Merge tag 'perf-core-for-mingo-4.18-20180516' 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:

- Add '-e intel_pt//u' test to the 'parse-events' 'perf test' entry,
  to help avoiding regressions in the events parser such as one
  that caused a revert in v4.17-rc (Arnaldo Carvalho de Melo)

- Fix NULL return handling in bpf__prepare_load() (YueHaibing)

- Warn about 'perf buildid-cache --purge-all' failures (Ravi Bangoria)

- Add infrastructure to help in writing eBPF C programs to be used
  with '-e name.c' type events in tools such as 'record' and 'trace',
  with headers for common constructs and an examples directory that
  will get populated as we add more such helpers and the 'perf bpf'
  branch that Jiri Olsa has been working on (Arnaldo Carvalho de Melo)

- Handle uncore event aliases in small groups properly (Kan Liang)

- Use the "_stest" symbol to identify the kernel map when loading kcore (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

31 files changed, 347 insertions, 50 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 2ba95d6fe852..caae4843cb70 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -195,6 +195,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_VFP_FPINST          0x1009
 #define KVM_REG_ARM_VFP_FPINST2         0x100A
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW                  (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)           (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+                                         KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION        KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR       0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS  1
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9abbf3044654..04b3256f8e6d 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_TIMER_CNT           ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL          ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW                  (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)           (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+                                         KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION        KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR       0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS  1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d554c11e01ff..578793e97431 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -320,6 +320,7 @@
 #define X86_FEATURE_AVX512_VPOPCNTDQ    (16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57                (16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID               (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE            (16*32+25) /* CLDEMOTE instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV      (17*32+ 0) /* MCA overflow recovery support */
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 1ea545965ee3..53b60ad452f5 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -76,6 +76,8 @@ $(OUTPUT)bpf_asm: $(OUTPUT)bpf_asm.o $(OUTPUT)bpf_exp.yacc.o $(OUTPUT)bpf_exp.le
         $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^
 
 $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
 clean: bpftool_clean
         $(call QUIET_CLEAN, bpf-progs)
diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bcc4423..61b9aa5d6415 100644
--- a/tools/bpf/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
@@ -1063,7 +1063,7 @@ static int cmd_load_pcap(char *file)
 
 static int cmd_load(char *arg)
 {
-        char *subcmd, *cont, *tmp = strdup(arg);
+        char *subcmd, *cont = NULL, *tmp = strdup(arg);
         int ret = CMD_OK;
 
         subcmd = strtok_r(tmp, " ", &cont);
@@ -1073,7 +1073,10 @@ static int cmd_load(char *arg)
                 bpf_reset();
                 bpf_reset_breakpoints();
 
-                ret = cmd_load_bpf(cont);
+                if (!cont)
+                        ret = CMD_ERR;
+                else
+                        ret = cmd_load_bpf(cont);
         } else if (matches(subcmd, "pcap") == 0) {
                 ret = cmd_load_pcap(cont);
         } else {
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 1065006c9bf5..b02c41e53d56 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -676,6 +676,13 @@ struct kvm_ioeventfd {
         __u8  pad[36];
 };
 
+#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
+                                              KVM_X86_DISABLE_EXITS_HTL | \
+                                              KVM_X86_DISABLE_EXITS_PAUSE)
+
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
         /* in */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index ae7dc46e8f8a..b5ac356ba323 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -885,6 +885,8 @@ endif
 
