sh: Trivial trace_mark() instrumentation for core events.

This implements a few trace points across events that are deemed
interesting. This implements a number of trace points:

	- The page fault handler / TLB miss
	- IPC calls
	- Kernel thread creation

The original LTTng patch had the slow-path instrumented, which
fails to account for the vast majority of events. In general
placing this in the fast-path is not a huge performance hit, as
we don't take page faults for kernel addresses.

The other bits of interest are some of the other trap handlers, as
well as the syscall entry/exit (which is better off being handled
through the tracehook API). Most of the other trap handlers are corner
cases where alternate means of notification exist, so there is little
value in placing extra trace points in these locations.

Based on top of the points provided both by the LTTng instrumentation
patch as well as the patch shipping in the ST-Linux tree, albeit in a
stripped down form.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>

3 files changed, 17 insertions, 4 deletions

diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 914e543102df..7b013aa8c43f 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -169,6 +169,7 @@ __asm__(".align 5\n"
 int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 {
         struct pt_regs regs;
+        int pid;
 
         memset(&regs, 0, sizeof(regs));
         regs.regs[4] = (unsigned long)arg;
@@ -178,8 +179,12 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
         regs.sr = (1 << 30);
 
         /* Ok, create the new process.. */
-        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
-                       &regs, 0, NULL, NULL);
+        pid = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
+                      &regs, 0, NULL, NULL);
+
+        trace_mark(kernel_arch_kthread_create, "pid %d fn %p", pid, fn);
+
+        return pid;
 }
 
 /*
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index d0dddc438c0c..b7aa09235b51 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -396,6 +396,7 @@ ATTRIB_NORET void kernel_thread_helper(void *arg, int (*fn)(void *))
 int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 {
         struct pt_regs regs;
+        int pid;
 
         memset(&regs, 0, sizeof(regs));
         regs.regs[2] = (unsigned long)arg;
@@ -404,8 +405,13 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
         regs.pc = (unsigned long)kernel_thread_helper;
         regs.sr = (1 << 30);
 
-        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
-                       &regs, 0, NULL, NULL);
+        /* Ok, create the new process.. */
+        pid = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
+                      &regs, 0, NULL, NULL);
+
+        trace_mark(kernel_arch_kthread_create, "pid %d fn %p", pid, fn);
+
+        return pid;
 }
 
 /*
diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c
index 0dfb88925add..38f098c9c72d 100644
--- a/arch/sh/kernel/sys_sh.c
+++ b/arch/sh/kernel/sys_sh.c
@@ -171,6 +171,8 @@ asmlinkage int sys_ipc(uint call, int first, int second,
         version = call >> 16; /* hack for backward compatibility */
         call &= 0xffff;
 
+        trace_mark(kernel_arch_ipc_call, "call %u first %d", call, first);
+
         if (call <= SEMTIMEDOP)
                 switch (call) {
                 case SEMOP: