[RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[Wang Nan]

This is the second version of 'perf bpf' patch series, based on
v4.1-rc3.

The goal of this series of patches is to integrate eBPF with perf.
After applying these patches, users are allowed to use following
command to load eBPF program compiled by LLVM into kernel then start
recording with filters on: 

 # perf bpf record --object sample_bpf.o -- -a sleep 4

Different from previous version (can be retrived from lkml:
https://lkml.org/lkml/2015/4/30/264 ), v2 series has following
modifications:

 1. Put common eBPF and eBPF object operations into tools/lib/bpf
    instead of perf itself. Other programs, like iproute2, can
    utilize libbpf for their own use.

 2. Doesn't rely on 'config' section. In v2 patch, eBPF programs
    describe their probing points in their section names. 'config'
    section is no longer mandatory for probing points. However, I
    still leave the space of 'config' section in libbpf for further
    expansion. See following descussion.

 3. Kprobe points will be removed after exiting.

 4. Redesign the logical of perf bpf command. Doesn't like v1 which
    implements 'perf bpf' as a standalone perf command, in this patch
    series perf bpf acts as a commmand wrapper. It loads eBPF programs
    into kernel then start other perf commands based on them.
    The first wrapped command is 'record'. In the example shown above,
    'perf record' will start and captures filtered samples. Other
    commands, like 'perf top', are possible to be wrapped in similay
    way.

Because of the new logic, a design decision should be made that, are we
actually need 'perf bpf' command? Another choice is to midify
'pref report' by introducing new option like '--ebpf-object' and
make them load BPF programs before do other things. I prefer keeping
'perf bpf' to group all eBPF related stuffs together using a uniform
entry. In addition, eBPF programs can act not only as filters but also
data aggregator. It is possible to make something link 'perf bpf run'
to simply make it run, and dump result after user hit 'C-c' or timeout.
The 'config' section may be utilized in this case to let 'perf bpf'
know how to display results.

Following is detail description.

 Patch  1/37 -  4/37 are bugfixs. Some of them are already acked.

 Patch  5/37 - 25/37 creates tools/lib/bpf.

  Libbpf will be compiled into libbpf.a and libbpf.so. It can be
  devided into 2 parts:

    1) User-kernel interface. The API is defined by tools/lib/bpf/bpf.h,
       encapsulates map and program loading operations. In
       bpf_load_program(), it doesn't use log buffer in the first try to
       improve performance, and retry with log buffer enabled when
       failure.

    2) ELF operations. The structure of eBPF object file is defined
       here. API of this part can be found in tools/lib/bpf/libbpf.h.
       'struct bpf_map_def' is also put here.

       Libbpf's API hides internal structures. Callers access data of
       object files with handlers and accessors. 'struct bpf_object *'
       is handler of a whole object file. 'struct bpf_prog_handler *'
       is handler and iterator of programs. Some of accessors are
       defined to enable caller to retrive section name and file
       descriptor of a program. Further accessor can be appended.

       In the design of libbpf, I explictly separate full procedure
       into opening and loading phase. Data are collected during
       'opening' phase. BPF syscalls are called in 'loading' phase.
       The separation is designed for potential cross-objects
       operations. Such separation also give caller a chance to let
       him/her to adjust bytecode and/or maps before real loading.
       (API of such operation is not provided in this version).

       During loading, fields in 'struct bpf_map_def' are also swapped
       if endianess mismatched.
  
 Patch 26/37 - 37/37 are patches on perf, which introduce 'perf bpf'
                     command and 'perf bpf record' subcommand.

   Like previous discussed, 'perf bpf' is not a standalone command.
   The usage should be:

     perf bpf [<options>] <command> --objects <objfile> -- \
	     <args passed to otehr cmds>

   First two patches make 'perf bpf' avaliable and make perf depend on
   libbpf. 28/37 creates 'perf bpf record' and directly passes
   everything after '--' to cmd_record(). Other stuffs resides in
   tools/perf/utils/bpf-loader.[ch], which are introduced in 29/37.
   Following patches do collection -> probing -> loading works step
   by step. In those operations, 'perf bpf' collects all required
   objects before creating kprobe points, and load programs into kernel
   after probing finish.

   A 'bpf_unload()' is used to remove kprobe points. I use 'atexit'
   hook to ensure it called before exiting. However, I find that
   atexit hookers are not always work well. For example, when program
   is canceled by SIGINT. Therefore we still need to call bpf_unload()
   after cmd_record().

   Patch 34 and 35 introduce a special syntax for event parsing:
   'group:name|bpf_fd=%d|', which allows 'perf bpf' to pass file
   descriptors of eBPF programs to evsel.

   Patch 36 and 37 regenerate arguments for cmd_record(), utilizes
   the '|bpf_fd=%d|' syntax to pass eBPF programs.

Wang Nan (37):
  tools perf: set vmlinux_path__nr_entries to 0 in vmlinux_path__exit.
  tools lib traceevent: install libtraceevent.a into libdir.
  tools build: Allow other override features to check.
  tools include: add __aligned_u64 to types.h.
  tools lib bpf: introduce 'bpf' library to tools.
  tools lib bpf: allow set printing function.
  tools lib bpf: defines basic interface.
  tools lib bpf: open eBPF object file and do basic validation.
  tools lib bpf: check swap according to EHDR.
  tools lib bpf: iterater over elf sections to collect information.
  tools lib bpf: collect version and license from ELF.
  tools lib bpf: collect map definitions.
  tools lib bpf: collect config section in object.
  tools lib bpf: collect symbol table in object files.
  tools lib bpf: collect bpf programs from object files.
  tools lib bpf: collect relocation sections from object file.
  tools lib bpf: collect relocation instructions for each program.
  tools lib bpf: clean elf memory after loading.
  tools lib bpf: add bpf.c/h for common bpf operations.
  tools lib bpf: create maps needed by object file.
  tools lib bpf: relocation programs.
  tools lib bpf: introduce bpf_load_program to bpf.c.
  tools lib bpf: load bpf programs in object file into kernel.
  tools lib bpf: accessors of bpf_program.
  tools lib bpf: accessors for struct bpf_object.
  tools perf: Add new 'perf bpf' command.
  tools perf: make perf depend on libbpf.
  tools perf: add 'perf bpf record' subcommand.
  tools perf: add bpf-loader and open elf object files.
  tools perf: collect all bpf programs.
  tools perf: config probe points of eBPF programs during prepartion.
  tools perf bpf: probe at kprobe points.
  tools perf bpf: load eBPF object into kernel.
  tools perf: add a bpf_wrapper global flag.
  tools perf: add bpf_fd field to evsel and introduce new event syntax.
  tools perf: generate event argv.
  tools perf bpf: passes generated arguments to cmd_record.

 tools/build/Makefile.feature          |    4 +-
 tools/include/linux/types.h           |    5 +
 tools/lib/bpf/.gitignore              |    2 +
 tools/lib/bpf/Build                   |    1 +
 tools/lib/bpf/Makefile                |  191 ++++++
 tools/lib/bpf/bpf.c                   |   87 +++
 tools/lib/bpf/bpf.h                   |   24 +
 tools/lib/bpf/libbpf.c                | 1089 +++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h                |   66 ++
 tools/lib/traceevent/Makefile         |   20 +-
 tools/perf/Build                      |    1 +
 tools/perf/Documentation/perf-bpf.txt |   18 +
 tools/perf/Makefile.perf              |   20 +-
 tools/perf/builtin-bpf.c              |  202 ++++++
 tools/perf/builtin.h                  |    1 +
 tools/perf/command-list.txt           |    1 +
 tools/perf/perf.c                     |   10 +
 tools/perf/perf.h                     |    1 +
 tools/perf/util/Build                 |    1 +
 tools/perf/util/bpf-loader.c          |  319 ++++++++++
 tools/perf/util/bpf-loader.h          |   24 +
 tools/perf/util/debug.c               |    5 +
 tools/perf/util/debug.h               |    1 +
 tools/perf/util/evsel.c               |    1 +
 tools/perf/util/evsel.h               |    1 +
 tools/perf/util/parse-events.c        |   19 +
 tools/perf/util/parse-events.h        |    3 +
 tools/perf/util/parse-events.l        |    8 +-
 tools/perf/util/parse-events.y        |   21 +
 tools/perf/util/parse-options.c       |    8 +-
 tools/perf/util/parse-options.h       |    2 +
 tools/perf/util/symbol.c              |    1 +
 32 files changed, 2145 insertions(+), 12 deletions(-)
 create mode 100644 tools/lib/bpf/.gitignore
 create mode 100644 tools/lib/bpf/Build
 create mode 100644 tools/lib/bpf/Makefile
 create mode 100644 tools/lib/bpf/bpf.c
 create mode 100644 tools/lib/bpf/bpf.h
 create mode 100644 tools/lib/bpf/libbpf.c
 create mode 100644 tools/lib/bpf/libbpf.h
 create mode 100644 tools/perf/Documentation/perf-bpf.txt
 create mode 100644 tools/perf/builtin-bpf.c
 create mode 100644 tools/perf/util/bpf-loader.c
 create mode 100644 tools/perf/util/bpf-loader.h

-- 
1.8.3.4

[RFC PATCH v2 01/37] tools perf: set vmlinux_path__nr_entries to 0 in vmlinux_path__exit.

[Wang Nan]

Original vmlinux_path__exit() doesn't revert vmlinux_path__nr_entries
to its original state. After the while loop vmlinux_path__nr_entries
becomes -1 instead of 0. This makes a problem that, if runs twice,
during the second run vmlinux_path__init() will set vmlinux_path[-1]
to strdup("vmlinux"), corrupts random memory.

This patch reset vmlinux_path__nr_entries to 0 after the while loop.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/symbol.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 201f6c4c..451777f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1802,6 +1802,7 @@ static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0)
 		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+	vmlinux_path__nr_entries = 0;
 
 	zfree(&vmlinux_path);
 }
-- 
1.8.3.4

[RFC PATCH v2 02/37] tools lib traceevent: install libtraceevent.a into libdir.

[Wang Nan]

Before this patch, 'make install' installs libraries into bindir:

  $ make install DESTDIR=./tree
   INSTALL  trace_plugins
   INSTALL  libtraceevent.a
   INSTALL  libtraceevent.so
  $ find ./tree
   ./tree/
   ./tree/usr
   ./tree/usr/local
   ./tree/usr/local/bin
   ./tree/usr/local/bin/libtraceevent.a
   ./tree/usr/local/bin/libtraceevent.so
   ...

/usr/local/lib( or lib64) should be a better place.

This patch replaces 'bin' with libdir. For __LP64__ building, libraries
are installed to /usr/local/lib64. For other building, to
/usr/local/lib instead.

After applying this patch:

  $ make install DESTDIR=./tree
   INSTALL  trace_plugins
   INSTALL  libtraceevent.a
   INSTALL  libtraceevent.so
  $ find ./tree
   ./tree
   ./tree/usr
   ./tree/usr/local
   ./tree/usr/local/lib64
   ./tree/usr/local/lib64/libtraceevent.a
   ./tree/usr/local/lib64/traceevent
   ./tree/usr/local/lib64/traceevent/plugins
   ./tree/usr/local/lib64/traceevent/plugins/plugin_mac80211.so
   ./tree/usr/local/lib64/traceevent/plugins/plugin_hrtimer.so
   ...
   ./tree/usr/local/lib64/libtraceevent.so

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/traceevent/Makefile | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d410da3..8464039 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -34,9 +34,15 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
 prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
 man_dir_SQ = '$(subst ','\'',$(man_dir))'
 
@@ -58,7 +64,7 @@ ifeq ($(prefix),$(HOME))
 override plugin_dir = $(HOME)/.traceevent/plugins
 set_plugin_dir := 0
 else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
 endif
 endif
 
@@ -85,11 +91,11 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-export prefix bindir src obj
+export prefix libdir src obj
 
 # Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
@@ -240,7 +246,7 @@ endef
 
 install_lib: all_cmd install_plugins
 	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(bindir_SQ))
+		$(call do_install,$(LIB_FILE),$(libdir_SQ))
 
 install_plugins: $(PLUGINS)
 	$(call QUIET_INSTALL, trace_plugins) \
-- 
1.8.3.4

[RFC PATCH v2 03/37] tools build: Allow other override features to check.

[Wang Nan]

Replace strong binding of FEATURE_TESTS and FEATURE_DISPLAY by weak
binding. This patch enables other makefiles which include
tools/build/Makefile.feature enable only limited feathres to check.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/build/Makefile.feature | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3a0b0ca..2975632 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS =			\
+FEATURE_TESTS ?=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -53,7 +53,7 @@ FEATURE_TESTS =			\
 	zlib				\
 	lzma
 
-FEATURE_DISPLAY =			\
+FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\
 	gtk2				\
-- 
1.8.3.4

[RFC PATCH v2 04/37] tools include: add __aligned_u64 to types.h.

[Wang Nan]

Following patches will introduce linux/bpf.h to a new libbpf library,
which requires definition of __aligned_u64. This patch add it to the
common types.h for tools.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/include/linux/types.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index b5cf25e..10a2cdc 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -60,6 +60,11 @@ typedef __u32 __bitwise __be32;
 typedef __u64 __bitwise __le64;
 typedef __u64 __bitwise __be64;
 
+/* Taken from uapi/linux/types.h. Required by linux/bpf.h */
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
 struct list_head {
 	struct list_head *next, *prev;
 };
-- 
1.8.3.4

[RFC PATCH v2 05/37] tools lib bpf: introduce 'bpf' library to tools.

[Wang Nan]

This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
Makefile and Build for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent. Before building,
it checks the existance of libelf in Makefile, and deny to build if
not found. Instead of throw an error if libelf not found, the error
raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/.gitignore |   2 +
 tools/lib/bpf/Build      |   1 +
 tools/lib/bpf/Makefile   | 191 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c   |  15 ++++
 tools/lib/bpf/libbpf.h   |  12 +++
 5 files changed, 221 insertions(+)
 create mode 100644 tools/lib/bpf/.gitignore
 create mode 100644 tools/lib/bpf/Build
 create mode 100644 tools/lib/bpf/Makefile
 create mode 100644 tools/lib/bpf/libbpf.c
 create mode 100644 tools/lib/bpf/libbpf.h

