Merge tag 'perf-core-for-mingo-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf tooling changes from Arnaldo Carvalho de Melo:

New features:

 - Port 'perf kvm stat' to PowerPC (Hemant Kumar)

Infrastructure changes:

 - Use the 'feature-dump' target to do the feature checks just once and then
   add code to reuse that in the tests/make makefile, speeding up the
   'make -C tools/perf build-test' target (Wang Nan)

 - Reduce the number of tests the 'build-test' target do to those that don't
   pollute the source tree (Arnaldo Carvalho de Melo)

 - Improve the output of the build tests a bit by aligning the name of the
   tests, more can be done to filter out uninteresting info in the output
   (Arnaldo Carvalho de Melo)

 - Add perf_evlist pointer to *info_priv_size(), more prep work for
   supporting the coresight architecture (Mathieu Poirier)

 - Improve the 'perf test bp_signal' test (Wang Nan)

 - Check environment before starting the BPF 'perf test', so that we can just
   'Skip' older kernels instead of 'FAIL'ing them (Wang Nan)

 - Fix cpumode of synthesized buildid event (Wang Nan)

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

25 files changed, 688 insertions, 122 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 674c47d5f9d1..7bff2ea831cf 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -119,6 +119,14 @@ ifeq ($(feature-all), 1)
   # test-all.c passed - just set all the core feature flags to 1:
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
+  #
+  # test-all.c does not comprise these tests, so we need to
+  # for this case to get features proper values
+  #
+  $(call feature_check,compile-32)
+  $(call feature_check,compile-x32)
+  $(call feature_check,bionic)
+  $(call feature_check,libbabeltrace)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c
index 31dbf45bf99c..c54e6551ae4c 100644
--- a/tools/build/feature/test-compile.c
+++ b/tools/build/feature/test-compile.c
@@ -1,4 +1,6 @@
+#include <stdio.h>
 int main(void)
 {
+	printf("Hello World!\n");
 	return 0;
 }
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcd9a70c7193..4b68f465195c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -75,10 +75,17 @@ clean:
 	$(make)
 
