Fixes for 5.15

Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/queue-5.15/perf-evlist-add-evlist__add_dummy_on_all_cpus.patch b/queue-5.15/perf-evlist-add-evlist__add_dummy_on_all_cpus.patch
new file mode 100644 (file)
index 0000000..8de4370
--- /dev/null
+++ b/queue-5.15/perf-evlist-add-evlist__add_dummy_on_all_cpus.patch
@@ -0,0 +1,106 @@
+From 0a003b10018e512d197f32f7f7ca076a62698289 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 24 May 2022 10:54:26 +0300
+Subject: perf evlist: Add evlist__add_dummy_on_all_cpus()
+
+From: Adrian Hunter <adrian.hunter@intel.com>
+
+[ Upstream commit 126d68fdcabed8c2ca5ffaba785add93ef722da8 ]
+
+Add evlist__add_dummy_on_all_cpus() to enable creating a system-wide dummy
+event that sets up the system-wide maps before map propagation.
+
+For convenience, add evlist__add_aux_dummy() so that the logic can be used
+whether or not the event needs to be system-wide.
+
+Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
+Acked-by: Ian Rogers <irogers@google.com>
+Acked-by: Namhyung Kim <namhyung@kernel.org>
+Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
+Cc: Ian Rogers <irogers@google.com>
+Cc: Jiri Olsa <jolsa@kernel.org>
+Cc: Leo Yan <leo.yan@linaro.org>
+Link: https://lore.kernel.org/r/20220524075436.29144-6-adrian.hunter@intel.com
+Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
+Stable-dep-of: f9cdeb58a9cf ("perf evlist: Avoid frequency mode for the dummy event")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ tools/perf/util/evlist.c | 45 ++++++++++++++++++++++++++++++++++++++++
+ tools/perf/util/evlist.h |  5 +++++
+ 2 files changed, 50 insertions(+)
+
+diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
+index 39d294f6c3218..a75cdcf381308 100644
+--- a/tools/perf/util/evlist.c
++++ b/tools/perf/util/evlist.c
+@@ -258,6 +258,51 @@ int evlist__add_dummy(struct evlist *evlist)
+       return 0;
+ }
+ 
++static void evlist__add_on_all_cpus(struct evlist *evlist, struct evsel *evsel)
++{
++      evsel->core.system_wide = true;
++
++      /*
++       * All CPUs.
++       *
++       * Note perf_event_open() does not accept CPUs that are not online, so
++       * in fact this CPU list will include only all online CPUs.
++       */
++      perf_cpu_map__put(evsel->core.own_cpus);
++      evsel->core.own_cpus = perf_cpu_map__new(NULL);
++      perf_cpu_map__put(evsel->core.cpus);
++      evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
++
++      /* No threads */
++      perf_thread_map__put(evsel->core.threads);
++      evsel->core.threads = perf_thread_map__new_dummy();
++
++      evlist__add(evlist, evsel);
++}
++
++struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
++{
++      struct evsel *evsel = evlist__dummy_event(evlist);
++
++      if (!evsel)
++              return NULL;
++
++      evsel->core.attr.exclude_kernel = 1;
++      evsel->core.attr.exclude_guest = 1;
++      evsel->core.attr.exclude_hv = 1;
++      evsel->core.attr.freq = 0;
++      evsel->core.attr.sample_period = 1;
++      evsel->no_aux_samples = true;
++      evsel->name = strdup("dummy:u");
++
++      if (system_wide)
++              evlist__add_on_all_cpus(evlist, evsel);
++      else
++              evlist__add(evlist, evsel);
++
++      return evsel;
++}
++
+ static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
+ {
+       struct evsel *evsel, *n;
+diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
+index ec177f783ee67..decf5c944adba 100644
+--- a/tools/perf/util/evlist.h
++++ b/tools/perf/util/evlist.h
+@@ -112,6 +112,11 @@ int __evlist__add_default_attrs(struct evlist *evlist,
+ int arch_evlist__add_default_attrs(struct evlist *evlist);
+ 
+ int evlist__add_dummy(struct evlist *evlist);
++struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide);
++static inline struct evsel *evlist__add_dummy_on_all_cpus(struct evlist *evlist)
++{
++      return evlist__add_aux_dummy(evlist, true);
++}
+ 
+ int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+                        evsel__sb_cb_t cb, void *data);
+-- 
+2.42.0
+

diff --git a/queue-5.15/perf-evlist-avoid-frequency-mode-for-the-dummy-event.patch b/queue-5.15/perf-evlist-avoid-frequency-mode-for-the-dummy-event.patch
new file mode 100644 (file)
index 0000000..8b7fe44
--- /dev/null
+++ b/queue-5.15/perf-evlist-avoid-frequency-mode-for-the-dummy-event.patch
@@ -0,0 +1,86 @@
+From da8f87e2b5cdc7a5ba2266e20827cb521e0961ef Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 15 Sep 2023 20:56:40 -0700
+Subject: perf evlist: Avoid frequency mode for the dummy event
+
+From: Ian Rogers <irogers@google.com>
+
+[ Upstream commit f9cdeb58a9cf46c09b56f5f661ea8da24b6458c3 ]
+
+Dummy events are created with an attribute where the period and freq
+are zero. evsel__config will then see the uninitialized values and
+initialize them in evsel__default_freq_period. As fequency mode is
+used by default the dummy event would be set to use frequency
+mode. However, this has no effect on the dummy event but does cause
+unnecessary timers/interrupts. Avoid this overhead by setting the
+period to 1 for dummy events.
