Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
index b0a035f..58d44d5 100644
--- a/tools/lib/api/fd/array.c
+++ b/tools/lib/api/fd/array.c
@@ -1,7 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
*/
#include "array.h"
#include <errno.h>
diff --git a/tools/lib/argv_split.c b/tools/lib/argv_split.c
new file mode 100644
index 0000000..0a58ccf
--- /dev/null
+++ b/tools/lib/argv_split.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helper function for splitting a string into an argv-like array.
+ */
+
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
+
+static const char *skip_arg(const char *cp)
+{
+ while (*cp && !isspace(*cp))
+ cp++;
+
+ return cp;
+}
+
+static int count_argc(const char *str)
+{
+ int count = 0;
+
+ while (*str) {
+ str = skip_spaces(str);
+ if (*str) {
+ count++;
+ str = skip_arg(str);
+ }
+ }
+
+ return count;
+}
+
+/**
+ * argv_free - free an argv
+ * @argv - the argument vector to be freed
+ *
+ * Frees an argv and the strings it points to.
+ */
+void argv_free(char **argv)
+{
+ char **p;
+ for (p = argv; *p; p++) {
+ free(*p);
+ *p = NULL;
+ }
+
+ free(argv);
+}
+
+/**
+ * argv_split - split a string at whitespace, returning an argv
+ * @str: the string to be split
+ * @argcp: returned argument count
+ *
+ * Returns an array of pointers to strings which are split out from
+ * @str. This is performed by strictly splitting on white-space; no
+ * quote processing is performed. Multiple whitespace characters are
+ * considered to be a single argument separator. The returned array
+ * is always NULL-terminated. Returns NULL on memory allocation
+ * failure.
+ */
+char **argv_split(const char *str, int *argcp)
+{
+ int argc = count_argc(str);
+ char **argv = calloc(argc + 1, sizeof(*argv));
+ char **argvp;
+
+ if (argv == NULL)
+ goto out;
+
+ if (argcp)
+ *argcp = argc;
+
+ argvp = argv;
+
+ while (*str) {
+ str = skip_spaces(str);
+
+ if (*str) {
+ const char *p = str;
+ char *t;
+
+ str = skip_arg(str);
+
+ t = strndup(p, str-p);
+ if (t == NULL)
+ goto fail;
+ *argvp++ = t;
+ }
+ }
+ *argvp = NULL;
+
+out:
+ return argv;
+
+fail:
+ argv_free(argv);
+ return NULL;
+}
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 38748b0..3849478 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -1,9 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* From lib/bitmap.c
* Helper functions for bitmap.h.
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2. See the file COPYING for more details.
*/
#include <linux/bitmap.h>
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index f81e549..d9e9dec 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,2 +1,5 @@
libbpf_version.h
+libbpf.pc
FEATURE-DUMP.libbpf
+test_libbpf
+libbpf.so.*
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6eb9bac..e3962cf 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1,3 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
+ netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
+ btf_dump.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index d49902e..56ce629 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,34 +1,24 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
# Most of this file is copied from tools/lib/traceevent/Makefile
-BPF_VERSION = 0
-BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 1
+LIBBPF_VERSION := $(shell \
+ grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
+ sort -rV | head -n1 | cut -d'_' -f2)
+LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
MAKEFLAGS += --no-print-directory
-ifeq ($(srctree),)
+# This will work when bpf is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is a ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
srctree := $(patsubst %/,%,$(dir $(CURDIR)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
srctree := $(patsubst %/,%,$(dir $(srctree)))
#$(info Determined 'srctree' to be $(srctree))
endif
-# 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)
-
INSTALL = install
# Use DESTDIR for installing into a different root directory.
@@ -54,7 +44,7 @@
export man_dir man_dir_SQ INSTALL
export DESTDIR DESTDIR_SQ
-include ../../scripts/Makefile.include
+include $(srctree)/tools/scripts/Makefile.include
# copy a bit from Linux kbuild
@@ -66,10 +56,10 @@
endif
FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx
FEATURE_DISPLAY = libelf bpf
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
check_feat := 1
@@ -94,16 +84,12 @@
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-LIB_FILE = libbpf.a libbpf.so
-
-VERSION = $(BPF_VERSION)
-PATCHLEVEL = $(BPF_PATCHLEVEL)
-EXTRAVERSION = $(BPF_EXTRAVERSION)
-
OBJ = $@
N =
-LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE = libbpf.a libbpf.so*
+PC_FILE = libbpf.pc
# Set compile option CFLAGS
ifdef EXTRA_CFLAGS
@@ -125,6 +111,11 @@
override CFLAGS += -Werror -Wall
override CFLAGS += -fPIC
override CFLAGS += $(INCLUDES)
+override CFLAGS += -fvisibility=hidden
+override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+
+# flags specific for shared library
+SHLIB_FLAGS := -DSHARED
ifeq ($(VERBOSE),1)
Q =
@@ -142,18 +133,39 @@
export srctree OUTPUT CC LD CFLAGS V
include $(srctree)/tools/build/Makefile.include
-BPF_IN := $(OUTPUT)libbpf-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+SHARED_OBJDIR := $(OUTPUT)sharedobjs/
+STATIC_OBJDIR := $(OUTPUT)staticobjs/
+BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o
+BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o
+VERSION_SCRIPT := libbpf.map
-CMD_TARGETS = $(LIB_FILE)
+LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE))
+
+GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
+ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \
+ sort -u | wc -l)
+VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
+ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
+
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
+
+CXX_TEST_TARGET = $(OUTPUT)test_libbpf
+
+ifeq ($(feature-cxx), 1)
+ CMD_TARGETS += $(CXX_TEST_TARGET)
+endif
TARGETS = $(CMD_TARGETS)
-all: fixdep all_cmd
+all: fixdep
+ $(Q)$(MAKE) all_cmd
-all_cmd: $(CMD_TARGETS)
+all_cmd: $(CMD_TARGETS) check
-$(BPF_IN): force elfdep bpfdep
+$(BPF_IN_SHARED): force elfdep bpfdep
@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -166,14 +178,63 @@
@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
- $(Q)$(MAKE) $(build)=libbpf
+ @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
+ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
+ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
+ $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
-$(OUTPUT)libbpf.so: $(BPF_IN)
- $(QUIET_LINK)$(CC) --shared $^ -o $@
+$(BPF_IN_STATIC): force elfdep bpfdep
+ $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
-$(OUTPUT)libbpf.a: $(BPF_IN)
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED)
+ $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+ @ln -sf $(@F) $(OUTPUT)libbpf.so
+ @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
+
+$(OUTPUT)libbpf.a: $(BPF_IN_STATIC)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