 # Among the variables below, these:
 #   perfexecdir
+#   perf_include_dir
+#   perf_examples_dir
 #   template_dir
 #   mandir
 #   infodir
@@ -904,6 +906,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
+perf_include_dir = lib/include/perf
+perf_examples_dir = lib/examples/perf
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
@@ -934,6 +938,8 @@ bindir_SQ = $(subst ','\'',$(bindir))
 mandir_SQ = $(subst ','\'',$(mandir))
 infodir_SQ = $(subst ','\'',$(infodir))
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir))
+perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir))
 template_dir_SQ = $(subst ','\'',$(template_dir))
 htmldir_SQ = $(subst ','\'',$(htmldir))
 tipdir_SQ = $(subst ','\'',$(tipdir))
@@ -944,14 +950,20 @@ srcdir_SQ = $(subst ','\'',$(srcdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
+perf_include_instdir = $(perf_include_dir)
+perf_examples_instdir = $(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
 tip_instdir = $(tipdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
+perf_include_instdir = $(prefix)/$(perf_include_dir)
+perf_examples_instdir = $(prefix)/$(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
 tip_instdir = $(prefix)/$(tipdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir))
+perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir))
 STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
 tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
@@ -999,6 +1011,8 @@ $(call detected_var,ETC_PERFCONFIG_SQ)
 $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
+$(call detected_var,perf_include_dir_SQ)
+$(call detected_var,perf_examples_dir_SQ)
 $(call detected_var,tipdir_SQ)
 $(call detected_var,srcdir_SQ)
 $(call detected_var,LIBDIR)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 83e453de36f8..c63a3971d719 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -767,6 +767,14 @@ ifndef NO_JVMTI
 endif
         $(call QUIET_INSTALL, libexec) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBBPF
+        $(call QUIET_INSTALL, lib) \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+                $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+        $(call QUIET_INSTALL, lib) \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+                $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+endif
         $(call QUIET_INSTALL, perf-archive) \
                 $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(call QUIET_INSTALL, perf-with-kcore) \
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 944070e98a2c..63eb49082774 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -175,7 +175,7 @@ static const struct option options[] = {
         OPT_UINTEGER('s', "nr_secs"     , &p0.nr_secs,          "max number of seconds to run (default: 5 secs)"),
         OPT_UINTEGER('u', "usleep"      , &p0.sleep_usecs,      "usecs to sleep per loop iteration"),
 
-        OPT_BOOLEAN('R', "data_reads"   , &p0.data_reads,       "access the data via writes (can be mixed with -W)"),
+        OPT_BOOLEAN('R', "data_reads"   , &p0.data_reads,       "access the data via reads (can be mixed with -W)"),
         OPT_BOOLEAN('W', "data_writes"  , &p0.data_writes,      "access the data via writes (can be mixed with -R)"),
         OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards,  "access the data backwards as well"),
         OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 7a7403913b57..115110a4796a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -488,8 +488,12 @@ int cmd_buildid_cache(int argc, const char **argv)
                 }
         }
 
-        if (purge_all)
-                ret = build_id_cache__purge_all();
+        if (purge_all) {
+                if (build_id_cache__purge_all()) {
+                        pr_warning("Couldn't remove some caches. Error: %s.\n",
+                                str_error_r(errno, sbuf, sizeof(sbuf)));
+                }
+        }
 
