13 files changed, 138 insertions, 48 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0a22407e1d7d..5d34815c7ccb 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -77,6 +77,9 @@ include config/utilities.mak
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 #
 # Define NO_LIBBPF if you do not want BPF support
+#
+# Define FEATURES_DUMP to provide features detection dump file
+# and bypass the feature detection
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -166,6 +169,15 @@ ifeq ($(config),1)
 include config/Makefile
 endif
 
+# The FEATURE_DUMP_EXPORT holds location of the actual
+# FEATURE_DUMP file to be used to bypass feature detection
+# (for bpf or any other subproject)
+ifeq ($(FEATURES_DUMP),)
+FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
+else
+FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+endif
+
 export prefix bindir sharedir sysconfdir DESTDIR
 
 # sparse is architecture-neutral, which means that we need to tell it
@@ -436,7 +448,7 @@ $(LIBAPI)-clean:
         $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
 $(LIBBPF): fixdep FORCE
-        $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP)
+        $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
 
 $(LIBBPF)-clean:
         $(call QUIET_CLEAN, libbpf)
@@ -611,6 +623,17 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
         $(python-clean)
 
 #
+# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
+# file if defined, with no further action.
+feature-dump:
+ifdef FEATURE_DUMP_COPY
+        @cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY)
+        @echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)"
+else
+        @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
+endif
+
+#
 # Trick: if ../../.git does not exist - we are building out of tree for example,
 # then force version regeneration:
 #
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 3e89ba825f6b..7f064eb37158 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -17,7 +17,7 @@ static pid_t spawn(void)
         if (pid)
                 return pid;
 
-        while(1);
+        while(1)
                 sleep(5);
         return 0;
 }
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index e5959c136a19..511141b102e8 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -181,7 +181,11 @@ LDFLAGS += -Wl,-z,noexecstack
 
 EXTLIBS = -lpthread -lrt -lm -ldl
 
+ifeq ($(FEATURES_DUMP),)
 include $(srctree)/tools/build/Makefile.feature
+else
+include $(FEATURES_DUMP)
+endif
 
 ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index df38decc48c3..f918015512af 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -5,7 +5,7 @@ ifeq ($(MAKECMDGOALS),)
 # no target specified, trigger the whole suite
 all:
         @echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile
-        @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf
+        @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf SET_PARALLEL=1 SET_O=1
 else
 # run only specific test over 'Makefile'
 %:
@@ -13,6 +13,26 @@ else
 endif
 else
 PERF := .
+PERF_O := $(PERF)
+O_OPT :=
+
+ifneq ($(O),)
+  FULL_O := $(shell readlink -f $(O) || echo $(O))
+  PERF_O := $(FULL_O)
+  ifeq ($(SET_O),1)
+    O_OPT := 'O=$(FULL_O)'
+  endif
+  K_O_OPT := 'O=$(FULL_O)'
+endif
+
+PARALLEL_OPT=
+ifeq ($(SET_PARALLEL),1)
+  cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
+  ifeq ($(cores),0)
+    cores := 1
+  endif
+  PARALLEL_OPT="-j$(cores)"
+endif
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -156,11 +176,11 @@ test_make_doc    := $(test_ok)
 test_make_help_O := $(test_ok)
 test_make_doc_O  := $(test_ok)
 
-test_make_python_perf_so := test -f $(PERF)/python/perf.so
+test_make_python_perf_so := test -f $(PERF_O)/python/perf.so
 
-test_make_perf_o           := test -f $(PERF)/perf.o
-test_make_util_map_o       := test -f $(PERF)/util/map.o
-test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
+test_make_perf_o           := test -f $(PERF_O)/perf.o
+test_make_util_map_o       := test -f $(PERF_O)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF_O)/util/pmu-bison.o
 
 define test_dest_files
   for file in $(1); do                          \
@@ -227,7 +247,7 @@ test_make_perf_o_O            := test -f $$TMP_O/perf.o
 test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
 test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
 