 #
-# The build-test target is not really parallel, don't print the jobs info:
+# The build-test target is not really parallel, don't print the jobs info,
+# it also uses only the tests/make targets that don't pollute the source
+# repository, i.e. that uses O= or builds the tarpkg outside the source
+# repo directories.
+#
+# For a full test, use:
+#
+# make -C tools/perf -f tests/make
 #
 build-test:
-	@$(MAKE) SHUF=1 -f tests/make --no-print-directory
+	@$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile --no-print-directory tarpkg out
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7fbca175099e..9f9cea3478fd 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,5 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+HAVE_KVM_STAT_SUPPORT := 1
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 7b8b0d1a1b62..c8fe2074d217 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,6 @@
 libperf-y += header.o
 libperf-y += sym-handling.o
+libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
new file mode 100644
index 000000000000..0dd6b7f2d44f
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -0,0 +1,123 @@
+#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H
+#define ARCH_PERF_BOOK3S_HV_HCALLS_H
+
+/*
+ * PowerPC HCALL codes : hcall code to name mapping
+ */
+#define kvm_trace_symbol_hcall \
+	{0x4, "H_REMOVE"},					\
+	{0x8, "H_ENTER"},					\
+	{0xc, "H_READ"},					\
+	{0x10, "H_CLEAR_MOD"},					\
+	{0x14, "H_CLEAR_REF"},					\
+	{0x18, "H_PROTECT"},					\
+	{0x1c, "H_GET_TCE"},					\
+	{0x20, "H_PUT_TCE"},					\
+	{0x24, "H_SET_SPRG0"},					\
+	{0x28, "H_SET_DABR"},					\
+	{0x2c, "H_PAGE_INIT"},					\
+	{0x30, "H_SET_ASR"},					\
+	{0x34, "H_ASR_ON"},					\
+	{0x38, "H_ASR_OFF"},					\
+	{0x3c, "H_LOGICAL_CI_LOAD"},				\
+	{0x40, "H_LOGICAL_CI_STORE"},				\
+	{0x44, "H_LOGICAL_CACHE_LOAD"},				\
+	{0x48, "H_LOGICAL_CACHE_STORE"},			\
+	{0x4c, "H_LOGICAL_ICBI"},				\
+	{0x50, "H_LOGICAL_DCBF"},				\
+	{0x54, "H_GET_TERM_CHAR"},				\
+	{0x58, "H_PUT_TERM_CHAR"},				\
+	{0x5c, "H_REAL_TO_LOGICAL"},				\
+	{0x60, "H_HYPERVISOR_DATA"},				\
+	{0x64, "H_EOI"},					\
+	{0x68, "H_CPPR"},					\
+	{0x6c, "H_IPI"},					\
+	{0x70, "H_IPOLL"},					\
+	{0x74, "H_XIRR"},					\
+	{0x78, "H_MIGRATE_DMA"},				\
+	{0x7c, "H_PERFMON"},					\
+	{0xdc, "H_REGISTER_VPA"},				\
+	{0xe0, "H_CEDE"},					\
+	{0xe4, "H_CONFER"},					\
+	{0xe8, "H_PROD"},					\
+	{0xec, "H_GET_PPP"},					\
+	{0xf0, "H_SET_PPP"},					\
+	{0xf4, "H_PURR"},					\
+	{0xf8, "H_PIC"},					\
+	{0xfc, "H_REG_CRQ"},					\
+	{0x100, "H_FREE_CRQ"},					\
+	{0x104, "H_VIO_SIGNAL"},				\
+	{0x108, "H_SEND_CRQ"},					\
+	{0x110, "H_COPY_RDMA"},					\
+	{0x114, "H_REGISTER_LOGICAL_LAN"},			\
+	{0x118, "H_FREE_LOGICAL_LAN"},				\
+	{0x11c, "H_ADD_LOGICAL_LAN_BUFFER"},			\
+	{0x120, "H_SEND_LOGICAL_LAN"},				\
+	{0x124, "H_BULK_REMOVE"},				\
+	{0x130, "H_MULTICAST_CTRL"},				\
+	{0x134, "H_SET_XDABR"},					\
+	{0x138, "H_STUFF_TCE"},					\
+	{0x13c, "H_PUT_TCE_INDIRECT"},				\
+	{0x14c, "H_CHANGE_LOGICAL_LAN_MAC"},			\
+	{0x150, "H_VTERM_PARTNER_INFO"},			\
+	{0x154, "H_REGISTER_VTERM"},				\
+	{0x158, "H_FREE_VTERM"},				\
+	{0x15c, "H_RESET_EVENTS"},				\
+	{0x160, "H_ALLOC_RESOURCE"},				\
+	{0x164, "H_FREE_RESOURCE"},				\
+	{0x168, "H_MODIFY_QP"},					\
+	{0x16c, "H_QUERY_QP"},					\
+	{0x170, "H_REREGISTER_PMR"},				\
+	{0x174, "H_REGISTER_SMR"},				\
+	{0x178, "H_QUERY_MR"},					\
+	{0x17c, "H_QUERY_MW"},					\
+	{0x180, "H_QUERY_HCA"},					\
+	{0x184, "H_QUERY_PORT"},				\
+	{0x188, "H_MODIFY_PORT"},				\
+	{0x18c, "H_DEFINE_AQP1"},				\
+	{0x190, "H_GET_TRACE_BUFFER"},				\
+	{0x194, "H_DEFINE_AQP0"},				\
+	{0x198, "H_RESIZE_MR"},					\
+	{0x19c, "H_ATTACH_MCQP"},				\
+	{0x1a0, "H_DETACH_MCQP"},				\
+	{0x1a4, "H_CREATE_RPT"},				\
+	{0x1a8, "H_REMOVE_RPT"},				\
+	{0x1ac, "H_REGISTER_RPAGES"},				\
+	{0x1b0, "H_DISABLE_AND_GETC"},				\
+	{0x1b4, "H_ERROR_DATA"},				\
+	{0x1b8, "H_GET_HCA_INFO"},				\
+	{0x1bc, "H_GET_PERF_COUNT"},				\
+	{0x1c0, "H_MANAGE_TRACE"},				\
+	{0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"},			\
+	{0x1d8, "H_POLL_PENDING"},				\
+	{0x1e4, "H_QUERY_INT_STATE"},				\
+	{0x244, "H_ILLAN_ATTRIBUTES"},				\
+	{0x250, "H_MODIFY_HEA_QP"},				\
+	{0x254, "H_QUERY_HEA_QP"},				\
+	{0x258, "H_QUERY_HEA"},					\
+	{0x25c, "H_QUERY_HEA_PORT"},				\
+	{0x260, "H_MODIFY_HEA_PORT"},				\
+	{0x264, "H_REG_BCMC"},					\
+	{0x268, "H_DEREG_BCMC"},				\
+	{0x26c, "H_REGISTER_HEA_RPAGES"},			\
+	{0x270, "H_DISABLE_AND_GET_HEA"},			\
+	{0x274, "H_GET_HEA_INFO"},				\
+	{0x278, "H_ALLOC_HEA_RESOURCE"},			\
+	{0x284, "H_ADD_CONN"},					\
+	{0x288, "H_DEL_CONN"},					\
+	{0x298, "H_JOIN"},					\
+	{0x2a4, "H_VASI_STATE"},				\
+	{0x2b0, "H_ENABLE_CRQ"},				\
