perf tools fixes for v6.5: 3rd batch

- Revert a patch that unconditionally resolved addresses to inlines in
   callchains, something that was done before when DWARF mode was asked
   for, but could as well be done when just frame pointers (the default)
   was selected. This enriches the callchains with inlines but the way to
   resolve it is gross right now, relying on addr2line, and even if we come
   up with an efficient way of processing all the associated DWARF info for
   a big file as vmlinux is, this has to be something people opt-in, as it
   will still result in overheads, so revert it until we get this done in a
   saner way.
 
 - Update the x86 msr-index.h header with the kernel original, no change
   in tooling output, just addresses a tools/perf build warning.
 
 - Resolve a regression where special "tool events", such as
   "duration_time" were being presented for all CPUs, when it only makes
   sense to show it for the workload, that is, just once.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCZNP/OAAKCRCyPKLppCJ+
 J7cGAQDgNpsAqGk+/Xkk7lPcp8aJ7q+5oaxv8iaGhdblq7V52gD+L2t8sNPQYWE3
 sy2QQ+9tsZiONfpdxknsduxoyfE+Vgs=
 =CRYB
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-fixes-for-v6.5-3-2023-08-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Revert a patch that unconditionally resolved addresses to inlines in
   callchains, something that was done before when DWARF mode was asked
   for, but could as well be done when just frame pointers (the default)
   was selected.

   This enriches the callchains with inlines but the way to resolve it
   is gross right now, relying on addr2line, and even if we come up with
   an efficient way of processing all the associated DWARF info for a
   big file as vmlinux is, this has to be something people opt-in, as it
   will still result in overheads, so revert it until we get this done
   in a saner way.

 - Update the x86 msr-index.h header with the kernel original, no change
   in tooling output, just addresses a tools/perf build warning.

  - Resolve a regression where special "tool events", such as
    "duration_time" were being presented for all CPUs, when it only
    makes sense to show it for the workload, that is, just once.

* tag 'perf-tools-fixes-for-v6.5-3-2023-08-09' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf stat: Don't display zero tool counts
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  Revert "perf report: Append inlines to non-DWARF callchains"

tools/arch/x86/include/asm/msr-index.h

@@ -545,6 +545,7 @@
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)
+#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9
 
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030

tools/perf/util/machine.c

@@ -45,7 +45,6 @@
 
 static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd,
 				     struct thread *th, bool lock);
-static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip);
 
 static struct dso *machine__kernel_dso(struct machine *machine)
 {
@@ -2385,10 +2384,6 @@ static int add_callchain_ip(struct thread *thread,
 	ms.maps = maps__get(al.maps);
 	ms.map = map__get(al.map);
 	ms.sym = al.sym;
-
-	if (!branch && append_inlines(cursor, &ms, ip) == 0)
-		goto out;
-
 	srcline = callchain_srcline(&ms, al.addr);
 	err = callchain_cursor_append(cursor, ip, &ms,
 				      branch, flags, nr_loop_iter,

tools/perf/util/stat-display.c

@@ -931,6 +931,11 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 	 */
 	if (config->aggr_mode == AGGR_THREAD && config->system_wide)
 		return true;
+
+	/* Tool events have the software PMU but are only gathered on 1. */
+	if (evsel__is_tool(counter))
+		return true;
+
 	/*
 	 * Skip value 0 when it's an uncore event and the given aggr id
 	 * does not belong to the PMU cpumask.