+$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
+ $(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
+
+$(OUTPUT)libbpf.pc:
+ $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+ -e "s|@LIBDIR@|$(libdir_SQ)|" \
+ -e "s|@VERSION@|$(LIBBPF_VERSION)|" \
+ < libbpf.pc.template > $@
+
+check: check_abi
+
+check_abi: $(OUTPUT)libbpf.so
+ @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \
+ echo "Warning: Num of global symbols in $(BPF_IN_SHARED)" \
+ "($(GLOBAL_SYM_COUNT)) does NOT match with num of" \
+ "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
+ "Please make sure all LIBBPF_API symbols are" \
+ "versioned in $(VERSION_SCRIPT)." >&2; \
+ readelf -s --wide $(OUTPUT)libbpf-in.o | \
+ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \
+ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
+ readelf -s --wide $(OUTPUT)libbpf.so | \
+ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
+ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
+ diff -u $(OUTPUT)libbpf_global_syms.tmp \
+ $(OUTPUT)libbpf_versioned_syms.tmp; \
+ rm $(OUTPUT)libbpf_global_syms.tmp \
+ $(OUTPUT)libbpf_versioned_syms.tmp; \
+ exit 1; \
+ fi
+
+define do_install_mkdir
+ if [ ! -d '$(DESTDIR_SQ)$1' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+ fi
+endef
+
define do_install
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
@@ -182,16 +243,23 @@
endef
install_lib: all_cmd
- $(call QUIET_INSTALL, $(LIB_FILE)) \
- $(call do_install,$(LIB_FILE),$(libdir_SQ))
+ $(call QUIET_INSTALL, $(LIB_TARGET)) \
+ $(call do_install_mkdir,$(libdir_SQ)); \
+ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
install_headers:
$(call QUIET_INSTALL, headers) \
$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
- $(call do_install,libbpf.h,$(prefix)/include/bpf,644);
- $(call do_install,btf.h,$(prefix)/include/bpf,644);
+ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,btf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
+ $(call do_install,xsk.h,$(prefix)/include/bpf,644);
-install: install_lib
+install_pkgconfig: $(PC_FILE)
+ $(call QUIET_INSTALL, $(PC_FILE)) \
+ $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
+
+install: install_lib install_pkgconfig
### Cleaning rules
@@ -200,8 +268,9 @@
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
clean:
- $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so .*.d .*.cmd \
- $(RM) LIBBPF-CFLAGS
+ $(call QUIET_CLEAN, libbpf) $(RM) -rf $(TARGETS) $(CXX_TEST_TARGET) \
+ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
+ *.pc LIBBPF-CFLAGS $(SHARED_OBJDIR) $(STATIC_OBJDIR)
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
new file mode 100644
index 0000000..8928f77
--- /dev/null
+++ b/tools/lib/bpf/README.rst
@@ -0,0 +1,168 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+libbpf API naming convention
+============================
+
+libbpf API provides access to a few logically separated groups of
+functions and types. Every group has its own naming convention
+described here. It's recommended to follow these conventions whenever a
+new function or type is added to keep libbpf API clean and consistent.
+
+All types and functions provided by libbpf API should have one of the
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
+``perf_buffer_``.
+
+System call wrappers
+--------------------
+
+System call wrappers are simple wrappers for commands supported by
+sys_bpf system call. These wrappers should go to ``bpf.h`` header file
+and map one-on-one to corresponding commands.
+
+For example ``bpf_map_lookup_elem`` wraps ``BPF_MAP_LOOKUP_ELEM``
+command of sys_bpf, ``bpf_prog_attach`` wraps ``BPF_PROG_ATTACH``, etc.
+
+Objects
+-------
+
+Another class of types and functions provided by libbpf API is "objects"
+and functions to work with them. Objects are high-level abstractions
+such as BPF program or BPF map. They're represented by corresponding
+structures such as ``struct bpf_object``, ``struct bpf_program``,
+``struct bpf_map``, etc.
+
+Structures are forward declared and access to their fields should be
+provided via corresponding getters and setters rather than directly.
+
+These objects are associated with corresponding parts of ELF object that
+contains compiled BPF programs.
+
+For example ``struct bpf_object`` represents ELF object itself created
+from an ELF file or from a buffer, ``struct bpf_program`` represents a
+program in ELF object and ``struct bpf_map`` is a map.
+
+Functions that work with an object have names built from object name,
+double underscore and part that describes function purpose.
+
+For example ``bpf_object__open`` consists of the name of corresponding
+object, ``bpf_object``, double underscore and ``open`` that defines the
+purpose of the function to open ELF file and create ``bpf_object`` from
+it.
+
+Another example: ``bpf_program__load`` is named for corresponding
+object, ``bpf_program``, that is separated from other part of the name
+by double underscore.
+
+All objects and corresponding functions other than BTF related should go
+to ``libbpf.h``. BTF types and functions should go to ``btf.h``.
+
+Auxiliary functions
+-------------------
+
+Auxiliary functions and types that don't fit well in any of categories
+described above should have ``libbpf_`` prefix, e.g.
+``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
+
+AF_XDP functions
+-------------------
+
+AF_XDP functions should have an ``xsk_`` prefix, e.g.
+``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
+of both low-level ring access functions and high-level configuration
+functions. These can be mixed and matched. Note that these functions
+are not reentrant for performance reasons.
+
+Please take a look at Documentation/networking/af_xdp.rst in the Linux
+kernel source tree on how to use XDP sockets and for some common
+mistakes in case you do not get any traffic up to user space.
+
+libbpf ABI
+==========
+
+libbpf can be both linked statically or used as DSO. To avoid possible
+conflicts with other libraries an application is linked with, all
+non-static libbpf symbols should have one of the prefixes mentioned in
+API documentation above. See API naming convention to choose the right
+name for a new symbol.
+
+Symbol visibility
+-----------------
+
+libbpf follow the model when all global symbols have visibility "hidden"
+by default and to make a symbol visible it has to be explicitly
+attributed with ``LIBBPF_API`` macro. For example:
+
+.. code-block:: c
+
+ LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+
+This prevents from accidentally exporting a symbol, that is not supposed
+to be a part of ABI what, in turn, improves both libbpf developer- and
+user-experiences.
+
+ABI versionning
+---------------
+
+To make future ABI extensions possible libbpf ABI is versioned.
+Versioning is implemented by ``libbpf.map`` version script that is
+passed to linker.
+
+Version name is ``LIBBPF_`` prefix + three-component numeric version,
+starting from ``0.0.1``.