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
new file mode 100644
index 0000000..812aeed
--- /dev/null
+++ b/tools/lib/bpf/.gitignore
@@ -0,0 +1,2 @@
+libbpf_version.h
+FEATURE-DUMP
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
new file mode 100644
index 0000000..a316484
--- /dev/null
+++ b/tools/lib/bpf/Build
@@ -0,0 +1 @@
+libbpf-y := libbpf.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
new file mode 100644
index 0000000..bd5769c
--- /dev/null
+++ b/tools/lib/bpf/Makefile
@@ -0,0 +1,191 @@
+BPF_VERSION = 0
+BPF_PATCHLEVEL = 0
+BPF_EXTRAVERSION = 1
+
+# Version of eBPF elf file
+FILE_VERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
+EXT = -std=gnu99
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
+prefix ?= /usr/local
+libdir = $(prefix)/$(libdir_relative)
+man_dir = $(prefix)/share/man
+man_dir_SQ = '$(subst ','\'',$(man_dir))'
+
+export man_dir man_dir_SQ INSTALL
+export DESTDIR DESTDIR_SQ
+
+include ../../scripts/Makefile.include
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+FEATURE_DISPLAY = libelf libelf-getphdrnum libelf-mmap
+FEATURE_TESTS = libelf
+include $(srctree)/tools/build/Makefile.feature
+
+ifeq ($(feature-libelf-mmap), 1)
+  override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
+endif
+
+ifeq ($(feature-libelf-getphdrnum), 1)
+  override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
+endif
+
+export prefix libdir src obj
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
+
+LIB_FILE = libbpf.a libbpf.so
+
+VERSION		= $(BPF_VERSION)
+PATCHLEVEL	= $(BPF_PATCHLEVEL)
+EXTRAVERSION	= $(BPF_EXTRAVERSION)
+
+OBJ		= $@
+N		=
+
+LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+
+INCLUDES = -I. -I $(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+  CFLAGS := $(EXTRA_CFLAGS)
+else
+  CFLAGS := -g -Wall
+endif
+
+# Append required CFLAGS
+override CFLAGS += -fPIC
+override CFLAGS += $(INCLUDES)
+override CFLAGS += -D_GNU_SOURCE
+
+ifeq ($(VERBOSE),1)
+  Q =
+else
+  Q = @
+endif
+
+# Disable command line variables (CFLAGS) overide from top
+# level Makefile (perf), otherwise build Makefile will get
+# the same command line setup.
+MAKEOVERRIDES=
+
+export srctree OUTPUT CC LD CFLAGS V
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
+
+BPF_IN    := $(OUTPUT)libbpf-in.o
+LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+
+CMD_TARGETS = $(LIB_FILE)
+
+TARGETS = $(CMD_TARGETS)
+
+all: $(VERSION_FILES) all_cmd
+
+all_cmd: $(CMD_TARGETS)
+
+$(BPF_IN): force elfdep
+	$(Q)$(MAKE) $(build)=libbpf
+
+$(OUTPUT)libbpf.so: $(BPF_IN)
+	$(QUIET_LINK)$(CC) --shared $^ -o $@
+
+$(OUTPUT)libbpf.a: $(BPF_IN)
+	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
+
+define update_dir
+  (echo $1 > $@.tmp;				\
+   if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
+     rm -f $@.tmp;				\
+   else						\
+     echo '  UPDATE                 $@';	\
+     mv -f $@.tmp $@;				\
+   fi);
+endef
+
+define do_install
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd
+	$(call QUIET_INSTALL, $(LIB_FILE)) \
+		$(call do_install,$(LIB_FILE),$(libdir_SQ))
+
+install: install_lib
+
+### Cleaning rules
+
+config-clean:
+	$(call QUIET_CLEAN, config)
+	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
+
+clean:
+	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) LIBBPF-CFLAGS
+	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP
+	
+
+
+PHONY += force elfdep
+force:
+
+elfdep:
+	@if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit -1 ; fi
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
new file mode 100644
index 0000000..bebe99a
--- /dev/null
+++ b/tools/lib/bpf/libbpf.c
@@ -0,0 +1,15 @@
+/*
+ * common eBPF ELF loading operations.
+ *
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <linux/bpf.h>
+
+#include "libbpf.h"
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
new file mode 100644
index 0000000..10845a0
--- /dev/null
+++ b/tools/lib/bpf/libbpf.h
@@ -0,0 +1,12 @@
+/*
+ * Common eBPF object loader operations.
+ *
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#ifndef __BPF_LIBBPF_H
+#define __BPF_LIBBPF_H
+
+#endif
-- 
1.8.3.4

[RFC PATCH v2 06/37] tools lib bpf: allow set printing function.

[Wang Nan]

By libbpf_set_print(), users of libbpf are allowed to register he/she
own debug, info and warning printing functions. Libbpf will use those
functions to print messages. If not provided, default info and warning
printing functions are fprintf(stderr, ...); defailt debug printing
is NULL.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h |  4 ++++
 2 files changed, 47 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bebe99a..d7a7869 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8,8 +8,51 @@
  */
 
 #include <stdlib.h>
+#include <stdio.h>
+#include <stdarg.h>
+#include <string.h>
 #include <unistd.h>
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 
 #include "libbpf.h"
+
+#define __printf(a, b)	__attribute__((format(printf, a, b)))
+
+__printf(1, 2)
+static int __base_pr(const char *format, ...)
+{
+	va_list args;
+	int err;
+
+	va_start(args, format);
+	err = vfprintf(stderr, format, args);
+	va_end(args);
+	return err;
+}
+
+static __printf(1, 2) int (*__pr_warning)(const char *format, ...) =
+	__base_pr;
+static __printf(1, 2) int (*__pr_info)(const char *format, ...) =
+	__base_pr;
+static __printf(1, 2) int (*__pr_debug)(const char *format, ...) =
+	NULL;
+
+#define __pr(func, fmt, ...)	\
+do { 				\
+	if ((func))	\
+		(func)("libbpf: " fmt, ##__VA_ARGS__); \
+} while(0)
+
+#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+void libbpf_set_print(int (*warn)(const char *format, ...),
+		      int (*info)(const char *format, ...),
+		      int (*debug)(const char *format, ...))
+{
+	__pr_warning = warn;
+	__pr_info = info;
+	__pr_debug = debug;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 10845a0..eb306c0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -9,4 +9,8 @@
 #ifndef __BPF_LIBBPF_H
 #define __BPF_LIBBPF_H
 
+void libbpf_set_print(int (*warn)(const char *format, ...),
+		      int (*info)(const char *format, ...),
+		      int (*debug)(const char *format, ...));
+
 #endif
-- 
1.8.3.4

[RFC PATCH v2 07/37] tools lib bpf: defines basic interface.

[Wang Nan]

bpf_open_object() and bpf_close_object() are open and close function of
eBPF object files. 'struct bpf_object' will be handler of one object
file. Its internal structure is hide to user.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 11 +++++++++++
 tools/lib/bpf/libbpf.h |  8 ++++++++
 2 files changed, 19 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d7a7869..f8decff 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -12,6 +12,7 @@
 #include <stdarg.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 
@@ -56,3 +57,13 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 	__pr_info = info;
 	__pr_debug = debug;
 }
+
+struct bpf_object *bpf_open_object(const char *path)
+{
+	return NULL;
+}
+
+void bpf_close_object(struct bpf_object *object)
+{
+	return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index eb306c0..e523ae9 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -9,8 +9,16 @@
 #ifndef __BPF_LIBBPF_H
 #define __BPF_LIBBPF_H
 
+#include <stdio.h>
+
 void libbpf_set_print(int (*warn)(const char *format, ...),
 		      int (*info)(const char *format, ...),
 		      int (*debug)(const char *format, ...));
 
+/* Hide internal to user */
+struct bpf_object;
+
+struct bpf_object *bpf_open_object(const char *path);
+void bpf_close_object(struct bpf_object *object);
+
 #endif
-- 
1.8.3.4

[RFC PATCH v2 08/37] tools lib bpf: open eBPF object file and do basic validation.

[Wang Nan]

This patch adds basic 'struct bpf_object' which will be used for eBPF
object file loading. eBPF object files are compiled by LLVM as ELF
format. In this patch, libelf is used to open those files, read EHDR
and do basic validation according to e_type and e_machine.

All elf related staffs are grouped together and reside in elf field of
'struct bpf_object'. bpf_obj_clear_elf() is introduced to clear it.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 156 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 154 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f8decff..43c16bc 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -12,9 +12,12 @@
 #include <stdarg.h>
 #include <string.h>
 #include <unistd.h>
+#include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
 #include <linux/bpf.h>
+#include <libelf.h>
+#include <gelf.h>
 
 #include "libbpf.h"
 
@@ -58,12 +61,161 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 	__pr_debug = debug;
 }
 
-struct bpf_object *bpf_open_object(const char *path)
+#ifdef HAVE_LIBELF_MMAP_SUPPORT
+# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
+#else
+# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
+#endif
+
+struct bpf_object {
+	char *path;
+
+	/*
+	 * Information when doing elf related work. Only valid if fd
+	 * is valid.
+	 */
+	struct {
+		int fd;
+		Elf *elf;
+		GElf_Ehdr ehdr;
+	} elf;
+};
+#define obj_elf_valid(o)	((o)->elf.fd >= 0)
+
+static struct bpf_object *__bpf_obj_alloc(const char *path)
+{
+	struct bpf_object *obj;
+
+	obj = calloc(1, sizeof(struct bpf_object));
+	if (!obj) {
+		pr_warning("alloc memory failed for %s\n", path);
+		return NULL;
+	}
+
+	obj->path = strdup(path);
+	if (!obj->path) {
+		pr_warning("failed to strdup '%s'\n", path);
+		free(obj);
+		return NULL;
+	}
+	return obj;
+}
+
+static struct bpf_object *bpf_obj_alloc(const char *path)
 {
+	struct bpf_object *obj;
+
+	obj = __bpf_obj_alloc(path);
+	if (!obj)
+		goto out;
+
+	obj->elf.fd = -1;
+	return obj;
+out:
+	bpf_close_object(obj);
 	return NULL;
 }
 
-void bpf_close_object(struct bpf_object *object)
+static void bpf_obj_clear_elf(struct bpf_object *obj)
+{
+	if (!obj_elf_valid(obj))
+		return;
+
+	if (obj->elf.elf) {
+		elf_end(obj->elf.elf);
+		obj->elf.elf = NULL;
+	}
+	if (obj->elf.fd >= 0) {
+		close(obj->elf.fd);
+		obj->elf.fd = -1;
+	}
+}
+
+static int bpf_obj_elf_init(struct bpf_object *obj)
 {
+	int err = 0;
+	GElf_Ehdr *ep;
+
+	if (obj_elf_valid(obj)) {
+		pr_warning("elf init: internal error\n");
+		return -EEXIST;
+	}
+	
+	obj->elf.fd = open(obj->path, O_RDONLY);
+	if (obj->elf.fd < 0) {
+		pr_warning("failed to open %s: %s\n", obj->path,
+				strerror(errno));
+		return -errno;
+	}
+
+	obj->elf.elf = elf_begin(obj->elf.fd,
+				 LIBBPF_ELF_C_READ_MMAP,
+				 NULL);
+	if (!obj->elf.elf) {
+		pr_warning("failed to open %s as ELF file\n",
+				obj->path);
+		err = -EINVAL;
+		goto errout;
+	}
+
+	if (!gelf_getehdr(obj->elf.elf, &obj->elf.ehdr)) {
+		pr_warning("failed to get EHDR from %s\n",
+				obj->path);
+		err = -EINVAL;
+		goto errout;
+	}
+	ep = &obj->elf.ehdr;
+
+	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
+		pr_warning("%s is not an eBPF object file\n",
+			obj->path);
+		err = -EINVAL;
+		goto errout;
+	}
+
 	return 0;
+errout:
+	bpf_obj_clear_elf(obj);
+	return err;
+}
+
+struct bpf_object *bpf_open_object(const char *path)
+{
+	struct bpf_object *obj;
+
+	/* param validation */
+	if (!path)
+		return NULL;
+
+ 	pr_debug("loading %s\n", path);
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warning("failed to init libelf for %s\n", path);
+		return NULL;
+	}
+
+	obj = bpf_obj_alloc(path);
+	if (!obj)
+		return NULL;
+
+	if (bpf_obj_elf_init(obj))
+		goto out;
+
+	return obj;
+
+out:
+	bpf_close_object(obj);
+	return NULL;
+}
+
+void bpf_close_object(struct bpf_object *obj)
+{
+	if (!obj)
+		return;
+
+	bpf_obj_clear_elf(obj);
+
+	if (obj->path)
+		free(obj->path);
+	free(obj);
 }
-- 
1.8.3.4

[RFC PATCH v2 09/37] tools lib bpf: check swap according to EHDR.

[Wang Nan]

Check endianess according to EHDR to support loading eBPF objects into
big endian machines. Code is taken from tools/perf/util/symbol-elf.c.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 43c16bc..a4910a8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -69,6 +69,7 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 
 struct bpf_object {
 	char *path;
+	bool needs_swap;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -109,6 +110,7 @@ static struct bpf_object *bpf_obj_alloc(const char *path)
 	if (!obj)
 		goto out;
 
+	obj->needs_swap = false;
 	obj->elf.fd = -1;
 	return obj;
 out:
@@ -179,6 +181,31 @@ errout:
 	return err;
 }
 
+static int
+bpf_obj_swap_init(struct bpf_object *obj)
+{
+	static unsigned int const endian = 1;
+
+	obj->needs_swap = false;
+
+	switch (obj->elf.ehdr.e_ident[EI_DATA]) {
+	case ELFDATA2LSB:
+		/* We are big endian, BPF obj is little endian. */
+		if (*(unsigned char const *)&endian != 1)
+			obj->needs_swap = true;
+		return 0;
+
+	case ELFDATA2MSB:
+		/* We are little endian, BPF obj is big endian. */
+		if (*(unsigned char const *)&endian != 0)
+			obj->needs_swap = true;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
 struct bpf_object *bpf_open_object(const char *path)
 {
 	struct bpf_object *obj;
@@ -200,6 +227,8 @@ struct bpf_object *bpf_open_object(const char *path)
 
 	if (bpf_obj_elf_init(obj))
 		goto out;
+	if (bpf_obj_swap_init(obj))
+		goto out;
 
 	return obj;
 
-- 
1.8.3.4

[RFC PATCH v2 10/37] tools lib bpf: iterater over elf sections to collect information.

[Wang Nan]

bpf_obj_elf_collect() is introduced to iterate over each elf sections
to collection informations in eBPF object files. This function will
futher enhanced to collect license, kernel version, programs, configs
and map information.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a4910a8..1af80c3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -206,6 +206,58 @@ bpf_obj_swap_init(struct bpf_object *obj)
 	}
 }
 
+static int bpf_obj_elf_collect(struct bpf_object *obj)
+{
+	Elf *elf = obj->elf.elf;
+	GElf_Ehdr *ep = &obj->elf.ehdr;
+	Elf_Scn *scn = NULL;
+	int idx = 0, err = 0;
+
+	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
+	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
+		pr_warning("failed to get e_shstrndx from %s\n",
+			   obj->path);
+		return -EINVAL;
+	}
+
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		char *name;
+		GElf_Shdr sh;
+		Elf_Data *data;
+
+		idx++;
+		if (gelf_getshdr(scn, &sh) != &sh) {
+			pr_warning("failed to get section header"
+				   " from %s\n", obj->path);
+			err = -EINVAL;
+			goto out;
+		}
+
+		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
+		if (!name) {
+			pr_warning("failed to get section name "
+				   "from %s\n", obj->path);
+			err = -EINVAL;
+			goto out;
+		}
+
+		data = elf_getdata(scn, 0);
+		if (!data) {
+			pr_warning("failed to get section data "
+				   "from %s(%s)\n", name, obj->path);
+			err = -EINVAL;
+			goto out;
+		}
+		pr_debug("section %s, size %ld, link %d, "
+			 "flags %lx, type=%d\n",
+			 name, (unsigned long)data->d_size,
+			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
+			 (int)sh.sh_type);
+	}
+out:
+	return err;
+}
+
 struct bpf_object *bpf_open_object(const char *path)
 {
 	struct bpf_object *obj;
@@ -229,6 +281,8 @@ struct bpf_object *bpf_open_object(const char *path)
 		goto out;
 	if (bpf_obj_swap_init(obj))
 		goto out;
+	if (bpf_obj_elf_collect(obj))
+		goto out;
 
 	return obj;
 
-- 
1.8.3.4

[RFC PATCH v2 11/37] tools lib bpf: collect version and license from ELF.

