[PATCH V4 0/3] riscv: Add perf callchain support

[PATCH V4 0/3] riscv: Add perf callchain support

[Mao Han]

This patch set add perf callchain(FP/DWARF) support for RISC-V.
It comes from the csky version callchain support with some
slight modifications. The patchset base on Linux 5.3.

Changes since v3:
  - Add more strict check for unwind_frame_kernel
  - update for kernel 5.3

Changes since v2:
  - fix inconsistent comment
  - force to build kernel with -fno-omit-frame-pointer if perf
    event is enabled

Changes since v1:
  - simplify implementation and code convention

Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: linux-riscv <linux-riscv@lists.infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Guo Ren <guoren@kernel.org>

Mao Han (3):
  riscv: Add perf callchain support
  riscv: Add support for perf registers sampling
  riscv: Add support for libdw

 arch/riscv/Kconfig                            |   2 +
 arch/riscv/Makefile                           |   3 +
 arch/riscv/include/uapi/asm/perf_regs.h       |  42 ++++++++++
 arch/riscv/kernel/Makefile                    |   4 +-
 arch/riscv/kernel/perf_callchain.c            | 115 ++++++++++++++++++++++++++
 arch/riscv/kernel/perf_regs.c                 |  44 ++++++++++
 tools/arch/riscv/include/uapi/asm/perf_regs.h |  42 ++++++++++
 tools/perf/Makefile.config                    |   6 +-
 tools/perf/arch/riscv/Build                   |   1 +
 tools/perf/arch/riscv/Makefile                |   3 +
 tools/perf/arch/riscv/include/perf_regs.h     |  96 +++++++++++++++++++++
 tools/perf/arch/riscv/util/Build              |   2 +
 tools/perf/arch/riscv/util/dwarf-regs.c       |  72 ++++++++++++++++
 tools/perf/arch/riscv/util/unwind-libdw.c     |  57 +++++++++++++
 14 files changed, 487 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/include/uapi/asm/perf_regs.h
 create mode 100644 arch/riscv/kernel/perf_callchain.c
 create mode 100644 arch/riscv/kernel/perf_regs.c
 create mode 100644 tools/arch/riscv/include/uapi/asm/perf_regs.h
 create mode 100644 tools/perf/arch/riscv/Build
 create mode 100644 tools/perf/arch/riscv/Makefile
 create mode 100644 tools/perf/arch/riscv/include/perf_regs.h
 create mode 100644 tools/perf/arch/riscv/util/Build
 create mode 100644 tools/perf/arch/riscv/util/dwarf-regs.c
 create mode 100644 tools/perf/arch/riscv/util/unwind-libdw.c

-- 
2.7.4

[PATCH V4 1/3] riscv: Add perf callchain support

[Mao Han]

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_mao@c-sky.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: linux-riscv <linux-riscv@lists.infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Guo Ren <guoren@kernel.org>
---
 arch/riscv/Makefile                |   3 +
 arch/riscv/kernel/Makefile         |   3 +-
 arch/riscv/kernel/perf_callchain.c | 115 +++++++++++++++++++++++++++++++++++++
 3 files changed, 120 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/kernel/perf_callchain.c

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 7a117be..946565b 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -54,6 +54,9 @@ endif
 ifeq ($(CONFIG_MODULE_SECTIONS),y)
 	KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds
 endif
+ifeq ($(CONFIG_PERF_EVENTS),y)
+        KBUILD_CFLAGS += -fno-omit-frame-pointer
+endif
 
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
 
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 2420d37..b1bea89 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -38,6 +38,7 @@ 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..d75d15c
--- /dev/null
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -0,0 +1,115 @@
+// 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;
+	if (frame->fp < CONFIG_PAGE_OFFSET)
+		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 -fno-omit-frame-pointer, 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

Re: [PATCH V4 1/3] riscv: Add perf callchain support

[Greentime Hu]

