perf parse-events: Remove BPF event support

New features like the BPF --filter support in perf record have made the
BPF event functionality somewhat redundant. As shown by commit
fcb027c1a4f6 ("perf tools: Revert enable indices setting syntax for BPF
map") and commit 14e4b9f ("perf trace: Raw augmented syscalls fix
libbpf 1.0+ compatibility") the BPF event support hasn't been well
maintained and it adds considerable complexity in areas like event
parsing, not least as '/' is a separator for event modifiers as well as
in paths.

This patch removes support in the event parser for BPF events and then
the associated functions are removed. This leads to the removal of whole
source files like bpf-loader.c.  Removing support means that augmented
syscalls in perf trace is broken, this will be fixed in a later commit
adding support using BPF skeletons.

The removal of BPF events causes an unused label warning from flex
generated code, so update build to ignore it:

  ```
  util/parse-events-flex.c:2704:1: error: label ‘find_rule’ defined but not used [-Werror=unused-label]
  2704 | find_rule: /* we branch to this label when backing up */
  ```

Committer notes:

Extracted from a larger patch that was also removing the support for
linking with libllvm and libclang, that were an alternative to using an
external clang execution to compile the .c event source code into BPF
bytecode.

Testing it:

  # perf trace -e /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c
  event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c'
                        \___ Bad event or PMU

  Unabled to find PMU or event on a PMU of 'home'

  Initial error:
  event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c'
                        \___ Cannot find PMU `home'. Missing kernel support?
  Run 'perf list' for a list of valid events

   Usage: perf trace [<options>] [<command>]
      or: perf trace [<options>] -- <command> [<options>]
      or: perf trace record [<options>] [<command>]
      or: perf trace record [<options>] -- <command> [<options>]

      -e, --event <event>   event/syscall selector. use 'perf list' to list available events
  #

Signed-off-by: Ian Rogers <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Andrii Nakryiko <[email protected]>
Cc: Anshuman Khandual <[email protected]>
Cc: Athira Rajeev <[email protected]>
Cc: Brendan Gregg <[email protected]>
Cc: Carsten Haitzler <[email protected]>
Cc: Eduard Zingerman <[email protected]>
Cc: Fangrui Song <[email protected]>
Cc: He Kuang <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: James Clark <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Nathan Chancellor <[email protected]>
Cc: Naveen N. Rao <[email protected]>
Cc: Nick Desaulniers <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Rob Herring <[email protected]>
Cc: Tiezhu Yang <[email protected]>
Cc: Tom Rix <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Wang ShaoBo <[email protected]>
Cc: Yang Jihong <[email protected]>
Cc: Yonghong Song <[email protected]>
Cc: YueHaibing <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: captain5050

tools/perf/Documentation/perf-config.txt

@@ -125,9 +125,6 @@ Given a $HOME/.perfconfig like this:
 		group = true
 		skip-empty = true
 
-	[llvm]
-		dump-obj = true
-		clang-opt = -g
 
 You can hide source code of annotate feature setting the config to false with
 
@@ -657,36 +654,6 @@ ftrace.*::
 		-F option is not specified. Possible values are 'function' and
 		'function_graph'.
 
-llvm.*::
-	llvm.clang-path::
-		Path to clang. If omit, search it from $PATH.
-
-	llvm.clang-bpf-cmd-template::
-		Cmdline template. Below lines show its default value. Environment
-		variable is used to pass options.
-		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
-		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
-		"-Wno-unused-value -Wno-pointer-sign "		\
-		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
-
-	llvm.clang-opt::
-		Options passed to clang.
-
-	llvm.kbuild-dir::
-		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
-		If set to "" deliberately, skip kernel header auto-detector.
-
-	llvm.kbuild-opts::
-		Options passed to 'make' when detecting kernel header options.
-
-	llvm.dump-obj::
-		Enable perf dump BPF object files compiled by LLVM.
-
-	llvm.opts::
-		Options passed to llc.
-
 samples.*::
 
 	samples.context::

tools/perf/Documentation/perf-record.txt

@@ -99,20 +99,6 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
-        - a BPF source file (ending in .c) or a precompiled object file (ending
-          in .o) selects one or more BPF events.
-          The BPF program can attach to various perf events based on the ELF section
-          names.
-
-          When processing a '.c' file, perf searches an installed LLVM to compile it
-          into an object file first. Optional clang options can be passed via the
-          '--clang-opt' command line option, e.g.:
-
-            perf record --clang-opt "-DLINUX_VERSION_CODE=0x50000" \
-                        -e tests/bpf-script-example.c
-
-          Note: '--clang-opt' must be placed before '--event/-e'.
-
 	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
 	  Each event is separated by commas and the group should be quoted to
 	  prevent the shell interpretation.  You also need to use --group on
@@ -547,14 +533,6 @@ PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE)
 switch events will be enabled automatically, which can be suppressed by
 by the option --no-switch-events.
 