[Wang Nan]

Expand bpf_obj_elf_collect() to collect license and kernel version
information in eBPF object file. eBPF object file should have a section
named 'license', which contains a string. It should also have a section
named 'version', contains a u32 LINUX_VERSION_CODE.

bpf_obj_validate() is introduced to validate object file after loaded.
Currently it only check existance of 'version' section.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1af80c3..b26f1ee 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -15,12 +15,22 @@
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
+#include <byteswap.h>
 #include <linux/bpf.h>
 #include <libelf.h>
 #include <gelf.h>
 
 #include "libbpf.h"
 
+#ifdef min
+# undef min
+#endif
+#define min(x, y) ({				\
+	typeof(x) _min1 = (x);			\
+	typeof(y) _min2 = (y);			\
+	(void) (&_min1 == &_min2);		\
+	_min1 < _min2 ? _min1 : _min2; })
+
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -70,6 +80,8 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 struct bpf_object {
 	char *path;
 	bool needs_swap;
+	char license[64];
+	u32 kern_version;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -206,6 +218,32 @@ bpf_obj_swap_init(struct bpf_object *obj)
 	}
 }
 
+static int bpf_obj_license_init(struct bpf_object *obj,
+				void *data, size_t size)
+{
+	memcpy(obj->license, data,
+	       min(size, sizeof(obj->license) - 1));
+	pr_debug("license of %s is %s\n", obj->path, obj->license);
+	return 0;
+}
+
+static int bpf_obj_kver_init(struct bpf_object *obj,
+			     void *data, size_t size)
+{
+	u32 kver;
+	if (size < sizeof(kver)) {
+		pr_warning("invalid kver section in %s\n", obj->path);
+		return -EINVAL;
+	}
+	memcpy(&kver, data, sizeof(kver));
+	if (obj->needs_swap)
+		kver = bswap_32(kver);
+	obj->kern_version = kver;
+	pr_debug("kernel version of %s is %x\n", obj->path,
+		 obj->kern_version);
+	return 0;
+}
+
 static int bpf_obj_elf_collect(struct bpf_object *obj)
 {
 	Elf *elf = obj->elf.elf;
@@ -253,11 +291,30 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 			 name, (unsigned long)data->d_size,
 			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
 			 (int)sh.sh_type);
+
+		if (strcmp(name, "license") == 0)
+			err = bpf_obj_license_init(obj, data->d_buf,
+						   data->d_size);
+		else if (strcmp(name, "version") == 0)
+			err = bpf_obj_kver_init(obj, data->d_buf,
+						data->d_size);
+		if (err)
+			goto out;
 	}
 out:
 	return err;
 }
 
+static int bpf_obj_validate(struct bpf_object *obj)
+{
+	if (obj->kern_version == 0) {
+		pr_warning("%s doesn't provide kernel version\n",
+			   obj->path);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 struct bpf_object *bpf_open_object(const char *path)
 {
 	struct bpf_object *obj;
@@ -283,6 +340,8 @@ struct bpf_object *bpf_open_object(const char *path)
 		goto out;
 	if (bpf_obj_elf_collect(obj))
 		goto out;
+	if (bpf_obj_validate(obj))
+		goto out;
 
 	return obj;
 
-- 
1.8.3.4

[RFC PATCH v2 12/37] tools lib bpf: collect map definitions.

[Wang Nan]

If maps are used by eBPF programs, corresponding object file(s) should
contain a section named 'map'. Which contains map definitions. This
patch copies the data of the whole section. Map data parsing should be
acted just before map loading.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b26f1ee..6ee5f3c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -82,6 +82,8 @@ struct bpf_object {
 	bool needs_swap;
 	char license[64];
 	u32 kern_version;
+	void *maps_buf;
+	size_t maps_buf_sz;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -244,6 +246,27 @@ static int bpf_obj_kver_init(struct bpf_object *obj,
 	return 0;
 }
 
+static int bpf_obj_maps_init(struct bpf_object *obj, void *data,
+			     size_t size)
+{
+	if (size == 0) {
+		pr_debug("%s doesn't need map definition\n",
+			 obj->path);
+		return 0;
+	}
+
+	obj->maps_buf = malloc(size);
+	if (!obj->maps_buf) {
+		pr_warning("malloc maps failed: %s\n", obj->path);
+		return -ENOMEM;
+	}
+
+	obj->maps_buf_sz = size;
+	memcpy(obj->maps_buf, data, size);
+	pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
+	return 0;
+}
+
 static int bpf_obj_elf_collect(struct bpf_object *obj)
 {
 	Elf *elf = obj->elf.elf;
@@ -298,6 +321,9 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "version") == 0)
 			err = bpf_obj_kver_init(obj, data->d_buf,
 						data->d_size);
+		else if (strcmp(name, "maps") == 0)
+			err = bpf_obj_maps_init(obj, data->d_buf,
+						data->d_size);
 		if (err)
 			goto out;
 	}
@@ -359,5 +385,7 @@ void bpf_close_object(struct bpf_object *obj)
 
 	if (obj->path)
 		free(obj->path);
+	if (obj->maps_buf)
+		free(obj->maps_buf);
 	free(obj);
 }
-- 
1.8.3.4

[RFC PATCH v2 13/37] tools lib bpf: collect config section in object.

[Wang Nan]

A 'config' section is allowed to enable eBPF object file to pass
something to user. libbpf doesn't use config string.

To make further processing easiler, this patch converts '\0' in the
whole config strings into '\n'

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6ee5f3c..43b22a5 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -84,6 +84,7 @@ struct bpf_object {
 	u32 kern_version;
 	void *maps_buf;
 	size_t maps_buf_sz;
+	char *config_str;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -267,6 +268,48 @@ static int bpf_obj_maps_init(struct bpf_object *obj, void *data,
 	return 0;
 }
 
+static int bpf_obj_config_init(struct bpf_object *obj, void *data,
+			       size_t size)
+{
+	char *config_str;
+	char *p, *pend;
+
+	if (size == 0) {
+		pr_debug("bpf: config section in %s empty\n",
+			 obj->path);
+		return 0;
+	}
+	if (obj->config_str) {
+		pr_warning("bpf: multiple config section in %s\n",
+			   obj->path);
+		return -EEXIST;
+	}
+
+	config_str = malloc(size + 1);
+	if (!config_str) {
+		pr_warning("bpf: malloc config string failed\n");
+		return -ENOMEM;
+	}
+
+	memcpy(config_str, data, size);
+
+	/*
+	 * It is possible that config section contains multiple
+	 * Make it a big string by converting all '\0' to '\n' and
+	 * append final '\0'.
+	 */
+	pend = config_str + size;
+	for (p = config_str; p < pend; p++)
+		*p == '\0' ? *p = '\n' : 0 ;
+	*pend = '\0';
+
+	obj->config_str = config_str;
+	pr_debug("--- CONFIG STRING IN %s: ---\n%s\n",
+		 obj->path, config_str);
+	pr_debug("----------------------------\n");
+	return 0;
+}
+
 static int bpf_obj_elf_collect(struct bpf_object *obj)
 {
 	Elf *elf = obj->elf.elf;
@@ -324,6 +367,9 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "maps") == 0)
 			err = bpf_obj_maps_init(obj, data->d_buf,
 						data->d_size);
+		else if (strcmp(name, "config") == 0)
+			err = bpf_obj_config_init(obj, data->d_buf,
+						  data->d_size);
 		if (err)
 			goto out;
 	}
@@ -387,5 +433,7 @@ void bpf_close_object(struct bpf_object *obj)
 		free(obj->path);
 	if (obj->maps_buf)
 		free(obj->maps_buf);
+	if (obj->config_str)
+		free(obj->config_str);
 	free(obj);
 }
-- 
1.8.3.4

[RFC PATCH v2 14/37] tools lib bpf: collect symbol table in object files.

[Wang Nan]

This patch collects symbols section. This section is useful when
linking ELF maps.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 43b22a5..2068f0b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -94,6 +94,7 @@ struct bpf_object {
 		int fd;
 		Elf *elf;
 		GElf_Ehdr ehdr;
+		Elf_Data *symbols;
 	} elf;
 };
 #define obj_elf_valid(o)	((o)->elf.fd >= 0)
@@ -142,6 +143,8 @@ static void bpf_obj_clear_elf(struct bpf_object *obj)
 		elf_end(obj->elf.elf);
 		obj->elf.elf = NULL;
 	}
+	obj->elf.symbols = NULL;
+
 	if (obj->elf.fd >= 0) {
 		close(obj->elf.fd);
 		obj->elf.fd = -1;
@@ -370,6 +373,14 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "config") == 0)
 			err = bpf_obj_config_init(obj, data->d_buf,
 						  data->d_size);
+		else if (sh.sh_type == SHT_SYMTAB) {
+			if (obj->elf.symbols) {
+				pr_warning("bpf: multiple SYMTAB in %s\n",
+					   obj->path);
+				err = -EEXIST;
+			} else
+				obj->elf.symbols = data;
+		}
 		if (err)
 			goto out;
 	}
-- 
1.8.3.4

[RFC PATCH v2 15/37] tools lib bpf: collect bpf programs from object files.

[Wang Nan]

This patch collects all programs in an object file into an array of
'struct bpf_program' for further processing. That structure is for
representing each eBPF program. 'bpf_prog' should be a better name, but
it has been used by linux/filter.h. Although it is a kernel space name,
I still prefer to call it 'bpf_program' to prevent possible confusion.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 111 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2068f0b..18b221f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -77,6 +77,18 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+/* 
+ * bpf_prog should be a better name but it has been used in
+ * linux/filter.h.
+ */
+struct bpf_program {
+	/* Index in elf obj file, for relocation use. */
+	int idx;
+	char *section_name;
+	struct bpf_insn *insns;
+	size_t insns_cnt;
+};
+
 struct bpf_object {
 	char *path;
 	bool needs_swap;
@@ -86,6 +98,9 @@ struct bpf_object {
 	size_t maps_buf_sz;
 	char *config_str;
 
+	struct bpf_program *programs;
+	size_t nr_programs;
+
 	/*
 	 * Information when doing elf related work. Only valid if fd
 	 * is valid.
@@ -99,6 +114,79 @@ struct bpf_object {
 };
 #define obj_elf_valid(o)	((o)->elf.fd >= 0)
 
+static void bpf_clear_program(struct bpf_program *prog)
+{
+	if (!prog)
+		return;
+	if (prog->section_name) {
+		free(prog->section_name);
+		prog->section_name = NULL;
+	}
+	if (prog->insns) {
+		free(prog->insns);
+		prog->insns = NULL;
+	}
+	prog->insns_cnt = 0;
+	prog->idx = -1;
+}
+
+static struct bpf_program *
+bpf_program_alloc(struct bpf_object *obj, void *data, size_t size,
+		  char *name, int idx)
+{
+	struct bpf_program *prog, *progs;
+	int nr_progs;
+
+	if (size < sizeof(struct bpf_insn)) {
+		pr_warning("corrupted section '%s'\n", name);
+		return NULL;
+	}
+	
+	progs = obj->programs;
+	nr_progs = obj->nr_programs;
+
+	progs = realloc(progs, sizeof(*prog) * (nr_progs + 1));
+	if (!progs) {
+		/*
+		 * In this case the original obj->programs
+		 * is still valid, so don't need special treat for
+		 * bpf_close_object().
+		 */
+		pr_warning("failed to alloc a new program '%s'\n",
+			   name);
+		return NULL;
+	}
+
+	obj->programs = progs;
+
+	prog = &progs[nr_progs];
+	bzero(prog, sizeof(*prog));
+
+	obj->nr_programs = nr_progs + 1;
+
+	prog->section_name = strdup(name);
+	if (!prog->section_name) {
+		pr_warning("failed to alloc name for prog %s\n",
+			   name);
+		goto out;
+	}
+
+	prog->insns = malloc(size);
+	if (!prog->insns) {
+		pr_warning("failed to alloc insns for %s\n", name);
+		goto out;
+	}
+	prog->insns_cnt = size / sizeof(struct bpf_insn);
+	memcpy(prog->insns, data,
+	       prog->insns_cnt * sizeof(struct bpf_insn));
+	prog->idx = idx;
+
+	return prog;
+out:
+	bpf_clear_program(prog);
+	return NULL;
+}
+
 static struct bpf_object *__bpf_obj_alloc(const char *path)
 {
 	struct bpf_object *obj;
@@ -380,6 +468,22 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 				err = -EEXIST;
 			} else
 				obj->elf.symbols = data;
+		} else if ((sh.sh_type == SHT_PROGBITS) &&
+			   (sh.sh_flags & SHF_EXECINSTR) &&
+			   (data->d_size > 0)) {
+			struct bpf_program *prog;
+
+			prog = bpf_program_alloc(obj, data->d_buf,
+						 data->d_size, name,
+						 idx);
+			if (!prog) {
+				pr_warning("failed to alloc "
+					   "program %s (%s)", name,
+					   obj->path);
+				err = -ENOMEM;
+			} else
+				pr_debug("found program %s\n",
+					 prog->section_name);
 		}
 		if (err)
 			goto out;
@@ -446,5 +550,12 @@ void bpf_close_object(struct bpf_object *obj)
 		free(obj->maps_buf);
 	if (obj->config_str)
 		free(obj->config_str);
+	if (obj->programs) {
+		size_t i;
+
+		for (i = 0; i < obj->nr_programs; i++)
+			bpf_clear_program(&obj->programs[i]);
+		free(obj->programs);
+	}
 	free(obj);
 }
-- 
1.8.3.4

[RFC PATCH v2 16/37] tools lib bpf: collect relocation sections from object file.

[Wang Nan]

This patch collects relocation sections into 'struct object'.
Such sections are used for connecting maps to bpf programs.
'reloc' field in 'struct bpf_object' is introduced for storing
such informations.

This patch simply store the data into 'reloc' field. Following
patch will parse them to know the exact instructions which are
needed to be relocated.

Note that the collected data will be invalid after ELF object file
is closed.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 18b221f..8fd29a9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -110,6 +110,11 @@ struct bpf_object {
 		Elf *elf;
 		GElf_Ehdr ehdr;
 		Elf_Data *symbols;
+		struct {
+			GElf_Shdr shdr;
+			Elf_Data *data;
+		} *reloc;
+		int nr_reloc;
 	} elf;
 };
 #define obj_elf_valid(o)	((o)->elf.fd >= 0)
@@ -233,6 +238,12 @@ static void bpf_obj_clear_elf(struct bpf_object *obj)
 	}
 	obj->elf.symbols = NULL;
 
+	if (obj->elf.reloc) {
+		free(obj->elf.reloc);
+		obj->elf.reloc = NULL;
+		obj->elf.nr_reloc = 0;
+	}
+
 	if (obj->elf.fd >= 0) {
 		close(obj->elf.fd);
 		obj->elf.fd = -1;
@@ -484,6 +495,24 @@ static int bpf_obj_elf_collect(struct bpf_object *obj)
 			} else
 				pr_debug("found program %s\n",
 					 prog->section_name);
+		} else if (sh.sh_type == SHT_REL) {
+			void *reloc = obj->elf.reloc;
+			int nr_reloc = obj->elf.nr_reloc;
+
+			reloc = realloc(reloc,
+					sizeof(*obj->elf.reloc) * (++nr_reloc));
+			if (!reloc) {
+				pr_warning("realloc failed\n");
+				err = -ENOMEM;
+			} else {
+				int n = nr_reloc - 1;
+
+				obj->elf.reloc = reloc;
+				obj->elf.nr_reloc = nr_reloc;
+
+				obj->elf.reloc[n].shdr = sh;
+				obj->elf.reloc[n].data = data;
+			}
 		}
 		if (err)
 			goto out;
-- 
1.8.3.4

[RFC PATCH v2 17/37] tools lib bpf: collect relocation instructions for each program.

[Wang Nan]

This patch records the indics of instructions which are needed to be
relocated. Those information are saved in 'reloc_desc' field in
'struct bpf_program'. In loading phase (this patch takes effect in
opening phase), the collected instructions will be replaced by
map loading instructions.

Since we are going to close the ELF file and clear all data at the end
of 'opening' phase, ELF information will no longer be valid in
'loading' phase. We have to locate the instructions before maps are
loaded, instead of directly modifying the instruction.

