Merge tag 'perf-core-for-mingo-4.14-20170814' of...

Merge tag 'perf-core-for-mingo-4.14-20170814' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: Infrastructure changes: - Do not consider empty files as valid srclines (Milian Wolff) - Fix wrong size in perf_record_mmap for last kernel module, which resulted in erroneous symbol resolution in at least s390x (Thomas Richter) - Add missing newline to expr parser error messages (Andi Kleen) - Fix saved values rbtree lookup in 'perf stat' (Andi Kleen) - Add support for shell based tests in 'perf test', add a few that run 'perf probe', 'perf trace', using kprobes, uprobes to check the output of those tools and the effects on the system, checking, for instance, DWARF backtraces from uprobes (Arnaldo Carvalho de Melo) Arch specific changes: - Add ppc64le to audit uname list in the python scripting support (Naveen N. Rao) - Update POWER9 vendor events tables (Sukadev Bhattiprolu) - Fix module symbol adjustment for s390x (Thomas Richter) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>

Merge tag 'perf-core-for-mingo-4.14-20170814' of...
Merge tag 'perf-core-for-mingo-4.14-20170814' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: Infrastructure changes: - Do not consider empty files as valid srclines (Milian Wolff) - Fix wrong size in perf_record_mmap for last kernel module, which resulted in erroneous symbol resolution in at least s390x (Thomas Richter) - Add missing newline to expr parser error messages (Andi Kleen) - Fix saved values rbtree lookup in 'perf stat' (Andi Kleen) - Add support for shell based tests in 'perf test', add a few that run 'perf probe', 'perf trace', using kprobes, uprobes to check the output of those tools and the effects on the system, checking, for instance, DWARF backtraces from uprobes (Arnaldo Carvalho de Melo) Arch specific changes: - Add ppc64le to audit uname list in the python scripting support (Naveen N. Rao) - Update POWER9 vendor events tables (Sukadev Bhattiprolu) - Fix module symbol adjustment for s390x (Thomas Richter) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
cf31b7dd · Ingo Molnar · 82119cbe · 8fc375d7 · cf31b7dd · cf31b7dd
Commit cf31b7dd authored Aug 14, 2017 by Ingo Molnar
80 changed files
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -760,7 +760,11 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
-		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+		$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
+		$(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'

 install-bin: install-tools install-tests install-traceevent-plugins


--- a/tools/perf/arch/s390/util/sym-handling.c
+++ b/tools/perf/arch/s390/util/sym-handling.c
@@ -19,4 +19,11 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 	return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN;
 }

+void arch__adjust_sym_map_offset(GElf_Sym *sym,
+				 GElf_Shdr *shdr __maybe_unused,
+				 struct map *map)
+{
+	if (map->type == MAP__FUNCTION)
+		sym->st_value += map->start;
+}
 #endif
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H

+#include <linux/compiler.h>
+struct test;
+
 /* Tests */
-int test__rdpmc(int subtest);
-int test__perf_time_to_tsc(int subtest);
-int test__insn_x86(int subtest);
-int test__intel_cqm_count_nmi_context(int subtest);
+int test__rdpmc(struct test *test __maybe_unused, int subtest);
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
+int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest);

 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;

--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -171,7 +171,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64)
 * verbose (-v) option to see all the instructions and whether or not they
 * decoded successfuly.
 */
-int test__insn_x86(int subtest __maybe_unused)
+int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = 0;


--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -36,7 +36,7 @@ static pid_t spawn(void)
 * the last read counter value to avoid triggering a WARN_ON_ONCE() in
 * smp_call_function_many() caused by sending IPIs from NMI context.
 */
-int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
+int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_evlist *evlist = NULL;
 	struct perf_evsel *evsel = NULL;

--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -37,7 +37,7 @@
 * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
 * supported then then the test passes but " (not supported)" is printed.
 */
-int test__perf_time_to_tsc(int subtest __maybe_unused)
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,

--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -154,7 +154,7 @@ static int __test__rdpmc(void)
 	return 0;
 }

-int test__rdpmc(int subtest __maybe_unused)
+int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int status = 0;
 	int wret = 0;