+	{0x2b8, "H_GET_EM_PARMS"},				\
+	{0x2d0, "H_SET_MPP"},					\
+	{0x2d4, "H_GET_MPP"},					\
+	{0x2ec, "H_HOME_NODE_ASSOCIATIVITY"},			\
+	{0x2f4, "H_BEST_ENERGY"},				\
+	{0x2fc, "H_XIRR_X"},					\
+	{0x300, "H_RANDOM"},					\
+	{0x304, "H_COP"},					\
+	{0x314, "H_GET_MPP_X"},					\
+	{0x31c, "H_SET_MODE"},					\
+	{0xf000, "H_RTAS"}					\
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
new file mode 100644
index 000000000000..e68ba2da8970
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -0,0 +1,33 @@
+#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
+#define ARCH_PERF_BOOK3S_HV_EXITS_H
+
+/*
+ * PowerPC Interrupt vectors : exit code to name mapping
+ */
+
+#define kvm_trace_symbol_exit \
+	{0x0,	"RETURN_TO_HOST"}, \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
new file mode 100644
index 000000000000..74eee30398f8
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -0,0 +1,170 @@
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+#include "util/debug.h"
+
+#include "book3s_hv_exits.h"
+#include "book3s_hcalls.h"
+
+#define NR_TPS 4
+
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 40;
+const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
+const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
+
+define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit);
+define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall);
+
+/* Tracepoints specific to ppc_book3s_hv */
+const char *ppc_book3s_hv_kvm_tp[] = {
+	"kvm_hv:kvm_guest_enter",
+	"kvm_hv:kvm_guest_exit",
+	"kvm_hv:kvm_hcall_enter",
+	"kvm_hv:kvm_hcall_exit",
+	NULL,
+};
+
+/* 1 extra placeholder for NULL */
+const char *kvm_events_tp[NR_TPS + 1];
+const char *kvm_exit_reason;
+
+static void hcall_event_get_key(struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct event_key *key)
+{
+	key->info = 0;
+	key->key = perf_evsel__intval(evsel, sample, "req");
+}
+
+static const char *get_hcall_exit_reason(u64 exit_code)
+{
+	struct exit_reasons_table *tbl = hcall_reasons;
+
+	while (tbl->reason != NULL) {
+		if (tbl->exit_code == exit_code)
+			return tbl->reason;
+		tbl++;
+	}
+
+	pr_debug("Unknown hcall code: %lld\n",
+	       (unsigned long long)exit_code);
+	return "UNKNOWN";
+}
+
+static bool hcall_event_end(struct perf_evsel *evsel,
+			    struct perf_sample *sample __maybe_unused,
+			    struct event_key *key __maybe_unused)
+{
+	return (!strcmp(evsel->name, kvm_events_tp[3]));
+}
+
+static bool hcall_event_begin(struct perf_evsel *evsel,
+			      struct perf_sample *sample, struct event_key *key)
+{
+	if (!strcmp(evsel->name, kvm_events_tp[2])) {
+		hcall_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				   struct event_key *key,
+				   char *decode)
+{
+	const char *hcall_reason = get_hcall_exit_reason(key->key);
+
+	scnprintf(decode, decode_str_len, "%s", hcall_reason);
+}
+
+static struct kvm_events_ops hcall_events = {
+	.is_begin_event = hcall_event_begin,
+	.is_end_event = hcall_event_end,
+	.decode_key = hcall_event_decode_key,
+	.name = "HCALL-EVENT",
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ .name = "hcall", .ops = &hcall_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	NULL,
+};
+
+
+static int is_tracepoint_available(const char *str, struct perf_evlist *evlist)
+{
+	struct parse_events_error err;
+	int ret;
+
+	err.str = NULL;
+	ret = parse_events(evlist, str, &err);
+	if (err.str)
+		pr_err("%s : %s\n", str, err.str);
+	return ret;
+}
+
+static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm,
+				struct perf_evlist *evlist)
+{
+	const char **events_ptr;
+	int i, nr_tp = 0, err = -1;
+
+	/* Check for book3s_hv tracepoints */
+	for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) {
+		err = is_tracepoint_available(*events_ptr, evlist);
+		if (err)
+			return -1;
+		nr_tp++;
+	}
+
+	for (i = 0; i < nr_tp; i++)
+		kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i];
+
+	kvm_events_tp[i] = NULL;
+	kvm_exit_reason = "trap";
+	kvm->exit_reasons = hv_exit_reasons;
+	kvm->exit_reasons_isa = "HV";
+
+	return 0;
+}
+
+/* Wrapper to setup kvm tracepoints */
+static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist == NULL)
+		return -ENOMEM;
+
+	/* Right now, only supported on book3s_hv */
+	return ppc__setup_book3s_hv(kvm, evlist);
+}
+
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm)
+{
+	return ppc__setup_kvm_tp(kvm);
+}
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+	int ret;
+
+	ret = ppc__setup_kvm_tp(kvm);
+	if (ret) {
+		kvm->exit_reasons = NULL;
+		kvm->exit_reasons_isa = NULL;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index a5dbc07ec9dc..ed57df2e6d68 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -10,7 +10,7 @@
  */
 
