summaryrefslogtreecommitdiff
path: root/tools/perf/arch/powerpc
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-10-03 12:47:28 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-03 12:47:28 -0700
commit12b7bcb43e6ea834ab2f5dc52d971e379a0ca109 (patch)
tree65218ee4792a1bae88feb75e615c5ec4e602c7a2 /tools/perf/arch/powerpc
parent00bcf5cdd6c0e2e92ce3dd852ca68a3b779fa4ec (diff)
parent41aad2a6d4fcdda8d73c9739daf7a9f3f49499d6 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "The main kernel side changes were: - uprobes enhancements (Masami Hiramatsu) - Uncore group events enhancements (David Carrillo-Cisneros) - x86 Intel: Add support for Skylake server uncore PMUs (Kan Liang) - x86 Intel: LBR cleanups and enhancements, for better branch annotation tracking (Peter Zijlstra) - x86 Intel: Add support for PTWRITE and power event tracing (Alexander Shishkin) - ... various fixes, cleanups and smaller enhancements. Lots of tooling changes - a couple of highlights: - Support event group view with hierarchy mode in 'perf top' and 'perf report' (Namhyung Kim) e.g.: $ perf record -e '{cycles,instructions}' make $ perf report --hierarchy --stdio ... # Overhead Command / Shared Object / Symbol # ...................... .................................. ... 25.74% 27.18%sh 19.96% 24.14%libc-2.24.so 9.55% 14.64%[.] __strcmp_sse2 1.54% 0.00%[.] __tfind 1.07% 1.13%[.] _int_malloc 0.95% 0.00%[.] __strchr_sse2 0.89% 1.39%[.] __tsearch 0.76% 0.00%[.] strlen - Add branch stack / basic block info to 'perf annotate --stdio', where for each branch, we add an asm comment after the instruction with information on how often it was taken and predicted. See example with color output at: http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png (Peter Zijlstra) - Add support for using symbols in address filters with Intel PT and ARM CoreSight (hardware assisted tracing facilities) (Adrian Hunter, Mathieu Poirier) - Add support for interacting with Coresight PMU ETMs/PTMs, that are IP blocks to perform hardware assisted tracing on a ARM CPU core (Mathieu Poirier) - Support generating cross arch probes, i.e. if you specify a vmlinux file for different arch than the one in the host machine, $ perf probe --definition function_name args will generate the probe definition string needed to append to the target machine /sys/kernel/debug/tracing/kprobes_events file, using scripting (Masami Hiramatsu). - Allow configuring the default 'perf report -s' sort order in ~/.perfconfig, for instance, "sym,dso" may be more fitting for kernel developers. (Arnaldo Carvalho de Melo) - ... plus lots of other changes, refactorings, features and fixes" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (149 commits) perf tests: Add dwarf unwind test for powerpc perf probe: Match linkage name with mangled name perf probe: Fix to cut off incompatible chars from group name perf probe: Skip if the function address is 0 perf probe: Ignore the error of finding inline instance perf intel-pt: Fix decoding when there are address filters perf intel-pt: Enable decoder to handle TIP.PGD with missing IP perf intel-pt: Read address filter from AUXTRACE_INFO event perf intel-pt: Record address filter in AUXTRACE_INFO event perf intel-pt: Add a helper function for processing AUXTRACE_INFO perf intel-pt: Fix missing error codes processing auxtrace_info perf intel-pt: Add support for recording the max non-turbo ratio perf intel-pt: Fix snapshot overlap detection decoder errors perf probe: Increase debug level of SDT debug messages perf record: Add support for using symbols in address filters perf symbols: Add dso__last_symbol() perf record: Fix error paths perf record: Rename label 'out_symbol_exit' perf script: Fix vanished idle symbols perf evsel: Add support for address filters ...