--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -13,13 +13,13 @@
 #

 # Power8 entries
-004b0000,1,power8.json,core
-004b0201,1,power8.json,core
-004c0000,1,power8.json,core
-004d0000,1,power8.json,core
-004d0100,1,power8.json,core
-004d0200,1,power8.json,core
-004c0100,1,power8.json,core
-004e0100,1,power9.json,core
-004e0200,1,power9.json,core
-004e1200,1,power9.json,core
+004b0000,1,power8,core
+004b0201,1,power8,core
+004c0000,1,power8,core
+004d0000,1,power8,core
+004d0100,1,power8,core
+004d0200,1,power8,core
+004c0100,1,power8,core
+004e0100,1,power9,core
+004e0200,1,power9,core
+004e1200,1,power9,core
--- a/tools/perf/pmu-events/arch/powerpc/power9/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
 [
-  {,
-    "EventCode": "0x10058",
-    "EventName": "PM_MEM_LOC_THRESH_IFU",
-    "BriefDescription": "Local Memory above threshold for IFU speculation control",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x4505E",
-    "EventName": "PM_FLOP_CMPL",
-    "BriefDescription": "Floating Point Operation Finished",
-    "PublicDescription": ""
-  },
  {,
    "EventCode": "0x1415A",
    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC",
-    "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load",
-    "PublicDescription": ""
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load"
  },
  {,
-    "EventCode": "0x2D028",
-    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2",
-    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache",
-    "PublicDescription": ""
+    "EventCode": "0x10058",
+    "EventName": "PM_MEM_LOC_THRESH_IFU",
+    "BriefDescription": "Local Memory above threshold for IFU speculation control"
  },
  {,
-    "EventCode": "0x2D154",
-    "EventName": "PM_MRK_DERAT_MISS_64K",
-    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K",
-    "PublicDescription": ""
+    "EventCode": "0x2D028",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache"
  },
  {,
    "EventCode": "0x30012",
    "EventName": "PM_FLUSH_COMPLETION",
-    "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush",
-    "PublicDescription": ""
+    "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush"
+  },
+  {,
+    "EventCode": "0x2D154",
+    "EventName": "PM_MRK_DERAT_MISS_64K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K"
  },
  {,
    "EventCode": "0x4016E",
    "EventName": "PM_THRESH_NOT_MET",
-    "BriefDescription": "Threshold counter did not meet threshold",
-    "PublicDescription": ""
+    "BriefDescription": "Threshold counter did not meet threshold"
  }
 ]
\ No newline at end of file
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
 [
  {,
-    "EventCode": "0x10008",
-    "EventName": "PM_RUN_SPURR",
-    "BriefDescription": "Run SPURR",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x1000A",
-    "EventName": "PM_PMC3_REWIND",
-    "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change.",
-    "PublicDescription": ""
+    "EventCode": "0x3006E",
+    "EventName": "PM_NEST_REF_CLK",
+    "BriefDescription": "Multiply by 4 to obtain the number of PB cycles"
  },
  {,
-    "EventCode": "0x1C040",
-    "EventName": "PM_DATA_FROM_L2_NO_CONFLICT",
-    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x20010",
+    "EventName": "PM_PMC1_OVERFLOW",
+    "BriefDescription": "Overflow from counter 1"
  },
  {,
-    "EventCode": "0x1C050",
-    "EventName": "PM_DATA_CHIP_PUMP_CPRED",
-    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x2005A",
+    "EventName": "PM_DARQ1_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use"
  },
  {,
-    "EventCode": "0x1D15E",
-    "EventName": "PM_MRK_RUN_CYC",
-    "BriefDescription": "Run cycles in which a marked instruction is in the pipeline",
-    "PublicDescription": ""
+    "EventCode": "0x3C048",
+    "EventName": "PM_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
  },
  {,
-    "EventCode": "0x15158",
-    "EventName": "PM_SYNC_MRK_L2HIT",
-    "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt",
-    "PublicDescription": ""
+    "EventCode": "0x10008",
+    "EventName": "PM_RUN_SPURR",
+    "BriefDescription": "Run SPURR"
  },
  {,
-    "EventCode": "0x20010",
-    "EventName": "PM_PMC1_OVERFLOW",
-    "BriefDescription": "Overflow from counter 1",
-    "PublicDescription": ""
+    "EventCode": "0x200F6",
+    "EventName": "PM_LSU_DERAT_MISS",
+    "BriefDescription": "DERAT Reloaded due to a DERAT miss"
  },
  {,
-    "EventCode": "0x2C040",
-    "EventName": "PM_DATA_FROM_L2_MEPF",
-    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x4C048",
+    "EventName": "PM_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
  },
  {,
-    "EventCode": "0x2005A",
-    "EventName": "PM_DARQ1_7_9_ENTRIES",
-    "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use",
-    "PublicDescription": ""
+    "EventCode": "0x1D15E",
+    "EventName": "PM_MRK_RUN_CYC",
+    "BriefDescription": "Run cycles in which a marked instruction is in the pipeline"
  },
  {,
-    "EventCode": "0x2C05C",