'struct bpf_map_def' is introduce in this patch to let us know how many
maps defined in the object.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h |  10 ++++
 2 files changed, 138 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8fd29a9..ded96cb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10,6 +10,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
+#include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -87,6 +88,12 @@ struct bpf_program {
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt;
+
+	struct {
+		int insn_idx;
+		int map_idx;
+	} *reloc_desc;
+	int nr_reloc;
 };
 
 struct bpf_object {
@@ -131,6 +138,12 @@ static void bpf_clear_program(struct bpf_program *prog)
 		free(prog->insns);
 		prog->insns = NULL;
 	}
+	if (prog->reloc_desc) {
+		free(prog->reloc_desc);
+		prog->reloc_desc = NULL;
+	}
+
+	prog->nr_reloc = 0;
 	prog->insns_cnt = 0;
 	prog->idx = -1;
 }
@@ -521,6 +534,119 @@ out:
 	return err;
 }
 
+static struct bpf_program *
+bpf_find_prog_by_idx(struct bpf_object *obj, int idx)
+{
+	struct bpf_program *prog;
+	size_t i;
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		if (prog->idx == idx)
+			return prog;
+	}
+	return NULL;
+}
+
+static int
+bpf_program_collect_reloc(struct bpf_object *obj,
+			  GElf_Shdr *shdr,
+			  Elf_Data *data,
+			  struct bpf_program *prog)
+{
+	int i, nrels;
+	size_t nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
+
+	pr_debug("collecting relocating info for: '%s'\n",
+			prog->section_name);
+	nrels = shdr->sh_size / shdr->sh_entsize;
+	
+	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
+	if (!prog->reloc_desc) {
+		pr_warning("failed to alloc memory in relocation\n");
+		return -ENOMEM;
+	}
+	prog->nr_reloc = nrels;
+
+	for (i = 0; i < nrels; i++) {
+		GElf_Sym sym;
+		GElf_Rel rel;
+		unsigned int insn_idx;
+		struct bpf_insn *insns = prog->insns;
+		size_t map_idx;
+
+		if (!gelf_getrel(data, i, &rel)) {
+			pr_warning("relocation: failed to get "
+				   "%d reloc\n", i);
+			return -EINVAL;
+		}
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
+		if (!gelf_getsym(obj->elf.symbols,
+				 GELF_R_SYM(rel.r_info),
+				 &sym)) {
+			pr_warning("relocation: symbol %"PRIx64
+				   " not found\n",
+				   GELF_R_SYM(rel.r_info));
+			return -EINVAL;
+		}
+
+		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
+			pr_warning("bpf: relocation: invalid relo for "
+				   "insns[%d].code 0x%x\n",
+				   insn_idx, insns[insn_idx].code);
+			return -EINVAL;
+		}
+
+		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		if (map_idx >= nr_maps) {
+			pr_warning("bpf relocation: map_idx %d large than %d\n",
+				   (int)map_idx, (int)nr_maps - 1);
+			return -EINVAL;
+		}
+
+		prog->reloc_desc[i].insn_idx = insn_idx;
+		prog->reloc_desc[i].map_idx = map_idx;
+	}
+	return 0;
+}
+
+static int bpf_obj_collect_reloc(struct bpf_object *obj)
+{
+	int i, err;
+
+	if (!obj_elf_valid(obj)) {
+		pr_warning("Internal error: elf object is closed\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < obj->elf.nr_reloc; i++) {
+		GElf_Shdr *shdr = &obj->elf.reloc[i].shdr;
+		Elf_Data *data = obj->elf.reloc[i].data;
+		int idx = shdr->sh_info;
+		struct bpf_program *prog;
+
+		if (shdr->sh_type != SHT_REL) {
+			pr_warning("internal error at %d\n", __LINE__);
+			return -EINVAL;
+		}
+
+		prog = bpf_find_prog_by_idx(obj, idx);
+		if (!prog) {
+			pr_warning("relocation failed: no %d section\n",
+				   idx);
+			return -ENOENT;
+		}
+
+		err = bpf_program_collect_reloc(obj, shdr, data, prog);
+		if (err)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int bpf_obj_validate(struct bpf_object *obj)
 {
 	if (obj->kern_version == 0) {
@@ -556,6 +682,8 @@ struct bpf_object *bpf_open_object(const char *path)
 		goto out;
 	if (bpf_obj_elf_collect(obj))
 		goto out;
+	if (bpf_obj_collect_reloc(obj))
+		goto out;
 	if (bpf_obj_validate(obj))
 		goto out;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e523ae9..3505be7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -21,4 +21,14 @@ struct bpf_object;
 struct bpf_object *bpf_open_object(const char *path);
 void bpf_close_object(struct bpf_object *object);
 
+/*
+ * packed attribute is unnecessary for 'bpf_map_def'.
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+};
+
 #endif
-- 
1.8.3.4

[RFC PATCH v2 18/37] tools lib bpf: clean elf memory after loading.

[Wang Nan]

After all eBPF programs in an object file are loaded, related ELF
information is useless. Close the object file and free those memory.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ded96cb..9ed8cca 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -687,8 +687,8 @@ struct bpf_object *bpf_open_object(const char *path)
 	if (bpf_obj_validate(obj))
 		goto out;
 
+	bpf_obj_clear_elf(obj);
 	return obj;
-
 out:
 	bpf_close_object(obj);
 	return NULL;
-- 
1.8.3.4

[RFC PATCH v2 19/37] tools lib bpf: add bpf.c/h for common bpf operations.

[Wang Nan]

This patch introduces bpf.c and bpf.h, which hold common functions
issuing bpf syscall. The goal of these two files is to hide syscall
completly from user.  Note that bpf.c and bpf.h only deal with kernel
interface. Things like structure of 'map' section in the ELF object is
not cared by of bpf.[ch].

We first introduce bpf_create_map().

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/Build |  2 +-
 tools/lib/bpf/bpf.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/bpf.h | 17 +++++++++++++++++
 3 files changed, 71 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/bpf.c
 create mode 100644 tools/lib/bpf/bpf.h

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index a316484..d874975 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o
+libbpf-y := libbpf.o bpf.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
new file mode 100644
index 0000000..3dbe30d
--- /dev/null
+++ b/tools/lib/bpf/bpf.c
@@ -0,0 +1,53 @@
+/*
+ * common eBPF ELF operations.
+ *
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <linux/bpf.h>
+#include "bpf.h"
+
+/* When building perf, unistd.h is override. __NR_bpf by ourself. */
+#if defined(__i386__)
+#ifndef __NR_bpf
+# define __NR_bpf 357
+#endif
+#endif
+
+#if defined(__x86_64__)
+#ifndef __NR_bpf
+# define __NR_bpf 321
+#endif
+#endif
+
+#if defined(__aarch64__)
+#ifndef __NR_bpf
+# define __NR_bpf 280
+#endif
+#endif
+
+static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, unsigned int size)
+{
+	return syscall(__NR_bpf, cmd, attr, size);
+}
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
+		   int max_entries)
+{
+	union bpf_attr attr;
+	memset(&attr, '\0', sizeof(attr));
+	
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
new file mode 100644
index 0000000..1e9a53b
--- /dev/null
+++ b/tools/lib/bpf/bpf.h
@@ -0,0 +1,17 @@
+/*
+ * common eBPF ELF operations.
+ *
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#ifndef __LIBBPF_BPF_H
+#define __LIBBPF_BPF_H
+
+#include <linux/bpf.h>
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
+		   int max_entries);
+
+#endif
-- 
1.8.3.4

[RFC PATCH v2 20/37] tools lib bpf: create maps needed by object file.

[Wang Nan]

This patch creates maps based on 'map' section in object file using
bpf_create_map(), and store the fds into an array in
'struct bpf_object'. Since the byte order of the object may differ
from the host, swap map definition before processing.

This is the first patch in 'loading' phase. Previous patches parse ELF
object file and create needed data structure, but doesnnt play with
kernel. They belong to 'opening' phase.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h |  4 +++
 2 files changed, 102 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 9ed8cca..6ff4cb6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -22,6 +22,7 @@
 #include <gelf.h>
 
 #include "libbpf.h"
+#include "bpf.h"
 
 #ifdef min
 # undef min
@@ -107,6 +108,7 @@ struct bpf_object {
 
 	struct bpf_program *programs;
 	size_t nr_programs;
+	int *maps_fds;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -613,6 +615,67 @@ bpf_program_collect_reloc(struct bpf_object *obj,
 	return 0;
 }
 
+static int
+bpf_obj_create_maps(struct bpf_object *obj)
+{
+	unsigned int i;
+	size_t nr_maps;
+	int *pfd;
+
+	nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
+	if (!obj->maps_buf || !nr_maps) {
+		pr_debug("don't need create maps for %s\n",
+			 obj->path);
+		return 0;
+	}
+
+	obj->maps_fds = malloc(sizeof(int) * nr_maps);
+	if (!obj->maps_fds) {
+		pr_warning("realloc perf_bpf_maps_fds failed\n");
+		return -ENOMEM;
+	}
+
+	/* fill all fd with -1 */
+	memset(obj->maps_fds, 0xff, sizeof(int) * nr_maps);
+	
+	pfd = obj->maps_fds;
+	for (i = 0; i < nr_maps; i++) {
+		struct bpf_map_def def;
+
+		def = *(struct bpf_map_def *)(obj->maps_buf +
+				i * sizeof(struct bpf_map_def));
+
+		if (obj->needs_swap) {
+			def.type	= bswap_32(def.type);
+			def.key_size	= bswap_32(def.key_size);
+			def.value_size	= bswap_32(def.value_size);
+			def.max_entries	= bswap_32(def.max_entries);
+		}
+
+		*pfd = bpf_create_map(def.type,
+				      def.key_size,
+				      def.value_size,
+				      def.max_entries);
+		if (*pfd < 0) {
+			size_t j;
+			int err = *pfd;
+
+			pr_warning("failed to create map: %s\n",
+				   strerror(errno));
+			for (j = 0; j < i; j++) {
+				close(obj->maps_fds[j]);
+				obj->maps_fds[j] = -1;
+			}
+			free(obj->maps_fds);
+			obj->maps_fds = NULL;
+			return err;
+		}
+		pr_debug("create map: fd=%d\n", *pfd);
+		pfd ++;
+	}
+	return 0;
+}
+
 static int bpf_obj_collect_reloc(struct bpf_object *obj)
 {
 	int i, err;
@@ -694,12 +757,47 @@ out:
 	return NULL;
 }
 
+int bpf_unload_object(struct bpf_object *obj)
+{
+	if (!obj)
+		return -EINVAL;
+
+	if (obj->maps_fds) {
+		size_t i;
+		size_t sz = sizeof(struct bpf_map_def);
+
+		for (i = 0; i < obj->maps_buf_sz; i += sz) {
+			if (obj->maps_fds[i] >= 0)
+				close(obj->maps_fds[i]);
+		}
+		free(obj->maps_fds);
+	}
+
+	return 0;
+}
+
+int bpf_load_object(struct bpf_object *obj)
+{
+	if (!obj)
+		return -EINVAL;
+
+	if (bpf_obj_create_maps(obj))
+		goto out;
+
+	return 0;
+out:
+	bpf_unload_object(obj);
+	pr_warning("failed to load object '%s'\n", obj->path);
+	return -EINVAL;
+}
+
 void bpf_close_object(struct bpf_object *obj)
 {
 	if (!obj)
 		return;
 
 	bpf_obj_clear_elf(obj);
+	bpf_unload_object(obj);
 
 	if (obj->path)
 		free(obj->path);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3505be7..c0b290d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -21,6 +21,10 @@ struct bpf_object;
 struct bpf_object *bpf_open_object(const char *path);
 void bpf_close_object(struct bpf_object *object);
 
+/* Load/unload object into/from kernel */
+int bpf_load_object(struct bpf_object *obj);
+int bpf_unload_object(struct bpf_object *obj);
+
 /*
  * packed attribute is unnecessary for 'bpf_map_def'.
  */
-- 
1.8.3.4

[RFC PATCH v2 21/37] tools lib bpf: relocation programs.

[Wang Nan]

If an eBPF program access a map, LLVM generates a relocated load
instruction. To enable the usage of that map, relocation must be done
by replacing original instructions by map loading instructions.

Based on relocation description collected during 'opening' phase, this
patch replaces the instructions with map loading with correct map fd.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6ff4cb6..5e25ea7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -676,6 +676,52 @@ bpf_obj_create_maps(struct bpf_object *obj)
 	return 0;
 }
 
+static int
+bpf_program_relocate(struct bpf_object *obj, struct bpf_program *prog)
+{
+	int i;
+
+	if (!prog || !prog->reloc_desc)
+		return 0;
+
+	for (i = 0; i < prog->nr_reloc; i++) {
+		int insn_idx, map_idx;
+		struct bpf_insn *insns = prog->insns;
+
+		insn_idx = prog->reloc_desc[i].insn_idx;
+		map_idx = prog->reloc_desc[i].map_idx;
+
+		if (insn_idx >= (int)prog->insns_cnt) {
+			pr_warning("relocation out of range: '%s'\n",
+				   prog->section_name);
+			return -ERANGE;
+		}
+		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+		insns[insn_idx].imm = obj->maps_fds[map_idx];
+	}
+
+	return 0;
+}
+
+static int
+bpf_obj_relocate(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	size_t i;
+	int err;
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+
+		if ((err = bpf_program_relocate(obj, prog))) {
+			pr_warning("failed to relocate '%s'\n",
+				   prog->section_name);
+			return err;
+		}
+	}
+	return 0;
+}
+
 static int bpf_obj_collect_reloc(struct bpf_object *obj)
 {
 	int i, err;
@@ -783,6 +829,8 @@ int bpf_load_object(struct bpf_object *obj)
 
 	if (bpf_obj_create_maps(obj))
 		goto out;
+	if (bpf_obj_relocate(obj))
+		goto out;
 
 	return 0;
 out:
-- 
1.8.3.4

[RFC PATCH v2 22/37] tools lib bpf: introduce bpf_load_program to bpf.c.

[Wang Nan]

bpf_load_program() can be used to load bpf program into kernel. To make
loading faster, first try to load without logbuf. Try again with logbuf
if the first try failed.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/bpf.c | 34 ++++++++++++++++++++++++++++++++++
 tools/lib/bpf/bpf.h |  7 +++++++
 2 files changed, 41 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3dbe30d..e4eed22 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -33,6 +33,11 @@
 #endif
 #endif
 
+static __u64 ptr_to_u64(void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, unsigned int size)
 {
 	return syscall(__NR_bpf, cmd, attr, size);
@@ -51,3 +56,32 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
+
+int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+		     size_t insns_cnt, char *license,
+		     u32 kern_version, char *log_buf, size_t log_buf_sz)
+{
+	int fd;
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = type;
+	attr.insn_cnt = (__u32)insns_cnt;
+	attr.insns = ptr_to_u64((void *) insns);
+	attr.license = ptr_to_u64((void *) license);
+	attr.log_buf = ptr_to_u64(NULL);
+	attr.log_size = 0;
+	attr.log_level = 0;
+	attr.kern_version = kern_version;
+
+	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	if ((fd >= 0) || !log_buf || !log_buf_sz)
+		return fd;
+
+	/* Try again with log */
+	attr.log_buf = ptr_to_u64(log_buf);
+	attr.log_size = log_buf_sz;
+	attr.log_level = 1;
+	log_buf[0] = 0;
+	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 1e9a53b..fb2a613 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -14,4 +14,11 @@
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries);
 
+/* Recommend log buffer size */
+#define BPF_LOG_BUF_SIZE 65536
+int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+		     size_t insns_cnt, char *license,
+		     u32 kern_version, char *log_buf,
+		     size_t log_buf_sz);
+
 #endif
-- 
1.8.3.4

[RFC PATCH v2 23/37] tools lib bpf: load bpf programs in object file into kernel.

[Wang Nan]

This patch utilizes previous introduced bpf_load_program to load
programs in the ELF file into kernel. Result is stored in 'fd' field
in 'struct bpf_program'.

