Merge tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Use BPF + BTF to collect and pretty print syscall and tracepoint
   arguments in 'perf trace', done as an GSoC activity

 - Data-type profiling improvements:

     - Cache debuginfo to speed up data type resolution

     - Add the 'typecln' sort order, to show which cacheline in a target
       is hot or cold. The following shows members in the cfs_rq's first
       cache line:

         $ perf report -s type,typecln,typeoff -H
         ...
         -    2.67%        struct cfs_rq
            +    1.23%        struct cfs_rq: cache-line 2
            +    0.57%        struct cfs_rq: cache-line 4
            +    0.46%        struct cfs_rq: cache-line 6
            -    0.41%        struct cfs_rq: cache-line 0
                    0.39%        struct cfs_rq +0x14 (h_nr_running)
                    0.02%        struct cfs_rq +0x38 (tasks_timeline.rb_leftmost)

     - When a typedef resolves to a unnamed struct, use the typedef name

     - When a struct has just one basic type field (int, etc), resolve
       the type sort order to the name of the struct, not the type of
       the field

     - Support type folding/unfolding in the data-type annotation TUI

     - Fix bitfields offsets and sizes

     - Initial support for PowerPC, using libcapstone and the usual
       objdump disassembly parsing routines

 - Add support for disassembling and addr2line using the LLVM libraries,
   speeding up those operations

 - Support --addr2line option in 'perf script' as with other tools

 - Intel branch counters (LBR event logging) support, only available in
   recent Intel processors, for instance, the new "brcntr" field can be
   asked from 'perf script' to print the information collected from this
   feature:

     $ perf script -F +brstackinsn,+brcntr

     # Branch counter abbr list:
     # branch-instructions:ppp = A
     # branch-misses = B
     # '-' No event occurs
     # '+' Event occurrences may be lost due to branch counter saturated
         tchain_edit  332203 3366329.405674:  53030 branch-instructions:ppp:    401781 f3+0x2c (home/sdp/test/tchain_edit)
            f3+31:
         0000000000401774   insn: eb 04                  br_cntr: AA  # PRED 5 cycles [5]
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 1 cycles [6] 2.00 IPC
         0000000000401766   insn: 8b 45 fc
         0000000000401769   insn: 83 e0 01
         000000000040176c   insn: 85 c0
         000000000040176e   insn: 74 06                  br_cntr: A   # PRED 1 cycles [7] 4.00 IPC
         0000000000401776   insn: 83 45 fc 01
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 7 cycles [14] 0.43 IPC

 - Support Timed PEBS (Precise Event-Based Sampling), a recent hardware
   feature in Intel processors

 - Add 'perf ftrace profile' subcommand, using ftrace's function-graph
   tracer so that users can see the total, average, max execution time
   as well as the number of invocations easily, for instance:

     $ sudo perf ftrace profile -G __x64_sys_perf_event_open -- \
       perf stat -e cycles -C1 true 2> /dev/null | head
     # Total (us)  Avg (us)  Max (us)  Count  Function
           65.611    65.611    65.611      1  __x64_sys_perf_event_open
           30.527    30.527    30.527      1  anon_inode_getfile
           30.260    30.260    30.260      1  __anon_inode_getfile
           29.700    29.700    29.700      1  alloc_file_pseudo
           17.578    17.578    17.578      1  d_alloc_pseudo
           17.382    17.382    17.382      1  __d_alloc
           16.738    16.738    16.738      1  kmem_cache_alloc_lru
           15.686    15.686    15.686      1  perf_event_alloc
           14.012     7.006    11.264      2  obj_cgroup_charge

 - 'perf sched timehist' improvements, including the addition of
   priority showing/filtering command line options

 - Varios improvements to the 'perf probe', including 'perf test'
   regression testings

 - Introduce the 'perf check', initially to check if some feature is
   in place, using it in 'perf test'

 - Various fixes for 32-bit systems

 - Address more leak sanitizer failures

 - Fix memory leaks (LBR, disasm lock ops, etc)

 - More reference counting fixes (branch_info, etc)

 - Constify 'struct perf_tool' parameters to improve code generation
   and reduce the chances of having its internals changed, which isn't
   expected

 - More constifications in various other places

 - Add more build tests, including for JEVENTS

 - Add more 'perf test' entries ('perf record LBR', pipe/inject,
   --setup-filter, 'perf ftrace', 'cgroup sampling', etc)

 - Inject build ids for all entries in a call chain in 'perf inject',
   not just for the main sample

 - Improve the BPF based sample filter, allowing root to setup filters
   in bpffs that then can be used by non-root users

 - Allow filtering by cgroups with the BPF based sample filter

 - Allow a more compact way for 'perf mem report' using the
   -T/--type-profile and also provide a --sort option similar to the one
   in 'perf report', 'perf top', to setup the sort order manually

 - Fix --group behavior in 'perf annotate' when leader has no samples,
   where it was not showing anything even when other events in the group
   had samples

 - Fix spinlock and rwlock accounting in 'perf lock contention'

 - Fix libsubcmd fixdep Makefile dependencies

 - Improve 'perf ftrace' error message when ftrace isn't available

 - Update various Intel JSON vendor event files

 - ARM64 CoreSight hardware tracing infrastructure improvements, mostly
   not visible to users