-    "EventName": "PM_INST_GRP_PUMP_CPRED",
-    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)",
-    "PublicDescription": ""
+    "EventCode": "0x4003E",
+    "EventName": "PM_LD_CMPL",
+    "BriefDescription": "count of Loads completed"
  },
  {,
    "EventCode": "0x2D156",
    "EventName": "PM_MRK_DTLB_MISS_4K",
-    "BriefDescription": "Marked Data TLB Miss page size 4k",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x2E05A",
-    "EventName": "PM_LRQ_REJECT",
-    "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects",
-    "PublicDescription": ""
+    "BriefDescription": "Marked Data TLB Miss page size 4k"
  },
  {,
-    "EventCode": "0x2E05C",
-    "EventName": "PM_LSU_REJECT_ERAT_MISS",
-    "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)",
-    "PublicDescription": ""
+    "EventCode": "0x4C042",
+    "EventName": "PM_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load"
  },
  {,
-    "EventCode": "0x200F6",
-    "EventName": "PM_LSU_DERAT_MISS",
-    "BriefDescription": "DERAT Reloaded due to a DERAT miss",
-    "PublicDescription": ""
+    "EventCode": "0x4D02C",
+    "EventName": "PM_PMC1_REWIND",
+    "BriefDescription": ""
  },
  {,
-    "EventCode": "0x3C048",
-    "EventName": "PM_DATA_FROM_DL2L3_SHR",
-    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x15158",
+    "EventName": "PM_SYNC_MRK_L2HIT",
+    "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt"
  },
  {,
    "EventCode": "0x3404A",
    "EventName": "PM_INST_FROM_RMEM",
-    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)",
-    "PublicDescription": ""
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)"
  },
  {,
-    "EventCode": "0x3C058",
-    "EventName": "PM_LARX_FIN",
-    "BriefDescription": "Larx finished",
-    "PublicDescription": ""
+    "EventCode": "0x301E2",
+    "EventName": "PM_MRK_ST_CMPL",
+    "BriefDescription": "Marked store completed and sent to nest"
  },
  {,
-    "EventCode": "0x3E050",
-    "EventName": "PM_DARQ1_4_6_ENTRIES",
-    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use",
-    "PublicDescription": ""
+    "EventCode": "0x1C050",
+    "EventName": "PM_DATA_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load"
  },
  {,
-    "EventCode": "0x3006E",
-    "EventName": "PM_NEST_REF_CLK",
-    "BriefDescription": "Multiply by 4 to obtain the number of PB cycles",
-    "PublicDescription": ""
+    "EventCode": "0x4C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load"
  },
  {,
-    "EventCode": "0x301E2",
-    "EventName": "PM_MRK_ST_CMPL",
-    "BriefDescription": "Marked store completed and sent to nest",
-    "PublicDescription": ""
+    "EventCode": "0x2E05C",
+    "EventName": "PM_LSU_REJECT_ERAT_MISS",
+    "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)"
  },
  {,
-    "EventCode": "0x4D02C",
-    "EventName": "PM_PMC1_REWIND",
-    "BriefDescription": "",
-    "PublicDescription": ""
+    "EventCode": "0x1000A",
+    "EventName": "PM_PMC3_REWIND",
+    "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change."
  },
  {,
-    "EventCode": "0x4003E",
-    "EventName": "PM_LD_CMPL",
-    "BriefDescription": "count of Loads completed",
-    "PublicDescription": ""
+    "EventCode": "0x3C058",
+    "EventName": "PM_LARX_FIN",
+    "BriefDescription": "Larx finished"
  },
  {,
-    "EventCode": "0x4C040",
-    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER",
-    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x1C040",
+    "EventName": "PM_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load"
  },
  {,
-    "EventCode": "0x4C042",
-    "EventName": "PM_DATA_FROM_L3",
-    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x2C040",
+    "EventName": "PM_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load"
  },
  {,
-    "EventCode": "0x4C048",
-    "EventName": "PM_DATA_FROM_DL2L3_MOD",
-    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load",
-    "PublicDescription": ""
+    "EventCode": "0x2E05A",
+    "EventName": "PM_LRQ_REJECT",
+    "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects"
+  },
+  {,
+    "EventCode": "0x2C05C",
+    "EventName": "PM_INST_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)"
  },
  {,
    "EventCode": "0x4D056",
    "EventName": "PM_NON_FMA_FLOP_CMPL",
-    "BriefDescription": "Non FMA instruction completed",
-    "PublicDescription": ""
+    "BriefDescription": "Non FMA instruction completed"
+  },
+  {,
+    "EventCode": "0x3E050",
+    "EventName": "PM_DARQ1_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use"
  }
 ]
\ No newline at end of file
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
--- a/tools/perf/pmu-events/arch/powerpc/power9/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -57,6 +57,7 @@ try:
 		'ia64'	: audit.MACH_IA64,
 		'ppc'	: audit.MACH_PPC,
 		'ppc64'	: audit.MACH_PPC64,
+		'ppc64le' : audit.MACH_PPC64LE,
 		's390'	: audit.MACH_S390,
 		's390x'	: audit.MACH_S390X,
 		'i386'	: audit.MACH_X86,