---clang-path=PATH::
-Path to clang binary to use for compiling BPF scriptlets.
-(enabled when BPF support is on)
-
---clang-opt=OPTIONS::
-Options passed to clang when compiling BPF scriptlets.
-(enabled when BPF support is on)
-
 --vmlinux=PATH::
 Specify vmlinux path which has debuginfo.
 (enabled when BPF prologue is on)

tools/perf/Makefile.config

@@ -589,18 +589,6 @@ ifndef NO_LIBELF
 	LIBBPF_STATIC := 1
       endif
     endif
-
-    ifndef NO_DWARF
-      ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
-        CFLAGS += -DHAVE_BPF_PROLOGUE
-        $(call detected,CONFIG_BPF_PROLOGUE)
-      else
-        msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset());
-      endif
-    else
-      msg := $(warning DWARF support is off, BPF prologue is disabled);
-    endif
-
   endif # NO_LIBBPF
 endif # NO_LIBELF
 

tools/perf/builtin-record.c

@@ -37,8 +37,6 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/perf_api_probe.h"
-#include "util/llvm-utils.h"
-#include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
 #include "util/cpu-set-sched.h"
@@ -2465,16 +2463,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
-	err = bpf__apply_obj_config();
-	if (err) {
-		char errbuf[BUFSIZ];
-
-		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Apply config to BPF failed: %s\n",
-			 errbuf);
-		goto out_free_threads;
-	}
-
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
@@ -3486,10 +3474,6 @@ static struct option __record_options[] = {
 		    "collect kernel callchains"),
 	OPT_BOOLEAN(0, "user-callchains", &record.opts.user_callchains,
 		    "collect user callchains"),
-	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
-		   "clang binary to use for compiling BPF scriptlets"),
-	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
-		   "options passed to clang when compiling BPF scriptlets"),
 	OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN(0, "buildid-all", &record.buildid_all,
@@ -3967,27 +3951,6 @@ int cmd_record(int argc, const char **argv)
 
 	setlocale(LC_ALL, "");
 
-#ifndef HAVE_LIBBPF_SUPPORT
-# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c)
-	set_nobuild('\0', "clang-path", true);
-	set_nobuild('\0', "clang-opt", true);
-# undef set_nobuild
-#endif
-
-#ifndef HAVE_BPF_PROLOGUE
-# if !defined (HAVE_DWARF_SUPPORT)
-#  define REASON  "NO_DWARF=1"
-# elif !defined (HAVE_LIBBPF_SUPPORT)
-#  define REASON  "NO_LIBBPF=1"
-# else
-#  define REASON  "this architecture doesn't support BPF prologue"
-# endif
-# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c)
-	set_nobuild('\0', "vmlinux", true);
-# undef set_nobuild
-# undef REASON
-#endif
-
 #ifndef HAVE_BPF_SKEL
 # define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c)
 	set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true);
@@ -4116,14 +4079,6 @@ int cmd_record(int argc, const char **argv)
 	if (dry_run)
 		goto out;
 
-	err = bpf__setup_stdout(rec->evlist);
-	if (err) {
-		bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Setup BPF stdout failed: %s\n",
-			 errbuf);
-		goto out;
-	}
-
 	err = -ENOMEM;
 
 	if (rec->no_buildid_cache || rec->no_buildid) {

tools/perf/builtin-trace.c

@@ -18,6 +18,7 @@
 #include <api/fs/tracing_path.h>
 #ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #endif
 #include "util/bpf_map.h"
 #include "util/rlimit.h"
@@ -53,7 +54,6 @@
 #include "trace/beauty/beauty.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
-#include "util/bpf-loader.h"
 #include "util/tracepoint.h"
 #include "callchain.h"
 #include "print_binary.h"
@@ -3287,17 +3287,6 @@ static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace, const ch
 	return bpf_object__find_map_by_name(trace->bpf_obj, name);
 }
 
-static void trace__set_bpf_map_filtered_pids(struct trace *trace)
-{
-	trace->filter_pids.map = trace__find_bpf_map_by_name(trace, "pids_filtered");
-}
-
-static void trace__set_bpf_map_syscalls(struct trace *trace)
-{
-	trace->syscalls.prog_array.sys_enter = trace__find_bpf_map_by_name(trace, "syscalls_sys_enter");
-	trace->syscalls.prog_array.sys_exit  = trace__find_bpf_map_by_name(trace, "syscalls_sys_exit");
-}
-
 static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name)
 {
 	struct bpf_program *pos, *prog = NULL;
@@ -3553,71 +3542,19 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace)
 	return err;
 }
 
