Merge tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Improvements for the flamegraph python script, including:
       - Display perf.data header
       - Display PIDs of user stacks
       - Added option to change color scheme
       - Default to blue/green color scheme to improve accessibility
       - Correctly identify kernel stacks when debuginfo is available

   - Improvements for 'perf bench futex':
       - Add --mlockall parameter
       - Add --broadcast and --pi to the 'requeue' sub benchmark

   - Add support for PMU aliases.

   - Introduce an ARM Coresight ETE decoder.

   - Add a 'perf bench' entry for evlist open/close operations, to help
     quantify improvements with multithreading 'perf record'.

   - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf
     script's python scripting.

   - Add a 'perf test' entry for PMU aliases.

   - Add a 'perf test' entry for 'perf record/perf report/perf script'
     pipe mode.

  Fixes:

   - perf script dlfilter (API for filtering via dynamically loaded
     shared object introduced in v5.14) fixes and a 'perf test' entry
     for it.

   - Fix get_current_dir_name() compilation on Android.

   - Fix issues with asciidoc and double dashes uses.

   - Fix memory leaks in the BTF handling code.

   - Fix leftover problems in the Documentation from the infrastructure
     originally lifted from the git codebase.

   - Fix *probe_vfs_getname.sh 'perf test' failures.

   - Handle fd gaps in 'perf test's test__dso_data_reopen().

   - Make sure to show disasembly warnings for 'perf annotate --stdio'.

   - Fix output from pipe to file and vice-versa in 'perf
     record/report/script'.

   - Correct 'perf data -h' output.

   - Fix wrong comm in system-wide mode with 'perf record --delay'.

   - Do not allow --for-each-cgroup without cpu in 'perf stat'

   - Make 'perf test --skip' work on shell tests.

   - Fix libperf's verbose printing.

  Misc improvements:

   - Preparatory patches for multithreading various 'perf record' phases
     (synthesizing, opening, recording, etc).

   - Add sparse context/locking annotations in compiler-types.h, also to
     help with the multithreading effort.

   - Optimize the generation of the arch specific erno tables used in
     'perf trace'.

   - Optimize libperf's perf_cpu_map__max().

   - Improve ARM's CoreSight warnings.

   - Report collisions in AUX records.

   - Improve warnings for the LLVM 'perf test' entry.

   - Improve the PMU events 'perf test' codebase.

   - perf test: Do not compare overheads in the zstd comp test

   - Better support annotation on ARM.

   - Update 'perf trace's cmd string table to decode sys_bpf() first
     arg.

  Vendor events:

   - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and
     Elhart Lake.

   - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake
     servers.

  Hardware tracing:

   - Improvements for the ARM hardware tracing auxtrace support"

* tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits)
  perf tests: Add test for PMU aliases
  perf pmu: Add PMU alias support
  perf session: Report collisions in AUX records
  perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event
  perf build: Report failure for testing feature libopencsd
  perf cs-etm: Show a warning for an unknown magic number
  perf cs-etm: Print the decoder name
  perf cs-etm: Create ETE decoder
  perf cs-etm: Update OpenCSD decoder for ETE
  perf cs-etm: Fix typo
  perf cs-etm: Save TRCDEVARCH register
  perf cs-etm: Refactor out ETMv4 header saving
  perf cs-etm: Initialise architecture based on TRCIDR1
  perf cs-etm: Refactor initialisation of decoder params.
  tools build: Fix feature detect clean for out of source builds
  perf evlist: Add evlist__for_each_entry_from() macro
  perf evsel: Handle precise_ip fallback in evsel__open_cpu()
  perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()
  perf evsel: Move test_attr__open() to success path in evsel__open_cpu()
  perf evsel: Move ignore_missing_thread() to fallback code
  ...

1 files changed, 50 insertions, 2 deletions

diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 31b53cc7d5bc..b3853aac3021 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -13,6 +13,20 @@
 #include <sys/types.h>
 #include <linux/futex.h>
 
+struct bench_futex_parameters {
+	bool silent;
+	bool fshared;
+	bool mlockall;
+	bool multi; /* lock-pi */
+	bool pi; /* requeue-pi */
+	bool broadcast; /* requeue */
+	unsigned int runtime; /* seconds*/
+	unsigned int nthreads;
+	unsigned int nfutexes;
+	unsigned int nwakes;
+	unsigned int nrequeue;
+};
+
 /**
  * futex() - SYS_futex syscall wrapper
  * @uaddr:	address of first futex
@@ -20,7 +34,7 @@
  * @val:	typically expected value of uaddr, but varies by op
  * @timeout:	typically an absolute struct timespec (except where noted
  *		otherwise). Overloaded by some ops
- * @uaddr2:	address of second futex for some ops\
+ * @uaddr2:	address of second futex for some ops
  * @val3:	varies by op
  * @opflags:	flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG
  *
@@ -77,7 +91,7 @@ futex_unlock_pi(u_int32_t *uaddr, int opflags)
 /**
 * futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
 * @nr_wake:        wake up to this many tasks
-* @nr_requeue:        requeue up to this many tasks
+* @nr_requeue:     requeue up to this many tasks
 */
 static inline int
 futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
@@ -86,4 +100,38 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
 		 val, opflags);
 }
+
+/**
+ * futex_wait_requeue_pi() - block on uaddr and prepare to requeue to uaddr2
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ *
+ * This is the first half of the requeue_pi mechanism. It shall always be
+ * paired with futex_cmp_requeue_pi().
+ */
+static inline int
+futex_wait_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+		      struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0,
+		     opflags);
+}
+
+/**
+ * futex_cmp_requeue_pi() - requeue tasks from uaddr to uaddr2
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ * @nr_requeue:	requeue up to this many tasks
+ *
+ * This is the second half of the requeue_pi mechanism. It shall always be
+ * paired with futex_wait_requeue_pi(). The first waker is always awoken.
+ */
+static inline int
+futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+		     int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2,
+		     val, opflags);
+}
+
 #endif /* _FUTEX_H */