--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -169,7 +169,7 @@ static int run_dir(const char *d, const char *perf)
 	return system(cmd);
 }

-int test__attr(int subtest __maybe_unused)
+int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct stat st;
 	char path_perf[PATH_MAX];

--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -75,7 +75,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 }


-int test__backward_ring_buffer(int subtest __maybe_unused)
+int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0;
 	char pid[16], sbuf[STRERR_BUFSIZE];

--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -40,7 +40,7 @@ static int test_bitmap(const char *str)
 	return ret;
 }

-int test__bitmap_print(int subtest __maybe_unused)
+int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
 	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));

--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -164,7 +164,7 @@ static long long bp_count(int fd)
 	return count;
 }

-int test__bp_signal(int subtest __maybe_unused)
+int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct sigaction sa;
 	long long count1, count2, count3;

--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -57,7 +57,7 @@ static long long bp_count(int fd)
 #define EXECUTIONS 10000
 #define THRESHOLD  100

-int test__bp_signal_overflow(int subtest __maybe_unused)
+int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_event_attr pe;
 	struct sigaction sa;

--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -321,7 +321,7 @@ static int check_env(void)
 	return 0;
 }

-int test__bpf(int i)
+int test__bpf(struct test *test __maybe_unused, int i)
 {
 	int err;

@@ -351,7 +351,7 @@ const char *test__bpf_subtest_get_desc(int i __maybe_unused)
 	return NULL;
 }

-int test__bpf(int i __maybe_unused)
+int test__bpf(struct test *test __maybe_unused, int i __maybe_unused)
 {
 	pr_debug("Skip BPF test because BPF support is not compiled\n");
 	return TEST_SKIP;

--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -6,7 +6,10 @@
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <sys/types.h>
+#include <dirent.h>
 #include <sys/wait.h>
+#include <sys/stat.h>
 #include "builtin.h"
 #include "hist.h"
 #include "intlist.h"
@@ -14,8 +17,10 @@
 #include "debug.h"
 #include "color.h"
 #include <subcmd/parse-options.h>
+#include "string2.h"
 #include "symbol.h"
 #include <linux/kernel.h>
+#include <subcmd/exec-cmd.h>

 static bool dont_fork;

@@ -179,7 +184,7 @@ static struct test generic_tests[] = {
 	},
 	{
 		.desc = "Session topology",
-		.func = test_session_topology,
+		.func = test__session_topology,
 	},
 	{
 		.desc = "BPF filter",
@@ -325,7 +330,7 @@ static int run_test(struct test *test, int subtest)
 			}
 		}

-		err = test->func(subtest);
+		err = test->func(test, subtest);
 		if (!dont_fork)
 			exit(err);
 	}
@@ -383,12 +388,143 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	return err;
 }