+
+Every time ABI is being changed, e.g. because a new symbol is added or
+semantic of existing symbol is changed, ABI version should be bumped.
+This bump in ABI version is at most once per kernel development cycle.
+
+For example, if current state of ``libbpf.map`` is:
+
+.. code-block::
+ LIBBPF_0.0.1 {
+ global:
+ bpf_func_a;
+ bpf_func_b;
+ local:
+ \*;
+ };
+
+, and a new symbol ``bpf_func_c`` is being introduced, then
+``libbpf.map`` should be changed like this:
+
+.. code-block::
+ LIBBPF_0.0.1 {
+ global:
+ bpf_func_a;
+ bpf_func_b;
+ local:
+ \*;
+ };
+ LIBBPF_0.0.2 {
+ global:
+ bpf_func_c;
+ } LIBBPF_0.0.1;
+
+, where new version ``LIBBPF_0.0.2`` depends on the previous
+``LIBBPF_0.0.1``.
+
+Format of version script and ways to handle ABI changes, including
+incompatible ones, described in details in [1].
+
+Stand-alone build
+=================
+
+Under https://github.com/libbpf/libbpf there is a (semi-)automated
+mirror of the mainline's version of libbpf for a stand-alone build.
+
+However, all changes to libbpf's code base must be upstreamed through
+the mainline kernel tree.
+
+License
+=======
+
+libbpf is dual-licensed under LGPL 2.1 and BSD 2-Clause.
+
+Links
+=====
+
+[1] https://www.akkadia.org/drepper/dsohowto.pdf
+ (Chapter 3. Maintaining APIs and ABIs).
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 60aa4ca..cbb9335 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/*
* common eBPF ELF operations.
@@ -22,21 +22,15 @@
*/
#include <stdlib.h>
+#include <string.h>
#include <memory.h>
#include <unistd.h>
#include <asm/unistd.h>
+#include <errno.h>
#include <linux/bpf.h>
#include "bpf.h"
#include "libbpf.h"
-#include "nlattr.h"
-#include <linux/rtnetlink.h>
-#include <linux/if_link.h>
-#include <sys/socket.h>
-#include <errno.h>
-
-#ifndef SOL_NETLINK
-#define SOL_NETLINK 270
-#endif
+#include "libbpf_internal.h"
/*
* When building perf, unistd.h is overridden. __NR_bpf is
@@ -53,15 +47,13 @@
# define __NR_bpf 349
# elif defined(__s390__)
# define __NR_bpf 351
+# elif defined(__arc__)
+# define __NR_bpf 280
# else
# error __NR_bpf not defined. libbpf does not support your arch.
# endif
#endif
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
-
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
@@ -73,9 +65,19 @@
return syscall(__NR_bpf, cmd, attr, size);
}
+static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
+{
+ int fd;
+
+ do {
+ fd = sys_bpf(BPF_PROG_LOAD, attr, size);
+ } while (fd < 0 && errno == EAGAIN);
+
+ return fd;
+}
+
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
{
- __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
@@ -85,8 +87,9 @@
attr.value_size = create_attr->value_size;
attr.max_entries = create_attr->max_entries;
attr.map_flags = create_attr->map_flags;
- memcpy(attr.map_name, create_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (create_attr->name)
+ memcpy(attr.map_name, create_attr->name,
+ min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1));
attr.numa_node = create_attr->numa_node;
attr.btf_fd = create_attr->btf_fd;
attr.btf_key_type_id = create_attr->btf_key_type_id;
@@ -151,7 +154,6 @@
int key_size, int inner_map_fd, int max_entries,
__u32 map_flags, int node)
{
- __u32 name_len = name ? strlen(name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
@@ -162,7 +164,9 @@
attr.inner_map_fd = inner_map_fd;
attr.max_entries = max_entries;
attr.map_flags = map_flags;
- memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (name)
+ memcpy(attr.map_name, name,
+ min(strlen(name), BPF_OBJ_NAME_LEN - 1));
if (node >= 0) {
attr.map_flags |= BPF_F_NUMA_NODE;
@@ -181,42 +185,132 @@
-1);
}
+static void *
+alloc_zero_tailing_info(const void *orecord, __u32 cnt,
+ __u32 actual_rec_size, __u32 expected_rec_size)
+{
+ __u64 info_len = actual_rec_size * cnt;
+ void *info, *nrecord;
+ int i;
+
+ info = malloc(info_len);
+ if (!info)
+ return NULL;
+
+ /* zero out bytes kernel does not understand */
+ nrecord = info;
+ for (i = 0; i < cnt; i++) {
+ memcpy(nrecord, orecord, expected_rec_size);
+ memset(nrecord + expected_rec_size, 0,
+ actual_rec_size - expected_rec_size);
+ orecord += actual_rec_size;
+ nrecord += actual_rec_size;
+ }
+
+ return info;
+}
+
int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
char *log_buf, size_t log_buf_sz)
{
+ void *finfo = NULL, *linfo = NULL;
union bpf_attr attr;
- __u32 name_len;
+ __u32 log_level;
int fd;
- if (!load_attr)
+ if (!load_attr || !log_buf != !log_buf_sz)
return -EINVAL;
- name_len = load_attr->name ? strlen(load_attr->name) : 0;
+ log_level = load_attr->log_level;
+ if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
+ return -EINVAL;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
attr.insn_cnt = (__u32)load_attr->insns_cnt;
attr.insns = ptr_to_u64(load_attr->insns);
attr.license = ptr_to_u64(load_attr->license);
- attr.log_buf = ptr_to_u64(NULL);
- attr.log_size = 0;
- attr.log_level = 0;
+
+ attr.log_level = log_level;
+ if (log_level) {
+ attr.log_buf = ptr_to_u64(log_buf);
+ attr.log_size = log_buf_sz;
+ } else {
+ attr.log_buf = ptr_to_u64(NULL);
+ attr.log_size = 0;
+ }
+
attr.kern_version = load_attr->kern_version;
attr.prog_ifindex = load_attr->prog_ifindex;
- memcpy(attr.prog_name, load_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ attr.prog_btf_fd = load_attr->prog_btf_fd;
+ attr.func_info_rec_size = load_attr->func_info_rec_size;
+ attr.func_info_cnt = load_attr->func_info_cnt;
+ attr.func_info = ptr_to_u64(load_attr->func_info);
+ attr.line_info_rec_size = load_attr->line_info_rec_size;
+ attr.line_info_cnt = load_attr->line_info_cnt;
+ attr.line_info = ptr_to_u64(load_attr->line_info);
+ if (load_attr->name)
+ memcpy(attr.prog_name, load_attr->name,
+ min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+ attr.prog_flags = load_attr->prog_flags;
- fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
- if (fd >= 0 || !log_buf || !log_buf_sz)
+ fd = sys_bpf_prog_load(&attr, sizeof(attr));
+ if (fd >= 0)
return fd;
+ /* After bpf_prog_load, the kernel may modify certain attributes
+ * to give user space a hint how to deal with loading failure.