 - Update power10 JSON events

* tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (310 commits)
  perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space
  perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space
  perf env: Find correct branch counter info on hybrid
  perf evlist: Print hint for group
  tools: Drop nonsensical -O6
  perf pmu: To info add event_type_desc
  perf evsel: Add accessor for tool_event
  perf pmus: Fake PMU clean up
  perf list: Avoid potential out of bounds memory read
  perf help: Fix a typo ("bellow")
  perf ftrace: Detect whether ftrace is enabled on system
  perf test shell probe_vfs_getname: Remove extraneous '=' from probe line number regex
  perf build: Require at least clang 16.0.6 to build BPF skeletons
  perf trace: If a syscall arg is marked as 'const', assume it is coming _from_ userspace
  perf parse-events: Remove duplicated include in parse-events.c
  perf callchain: Allow symbols to be optional when resolving a callchain
  perf inject: Lazy build-id mmap2 event insertion
  perf inject: Add new mmap2-buildid-all option
  perf inject: Fix build ID injection
  perf annotate-data: Add pr_debug_scope()
  ...

1 files changed, 30 insertions, 3 deletions

diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d5c821c22f79..8b9e05a1932f 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -14,6 +14,7 @@
 #include "spark.h"
 #include "hashmap.h"
 #include "disasm.h"
+#include "branch.h"
 
 struct hist_browser_timer;
 struct hist_entry;
@@ -30,6 +31,7 @@ struct annotated_data_type;
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
 #define ANNOTATION__AVG_IPC_WIDTH 36
+#define ANNOTATION__BR_CNTR_WIDTH 30
 #define ANNOTATION_DUMMY_LEN	256
 
 struct annotation_options {
@@ -43,6 +45,7 @@ struct annotation_options {
 	     show_nr_jumps,
 	     show_minmax_cycle,
 	     show_asm_raw,
+	     show_br_cntr,
 	     annotate_src,
 	     full_addr;
 	u8   offset_level;
@@ -103,6 +106,10 @@ struct annotation_line {
 	char			*fileloc;
 	char			*path;
 	struct cycles_info	*cycles;
+	int			 num_aggr;
+	int			 br_cntr_nr;
+	u64			*br_cntr;
+	struct evsel		*evsel;
 	int			 jump_sources;
 	u32			 idx;
 	int			 idx_asm;
@@ -113,7 +120,10 @@ struct annotation_line {
 struct disasm_line {
 	struct ins		 ins;
 	struct ins_operands	 ops;
-
+	union {
+		u8 bytes[4];
+		u32 raw_insn;
+	} raw;
 	/* This needs to be at the end. */
 	struct annotation_line	 al;
 };
@@ -285,6 +295,9 @@ struct annotated_source {
 struct annotation_line *annotated_source__get_line(struct annotated_source *src,
 						   s64 offset);
 
+/* A branch counter once saturated */
+#define ANNOTATION__BR_CNTR_SATURATED_FLAG	(1ULL << 63)
+
 /**
  * struct annotated_branch - basic block and IPC information for a symbol.
  *
@@ -294,6 +307,7 @@ struct annotation_line *annotated_source__get_line(struct annotated_source *src,
  * @cover_insn: Number of distinct, actually executed instructions.
  * @cycles_hist: Array of cyc_hist for each instruction.
  * @max_coverage: Maximum number of covered basic block (used for block-range).
+ * @br_cntr: Array of the occurrences of events (branch counters) during a block.
  *
  * This struct is used by two different codes when the sample has branch stack
  * and cycles information.  annotation__compute_ipc() calculates average IPC
@@ -310,6 +324,7 @@ struct annotated_branch {
 	unsigned int		cover_insn;
 	struct cyc_hist		*cycles_hist;
 	u64			max_coverage;
+	u64			*br_cntr;
 };
 
 struct LOCKABLE annotation {
@@ -336,7 +351,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (symbol_conf.show_total_period ? 12 : 7) * notes->src->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 8) * notes->src->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al)
@@ -344,6 +359,11 @@ static inline bool annotation_line__filter(struct annotation_line *al)
 	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
+static inline u8 annotation__br_cntr_width(void)
+{
+	return annotate_opts.show_br_cntr ? ANNOTATION__BR_CNTR_WIDTH : 0;
+}
+
 void annotation__update_column_widths(struct annotation *notes);
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms);
 
@@ -380,7 +400,9 @@ struct annotated_branch *annotation__get_branch(struct annotation *notes);
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
-				    unsigned cycles);
+				    unsigned cycles,
+				    struct evsel *evsel,
+				    u64 br_cntr);
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
 				 struct evsel *evsel, u64 addr);
@@ -540,4 +562,9 @@ struct annotated_basic_block {
 int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
 			      struct list_head *head);
 
+void debuginfo_cache__delete(void);
+
+int annotation_br_cntr_entry(char **str, int br_cntr_nr, u64 *br_cntr,
+			     int num_aggr, struct evsel *evsel);
+int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header);
 #endif	/* __PERF_ANNOTATE_H */