Merge tag 'perf-tools-fixes-for-v6.2-2-2023-01-11' of...

Merge tag 'perf-tools-fixes-for-v6.2-2-2023-01-11' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Make 'perf kmem' cope with the removal of some
   kmem:kmem_cache_alloc_node and kmem:kmalloc_node in the
   11e9734b ("mm/slab_common: unify NUMA and UMA version of
   tracepoints") commit, making sure it works with Linux >= 6.2 as well
   as with older kernels where those tracepoints are present.

 - Also make it handle the new "node" kmem:kmalloc and
   kmem:kmem_cache_alloc tracepoint field introduced in that same
   commit.

 - Fix hardware tracing PMU address filter duplicate symbol selection,
   that was preventing to match with static functions with the same name
   present in different object files.

 - Fix regression on what linux/types.h file gets used to build the "BPF
   prologue" 'perf test' entry, the system one lacks the fmode_t
   definition used in this test, so provide that type in the test
   itself.

 - Avoid build breakage with libbpf < 0.8.0 + LIBBPF_DYNAMIC=1. If the
   user asks for linking with the libbpf package provided by the distro,
   then it has to be >= 0.8.0. Using the libbpf supplied with the kernel
   would be a fallback in that case.

 - Fix the build when libbpf isn't available or explicitly disabled via
   NO_LIBBPF=1.

 - Don't try to install libtraceevent plugins as its not anymore in the
   kernel sources and will thus always fail.

* tag 'perf-tools-fixes-for-v6.2-2-2023-01-11' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf auxtrace: Fix address filter duplicate symbol selection
  perf bpf: Avoid build breakage with libbpf < 0.8.0 + LIBBPF_DYNAMIC=1
  perf build: Fix build error when NO_LIBBPF=1
  perf tools: Don't install libtraceevent plugins as its not anymore in the kernel sources
  perf kmem: Support field "node" in evsel__process_alloc_event() coping with recent tracepoint restructuring
  perf kmem: Support legacy tracepoints
  perf build: Properly guard libbpf includes
  perf tests bpf prologue: Fix bpf-script-test-prologue test compile issue with clang

tools/perf/Makefile.config

@@ -589,6 +589,8 @@ ifndef NO_LIBELF
           $(call feature_check,libbpf-bpf_program__set_insns)
           ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
             CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+          else
+            dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources);
           endif
           $(call feature_check,libbpf-btf__raw_data)
           ifeq ($(feature-libbpf-btf__raw_data), 1)
@@ -602,6 +604,8 @@ ifndef NO_LIBELF
           dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
         endif
       else
+        # Libbpf will be built as a static library from tools/lib/bpf.
+	LIBBPF_STATIC := 1
 	CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
         CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
         CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
@@ -1314,14 +1318,6 @@ tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
 export perfexec_instdir_SQ
 
-# If we install to $(HOME) we keep the traceevent default:
-# $(HOME)/.traceevent/plugins
-# Otherwise we install plugins into the global $(libdir).
-ifdef DESTDIR
-plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(plugindir))
-endif
-
 print_var = $(eval $(print_var_code)) $(info $(MSG))
 define print_var_code
     MSG = $(shell printf '...%40s: %s' $(1) $($(1)))

tools/perf/Makefile.perf

@@ -303,10 +303,12 @@ ifneq ($(OUTPUT),)
 else
   LIBBPF_OUTPUT = $(CURDIR)/libbpf
 endif
-LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
-LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
-LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
-CFLAGS += -I$(LIBBPF_OUTPUT)/include
+ifdef LIBBPF_STATIC
+  LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
+  LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
+  LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
+  CFLAGS += -I$(LIBBPF_OUTPUT)/include
+endif
 
 ifneq ($(OUTPUT),)
   LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd
@@ -393,10 +395,8 @@ endif
 export PERL_PATH
 
 PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL)
-ifndef NO_LIBBPF
-  ifndef LIBBPF_DYNAMIC
+ifdef LIBBPF_STATIC
   PERFLIBS += $(LIBBPF)
-  endif
 endif
 
 # We choose to avoid "if .. else if .. else .. endif endif"
@@ -756,12 +756,15 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(arch_errno_name_array) \
 	$(sync_file_range_arrays) \
 	$(LIBAPI) \
-	$(LIBBPF) \
 	$(LIBPERF) \
 	$(LIBSUBCMD) \
 	$(LIBSYMBOL) \
 	bpf-skel
 
+ifdef LIBBPF_STATIC
+prepare: $(LIBBPF)
+endif
+
 $(OUTPUT)%.o: %.c prepare FORCE
 	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
 

tools/perf/builtin-kmem.c

@@ -26,6 +26,7 @@
 #include "util/string2.h"
 
 #include <linux/kernel.h>
+#include <linux/numa.h>
 #include <linux/rbtree.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
@@ -185,22 +186,33 @@ static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *s
 	total_allocated += bytes_alloc;
 
 	nr_allocs++;
-	return 0;
-}
 
-static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample)
-{
-	int ret = evsel__process_alloc_event(evsel, sample);
+	/*
+	 * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA
+	 * version of tracepoints") adds the field "node" into the
+	 * tracepoints 'kmalloc' and 'kmem_cache_alloc'.
+	 *
+	 * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node'
+	 * also contain the field "node".
+	 *
+	 * If the tracepoint contains the field "node" the tool stats the
+	 * cross allocation.
+	 */
+	if (evsel__field(evsel, "node")) {
+		int node1, node2;
 
