+        jnz ftrace_graph_caller
 #endif
 .globl ftrace_stub
 ftrace_stub:
@@ -1215,8 +1220,8 @@ END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-ENTRY(ftrace_return_caller)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
         cmpl $0, function_trace_stop
         jne ftrace_stub
 
@@ -1230,7 +1235,7 @@ ENTRY(ftrace_return_caller)
         popl %ecx
         popl %eax
         ret
-END(ftrace_return_caller)
+END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index bb137f7297ed..7ef914e6a2f6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -111,7 +111,6 @@ static void ftrace_mod_code(void)
          */
         mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
                                              MCOUNT_INSN_SIZE);
-
 }
 
 void ftrace_nmi_enter(void)
@@ -323,9 +322,53 @@ int __init ftrace_dyn_arch_init(void *data)
 }
 #endif
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+static int ftrace_mod_jmp(unsigned long ip,
+                          int old_offset, int new_offset)
+{
+        unsigned char code[MCOUNT_INSN_SIZE];
+
+        if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+                return -EFAULT;
+
+        if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
+                return -EINVAL;
+
+        *(int *)(&code[1]) = new_offset;
+
+        if (do_ftrace_mod_code(ip, &code))
+                return -EPERM;
+
+        return 0;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+        unsigned long ip = (unsigned long)(&ftrace_graph_call);
+        int old_offset, new_offset;
+
+        old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
+        new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
+
+        return ftrace_mod_jmp(ip, old_offset, new_offset);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+        unsigned long ip = (unsigned long)(&ftrace_graph_call);
+        int old_offset, new_offset;
+
+        old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
+        new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
+
+        return ftrace_mod_jmp(ip, old_offset, new_offset);
+}
 
-#ifndef CONFIG_DYNAMIC_FTRACE
+#else /* CONFIG_DYNAMIC_FTRACE */
 
 /*
  * These functions are picked from those used on
@@ -343,11 +386,12 @@ void ftrace_nmi_exit(void)
 {
         atomic_dec(&in_nmi);
 }
+
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
 /* Add a function return address to the trace stack on thread info.*/
 static int push_return_trace(unsigned long ret, unsigned long long time,
-                                unsigned long func)
+                                unsigned long func, int *depth)
 {
         int index;
 
@@ -365,21 +409,22 @@ static int push_return_trace(unsigned long ret, unsigned long long time,
         current->ret_stack[index].ret = ret;
         current->ret_stack[index].func = func;
         current->ret_stack[index].calltime = time;
+        *depth = index;
 
         return 0;
 }
 
 /* Retrieve a function return address to the trace stack on thread info.*/
-static void pop_return_trace(unsigned long *ret, unsigned long long *time,
-                                unsigned long *func, unsigned long *overrun)
+static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 {
         int index;
 
         index = current->curr_ret_stack;
         *ret = current->ret_stack[index].ret;
-        *func = current->ret_stack[index].func;
-        *time = current->ret_stack[index].calltime;
-        *overrun = atomic_read(&current->trace_overrun);
+        trace->func = current->ret_stack[index].func;
+        trace->calltime = current->ret_stack[index].calltime;
+        trace->overrun = atomic_read(&current->trace_overrun);
+        trace->depth = index;
         current->curr_ret_stack--;
 }
 
@@ -389,13 +434,14 @@ static void pop_return_trace(unsigned long *ret, unsigned long long *time,
  */
 unsigned long ftrace_return_to_handler(void)
 {
-        struct ftrace_retfunc trace;
-        pop_return_trace(&trace.ret, &trace.calltime, &trace.func,
-                        &trace.overrun);
+        struct ftrace_graph_ret trace;
+        unsigned long ret;
+
+        pop_return_trace(&trace, &ret);
         trace.rettime = cpu_clock(raw_smp_processor_id());
-        ftrace_function_return(&trace);
+        ftrace_graph_return(&trace);
 
-        return trace.ret;
+        return ret;
 }
 
 /*
@@ -407,6 +453,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
         unsigned long old;
         unsigned long long calltime;
         int faulted;
+        struct ftrace_graph_ent trace;
         unsigned long return_hooker = (unsigned long)
                                 &return_to_handler;
 
@@ -440,20 +487,27 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
         );
 
         if (WARN_ON(faulted)) {
-                unregister_ftrace_return();
+                unregister_ftrace_graph();
                 return;
         }
 
         if (WARN_ON(!__kernel_text_address(old))) {
-                unregister_ftrace_return();
+                unregister_ftrace_graph();
                 *parent = old;
                 return;
         }
 
         calltime = cpu_clock(raw_smp_processor_id());
 
-        if (push_return_trace(old, calltime, self_addr) == -EBUSY)
+        if (push_return_trace(old, calltime,
+                                self_addr, &trace.depth) == -EBUSY) {
                 *parent = old;
+                return;
+        }
+
+        trace.func = self_addr;
+        ftrace_graph_entry(&trace);
+
 }
 
-#endif /* CONFIG_FUNCTION_RET_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c622772744d8..c27af49a4ede 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <linux/ftrace.h>
 #include <asm/system.h>
 
 unsigned long idle_halt;
@@ -100,6 +101,9 @@ static inline int hlt_use_halt(void)
 void default_idle(void)
 {
         if (hlt_use_halt()) {
+                struct power_trace it;
+
+                trace_power_start(&it, POWER_CSTATE, 1);
                 current_thread_info()->status &= ~TS_POLLING;
                 /*
                  * TS_POLLING-cleared state must be visible before we
@@ -112,6 +116,7 @@ void default_idle(void)
                 else
                         local_irq_enable();
                 current_thread_info()->status |= TS_POLLING;
+                trace_power_end(&it);
         } else {
                 local_irq_enable();
                 /* loop is done by the caller */
@@ -154,24 +159,31 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
  */
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
+        struct power_trace it;
+
+        trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
         if (!need_resched()) {
                 __monitor((void *)&current_thread_info()->flags, 0, 0);
                 smp_mb();
                 if (!need_resched())
                         __mwait(ax, cx);
         }
+        trace_power_end(&it);
 }
 
 /* Default MONITOR/MWAIT with no hints, used for default C1 state */
 static void mwait_idle(void)
 {
+        struct power_trace it;
         if (!need_resched()) {
+                trace_power_start(&it, POWER_CSTATE, 1);
                 __monitor((void *)&current_thread_info()->flags, 0, 0);
                 smp_mb();
                 if (!need_resched())
                         __sti_mwait(0, 0);
                 else
                         local_irq_enable();
+                trace_power_end(&it);
         } else
                 local_irq_enable();
 }
@@ -183,9 +195,13 @@ static void mwait_idle(void)
  */
 static void poll_idle(void)
 {
+        struct power_trace it;
+
+        trace_power_start(&it, POWER_CSTATE, 0);
         local_irq_enable();
         while (!need_resched())
                 cpu_relax();
+        trace_power_end(&it);
 }
 
 /*