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 5.1.
CC: Palmer Dabbelt <[email protected]>
CC: linux-riscv <[email protected]>
CC: Christoph Hellwig <[email protected]>
CC: Guo Ren <[email protected]>
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
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 | 113 ++++++++++++++++++++++++++
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, 485 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
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 <[email protected]>
CC: Palmer Dabbelt <[email protected]>
CC: linux-riscv <[email protected]>
CC: Christoph Hellwig <[email protected]>
CC: Guo Ren <[email protected]>
---
arch/riscv/Makefile | 3 +
arch/riscv/kernel/Makefile | 3 +-
arch/riscv/kernel/perf_callchain.c | 113 +++++++++++++++++++++++++++++++++++++
3 files changed, 118 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/kernel/perf_callchain.c
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index c6342e6..4396abc 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -59,6 +59,9 @@ 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 += $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 5985681..dd2ba44 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -37,6 +37,7 @@ obj-$(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..8b57903
--- /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 -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
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 <[email protected]>
CC: Palmer Dabbelt <[email protected]>
CC: linux-riscv <[email protected]>
CC: Christoph Hellwig <[email protected]>
CC: Guo Ren <[email protected]>
---
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 fe3f97e..8f2e6d3 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -59,6 +59,10 @@ ifeq ($(SRCARCH),arm64)
LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
endif
+ifeq ($(SRCARCH),riscv)
+ NO_PERF_REGS := 0
+endif
+
ifeq ($(ARCH),s390)
NO_PERF_REGS := 0
NO_SYSCALL_TABLE := 0
@@ -77,7 +81,7 @@ endif
# Disable it on all other architectures in case libdw unwind
# support is detected in system. Add supported architectures
# to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 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
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 <[email protected]>
CC: Palmer Dabbelt <[email protected]>
CC: linux-riscv <[email protected]>
CC: Christoph Hellwig <[email protected]>
CC: Guo Ren <[email protected]>
---
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 eb56c82..effd157 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -33,6 +33,8 @@ 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 RISCV_ISA_A if SMP
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 dd2ba44..024badc 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -39,5 +39,6 @@ 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
PING?
On Fri, May 17, 2019 at 04:43:01PM +0800, Mao Han wrote:
> 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 5.1.
>
> CC: Palmer Dabbelt <[email protected]>
> CC: linux-riscv <[email protected]>
> CC: Christoph Hellwig <[email protected]>
> CC: Guo Ren <[email protected]>
>
> 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
>
> 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 | 113 ++++++++++++++++++++++++++
> 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, 485 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
>
>
> _______________________________________________
> linux-riscv mailing list
> [email protected]
> http://lists.infradead.org/mailman/listinfo/linux-riscv
Hello Mao Han,
On Fri, 17 May 2019, Mao Han wrote:
> 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 5.1.
>
> CC: Palmer Dabbelt <[email protected]>
> CC: linux-riscv <[email protected]>
> CC: Christoph Hellwig <[email protected]>
> CC: Guo Ren <[email protected]>
I tried these patches on v5.3-rc4, both on the HiFive Unleashed board
with a Debian-based rootfs and QEMU rv64 with a Fedora-based rootfs. For
QEMU, I used defconfig, and for the HiFive Unleashed, I added a few more
Kconfig directives; and on both, I enabled CONFIG_PERF_EVENTS. I built
the perf tools from the kernel tree.
Upon running "/root/bin/perf record -e cpu-clock --call-graph fp
/bin/ls", I see the backtraces below. The first is on the HiFive
Unleashed, the second is on QEMU.
Could you take a look and tell me if you see similar issues? And if not,
could you please walk me through your process for testing these patches on
rv64, so I can reproduce it here?