During loading, it allocs a log buffer and free it before return.
Note that that buffer is not passed to bpf_load_program() if the first
loading try is successful. Doesn't use a statically allocated log
buffer to avoid potention multi-thread problem.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5e25ea7..e8ef78e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -95,6 +95,8 @@ struct bpf_program {
 		int map_idx;
 	} *reloc_desc;
 	int nr_reloc;
+
+	int fd;
 };
 
 struct bpf_object {
@@ -128,10 +130,24 @@ struct bpf_object {
 };
 #define obj_elf_valid(o)	((o)->elf.fd >= 0)
 
+static void bpf_unload_program(struct bpf_program *prog)
+{
+	if (!prog)
+		return;
+
+	if (prog->fd >= 0) {
+		close(prog->fd);
+		prog->fd = -1;
+	}
+}
+
 static void bpf_clear_program(struct bpf_program *prog)
 {
 	if (!prog)
 		return;
+
+	bpf_unload_program(prog);
+
 	if (prog->section_name) {
 		free(prog->section_name);
 		prog->section_name = NULL;
@@ -200,6 +216,7 @@ bpf_program_alloc(struct bpf_object *obj, void *data, size_t size,
 	memcpy(prog->insns, data,
 	       prog->insns_cnt * sizeof(struct bpf_insn));
 	prog->idx = idx;
+	prog->fd = -1;
 
 	return prog;
 out:
@@ -756,6 +773,59 @@ static int bpf_obj_collect_reloc(struct bpf_object *obj)
 	return 0;
 }
 
+static int
+bpf_obj_load_prog(struct bpf_object *obj, struct bpf_program *prog)
+{
+	int fd, err;
+	char *log_buf;
+
+	log_buf = malloc(BPF_LOG_BUF_SIZE);
+	if (!log_buf)
+		pr_warning("Alloc log buffer for bpf loader error, "
+			   "continue without log\n");
+
+	fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, prog->insns,
+			      prog->insns_cnt, obj->license,
+			      obj->kern_version, log_buf,
+			      BPF_LOG_BUF_SIZE);
+
+	if (fd >= 0) {
+		prog->fd = fd;
+		pr_debug("load bpf program '%s': fd = %d\n",
+			 prog->section_name, prog->fd);
+		err = 0;
+		goto out;
+	}
+
+	err = -EINVAL;
+	pr_warning("load bpf program '%s' failed: %s\n",
+		   prog->section_name, strerror(errno));
+
+	if (log_buf)
+		pr_warning("bpf: load: failed to load program '%s':\n"
+			   "-- BEGIN DUMP LOG ---\n%s\n-- END LOG --\n",
+				prog->section_name, log_buf);
+
+out:
+	if (log_buf)
+		free(log_buf);
+	return err;
+}
+
+static int
+bpf_obj_load_progs(struct bpf_object *obj)
+{
+	size_t i;
+	int err;
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		err = bpf_obj_load_prog(obj, &obj->programs[i]);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static int bpf_obj_validate(struct bpf_object *obj)
 {
 	if (obj->kern_version == 0) {
@@ -819,6 +889,13 @@ int bpf_unload_object(struct bpf_object *obj)
 		free(obj->maps_fds);
 	}
 
+	if (obj->programs) {
+		size_t i;
+
+		for (i = 0; i < obj->nr_programs; i++)
+			bpf_unload_program(&obj->programs[i]);
+	}
+
 	return 0;
 }
 
@@ -831,6 +908,8 @@ int bpf_load_object(struct bpf_object *obj)
 		goto out;
 	if (bpf_obj_relocate(obj))
 		goto out;
+	if (bpf_obj_load_progs(obj))
+		goto out;
 
 	return 0;
 out:
-- 
1.8.3.4

[RFC PATCH v2 24/37] tools lib bpf: accessors of bpf_program.

[Wang Nan]

This patch introduces accessors for user of libbpf to retrive section
name and fd of a opened/loaded eBPF program. 'struct bpf_prog_handler'
is used for that purpose. Accessors of programs section name and file
descriptor are provided. Set/get private data are also impelmented.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 137 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h |  25 +++++++++
 2 files changed, 162 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e8ef78e..d770adc 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -79,6 +79,20 @@ void libbpf_set_print(int (*warn)(const char *format, ...),
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+#ifndef container_of
+# define container_of(ptr, type, member) ({			\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+#endif
+
+/* Accessing of project */
+struct bpf_prog_handler {
+	struct bpf_object *obj;
+
+	void *priv;
+	bpf_prog_clear_priv_t clear_priv;
+};
+
 /* 
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -97,6 +111,7 @@ struct bpf_program {
 	int nr_reloc;
 
 	int fd;
+	struct bpf_prog_handler handler;
 };
 
 struct bpf_object {
@@ -146,6 +161,12 @@ static void bpf_clear_program(struct bpf_program *prog)
 	if (!prog)
 		return;
 
+	if (prog->handler.clear_priv)
+		prog->handler.clear_priv(&prog->handler, prog->handler.priv);
+
+	prog->handler.priv = NULL;
+	prog->handler.clear_priv = NULL;
+
 	bpf_unload_program(prog);
 
 	if (prog->section_name) {
@@ -217,6 +238,7 @@ bpf_program_alloc(struct bpf_object *obj, void *data, size_t size,
 	       prog->insns_cnt * sizeof(struct bpf_insn));
 	prog->idx = idx;
 	prog->fd = -1;
+	prog->handler.obj = obj;
 
 	return prog;
 out:
@@ -941,3 +963,118 @@ void bpf_close_object(struct bpf_object *obj)
 	}
 	free(obj);
 }
+
+static inline struct bpf_program *
+handler_to_prog(struct bpf_prog_handler *handler)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	size_t idx;
+
+	if (!handler)
+		goto out_warn;
+
+	obj = handler->obj;
+	prog = container_of(handler, struct bpf_program, handler);
+	idx = prog - obj->programs;
+	if (idx >= obj->nr_programs)
+		goto out_warn;
+	return &obj->programs[idx];
+
+out_warn:
+	pr_warning("invalid handler %p\n", handler);
+	return NULL;
+}
+
+struct bpf_prog_handler *
+bpf_next_prog(struct bpf_object *obj, struct bpf_prog_handler *handler)
+{
+	struct bpf_program *prog;
+	size_t idx;
+
+	if (!obj->programs)
+		return NULL;
+	/* First handler */
+	if (handler == NULL)
+		return (&obj->programs[0].handler);
+
+	if (handler->obj != obj) {
+		pr_warning("error: program handler doesn't "
+			   "match object\n");
+		return NULL;
+	}
+
+	prog = handler_to_prog(handler);
+	if (!prog)
+		return NULL;
+
+	idx = (prog - obj->programs) + 1;
+	if (idx >= obj->nr_programs)
+		return NULL;
+	return &obj->programs[idx].handler;
+}
+
+int bpf_prog_set_private(struct bpf_prog_handler *handler, void *priv,
+			 bpf_prog_clear_priv_t clear_priv)
+{
+	struct bpf_program *prog;
+
+	prog = handler_to_prog(handler);
+	if (!prog)
+		return -EINVAL;
+
+	if (prog->handler.priv && prog->handler.clear_priv)
+		prog->handler.clear_priv(&prog->handler, prog->handler.priv);
+
+	prog->handler.priv = priv;
+	prog->handler.clear_priv = clear_priv;
+	return 0;
+}
+
+int bpf_prog_get_private(struct bpf_prog_handler *handler, void **ppriv)
+{
+	struct bpf_program *prog;
+
+	prog = handler_to_prog(handler);
+	if (!prog || !ppriv)
+		return -EINVAL;
+
+	*ppriv = prog->handler.priv;
+	return 0;
+}
+
+int bpf_prog_get_title(struct bpf_prog_handler *handler,
+		       const char **ptitle, bool dup)
+{
+	struct bpf_program *prog;
+	const char *title;
+
+	prog = handler_to_prog(handler);
+	if (!prog || !ptitle)
+		return -EINVAL;
+
+	title = prog->section_name;
+	if (dup) {
+		title = strdup(title);
+		if (!title) {
+			pr_warning("failed to strdup program title\n");
+			*ptitle = NULL;
+			return -ENOMEM;
+		}
+	}
+
+	*ptitle = title;
+	return 0;
+}
+
+int bpf_prog_get_fd(struct bpf_prog_handler *handler, int *pfd)
+{
+	struct bpf_program *prog;
+
+	prog = handler_to_prog(handler);
+	if (!prog || !pfd)
+		return -EINVAL;
+
+	*pfd = prog->fd;
+	return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c0b290d..b451d1a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,7 @@
 #define __BPF_LIBBPF_H
 
 #include <stdio.h>
+#include <stdbool.h>
 
 void libbpf_set_print(int (*warn)(const char *format, ...),
 		      int (*info)(const char *format, ...),
@@ -25,6 +26,30 @@ void bpf_close_object(struct bpf_object *object);
 int bpf_load_object(struct bpf_object *obj);
 int bpf_unload_object(struct bpf_object *obj);
 
+/* Accessors of bpf_program. */
+struct bpf_prog_handler;
+struct bpf_prog_handler *bpf_next_prog(struct bpf_object *obj,
+				    struct bpf_prog_handler *handler);
+
+#define bpf_obj_for_each_prog(obj, pos)			\
+	for ((pos) = bpf_next_prog((obj), NULL);	\
+	     (pos) != NULL; 				\
+	     (pos) = bpf_next_prog((obj), (pos)))
+
+typedef void (*bpf_prog_clear_priv_t)(struct bpf_prog_handler *,
+				      void *);
+
+int bpf_prog_set_private(struct bpf_prog_handler *handler, void *priv,
+			 bpf_prog_clear_priv_t clear_priv);
+
+int bpf_prog_get_private(struct bpf_prog_handler *handler,
+			 void **ppriv);
+
+int bpf_prog_get_title(struct bpf_prog_handler *handler,
+		       const char **ptitle, bool dup);
+
+int bpf_prog_get_fd(struct bpf_prog_handler *handler, int *pfd);
+
 /*
  * packed attribute is unnecessary for 'bpf_map_def'.
  */
-- 
1.8.3.4

[RFC PATCH v2 25/37] tools lib bpf: accessors for struct bpf_object.

[Wang Nan]

This patch add an accessor which allows caller to get count of programs
in an object file.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/lib/bpf/libbpf.c | 9 +++++++++
 tools/lib/bpf/libbpf.h | 3 +++
 2 files changed, 12 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d770adc..89c725a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -964,6 +964,15 @@ void bpf_close_object(struct bpf_object *obj)
 	free(obj);
 }
 
+int bpf_obj_get_prog_cnt(struct bpf_object *obj, size_t *pcnt)
+{
+	if (!obj || !pcnt)
+		return -EINVAL;
+
+	*pcnt = obj->nr_programs;
+	return 0;
+}
+
 static inline struct bpf_program *
 handler_to_prog(struct bpf_prog_handler *handler)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b451d1a..31ff5d9 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -26,6 +26,9 @@ void bpf_close_object(struct bpf_object *object);
 int bpf_load_object(struct bpf_object *obj);
 int bpf_unload_object(struct bpf_object *obj);
 
+/* Accessors of bpf_object */
+int bpf_obj_get_prog_cnt(struct bpf_object *obj, size_t *pcnt);
+
 /* Accessors of bpf_program. */
 struct bpf_prog_handler;
 struct bpf_prog_handler *bpf_next_prog(struct bpf_object *obj,
-- 
1.8.3.4

[RFC PATCH v2 26/37] tools perf: Add new 'perf bpf' command.

[Wang Nan]

Adding new 'perf bpf' command to provide eBPF program management
operations. This patch only creates basic 'perf bpf'. Subcommands will
be introduced in following patches.

To utilize existing code of usage_with_options() while enable
subcommand list get output after 'Usage ...' indicator, this patch
add a usage_with_options_noexit() function, which does similar thing
except exiting, allows caller print more information before quit.

In this patch, 'perf bpf' command won't be built if doesn't find
libelf.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/Build                      |  1 +
 tools/perf/Documentation/perf-bpf.txt | 18 ++++++++
 tools/perf/builtin-bpf.c              | 85 +++++++++++++++++++++++++++++++++++
 tools/perf/builtin.h                  |  1 +
 tools/perf/command-list.txt           |  1 +
 tools/perf/perf.c                     |  3 ++
 tools/perf/util/parse-options.c       |  8 +++-
 tools/perf/util/parse-options.h       |  2 +
 8 files changed, 118 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/Documentation/perf-bpf.txt
 create mode 100644 tools/perf/builtin-bpf.c

diff --git a/tools/perf/Build b/tools/perf/Build
index b77370e..c3c6cc3 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -19,6 +19,7 @@ perf-y += builtin-kvm.o
 perf-y += builtin-inject.o
 perf-y += builtin-mem.o
 perf-y += builtin-data.o
+perf-$(CONFIG_LIBELF) += builtin-bpf.o
 
 perf-$(CONFIG_AUDIT) += builtin-trace.o
 perf-$(CONFIG_LIBELF) += builtin-probe.o
diff --git a/tools/perf/Documentation/perf-bpf.txt b/tools/perf/Documentation/perf-bpf.txt
new file mode 100644
index 0000000..0e8b590
--- /dev/null
+++ b/tools/perf/Documentation/perf-bpf.txt
@@ -0,0 +1,18 @@
+perf-bpf(1)
+==============
+
+NAME
+----
+perf-bpf - Management of eBPF programs.
+
+SYNOPSIS
+--------
+[verse]
+'perf bpf' [<common options>] <command> [<options>]",
+
+DESCRIPTION
+-----------
+Management of eBPF programs.
+
+OPTIONS
+-------
diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
new file mode 100644
index 0000000..a8858e2
--- /dev/null
+++ b/tools/perf/builtin-bpf.c
@@ -0,0 +1,85 @@
+/*
+ * builtin-bpf.c
+ *
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ *
+ * Builtin bpf command: management of bpf programs.
+ */
+#include "builtin.h"
+#include "perf.h"
+#include "debug.h"
+#include "parse-options.h"
+
+typedef int (*bpf_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+
+struct bpf_cmd {
+	const char	*name;
+	const char	*summary;
+	bpf_cmd_fn_t	fn;
+};
+
+static struct bpf_cmd bpf_cmds[];
+
+#define for_each_cmd(cmd) \
+	for (cmd = bpf_cmds; cmd && cmd->name; cmd++)
+
+struct option bpf_options[] = {
+	OPT_INCR('v', "verbose", &verbose, "be more verbose "
+					   "(show debug information)"),
+	OPT_END()
+};
+
+static const char *bpf_usage[] = {
+	"perf bpf [<command options>] <command> [<options>]",
+	NULL
+};
+
+static void print_usage(void)
+{
+	struct bpf_cmd *cmd;
+
+	usage_with_options_noexit(bpf_usage, bpf_options);
+	printf("\tAvailable commands:\n");
+	for_each_cmd(cmd)
+		printf("\t %s\t- %s\n", cmd->name, cmd->summary);
+	exit(129);
+}
+
+static const char * const bpf_subcommands[] = { NULL };
+
+static struct bpf_cmd bpf_cmds[] = {
+	{ .name = NULL, },
+};
+
+int cmd_bpf(int argc, const char **argv,
+	    const char *prefix __maybe_unused)
+{
+	struct bpf_cmd *cmd;
+	const char *cmdstr;
+
+	/* No command specified. */
+	if (argc < 2)
+		goto usage;
+
+	argc = parse_options_subcommand(argc, argv, bpf_options, bpf_subcommands, bpf_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+	if (argc < 1)
+		goto usage;
+
+	cmdstr = argv[0];
+
+	for_each_cmd(cmd) {
+		if (strcmp(cmd->name, cmdstr))
+			continue;
+
+		return cmd->fn(argc, argv, prefix);
+	}
+
+	pr_err("Unknown command %s\n", cmdstr);
+usage:
+	print_usage();
+	return -1;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3688ad2..c2c4a0d 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -38,6 +38,7 @@ extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
 extern int cmd_mem(int argc, const char **argv, const char *prefix);
 extern int cmd_data(int argc, const char **argv, const char *prefix);
+extern int cmd_bpf(int argc, const char **argv, const char *prefix);
 
 extern int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00fcaf8..1000463 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -5,6 +5,7 @@
 perf-annotate			mainporcelain common
 perf-archive			mainporcelain common
 perf-bench			mainporcelain common
+perf-bpf			mainporcelain full
 perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index b857fcb..eff1a55 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -64,6 +64,9 @@ static struct cmd_struct commands[] = {
 	{ "inject",	cmd_inject,	0 },
 	{ "mem",	cmd_mem,	0 },
 	{ "data",	cmd_data,	0 },
+#ifdef HAVE_LIBELF_SUPPORT
+	{ "bpf",	cmd_bpf,	0 },
+#endif
 };
 
 struct pager_config {
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 01626be..09e48a2 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -672,9 +672,15 @@ int usage_with_options_internal(const char * const *usagestr,
 void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
+	usage_with_options_noexit(usagestr, opts);
+	exit(129);
+}
+
+void usage_with_options_noexit(const char * const *usagestr,
+			       const struct option *opts)
+{
 	exit_browser(false);
 	usage_with_options_internal(usagestr, opts, 0);
-	exit(129);
 }
 
 int parse_options_usage(const char * const *usagestr,
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd..41194db 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -156,6 +156,8 @@ extern int parse_options_subcommand(int argc, const char **argv,
 
 extern NORETURN void usage_with_options(const char * const *usagestr,
                                         const struct option *options);
+extern void usage_with_options_noexit(const char * const *usagestr,
+				      const struct option *options);
 
 /*----- incremantal advanced APIs -----*/
 
-- 
1.8.3.4

[RFC PATCH v2 27/37] tools perf: make perf depend on libbpf.

