Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1180724

[PATCH 15/39] perf tools: Auto detecting kernel include options

From Wang Nan <wangnan0@huawei.com>
Newsgroups linux.kernel
Subject [PATCH 15/39] perf tools: Auto detecting kernel include options
Date 2015-07-09 14:50 +0200
Message-ID <pKjr6-dD-65@gated-at.bofh.it> (permalink)
References <pKjhn-9T-3@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

To help user find correct kernel include options, this patch extracts
them from kbuild system by an embedded script kinc_fetch_script, which
creates a temporary directory, generates Makefile and an empty dummy.o
then use the Makefile to fetch $(NOSTDINC_FLAGS), $(LINUXINCLUDE) and
$(EXTRA_CFLAGS) options. The result is passed to compiler script using
'KERNEL_INC_OPTIONS' environment variable.

Because options from kbuild contains relative path like
'Iinclude/generated/uapi', the work directory must be changed. This is
done by previous patch.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/util/llvm-utils.c | 59 ++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 54 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 2ca2bd6..b658896 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -218,15 +218,42 @@ static const char *kbuild_detector =
 "fi\n"
 "exit -1\n";
 
+static const char *kinc_fetch_script =
+"#!/usr/bin/env sh\n"
+"if ! test -d \"$KBUILD_DIR\"\n"
+"then\n"
+"	exit -1\n"
+"fi\n"
+"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
+"then\n"
+"	exit -1\n"
+"fi\n"
+"TMPDIR=`mktemp -d`\n"
+"if test -z \"$TMPDIR\"\n"
+"then\n"
+"    exit -1\n"
+"fi\n"
+"cat << EOF > $TMPDIR/Makefile\n"
+"obj-y := dummy.o\n"
+"\\$(obj)/%.o: \\$(src)/%.c\n"
+"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
+"EOF\n"
+"touch $TMPDIR/dummy.c\n"
+"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
+"RET=$?\n"
+"rm -rf $TMPDIR\n"
+"exit $RET\n";
+
 static inline void
-get_kbuild_opts(char **kbuild_dir)
+get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 {
 	int err;
 
-	if (!kbuild_dir)
+	if (!kbuild_dir || !kbuild_include_opts)
 		return;
 
 	*kbuild_dir = NULL;
+	*kbuild_include_opts = NULL;
 
 	if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) {
 		pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n");
@@ -247,6 +274,26 @@ get_kbuild_opts(char **kbuild_dir)
 "     \tdetection.\n\n");
 		return;
 	}
+
+	pr_debug("Kernel build dir is set to %s\n", *kbuild_dir);
+	force_set_env("KBUILD_DIR", *kbuild_dir);
+	err = read_from_pipe(kinc_fetch_script,
+			     (void **)kbuild_include_opts,
+			     NULL);
+	if (err) {
+		pr_warning(
+"WARNING:\tunable to get kernel include directories from '%s'\n"
+"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n"
+"     \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n"
+"     \toption in [llvm] to \"\" to suppress this detection.\n\n",
+			*kbuild_dir);
+
+		free(*kbuild_dir);
+		*kbuild_dir = NULL;
+		return;
+	}
+
+	pr_debug("include option is set to %s\n", *kbuild_include_opts);
 }
 
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
@@ -256,7 +303,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	char clang_path[PATH_MAX];
 	const char *clang_opt = llvm_param.clang_opt;
 	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *kbuild_dir = NULL;
+	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
 	void *obj_buf = NULL;
 	size_t obj_buf_sz;
 
@@ -278,11 +325,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 * This is an optional work. Even it fail we can continue our
 	 * work. Needn't to check error return.
 	 */
-	get_kbuild_opts(&kbuild_dir);
+	get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
 
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
-	force_set_env("KERNEL_INC_OPTIONS", NULL);
+	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
 	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
 
 	/*
@@ -305,6 +352,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	}
 
 	free(kbuild_dir);
+	free(kbuild_include_opts);
 	if (!p_obj_buf)
 		free(obj_buf);
 	else
@@ -315,6 +363,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	return 0;
 errout:
 	free(kbuild_dir);
+	free(kbuild_include_opts);
 	free(obj_buf);
 	if (p_obj_buf)
 		*p_obj_buf = NULL;
-- 
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[GIT PULL 00/39] perf tools: filtering events using eBPF programs Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:40 +0200
  [PATCH 36/39] perf tools: Use same BPF program if arguments are identical Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 25/39] perf tools: Attach eBPF program to perf event Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 27/39] perf record: Add clang options for compiling BPF scripts Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 34/39] perf tools: Add prologue for BPF programs for fetching arguments Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 31/39] perf tools: Move linux/filter.h to tools/include Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 26/39] perf tools: Suppress probing messages when probing by BPF loading Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 28/39] bpf tools: Load a program with different instances using preprocessor Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
    Re: [PATCH 28/39] bpf tools: Load a program with different instances  using preprocessor "Wangnan (F)" <wangnan0@huawei.com> - 2015-07-13 08:00 +0200
  [PATCH 13/39] perf tools: Call clang to compile C source to object code Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 32/39] perf tools: Add BPF_PROLOGUE config options for further patches Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 06/39] bpf tools: Create eBPF maps defined in an object file Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
    Re: [PATCH 06/39] bpf tools: Create eBPF maps defined in an object  file "Wangnan (F)" <wangnan0@huawei.com> - 2015-07-14 06:10 +0200
  [PATCH 35/39] perf tools: Generate prologue for BPF programs Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 30/39] perf probe: Reset args and nargs for probe_trace_event when failure Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 18/39] perf record: Enable passing bpf object file to --event Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 14/39] perf tools: Auto detecting kernel build directory Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 23/39] perf record: Load all eBPF object into kernel Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 24/39] perf tools: Add bpf_fd field to evsel and config it Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 22/39] perf record: Probe at kprobe points Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 15/39] perf tools: Auto detecting kernel include options Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 29/39] perf tools: Fix probe-event.h include Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 02/39] bpf tools: Collect eBPF programs from their own sections Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
    Re: [PATCH 02/39] bpf tools: Collect eBPF programs from their own  sections "Wangnan (F)" <wangnan0@huawei.com> - 2015-07-10 05:20 +0200
      Re: [PATCH 02/39] bpf tools: Collect eBPF programs from their own  sections "Wangnan (F)" <wangnan0@huawei.com> - 2015-07-14 06:10 +0200
  [PATCH 21/39] perf probe: Attach trace_probe_event with perf_probe_event Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 09/39] bpf tools: Load eBPF programs in object files into kernel Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  [PATCH 37/39] perf record: Support custom vmlinux path Wang Nan <wangnan0@huawei.com> - 2015-07-09 14:50 +0200
  perf test LLVM was: Re: [GIT PULL 00/39] perf tools: filtering  events using eBPF programs Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-07-14 17:40 +0200
    Re: perf test LLVM was: Re: [GIT PULL 00/39] perf tools: filtering  events using eBPF programs "Wangnan (F)" <wangnan0@huawei.com> - 2015-07-15 13:10 +0200
      Re: perf test LLVM was: Re: [GIT PULL 00/39] perf tools: filtering  events using eBPF programs Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-07-15 13:30 +0200

csiph-web