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/sie.h>
 
 define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
 define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
@@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
 define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
 define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
 
+const char *vcpu_id_str = "id";
+const int decode_str_len = 40;
+const char *kvm_exit_reason = "icptcode";
+const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
+const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";
+
 static void event_icpt_insn_get_key(struct perf_evsel *evsel,
 				    struct perf_sample *sample,
 				    struct event_key *key)
@@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_s390_sie_enter",
 	"kvm:kvm_s390_sie_exit",
 	"kvm:kvm_s390_intercept_instruction",
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 8d8150f1cf9b..d66f9ad4df2e 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -60,7 +60,9 @@ struct branch {
 	u64 misc;
 };
 
-static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f05daacc9e78..6f7d453b0e32 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
 	return attr;
 }
 
-static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_PT_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 14e4e668fad7..b63d4be655a2 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,5 +1,7 @@
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
 define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
@@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 20;
+const char *kvm_exit_reason = "exit_reason";
+const char *kvm_entry_trace = "kvm:kvm_entry";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+
 /*
  * For the mmio events, we treat:
  * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
@@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				  struct event_key *key,
 				  char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+	scnprintf(decode, decode_str_len, "%#lx:%s",
 		  (unsigned long)key->key,
 		  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
 }
@@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				    struct event_key *key,
 				    char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+	scnprintf(decode, decode_str_len, "%#llx:%s",
 		  (unsigned long long)key->key,
 		  key->info ? "POUT" : "PIN");
 }
@@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_entry",
 	"kvm:kvm_exit",
 	"kvm:kvm_mmio",
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d93bff7fc0e4..632efc6b79a0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 
 static int build_id_cache__kcore_dir(char *dir, size_t sz)
 {
-	struct timeval tv;
-	struct tm tm;
-	char dt[32];
-
-	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
-		return -1;
-
-	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
-		return -1;
-
-	scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
-	return 0;
+	return fetch_current_timestamp(dir, sz);
 }
 