+ * Check to see whether we can make some changes and load again.
+ */
+ while (errno == E2BIG && (!finfo || !linfo)) {
+ if (!finfo && attr.func_info_cnt &&
+ attr.func_info_rec_size < load_attr->func_info_rec_size) {
+ /* try with corrected func info records */
+ finfo = alloc_zero_tailing_info(load_attr->func_info,
+ load_attr->func_info_cnt,
+ load_attr->func_info_rec_size,
+ attr.func_info_rec_size);
+ if (!finfo)
+ goto done;
+
+ attr.func_info = ptr_to_u64(finfo);
+ attr.func_info_rec_size = load_attr->func_info_rec_size;
+ } else if (!linfo && attr.line_info_cnt &&
+ attr.line_info_rec_size <
+ load_attr->line_info_rec_size) {
+ linfo = alloc_zero_tailing_info(load_attr->line_info,
+ load_attr->line_info_cnt,
+ load_attr->line_info_rec_size,
+ attr.line_info_rec_size);
+ if (!linfo)
+ goto done;
+
+ attr.line_info = ptr_to_u64(linfo);
+ attr.line_info_rec_size = load_attr->line_info_rec_size;
+ } else {
+ break;
+ }
+
+ fd = sys_bpf_prog_load(&attr, sizeof(attr));
+
+ if (fd >= 0)
+ goto done;
+ }
+
+ if (log_level || !log_buf)
+ goto done;
+
/* 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));
+ fd = sys_bpf_prog_load(&attr, sizeof(attr));
+done:
+ free(finfo);
+ free(linfo);
+ return fd;
}
int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
@@ -239,13 +333,13 @@
}
int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
- size_t insns_cnt, int strict_alignment,
- const char *license, __u32 kern_version,
- char *log_buf, size_t log_buf_sz, int log_level)
+ size_t insns_cnt, __u32 prog_flags, const char *license,
+ __u32 kern_version, char *log_buf, size_t log_buf_sz,
+ int log_level)
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.prog_type = type;
attr.insn_cnt = (__u32)insns_cnt;
attr.insns = ptr_to_u64(insns);
@@ -255,9 +349,9 @@
attr.log_level = log_level;
log_buf[0] = 0;
attr.kern_version = kern_version;
- attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+ attr.prog_flags = prog_flags;
- return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+ return sys_bpf_prog_load(&attr, sizeof(attr));
}
int bpf_map_update_elem(int fd, const void *key, const void *value,
@@ -265,7 +359,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.value = ptr_to_u64(value);
@@ -278,7 +372,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.value = ptr_to_u64(value);
@@ -286,11 +380,36 @@
return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
}
+int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
+{
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.value = ptr_to_u64(value);
+ attr.flags = flags;
+
+ return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
+{
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.value = ptr_to_u64(value);
+
+ return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
int bpf_map_delete_elem(int fd, const void *key)
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
@@ -301,7 +420,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.map_fd = fd;
attr.key = ptr_to_u64(key);
attr.next_key = ptr_to_u64(next_key);
@@ -309,11 +428,21 @@
return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}
+int bpf_map_freeze(int fd)
+{
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+
+ return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.pathname = ptr_to_u64((void *)pathname);
attr.bpf_fd = fd;
@@ -324,7 +453,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.pathname = ptr_to_u64((void *)pathname);
return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
@@ -335,7 +464,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.target_fd = target_fd;
attr.attach_bpf_fd = prog_fd;
attr.attach_type = type;
@@ -348,7 +477,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.target_fd = target_fd;
attr.attach_type = type;
@@ -359,7 +488,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.target_fd = target_fd;
attr.attach_bpf_fd = prog_fd;
attr.attach_type = type;
@@ -373,7 +502,7 @@
union bpf_attr attr;
int ret;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.query.target_fd = target_fd;
attr.query.attach_type = type;
attr.query.query_flags = query_flags;
@@ -394,7 +523,7 @@
union bpf_attr attr;
int ret;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.test.prog_fd = prog_fd;
attr.test.data_in = ptr_to_u64(data);
attr.test.data_out = ptr_to_u64(data_out);
@@ -411,41 +540,69 @@
return ret;
}
-int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
+int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
+{
+ union bpf_attr attr;
+ int ret;
+
+ if (!test_attr->data_out && test_attr->data_size_out > 0)
+ return -EINVAL;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.test.prog_fd = test_attr->prog_fd;
+ attr.test.data_in = ptr_to_u64(test_attr->data_in);
+ attr.test.data_out = ptr_to_u64(test_attr->data_out);
+ attr.test.data_size_in = test_attr->data_size_in;
+ attr.test.data_size_out = test_attr->data_size_out;
+ attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in);
+ attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out);
+ attr.test.ctx_size_in = test_attr->ctx_size_in;
+ attr.test.ctx_size_out = test_attr->ctx_size_out;
+ attr.test.repeat = test_attr->repeat;
+
+ ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+ test_attr->data_size_out = attr.test.data_size_out;
+ test_attr->ctx_size_out = attr.test.ctx_size_out;
+ test_attr->retval = attr.test.retval;
+ test_attr->duration = attr.test.duration;
+ return ret;
+}
+
+static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
{
union bpf_attr attr;
int err;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.start_id = start_id;
- err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
+ err = sys_bpf(cmd, &attr, sizeof(attr));
if (!err)
*next_id = attr.next_id;
return err;
}
+int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID);
+}
+
int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
{
- union bpf_attr attr;
- int err;
+ return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID);
+}
- bzero(&attr, sizeof(attr));
- attr.start_id = start_id;
-
- err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
- if (!err)
- *next_id = attr.next_id;
-
- return err;
+int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID);
}
int bpf_prog_get_fd_by_id(__u32 id)
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.prog_id = id;
return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -455,7 +612,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.map_id = id;
return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -465,7 +622,7 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.btf_id = id;
return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -476,7 +633,7 @@
union bpf_attr attr;
int err;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.info.bpf_fd = prog_fd;
attr.info.info_len = *info_len;
attr.info.info = ptr_to_u64(info);
@@ -492,134 +649,13 @@
{
union bpf_attr attr;
- bzero(&attr, sizeof(attr));
+ memset(&attr, 0, sizeof(attr));
attr.raw_tracepoint.name = ptr_to_u64(name);
attr.raw_tracepoint.prog_fd = prog_fd;
return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
}
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
- struct sockaddr_nl sa;
- int sock, seq = 0, len, ret = -1;
- char buf[4096];
- struct nlattr *nla, *nla_xdp;
- struct {
- struct nlmsghdr nh;
- struct ifinfomsg ifinfo;
- char attrbuf[64];
- } req;
- struct nlmsghdr *nh;
- struct nlmsgerr *err;
- socklen_t addrlen;
- int one = 1;
-
- memset(&sa, 0, sizeof(sa));
- sa.nl_family = AF_NETLINK;
-
- sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
- if (sock < 0) {
- return -errno;
- }
-
- if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