-test_default = test -x $(PERF)/perf
+test_default = test -x $(PERF_O)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
 
 test_default_O = test -x $$TMP_O/perf
@@ -247,12 +267,12 @@ endif
 
 MAKEFLAGS := --no-print-directory
 
-clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
 
 $(run):
         $(call clean)
         @TMP_DEST=$$(mktemp -d); \
-        cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
+        cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1; \
         echo "  test: $(call test,$@)" >> $@ 2>&1; \
@@ -263,7 +283,7 @@ $(run_O):
         $(call clean)
         @TMP_O=$$(mktemp -d); \
         TMP_DEST=$$(mktemp -d); \
-        cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
+        cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1 && \
         echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
@@ -276,17 +296,22 @@ tarpkg:
         ( eval $$cmd ) >> $@ 2>&1 && \
         rm -f $@
 
+KERNEL_O := ../..
+ifneq ($(O),)
+  KERNEL_O := $(O)
+endif
+
 make_kernelsrc:
-        @echo "- make -C <kernelsrc> tools/perf"
+        @echo "- make -C <kernelsrc> $(PARALLEL_OPT) $(K_O_OPT) tools/perf"
         $(call clean); \
-        (make -C ../.. tools/perf) > $@ 2>&1 && \
-        test -x perf && rm -f $@ || (cat $@ ; false)
+        (make -C ../.. $(PARALLEL_OPT) $(K_O_OPT) tools/perf) > $@ 2>&1 && \
+        test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
 make_kernelsrc_tools:
-        @echo "- make -C <kernelsrc>/tools perf"
+        @echo "- make -C <kernelsrc>/tools $(PARALLEL_OPT) $(K_O_OPT) perf"
         $(call clean); \
-        (make -C ../../tools perf) > $@ 2>&1 && \
-        test -x perf && rm -f $@ || (cat $@ ; false)
+        (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
+        test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
         @echo OK
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d4d7cc27252f..718bd46d47fa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser,
                                 nd = browser->curr_hot;
                         break;
                 case K_UNTAB:
-                        if (nd != NULL)
+                        if (nd != NULL) {
                                 nd = rb_next(nd);
                                 if (nd == NULL)
                                         nd = rb_first(&browser->entries);
-                        else
+                        } else
                                 nd = browser->curr_hot;
                         break;
                 case K_F1:
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index c226303e3da0..68a7612019dc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -131,6 +131,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                         symlen = unresolved_col_width + 4 + 2;
                         hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
                                            symlen);
+                        hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+                                           symlen);
                 }
 
                 if (h->mem_info->iaddr.sym) {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 81a2eb77ba7f..05d815851be1 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2068,6 +2068,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
                 err = -ENOMEM;
                 goto err_free_queues;
         }
+
+        /*
+         * Since this thread will not be kept in any rbtree not in a
+         * list, initialize its list node so that at thread__put() the
+         * current thread lifetime assuption is kept and we don't segfault
+         * at list_del_init().
+         */
+        INIT_LIST_HEAD(&pt->unknown_thread->node);
+
         err = thread__set_comm(pt->unknown_thread, "unknown", 0);
         if (err)
                 goto err_delete_thread;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4f7b0efdde2f..813d9b272c81 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 {
         char help[BUFSIZ];
 
+        if (!e)
+                return;
+
         /*
          * We get error directly from syscall errno ( > 0),
          * or from encoded pointer's error ( < 0).
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2be10fb27172..4ce5c5e18f48 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -686,8 +686,9 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
                 pf->fb_ops = NULL;
 #if _ELFUTILS_PREREQ(0, 142)
         } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
-                   pf->cfi != NULL) {
-                if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+                   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
+                if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
+                     (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) ||
                     dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
                         pr_warning("Failed to get call frame on 0x%jx\n",
                                    (uintmax_t)pf->addr);
@@ -1015,8 +1016,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
         return DWARF_CB_OK;
 }
 
