From 830fafecc211bef5bc6e253ab7e39c9e7560f758 Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Thu, 5 Nov 2009 16:20:09 +0900
Subject: [PATCH] sh: perf events: Preliminary callchain support.

This implements preliminary support for perf callchains (at the moment
only the kernel side is implemented). The actual implementation itself is
just a simple wrapper around the unwinder API, which allows for callchain
generation with or without the dwarf unwinder.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 arch/sh/kernel/Makefile         |  2 +-
 arch/sh/kernel/perf_callchain.c | 98 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+), 1 deletion(-)
 create mode 100644 arch/sh/kernel/perf_callchain.c

diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index 0a67baf..8edb927 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
-obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= localtimer.o
 
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
new file mode 100644
index 0000000..24ea837
--- /dev/null
+++ b/arch/sh/kernel/perf_callchain.c
@@ -0,0 +1,98 @@
+/*
+ * Performance event callchain support - SuperH architecture code
+ *
+ * Copyright (C) 2009  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <asm/unwinder.h>
+#include <asm/ptrace.h>
+
+static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
+
+static void callchain_warning(void *data, char *msg)
+{
+}
+
+static void
+callchain_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+}
+
+static int callchain_stack(void *data, char *name)
+{
+	return 0;
+}
+
+static void callchain_address(void *data, unsigned long addr, int reliable)
+{
+	struct perf_callchain_entry *entry = data;
+
+	if (reliable)
+		callchain_store(entry, addr);
+}
+
+static const struct stacktrace_ops callchain_ops = {
+	.warning	= callchain_warning,
+	.warning_symbol	= callchain_warning_symbol,
+	.stack		= callchain_stack,
+	.address	= callchain_address,
+};
+
+static void
+perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	callchain_store(entry, regs->pc);
+
+	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
+}
+
+static void
+perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+	int is_user;
+
+	if (!regs)
+		return;
+
+	is_user = user_mode(regs);
+
+	if (!current || current->pid == 0)
+		return;
+
+	if (is_user && current->state != TASK_RUNNING)
+		return;
+
+	/*
+	 * Only the kernel side is implemented for now.
+	 */
+	if (!is_user)
+		perf_callchain_kernel(regs, entry);
+}
+
+/*
+ * No need for separate IRQ and NMI entries.
+ */
+static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+
+	entry->nr = 0;
+
+	perf_do_callchain(regs, entry);
+
+	return entry;
+}
-- 
2.7.4