Hi Mao,

Mao Han <han_mao@c-sky.com> 於 2019年8月20日 週二 下午4:57寫道：
>
> 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_mao@c-sky.com>
> Cc: Paul Walmsley <paul.walmsley@sifive.com>
> Cc: Greentime Hu <green.hu@gmail.com>
> Cc: Palmer Dabbelt <palmer@sifive.com>
> Cc: linux-riscv <linux-riscv@lists.infradead.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Guo Ren <guoren@kernel.org>
> ---
>  arch/riscv/Makefile                |   3 +
>  arch/riscv/kernel/Makefile         |   3 +-
>  arch/riscv/kernel/perf_callchain.c | 115 +++++++++++++++++++++++++++++++++++++
>  3 files changed, 120 insertions(+), 1 deletion(-)
>  create mode 100644 arch/riscv/kernel/perf_callchain.c
>
> diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
> index 7a117be..946565b 100644
> --- a/arch/riscv/Makefile
> +++ b/arch/riscv/Makefile
> @@ -54,6 +54,9 @@ endif
>  ifeq ($(CONFIG_MODULE_SECTIONS),y)
>         KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds
>  endif
> +ifeq ($(CONFIG_PERF_EVENTS),y)
> +        KBUILD_CFLAGS += -fno-omit-frame-pointer
> +endif
>
>  KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
>
> diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> index 2420d37..b1bea89 100644
> --- a/arch/riscv/kernel/Makefile
> +++ b/arch/riscv/kernel/Makefile
> @@ -38,6 +38,7 @@ obj-$(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..d75d15c
> --- /dev/null
> +++ b/arch/riscv/kernel/perf_callchain.c
> @@ -0,0 +1,115 @@
> +// 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;
> +       if (frame->fp < CONFIG_PAGE_OFFSET)
> +               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 -fno-omit-frame-pointer, 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
>

Not sure if I did something wrong. I encounter a build error when I
try to build tools/perf/tests

  CC       arch/riscv/util/dwarf-regs.o
arch/riscv/util/dwarf-regs.c:64:5: error: no previous prototype for
‘regs_query_register_offset’ [-Werror=missing-prototypes]

I simply add its prototype and it could be built pass.
This is my testing results.
# ./perf test
 1: vmlinux symtab matches kallsyms                       : Skip
 2: Detect openat syscall event                           : FAILED!
 3: Detect openat syscall event on all cpus               : FAILED!
 4: Read samples using the mmap interface                 : FAILED!
 5: Test data source output                               : Ok
 6: Parse event definition strings                        : FAILED!
 7: Simple expression parser                              : Ok
 8: PERF_RECORD_* events & perf_sample fields             : FAILED!
 9: Parse perf pmu format                                 : Ok
10: DSO data read                                         : Ok
11: DSO data cache                                        : Ok
12: DSO data reopen                                       : Ok
13: Roundtrip evsel->name                                 : Ok
14: Parse sched tracepoints fields                        : FAILED!
15: syscalls:sys_enter_openat event fields                : FAILED!
16: Setup struct perf_event_attr                          : FAILED!
17: Match and link multiple hists                         : Ok
18: 'import perf' in python                               : FAILED!

19: Breakpoint overflow signal handler                    : FAILED!
20: Breakpoint overflow sampling                          : FAILED!
21: Breakpoint accounting                                 : Skip
22: Watchpoint                                            :
22.1: Read Only Watchpoint                                : FAILED!
22.2: Write Only Watchpoint                               : FAILED!
22.3: Read / Write Watchpoint                             : FAILED!
22.4: Modify Watchpoint                                   : FAILED!
23: Number of exit events of a simple workload            : Ok
24: Software clock events period values                   : Ok
25: Object code reading                                   : Ok
26: Sample parsing                                        : Ok
27: Use a dummy software event to keep tracking           : Ok
28: Parse with no sample_id_all bit set                   : Ok
29: Filter hist entries                                   : Ok
30: Lookup mmap thread                                    : Ok
31: Share thread mg                                       : Ok
32: Sort output of hist entries                           : Ok
33: Cumulate child hist entries                           : Ok
34: Track with sched_switch                               : Ok
35: Filter fds with revents mask in a fdarray             : Ok
36: Add fd to a fdarray, making it autogrow               : Ok
37: kmod_path__parse                                      : Ok
38: Thread map                                            : Ok
39: LLVM search and compile                               :
39.1: Basic BPF llvm compile                              : Skip
39.2: kbuild searching                                    : Skip
39.3: Compile source for BPF prologue generation          : Skip
39.4: Compile source for BPF relocation                   : Skip
40: Session topology                                      : FAILED!
41: BPF filter                                            :
41.1: Basic BPF filtering                                 : Skip
41.2: BPF pinning                                         : Skip
41.3: BPF relocation checker                              : Skip
42: Synthesize thread map                                 : Ok
43: Remove thread map                                     : Ok
44: Synthesize cpu map                                    : Ok
45: Synthesize stat config                                : Ok
46: Synthesize stat                                       : Ok
47: Synthesize stat round                                 : Ok
48: Synthesize attr update                                : Ok
49: Event times                                           : Ok
50: Read backward ring buffer                             : Skip
51: Print cpu map                                         : Ok
52: Probe SDT events                                      : Skip
53: is_printable_array                                    : Ok
54: Print bitmap                                          : Ok
55: perf hooks                                            : Ok
56: builtin clang support                                 : Skip (not
compiled in)
57: unit_number__scnprintf                                : Ok
58: mem2node                                              : Ok
59: time utils                                            : Ok
60: map_groups__merge_in                                  : Ok
61: probe libc's inet_pton & backtrace it with ping       : FAILED!
62: Add vfs_getname probe to get syscall args filenames   : FAILED!
63: Check open filename arg using perf trace + vfs_getname: Skip
64: Use vfs_getname probe to get syscall args filenames   : FAILED!
65: Zstd perf.data compression/decompression              : Skip