+static const char *shell_test__description(char *description, size_t size,
+					   const char *path, const char *name)
+{
+	FILE *fp;
+	char filename[PATH_MAX];
+
+	path__join(filename, sizeof(filename), path, name);
+	fp = fopen(filename, "r");
+	if (!fp)
+		return NULL;
+
+	description = fgets(description, size, fp);
+	fclose(fp);
+
+	return description ? trim(description + 1) : NULL;
+}
+
+#define for_each_shell_test(dir, ent)		\
+	while ((ent = readdir(dir)) != NULL)	\
+		if (ent->d_type == DT_REG && ent->d_name[0] != '.')
+
+static const char *shell_tests__dir(char *path, size_t size)
+{
+	const char *devel_dirs[] = { "./tools/perf/tests", "./tests", };
+        char *exec_path;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
+		struct stat st;
+		if (!lstat(devel_dirs[i], &st)) {
+			scnprintf(path, size, "%s/shell", devel_dirs[i]);
+			if (!lstat(devel_dirs[i], &st))
+				return path;
+		}
+	}
+
+        /* Then installed path. */
+        exec_path = get_argv_exec_path();
+        scnprintf(path, size, "%s/tests/shell", exec_path);
+	free(exec_path);
+	return path;
+}
+
+static int shell_tests__max_desc_width(void)
+{
+	DIR *dir;
+	struct dirent *ent;
+	char path_dir[PATH_MAX];
+	const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+	int width = 0;
+
+	if (path == NULL)
+		return -1;
+
+	dir = opendir(path);
+	if (!dir)
+		return -1;
+
+	for_each_shell_test(dir, ent) {
+		char bf[256];
+		const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name);
+
+		if (desc) {
+			int len = strlen(desc);
+
+			if (width < len)
+				width = len;
+		}
+	}
+
+	closedir(dir);
+	return width;
+}
+
+struct shell_test {
+	const char *dir;
+	const char *file;
+};
+
+static int shell_test__run(struct test *test, int subdir __maybe_unused)
+{
+	int err;
+	char script[PATH_MAX];
+	struct shell_test *st = test->priv;
+
+	path__join(script, sizeof(script), st->dir, st->file);
+
+	err = system(script);
+	if (!err)
+		return TEST_OK;
+
+	return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL;
+}
+
+static int run_shell_tests(int argc, const char *argv[], int i, int width)
+{
+	DIR *dir;
+	struct dirent *ent;
+	char path_dir[PATH_MAX];
+	struct shell_test st = {
+		.dir = shell_tests__dir(path_dir, sizeof(path_dir)),
+	};
+
+	if (st.dir == NULL)
+		return -1;
+
+	dir = opendir(st.dir);
+	if (!dir)
+		return -1;
+
+	for_each_shell_test(dir, ent) {
+		int curr = i++;
+		char desc[256];
+		struct test test = {
+			.desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name),
+			.func = shell_test__run,
+			.priv = &st,
+		};
+
+		if (!perf_test__matches(&test, curr, argc, argv))
+			continue;
+
+		st.file = ent->d_name;
+		pr_info("%2d: %-*s:", i, width, test.desc);
+		test_and_print(&test, false, -1);
+	}
+
+	closedir(dir);
+	return 0;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	struct test *t;
 	unsigned int j;
 	int i = 0;
-	int width = 0;
+	int width = shell_tests__max_desc_width();

 	for_each_test(j, t) {
 		int len = strlen(t->desc);
@@ -455,6 +591,37 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 	}

+	return run_shell_tests(argc, argv, i, width);
+}
+
+static int perf_test__list_shell(int argc, const char **argv, int i)
+{
+	DIR *dir;
+	struct dirent *ent;
+	char path_dir[PATH_MAX];
+	const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+
+	if (path == NULL)
+		return -1;
+
+	dir = opendir(path);
+	if (!dir)
+		return -1;
+
+	for_each_shell_test(dir, ent) {
+		int curr = i++;
+		char bf[256];
+		struct test t = {
+			.desc = shell_test__description(bf, sizeof(bf), path, ent->d_name),
+		};
+
+		if (!perf_test__matches(&t, curr, argc, argv))
+			continue;
+
+		pr_info("%2d: %s\n", i, t.desc);
+	}
+
+	closedir(dir);
 	return 0;
 }

@@ -465,12 +632,17 @@ static int perf_test__list(int argc, const char **argv)
 	int i = 0;

 	for_each_test(j, t) {
-		if (argc > 1 && !strstr(t->desc, argv[1]))
+		int curr = i++;
+
+		if (!perf_test__matches(t, curr, argc, argv) ||
+		    (t->is_supported && !t->is_supported()))
 			continue;

-		pr_info("%2d: %s\n", ++i, t->desc);
+		pr_info("%2d: %s\n", i, t->desc);
 	}

+	perf_test__list_shell(argc, argv, i);
+
 	return 0;
 }

@@ -498,7 +670,7 @@ int cmd_test(int argc, const char **argv)

 	argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
 	if (argc >= 1 && !strcmp(argv[0], "list"))
-		return perf_test__list(argc, argv);
+		return perf_test__list(argc - 1, argv + 1);

 	symbol_conf.priv_size = sizeof(int);
 	symbol_conf.sort_by_name = true;

--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -33,12 +33,12 @@ const char *test__clang_subtest_get_desc(int i)
 }

 #ifndef HAVE_LIBCLANGLLVM_SUPPORT
-int test__clang(int i __maybe_unused)
+int test__clang(struct test *test __maybe_unused, int i __maybe_unused)
 {
 	return TEST_SKIP;
 }
 #else
-int test__clang(int i)
+int test__clang(struct test *test __maybe_unused, int i)
 {
 	if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table))
 		return TEST_FAIL;

