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>

4 files changed, 50 insertions, 28 deletions

diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 914e543102d..7b013aa8c43 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 d0dddc438c0..b7aa09235b5 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 0dfb88925ad..38f098c9c72 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:
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index 08a08ea5d69..898d477e47c 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -15,28 +15,13 @@
 #include <linux/mm.h>
 #include <linux/hardirq.h>
 #include <linux/kprobes.h>
+#include <linux/marker.h>
 #include <asm/io_trapped.h>
 #include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 #include <asm/kgdb.h>
 
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	int ret = 0;
-
-#ifdef CONFIG_KPROBES
-	if (!user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, trap))
-			ret = 1;
-		preempt_enable();
-	}
-#endif
-
-	return ret;
-}
-
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
@@ -261,6 +246,25 @@ do_sigbus:
 		goto no_context;
 }
 
+static inline int notify_page_fault(struct pt_regs *regs, int trap)
+{
+	int ret = 0;
+
+	trace_mark(kernel_arch_trap_entry, "trap_id %d ip #p%ld",
+		   trap >> 5, instruction_pointer(regs));
+
+#ifdef CONFIG_KPROBES
+	if (!user_mode(regs)) {
+		preempt_disable();
+		if (kprobe_running() && kprobe_fault_handler(regs, trap))
+			ret = 1;
+		preempt_enable();
+	}
+#endif
+
+	return ret;
+}
+
 #ifdef CONFIG_SH_STORE_QUEUES
 /*
  * This is a special case for the SH-4 store queues, as pages for this
@@ -284,15 +288,18 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs,
 	pmd_t *pmd;
 	pte_t *pte;
 	pte_t entry;
+	int ret = 0;
 
 	if (notify_page_fault(regs, lookup_exception_vector()))
-		return 0;
+		goto out;
 
 #ifdef CONFIG_SH_KGDB
 	if (kgdb_nofault && kgdb_bus_err_hook)
 		kgdb_bus_err_hook();
 #endif
 
+	ret = 1;
+
 	/*
 	 * We don't take page faults for P1, P2, and parts of P4, these
 	 * are always mapped, whether it be due to legacy behaviour in
@@ -302,24 +309,23 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs,
 		pgd = pgd_offset_k(address);
 	} else {
 		if (unlikely(address >= TASK_SIZE || !current->mm))
-			return 1;
+			goto out;
 
 		pgd = pgd_offset(current->mm, address);
 	}
 
 	pud = pud_offset(pgd, address);
 	if (pud_none_or_clear_bad(pud))
-		return 1;
+		goto out;
 	pmd = pmd_offset(pud, address);
 	if (pmd_none_or_clear_bad(pmd))
-		return 1;
-
+		goto out;
 	pte = pte_offset_kernel(pmd, address);
 	entry = *pte;
 	if (unlikely(pte_none(entry) || pte_not_present(entry)))
-		return 1;
+		goto out;
 	if (unlikely(writeaccess && !pte_write(entry)))
-		return 1;
+		goto out;
 
 	if (writeaccess)
 		entry = pte_mkdirty(entry);
@@ -336,5 +342,8 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs,
 	set_pte(pte, entry);
 	update_mmu_cache(NULL, address, entry);
 
-	return 0;
+	ret = 0;
+out:
+	trace_mark(kernel_arch_trap_exit, MARK_NOARGS);
+	return ret;
 }