-static void trace__delete_augmented_syscalls(struct trace *trace)
-{
-	struct evsel *evsel, *tmp;
-
-	evlist__remove(trace->evlist, trace->syscalls.events.augmented);
-	evsel__delete(trace->syscalls.events.augmented);
-	trace->syscalls.events.augmented = NULL;
-
-	evlist__for_each_entry_safe(trace->evlist, tmp, evsel) {
-		if (evsel->bpf_obj == trace->bpf_obj) {
-			evlist__remove(trace->evlist, evsel);
-			evsel__delete(evsel);
-		}
-
-	}
-
-	bpf_object__close(trace->bpf_obj);
-	trace->bpf_obj = NULL;
-}
 #else // HAVE_LIBBPF_SUPPORT
 static struct bpf_map *trace__find_bpf_map_by_name(struct trace *trace __maybe_unused,
 						   const char *name __maybe_unused)
 {
 	return NULL;
 }
 
-static void trace__set_bpf_map_filtered_pids(struct trace *trace __maybe_unused)
-{
-}
-
-static void trace__set_bpf_map_syscalls(struct trace *trace __maybe_unused)
-{
-}
-
-static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace __maybe_unused,
-							    const char *name __maybe_unused)
-{
-	return NULL;
-}
-
 static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace __maybe_unused)
 {
 	return 0;
 }
-
-static void trace__delete_augmented_syscalls(struct trace *trace __maybe_unused)
-{
-}
 #endif // HAVE_LIBBPF_SUPPORT
 
-static bool trace__only_augmented_syscalls_evsels(struct trace *trace)
-{
-	struct evsel *evsel;
-
-	evlist__for_each_entry(trace->evlist, evsel) {
-		if (evsel == trace->syscalls.events.augmented ||
-		    evsel->bpf_obj == trace->bpf_obj)
-			continue;
-
-		return false;
-	}
-
-	return true;
-}
-
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
 	if (trace->syscalls.events.sys_enter)
@@ -3981,16 +3918,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
-	err = bpf__apply_obj_config();
-	if (err) {
-		char errbuf[BUFSIZ];
-
-		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
-		pr_err("ERROR: Apply config to BPF failed: %s\n",
-			 errbuf);
-		goto out_error_open;
-	}
-
 	err = trace__set_filter_pids(trace);
 	if (err < 0)
 		goto out_error_mem;
@@ -4922,77 +4849,6 @@ int cmd_trace(int argc, const char **argv)
 				       "cgroup monitoring only available in system-wide mode");
 	}
 
-	evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
-	if (IS_ERR(evsel)) {
-		bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
-		pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
-		goto out;
-	}
-
-	if (evsel) {
-		trace.syscalls.events.augmented = evsel;
-
-		evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter");
-		if (evsel == NULL) {
-			pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n");
-			goto out;
-		}
-
-		if (evsel->bpf_obj == NULL) {
-			pr_err("ERROR: raw_syscalls:sys_enter not associated to a BPF object\n");
-			goto out;
-		}
-
-		trace.bpf_obj = evsel->bpf_obj;
-
-		/*
-		 * If we have _just_ the augmenter event but don't have a
-		 * explicit --syscalls, then assume we want all strace-like
-		 * syscalls:
-		 */
-		if (!trace.trace_syscalls && trace__only_augmented_syscalls_evsels(&trace))
-			trace.trace_syscalls = true;
-		/*
-		 * So, if we have a syscall augmenter, but trace_syscalls, aka
-		 * strace-like syscall tracing is not set, then we need to trow
-		 * away the augmenter, i.e. all the events that were created
-		 * from that BPF object file.
-		 *
-		 * This is more to fix the current .perfconfig trace.add_events
-		 * style of setting up the strace-like eBPF based syscall point
-		 * payload augmenter.
-		 *
-		 * All this complexity will be avoided by adding an alternative
-		 * to trace.add_events in the form of
-		 * trace.bpf_augmented_syscalls, that will be only parsed if we
-		 * need it.
-		 *
-		 * .perfconfig trace.add_events is still useful if we want, for
-		 * instance, have msr_write.msr in some .perfconfig profile based
-		 * 'perf trace --config determinism.profile' mode, where for some
-		 * particular goal/workload type we want a set of events and
-		 * output mode (with timings, etc) instead of having to add
-		 * all via the command line.
-		 *
-		 * Also --config to specify an alternate .perfconfig file needs
-		 * to be implemented.
-		 */
-		if (!trace.trace_syscalls) {
-			trace__delete_augmented_syscalls(&trace);
-		} else {
-			trace__set_bpf_map_filtered_pids(&trace);
-			trace__set_bpf_map_syscalls(&trace);
-			trace.syscalls.unaugmented_prog = trace__find_bpf_program_by_title(&trace, "!raw_syscalls:unaugmented");
-		}
-	}
-
-	err = bpf__setup_stdout(trace.evlist);
-	if (err) {
-		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
-		pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
-		goto out;
-	}
-
 	err = -1;
 
 	if (map_dump_str) {

tools/perf/perf.c

@@ -18,7 +18,6 @@
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
 #include <subcmd/parse-options.h>
-#include "util/bpf-loader.h"
 #include "util/debug.h"
 #include "util/event.h"
 #include "util/util.h" // usage()
@@ -324,7 +323,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
-	bpf__clear();
 
 	if (status)
 		return status & 0xff;