Diffstat (limited to 'tools/perf/arch/powerpc')
-rw-r--r--tools/perf/arch/powerpc/Build1
-rw-r--r--tools/perf/arch/powerpc/include/arch-tests.h13
-rw-r--r--tools/perf/arch/powerpc/include/dwarf-regs-table.h27
-rw-r--r--tools/perf/arch/powerpc/include/perf_regs.h2
-rw-r--r--tools/perf/arch/powerpc/tests/Build4
-rw-r--r--tools/perf/arch/powerpc/tests/arch-tests.c15
-rw-r--r--tools/perf/arch/powerpc/tests/dwarf-unwind.c62
-rw-r--r--tools/perf/arch/powerpc/tests/regs_load.S94
-rw-r--r--tools/perf/arch/powerpc/util/sym-handling.c2
9 files changed, 219 insertions, 1 deletions
diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build
index 54afe4a467e7..db52fa22d3a1 100644
--- a/tools/perf/arch/powerpc/Build
+++ b/tools/perf/arch/powerpc/Build
@@ -1 +1,2 @@
libperf-y += util/
+libperf-y += tests/
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
new file mode 100644
index 000000000000..84d8dedef2ed
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -0,0 +1,13 @@
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+ struct thread *thread);
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/powerpc/include/dwarf-regs-table.h b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..db4730f5585c
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
@@ -0,0 +1,27 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+/*
+ * Reference:
+ * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
+ * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf
+ */
+#define REG_DWARFNUM_NAME(reg, idx) [idx] = "%" #reg
+
+static const char * const powerpc_regstr_tbl[] = {
+ "%gpr0", "%gpr1", "%gpr2", "%gpr3", "%gpr4",
+ "%gpr5", "%gpr6", "%gpr7", "%gpr8", "%gpr9",
+ "%gpr10", "%gpr11", "%gpr12", "%gpr13", "%gpr14",
+ "%gpr15", "%gpr16", "%gpr17", "%gpr18", "%gpr19",
+ "%gpr20", "%gpr21", "%gpr22", "%gpr23", "%gpr24",
+ "%gpr25", "%gpr26", "%gpr27", "%gpr28", "%gpr29",
+ "%gpr30", "%gpr31",
+ REG_DWARFNUM_NAME(msr, 66),
+ REG_DWARFNUM_NAME(ctr, 109),
+ REG_DWARFNUM_NAME(link, 108),
+ REG_DWARFNUM_NAME(xer, 101),
+ REG_DWARFNUM_NAME(dar, 119),
+ REG_DWARFNUM_NAME(dsisr, 118),
+};
+
+#endif
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 75de0e92e71e..c12f4e804f66 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -5,6 +5,8 @@
#include <linux/types.h>
#include <asm/perf_regs.h>
+void perf_regs_load(u64 *regs);
+
#define PERF_REGS_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1)
#define PERF_REGS_MAX PERF_REG_POWERPC_MAX
#ifdef __powerpc64__
diff --git a/tools/perf/arch/powerpc/tests/Build b/tools/perf/arch/powerpc/tests/Build
new file mode 100644
index 000000000000..d827ef384b33
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/Build
@@ -0,0 +1,4 @@
+libperf-$(CONFIG_DWARF_UNWIND) += regs_load.o
+libperf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c
new file mode 100644
index 000000000000..e24f46241f40
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/arch-tests.c
@@ -0,0 +1,15 @@
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ {
+ .desc = "Test dwarf unwind",
+ .func = test__dwarf_unwind,
+ },
+#endif
+ {
+ .func = NULL,
+ },
+};
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..0bac3137ccbd
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -0,0 +1,62 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+ struct thread *thread, u64 *regs)