thanks,
- Paul
# /root/bin/perf record -e cpu-clock --call-graph fp /bin/ls
[ 213.258888] Unable to handle kernel paging request at virtual address ffffffd2d979000c
[ 213.266025] Oops [#1]
[ 213.268278] Modules linked in:
[ 213.271323] CPU: 2 PID: 165 Comm: ls Not tainted 5.3.0-rc4-00006-g2615b94055fc #164
[ 213.278961] sepc: ffffffe0005bde76 ra : ffffffe0005bde84 sp : ffffffe1f609d870
[ 213.286166] gp : ffffffe000dbe6c0 tp : ffffffe1f60fa600 t0 : 0000000000046000
[ 213.293372] t1 : 0000000000000002 t2 : 0000002aaaac4890 s0 : ffffffe1f609d8b0
[ 213.300579] s1 : ffffffe1f609d8d8 a0 : 0000000000000004 a1 : 0000000000000000
[ 213.307785] a2 : 10ef8552d9790004 a3 : 0000000000000018 a4 : 0000000000000018
[ 213.314991] a5 : 0000000000000003 a6 : 0000000000000001 a7 : ffffffe1f7b685e0
[ 213.322198] s2 : 10ef8552d9790014 s3 : 0000003fffffffff s4 : 0000000000001ff8
[ 213.329404] s5 : b7e9595db7f9e15f s6 : ffffffe000dbe128 s7 : ffffffe1f8d6f820
[ 213.336610] s8 : 00000031a394a3e8 s9 : ffffffe000656150 s10: 0000000200000120
[ 213.343816] s11: 0000002aaaabc938 t3 : ffffffe1f7b685c0 t4 : 0000000000000001
[ 213.351021] t5 : 0000000000000008 t6 : 0000000000000000
[ 213.356319] sstatus: 0000000200000100 sbadaddr: ffffffd2d979000c scause: 000000000000000d
[ 213.364482] ---[ end trace f325867b8e0786aa ]---
[ 213.369083] Kernel panic - not syncing: Fatal exception in interrupt
[ 213.375421] SMP: stopping secondary CPUs
[ 213.379336] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---
# /root/bin/perf record -e cpu-clock --call-graph fp /bin/ls
[ 3465.349655] Unable to handle kernel paging request at virtual address d9bfd43b47718688
[ 3465.352356] Oops [#1]
[ 3465.353375] Modules linked in:
[ 3465.354496] CPU: 0 PID: 9501 Comm: ls Not tainted 5.3.0-rc4-00004-g3bfea1b43363 #165
[ 3465.355904] sepc: ffffffe000039a0a ra : ffffffe000039a18 sp : ffffffe078c5b5e0
[ 3465.361041] gp : ffffffe000837760 tp : ffffffe078d88940 t0 : 0000000000046000
[ 3465.366104] t1 : 0000000000000002 t2 : 000000004387194a s0 : ffffffe078c5b620
[ 3465.366839] s1 : ffffffe078c5b648 a0 : 0000000000000004 a1 : 0000000000000000
[ 3465.369101] a2 : d9bfd43b47718680 a3 : 0000000000000690 a4 : 0000000000000018
[ 3465.370949] a5 : 0000000000000003 a6 : 0000000000000001 a7 : ffffffe0743b16d0
[ 3465.371650] s2 : d9bfd43b47718690 s3 : 0000003fffffffff s4 : 0000000000001ff8
[ 3465.372658] s5 : e85970cf9e9fbbc8 s6 : ffffffe0008371c8 s7 : ffffffe07a1527a0
[ 3465.373570] s8 : 00000326c7b3d418 s9 : ffffffe0000d3326 s10: 0000000000000120
[ 3465.377102] s11: ffffffe078cb4880 t3 : ffffffe0743b16c0 t4 : 0000000000000001
[ 3465.378125] t5 : 0000000000000008 t6 : ffffffe078c5bd60
[ 3465.380603] sstatus: 0000000000000100 sbadaddr: d9bfd43b47718688 scause: 000000000000000d
[ 3465.382872] ---[ end trace f0ff9969d564eb82 ]---
[ 3465.383998] Kernel panic - not syncing: Fatal exception in interrupt
[ 3465.385812] SMP: stopping secondary CPUs
[ 3465.394408] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---
Hi Paul,
On Fri, Aug 16, 2019 at 10:14:01AM -0700, Paul Walmsley wrote:
> Hello Mao Han,
>
> On Fri, 17 May 2019, Mao Han wrote:
>
> > 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 5.1.
> >
> > CC: Palmer Dabbelt <[email protected]>
> > CC: linux-riscv <[email protected]>
> > CC: Christoph Hellwig <[email protected]>
> > CC: Guo Ren <[email protected]>
>
> I tried these patches on v5.3-rc4, both on the HiFive Unleashed board
> with a Debian-based rootfs and QEMU rv64 with a Fedora-based rootfs. For
> QEMU, I used defconfig, and for the HiFive Unleashed, I added a few more
> Kconfig directives; and on both, I enabled CONFIG_PERF_EVENTS. I built
> the perf tools from the kernel tree.
>
> Upon running "/root/bin/perf record -e cpu-clock --call-graph fp
> /bin/ls", I see the backtraces below. The first is on the HiFive
> Unleashed, the second is on QEMU.
>
> Could you take a look and tell me if you see similar issues? And if not,
> could you please walk me through your process for testing these patches on
> rv64, so I can reproduce it here?
>
I'v tried the command line above and got similar issues with probability.
unwind_frame_kernel can not stop unwind when fp is a quite large
value(like 0x70aac93ff0eff584) which can pass the simple stack check.
if (kstack_end((void *)frame->fp))
return -EPERM;
if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
return -EPERM;
handle_exception from arch/riscv/kernel/entry.S will use s0(fp) as temp
register. The context for this frame is unpredictable. We may add more
strict check in unwind_frame_kernel or keep s0 always 0 in handle_exception
to fix this issue.
Breakpoint 1, unwind_frame_kernel (frame=0xffffffe0000057a0 <rcu_init+118>)
at arch/riscv/kernel/perf_callchain.c:14
14 {
1: /x *frame = {fp = 0xffffffe000005ee0, ra = 0xffffffe000124c90}
(gdb)
Continuing.