 static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4418d9214872..bff666458b28 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -30,7 +30,6 @@
 #include <math.h>
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include <asm/kvm_perf.h>
 #include "util/kvm-stat.h"
 
 void exit_event_get_key(struct perf_evsel *evsel,
@@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel,
 			struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
+	key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
 }
 
 bool kvm_exit_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_EXIT_TRACE);
+	return !strcmp(evsel->name, kvm_exit_trace);
 }
 
 bool exit_event_begin(struct perf_evsel *evsel,
@@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel,
 
 bool kvm_entry_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_ENTRY_TRACE);
+	return !strcmp(evsel->name, kvm_entry_trace);
 }
 
 bool exit_event_end(struct perf_evsel *evsel,
@@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
 						  key->key);
 
-	scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
+	scnprintf(decode, decode_str_len, "%s", exit_reason);
 }
 
 static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
@@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 	time_diff = sample->time - time_begin;
 
 	if (kvm->duration && time_diff > kvm->duration) {
-		char decode[DECODE_STR_LEN];
+		char decode[decode_str_len];
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
 		if (!skip_event(decode)) {
@@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 			return NULL;
 		}
 
-		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
+							  vcpu_id_str);
 		thread__set_priv(thread, vcpu_record);
 	}
 
@@ -574,7 +574,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-	char decode[DECODE_STR_LEN];
+	char decode[decode_str_len];
 	struct kvm_event *event;
 	int vcpu = kvm->trace_vcpu;
 
@@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
 	pr_info("\n\n");
 	print_vcpu_info(kvm);
-	pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
+	pr_info("%*s ", decode_str_len, kvm->events_ops->name);
 	pr_info("%10s ", "Samples");
 	pr_info("%9s ", "Samples%");
 
@@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 		min = get_event_min(event, vcpu);
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		pr_info("%*s ", DECODE_STR_LEN, decode);
+		pr_info("%*s ", decode_str_len, decode);
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -1132,6 +1132,11 @@ exit:
 		_p;			\
 	})
 
+int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused)
+{
+	return 0;
+}
+
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
@@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		NULL
 	};
 	const char * const *events_tp;
+	int ret;
+
 	events_tp_size = 0;
+	ret = setup_kvm_events_tp(kvm);
+	if (ret < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return ret;
+	}
 
 	for (events_tp = kvm_events_tp; *events_tp; events_tp++)
 		events_tp_size++;
@@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	/*
 	 * generate the event list
 	 */
+	err = setup_kvm_events_tp(kvm);
+	if (err < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return err;
+	}
+
 	kvm->evlist = kvm_live_event_list();
 	if (kvm->evlist == NULL) {
 		err = -1;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 319712a4e02b..0ee0d5cd31a7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,7 +49,9 @@ struct record {
 	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
+	bool			no_buildid_set;
 	bool			no_buildid_cache;
+	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	unsigned long long	samples;
 };
@@ -1097,10 +1099,12 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
-	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
-		    "do not update the buildid cache"),
-	OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
-		    "do not collect buildids in perf.data"),
+	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
+			&record.no_buildid_cache_set,
+			"do not update the buildid cache"),
+	OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid,
+			&record.no_buildid_set,
+			"do not collect buildids in perf.data"),
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 511141b102e8..0045a5ddd0ca 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -61,50 +61,45 @@ endif
 
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
-else
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
-  endif
-  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
-
-  # Set per-feature check compilation flags
-  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
-  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 endif
+#
+# For linking with debug library, run like:
+#
+#   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+#
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+endif
+LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+# Set per-feature check compilation flags
+FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifndef NO_LIBELF
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-  ifdef LIBDW_DIR
-    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+# for linking with debug library, run like:
+# make DEBUG=1 LIBDW_DIR=/opt/libdw/
+ifdef LIBDW_DIR
+  LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+  LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 
-ifdef LIBBABELTRACE
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
-  ifdef LIBBABELTRACE_DIR
-    LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
-    LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+# for linking with debug library, run like:
+# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
+ifdef LIBBABELTRACE_DIR
+  LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
+  LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 # include ARCH specific config
@@ -145,28 +140,26 @@ ifdef PARSER_DEBUG
   $(call detected_var,PARSER_DEBUG_FLEX)
 endif
 