I also try the command that Paul pointed out.
./perf record -e cpu-clock --call-graph fp /bin/ls
It works fine now. It can generate a perf.data now.

Re: [PATCH V4 1/3] riscv: Add perf callchain support

[Mao Han]

Hi Greentime,
On Wed, Aug 21, 2019 at 05:16:13PM +0800, Greentime Hu wrote:
> Hi Mao,
> 
> Mao Han <han_mao@c-sky.com> 於 2019年8月20日 週二 下午4:57寫道：
> >
> > 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.
> >
> >
> 
> Not sure if I did something wrong. I encounter a build error when I
> try to build tools/perf/tests
> 
>   CC       arch/riscv/util/dwarf-regs.o
> arch/riscv/util/dwarf-regs.c:64:5: error: no previous prototype for
> ‘regs_query_register_offset’ [-Werror=missing-prototypes]
>

This seems becasue I didn't add PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
in tools/perf/arch/riscv/Makefile so the prototype in
./util/include/dwarf-regs.h is not declared. I'll add that in the next
version.
 
> I simply add its prototype and it could be built pass.
> This is my testing results.
> # ./perf test
>  1: vmlinux symtab matches kallsyms                       : Skip
>  2: Detect openat syscall event                           : FAILED!
>  3: Detect openat syscall event on all cpus               : FAILED!
>  4: Read samples using the mmap interface                 : FAILED!
>  5: Test data source output                               : Ok
>  6: Parse event definition strings                        : FAILED!
>  7: Simple expression parser                              : Ok
>  8: PERF_RECORD_* events & perf_sample fields             : FAILED!
>  9: Parse perf pmu format                                 : Ok
> 10: DSO data read                                         : Ok
> 11: DSO data cache                                        : Ok
> 12: DSO data reopen                                       : Ok
> 13: Roundtrip evsel->name                                 : Ok
> 14: Parse sched tracepoints fields                        : FAILED!
> 15: syscalls:sys_enter_openat event fields                : FAILED!
> 16: Setup struct perf_event_attr                          : FAILED!
> 17: Match and link multiple hists                         : Ok
> 18: 'import perf' in python                               : FAILED!
> 
> 19: Breakpoint overflow signal handler                    : FAILED!
> 20: Breakpoint overflow sampling                          : FAILED!
> 21: Breakpoint accounting                                 : Skip
> 22: Watchpoint                                            :
> 22.1: Read Only Watchpoint                                : FAILED!
> 22.2: Write Only Watchpoint                               : FAILED!
> 22.3: Read / Write Watchpoint                             : FAILED!
> 22.4: Modify Watchpoint                                   : FAILED!
> 23: Number of exit events of a simple workload            : Ok
> 24: Software clock events period values                   : Ok
> 25: Object code reading                                   : Ok
> 26: Sample parsing                                        : Ok
> 27: Use a dummy software event to keep tracking           : Ok
> 28: Parse with no sample_id_all bit set                   : Ok
> 29: Filter hist entries                                   : Ok
> 30: Lookup mmap thread                                    : Ok
> 31: Share thread mg                                       : Ok
> 32: Sort output of hist entries                           : Ok
> 33: Cumulate child hist entries                           : Ok
> 34: Track with sched_switch                               : Ok
> 35: Filter fds with revents mask in a fdarray             : Ok
> 36: Add fd to a fdarray, making it autogrow               : Ok
> 37: kmod_path__parse                                      : Ok
> 38: Thread map                                            : Ok
> 39: LLVM search and compile                               :
> 39.1: Basic BPF llvm compile                              : Skip
> 39.2: kbuild searching                                    : Skip
> 39.3: Compile source for BPF prologue generation          : Skip
> 39.4: Compile source for BPF relocation                   : Skip
> 40: Session topology                                      : FAILED!
> 41: BPF filter                                            :
> 41.1: Basic BPF filtering                                 : Skip
> 41.2: BPF pinning                                         : Skip
> 41.3: BPF relocation checker                              : Skip
> 42: Synthesize thread map                                 : Ok
> 43: Remove thread map                                     : Ok
> 44: Synthesize cpu map                                    : Ok
> 45: Synthesize stat config                                : Ok
> 46: Synthesize stat                                       : Ok
> 47: Synthesize stat round                                 : Ok
> 48: Synthesize attr update                                : Ok
> 49: Event times                                           : Ok