--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -673,7 +673,7 @@ static int do_test_code_reading(bool try_kcore)
 	return err;
 }

-int test__code_reading(int subtest __maybe_unused)
+int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret;


--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -72,7 +72,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 }


-int test__cpu_map_synthesize(int subtest __maybe_unused)
+int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct cpu_map *cpus;

@@ -106,7 +106,7 @@ static int cpu_map_print(const char *str)
 	return !strcmp(buf, str);
 }

-int test__cpu_map_print(int subtest __maybe_unused)
+int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));

--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -112,7 +112,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine)
 	return fd;
 }

-int test__dso_data(int subtest __maybe_unused)
+int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	struct dso *dso;
@@ -247,7 +247,7 @@ static int set_fd_limit(int n)
 	return setrlimit(RLIMIT_NOFILE, &rlim);
 }

-int test__dso_data_cache(int subtest __maybe_unused)
+int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt();
@@ -307,7 +307,7 @@ int test__dso_data_cache(int subtest __maybe_unused)
 	return 0;
 }

-int test__dso_data_reopen(int subtest __maybe_unused)
+int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt();

--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -154,7 +154,7 @@ static noinline int krava_1(struct thread *thread)
 	return krava_2(thread);
 }

-int test__dwarf_unwind(int subtest __maybe_unused)
+int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine *machine;
 	struct thread *thread;

--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -213,7 +213,7 @@ static int test_times(int (attach)(struct perf_evlist *),
 * and checks that enabled and running times
 * match.
 */
-int test__event_times(int subtest __maybe_unused)
+int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err, ret = 0;


--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -76,7 +76,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 	return 0;
 }

-int test__event_update(int subtest __maybe_unused)
+int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel;

--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -97,7 +97,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
 #define perf_evsel__name_array_test(names) \
 	__perf_evsel__name_array_test(names, ARRAY_SIZE(names))

-int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
+int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = 0, ret = 0;


--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 	return ret;
 }

-int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
+int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
 	int ret = 0;

--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -13,7 +13,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2)
 	return 0;
 }

-int test__expr(int subtest __maybe_unused)
+int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
 	const char *p;
 	const char **other;

--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -26,7 +26,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 	return printed + fdarray__fprintf(fda, fp);
 }

-int test__fdarray__filter(int subtest __maybe_unused)
+int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(5, 5);
@@ -104,7 +104,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 	return err;
 }

-int test__fdarray__add(int subtest __maybe_unused)
+int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(2, 2);

--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -687,7 +687,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	return err;
 }

-int test__hists_cumulate(int subtest __maybe_unused)
+int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;

--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -101,7 +101,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 	return TEST_FAIL;
 }

-int test__hists_filter(int subtest __maybe_unused)
+int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;

--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other)
 	return __validate_link(leader, 0) || __validate_link(other, 1);
 }

-int test__hists_link(int subtest __maybe_unused)
+int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	struct hists *hists, *first_hists;

--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -573,7 +573,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 	return err;
 }

-int test__hists_output(int subtest __maybe_unused)
+int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;

--- a/tools/perf/tests/is_printable_array.c
+++ b/tools/perf/tests/is_printable_array.c
@@ -4,7 +4,7 @@
 #include "debug.h"
 #include "print_binary.h"

-int test__is_printable_array(int subtest __maybe_unused)
+int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
 	char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };

--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -49,7 +49,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
 * when an event is disabled but a dummy software event is not disabled.  If the
 * test passes %0 is returned, otherwise %-1 is returned.
 */
-int test__keep_tracking(int subtest __maybe_unused)
+int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,

--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -50,7 +50,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 #define M(path, c, e) \
 	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))

-int test__kmod_path__parse(int subtest __maybe_unused)
+int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
 	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
 	T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);

--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -132,7 +132,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 	return ret;
 }

-int test__llvm(int subtest)
+int test__llvm(struct test *test __maybe_unused, int subtest)
 {
 	int ret;
 	void *obj_buf = NULL;

--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -22,7 +22,7 @@
 * Then it checks if the number of syscalls reported as perf events by
 * the kernel corresponds to the number of syscalls made.
 */
-int test__basic_mmap(int subtest __maybe_unused)
+int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;

--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -221,7 +221,7 @@ static int mmap_events(synth_cb synth)
 *
 * by using all thread objects.
 */
-int test__mmap_thread_lookup(int subtest __maybe_unused)
+int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	/* perf_event__synthesize_threads synthesize */
 	TEST_ASSERT_VAL("failed with sythesizing all",