- &one, sizeof(one)) < 0) {
- fprintf(stderr, "Netlink error reporting not supported\n");
- }
-
- if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- addrlen = sizeof(sa);
- if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- if (addrlen != sizeof(sa)) {
- ret = -LIBBPF_ERRNO__INTERNAL;
- goto cleanup;
- }
-
- memset(&req, 0, sizeof(req));
- req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
- req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
- req.nh.nlmsg_type = RTM_SETLINK;
- req.nh.nlmsg_pid = 0;
- req.nh.nlmsg_seq = ++seq;
- req.ifinfo.ifi_family = AF_UNSPEC;
- req.ifinfo.ifi_index = ifindex;
-
- /* started nested attribute for XDP */
- nla = (struct nlattr *)(((char *)&req)
- + NLMSG_ALIGN(req.nh.nlmsg_len));
- nla->nla_type = NLA_F_NESTED | IFLA_XDP;
- nla->nla_len = NLA_HDRLEN;
-
- /* add XDP fd */
- nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
- nla_xdp->nla_type = IFLA_XDP_FD;
- nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
- memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
- nla->nla_len += nla_xdp->nla_len;
-
- /* if user passed in any flags, add those too */
- if (flags) {
- nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
- nla_xdp->nla_type = IFLA_XDP_FLAGS;
- nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
- memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
- nla->nla_len += nla_xdp->nla_len;
- }
-
- req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
- if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- len = recv(sock, buf, sizeof(buf), 0);
- if (len < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
- nh = NLMSG_NEXT(nh, len)) {
- if (nh->nlmsg_pid != sa.nl_pid) {
- ret = -LIBBPF_ERRNO__WRNGPID;
- goto cleanup;
- }
- if (nh->nlmsg_seq != seq) {
- ret = -LIBBPF_ERRNO__INVSEQ;
- goto cleanup;
- }
- switch (nh->nlmsg_type) {
- case NLMSG_ERROR:
- err = (struct nlmsgerr *)NLMSG_DATA(nh);
- if (!err->error)
- continue;
- ret = err->error;
- nla_dump_errormsg(nh);
- goto cleanup;
- case NLMSG_DONE:
- break;
- default:
- break;
- }
- }
-
- ret = 0;
-
-cleanup:
- close(sock);
- return ret;
-}
-
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
bool do_log)
{
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 6f38164..0db0133 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
/*
* common eBPF ELF operations.
@@ -20,12 +20,21 @@
* You should have received a copy of the GNU Lesser General Public
* License along with this program; if not, see <http://www.gnu.org/licenses>
*/
-#ifndef __BPF_BPF_H
-#define __BPF_BPF_H
+#ifndef __LIBBPF_BPF_H
+#define __LIBBPF_BPF_H
#include <linux/bpf.h>
#include <stdbool.h>
#include <stddef.h>
+#include <stdint.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
struct bpf_create_map_attr {
const char *name;
@@ -42,21 +51,24 @@
__u32 inner_map_fd;
};
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size, int max_entries,
- __u32 map_flags, int node);
-int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size, int max_entries,
- __u32 map_flags);
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
- int max_entries, __u32 map_flags);
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int inner_map_fd, int max_entries,
- __u32 map_flags, int node);
-int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
- int key_size, int inner_map_fd, int max_entries,
- __u32 map_flags);
+LIBBPF_API int
+bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+ int key_size, int value_size,
+ int max_entries, __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+ int key_size, int value_size,
+ int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
+ int value_size, int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
+ const char *name, int key_size,
+ int inner_map_fd, int max_entries,
+ __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
+ const char *name, int key_size,
+ int inner_map_fd, int max_entries,
+ __u32 map_flags);
struct bpf_load_program_attr {
enum bpf_prog_type prog_type;
@@ -67,48 +79,100 @@
const char *license;
__u32 kern_version;
__u32 prog_ifindex;
+ __u32 prog_btf_fd;
+ __u32 func_info_rec_size;
+ const void *func_info;
+ __u32 func_info_cnt;
+ __u32 line_info_rec_size;
+ const void *line_info;
+ __u32 line_info_cnt;
+ __u32 log_level;
+ __u32 prog_flags;
};
+/* Flags to direct loading requirements */
+#define MAPS_RELAX_COMPAT 0x01
+
/* Recommend log buffer size */
-#define BPF_LOG_BUF_SIZE (256 * 1024)
-int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
- char *log_buf, size_t log_buf_sz);
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
- size_t insns_cnt, const char *license,
- __u32 kern_version, char *log_buf,
- size_t log_buf_sz);
-int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
- size_t insns_cnt, int strict_alignment,
- const char *license, __u32 kern_version,
- char *log_buf, size_t log_buf_sz, int log_level);
+#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
+LIBBPF_API int
+bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+ char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
+ const struct bpf_insn *insns, size_t insns_cnt,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
+ const struct bpf_insn *insns,
+ size_t insns_cnt, __u32 prog_flags,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz,
+ int log_level);
-int bpf_map_update_elem(int fd, const void *key, const void *value,
- __u64 flags);
+LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
+ __u64 flags);
-int bpf_map_lookup_elem(int fd, const void *key, void *value);
-int bpf_map_delete_elem(int fd, const void *key);
-int bpf_map_get_next_key(int fd, const void *key, void *next_key);
-int bpf_obj_pin(int fd, const char *pathname);
-int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
- unsigned int flags);
-int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
- void *data_out, __u32 *size_out, __u32 *retval,
- __u32 *duration);
-int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_prog_get_fd_by_id(__u32 id);
-int bpf_map_get_fd_by_id(__u32 id);
-int bpf_btf_get_fd_by_id(__u32 id);
-int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
- __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
-int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
- bool do_log);
-int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
- __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
- __u64 *probe_addr);
+LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
+ __u64 flags);
+LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
+ void *value);
+LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
+LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_map_freeze(int fd);
+LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
+LIBBPF_API int bpf_obj_get(const char *pathname);
+LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
+ enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
+ enum bpf_attach_type type);
+
+struct bpf_prog_test_run_attr {
+ int prog_fd;
+ int repeat;
+ const void *data_in;
+ __u32 data_size_in;
+ void *data_out; /* optional */
+ __u32 data_size_out; /* in: max length of data_out
+ * out: length of data_out */
+ __u32 retval; /* out: return code of the BPF program */
+ __u32 duration; /* out: average per repetition in ns */
+ const void *ctx_in; /* optional */
+ __u32 ctx_size_in;
+ void *ctx_out; /* optional */
+ __u32 ctx_size_out; /* in: max length of ctx_out
+ * out: length of cxt_out */
+};
+
+LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
+
+/*
+ * bpf_prog_test_run does not check that data_out is large enough. Consider
+ * using bpf_prog_test_run_xattr instead.