         if (missing_filename)
                 ret = build_id_cache__fprintf_missing(session, stdout);
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
new file mode 100644
index 000000000000..b9c203219691
--- /dev/null
+++ b/tools/perf/examples/bpf/5sec.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+    Description:
+
+    . Disable strace like syscall tracing (--no-syscalls), or try tracing
+      just some (-e *sleep).
+
+    . Attach a filter function to a kernel function, returning when it should
+      be considered, i.e. appear on the output.
+
+    . Run it system wide, so that any sleep of >= 5 seconds and < than 6
+      seconds gets caught.
+
+    . Ask for callgraphs using DWARF info, so that userspace can be unwound
+
+    . While this is running, run something like "sleep 5s".
+
+    . If we decide to add tv_nsec as well, then it becomes:
+
+      int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
+
+      I.e. add where it comes from (rqtp->tv_nsec) and where it will be
+      accessible in the function body (nsec)
+
+    # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
+         0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
+                                           hrtimer_nanosleep ([kernel.kallsyms])
+                                           __x64_sys_nanosleep ([kernel.kallsyms])
+                                           do_syscall_64 ([kernel.kallsyms])
+                                           entry_SYSCALL_64 ([kernel.kallsyms])
+                                           __GI___nanosleep (/usr/lib64/libc-2.26.so)
+                                           rpl_nanosleep (/usr/bin/sleep)
+                                           xnanosleep (/usr/bin/sleep)
+                                           main (/usr/bin/sleep)
+                                           __libc_start_main (/usr/lib64/libc-2.26.so)
+                                           _start (/usr/bin/sleep)
+    ^C#
+
+   Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
+*/
+
+#include <bpf.h>
+
+int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+{
+        return sec == 5;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
new file mode 100644
index 000000000000..3776d26db9e7
--- /dev/null
+++ b/tools/perf/examples/bpf/empty.c
@@ -0,0 +1,3 @@
+#include <bpf.h>
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
new file mode 100644
index 000000000000..dd764ad5efdf
--- /dev/null
+++ b/tools/perf/include/bpf/bpf.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _PERF_BPF_H
+#define _PERF_BPF_H
+#define SEC(NAME) __attribute__((section(NAME),  used))
+
+#define probe(function, vars) \
+        SEC(#function "=" #function " " #vars) function
+
+#define license(name) \
+char _license[] SEC("license") = #name; \
+int _version SEC("version") = LINUX_VERSION_CODE;
+
+#endif /* _PERF_BPF_H */
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 93656f2fd53a..7e3cce3bcf3b 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
 GenuineIntel-6-2A,v15,sandybridge,core
 GenuineIntel-6-2C,v2,westmereep-dp,core
-GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
 GenuineIntel-6-55,v1,skylakex,core
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 18b06444f230..6829dd416a99 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,14 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
         return 0;
 }
 
+static int test__intel_pt(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0);
+        return 0;
+}
+
 static int count_tracepoints(void)
 {
         struct dirent *events_ent;
@@ -1637,6 +1645,11 @@ static struct evlist_test test__events[] = {
                 .check = test__checkevent_config_cache,
                 .id    = 51,
         },
+        {
+                .name  = "intel_pt//u",
+                .check = test__intel_pt,
+                .id    = 52,
+        },
 };
 
 static struct evlist_test test__events_pmu[] = {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 016882dbbc16..ee86473643be 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -16,7 +16,7 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 trace_libc_inet_pton_backtrace() {
         idx=0
         expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-        expected[1]=".*inet_pton[[:space:]]\($libc\)$"
+        expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$"
         case "$(uname -m)" in
         s390x)
                 eventattr='call-graph=dwarf,max-stack=4'
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8052373bcd6a..5d4c45b76895 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -152,6 +152,8 @@ libperf-y += perf-hooks.o
 libperf-$(CONFIG_CXX) += c++/
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
+
 # avoid compiler warnings in 32-bit mode
 CFLAGS_genelf_debug.o  += -Wno-packed
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 536ee148bff8..5d74a30fe00f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1263,6 +1263,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
                                 max_percent = sample->percent;
                 }
 
+                if (al->samples_nr > nr_percent)
+                        nr_percent = al->samples_nr;
+
                 if (max_percent < min_pcnt)
                         return -1;
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index af7ad814b2c3..cee658733e2c 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
         }
 
         obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
-        if (IS_ERR(obj)) {
+        if (IS_ERR_OR_NULL(obj)) {
                 pr_debug("bpf: failed to load buffer\n");
                 return ERR_PTR(-EINVAL);
         }
@@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
                         pr_debug("bpf: successfull builtin compilation\n");
                 obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 
-                if (!IS_ERR(obj) && llvm_param.dump_obj)
+                if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
                         llvm__dump_obj(filename, obj_buf, obj_buf_sz);
 
                 free(obj_buf);
         } else
                 obj = bpf_object__open(filename);
 
-        if (IS_ERR(obj)) {
+        if (IS_ERR_OR_NULL(obj)) {
                 pr_debug("bpf: failed to load %s\n", filename);
                 return obj;
         }
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 6533b1adb50b..822ba915d144 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -239,6 +239,7 @@ static void cs_etm__free(struct perf_session *session)
         for (i = 0; i < aux->num_cpu; i++)
                 zfree(&aux->metadata[i]);
 
