Merge tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - cgroup improvements for 'perf stat', allowing for compact
   specification of events and cgroups in the command line.

 - Support per thread topdown metrics in 'perf stat'.

 - Support sample-read topdown metric group in 'perf record'

 - Show start of latency in addition to its start in 'perf sched
   latency'.

 - Add min, max to 'perf script' futex-contention output, in addition to
   avg.

 - Allow usage of 'perf_event_attr->exclusive' attribute via the new
   ':e' event modifier.

 - Add 'snapshot' command to 'perf record --control', using it with
   Intel PT.

 - Support FIFO file names as alternative options to 'perf record
   --control'.

 - Introduce branch history "streams", to compare 'perf record' runs
   with 'perf diff' based on branch records and report hot streams.

 - Support PE executable symbol tables using libbfd, to profile, for
   instance, wine binaries.

 - Add filter support for option 'perf ftrace -F/--funcs'.

 - Allow configuring the 'disassembler_style' 'perf annotate' knob via
   'perf config'

 - Update CascadelakeX and SkylakeX JSON vendor events files.

 - Add support for parsing perchip/percore JSON vendor events.

 - Add power9 hv_24x7 core level metric events.

 - Add L2 prefetch, ITLB instruction fetch hits JSON events for AMD
   zen1.

 - Enable Family 19h users by matching Zen2 AMD vendor events.

 - Use debuginfod in 'perf probe' when required debug files not found
   locally.

 - Display negative tid in non-sample events in 'perf script'.

 - Make GTK2 support opt-in

 - Add build test with GTK+

 - Add missing -lzstd to the fast path feature detection

 - Add scripts to auto generate 'mmap', 'mremap' string<->id tables for
   use in 'perf trace'.

 - Show python test script in verbose mode.

 - Fix uncore metric expressions

 - Msan uninitialized use fixes.

 - Use condition variables in 'perf bench numa'

 - Autodetect python3 binary in systems without python2.

 - Support md5 build ids in addition to sha1.

 - Add build id 'perf test' regression test.

 - Fix printable strings in python3 scripts.

 - Fix off by ones in 'perf trace' in arches using libaudit.

 - Fix JSON event code for events referencing std arch events.

 - Introduce 'perf test' shell script for Arm CoreSight testing.

 - Add rdtsc() for Arm64 for used in the PERF_RECORD_TIME_CONV metadata
   event and in 'perf test tsc'.

 - 'perf c2c' improvements: Add "RMT Load Hit" metric, "Total Stores",
   fixes and documentation update.

 - Fix usage of reloc_sym in 'perf probe' when using both kallsyms and
   debuginfo files.

 - Do not print 'Metric Groups:' unnecessarily in 'perf list'

 - Refcounting fixes in the event parsing code.

 - Add expand cgroup event 'perf test' entry.

 - Fix out of bounds CPU map access when handling armv8_pmu events in
   'perf stat'.

 - Add build-id injection 'perf bench' benchmark.

 - Enter namespace when reading build-id in 'perf inject'.

 - Do not load map/dso when injecting build-id speeding up the 'perf
   inject' process.

 - Add --buildid-all option to avoid processing all samples, just the
   mmap metadata events.

 - Add feature test to check if libbfd has buildid support

 - Add 'perf test' entry for PE binary format support.

 - Fix typos in power8 PMU vendor events JSON files.

 - Hide libtraceevent non API functions.

* tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (113 commits)
  perf c2c: Update documentation for metrics reorganization
  perf c2c: Add metrics "RMT Load Hit"
  perf c2c: Correct LLC load hit metrics
  perf c2c: Change header for LLC local hit
  perf c2c: Use more explicit headers for HITM
  perf c2c: Change header from "LLC Load Hitm" to "Load Hitm"
  perf c2c: Organize metrics based on memory hierarchy
  perf c2c: Display "Total Stores" as a standalone metrics
  perf c2c: Display the total numbers continuously
  perf bench: Use condition variables in numa.
  perf jevents: Fix event code for events referencing std arch events
  perf diff: Support hot streams comparison
  perf streams: Report hot streams
  perf streams: Calculate the sum of total streams hits
  perf streams: Link stream pair
  perf streams: Compare two streams
  perf streams: Get the evsel_streams by evsel_idx
  perf streams: Introduce branch history "streams"
  perf intel-pt: Improve PT documentation slightly
  perf tools: Add support for exclusive groups/events
  ...

1 files changed, 99 insertions, 0 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 2775b752f2fa..1b60985690bb 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1613,3 +1613,102 @@ void callchain_param_setup(u64 sample_type)
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
 }
+
+static bool chain_match(struct callchain_list *base_chain,
+			struct callchain_list *pair_chain)
+{
+	enum match_result match;
+
+	match = match_chain_strings(base_chain->srcline,
+				    pair_chain->srcline);
+	if (match != MATCH_ERROR)
+		return match == MATCH_EQ;
+
+	match = match_chain_dso_addresses(base_chain->ms.map,
+					  base_chain->ip,
+					  pair_chain->ms.map,
+					  pair_chain->ip);
+
+	return match == MATCH_EQ;
+}
+
+bool callchain_cnode_matched(struct callchain_node *base_cnode,
+			     struct callchain_node *pair_cnode)
+{
+	struct callchain_list *base_chain, *pair_chain;
+	bool match = false;
+
+	pair_chain = list_first_entry(&pair_cnode->val,
+				      struct callchain_list,
+				      list);
+
+	list_for_each_entry(base_chain, &base_cnode->val, list) {
+		if (&pair_chain->list == &pair_cnode->val)
+			return false;
+
+		if (!base_chain->srcline || !pair_chain->srcline) {
+			pair_chain = list_next_entry(pair_chain, list);
+			continue;
+		}
+
+		match = chain_match(base_chain, pair_chain);
+		if (!match)
+			return false;
+
+		pair_chain = list_next_entry(pair_chain, list);
+	}
+
+	/*
+	 * Say chain1 is ABC, chain2 is ABCD, we consider they are
+	 * not fully matched.
+	 */
+	if (pair_chain && (&pair_chain->list != &pair_cnode->val))
+		return false;
+
+	return match;
+}
+
+static u64 count_callchain_hits(struct hist_entry *he)
+{
+	struct rb_root *root = &he->sorted_chain;
+	struct rb_node *rb_node = rb_first(root);
+	struct callchain_node *node;
+	u64 chain_hits = 0;
+
+	while (rb_node) {
+		node = rb_entry(rb_node, struct callchain_node, rb_node);
+		chain_hits += node->hit;
+		rb_node = rb_next(rb_node);
+	}
+
+	return chain_hits;
+}
+
+u64 callchain_total_hits(struct hists *hists)
+{
+	struct rb_node *next = rb_first_cached(&hists->entries);
+	u64 chain_hits = 0;
+
+	while (next) {
+		struct hist_entry *he = rb_entry(next, struct hist_entry,
+						 rb_node);
+
+		chain_hits += count_callchain_hits(he);
+		next = rb_next(&he->rb_node);
+	}
+
+	return chain_hits;
+}
+
+s64 callchain_avg_cycles(struct callchain_node *cnode)
+{
+	struct callchain_list *chain;
+	s64 cycles = 0;
+
+	list_for_each_entry(chain, &cnode->val, list) {
+		if (chain->srcline && chain->branch_count)
+			cycles += chain->cycles_count / chain->branch_count;
+	}
+
+	return cycles;
+}