+ */
+LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
+ __u32 size, void *data_out, __u32 *size_out,
+ __u32 *retval, __u32 *duration);
+LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
+ __u32 query_flags, __u32 *attach_flags,
+ __u32 *prog_ids, __u32 *prog_cnt);
+LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
+LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
+ __u32 log_buf_size, bool do_log);
+LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
+ __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
+ __u64 *probe_offset, __u64 *probe_addr);
+
+#ifdef __cplusplus
+} /* extern "C" */
#endif
+
+#endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
new file mode 100644
index 0000000..8c67561
--- /dev/null
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2018 Facebook */
+
+#include <string.h>
+#include <stdlib.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+struct bpf_prog_linfo {
+ void *raw_linfo;
+ void *raw_jited_linfo;
+ __u32 *nr_jited_linfo_per_func;
+ __u32 *jited_linfo_func_idx;
+ __u32 nr_linfo;
+ __u32 nr_jited_func;
+ __u32 rec_size;
+ __u32 jited_rec_size;
+};
+
+static int dissect_jited_func(struct bpf_prog_linfo *prog_linfo,
+ const __u64 *ksym_func, const __u32 *ksym_len)
+{
+ __u32 nr_jited_func, nr_linfo;
+ const void *raw_jited_linfo;
+ const __u64 *jited_linfo;
+ __u64 last_jited_linfo;
+ /*
+ * Index to raw_jited_linfo:
+ * i: Index for searching the next ksym_func
+ * prev_i: Index to the last found ksym_func
+ */
+ __u32 i, prev_i;
+ __u32 f; /* Index to ksym_func */
+
+ raw_jited_linfo = prog_linfo->raw_jited_linfo;
+ jited_linfo = raw_jited_linfo;
+ if (ksym_func[0] != *jited_linfo)
+ goto errout;
+
+ prog_linfo->jited_linfo_func_idx[0] = 0;
+ nr_jited_func = prog_linfo->nr_jited_func;
+ nr_linfo = prog_linfo->nr_linfo;
+
+ for (prev_i = 0, i = 1, f = 1;
+ i < nr_linfo && f < nr_jited_func;
+ i++) {
+ raw_jited_linfo += prog_linfo->jited_rec_size;
+ last_jited_linfo = *jited_linfo;
+ jited_linfo = raw_jited_linfo;
+
+ if (ksym_func[f] == *jited_linfo) {
+ prog_linfo->jited_linfo_func_idx[f] = i;
+
+ /* Sanity check */
+ if (last_jited_linfo - ksym_func[f - 1] + 1 >
+ ksym_len[f - 1])
+ goto errout;
+
+ prog_linfo->nr_jited_linfo_per_func[f - 1] =
+ i - prev_i;
+ prev_i = i;
+
+ /*
+ * The ksym_func[f] is found in jited_linfo.
+ * Look for the next one.
+ */
+ f++;
+ } else if (*jited_linfo <= last_jited_linfo) {
+ /* Ensure the addr is increasing _within_ a func */
+ goto errout;
+ }
+ }
+
+ if (f != nr_jited_func)
+ goto errout;
+
+ prog_linfo->nr_jited_linfo_per_func[nr_jited_func - 1] =
+ nr_linfo - prev_i;
+
+ return 0;
+
+errout:
+ return -EINVAL;
+}
+
+void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo)
+{
+ if (!prog_linfo)
+ return;
+
+ free(prog_linfo->raw_linfo);
+ free(prog_linfo->raw_jited_linfo);
+ free(prog_linfo->nr_jited_linfo_per_func);
+ free(prog_linfo->jited_linfo_func_idx);
+ free(prog_linfo);
+}
+
+struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
+{
+ struct bpf_prog_linfo *prog_linfo;
+ __u32 nr_linfo, nr_jited_func;
+
+ nr_linfo = info->nr_line_info;
+
+ if (!nr_linfo)
+ return NULL;
+
+ /*
+ * The min size that bpf_prog_linfo has to access for
+ * searching purpose.