[Wang Nan]

By adding libbpf into perf's Makefile, this patch enable perf to
build libbpf during building if libelf is found and NO_LIBELF is not
set. The newly introduced code is similar to libapi and libtraceevent
building in Makefile.perf.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/Makefile.perf | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a205..c69821c 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -123,6 +123,7 @@ STRIP   = strip
 
 LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
+BPF_DIR = $(srctree)/tools/lib/bpf/
 
 # include config/Makefile by default and rule out
 # non-config cases
@@ -158,6 +159,7 @@ strip-libs = $(filter-out -l%,$(1))
 
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
+  BPF_PATH=$(OUTPUT)
 ifneq ($(subdir),)
   LIB_PATH=$(OUTPUT)/../lib/api/
 else
@@ -166,6 +168,7 @@ endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
   LIB_PATH=$(LIB_DIR)
+  BPF_PATH=$(BPF_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -174,6 +177,9 @@ export LIBTRACEEVENT
 LIBAPI = $(LIB_PATH)libapi.a
 export LIBAPI
 
+LIBBPF = $(BPF_PATH)/libbpf.a
+export LIBBPF
+
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
 PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
@@ -225,6 +231,11 @@ export PERL_PATH
 LIB_FILE=$(OUTPUT)libperf.a
 
 PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT)
+ifndef NO_LIBELF
+  ifeq ($(feature-libelf), 1)
+    PERFLIBS += $(LIBBPF)
+  endif
+endif
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
@@ -387,6 +398,13 @@ $(LIBAPI)-clean:
 	$(call QUIET_CLEAN, libapi)
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
+$(LIBBPF): FORCE
+	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a
+
+$(LIBBPF)-clean:
+	$(call QUIET_CLEAN, libbpf)
+	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
+
 help:
 	@echo 'Perf make targets:'
 	@echo '  doc		- make *all* documentation (see below)'
@@ -525,7 +543,7 @@ config-clean:
 	$(call QUIET_CLEAN, config)
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) .config-detected
-- 
1.8.3.4

[RFC PATCH v2 28/37] tools perf: add 'perf bpf record' subcommand.

[Wang Nan]

'perf bpf record' will be implemented to load eBPF object file then
start recording on events defined in it. This patch only adds a
'--object' option for selecting object file. Other arguments are
directly passed to cmd_record.

Example:

 # perf bpf --object obj1.o --object obj2.o -- -a command-to-record

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c | 111 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 109 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index a8858e2..b5c613f 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -48,14 +48,121 @@ static void print_usage(void)
 	exit(129);
 }
 
-static const char * const bpf_subcommands[] = { NULL };
+static const char * const bpf_record_usage[] = {
+	"perf bpf record [<options>] -- [options passed to record]",
+	NULL
+};
+
+struct param {
+	struct strlist *object_file_names;
+} param;
+
+static int add_bpf_object_file(const struct option *opt,
+			       const char *str,
+			       int unset __maybe_unused)
+{
+	struct strlist **filenames = (struct strlist **)opt->value;
+
+	if (!*filenames)
+		*filenames = strlist__new(true, NULL);
+
+	if (!*filenames) {
+		pr_err("alloc strlist failed\n");
+		return -ENOMEM;
+	}
+
+	strlist__add(*filenames, str);
+	return 0;
+}
+
+static int start_bpf_record(int argc, const char **argv)
+{
+	int i, new_argc, err, pos = 0;
+	const char **new_argv;
+
+	new_argc = argc + 1;
+	new_argv = malloc((new_argc + 1) * sizeof(const char *));
+	if (!new_argv) {
+		pr_err("malloc failed\n");
+		return -ENOMEM;
+	}
+	bzero(new_argv, sizeof(const char *) * (new_argc + 1));
+
+	new_argv[pos++] = strdup("bpf record --");
+
+	for (i = 0; i < argc; i++) {
+		new_argv[pos++] = strdup(argv[i]);
+		if (!new_argv[pos - 1]) {
+			pr_err("strdup failed\n");
+			err = -ENOMEM;
+			goto errout;
+		}
+	}
+
+	return cmd_record(new_argc, new_argv, NULL);
+
+errout:
+	if (new_argv) {
+		for (i = 0; i < pos; i++)
+			free((void *)new_argv[i]);
+		free(new_argv);
+	}
+	return err;
+}
+
+static int cmd_bpf_record(int argc, const char **argv,
+			    const char *prefix __maybe_unused)
+{
+	/*
+	 * Options in perf-record may be mirrored here. This command
+	 * should add '-e' options to cmd_record.
+	 */
+	static const struct option options[] = {
+		OPT_CALLBACK(0, "object", &param.object_file_names,
+			     "file", "eBPF object file name",
+			     add_bpf_object_file),
+		OPT_END()
+	};
+	struct str_node *str_node;
+
+	argc = parse_options(argc, argv, options,
+			     bpf_record_usage, PARSE_OPT_KEEP_DASHDASH);
+
+	if (!param.object_file_names) {
+		pr_err("At least one '--object' option is needed to "
+		       "select an eBPF object file\n");
+		goto usage;
+	}
+
+	if (!argv || strcmp(argv[0], "--")) {
+		pr_err("Should use '--' to pass options to perf "
+		       "record\n");
+		goto usage;
+	}
+
+	/* skip "--" */
+	argc--;
+	argv++;
+
+	strlist__for_each(str_node, param.object_file_names)
+		pr_debug("loading %s\n", str_node->s);
+
+	return start_bpf_record(argc, argv);
+usage:
+	usage_with_options(bpf_record_usage, options);
+	return -1;
+}
+
+
+static const char * const bpf_subcommands[] = { "record", NULL };
 
 static struct bpf_cmd bpf_cmds[] = {
+	{ "record", "load eBPF program into kernel then start record on events in it", cmd_bpf_record },
 	{ .name = NULL, },
 };
 
 int cmd_bpf(int argc, const char **argv,
-	    const char *prefix __maybe_unused)
+	    const char *prefix)
 {
 	struct bpf_cmd *cmd;
 	const char *cmdstr;
-- 
1.8.3.4

[RFC PATCH v2 29/37] tools perf: add bpf-loader and open elf object files.

[Wang Nan]

bpf_prepare_laod() is used to open each eBPF object files. The
returned handlers are stored into an array. A corresponding bpf_clear()
is introduced to free all resources.

For the propose of logging, 3 printing functions are defined using
DEFINE_PRINT_FN, which require a veprintf to process va_list args.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c     | 12 +++++++-
 tools/perf/util/Build        |  1 +
 tools/perf/util/bpf-loader.c | 69 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h | 13 +++++++++
 tools/perf/util/debug.c      |  5 ++++
 tools/perf/util/debug.h      |  1 +
 6 files changed, 100 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/util/bpf-loader.c
 create mode 100644 tools/perf/util/bpf-loader.h

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index b5c613f..e922921 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -12,6 +12,7 @@
 #include "perf.h"
 #include "debug.h"
 #include "parse-options.h"
+#include "bpf-loader.h"
 
 typedef int (*bpf_cmd_fn_t)(int argc, const char **argv, const char *prefix);
 
@@ -124,6 +125,7 @@ static int cmd_bpf_record(int argc, const char **argv,
 		OPT_END()
 	};
 	struct str_node *str_node;
+	int err;
 
 	argc = parse_options(argc, argv, options,
 			     bpf_record_usage, PARSE_OPT_KEEP_DASHDASH);
@@ -144,8 +146,16 @@ static int cmd_bpf_record(int argc, const char **argv,
 	argc--;
 	argv++;
 
-	strlist__for_each(str_node, param.object_file_names)
+	strlist__for_each(str_node, param.object_file_names) {
+		const char *fn = str_node->s;
+
 		pr_debug("loading %s\n", str_node->s);
+		if ((err = bpf_prepare_load(fn))) {
+			pr_err("bpf: failed to load object file %s\n",
+			       fn);
+			return -1;
+		}
+	}
 
 	return start_bpf_record(argc, argv);
 usage:
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a..609f6d6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -75,6 +75,7 @@ libperf-$(CONFIG_X86) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
 
+libperf-$(CONFIG_LIBELF) += bpf-loader.o
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
new file mode 100644
index 0000000..17cd2b6
--- /dev/null
+++ b/tools/perf/util/bpf-loader.c
@@ -0,0 +1,69 @@
+/*
+ * bpf-loader.c
+ *
+ * Load bpf files into kernel using libbpf; create kprobe events.
+ */
+
+#include <bpf/libbpf.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+
+#define DEFINE_PRINT_FN(name, level) \
+static int libbpf_##name(const char *fmt, ...)	\
+{						\
+	va_list args;				\
+	int ret;				\
+						\
+	va_start(args, fmt);			\
+	ret = veprintf(level, verbose, pr_fmt(fmt), args);\
+	va_end(args);				\
+	return ret;				\
+}
+
+DEFINE_PRINT_FN(warning, 0)
+DEFINE_PRINT_FN(info, 0)
+DEFINE_PRINT_FN(debug, 1)
+
+static bool libbpf_inited = false;
+
+#define MAX_OBJECTS	128
+
+struct {
+	struct bpf_object *objects[MAX_OBJECTS];
+	size_t nr_objects;
+} params;
+
+int bpf_prepare_load(const char *filename)
+{
+	struct bpf_object *obj;
+
+	if (!libbpf_inited)
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+
+	pr_debug("bpf: loading %s\n", filename);
+	if (params.nr_objects + 1 > MAX_OBJECTS) {
+		pr_err("Too many objects to load. "
+			"Increase MAX_OBJECTS\n");
+		return -EMFILE;
+	}
+
+	obj = bpf_open_object(filename);
+	if (!obj) {
+		pr_err("bpf: failed to load %s\n", filename);
+		return -EINVAL;
+	}
+
+	params.objects[params.nr_objects++] = obj;
+	return 0;
+}
+
+void bpf_clear(void)
+{
+	size_t i;
+
+	for (i = 0; i < params.nr_objects; i++)
+		bpf_close_object(params.objects[i]);
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
new file mode 100644
index 0000000..74eebc3
--- /dev/null
+++ b/tools/perf/util/bpf-loader.h
@@ -0,0 +1,13 @@
+/*
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#ifndef __BPF_LOADER_H
+#define __BPF_LOADER_H
+
+int bpf_prepare_load(const char *filename);
+
+void bpf_clear(void);
+#endif
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 2da5581..86d9c73 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -36,6 +36,11 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
 	return ret;
 }
 
+int veprintf(int level, int var, const char *fmt, va_list args)
+{
+	return _eprintf(level, var, fmt, args);
+}
+
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index caac2fd..8b9a088 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -50,6 +50,7 @@ void pr_stat(const char *fmt, ...);
 
 int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
 int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
+int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
 
-- 
1.8.3.4

[RFC PATCH v2 30/37] tools perf: collect all bpf programs.

[Wang Nan]

This patch collects 'struct bpf_prog_handler *' after opening an object
file. Handlers are stored into an array of MAX_PROBES slots.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/util/bpf-loader.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 17cd2b6..67bfb62 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -8,6 +8,7 @@
 #include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
+#include "probe-finder.h" // for MAX_PROBES
 
 #define DEFINE_PRINT_FN(name, level) \
 static int libbpf_##name(const char *fmt, ...)	\
@@ -32,11 +33,17 @@ static bool libbpf_inited = false;
 struct {
 	struct bpf_object *objects[MAX_OBJECTS];
 	size_t nr_objects;
+
+	struct {
+		struct bpf_prog_handler *prog;
+	} progs[MAX_PROBES];
+	size_t nr_progs;
 } params;
 
 int bpf_prepare_load(const char *filename)
 {
 	struct bpf_object *obj;
+	struct bpf_prog_handler *prog;
 
 	if (!libbpf_inited)
 		libbpf_set_print(libbpf_warning,
@@ -57,6 +64,24 @@ int bpf_prepare_load(const char *filename)
 	}
 
 	params.objects[params.nr_objects++] = obj;
+
+	bpf_obj_for_each_prog(obj, prog) {
+		const char *title;
+
+		if (params.nr_progs + 1 > MAX_PROBES) {
+			pr_err("Too many programs. "
+			       "Increase MAX_PROBES\n");
+			return -EMFILE;
+		}
+
+		params.progs[params.nr_progs++].prog = prog;
+
+		if (bpf_prog_get_title(prog, &title, false)) {
+			pr_err("Unable to get title of a program\n");
+			return -EINVAL;
+		}
+		pr_debug("bpf: add program '%s'\n", title);
+	}
 	return 0;
 }
 
-- 
1.8.3.4

[RFC PATCH v2 31/37] tools perf: config probe points of eBPF programs during prepartion.

[Wang Nan]

This patch parses section name of each program, and creates
corresponding 'struct perf_probe_event' structure.

parse_perf_probe_command() is used to do the main parsing works.
Parsing result is stored into a global array. This is because
add_perf_probe_events() is non-reentrantable. In following patch,
add_perf_probe_events will be introduced to insert kprobes. It accepts
an array of 'struct perf_probe_event' and do works in one call.

Define PERF_BPF_PROBE_GROUP as "perf_bpf_probe", which will be used
as group name of all eBPF probing points.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/util/bpf-loader.c | 74 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 67bfb62..3dc9b61 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -29,6 +29,7 @@ DEFINE_PRINT_FN(debug, 1)
 static bool libbpf_inited = false;
 
 #define MAX_OBJECTS	128
+#define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 struct {
 	struct bpf_object *objects[MAX_OBJECTS];
@@ -36,10 +37,78 @@ struct {
 
 	struct {
 		struct bpf_prog_handler *prog;
+		struct perf_probe_event *pevent;
 	} progs[MAX_PROBES];
 	size_t nr_progs;
+
+	struct perf_probe_event event_array[MAX_PROBES];
+	size_t nr_events;
 } params;
 
+static struct perf_probe_event *
+alloc_perf_probe_event(void)
+{
+	struct perf_probe_event *pev;
+	int n = params.nr_events;
+
+	if (n >= MAX_PROBES) {
+		pr_err("bpf: too many events, increase MAX_PROBES\n");
+		return NULL;
+	}
+
+	params.nr_events = n + 1;
+	pev = &params.event_array[n];
+	bzero(pev, sizeof(*pev));
+	return pev;
+}
+
+static int
+bpf_do_config(size_t prog_idx, const char *config_str)
+{
+	struct perf_probe_event *pev = alloc_perf_probe_event();
+	int err = 0;
+	
+	if (!pev)
+		return -ENOMEM;
+
+	if ((err = parse_perf_probe_command(config_str, pev)) < 0) {
+		pr_err("bpf config: %s is not a valid config string\n",
+			config_str);
+		/* parse failed, don't need clear pev. */
+		return -EINVAL;
+	}
+
+	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
+		pr_err("bpf config: '%s': group for event is set "
+		       "and not '%s'.\n", config_str,
+		       PERF_BPF_PROBE_GROUP);
+		err = -EINVAL;
+		goto errout;
+	} else if (!pev->group)
+		pev->group = strdup(PERF_BPF_PROBE_GROUP);
+
+	if (!pev->group) {
+		pr_err("bpf config: strdup failed\n");
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	if (!pev->event) {
+		pr_err("bpf config: '%s': event name is missing\n",
+				config_str);
+		err = -EINVAL;
+		goto errout;
+	}
+
+	pr_debug("bpf config: config '%s' ok\n", config_str);
+	params.progs[prog_idx].pevent = pev;
+	return 0;
+errout:
+	if (pev)
+		clear_perf_probe_event(pev);
+	return err;
+}
+
 int bpf_prepare_load(const char *filename)
 {
 	struct bpf_object *obj;
@@ -81,6 +150,8 @@ int bpf_prepare_load(const char *filename)
 			return -EINVAL;
 		}
 		pr_debug("bpf: add program '%s'\n", title);
+
+		bpf_do_config(params.nr_progs - 1, title);
 	}
 	return 0;
 }
@@ -89,6 +160,9 @@ void bpf_clear(void)
 {
 	size_t i;
 
+	for (i = 0; i < params.nr_events; i++)
+		clear_perf_probe_event(&params.event_array[i]);
+
 	for (i = 0; i < params.nr_objects; i++)
 		bpf_close_object(params.objects[i]);
 }
-- 
1.8.3.4

[RFC PATCH v2 32/37] tools perf bpf: probe at kprobe points.