+        thread__zput(aux->unknown_thread);
         zfree(&aux->metadata);
         zfree(&aux);
 }
@@ -610,8 +611,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
         return buff->len;
 }
 
-static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
-                                     struct auxtrace_queue *queue)
+static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+                                    struct auxtrace_queue *queue)
 {
         struct cs_etm_queue *etmq = queue->priv;
 
@@ -1355,6 +1356,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
         etm->auxtrace.free = cs_etm__free;
         session->auxtrace = &etm->auxtrace;
 
+        etm->unknown_thread = thread__new(999999999, 999999999);
+        if (!etm->unknown_thread)
+                goto err_free_queues;
+
+        /*
+         * Initialize list node so that at thread__zput() we can avoid
+         * segmentation fault at list_del_init().
+         */
+        INIT_LIST_HEAD(&etm->unknown_thread->node);
+
+        err = thread__set_comm(etm->unknown_thread, "unknown", 0);
+        if (err)
+                goto err_delete_thread;
+
+        if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+                goto err_delete_thread;
+
         if (dump_trace) {
                 cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
                 return 0;
@@ -1369,16 +1387,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
         err = cs_etm__synth_events(etm, session);
         if (err)
-                goto err_free_queues;
+                goto err_delete_thread;
 
         err = auxtrace_queues__process_index(&etm->queues, session);
         if (err)
-                goto err_free_queues;
+                goto err_delete_thread;
 
         etm->data_queued = etm->queues.populated;
 
         return 0;
 
+err_delete_thread:
+        thread__zput(etm->unknown_thread);
 err_free_queues:
         auxtrace_queues__free(&etm->queues);
         session->auxtrace = NULL;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 92ec009a292d..b13f5f234c8f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -127,6 +127,7 @@ struct perf_evsel {
         bool                    precise_max;
         bool                    ignore_missing_thread;
         bool                    forced_leader;
+        bool                    use_uncore_alias;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 1cca0a2fa641..976e658e38dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -14,11 +14,12 @@
 #include "config.h"
 #include "util.h"
 #include <sys/wait.h>
+#include <subcmd/exec-cmd.h>
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE                          \
                 "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
                 "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "     \
-                "$CLANG_OPTIONS $KERNEL_INC_OPTIONS "           \
+                "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
                 "-Wno-unused-value -Wno-pointer-sign "          \
                 "-working-directory $WORKING_DIR "              \
                 "-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
@@ -212,7 +213,7 @@ version_notice(void)
 "     \t\thttp://llvm.org/apt\n\n"
 "     \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
 "     \toption in [llvm] section of ~/.perfconfig to:\n\n"
-"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n"
+"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
 "     \t     -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
 "     \t     -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
 "     \t(Replace /path/to/llc with path to your llc)\n\n"
@@ -431,9 +432,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
         const char *clang_opt = llvm_param.clang_opt;
         char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
         char serr[STRERR_BUFSIZE];
-        char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
+        char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
+             *perf_bpf_include_opts = NULL;
         const char *template = llvm_param.clang_bpf_cmd_template;
-        char *command_echo, *command_out;
+        char *command_echo = NULL, *command_out;
+        char *perf_include_dir = system_path(PERF_INCLUDE_DIR);
 
         if (path[0] != '-' && realpath(path, abspath) == NULL) {
                 err = errno;
@@ -471,12 +474,14 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 
         snprintf(linux_version_code_str, sizeof(linux_version_code_str),
                  "0x%x", kernel_version);
-
+        if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0)
+                goto errout;
         force_set_env("NR_CPUS", nr_cpus_avail_str);
         force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
         force_set_env("CLANG_EXEC", clang_path);
         force_set_env("CLANG_OPTIONS", clang_opt);
         force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
+        force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
         force_set_env("WORKING_DIR", kbuild_dir ? : ".");
 