+{
+ struct stack_dump *stack = &sample->user_stack;
+ struct map *map;
+ unsigned long sp;
+ u64 stack_size, *buf;
+
+ buf = malloc(STACK_SIZE);
+ if (!buf) {
+ pr_debug("failed to allocate sample uregs data\n");
+ return -1;
+ }
+
+ sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
+
+ map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ if (!map) {
+ pr_debug("failed to get stack map\n");
+ free(buf);
+ return -1;
+ }
+
+ stack_size = map->end - sp;
+ stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+ memcpy(buf, (void *) sp, stack_size);
+ stack->data = (char *) buf;
+ stack->size = stack_size;
+ return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+ struct thread *thread)
+{
+ struct regs_dump *regs = &sample->user_regs;
+ u64 *buf;
+
+ buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+ if (!buf) {
+ pr_debug("failed to allocate sample uregs data\n");
+ return -1;
+ }
+
+ perf_regs_load(buf);
+ regs->abi = PERF_SAMPLE_REGS_ABI;
+ regs->regs = buf;
+ regs->mask = PERF_REGS_MASK;
+
+ return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/powerpc/tests/regs_load.S b/tools/perf/arch/powerpc/tests/regs_load.S
new file mode 100644
index 000000000000..d76c9a32f327
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/regs_load.S
@@ -0,0 +1,94 @@
+#include <linux/linkage.h>
+
+/* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */
+#define R0 0
+#define R1 1 * 8
+#define R2 2 * 8
+#define R3 3 * 8
+#define R4 4 * 8
+#define R5 5 * 8
+#define R6 6 * 8
+#define R7 7 * 8
+#define R8 8 * 8
+#define R9 9 * 8
+#define R10 10 * 8
+#define R11 11 * 8
+#define R12 12 * 8
+#define R13 13 * 8
+#define R14 14 * 8
+#define R15 15 * 8
+#define R16 16 * 8
+#define R17 17 * 8
+#define R18 18 * 8
+#define R19 19 * 8
+#define R20 20 * 8
+#define R21 21 * 8
+#define R22 22 * 8
+#define R23 23 * 8
+#define R24 24 * 8
+#define R25 25 * 8
+#define R26 26 * 8
+#define R27 27 * 8
+#define R28 28 * 8
+#define R29 29 * 8
+#define R30 30 * 8
+#define R31 31 * 8
+#define NIP 32 * 8
+#define CTR 35 * 8
+#define LINK 36 * 8
+#define XER 37 * 8
+
+.globl perf_regs_load
+perf_regs_load:
+ std 0, R0(3)
+ std 1, R1(3)
+ std 2, R2(3)
+ std 3, R3(3)
+ std 4, R4(3)
+ std 5, R5(3)
+ std 6, R6(3)
+ std 7, R7(3)
+ std 8, R8(3)
+ std 9, R9(3)
+ std 10, R10(3)
+ std 11, R11(3)
+ std 12, R12(3)
+ std 13, R13(3)
+ std 14, R14(3)
+ std 15, R15(3)
+ std 16, R16(3)
+ std 17, R17(3)
+ std 18, R18(3)
+ std 19, R19(3)
+ std 20, R20(3)
+ std 21, R21(3)
+ std 22, R22(3)
+ std 23, R23(3)
+ std 24, R24(3)
+ std 25, R25(3)
+ std 26, R26(3)
+ std 27, R27(3)
+ std 28, R28(3)
+ std 29, R29(3)
+ std 30, R30(3)
+ std 31, R31(3)
+
+ /* store NIP */
+ mflr 4
+ std 4, NIP(3)
+
+ /* Store LR */
+ std 4, LINK(3)
+
+ /* Store XER */
+ mfxer 4
+ std 4, XER(3)
+
+ /* Store CTR */
+ mfctr 4
+ std 4, CTR(3)
+
+ /* Restore original value of r4 */
+ ld 4, R4(3)
+
+ blr
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 35745a733100..ed9d5d15d5b6 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -108,7 +108,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
int i = 0;
map = get_target_map(pev->target, pev->uprobes);
- if (!map || map__load(map, NULL) < 0)
+ if (!map || map__load(map) < 0)
return;
for (i = 0; i < ntevs; i++) {