-ifndef NO_LIBPYTHON
-  # Try different combinations to accommodate systems that only have
-  # python[2][-config] in weird combinations but always preferring
-  # python2 and python2-config as per pep-0394. If we catch a
-  # python[-config] in version 3, the version check will kill it.
-  PYTHON2 := $(if $(call get-executable,python2),python2,python)
-  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
-  PYTHON2_CONFIG := \
-    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
-  override PYTHON_CONFIG := \
-    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+# Try different combinations to accommodate systems that only have
+# python[2][-config] in weird combinations but always preferring
+# python2 and python2-config as per pep-0394. If we catch a
+# python[-config] in version 3, the version check will kill it.
+PYTHON2 := $(if $(call get-executable,python2),python2,python)
+override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+PYTHON2_CONFIG := \
+  $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+override PYTHON_CONFIG := \
+  $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
 
-  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
-  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
-endif
+FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index fb80c9eb6a95..1d1bb489b4e8 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -29,14 +29,59 @@
 
 static int fd1;
 static int fd2;
+static int fd3;
 static int overflows;
+static int overflows_2;
+
+volatile long the_var;
+
+
+/*
+ * Use ASM to ensure watchpoint and breakpoint can be triggered
+ * at one instruction.
+ */
+#if defined (__x86_64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"incq (%rdi)\n"
+	"ret\n");
+#elif defined (__aarch64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"str x30, [x0]\n"
+	"ret\n");
+
+#else
+static void __test_function(volatile long *ptr)
+{
+	*ptr = 0x1234;
+}
+#endif
 
 __attribute__ ((noinline))
 static int test_function(void)
 {
+	__test_function(&the_var);
+	the_var++;
 	return time(NULL);
 }
 
+static void sig_handler_2(int signum __maybe_unused,
+			  siginfo_t *oh __maybe_unused,
+			  void *uc __maybe_unused)
+{
+	overflows_2++;
+	if (overflows_2 > 10) {
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
 static void sig_handler(int signum __maybe_unused,
 			siginfo_t *oh __maybe_unused,
 			void *uc __maybe_unused)
@@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused,
 		 */
 		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 	}
 }
 
-static int bp_event(void *fn, int setup_signal)
+static int __event(bool is_x, void *addr, int signal)
 {
 	struct perf_event_attr pe;
 	int fd;
@@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal)
 	pe.size = sizeof(struct perf_event_attr);
 
 	pe.config = 0;
-	pe.bp_type = HW_BREAKPOINT_X;
-	pe.bp_addr = (unsigned long) fn;
+	pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W;
+	pe.bp_addr = (unsigned long) addr;
 	pe.bp_len = sizeof(long);
 
 	pe.sample_period = 1;
@@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal)
 		return TEST_FAIL;
 	}
 
-	if (setup_signal) {
-		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
-		fcntl(fd, F_SETSIG, SIGIO);
-		fcntl(fd, F_SETOWN, getpid());
-	}
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, signal);
+	fcntl(fd, F_SETOWN, getpid());
 
 	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
 
 	return fd;
 }
 
+static int bp_event(void *addr, int signal)
+{
+	return __event(true, addr, signal);
+}
+
+static int wp_event(void *addr, int signal)
+{
+	return __event(false, addr, signal);
+}
+
 static long long bp_count(int fd)
 {
 	long long count;
@@ -114,7 +168,7 @@ static long long bp_count(int fd)
 int test__bp_signal(int subtest __maybe_unused)
 {
 	struct sigaction sa;
-	long long count1, count2;
+	long long count1, count2, count3;
 
 	/* setup SIGIO signal handler */
 	memset(&sa, 0, sizeof(struct sigaction));
@@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused)
 		return TEST_FAIL;
 	}
 