         /*
@@ -512,6 +517,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
         free(command_out);
         free(kbuild_dir);
         free(kbuild_include_opts);
+        free(perf_bpf_include_opts);
+        free(perf_include_dir);
 
         if (!p_obj_buf)
                 free(obj_buf);
@@ -526,6 +533,8 @@ errout:
         free(kbuild_dir);
         free(kbuild_include_opts);
         free(obj_buf);
+        free(perf_bpf_include_opts);
+        free(perf_include_dir);
         if (p_obj_buf)
                 *p_obj_buf = NULL;
         if (p_obj_buf_sz)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fb0272146d8..2fc4ee8b86c1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1219,13 +1219,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 
 int parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
-                         struct list_head *head_config, bool auto_merge_stats)
+                         struct list_head *head_config,
+                         bool auto_merge_stats,
+                         bool use_alias)
 {
         struct perf_event_attr attr;
         struct perf_pmu_info info;
         struct perf_pmu *pmu;
         struct perf_evsel *evsel;
         struct parse_events_error *err = parse_state->error;
+        bool use_uncore_alias;
         LIST_HEAD(config_terms);
 
         pmu = perf_pmu__find(name);
@@ -1244,11 +1247,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
                 memset(&attr, 0, sizeof(attr));
         }
 
+        use_uncore_alias = (pmu->is_uncore && use_alias);
+
         if (!head_config) {
                 attr.type = pmu->type;
                 evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
                 if (evsel) {
                         evsel->pmu_name = name;
+                        evsel->use_uncore_alias = use_uncore_alias;
                         return 0;
                 } else {
                         return -ENOMEM;
@@ -1282,6 +1288,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
                 evsel->metric_expr = info.metric_expr;
                 evsel->metric_name = info.metric_name;
                 evsel->pmu_name = name;
+                evsel->use_uncore_alias = use_uncore_alias;
         }
 
         return evsel ? 0 : -ENOMEM;
@@ -1317,7 +1324,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                 list_add_tail(&term->list, head);
 
                                 if (!parse_events_add_pmu(parse_state, list,
-                                                          pmu->name, head, true)) {
+                                                          pmu->name, head,
+                                                          true, true)) {
                                         pr_debug("%s -> %s/%s/\n", str,
                                                  pmu->name, alias->str);
                                         ok++;
@@ -1339,7 +1347,120 @@ int parse_events__modifier_group(struct list_head *list,
         return parse_events__modifier_event(list, event_mod, true);
 }
 
