Merge tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

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

   - Support instruction latency in 'perf report', with both memory
     latency (weight) and instruction latency information, users can
     locate expensive load instructions and understand time spent in
     different stages.

   - Extend 'perf c2c' to display the number of loads which were blocked
     by data or address conflict.

   - Add 'perf stat' support for L2 topdown events in systems such as
     Intel's Sapphire rapids server.

   - Add support for PERF_SAMPLE_CODE_PAGE_SIZE in various tools, as a
     sort key, for instance:

        perf report --stdio --sort=comm,symbol,code_page_size

   - New 'perf daemon' command to run long running sessions while
     providing a way to control the enablement of events without
     restarting a traditional 'perf record' session.

   - Enable counting events for BPF programs in 'perf stat' just like
     for other targets (tid, cgroup, cpu, etc), e.g.:

        # perf stat -e ref-cycles,cycles -b 254 -I 1000
           1.487903822            115,200      ref-cycles
           1.487903822             86,012      cycles
           2.489147029             80,560      ref-cycles
           2.489147029             73,784      cycles
        ^C

     The example above counts 'cycles' and 'ref-cycles' of BPF program
     of id 254. It is similar to bpftool-prog-profile command, but more
     flexible.

   - Support the new layout for PERF_RECORD_MMAP2 to carry the DSO
     build-id using infrastructure generalised from the eBPF subsystem,
     removing the need for traversing the perf.data file to collect
     build-ids at the end of 'perf record' sessions and helping with
     long running sessions where binaries can get replaced in updates,
     leading to possible mis-resolution of symbols.

   - Support filtering by hex address in 'perf script'.

   - Support DSO filter in 'perf script', like in other perf tools.

   - Add namespaces support to 'perf inject'

   - Add support for SDT (Dtrace Style Markers) events on ARM64.

  perf record:

   - Fix handling of eventfd() when draining a buffer in 'perf record'.

   - Improvements to the generation of metadata events for pre-existing
     threads (mmaps, comm, etc), speeding up the work done at the start
     of system wide or per CPU 'perf record' sessions.

  Hardware tracing:

   - Initial support for tracing KVM with Intel PT.

   - Intel PT fixes for IPC

   - Support Intel PT PSB (synchronization packets) events.

   - Automatically group aux-output events to overcome --filter syntax.

   - Enable PERF_SAMPLE_DATA_SRC on ARMs SPE.

   - Update ARM's CoreSight hardware tracing OpenCSD library to v1.0.0.

  perf annotate TUI:

   - Fix handling of 'k' ("show line number") hotkey

   - Fix jump parsing for C++ code.

  perf probe:

   - Add protection to avoid endless loop.

  cgroups:

   - Avoid reading cgroup mountpoint multiple times, caching it.

   - Fix handling of cgroup v1/v2 in mixed hierarchy.

  Symbol resolving:

   - Add OCaml symbol demangling.

   - Further fixes for handling PE executables when using perf with Wine
     and .exe/.dll files.

   - Fix 'perf unwind' DSO handling.

   - Resolve symbols against debug file first, to deal with artifacts
     related to LTO.

   - Fix gap between kernel end and module start on powerpc.

  Reporting tools:

   - The DSO filter shouldn't show samples in unresolved maps.

   - Improve debuginfod support in various tools.

  build ids:

   - Fix 16-byte build ids in 'perf buildid-cache', add a 'perf test'
     entry for that case.

  perf test:

   - Support for PERF_SAMPLE_WEIGHT_STRUCT.

   - Add test case for PERF_SAMPLE_CODE_PAGE_SIZE.

   - Shell based tests for 'perf daemon's commands ('start', 'stop,
     'reconfig', 'list', etc).

   - ARM cs-etm 'perf test' fixes.

   - Add parse-metric memory bandwidth testcase.

  Compiler related:

   - Fix 'perf probe' kretprobe issue caused by gcc 11 bug when used
     with -fpatchable-function-entry.

   - Fix ARM64 build with gcc 11's -Wformat-overflow.

   - Fix unaligned access in sample parsing test.

   - Fix printf conversion specifier for IP addresses on arm64, s390 and
     powerpc.

  Arch specific:

   - Support exposing Performance Monitor Counter SPRs as part of
     extended regs on powerpc.

   - Add JSON 'perf stat' metrics for ARM64's imx8mp, imx8mq and imx8mn
     DDR, fix imx8mm ones.