+	sa.sa_sigaction = (void *) sig_handler_2;
+	if (sigaction(SIGUSR1, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler 2\n");
+		return TEST_FAIL;
+	}
+
 	/*
 	 * We create following events:
 	 *
-	 * fd1 - breakpoint event on test_function with SIGIO
+	 * fd1 - breakpoint event on __test_function with SIGIO
 	 *       signal configured. We should get signal
 	 *       notification each time the breakpoint is hit
 	 *
-	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 * fd2 - breakpoint event on sig_handler with SIGUSR1
+	 *       configured. We should get SIGUSR1 each time when
+	 *       breakpoint is hit
+	 *
+	 * fd3 - watchpoint event on __test_function with SIGIO
 	 *       configured.
 	 *
 	 * Following processing should happen:
-	 *   - execute test_function
-	 *   - fd1 event breakpoint hit -> count1 == 1
-	 *   - SIGIO is delivered       -> overflows == 1
-	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *   Exec:               Action:                       Result:
+	 *   incq (%rdi)       - fd1 event breakpoint hit   -> count1 == 1
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 1
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 1  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 1
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   incq (%rdi)       - fd3 event watchpoint hit   -> count3 == 1       (wp and bp in one insn)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 2
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 2  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 2
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   the_var++         - fd3 event watchpoint hit   -> count3 == 2       (standalone watchpoint)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 3
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 3  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows == 3
+	 *   sys_rt_sigreturn  - return from sig_handler
 	 *
 	 * The test case check following error conditions:
 	 * - we get stuck in signal handler because of debug
@@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused)
 	 *
 	 */
 
-	fd1 = bp_event(test_function, 1);
-	fd2 = bp_event(sig_handler, 0);
+	fd1 = bp_event(__test_function, SIGIO);
+	fd2 = bp_event(sig_handler, SIGUSR1);
+	fd3 = wp_event((void *)&the_var, SIGIO);
 
 	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0);
 
 	/*
 	 * Kick off the test by trigering 'fd1'
@@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused)
 
 	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 
 	count1 = bp_count(fd1);
 	count2 = bp_count(fd2);
+	count3 = bp_count(fd3);
 
 	close(fd1);
 	close(fd2);
+	close(fd3);
 
-	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
-		 count1, count2, overflows);
+	pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n",
+		 count1, count2, count3, overflows, overflows_2);
 
 	if (count1 != 1) {
 		if (count1 == 11)
@@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused)
 			pr_debug("failed: wrong count for bp1%lld\n", count1);
 	}
 
-	if (overflows != 1)
+	if (overflows != 3)
 		pr_debug("failed: wrong overflow hit\n");
 
-	if (count2 != 1)
+	if (overflows_2 != 3)
+		pr_debug("failed: wrong overflow_2 hit\n");
+
+	if (count2 != 3)
 		pr_debug("failed: wrong count for bp2\n");
 
-	return count1 == 1 && overflows == 1 && count2 == 1 ?
+	if (count3 != 2)
+		pr_debug("failed: wrong count for bp3\n");
+
+	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 952ca99aba6b..4aed5cb4ac2d 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,7 +1,11 @@
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -243,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i)
 	return bpf_testcase_table[i].desc;
 }
 
+static int check_env(void)
+{
+	int err;
+	unsigned int kver_int;
+	char license[] = "GPL";
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	err = fetch_kernel_version(&kver_int, NULL, 0);
+	if (err) {
+		pr_debug("Unable to get kernel version\n");
+		return err;
+	}
+
+	err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+			       sizeof(insns) / sizeof(insns[0]),
+			       license, kver_int, NULL, 0);
+	if (err < 0) {
+		pr_err("Missing basic BPF support, skip this test: %s\n",
+		       strerror(errno));
+		return err;
+	}
+	close(err);
+
+	return 0;
+}
+
 int test__bpf(int i)
 {
 	int err;
@@ -255,6 +289,9 @@ int test__bpf(int i)
 		return TEST_SKIP;
 	}
 
+	if (check_env())
+		return TEST_SKIP;
+
 	err = __test__bpf(i);
 	return err;
 }
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f918015512af..cc72b67bde5e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -15,6 +15,7 @@ else
 PERF := .
 PERF_O := $(PERF)
 O_OPT :=
+FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O))
 
 ifneq ($(O),)
   FULL_O := $(shell readlink -f $(O) || echo $(O))
@@ -260,6 +261,8 @@ run := $(shell shuf -e $(run))
 run_O := $(shell shuf -e $(run_O))
 endif
 