+ */
+ if (info->line_info_rec_size <
+ offsetof(struct bpf_line_info, file_name_off))
+ return NULL;
+
+ prog_linfo = calloc(1, sizeof(*prog_linfo));
+ if (!prog_linfo)
+ return NULL;
+
+ /* Copy xlated line_info */
+ prog_linfo->nr_linfo = nr_linfo;
+ prog_linfo->rec_size = info->line_info_rec_size;
+ prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+ if (!prog_linfo->raw_linfo)
+ goto err_free;
+ memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
+ nr_linfo * prog_linfo->rec_size);
+
+ nr_jited_func = info->nr_jited_ksyms;
+ if (!nr_jited_func ||
+ !info->jited_line_info ||
+ info->nr_jited_line_info != nr_linfo ||
+ info->jited_line_info_rec_size < sizeof(__u64) ||
+ info->nr_jited_func_lens != nr_jited_func ||
+ !info->jited_ksyms ||
+ !info->jited_func_lens)
+ /* Not enough info to provide jited_line_info */
+ return prog_linfo;
+
+ /* Copy jited_line_info */
+ prog_linfo->nr_jited_func = nr_jited_func;
+ prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
+ prog_linfo->raw_jited_linfo = malloc(nr_linfo *
+ prog_linfo->jited_rec_size);
+ if (!prog_linfo->raw_jited_linfo)
+ goto err_free;
+ memcpy(prog_linfo->raw_jited_linfo,
+ (void *)(long)info->jited_line_info,
+ nr_linfo * prog_linfo->jited_rec_size);
+
+ /* Number of jited_line_info per jited func */
+ prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
+ sizeof(__u32));
+ if (!prog_linfo->nr_jited_linfo_per_func)
+ goto err_free;
+
+ /*
+ * For each jited func,
+ * the start idx to the "linfo" and "jited_linfo" array,
+ */
+ prog_linfo->jited_linfo_func_idx = malloc(nr_jited_func *
+ sizeof(__u32));
+ if (!prog_linfo->jited_linfo_func_idx)
+ goto err_free;
+
+ if (dissect_jited_func(prog_linfo,
+ (__u64 *)(long)info->jited_ksyms,
+ (__u32 *)(long)info->jited_func_lens))
+ goto err_free;
+
+ return prog_linfo;
+
+err_free:
+ bpf_prog_linfo__free(prog_linfo);
+ return NULL;
+}
+
+const struct bpf_line_info *
+bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
+ __u64 addr, __u32 func_idx, __u32 nr_skip)
+{
+ __u32 jited_rec_size, rec_size, nr_linfo, start, i;
+ const void *raw_jited_linfo, *raw_linfo;
+ const __u64 *jited_linfo;
+
+ if (func_idx >= prog_linfo->nr_jited_func)
+ return NULL;
+
+ nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx];
+ if (nr_skip >= nr_linfo)
+ return NULL;
+
+ start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip;
+ jited_rec_size = prog_linfo->jited_rec_size;
+ raw_jited_linfo = prog_linfo->raw_jited_linfo +
+ (start * jited_rec_size);
+ jited_linfo = raw_jited_linfo;
+ if (addr < *jited_linfo)
+ return NULL;
+
+ nr_linfo -= nr_skip;
+ rec_size = prog_linfo->rec_size;
+ raw_linfo = prog_linfo->raw_linfo + (start * rec_size);
+ for (i = 0; i < nr_linfo; i++) {
+ if (addr < *jited_linfo)
+ break;
+
+ raw_linfo += rec_size;
+ raw_jited_linfo += jited_rec_size;
+ jited_linfo = raw_jited_linfo;
+ }
+
+ return raw_linfo - rec_size;
+}
+
+const struct bpf_line_info *
+bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
+ __u32 insn_off, __u32 nr_skip)
+{
+ const struct bpf_line_info *linfo;
+ __u32 rec_size, nr_linfo, i;
+ const void *raw_linfo;
+
+ nr_linfo = prog_linfo->nr_linfo;
+ if (nr_skip >= nr_linfo)
+ return NULL;
+
+ rec_size = prog_linfo->rec_size;
+ raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size);
+ linfo = raw_linfo;
+ if (insn_off < linfo->insn_off)
+ return NULL;
+
+ nr_linfo -= nr_skip;
+ for (i = 0; i < nr_linfo; i++) {
+ if (insn_off < linfo->insn_off)
+ break;
+
+ raw_linfo += rec_size;
+ linfo = raw_linfo;
+ }
+
+ return raw_linfo - rec_size;
+}
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index cf94b07..1aa189a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,25 +1,24 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2018 Facebook */
+#include <endian.h>
+#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
#include <linux/err.h>
#include <linux/btf.h>
+#include <gelf.h>
#include "btf.h"
#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "hashmap.h"
-#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); }
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min(a, b) ((a) < (b) ? (a) : (b))
-
-#define BTF_MAX_NR_TYPES 65535
-
-#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
- ((k) == BTF_KIND_VOLATILE) || \
- ((k) == BTF_KIND_CONST) || \
- ((k) == BTF_KIND_RESTRICT))
+#define BTF_MAX_NR_TYPES 0x7fffffff
+#define BTF_MAX_STR_OFFSET 0x7fffffff
static struct btf_type btf_void;
@@ -37,6 +36,11 @@
int fd;
};
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
static int btf_add_type(struct btf *btf, struct btf_type *t)
{
if (btf->types_size - btf->nr_types < 2) {
@@ -65,54 +69,54 @@
return 0;
}
-static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
+static int btf_parse_hdr(struct btf *btf)
{
const struct btf_header *hdr = btf->hdr;
__u32 meta_left;
if (btf->data_size < sizeof(struct btf_header)) {
- elog("BTF header not found\n");
+ pr_debug("BTF header not found\n");
return -EINVAL;
}
if (hdr->magic != BTF_MAGIC) {
- elog("Invalid BTF magic:%x\n", hdr->magic);
+ pr_debug("Invalid BTF magic:%x\n", hdr->magic);
return -EINVAL;
}
if (hdr->version != BTF_VERSION) {
- elog("Unsupported BTF version:%u\n", hdr->version);
+ pr_debug("Unsupported BTF version:%u\n", hdr->version);
return -ENOTSUP;
}
if (hdr->flags) {
- elog("Unsupported BTF flags:%x\n", hdr->flags);
+ pr_debug("Unsupported BTF flags:%x\n", hdr->flags);
return -ENOTSUP;
}
meta_left = btf->data_size - sizeof(*hdr);
if (!meta_left) {
- elog("BTF has no data\n");
+ pr_debug("BTF has no data\n");
return -EINVAL;
}
if (meta_left < hdr->type_off) {
- elog("Invalid BTF type section offset:%u\n", hdr->type_off);
+ pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off);
return -EINVAL;
}
if (meta_left < hdr->str_off) {
- elog("Invalid BTF string section offset:%u\n", hdr->str_off);
+ pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
return -EINVAL;
}
if (hdr->type_off >= hdr->str_off) {
- elog("BTF type section offset >= string section offset. No type?\n");
+ pr_debug("BTF type section offset >= string section offset. No type?\n");
return -EINVAL;
}
if (hdr->type_off & 0x02) {