> 50: Read backward ring buffer                             : Skip
> 51: Print cpu map                                         : Ok
> 52: Probe SDT events                                      : Skip
> 53: is_printable_array                                    : Ok
> 54: Print bitmap                                          : Ok
> 55: perf hooks                                            : Ok
> 56: builtin clang support                                 : Skip (not
> compiled in)
> 57: unit_number__scnprintf                                : Ok
> 58: mem2node                                              : Ok
> 59: time utils                                            : Ok
> 60: map_groups__merge_in                                  : Ok
> 61: probe libc's inet_pton & backtrace it with ping       : FAILED!
> 62: Add vfs_getname probe to get syscall args filenames   : FAILED!
> 63: Check open filename arg using perf trace + vfs_getname: Skip
> 64: Use vfs_getname probe to get syscall args filenames   : FAILED!
> 65: Zstd perf.data compression/decompression              : Skip
>

The perf test result I got is quiet similar to yours, but with 5
less testcases.

 1: vmlinux symtab matches kallsyms            : Skip
 2: Detect openat syscall event                : FAILED!
 3: Detect openat syscall event on all cpus    : FAILED!
 4: Read samples using the mmap interface      : FAILED!
 5: Test data source output                    : Ok
 6: Parse event definition strings             : FAILED!
 7: Simple expression parser                   : Ok
 8: PERF_RECORD_* events & perf_sample fields  : FAILED!
 9: Parse perf pmu format                      : Ok
10: DSO data read                              : Ok
11: DSO data cache                             : Ok
12: DSO data reopen                            : Ok
13: Roundtrip evsel->name                      : Ok
14: Parse sched tracepoints fields             : FAILED!
15: syscalls:sys_enter_openat event fields     : FAILED!
16: Setup struct perf_event_attr               : Skip
17: Match and link multiple hists              : Ok
18: 'import perf' in python                    : Ok
19: Breakpoint overflow signal handler         : FAILED!
20: Breakpoint overflow sampling               : FAILED!
21: Breakpoint accounting                      : Skip
22: Watchpoint                                 :
22.1: Read Only Watchpoint                     : FAILED!
22.2: Write Only Watchpoint                    : FAILED!
22.3: Read / Write Watchpoint                  : FAILED!
22.4: Modify Watchpoint                        : FAILED!
23: Number of exit events of a simple workload : Ok
24: Software clock events period values        : Ok
25: Object code reading                        : Ok
26: Sample parsing                             : Ok
27: Use a dummy software event to keep tracking: Ok
28: Parse with no sample_id_all bit set        : Ok
29: Filter hist entries                        : Ok
30: Lookup mmap thread                         : Ok
31: Share thread mg                            : Ok
32: Sort output of hist entries                : Ok
33: Cumulate child hist entries                : Ok
34: Track with sched_switch                    : Ok
35: Filter fds with revents mask in a fdarray  : Ok
36: Add fd to a fdarray, making it autogrow    : Ok
37: kmod_path__parse                           : Ok
38: Thread map                                 : Ok
39: LLVM search and compile                    :
39.1: Basic BPF llvm compile                    : Skip
39.2: kbuild searching                          : Skip
39.3: Compile source for BPF prologue generation: Skip
39.4: Compile source for BPF relocation         : Skip
40: Session topology                           : FAILED!
41: BPF filter                                 :
41.1: Basic BPF filtering                      : Skip
41.2: BPF pinning                              : Skip
41.3: BPF relocation checker                   : Skip
42: Synthesize thread map                      : Ok
43: Remove thread map                          : Ok
44: Synthesize cpu map                         : Ok
45: Synthesize stat config                     : Ok
46: Synthesize stat                            : Ok
47: Synthesize stat round                      : Ok
48: Synthesize attr update                     : Ok
49: Event times                                : Ok
50: Read backward ring buffer                  : Skip
51: Print cpu map                              : Ok
52: Probe SDT events                           : Skip
53: is_printable_array                         : Ok
54: Print bitmap                               : Ok
55: perf hooks                                 : Ok
56: builtin clang support                      : Skip (not compiled in)
57: unit_number__scnprintf                     : Ok
58: mem2node                                   : Ok
59: time utils                                 : Ok
60: map_groups__merge_in                       : Ok

