This patch add support for perf callchain sampling on riscv platform.
The return address of leaf function is retrieved from pt_regs as
it is not saved in the outmost frame.
Signed-off-by: Mao Han <han_...@c-sky.com>
CC: Palmer Dabbelt <pal...@sifive.com>
CC: linux-riscv<linux-ri...@lists.infradead.org>
CC: Christoph Hellwig <h...@lst.de>
CC: Guo Ren <guo...@kernel.org>
---
arch/riscv/kernel/Makefile | 3 +-
arch/riscv/kernel/perf_callchain.c | 113 +++++++++++++++++++++++++++++++++++++
2 files changed, 115 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/kernel/perf_callchain.c
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 5985681..dd2ba44 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o
obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o
-obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o
clean:
diff --git a/arch/riscv/kernel/perf_callchain.c
b/arch/riscv/kernel/perf_callchain.c
new file mode 100644
index 0000000..88ea3b4
--- /dev/null
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+/* Kernel callchain */
+struct stackframe {
+ unsigned long fp;
+ unsigned long ra;
+};
+
+static int unwind_frame_kernel(struct stackframe *frame)
+{
+ if (kstack_end((void *)frame->fp))
+ return -EPERM;
+ if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
+ return -EPERM;
+
+ *frame = *((struct stackframe *)frame->fp - 1);
+ if (__kernel_text_address(frame->ra)) {
+ int graph = 0;
+
+ frame->ra = ftrace_graph_ret_addr(NULL, &graph, frame->ra,
+ NULL);
+ }
+ return 0;
+}
+
+static void notrace walk_stackframe(struct stackframe *fr,
+ struct perf_callchain_entry_ctx *entry)
+{
+ do {
+ perf_callchain_store(entry, fr->ra);
+ } while (unwind_frame_kernel(fr) >= 0);
+}
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
+ unsigned long fp, unsigned long reg_ra)
+{
+ struct stackframe buftail;
+ unsigned long ra = 0;
+ unsigned long *user_frame_tail =
+ (unsigned long *)(fp - sizeof(struct stackframe));
+
+ /* Check accessibility of one struct frame_tail beyond */
+ if (!access_ok(user_frame_tail, sizeof(buftail)))
+ return 0;
+ if (__copy_from_user_inatomic(&buftail, user_frame_tail,
+ sizeof(buftail)))
+ return 0;
+
+ if (reg_ra != 0)
+ ra = reg_ra;
+ else
+ ra = buftail.ra;
+
+ fp = buftail.fp;
+ perf_callchain_store(entry, ra);
+
+ return fp;
+}
+
+/*
+ * This will be called when the target is in user mode
+ * This function will only be called when we use
+ * "PERF_SAMPLE_CALLCHAIN" in
+ * kernel/events/core.c:perf_prepare_sample()
+ *
+ * How to trigger perf_callchain_[user/kernel] :
+ * $ perf record -e cpu-clock --call-graph fp ./program
+ * $ perf report --call-graph
+ *
+ * On RISC-V platform, the program being sampled and the C library
+ * need to be compiled with * -mbacktrace, otherwise the user
+ * stack will not contain function frame.
+ */
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+ struct pt_regs *regs)
+{
+ unsigned long fp = 0;
+
+ /* RISC-V does not support virtualization. */
+ if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+ return;
+
+ fp = regs->s0;
+ perf_callchain_store(entry, regs->sepc);
+
+ fp = user_backtrace(entry, fp, regs->ra);
+ while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
+ fp = user_backtrace(entry, fp, 0);
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+ struct pt_regs *regs)
+{
+ struct stackframe fr;
+
+ /* RISC-V does not support virtualization. */
+ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ pr_warn("RISC-V does not support perf in guest mode!");
+ return;
+ }
+
+ fr.fp = regs->s0;
+ fr.ra = regs->ra;
+ walk_stackframe(&fr, entry);
+}
--
2.7.4