-	if (!ret) {
-		int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
+		node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu});
 		node2 = evsel__intval(evsel, sample, "node");
 
-		if (node1 != node2)
+		/*
+		 * If the field "node" is NUMA_NO_NODE (-1), we don't take it
+		 * as a cross allocation.
+		 */
+		if ((node2 != NUMA_NO_NODE) && (node1 != node2))
 			nr_cross_allocs++;
 	}
 
-	return ret;
+	return 0;
 }
 
 static int ptr_cmp(void *, void *);
@@ -1369,8 +1381,8 @@ static int __cmd_kmem(struct perf_session *session)
 		/* slab allocator */
 		{ "kmem:kmalloc",		evsel__process_alloc_event, },
 		{ "kmem:kmem_cache_alloc",	evsel__process_alloc_event, },
-		{ "kmem:kmalloc_node",		evsel__process_alloc_node_event, },
-		{ "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, },
+		{ "kmem:kmalloc_node",		evsel__process_alloc_event, },
+		{ "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, },
 		{ "kmem:kfree",			evsel__process_free_event, },
 		{ "kmem:kmem_cache_free",	evsel__process_free_event, },
 		/* page allocator */
@@ -1824,6 +1836,19 @@ static int parse_line_opt(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static bool slab_legacy_tp_is_exposed(void)
+{
+	/*
+	 * The tracepoints "kmem:kmalloc_node" and
+	 * "kmem:kmem_cache_alloc_node" have been removed on the latest
+	 * kernel, if the tracepoint "kmem:kmalloc_node" is existed it
+	 * means the tool is running on an old kernel, we need to
+	 * rollback to support these legacy tracepoints.
+	 */
+	return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ?
+		false : true;
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	const char * const record_args[] = {
@@ -1831,22 +1856,28 @@ static int __cmd_record(int argc, const char **argv)
 	};
 	const char * const slab_events[] = {
 	"-e", "kmem:kmalloc",
-	"-e", "kmem:kmalloc_node",
 	"-e", "kmem:kfree",
 	"-e", "kmem:kmem_cache_alloc",
-	"-e", "kmem:kmem_cache_alloc_node",
 	"-e", "kmem:kmem_cache_free",
 	};
+	const char * const slab_legacy_events[] = {
+	"-e", "kmem:kmalloc_node",
+	"-e", "kmem:kmem_cache_alloc_node",
+	};
 	const char * const page_events[] = {
 	"-e", "kmem:mm_page_alloc",
 	"-e", "kmem:mm_page_free",
 	};
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
+	unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed();
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
-	if (kmem_slab)
+	if (kmem_slab) {
 		rec_argc += ARRAY_SIZE(slab_events);
+		if (slab_legacy_tp_exposed)
+			rec_argc += ARRAY_SIZE(slab_legacy_events);
+	}
 	if (kmem_page)
 		rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
 
@@ -1861,6 +1892,10 @@ static int __cmd_record(int argc, const char **argv)
 	if (kmem_slab) {
 		for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
 			rec_argv[i] = strdup(slab_events[j]);
+		if (slab_legacy_tp_exposed) {
+			for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++)
+				rec_argv[i] = strdup(slab_legacy_events[j]);
+		}
 	}
 	if (kmem_page) {
 		rec_argv[i++] = strdup("-g");

tools/perf/builtin-trace.c

@@ -16,7 +16,9 @@
 
 #include "util/record.h"
 #include <api/fs/tracing_path.h>
+#ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/bpf.h>
+#endif
 #include "util/bpf_map.h"
 #include "util/rlimit.h"
 #include "builtin.h"

tools/perf/tests/bpf-script-test-prologue.c

@@ -20,6 +20,8 @@
 # undef if
 #endif
 
+typedef unsigned int __bitwise fmode_t;
+
 #define FMODE_READ		0x1
 #define FMODE_WRITE		0x2
 

tools/perf/tests/make

@@ -222,19 +222,7 @@ installed_files_bin := bin/perf
 installed_files_bin += etc/bash_completion.d/perf
 installed_files_bin += libexec/perf-core/perf-archive
 
-installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
-
 installed_files_all := $(installed_files_bin)
-installed_files_all += $(installed_files_plugins)
 
 test_make_install       := $(call test_dest_files,$(installed_files_all))
 test_make_install_O     := $(call test_dest_files,$(installed_files_all))

tools/perf/util/auxtrace.c

@@ -2611,7 +2611,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 				*size = sym->start - *start;
 			if (idx > 0) {
 				if (*size)
-					return 1;
+					return 0;
 			} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
 				print_duplicate_syms(dso, sym_name);
 				return -EINVAL;

tools/perf/util/bpf_counter.h

@@ -4,9 +4,12 @@
 
 #include <linux/list.h>
 #include <sys/resource.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
+#endif
 
 struct evsel;
 struct target;
@@ -87,6 +90,8 @@ static inline void set_max_rlimit(void)
 	setrlimit(RLIMIT_MEMLOCK, &rinf);
 }
 
+#ifdef HAVE_BPF_SKEL
+
 static inline __u32 bpf_link_get_id(int fd)
 {
 	struct bpf_link_info link_info = { .id = 0, };
@@ -127,5 +132,6 @@ static inline int bperf_trigger_reading(int prog_fd, int cpu)
 
 	return bpf_prog_test_run_opts(prog_fd, &opts);
 }
+#endif /* HAVE_BPF_SKEL */
 
 #endif /* __PERF_BPF_COUNTER_H */