Breakpoint 1, unwind_frame_kernel (frame=0xffffffe0000057a0 <rcu_init+118>)
at arch/riscv/kernel/perf_callchain.c:14
14 {
1: /x *frame = {fp = 0xffffffe000124c74, ra = 0xffffffe000036cba}
(gdb)
Continuing.
Breakpoint 1, unwind_frame_kernel (frame=0xffffffe0000057a0 <rcu_init+118>)
at arch/riscv/kernel/perf_callchain.c:14
14 {
1: /x *frame = {fp = 0x70aac57ff0eff584, ra = 0x8082614d64ea740a}
(gdb)
Some time perf record can output perf.data correct. something like:
# perf record -e cpu-clock --call-graph fp ls
perf.data
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data (102 samples) ]
#
# perf report
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 102 of event 'cpu-clock'
# Event count (approx.): 25500000
#
# Children Self Command Shared Object Symbol
# ........ ........ ....... ................. .................................
#
30.39% 0.00% ls [kernel.kallsyms] [k] ret_from_exception
|
---ret_from_exception
|
|--16.67%--do_page_fault
| handle_mm_fault
| __handle_mm_fault
| |
| |--9.80%--filemap_map_pages
| | |
| | |--3.92%--alloc_set_pte
| | | page_add_file_rmap
| | |
| | --3.92%--filemap_map_pages
| |
| --0.98%--__do_fault
|
|--8.82%--schedule
| __sched_text_start
| finish_task_switch
|
--4.90%--__kprobes_text_start
irq_exit
irq_exit
28.43% 0.00% ls [kernel.kallsyms] [k] ret_from_syscall
|
---ret_from_syscall
|
|--15.69%--__se_sys_execve
| __do_execve_file
| search_binary_handler.part.7
I previous tested these patch with a program(callchain_test.c) mostly
running in userspace, so I didn't got this issues.
Thanks,
Mao Han
On Mon, Aug 19, 2019 at 04:18:01PM +0800, Mao Han wrote:
> Hi Paul,
> On Fri, Aug 16, 2019 at 10:14:01AM -0700, Paul Walmsley wrote:
> > Hello Mao Han,
> >
> > On Fri, 17 May 2019, Mao Han wrote:
> >
> > > 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 5.1.
> > >
> > > CC: Palmer Dabbelt <[email protected]>
> > > CC: linux-riscv <[email protected]>
> > > CC: Christoph Hellwig <[email protected]>
> > > CC: Guo Ren <[email protected]>
> >
> > I tried these patches on v5.3-rc4, both on the HiFive Unleashed board
> > with a Debian-based rootfs and QEMU rv64 with a Fedora-based rootfs. For
> > QEMU, I used defconfig, and for the HiFive Unleashed, I added a few more
> > Kconfig directives; and on both, I enabled CONFIG_PERF_EVENTS. I built
> > the perf tools from the kernel tree.
> >
> > Upon running "/root/bin/perf record -e cpu-clock --call-graph fp
> > /bin/ls", I see the backtraces below. The first is on the HiFive
> > Unleashed, the second is on QEMU.
> >
> > Could you take a look and tell me if you see similar issues? And if not,
> > could you please walk me through your process for testing these patches on
> > rv64, so I can reproduce it here?
> >
>
> I'v tried the command line above and got similar issues with probability.
> unwind_frame_kernel can not stop unwind when fp is a quite large
> value(like 0x70aac93ff0eff584) which can pass the simple stack check.
> if (kstack_end((void *)frame->fp))
> return -EPERM;
> if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
> return -EPERM;
> handle_exception from arch/riscv/kernel/entry.S will use s0(fp) as temp
> register. The context for this frame is unpredictable. We may add more
> strict check in unwind_frame_kernel or keep s0 always 0 in handle_exception
> to fix this issue.
>
perf record -e cpu-clock --call-graph fp /bin/ls seems can work stably
with this change applied.
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index 8b57903..dd27c67 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -16,6 +16,8 @@ static int unwind_frame_kernel(struct stackframe *frame)
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)) {
PS: I got some compile error while compiling glibc 2.30 with linux
v5.3-rc4 header. vfork.S include linux/sched.h(./include/uapi/linux/sched.h)
which has a struct clone_args inside, added by
7f192e3cd316ba58c88dfa26796cf77789dd9872.
On Mon, 19 Aug 2019, Mao Han wrote:
> PS: I got some compile error while compiling glibc 2.30 with linux
> v5.3-rc4 header. vfork.S include linux/sched.h(./include/uapi/linux/sched.h)
> which has a struct clone_args inside, added by
> 7f192e3cd316ba58c88dfa26796cf77789dd9872.
Noticed that also. Probably the sched.h uapi kernel header file needs an
"#ifndef __ASSEMBLY__" around the struct clone_args...
- Paul