-void parse_events__set_leader(char *name, struct list_head *list)
+/*
+ * Check if the two uncore PMUs are from the same uncore block
+ * The format of the uncore PMU name is uncore_#blockname_#pmuidx
+ */
+static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b)
+{
+        char *end_a, *end_b;
+
+        end_a = strrchr(pmu_name_a, '_');
+        end_b = strrchr(pmu_name_b, '_');
+
+        if (!end_a || !end_b)
+                return false;
+
+        if ((end_a - pmu_name_a) != (end_b - pmu_name_b))
+                return false;
+
+        return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0);
+}
+
+static int
+parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
+                                           struct parse_events_state *parse_state)
+{
+        struct perf_evsel *evsel, *leader;
+        uintptr_t *leaders;
+        bool is_leader = true;
+        int i, nr_pmu = 0, total_members, ret = 0;
+
+        leader = list_first_entry(list, struct perf_evsel, node);
+        evsel = list_last_entry(list, struct perf_evsel, node);
+        total_members = evsel->idx - leader->idx + 1;
+
+        leaders = calloc(total_members, sizeof(uintptr_t));
+        if (WARN_ON(!leaders))
+                return 0;
+
+        /*
+         * Going through the whole group and doing sanity check.
+         * All members must use alias, and be from the same uncore block.
+         * Also, storing the leader events in an array.
+         */
+        __evlist__for_each_entry(list, evsel) {
+
+                /* Only split the uncore group which members use alias */
+                if (!evsel->use_uncore_alias)
+                        goto out;
+
+                /* The events must be from the same uncore block */
+                if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name))
+                        goto out;
+
+                if (!is_leader)
+                        continue;
+                /*
+                 * If the event's PMU name starts to repeat, it must be a new
+                 * event. That can be used to distinguish the leader from
+                 * other members, even they have the same event name.
+                 */
+                if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+                        is_leader = false;
+                        continue;
+                }
+                /* The name is always alias name */
+                WARN_ON(strcmp(leader->name, evsel->name));
+
+                /* Store the leader event for each PMU */
+                leaders[nr_pmu++] = (uintptr_t) evsel;
+        }
+
+        /* only one event alias */
+        if (nr_pmu == total_members) {
+                parse_state->nr_groups--;
+                goto handled;
+        }
+
+        /*
+         * An uncore event alias is a joint name which means the same event
+         * runs on all PMUs of a block.
+         * Perf doesn't support mixed events from different PMUs in the same
+         * group. The big group has to be split into multiple small groups
+         * which only include the events from the same PMU.
+         *
+         * Here the uncore event aliases must be from the same uncore block.
+         * The number of PMUs must be same for each alias. The number of new
+         * small groups equals to the number of PMUs.
+         * Setting the leader event for corresponding members in each group.
+         */
+        i = 0;
+        __evlist__for_each_entry(list, evsel) {
+                if (i >= nr_pmu)
+                        i = 0;
+                evsel->leader = (struct perf_evsel *) leaders[i++];
+        }
+
+        /* The number of members and group name are same for each group */
+        for (i = 0; i < nr_pmu; i++) {
+                evsel = (struct perf_evsel *) leaders[i];
+                evsel->nr_members = total_members / nr_pmu;
+                evsel->group_name = name ? strdup(name) : NULL;
+        }
+
+        /* Take the new small groups into account */
+        parse_state->nr_groups += nr_pmu - 1;
+
+handled:
+        ret = 1;
+out:
+        free(leaders);
+        return ret;
+}
+
+void parse_events__set_leader(char *name, struct list_head *list,
+                              struct parse_events_state *parse_state)
 {
         struct perf_evsel *leader;
 
@@ -1348,6 +1469,9 @@ void parse_events__set_leader(char *name, struct list_head *list)
                 return;
         }
 
+        if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
+                return;
+
         __perf_evlist__set_leader(list);
         leader = list_entry(list->next, struct perf_evsel, node);
         leader->group_name = name ? strdup(name) : NULL;
@@ -1715,7 +1839,7 @@ int parse_events(struct perf_evlist *evlist, const char *str,
                 struct perf_evsel *last;
 
                 if (list_empty(&parse_state.list)) {
-                        WARN_ONCE(true, "WARNING: event parser found nothing");
+                        WARN_ONCE(true, "WARNING: event parser found nothing\n");
                         return -1;
                 }
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5015cfd58277..4473dac27aee 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
-                         struct list_head *head_config, bool auto_merge_stats);
+                         struct list_head *head_config,
+                         bool auto_merge_stats,
+                         bool use_alias);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str,
@@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old,
 
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
-void parse_events__set_leader(char *name, struct list_head *list);
+void parse_events__set_leader(char *name, struct list_head *list,
+                              struct parse_events_state *parse_state);
 void parse_events_update_lists(struct list_head *list_event,
                                struct list_head *list_all);
 void parse_events_evlist_error(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d14464c42714..e37608a87dba 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -161,7 +161,7 @@ PE_NAME '{' events '}'
         struct list_head *list = $3;
 
         inc_group_count(list, _parse_state);
-        parse_events__set_leader($1, list);
+        parse_events__set_leader($1, list, _parse_state);
         $$ = list;
 }
 |
@@ -170,7 +170,7 @@ PE_NAME '{' events '}'
         struct list_head *list = $2;
 
         inc_group_count(list, _parse_state);
-        parse_events__set_leader(NULL, list);
+        parse_events__set_leader(NULL, list, _parse_state);
         $$ = list;
 }
 