The comparison before/after applied this patch set:

/tools/perf/util# diff perf_test_before perf_test_after
1d0
< # perf test
8c7
<  7: Simple expression parser                   : FAILED!
---
>  7: Simple expression parser                   : Ok

[PATCH V4 2/3] riscv: Add support for perf registers sampling

[Mao Han]

This patch implements the perf registers sampling and validation API
for riscv arch. The valid registers and their register ID are defined in
perf_regs.h. Perf tool can backtrace in userspace with unwind library
and the registers/user stack dump support.

Signed-off-by: Mao Han <han_mao@c-sky.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: linux-riscv <linux-riscv@lists.infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Guo Ren <guoren@kernel.org>
---
 arch/riscv/Kconfig                      |  2 ++
 arch/riscv/include/uapi/asm/perf_regs.h | 42 +++++++++++++++++++++++++++++++
 arch/riscv/kernel/Makefile              |  1 +
 arch/riscv/kernel/perf_regs.c           | 44 +++++++++++++++++++++++++++++++++
 4 files changed, 89 insertions(+)
 create mode 100644 arch/riscv/include/uapi/asm/perf_regs.h
 create mode 100644 arch/riscv/kernel/perf_regs.c

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 59a4727..4bc976d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -35,6 +35,8 @@ config RISCV
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select SPARSE_IRQ
diff --git a/arch/riscv/include/uapi/asm/perf_regs.h b/arch/riscv/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..df1a581
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/perf_regs.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef _ASM_RISCV_PERF_REGS_H
+#define _ASM_RISCV_PERF_REGS_H
+
+enum perf_event_riscv_regs {
+	PERF_REG_RISCV_PC,
+	PERF_REG_RISCV_RA,
+	PERF_REG_RISCV_SP,
+	PERF_REG_RISCV_GP,
+	PERF_REG_RISCV_TP,
+	PERF_REG_RISCV_T0,
+	PERF_REG_RISCV_T1,
+	PERF_REG_RISCV_T2,
+	PERF_REG_RISCV_S0,
+	PERF_REG_RISCV_S1,
+	PERF_REG_RISCV_A0,
+	PERF_REG_RISCV_A1,
+	PERF_REG_RISCV_A2,
+	PERF_REG_RISCV_A3,
+	PERF_REG_RISCV_A4,
+	PERF_REG_RISCV_A5,
+	PERF_REG_RISCV_A6,
+	PERF_REG_RISCV_A7,
+	PERF_REG_RISCV_S2,
+	PERF_REG_RISCV_S3,
+	PERF_REG_RISCV_S4,
+	PERF_REG_RISCV_S5,
+	PERF_REG_RISCV_S6,
+	PERF_REG_RISCV_S7,
+	PERF_REG_RISCV_S8,
+	PERF_REG_RISCV_S9,
+	PERF_REG_RISCV_S10,
+	PERF_REG_RISCV_S11,
+	PERF_REG_RISCV_T3,
+	PERF_REG_RISCV_T4,
+	PERF_REG_RISCV_T5,
+	PERF_REG_RISCV_T6,
+	PERF_REG_RISCV_MAX,
+};
+#endif /* _ASM_RISCV_PERF_REGS_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index b1bea89..696020f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -40,5 +40,6 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 
 clean:
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
new file mode 100644
index 0000000..04a38fb
--- /dev/null
+++ b/arch/riscv/kernel/perf_regs.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_RISCV_MAX))
+		return 0;
+
+	return ((unsigned long *)regs)[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_RISCV_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+#if __riscv_xlen == 64
+	return PERF_SAMPLE_REGS_ABI_64;
+#else
+	return PERF_SAMPLE_REGS_ABI_32;
+#endif
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
-- 
2.7.4