+
+evlist__add_aux_dummy calls evlist__add_dummy then sets freq=0 and
+period=1. This isn't necessary after this change and so the setting is
+removed.
+
+From Stephane:
+
+The dummy event is not counting anything. It is used to collect mmap
+records and avoid a race condition during the synthesize mmap phase of
+perf record. As such, it should not cause any overhead during active
+profiling. Yet, it did. Because of a bug the dummy event was
+programmed as a sampling event in frequency mode. Events in that mode
+incur more kernel overheads because on timer tick, the kernel has to
+look at the number of samples for each event and potentially adjust
+the sampling period to achieve the desired frequency. The dummy event
+was therefore adding a frequency event to task and ctx contexts we may
+otherwise not have any, e.g.,
+
+  perf record -a -e cpu/event=0x3c,period=10000000/.
+
+On each timer tick the perf_adjust_freq_unthr_context() is invoked and
+if ctx->nr_freq is non-zero, then the kernel will loop over ALL the
+events of the context looking for frequency mode ones. In doing, so it
+locks the context, and enable/disable the PMU of each hw event. If all
+the events of the context are in period mode, the kernel will have to
+traverse the list for nothing incurring overhead. The overhead is
+multiplied by a very large factor when this happens in a guest kernel.
+There is no need for the dummy event to be in frequency mode, it does
+not count anything and therefore should not cause extra overhead for
+no reason.
+
+Fixes: 5bae0250237f ("perf evlist: Introduce perf_evlist__new_dummy constructor")
+Reported-by: Stephane Eranian <eranian@google.com>
+Signed-off-by: Ian Rogers <irogers@google.com>
+Acked-by: Adrian Hunter <adrian.hunter@intel.com>
+Cc: Yang Jihong <yangjihong1@huawei.com>
+Cc: Kan Liang <kan.liang@linux.intel.com>
+Link: https://lore.kernel.org/r/20230916035640.1074422-1-irogers@google.com
+Signed-off-by: Namhyung Kim <namhyung@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ tools/perf/util/evlist.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
+index 63ef40543a9fe..9d0f2feb25671 100644
+--- a/tools/perf/util/evlist.c
++++ b/tools/perf/util/evlist.c
+@@ -248,6 +248,9 @@ int evlist__add_dummy(struct evlist *evlist)
+               .type   = PERF_TYPE_SOFTWARE,
+               .config = PERF_COUNT_SW_DUMMY,
+               .size   = sizeof(attr), /* to capture ABI version */
++              /* Avoid frequency mode for dummy events to avoid associated timers. */
++              .freq = 0,
++              .sample_period = 1,
+       };
+       struct evsel *evsel = evsel__new_idx(&attr, evlist->core.nr_entries);
+ 
+@@ -268,8 +271,6 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
+       evsel->core.attr.exclude_kernel = 1;
+       evsel->core.attr.exclude_guest = 1;
+       evsel->core.attr.exclude_hv = 1;
+-      evsel->core.attr.freq = 0;
+-      evsel->core.attr.sample_period = 1;
+       evsel->core.system_wide = system_wide;
+       evsel->no_aux_samples = true;
+       evsel->name = strdup("dummy:u");
+-- 
+2.42.0
+

diff --git a/queue-5.15/perf-tools-get-rid-of-evlist__add_on_all_cpus.patch b/queue-5.15/perf-tools-get-rid-of-evlist__add_on_all_cpus.patch
new file mode 100644 (file)
index 0000000..a344093
--- /dev/null
+++ b/queue-5.15/perf-tools-get-rid-of-evlist__add_on_all_cpus.patch
@@ -0,0 +1,81 @@
+From 29da2f921a903316d2a22085056224a2d5251e9f Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 3 Oct 2022 13:46:45 -0700
+Subject: perf tools: Get rid of evlist__add_on_all_cpus()
+
+From: Namhyung Kim <namhyung@kernel.org>
+
+[ Upstream commit 60ea006f72512fd7c36f16cdbe91f4fc284f8115 ]
+
+The cpu and thread maps are properly handled in libperf now.  No need to
+do it in the perf tools anymore.  Let's remove the logic.