@@ -224,15 +224,15 @@ event_def: event_pmu |
            event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
         struct list_head *list, *orig_terms, *terms;
 
-        if (parse_events_copy_term_list($3, &orig_terms))
+        if (parse_events_copy_term_list($2, &orig_terms))
                 YYABORT;
 
         ALLOC_LIST(list);
-        if (parse_events_add_pmu(_parse_state, list, $1, $3, false)) {
+        if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
                 struct perf_pmu *pmu = NULL;
                 int ok = 0;
                 char *pattern;
@@ -251,7 +251,7 @@ PE_NAME '/' event_config '/'
                                         free(pattern);
                                         YYABORT;
                                 }
-                                if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
+                                if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false))
                                         ok++;
                                 parse_events_terms__delete(terms);
                         }
@@ -262,7 +262,7 @@ PE_NAME '/' event_config '/'
                 if (!ok)
                         YYABORT;
         }
-        parse_events_terms__delete($3);
+        parse_events_terms__delete($2);
         parse_events_terms__delete(orig_terms);
         $$ = list;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f48dc157c2bd..4a39f4d0a174 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1149,7 +1149,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
         bool is_64_bit;
         int err, fd;
         char kcore_filename[PATH_MAX];
-        struct symbol *sym;
+        u64 stext;
 
         if (!kmaps)
                 return -EINVAL;
@@ -1198,13 +1198,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
                 old_map = next;
         }
 
-        /* Find the kernel map using the first symbol */
-        sym = dso__first_symbol(dso);
-        list_for_each_entry(new_map, &md.maps, node) {
-                if (sym && sym->start >= new_map->start &&
-                    sym->start < new_map->end) {
-                        replacement_map = new_map;
-                        break;
+        /* Find the kernel map using the '_stext' symbol */
+        if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) {
+                list_for_each_entry(new_map, &md.maps, node) {
+                        if (stext >= new_map->start && stext < new_map->end) {
+                                replacement_map = new_map;
+                                break;
+                        }
                 }
         }
 
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 2cccbba64418..f304be71c278 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -56,6 +56,7 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 # to compile vs uClibc, that can be done here as well.
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
 CROSS_COMPILE ?= $(CROSS)
+LD = $(CC)
 HOSTCC = gcc
 
 # check if compiler option is supported
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index faadbe233966..4123d0ab90ba 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1108,7 +1108,7 @@ static void test_stacktrace_build_id(void)
 
         assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
                == 0);
-        assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+        assert(system("./urandom_read") == 0);
         /* disable stack trace collection */
         key = 0;
         val = 1;
@@ -1158,7 +1158,7 @@ static void test_stacktrace_build_id(void)
         } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
         CHECK(build_id_matches < 1, "build id match",
-              "Didn't find expected build ID from the map");
+              "Didn't find expected build ID from the map\n");
 
 disable_pmu:
         ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 195e9d4739a9..c1b1a4dc6a96 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -20,10 +20,10 @@ all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
 .ONESHELL:
 define RUN_TESTS
-        @export KSFT_TAP_LEVEL=`echo 1`;
-        @test_num=`echo 0`;
-        @echo "TAP version 13";
-        @for TEST in $(1); do                           \
+        @export KSFT_TAP_LEVEL=`echo 1`;                \
+        test_num=`echo 0`;                              \
+        echo "TAP version 13";                          \
+        for TEST in $(1); do                            \
                 BASENAME_TEST=`basename $$TEST`;        \
                 test_num=`echo $$test_num+1 | bc`;      \
                 echo "selftests: $$BASENAME_TEST";      \
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8f1e13d2e547..3ff81a478dbe 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,7 +5,8 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
+TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5b012f4981d4..6f289a49e5ec 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -66,7 +66,7 @@
         "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf",
@@ -92,10 +92,15 @@
         "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
-            "$TC action flush action bpf",
+            [
+                "$TC action flush action bpf",
+                0,
+                1,
+                255
+            ],
             "rm -f _c.o"
         ]
     },