-/* Find probe points from debuginfo */
-static int debuginfo__find_probes(struct debuginfo *dbg,
+static int debuginfo__find_probe_location(struct debuginfo *dbg,
                                   struct probe_finder *pf)
 {
         struct perf_probe_point *pp = &pf->pev->point;
@@ -1025,27 +1025,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
         Dwarf_Die *diep;
         int ret = 0;
 
-#if _ELFUTILS_PREREQ(0, 142)
-        Elf *elf;
-        GElf_Ehdr ehdr;
-        GElf_Shdr shdr;
-
-        /* Get the call frame information from this dwarf */
-        elf = dwarf_getelf(dbg->dbg);
-        if (elf == NULL)
-                return -EINVAL;
-
-        if (gelf_getehdr(elf, &ehdr) == NULL)
-                return -EINVAL;
-
-        if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-            shdr.sh_type == SHT_PROGBITS) {
-                pf->cfi = dwarf_getcfi_elf(elf);
-        } else {
-                pf->cfi = dwarf_getcfi(dbg->dbg);
-        }
-#endif
-
         off = 0;
         pf->lcache = intlist__new(NULL);
         if (!pf->lcache)
@@ -1108,6 +1087,39 @@ found:
         return ret;
 }
 
+/* Find probe points from debuginfo */
+static int debuginfo__find_probes(struct debuginfo *dbg,
+                                  struct probe_finder *pf)
+{
+        int ret = 0;
+
+#if _ELFUTILS_PREREQ(0, 142)
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+
+        if (pf->cfi_eh || pf->cfi_dbg)
+                return debuginfo__find_probe_location(dbg, pf);
+
+        /* Get the call frame information from this dwarf */
+        elf = dwarf_getelf(dbg->dbg);
+        if (elf == NULL)
+                return -EINVAL;
+
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                return -EINVAL;
+
+        if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+            shdr.sh_type == SHT_PROGBITS)
+                pf->cfi_eh = dwarf_getcfi_elf(elf);
+
+        pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+#endif
+
+        ret = debuginfo__find_probe_location(dbg, pf);
+        return ret;
+}
+
 struct local_vars_finder {
         struct probe_finder *pf;
         struct perf_probe_arg *args;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bed82716e1b4..0aec7704e395 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -76,7 +76,10 @@ struct probe_finder {
 
         /* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
-        Dwarf_CFI               *cfi;           /* Call Frame Information */
+        /* Call Frame Information from .eh_frame */
+        Dwarf_CFI               *cfi_eh;
+        /* Call Frame Information from .debug_frame */
+        Dwarf_CFI               *cfi_dbg;
 #endif
         Dwarf_Op                *fb_ops;        /* Frame base attribute */
         struct perf_probe_arg   *pvar;          /* Current target variable */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d5636ba94b20..40b7a0d0905b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1149,7 +1149,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 
                 machine = machines__find(machines, pid);
                 if (!machine)
-                        machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID);
+                        machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID);
                 return machine;
         }
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2f901d15e063..afb0c45eba34 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -310,7 +310,16 @@ int perf_stat_process_counter(struct perf_stat_config *config,
         int i, ret;
 
         aggr->val = aggr->ena = aggr->run = 0;
-        init_stats(ps->res_stats);
+
+        /*
+         * We calculate counter's data every interval,
+         * and the display code shows ps->res_stats
+         * avg value. We need to zero the stats for
+         * interval mode, otherwise overall avg running
+         * averages will be shown for each interval.
+         */
+        if (config->interval)
+                init_stats(ps->res_stats);
 
         if (counter->per_pkg)
                 zero_per_pkg(counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b2de6eb3376..ab02209a7cf3 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
          * Read the build id if possible. This is required for
          * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
          */
-        if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0)
+        if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
                 dso__set_build_id(dso, build_id);
 
         /*