+
+Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
+Signed-off-by: Namhyung Kim <namhyung@kernel.org>
+Cc: Ian Rogers <irogers@google.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: Jiri Olsa <jolsa@kernel.org>
+Cc: Kan Liang <kan.liang@linux.intel.com>
+Cc: Leo Yan <leo.yan@linaro.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Link: https://lore.kernel.org/r/20221003204647.1481128-4-namhyung@kernel.org
+Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
+Stable-dep-of: f9cdeb58a9cf ("perf evlist: Avoid frequency mode for the dummy event")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ tools/perf/util/evlist.c | 29 ++---------------------------
+ 1 file changed, 2 insertions(+), 27 deletions(-)
+
+diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
+index a75cdcf381308..63ef40543a9fe 100644
+--- a/tools/perf/util/evlist.c
++++ b/tools/perf/util/evlist.c
+@@ -258,28 +258,6 @@ int evlist__add_dummy(struct evlist *evlist)
+       return 0;
+ }
+ 
+-static void evlist__add_on_all_cpus(struct evlist *evlist, struct evsel *evsel)
+-{
+-      evsel->core.system_wide = true;
+-
+-      /*
+-       * All CPUs.
+-       *
+-       * Note perf_event_open() does not accept CPUs that are not online, so
+-       * in fact this CPU list will include only all online CPUs.
+-       */
+-      perf_cpu_map__put(evsel->core.own_cpus);
+-      evsel->core.own_cpus = perf_cpu_map__new(NULL);
+-      perf_cpu_map__put(evsel->core.cpus);
+-      evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
+-
+-      /* No threads */
+-      perf_thread_map__put(evsel->core.threads);
+-      evsel->core.threads = perf_thread_map__new_dummy();
+-
+-      evlist__add(evlist, evsel);
+-}
+-
+ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
+ {
+       struct evsel *evsel = evlist__dummy_event(evlist);
+@@ -292,14 +270,11 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
+       evsel->core.attr.exclude_hv = 1;
+       evsel->core.attr.freq = 0;
+       evsel->core.attr.sample_period = 1;
++      evsel->core.system_wide = system_wide;
+       evsel->no_aux_samples = true;
+       evsel->name = strdup("dummy:u");
+ 
+-      if (system_wide)
+-              evlist__add_on_all_cpus(evlist, evsel);
+-      else
+-              evlist__add(evlist, evsel);
+-
++      evlist__add(evlist, evsel);
+       return evsel;
+ }
+ 
+-- 
+2.42.0
+

diff --git a/queue-5.15/series b/queue-5.15/series
index f90ab59c2c4dc455710c75fcc99da799fdd8f8ea..3aaa6311501d28b79a06f8922aaade134f4c9904 100644 (file)
--- a/queue-5.15/series
+++ b/queue-5.15/series
@@ -99,3 +99,6 @@ r8152-check-for-unplug-in-rtl_phy_patch_request.patch
 r8152-check-for-unplug-in-r8153b_ups_en-r8153c_ups_e.patch
 r8152-rename-rtl8152_unplug-to-rtl8152_inaccessible.patch
 powerpc-mm-fix-boot-crash-with-flatmem.patch
+perf-evlist-add-evlist__add_dummy_on_all_cpus.patch
+perf-tools-get-rid-of-evlist__add_on_all_cpus.patch
+perf-evlist-avoid-frequency-mode-for-the-dummy-event.patch