[PATCH V4 3/3] riscv: Add support for libdw

[Mao Han]

This patch add support for DWARF register mappings and libdw registers
initialization, which is used by perf callchain analyzing when
--call-graph=dwarf is given.

Signed-off-by: Mao Han <han_mao@c-sky.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: linux-riscv <linux-riscv@lists.infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Guo Ren <guoren@kernel.org>
---
 tools/arch/riscv/include/uapi/asm/perf_regs.h | 42 ++++++++++++
 tools/perf/Makefile.config                    |  6 +-
 tools/perf/arch/riscv/Build                   |  1 +
 tools/perf/arch/riscv/Makefile                |  3 +
 tools/perf/arch/riscv/include/perf_regs.h     | 96 +++++++++++++++++++++++++++
 tools/perf/arch/riscv/util/Build              |  2 +
 tools/perf/arch/riscv/util/dwarf-regs.c       | 72 ++++++++++++++++++++
 tools/perf/arch/riscv/util/unwind-libdw.c     | 57 ++++++++++++++++
 8 files changed, 278 insertions(+), 1 deletion(-)
 create mode 100644 tools/arch/riscv/include/uapi/asm/perf_regs.h
 create mode 100644 tools/perf/arch/riscv/Build
 create mode 100644 tools/perf/arch/riscv/Makefile
 create mode 100644 tools/perf/arch/riscv/include/perf_regs.h
 create mode 100644 tools/perf/arch/riscv/util/Build
 create mode 100644 tools/perf/arch/riscv/util/dwarf-regs.c
 create mode 100644 tools/perf/arch/riscv/util/unwind-libdw.c