[Wang Nan]

In this patch, kprobe points are created using add_perf_probe_events.
Since all events are already grouped together in an array, calling
add_perf_probe_events() once creates all of them.

To ensure recover the system when existing, a bpf_unprobe() is also
provided and hooked to atexit(). Because all of events are in group
"perf_bpf_probe" (PERF_BPF_PROBE_GROUP), use 'perf_bpf_probe:*' string
to remove all of them should be a simple method. However, this also
introduces a constrain that only one instance of 'perf bpf' is allowed
to be active.

Due to the atexit hook, this patch must ensure bpf_unprobe() won't
error if it has been executed. A global flag 'is_probing' is used to
track probing state. bpf_unprobe() will do nothing if it is unset.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c     |  8 ++++++++
 tools/perf/util/bpf-loader.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  2 ++
 3 files changed, 58 insertions(+)

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index e922921..95e0c65 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -157,10 +157,18 @@ static int cmd_bpf_record(int argc, const char **argv,
 		}
 	}
 
+	if (bpf_probe()) {
+		pr_err("bpf: failed to probe\n");
+		goto errout;
+	}
+
 	return start_bpf_record(argc, argv);
 usage:
 	usage_with_options(bpf_record_usage, options);
 	return -1;
+errout:
+	bpf_clear();
+	return -1;
 }
 
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 3dc9b61..c820d1a 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -160,9 +160,57 @@ void bpf_clear(void)
 {
 	size_t i;
 
+	bpf_unprobe();
 	for (i = 0; i < params.nr_events; i++)
 		clear_perf_probe_event(&params.event_array[i]);
 
 	for (i = 0; i < params.nr_objects; i++)
 		bpf_close_object(params.objects[i]);
 }
+
+static bool is_probing = false;
+
+int bpf_unprobe(void)
+{
+	struct strlist *dellist;
+	int ret;
+
+	if (!is_probing)
+		return 0;
+
+	dellist = strlist__new(true, PERF_BPF_PROBE_GROUP ":*");
+	if (!dellist) {
+		pr_err("Failed to create dellist when unprobing\n");
+		return -ENOMEM;
+	}
+
+	ret = del_perf_probe_events(dellist);
+	strlist__delete(dellist);
+	if (ret < 0)
+		pr_err("  Error: failed to delete events: %s\n",
+			strerror(-ret));
+	else
+		is_probing = false;
+	return ret < 0 ? ret : 0;
+}
+
+static void bpf_unprobe_atexit(void)
+{
+	bpf_unprobe();
+}
+
+int bpf_probe(void)
+{
+	int err = add_perf_probe_events(params.event_array,
+					params.nr_events,
+					MAX_PROBES, 0);
+	/* add_perf_probe_events return negative when fail */
+	if (err < 0)
+		pr_err("bpf probe: failed to probe events\n");
+	else {
+		is_probing = true;
+		atexit(bpf_unprobe_atexit);
+	}
+
+	return err < 0 ? err : 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 74eebc3..30dea2e 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,6 +8,8 @@
 #define __BPF_LOADER_H
 
 int bpf_prepare_load(const char *filename);
+int bpf_probe(void);
+int bpf_unprobe(void);
 
 void bpf_clear(void);
 #endif
-- 
1.8.3.4

[RFC PATCH v2 33/37] tools perf bpf: load eBPF object into kernel.

[Wang Nan]

This patch utilizes bpf_load_object() provided by libbpf to load all
objects into kernel.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c     |  5 +++++
 tools/perf/util/bpf-loader.c | 16 ++++++++++++++++
 tools/perf/util/bpf-loader.h |  3 ++-
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index 95e0c65..8155f39 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -162,6 +162,11 @@ static int cmd_bpf_record(int argc, const char **argv,
 		goto errout;
 	}
 
+	if (bpf_load()) {
+		pr_err("bpf: failed to load\n");
+		goto errout;
+	}
+
 	return start_bpf_record(argc, argv);
 usage:
 	usage_with_options(bpf_record_usage, options);
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index c820d1a..7295a3b 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -214,3 +214,19 @@ int bpf_probe(void)
 
 	return err < 0 ? err : 0;
 }
+
+int bpf_load(void)
+{
+	size_t i;
+	int err;
+
+	for (i = 0; i < params.nr_objects; i++) {
+		err = bpf_load_object(params.objects[i]);
+		if (err) {
+			pr_err("failed to load object\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 30dea2e..1ccebdf 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -9,7 +9,8 @@
 
 int bpf_prepare_load(const char *filename);
 int bpf_probe(void);
-int bpf_unprobe(void);
+int bpf_load(void);
 
+int bpf_unprobe(void);
 void bpf_clear(void);
 #endif
-- 
1.8.3.4

[RFC PATCH v2 34/37] tools perf: add a bpf_wrapper global flag.

[Wang Nan]

The newly introduced flag is a indicator for 'perf bpf'. When commands
like 'cmd_record' is started using 'perf bpf', they should consider the
binding of bpf programs.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c | 3 +++
 tools/perf/perf.c        | 7 +++++++
 tools/perf/perf.h        | 1 +
 3 files changed, 11 insertions(+)

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index 8155f39..94978c7 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -201,6 +201,9 @@ int cmd_bpf(int argc, const char **argv,
 
 	cmdstr = argv[0];
 
+	/* This flag is for commands 'perf bpf' start. */
+	bpf_wrapper = true;
+
 	for_each_cmd(cmd) {
 		if (strcmp(cmd->name, cmdstr))
 			continue;
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index eff1a55..2c41c43 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -28,6 +28,13 @@ int use_browser = -1;
 static int use_pager = -1;
 const char *input_name;
 
+/*
+ * Only for cmd_bpf, set this wrapper to true. This flag is to tell
+ * commands like 'record' that they are running inside a 'perf bpf'
+ * command, and let them consider binding of bpf programs.
+ */
+bool bpf_wrapper = false;
+
 struct cmd_struct {
 	const char *cmd;
 	int (*fn)(int, const char **, const char *);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb63..f3d233a 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -69,4 +69,5 @@ struct record_opts {
 struct option;
 extern const char * const *record_usage;
 extern struct option *record_options;
+extern bool bpf_wrapper;
 #endif
-- 
1.8.3.4

[RFC PATCH v2 35/37] tools perf: add bpf_fd field to evsel and introduce new event syntax.

[Wang Nan]

This patch adds a bpf_fd field to 'struct evsel' and instroduces new
syntax for bpf use. Following patches will generate cmdline for
cmd_record, add '-e' options to enable tracing on events set in eBPF
object files. By using the newly introduced 'bpf_wrapper', this patch
ensures that the new '|bpf_fd=%d|' syntax is hidden to user, only
internal use is valid.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/util/evsel.c        |  1 +
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c | 19 +++++++++++++++++++
 tools/perf/util/parse-events.h |  3 +++
 tools/perf/util/parse-events.l |  8 +++++++-
 tools/perf/util/parse-events.y | 21 +++++++++++++++++++++
 6 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8..04d60a7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -205,6 +205,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
 	perf_evsel__object.init(evsel);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151..ff1f634 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -100,6 +100,7 @@ struct perf_evsel {
 	int			sample_read;
 	struct perf_evsel	*leader;
 	char			*group_name;
+	int			bpf_fd;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index be06553..5e49ddb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -471,6 +471,25 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 		return add_tracepoint_event(list, idx, sys, event);
 }
 
+int parse_events_set_bpf_fd(struct list_head *list, int bpf_fd)
+{
+	struct perf_evsel *evsel;
+
+	if (!bpf_wrapper) {
+		fprintf(stderr,
+			"ERROR:\n"
+			"\tbpf fd should only be set by 'perf bpf', \n"
+			"\tuser should never use '|' syntax when \n"
+			"\tsetup events.\n"
+			"\n");
+		return -EINVAL;
+	}
+
+	__evlist__for_each(list, evsel)
+		evsel->bpf_fd = bpf_fd;
+	return 0;
+}
+
 static int
 parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 52a2dda..427a74a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -102,6 +102,9 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_add_numeric(struct list_head *list, int *idx,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
+
+int parse_events_set_bpf_fd(struct list_head *list, int bpf_fd);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8895cf3..0be944a 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -88,7 +88,7 @@ static int term(yyscan_t scanner, int type)
 %}
 
 %x mem
-%s config
+%s config bpf_config
 %x event
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
@@ -156,6 +156,11 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 {name_minus}		{ return str(yyscanner, PE_NAME); }
 }
 
+<bpf_config>{
+bpf_fd			{ return PE_BPFFD; }
+"|"			{ BEGIN(INITIAL); return '|'; }
+}
+
 <mem>{
 {modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
 :			{ return ':'; }
@@ -230,6 +235,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
+"|"			{ BEGIN(bpf_config); return '|'; }
 -			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
 :			{ return ':'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 72def07..6c99322 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_BPFFD
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -62,12 +63,14 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <num> event_bpf_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
 %type <head> event_legacy_cache
 %type <head> event_legacy_mem
 %type <head> event_legacy_tracepoint
+%type <head> event_legacy_tracepoint_event
 %type <head> event_legacy_numeric
 %type <head> event_legacy_raw
 %type <head> event_def
@@ -371,6 +374,24 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
+event_legacy_tracepoint_event
+{
+	$$ = $1;	
+}
+|
+event_legacy_tracepoint_event '|' event_bpf_config '|'
+{
+	ABORT_ON(parse_events_set_bpf_fd($1, $3));
+	$$ = $1;
+}
+
+event_bpf_config:
+PE_BPFFD '=' PE_VALUE
+{
+	$$ = $3;
+}
+
+event_legacy_tracepoint_event:
 PE_NAME '-' PE_NAME ':' PE_NAME
 {
 	struct parse_events_evlist *data = _data;
-- 
1.8.3.4

[RFC PATCH v2 36/37] tools perf: generate event argv.

[Wang Nan]

bpf_load_gen_argv() generates argc and argv which will be passed to
other commands like cmd_record(). The generated arguments utilized
previous introduced '|' syntax to pass file descriptor of bpf
programs.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/util/bpf-loader.c | 87 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  8 ++++
 2 files changed, 95 insertions(+)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 7295a3b..a75b0b7 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -215,6 +215,93 @@ int bpf_probe(void)
 	return err < 0 ? err : 0;
 }
 
+int bpf_load_gen_argv(int *pargc, const char ***pargv,
+		      int old_argc, const char **old_argv,
+		      const char *arg0)
+{
+	const char **argv = NULL;
+	int i, argc, pos, err;
+
+	if (!pargc || !pargv)
+		return -EINVAL;
+	if (!old_argv && old_argc)
+		return -EINVAL;
+
+	/*
+	 * <arg0> <new args> <old args> NIL
+	 * Omit the last NIL in argc.
+	 */
+	argc = 1 + params.nr_progs * 2 + old_argc;
+	argv = malloc(sizeof(const char *) * (argc + 1));
+	if (!argv) {
+		pr_err("No enough memory\n");
+		return -ENOMEM;
+	}
+	bzero(argv, sizeof(char *) * (argc + 1));
+
+	pos = 0;
+
+	if (arg0)
+		argv[pos++] = strdup(arg0);
+
+	for (i = 0; i < (int)params.nr_progs; i++) {
+		struct bpf_prog_handler *prog =
+			params.progs[i].prog;
+		struct perf_probe_event *pevent =
+			params.progs[i].pevent;
+		int cmd_size, fd;
+		char *event_str;
+
+		err = bpf_prog_get_fd(prog, &fd);
+		if (err) {
+			pr_err("Unable to get program fd\n");
+			goto errout;
+		}
+
+		cmd_size = snprintf(NULL, 0,
+				"%s:%s|bpf_fd=%d|", pevent->group,
+				pevent->event, fd);
+
+		event_str = malloc(cmd_size + 1);
+		if (!event_str) {
+			pr_err("No enough menory\n");
+			goto errout;
+		}
+
+		snprintf(event_str, cmd_size + 1, "%s:%s|bpf_fd=%d|",
+			 pevent->group, pevent->event, fd);
+
+		argv[pos++] = strdup("-e");
+		if (!argv[pos - 1]) {
+			pr_err("No enough memory\n");
+			goto errout;
+		}
+
+		argv[pos++] = event_str;
+
+		pr_debug("event: -e %s\n", event_str);
+	}
+
+	for (i = 0; i < old_argc; i++) {
+		argv[pos++] = strdup(old_argv[i]);
+		if (!argv[pos - 1]) {
+			pr_err("No enough memory\n");
+			goto errout;
+		}
+	}
+
+	*pargc = pos;
+	*pargv = argv;
+	return 0;
+errout:
+	for (i = 0; (int)i < argc; i++) {
+		if (argv[i])
+			free((void *)argv[i]);
+	}
+	free(argv);
+	return err;
+}
+
 int bpf_load(void)
 {
 	size_t i;
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 1ccebdf..eea45f4 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -13,4 +13,12 @@ int bpf_load(void);
 
 int bpf_unprobe(void);
 void bpf_clear(void);
+
+/*
+ * Generates argv like '-e my_event|bpf_fd=5|' for wrapping other
+ * commands.
+ */
+int bpf_load_gen_argv(int *pargc, const char ***pargv,
+		      int old_argc, const char **old_argv,
+		      const char *arg0);
 #endif
-- 
1.8.3.4

[RFC PATCH v2 37/37] tools perf bpf: passes generated arguments to cmd_record.

[Wang Nan]

This patch utilizes previous introduced bpf_load_gen_argv() to generate
arguments for cmd_record.