+max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L)
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
@@ -273,7 +276,7 @@ $(run):
 	$(call clean)
 	@TMP_DEST=$$(mktemp -d); \
 	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
@@ -284,7 +287,7 @@ $(run_O):
 	@TMP_O=$$(mktemp -d); \
 	TMP_DEST=$$(mktemp -d); \
 	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
@@ -313,11 +316,43 @@ make_kernelsrc_tools:
 	(make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
 	test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
+FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP
+FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC
+
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
 
 out: $(run_O)
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
+
+ifeq ($(REUSE_FEATURES_DUMP),1)
+$(FEATURES_DUMP_FILE):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+$(FEATURES_DUMP_FILE_STATIC):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+# Add feature dump dependency for run/run_O targets
+$(foreach t,$(run) $(run_O),$(eval \
+	$(t): $(if $(findstring make_static,$(t)),\
+		$(FEATURES_DUMP_FILE_STATIC),\
+		$(FEATURES_DUMP_FILE))))
+
+# Append 'FEATURES_DUMP=' option to all test cases. For example:
+# make_no_libbpf: NO_LIBBPF=1  --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP
+# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC
+$(foreach t,$(run),$(if $(findstring make_static,$(t)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE))))
+endif
 
 .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 360fda01f3b0..ec164fe70718 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap)
 			 heap_array[last].ordinal);
 }
 
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist)
 {
 	if (itr)
-		return itr->info_priv_size(itr);
+		return itr->info_priv_size(itr, evlist);
 	return 0;
 }
 
@@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 	int err;
 
 	pr_debug2("Synthesizing auxtrace information\n");
-	priv_size = auxtrace_record__info_priv_size(itr);
+	priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
 	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
 	if (!ev)
 		return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b86f90db1352..e5a8e2d4f2af 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -293,7 +293,8 @@ struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
 				 struct perf_evlist *evlist,
 				 struct record_opts *opts);
-	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	size_t (*info_priv_size)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist);
 	int (*info_fill)(struct auxtrace_record *itr,
 			 struct perf_session *session,
 			 struct auxtrace_info_event *auxtrace_info,
@@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct perf_evlist *evlist,
 			     struct record_opts *opts);
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
 			       struct auxtrace_info_event *auxtrace_info,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6a7e273a514a..b28100ee1732 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -211,6 +211,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
+		bool in_kernel = false;
 
 		if (!pos->hit)
 			continue;
@@ -227,8 +228,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 			name_len = pos->long_name_len + 1;
 		}
 
+		in_kernel = pos->kernel ||
+				is_kernel_module(name,
+					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
 		err = write_buildid(name, name_len, pos->build_id, machine->pid,
-				    pos->kernel ? kmisc : umisc, fd);
+				    in_kernel ? kmisc : umisc, fd);
 		if (err)
 			break;
 	}
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index ae825d4ec110..d01e73592f6e 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 
 bool kvm_exit_event(struct perf_evsel *evsel);
 bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)	\
 	static struct exit_reasons_table name[] = {	\
@@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel);
  */
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
 
-extern const char * const kvm_events_tp[];
+extern const char *kvm_events_tp[];
 extern struct kvm_reg_events_ops kvm_reg_events_ops[];
 extern const char * const kvm_skip_events[];
+extern const char *vcpu_id_str;
+extern const int decode_str_len;
+extern const char *kvm_exit_reason;
+extern const char *kvm_entry_trace;
+extern const char *kvm_exit_trace;
 
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7a2da7ef556e..b9e2843cfbe7 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -701,3 +701,20 @@ bool is_regular_file(const char *file)
 
 	return S_ISREG(st.st_mode);
 }
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 61650f05e5c1..a8615816a00d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -344,5 +344,6 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 bool is_regular_file(const char *file);
+int fetch_current_timestamp(char *buf, size_t sz);
 
 #endif /* GIT_COMPAT_UTIL_H */