--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -16,7 +16,7 @@
 #include "debug.h"
 #include "stat.h"

-int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
+int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1, fd, cpu;
 	struct cpu_map *cpus;

--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -14,7 +14,7 @@
 #define AT_FDCWD       -100
 #endif

-int test__syscall_openat_tp_fields(int subtest __maybe_unused)
+int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {

--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -10,7 +10,7 @@
 #include "debug.h"
 #include "tests.h"

-int test__openat_syscall_event(int subtest __maybe_unused)
+int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1, fd;
 	struct perf_evsel *evsel;

--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1810,7 +1810,7 @@ static int test_pmu_events(void)
 	return ret;
 }

-int test__parse_events(int subtest __maybe_unused)
+int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret1, ret2 = 0;


--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -68,7 +68,7 @@ struct test_attr_event {
 *
 * Return: %0 on success, %-1 if the test fails.
 */
-int test__parse_no_sample_id_all(int subtest __maybe_unused)
+int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err;


--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -27,7 +27,7 @@ static void the_hook(void *_hook_flags)
 	*p = 0;
 }

-int test__perf_hooks(int subtest __maybe_unused)
+int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int hook_flags = 0;


--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -37,7 +37,7 @@ static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
 	return cpu;
 }

-int test__PERF_RECORD(int subtest __maybe_unused)
+int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {

--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -135,7 +135,7 @@ static struct list_head *test_terms_list(void)
 	return &terms;
 }

-int test__pmu(int subtest __maybe_unused)
+int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	char *format = test_format_dir_get();
 	LIST_HEAD(formats);

--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -9,7 +9,7 @@

 extern int verbose;

-int test__python_use(int subtest __maybe_unused)
+int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	char *cmd;
 	int ret;

--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -292,7 +292,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 * checks sample format bits separately and together.  If the test passes %0 is
 * returned, otherwise %-1 is returned.
 */
-int test__sample_parsing(int subtest __maybe_unused)
+int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;

--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -71,7 +71,7 @@ static int search_cached_probe(const char *target,
 	return ret;
 }

-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
 	int ret = TEST_FAIL;
 	char __tempdir[] = "./test-buildid-XXXXXX";
@@ -109,7 +109,7 @@ int test__sdt_event(int subtests __maybe_unused)
 	return ret;
 }
 #else
-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
 	pr_debug("Skip SDT event test because SDT support is not compiled\n");
 	return TEST_SKIP;

--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+perf probe -l | grep -q probe:vfs_getname
+had_vfs_getname=$?
+
+cleanup_probe_vfs_getname() {
+	if [ $had_vfs_getname -eq 1 ] ; then
+		perf probe -q -d probe:vfs_getname
+	fi
+}
+
+add_probe_vfs_getname() {
+	local verbose=$1
+	if [ $had_vfs_getname -eq 1 ] ; then
+               line=$(perf probe -L getname_flags | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
+               perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+	fi
+}
+
+skip_if_no_debuginfo() {
+	add_probe_vfs_getname -v 2>&1 | grep -q "^Failed to find the path for kernel" && return 2
+	return 1
+}
+
+skip_if_no_debuginfo() {
+	add_probe_vfs_getname -v 2>&1 | grep -q "^Failed to find the path for kernel" && return 2
+	return 1
+}
--- a/tools/perf/tests/shell/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
+# Add vfs_getname probe to get syscall args filenames
+#
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+cleanup_probe_vfs_getname
+exit $err
--- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
+# Use vfs_getname probe to get syscall args filenames
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf record' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname probe in the generated
+# perf.data file, with the temp file name as the pathname argument.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+record_open_file() {
+	echo "Recording open file:"
+	perf record -o ${perfdata} -e probe:vfs_getname touch $file
+}
+
+perf_script_filenames() {
+	echo "Looking at perf.data file for vfs_getname records for the file we touched:"
+	perf script -i ${perfdata} | \
+	egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname: +\([[:xdigit:]]+\) +pathname=\"${file}\""
+}
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+	exit $err
+fi
+
+record_open_file && perf_script_filenames
+err=$?
+rm -f ${perfdata}
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+# probe libc's inet_pton & backtrace it with ping
+
+# Installs a probe on libc's inet_pton function, that will use uprobes,
+# then use 'perf trace' on a ping to localhost asking for just one packet
+# with the a backtrace 3 levels deep, check that it is what we expect.
+# This needs no debuginfo package, all is done using the libc ELF symtab
+# and the CFI info in the binaries.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+trace_libc_inet_pton_backtrace() {
+	idx=0
+	expected[0]="PING.*bytes"
+	expected[1]="64 bytes from ::1.*"
+	expected[2]=".*ping statistics.*"
+	expected[3]=".*packets transmitted.*"
+	expected[4]="rtt min.*"
+	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
+	expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+	expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+	expected[8]=".*\(.*/bin/ping.*\)$"
+
+	perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 |& grep -v ^$ | while read line ; do
+		echo $line
+		echo "$line" | egrep -q "${expected[$idx]}"
+		if [ $? -ne 0 ] ; then
+			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+			exit 1
+		fi
+		let idx+=1
+		[ $idx -eq 9 ] && break
+	done
+}
+
+perf probe -q /lib64/libc-*.so inet_pton && \
+trace_libc_inet_pton_backtrace
+err=$?
+rm -f ${file}
+perf probe -q -d probe_libc:inet_pton
+exit $err
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+# Check open filename arg using perf trace + vfs_getname
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf trace' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname was used by 'perf trace',
+# that already handles "probe:vfs_getname" if present, and used in the
+# "open" syscall "filename" argument beautifier.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+trace_open_vfs_getname() {
+	perf trace -e open touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+}
+
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+	exit $err
+fi
+
+trace_open_vfs_getname
+err=$?
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -45,7 +45,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }

-int test__synthesize_stat_config(int subtest __maybe_unused)
+int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_stat_config stat_config = {
 		.aggr_mode	= AGGR_CORE,
@@ -75,7 +75,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }

-int test__synthesize_stat(int subtest __maybe_unused)
+int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_counts_values count;

@@ -101,7 +101,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }

-int test__synthesize_stat_round(int subtest __maybe_unused)
+int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to synthesize stat_config",
 		!perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,

--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -124,7 +124,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	return err;
 }

-int test__sw_clock_freq(int subtest __maybe_unused)
+int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret;


--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -306,7 +306,7 @@ static int process_events(struct perf_evlist *evlist,
 * evsel->system_wide and evsel->tracking flags (respectively) with other events
 * sometimes enabled or disabled.
 */
-int test__switch_tracking(int subtest __maybe_unused)
+int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	const char *sched_switch = "sched:sched_switch";
 	struct switch_tracking switch_tracking = { .tids = NULL, };

--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -32,7 +32,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 * if the number of exit event reported by the kernel is 1 or not
 * in order to check the kernel returns correct number of event.
 */
-int test__task_exit(int subtest __maybe_unused)
+int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;

--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -9,7 +9,7 @@
 #define NAME	(const char *) "perf"
 #define NAMEUL	(unsigned long) NAME

-int test__thread_map(int subtest __maybe_unused)
+int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct thread_map *map;

@@ -76,7 +76,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }

-int test__thread_map_synthesize(int subtest __maybe_unused)
+int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct thread_map *threads;

@@ -95,7 +95,7 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
 	return 0;
 }

-int test__thread_map_remove(int subtest __maybe_unused)
+int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct thread_map *threads;
 	char *str;

--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -4,7 +4,7 @@
 #include "map.h"
 #include "debug.h"

-int test__thread_mg_share(int subtest __maybe_unused)
+int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machines machines;
 	struct machine *machine;

--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -86,7 +86,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
 	return 0;
 }

-int test_session_topology(int subtest __maybe_unused)
+int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	char path[PATH_MAX];
 	struct cpu_map *map;

--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -5,7 +5,7 @@
 #include "units.h"
 #include "debug.h"

-int test__unit_number__scnprint(int subtest __maybe_unused)
+int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
 	struct {
 		u64		 n;

--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -11,7 +11,7 @@

 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))

-int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
+int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	struct rb_node *nd;

--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -62,7 +62,7 @@ all_expr: expr			{ *final_val = $1; }

 expr:	  NUMBER
 	| ID			{ if (lookup_id(ctx, $1, &$$) < 0) {
-					pr_debug("%s not found", $1);
+					pr_debug("%s not found\n", $1);
 					YYABORT;
 				  }
 				}

--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1138,7 +1138,8 @@ int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
 	return 0;
 }

-static int machine__create_module(void *arg, const char *name, u64 start)
+static int machine__create_module(void *arg, const char *name, u64 start,
+				  u64 size)
 {
 	struct machine *machine = arg;
 	struct map *map;
@@ -1149,6 +1150,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
 	map = machine__findnew_module_map(machine, start, name);
 	if (map == NULL)
 		return -1;
+	map->end = start + size;

 	dso__kernel_module_get_build_id(map->dso, machine->root_dir);


--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h