We should try to avoid triggering atexit() unprobe handler because the
state of the process is uncommon. For example, stdio and stderr are
closed. Moreover, we are unable to ensure atexit() handler will be
called at every situations.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-bpf.c | 36 ++++++++++--------------------------
 1 file changed, 10 insertions(+), 26 deletions(-)

diff --git a/tools/perf/builtin-bpf.c b/tools/perf/builtin-bpf.c
index 94978c7..c818c9f 100644
--- a/tools/perf/builtin-bpf.c
+++ b/tools/perf/builtin-bpf.c
@@ -78,36 +78,20 @@ static int add_bpf_object_file(const struct option *opt,
 
 static int start_bpf_record(int argc, const char **argv)
 {
-	int i, new_argc, err, pos = 0;
+	int new_argc, err;
 	const char **new_argv;
 
-	new_argc = argc + 1;
-	new_argv = malloc((new_argc + 1) * sizeof(const char *));
-	if (!new_argv) {
-		pr_err("malloc failed\n");
-		return -ENOMEM;
-	}
-	bzero(new_argv, sizeof(const char *) * (new_argc + 1));
-
-	new_argv[pos++] = strdup("bpf record --");
-
-	for (i = 0; i < argc; i++) {
-		new_argv[pos++] = strdup(argv[i]);
-		if (!new_argv[pos - 1]) {
-			pr_err("strdup failed\n");
-			err = -ENOMEM;
-			goto errout;
-		}
+	if ((err = bpf_load_gen_argv(&new_argc, &new_argv,
+				     argc, argv,
+				     "bpf record --")))
+	{
+		pr_err("Failed to generate arguments for record\n");
+		return err;
 	}
 
-	return cmd_record(new_argc, new_argv, NULL);
-
-errout:
-	if (new_argv) {
-		for (i = 0; i < pos; i++)
-			free((void *)new_argv[i]);
-		free(new_argv);
-	}
+	/* new_argv won't be freed because cmd_record may change it. */
+	err = cmd_record(new_argc, new_argv, NULL);
+	bpf_unprobe();
 	return err;
 }
 
-- 
1.8.3.4

Re: [RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[Ingo Molnar]

Just a small stylistic side note:

> Wang Nan (37):
>   tools perf: set vmlinux_path__nr_entries to 0 in vmlinux_path__exit.
>   tools lib traceevent: install libtraceevent.a into libdir.
>   tools build: Allow other override features to check.
>   tools include: add __aligned_u64 to types.h.
>   tools lib bpf: introduce 'bpf' library to tools.
>   tools lib bpf: allow set printing function.
>   tools lib bpf: defines basic interface.
>   tools lib bpf: open eBPF object file and do basic validation.
>   tools lib bpf: check swap according to EHDR.
>   tools lib bpf: iterater over elf sections to collect information.
>   tools lib bpf: collect version and license from ELF.
>   tools lib bpf: collect map definitions.
>   tools lib bpf: collect config section in object.
>   tools lib bpf: collect symbol table in object files.
>   tools lib bpf: collect bpf programs from object files.
>   tools lib bpf: collect relocation sections from object file.
>   tools lib bpf: collect relocation instructions for each program.
>   tools lib bpf: clean elf memory after loading.
>   tools lib bpf: add bpf.c/h for common bpf operations.
>   tools lib bpf: create maps needed by object file.
>   tools lib bpf: relocation programs.
>   tools lib bpf: introduce bpf_load_program to bpf.c.
>   tools lib bpf: load bpf programs in object file into kernel.
>   tools lib bpf: accessors of bpf_program.
>   tools lib bpf: accessors for struct bpf_object.
>   tools perf: Add new 'perf bpf' command.
>   tools perf: make perf depend on libbpf.
>   tools perf: add 'perf bpf record' subcommand.
>   tools perf: add bpf-loader and open elf object files.
>   tools perf: collect all bpf programs.
>   tools perf: config probe points of eBPF programs during prepartion.
>   tools perf bpf: probe at kprobe points.
>   tools perf bpf: load eBPF object into kernel.
>   tools perf: add a bpf_wrapper global flag.
>   tools perf: add bpf_fd field to evsel and introduce new event syntax.
>   tools perf: generate event argv.
>   tools perf bpf: passes generated arguments to cmd_record.

The titles of the changes have numerous problems and inconsistencies:

 - use consistent capitalization, i.e.:

    tools perf: Collect all bpf programs

 - don't use period at the end, i.e.:

    tools perf: Generate event argv

 - use consistent present tense verbs, i.e.:

    -  tools lib bpf: defines basic interface.
    +  tools lib bpf: Define basic interface

 - Always use verbs! I.e. these are bad:

    -   tools perf: config probe points of eBPF programs during prepartion.
    -   tools lib bpf: relocation programs.

 - take a look at 'git log tools/perf' to see what the established 
   title style is. For example it's not 'tools perf' but 'perf tools', 
   etc.

etc.

There's not a single title in this series that has a proper title. 
This makes the shortlog a difficult read and gives a bad first 
impression. Please fix.

Thanks,

    Ingo

Re: [RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[Wangnan (F)]

在 2015/5/15 16:03, Ingo Molnar 写道:
> Just a small stylistic side note:
>
>> Wang Nan (37):
>>    tools perf: set vmlinux_path__nr_entries to 0 in vmlinux_path__exit.
>>    tools lib traceevent: install libtraceevent.a into libdir.
>>    tools build: Allow other override features to check.
>>    tools include: add __aligned_u64 to types.h.
>>    tools lib bpf: introduce 'bpf' library to tools.
>>    tools lib bpf: allow set printing function.
>>    tools lib bpf: defines basic interface.
>>    tools lib bpf: open eBPF object file and do basic validation.
>>    tools lib bpf: check swap according to EHDR.
>>    tools lib bpf: iterater over elf sections to collect information.
>>    tools lib bpf: collect version and license from ELF.
>>    tools lib bpf: collect map definitions.
>>    tools lib bpf: collect config section in object.
>>    tools lib bpf: collect symbol table in object files.
>>    tools lib bpf: collect bpf programs from object files.
>>    tools lib bpf: collect relocation sections from object file.
>>    tools lib bpf: collect relocation instructions for each program.
>>    tools lib bpf: clean elf memory after loading.
>>    tools lib bpf: add bpf.c/h for common bpf operations.
>>    tools lib bpf: create maps needed by object file.
>>    tools lib bpf: relocation programs.
>>    tools lib bpf: introduce bpf_load_program to bpf.c.
>>    tools lib bpf: load bpf programs in object file into kernel.
>>    tools lib bpf: accessors of bpf_program.
>>    tools lib bpf: accessors for struct bpf_object.
>>    tools perf: Add new 'perf bpf' command.
>>    tools perf: make perf depend on libbpf.
>>    tools perf: add 'perf bpf record' subcommand.
>>    tools perf: add bpf-loader and open elf object files.
>>    tools perf: collect all bpf programs.
>>    tools perf: config probe points of eBPF programs during prepartion.
>>    tools perf bpf: probe at kprobe points.
>>    tools perf bpf: load eBPF object into kernel.
>>    tools perf: add a bpf_wrapper global flag.
>>    tools perf: add bpf_fd field to evsel and introduce new event syntax.
>>    tools perf: generate event argv.
>>    tools perf bpf: passes generated arguments to cmd_record.
> The titles of the changes have numerous problems and inconsistencies:
>
>   - use consistent capitalization, i.e.:
>
>      tools perf: Collect all bpf programs
>
>   - don't use period at the end, i.e.:
>
>      tools perf: Generate event argv
>
>   - use consistent present tense verbs, i.e.:
>
>      -  tools lib bpf: defines basic interface.
>      +  tools lib bpf: Define basic interface
>
>   - Always use verbs! I.e. these are bad:
>
>      -   tools perf: config probe points of eBPF programs during prepartion.
>      -   tools lib bpf: relocation programs.
>
>   - take a look at 'git log tools/perf' to see what the established
>     title style is. For example it's not 'tools perf' but 'perf tools',
>     etc.
>
> etc.
>
> There's not a single title in this series that has a proper title.
> This makes the shortlog a difficult read and gives a bad first
> impression. Please fix.

Sorry for the inconvenience. I have fixed titles in my local tree as 
follow. You will see the fixed title
in next version.

Thank you.

   perf tools: Set vmlinux_path__nr_entries to 0 in vmlinux_path__exit
   tools lib traceevent: Install libtraceevent.a into libdir
   tools: Allow other override features to check
   tools: Add __aligned_u64 to types.h
   tools lib bpf: Introduce 'bpf' library to tools
   tools lib bpf: Allow set printing function
   tools lib bpf: Define basic interface
   tools lib bpf: Open eBPF object file and do basic validation
   tools lib bpf: Check swap according to EHDR
   tools lib bpf: Iterater over elf sections to collect information
   tools lib bpf: Collect version and license from ELF
   tools lib bpf: Collect map definitions
   tools lib bpf: Collect config section in object
   tools lib bpf: Collect symbol table in object files
   tools lib bpf: Collect bpf programs from object files
   tools lib bpf: Collect relocation sections from object file
   tools lib bpf: Collect relocation instructions for each program
   tools lib bpf: Clean elf memory after loading
   tools lib bpf: Add bpf.c/h for common bpf operations
   tools lib bpf: Create maps needed by object file
   tools lib bpf: Relocate programs
   tools lib bpf: Introduce bpf_load_program to bpf.c
   tools lib bpf: Load bpf programs in object file into kernel
   tools lib bpf: Introduce accessors of bpf_program
   tools lib bpf: Introduce accessors for struct bpf_object
   perf tools: Add new 'perf bpf' command
   perf tools: Make perf depend on libbpf
   perf bpf: Add 'perf bpf record' subcommand
   perf bpf: Add bpf-loader and open elf object files
   perf bpf: Collect all bpf programs
   perf bpf: Parse probe points of eBPF programs during prepartion
   perf bpf: Probe at kprobe points
   perf bpf: Load eBPF object into kernel
   perf tools: Add a bpf_wrapper global flag
   perf tools: Add bpf_fd field to evsel and introduce new event syntax
   perf bpf: Generate event argv for other commands
   perf bpf: Pass generated arguments to cmd_record

> Thanks,
>
>      Ingo

Re: [RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[Ingo Molnar]

* Wangnan (F) <wangnan0@huawei.com> wrote:

>   perf tools: Set vmlinux_path__nr_entries to 0 in vmlinux_path__exit
>   tools lib traceevent: Install libtraceevent.a into libdir
>   tools: Allow other override features to check

Hm, to check what? Not sure I can parse this sentence at a glance.

>   tools: Add __aligned_u64 to types.h
>   tools lib bpf: Introduce 'bpf' library to tools
>   tools lib bpf: Allow set printing function
>   tools lib bpf: Define basic interface

So you changed 'tools perf' to 'perf tools', but you should probably 
find a better name for 'tools lib bpf' as well, say:

    bpf tools: Define basic interface

?

>   tools lib bpf: Open eBPF object file and do basic validation
>   tools lib bpf: Check swap according to EHDR
>   tools lib bpf: Iterater over elf sections to collect information

s/Iterater
  Iterate

s/elf
  ELF

>   tools lib bpf: Collect version and license from ELF

'ELF' is not a noun really. From ELF binaries? From ELF sections?

>   tools lib bpf: Collect map definitions
>   tools lib bpf: Collect config section in object
>   tools lib bpf: Collect symbol table in object files
>   tools lib bpf: Collect bpf programs from object files
>   tools lib bpf: Collect relocation sections from object file
>   tools lib bpf: Collect relocation instructions for each program
>   tools lib bpf: Clean elf memory after loading
>   tools lib bpf: Add bpf.c/h for common bpf operations
>   tools lib bpf: Create maps needed by object file
>   tools lib bpf: Relocate programs
>   tools lib bpf: Introduce bpf_load_program to bpf.c

s/bpf_load_program
  bpf_load_program

>   tools lib bpf: Load bpf programs in object file into kernel
>   tools lib bpf: Introduce accessors of bpf_program
>   tools lib bpf: Introduce accessors for struct bpf_object

so 'of' bpf_program, but 'for' struct bpf_object?

>   perf tools: Add new 'perf bpf' command
>   perf tools: Make perf depend on libbpf
>   perf bpf: Add 'perf bpf record' subcommand
>   perf bpf: Add bpf-loader and open elf object files

s/elf
  ELF

>   perf bpf: Collect all bpf programs
>   perf bpf: Parse probe points of eBPF programs during prepartion

s/prepartion
  preparation

>   perf bpf: Probe at kprobe points
>   perf bpf: Load eBPF object into kernel
>   perf tools: Add a bpf_wrapper global flag
>   perf tools: Add bpf_fd field to evsel and introduce new event syntax
>   perf bpf: Generate event argv for other commands
>   perf bpf: Pass generated arguments to cmd_record

s/cmd_record
  cmd_record()

Thanks,

	Ingo

Re: [RFC PATCH v2 00/37] perf tools: introduce 'perf bpf' command to load eBPF programs.

[Wangnan (F)]

在 2015/5/15 16:48, Ingo Molnar 写道:
> * Wangnan (F) <wangnan0@huawei.com> wrote:
>
>>    perf tools: Set vmlinux_path__nr_entries to 0 in vmlinux_path__exit
>>    tools lib traceevent: Install libtraceevent.a into libdir
>>    tools: Allow other override features to check
> Hm, to check what? Not sure I can parse this sentence at a glance.

Changed to:

   tools: Change FEATURE_TESTS and FEATURE_DISPLAY to weak binding

>>    tools: Add __aligned_u64 to types.h
>>    tools lib bpf: Introduce 'bpf' library to tools
>>    tools lib bpf: Allow set printing function
>>    tools lib bpf: Define basic interface
> So you changed 'tools perf' to 'perf tools', but you should probably
> find a better name for 'tools lib bpf' as well, say:
>
>      bpf tools: Define basic interface
>
> ?

The style is copied from lib traceevent. I'll change it as your suggestion.

[..]

Thanks a lot. I changed titles again:

   tools lib traceevent: Install libtraceevent.a into libdir
   tools: Change FEATURE_TESTS and FEATURE_DISPLAY to weak binding
   tools: Add __aligned_u64 to types.h
   bpf tools: Introduce 'bpf' library to tools
   bpf tools: Allow caller to set printing function
   bpf tools: Define basic interface
   bpf tools: Open eBPF object file and do basic validation
   bpf tools: Check endianess and set swap flag according to EHDR
   bpf tools: Iterate over ELF sections to collect information
   bpf tools: Collect version and license from ELF sections
   bpf tools: Collect map definitions from 'maps' section
   bpf tools: Collect config string from 'config' section
   bpf tools: Collect symbol table from SHT_SYMTAB section
   bpf tools: Collect eBPF programs from their own sections
   bpf tools: Collect relocation sections from SHT_REL sections
   bpf tools: Record map accessing instructions for each program
   bpf tools: Clear libelf and ELF parsing resrouce to finish opening
   bpf tools: Add bpf.c/h for common bpf operations
   bpf tools: Create eBPF maps defined in an object file
   bpf tools: Relocate eBPF programs
   bpf tools: Introduce bpf_load_program() to bpf.c
   bpf tools: Load eBPF programs in object files into kernel
   bpf tools: Introduce accessors for struct bpf_program
   bpf tools: Introduce accessors for struct bpf_object
   perf tools: Add new 'perf bpf' command
   perf tools: Make perf depend on libbpf
   perf bpf: Add 'perf bpf record' subcommand
   perf bpf: Add bpf-loader and open ELF object files
   perf bpf: Collect all eBPF programs
   perf bpf: Parse probe points of eBPF programs during preparation
   perf bpf: Probe at kprobe points
   perf bpf: Load all eBPF object into kernel
   perf tools: Add a bpf_wrapper global flag
   perf tools: Add bpf_fd field to evsel and introduce new event syntax
   perf bpf: Generate event argv for other commands
   perf bpf: Pass generated arguments to cmd_record()

Do you have further suggestion?

Thank you.

[tip:perf/core] tools include: add __aligned_u64 to types.h.

[tip-bot for Wang Nan]

Commit-ID:  70ba6b8f975bcff56e180e2c7550d2302fcbf923
Gitweb:     http://git.kernel.org/tip/70ba6b8f975bcff56e180e2c7550d2302fcbf923
Author:     Wang Nan <wangnan0@huawei.com>
AuthorDate: Fri, 15 May 2015 07:50:57 +0000
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 18 May 2015 10:17:32 -0300

tools include: add __aligned_u64 to types.h.

Following patches will introduce linux/bpf.h to a new libbpf library,
which requires definition of __aligned_u64. This patch add it to the
common types.h for tools.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: pi3orama@163.com
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1431676290-1230-5-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/types.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index 0bdeda6..8ebf627 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -64,6 +64,10 @@ typedef struct {
 	int counter;
 } atomic_t;
 
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
 struct list_head {
 	struct list_head *next, *prev;
 };