diff --git a/tools/arch/riscv/include/uapi/asm/perf_regs.h b/tools/arch/riscv/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..df1a581
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/perf_regs.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef _ASM_RISCV_PERF_REGS_H
+#define _ASM_RISCV_PERF_REGS_H
+
+enum perf_event_riscv_regs {
+	PERF_REG_RISCV_PC,
+	PERF_REG_RISCV_RA,
+	PERF_REG_RISCV_SP,
+	PERF_REG_RISCV_GP,
+	PERF_REG_RISCV_TP,
+	PERF_REG_RISCV_T0,
+	PERF_REG_RISCV_T1,
+	PERF_REG_RISCV_T2,
+	PERF_REG_RISCV_S0,
+	PERF_REG_RISCV_S1,
+	PERF_REG_RISCV_A0,
+	PERF_REG_RISCV_A1,
+	PERF_REG_RISCV_A2,
+	PERF_REG_RISCV_A3,
+	PERF_REG_RISCV_A4,
+	PERF_REG_RISCV_A5,
+	PERF_REG_RISCV_A6,
+	PERF_REG_RISCV_A7,
+	PERF_REG_RISCV_S2,
+	PERF_REG_RISCV_S3,
+	PERF_REG_RISCV_S4,
+	PERF_REG_RISCV_S5,
+	PERF_REG_RISCV_S6,
+	PERF_REG_RISCV_S7,
+	PERF_REG_RISCV_S8,
+	PERF_REG_RISCV_S9,
+	PERF_REG_RISCV_S10,
+	PERF_REG_RISCV_S11,
+	PERF_REG_RISCV_T3,
+	PERF_REG_RISCV_T4,
+	PERF_REG_RISCV_T5,
+	PERF_REG_RISCV_T6,
+	PERF_REG_RISCV_MAX,
+};
+#endif /* _ASM_RISCV_PERF_REGS_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 89ac5a1..eaf25ee 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -60,6 +60,10 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(SRCARCH),riscv)
+  NO_PERF_REGS := 0
+endif
+
 ifeq ($(SRCARCH),csky)
   NO_PERF_REGS := 0
 endif
@@ -82,7 +86,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
diff --git a/tools/perf/arch/riscv/Build b/tools/perf/arch/riscv/Build
new file mode 100644
index 0000000..e4e5f33
--- /dev/null
+++ b/tools/perf/arch/riscv/Build
@@ -0,0 +1 @@
+perf-y += util/
diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile
new file mode 100644
index 0000000..7fbca17
--- /dev/null
+++ b/tools/perf/arch/riscv/Makefile
@@ -0,0 +1,3 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h
new file mode 100644
index 0000000..7a8bcde
--- /dev/null
+++ b/tools/perf/arch/riscv/include/perf_regs.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_RISCV_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_RISCV_MAX
+#if __riscv_xlen == 64
+#define PERF_SAMPLE_REGS_ABI    PERF_SAMPLE_REGS_ABI_64
+#else
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+#endif
+
+#define PERF_REG_IP	PERF_REG_RISCV_PC
+#define PERF_REG_SP	PERF_REG_RISCV_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_RISCV_PC:
+		return "pc";
+	case PERF_REG_RISCV_RA:
+		return "ra";
+	case PERF_REG_RISCV_SP:
+		return "sp";
+	case PERF_REG_RISCV_GP:
+		return "gp";
+	case PERF_REG_RISCV_TP:
+		return "tp";
+	case PERF_REG_RISCV_T0:
+		return "t0";
+	case PERF_REG_RISCV_T1:
+		return "t1";
+	case PERF_REG_RISCV_T2:
+		return "t2";
+	case PERF_REG_RISCV_S0:
+		return "s0";
+	case PERF_REG_RISCV_S1:
+		return "s1";
+	case PERF_REG_RISCV_A0:
+		return "a0";
+	case PERF_REG_RISCV_A1:
+		return "a1";
+	case PERF_REG_RISCV_A2:
+		return "a2";
+	case PERF_REG_RISCV_A3:
+		return "a3";
+	case PERF_REG_RISCV_A4:
+		return "a4";
+	case PERF_REG_RISCV_A5:
+		return "a5";
+	case PERF_REG_RISCV_A6:
+		return "a6";
+	case PERF_REG_RISCV_A7:
+		return "a7";
+	case PERF_REG_RISCV_S2:
+		return "s2";
+	case PERF_REG_RISCV_S3:
+		return "s3";
+	case PERF_REG_RISCV_S4:
+		return "s4";
+	case PERF_REG_RISCV_S5:
+		return "s5";
+	case PERF_REG_RISCV_S6:
+		return "s6";
+	case PERF_REG_RISCV_S7:
+		return "s7";
+	case PERF_REG_RISCV_S8:
+		return "s8";
+	case PERF_REG_RISCV_S9:
+		return "s9";
+	case PERF_REG_RISCV_S10:
+		return "s10";
+	case PERF_REG_RISCV_S11:
+		return "s11";
+	case PERF_REG_RISCV_T3:
+		return "t3";
+	case PERF_REG_RISCV_T4:
+		return "t4";
+	case PERF_REG_RISCV_T5:
+		return "t5";
+	case PERF_REG_RISCV_T6:
+		return "t6";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/riscv/util/Build b/tools/perf/arch/riscv/util/Build
new file mode 100644
index 0000000..1160bb2
--- /dev/null
+++ b/tools/perf/arch/riscv/util/Build
@@ -0,0 +1,2 @@
+perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/riscv/util/dwarf-regs.c b/tools/perf/arch/riscv/util/dwarf-regs.c
new file mode 100644
index 0000000..f3555f6
--- /dev/null
+++ b/tools/perf/arch/riscv/util/dwarf-regs.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+ * Mapping of DWARF debug register numbers into register names.
+ */
+
+#include <stddef.h>
+#include <errno.h> /* for EINVAL */
+#include <string.h> /* for strcmp */
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+struct pt_regs_dwarfnum riscv_dwarf_regs_table[] = {
+	REG_DWARFNUM_NAME("%zero", 0),
+	REG_DWARFNUM_NAME("%ra", 1),
+	REG_DWARFNUM_NAME("%sp", 2),
+	REG_DWARFNUM_NAME("%gp", 3),
+	REG_DWARFNUM_NAME("%tp", 4),
+	REG_DWARFNUM_NAME("%t0", 5),
+	REG_DWARFNUM_NAME("%t1", 6),
+	REG_DWARFNUM_NAME("%t2", 7),
+	REG_DWARFNUM_NAME("%s0", 8),
+	REG_DWARFNUM_NAME("%s1", 9),
+	REG_DWARFNUM_NAME("%a0", 10),
+	REG_DWARFNUM_NAME("%a1", 11),
+	REG_DWARFNUM_NAME("%a2", 12),
+	REG_DWARFNUM_NAME("%a3", 13),
+	REG_DWARFNUM_NAME("%a4", 14),
+	REG_DWARFNUM_NAME("%a5", 15),
+	REG_DWARFNUM_NAME("%a6", 16),
+	REG_DWARFNUM_NAME("%a7", 17),
+	REG_DWARFNUM_NAME("%s2", 18),
+	REG_DWARFNUM_NAME("%s3", 19),
+	REG_DWARFNUM_NAME("%s4", 20),
+	REG_DWARFNUM_NAME("%s5", 21),
+	REG_DWARFNUM_NAME("%s6", 22),
+	REG_DWARFNUM_NAME("%s7", 23),
+	REG_DWARFNUM_NAME("%s8", 24),
+	REG_DWARFNUM_NAME("%s9", 25),
+	REG_DWARFNUM_NAME("%s10", 26),
+	REG_DWARFNUM_NAME("%s11", 27),
+	REG_DWARFNUM_NAME("%t3", 28),
+	REG_DWARFNUM_NAME("%t4", 29),
+	REG_DWARFNUM_NAME("%t5", 30),
+	REG_DWARFNUM_NAME("%t6", 31),
+	REG_DWARFNUM_END,
+};
+
+#define RISCV_MAX_REGS ((sizeof(riscv_dwarf_regs_table) / \
+		 sizeof(riscv_dwarf_regs_table[0])) - 1)
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n < RISCV_MAX_REGS) ? riscv_dwarf_regs_table[n].name : NULL;
+}
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_dwarfnum *roff;
+
+	for (roff = riscv_dwarf_regs_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->dwarfnum;
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c
new file mode 100644
index 0000000..19536e1
--- /dev/null
+++ b/tools/perf/arch/riscv/util/unwind-libdw.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[32];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_RISCV_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = 0;
+	dwarf_regs[1]  = REG(RA);
+	dwarf_regs[2]  = REG(SP);
+	dwarf_regs[3]  = REG(GP);
+	dwarf_regs[4]  = REG(TP);
+	dwarf_regs[5]  = REG(T0);
+	dwarf_regs[6]  = REG(T1);
+	dwarf_regs[7]  = REG(T2);
+	dwarf_regs[8]  = REG(S0);
+	dwarf_regs[9]  = REG(S1);
+	dwarf_regs[10] = REG(A0);
+	dwarf_regs[11] = REG(A1);
+	dwarf_regs[12] = REG(A2);
+	dwarf_regs[13] = REG(A3);
+	dwarf_regs[14] = REG(A4);
+	dwarf_regs[15] = REG(A5);
+	dwarf_regs[16] = REG(A6);
+	dwarf_regs[17] = REG(A7);
+	dwarf_regs[18] = REG(S2);
+	dwarf_regs[19] = REG(S3);
+	dwarf_regs[20] = REG(S4);
+	dwarf_regs[21] = REG(S5);
+	dwarf_regs[22] = REG(S6);
+	dwarf_regs[23] = REG(S7);
+	dwarf_regs[24] = REG(S8);
+	dwarf_regs[25] = REG(S9);
+	dwarf_regs[26] = REG(S10);
+	dwarf_regs[27] = REG(S11);
+	dwarf_regs[28] = REG(T3);
+	dwarf_regs[29] = REG(T4);
+	dwarf_regs[30] = REG(T5);
+	dwarf_regs[31] = REG(T6);
+	dwfl_thread_state_register_pc(thread, REG(PC));
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_RISCV_MAX,
+					   dwarf_regs);
+}
-- 
2.7.4