   - Fix common and uarch events for ARM64's A76 and Ampere eMag"

* tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (148 commits)
  perf buildid-cache: Don't skip 16-byte build-ids
  perf buildid-cache: Add test for 16-byte build-id
  perf symbol: Remove redundant libbfd checks
  perf test: Output the sub testing result in cs-etm
  perf test: Suppress logs in cs-etm testing
  perf tools: Fix arm64 build error with gcc-11
  perf intel-pt: Add documentation for tracing virtual machines
  perf intel-pt: Split VM-Entry and VM-Exit branches
  perf intel-pt: Adjust sample flags for VM-Exit
  perf intel-pt: Allow for a guest kernel address filter
  perf intel-pt: Support decoding of guest kernel
  perf machine: Factor out machine__idle_thread()
  perf machine: Factor out machines__find_guest()
  perf intel-pt: Amend decoder to track the NR flag
  perf intel-pt: Retain the last PIP packet payload as is
  perf intel_pt: Add vmlaunch and vmresume as branches
  perf script: Add branch types for VM-Entry and VM-Exit
  perf auxtrace: Automatically group aux-output events
  perf test: Fix unaligned access in sample parsing test
  perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing
  ...

1 files changed, 108 insertions, 1 deletions

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 80907bc32683..0d5ad42812b9 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -36,7 +36,7 @@ const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
 const char	*default_sort_order = "comm,dso,symbol";
 const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
 const char	default_tracepoint_sort_order[] = "trace";
@@ -1365,6 +1365,49 @@ struct sort_entry sort_global_weight = {
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
 
+static u64 he_ins_lat(struct hist_entry *he)
+{
+		return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
+}
+
+static int64_t
+sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+		return he_ins_lat(left) - he_ins_lat(right);
+}
+
+static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
+					      size_t size, unsigned int width)
+{
+		return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+}
+
+struct sort_entry sort_local_ins_lat = {
+	.se_header	= "Local INSTR Latency",
+	.se_cmp		= sort__local_ins_lat_cmp,
+	.se_snprintf	= hist_entry__local_ins_lat_snprintf,
+	.se_width_idx	= HISTC_LOCAL_INS_LAT,
+};
+
+static int64_t
+sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+		return left->stat.ins_lat - right->stat.ins_lat;
+}
+
+static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
+					       size_t size, unsigned int width)
+{
+		return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+}
+
+struct sort_entry sort_global_ins_lat = {
+	.se_header	= "INSTR Latency",
+	.se_cmp		= sort__global_ins_lat_cmp,
+	.se_snprintf	= hist_entry__global_ins_lat_snprintf,
+	.se_width_idx	= HISTC_GLOBAL_INS_LAT,
+};
+
 struct sort_entry sort_mem_daddr_sym = {
 	.se_header	= "Data Symbol",
 	.se_cmp		= sort__daddr_cmp,
@@ -1422,6 +1465,41 @@ struct sort_entry sort_mem_dcacheline = {
 };
 
 static int64_t
+sort__blocked_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_blk = PERF_MEM_BLK_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_blk = PERF_MEM_BLK_NA;
+
+	return (int64_t)(data_src_r.mem_blk - data_src_l.mem_blk);
+}
+
+static int hist_entry__blocked_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	char out[16];
+
+	perf_mem__blk_scnprintf(out, sizeof(out), he->mem_info);
+	return repsep_snprintf(bf, size, "%.*s", width, out);
+}
+
+struct sort_entry sort_mem_blocked = {
+	.se_header	= "Blocked",
+	.se_cmp		= sort__blocked_cmp,
+	.se_snprintf	= hist_entry__blocked_snprintf,
+	.se_width_idx	= HISTC_MEM_BLOCKED,
+};
+
+static int64_t
 sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	uint64_t l = 0, r = 0;
@@ -1492,6 +1570,31 @@ struct sort_entry sort_mem_data_page_size = {
 };
 
 static int64_t
+sort__code_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = left->code_page_size;
+	uint64_t r = right->code_page_size;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__code_page_size_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+	char str[PAGE_SIZE_NAME_LEN];
+
+	return repsep_snprintf(bf, size, "%-*s", width,
+			       get_page_size_name(he->code_page_size, str));
+}
+
+struct sort_entry sort_code_page_size = {
+	.se_header	= "Code Page Size",
+	.se_cmp		= sort__code_page_size_cmp,
+	.se_snprintf	= hist_entry__code_page_size_snprintf,
+	.se_width_idx	= HISTC_CODE_PAGE_SIZE,
+};
+
+static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	if (!left->branch_info || !right->branch_info)
@@ -1735,6 +1838,9 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
 	DIM(SORT_TIME, "time", sort_time),
+	DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
+	DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
+	DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
 };
 
 #undef DIM
@@ -1770,6 +1876,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 	DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
 	DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size),
+	DIM(SORT_MEM_BLOCKED, "blocked", sort_mem_blocked),
 };
 
 #undef DIM