- elog("BTF type section is not aligned to 4 bytes\n");
+ pr_debug("BTF type section is not aligned to 4 bytes\n");
return -EINVAL;
}
@@ -121,15 +125,15 @@
return 0;
}
-static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
+static int btf_parse_str_sec(struct btf *btf)
{
const struct btf_header *hdr = btf->hdr;
const char *start = btf->nohdr_data + hdr->str_off;
const char *end = start + btf->hdr->str_len;
- if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
start[0] || end[-1]) {
- elog("Invalid BTF string section\n");
+ pr_debug("Invalid BTF string section\n");
return -EINVAL;
}
@@ -138,7 +142,42 @@
return 0;
}
-static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
+static int btf_type_size(struct btf_type *t)
+{
+ int base_size = sizeof(struct btf_type);
+ __u16 vlen = btf_vlen(t);
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_FWD:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ return base_size;
+ case BTF_KIND_INT:
+ return base_size + sizeof(__u32);
+ case BTF_KIND_ENUM:
+ return base_size + vlen * sizeof(struct btf_enum);
+ case BTF_KIND_ARRAY:
+ return base_size + sizeof(struct btf_array);
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ return base_size + vlen * sizeof(struct btf_member);
+ case BTF_KIND_FUNC_PROTO:
+ return base_size + vlen * sizeof(struct btf_param);
+ case BTF_KIND_VAR:
+ return base_size + sizeof(struct btf_var);
+ case BTF_KIND_DATASEC:
+ return base_size + vlen * sizeof(struct btf_var_secinfo);
+ default:
+ pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
+ return -EINVAL;
+ }
+}
+
+static int btf_parse_type_sec(struct btf *btf)
{
struct btf_header *hdr = btf->hdr;
void *nohdr_data = btf->nohdr_data;
@@ -147,37 +186,13 @@
while (next_type < end_type) {
struct btf_type *t = next_type;
- __u16 vlen = BTF_INFO_VLEN(t->info);
+ int type_size;
int err;
- next_type += sizeof(*t);
- switch (BTF_INFO_KIND(t->info)) {
- case BTF_KIND_INT:
- next_type += sizeof(int);
- break;
- case BTF_KIND_ARRAY:
- next_type += sizeof(struct btf_array);
- break;
- case BTF_KIND_STRUCT:
- case BTF_KIND_UNION:
- next_type += vlen * sizeof(struct btf_member);
- break;
- case BTF_KIND_ENUM:
- next_type += vlen * sizeof(struct btf_enum);
- break;
- case BTF_KIND_TYPEDEF:
- case BTF_KIND_PTR:
- case BTF_KIND_FWD:
- case BTF_KIND_VOLATILE:
- case BTF_KIND_CONST:
- case BTF_KIND_RESTRICT:
- break;
- default:
- elog("Unsupported BTF_KIND:%u\n",
- BTF_INFO_KIND(t->info));
- return -EINVAL;
- }
-
+ type_size = btf_type_size(t);
+ if (type_size < 0)
+ return type_size;
+ next_type += type_size;
err = btf_add_type(btf, t);
if (err)
return err;
@@ -186,6 +201,11 @@
return 0;
}
+__u32 btf__get_nr_types(const struct btf *btf)
+{
+ return btf->nr_types;
+}
+
const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
{
if (type_id > btf->nr_types)
@@ -196,7 +216,7 @@
static bool btf_type_is_void(const struct btf_type *t)
{
- return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+ return t == &btf_void || btf_is_fwd(t);
}
static bool btf_type_is_void_or_null(const struct btf_type *t)
@@ -204,21 +224,6 @@
return !t || btf_type_is_void(t);
}
-static __s64 btf_type_size(const struct btf_type *t)
-{
- switch (BTF_INFO_KIND(t->info)) {
- case BTF_KIND_INT:
- case BTF_KIND_STRUCT:
- case BTF_KIND_UNION:
- case BTF_KIND_ENUM:
- return t->size;
- case BTF_KIND_PTR:
- return sizeof(void *);
- default:
- return -EINVAL;
- }
-}
-
#define MAX_RESOLVE_DEPTH 32
__s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
@@ -232,19 +237,26 @@
t = btf__type_by_id(btf, type_id);
for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
i++) {
- size = btf_type_size(t);
- if (size >= 0)
- break;
-
- switch (BTF_INFO_KIND(t->info)) {
+ switch (btf_kind(t)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_ENUM:
+ case BTF_KIND_DATASEC:
+ size = t->size;
+ goto done;
+ case BTF_KIND_PTR:
+ size = sizeof(void *);
+ goto done;
case BTF_KIND_TYPEDEF:
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
+ case BTF_KIND_VAR:
type_id = t->type;
break;
case BTF_KIND_ARRAY:
- array = (const struct btf_array *)(t + 1);
+ array = btf_array(t);
if (nelems && array->nelems > UINT32_MAX / nelems)
return -E2BIG;
nelems *= array->nelems;
@@ -260,6 +272,7 @@
if (size < 0)
return -EINVAL;
+done:
if (nelems && size > UINT32_MAX / nelems)
return -E2BIG;
@@ -274,7 +287,7 @@
t = btf__type_by_id(btf, type_id);
while (depth < MAX_RESOLVE_DEPTH &&
!btf_type_is_void_or_null(t) &&
- IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+ (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) {
type_id = t->type;
t = btf__type_by_id(btf, type_id);
depth++;
@@ -317,10 +330,8 @@
free(btf);
}
-struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+struct btf *btf__new(__u8 *data, __u32 size)
{
- __u32 log_buf_size = 0;
- char *log_buf = NULL;
struct btf *btf;
int err;
@@ -330,16 +341,6 @@
btf->fd = -1;
- if (err_log) {
- log_buf = malloc(BPF_LOG_BUF_SIZE);
- if (!log_buf) {
- err = -ENOMEM;
- goto done;
- }
- *log_buf = 0;
- log_buf_size = BPF_LOG_BUF_SIZE;
- }
-
btf->data = malloc(size);
if (!btf->data) {
err = -ENOMEM;
@@ -349,30 +350,17 @@
memcpy(btf->data, data, size);
btf->data_size = size;
- btf->fd = bpf_load_btf(btf->data, btf->data_size,
- log_buf, log_buf_size, false);
-
- if (btf->fd == -1) {
- err = -errno;
- elog("Error loading BTF: %s(%d)\n", strerror(errno), errno);
- if (log_buf && *log_buf)
- elog("%s\n", log_buf);
- goto done;
- }
-
- err = btf_parse_hdr(btf, err_log);
+ err = btf_parse_hdr(btf);
if (err)
goto done;
- err = btf_parse_str_sec(btf, err_log);
+ err = btf_parse_str_sec(btf);
if (err)
goto done;
- err = btf_parse_type_sec(btf, err_log);
+ err = btf_parse_type_sec(btf);
done:
- free(log_buf);
-
if (err) {
btf__free(btf);
return ERR_PTR(err);
@@ -381,11 +369,259 @@
return btf;
}
+static bool btf_check_endianness(const GElf_Ehdr *ehdr)
+{
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+ Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
+ int err = 0, fd = -1, idx = 0;
+ struct btf *btf = NULL;
+ Elf_Scn *scn = NULL;
+ Elf *elf = NULL;
+ GElf_Ehdr ehdr;
+
+ if (elf_version(EV_CURRENT) == EV_NONE) {
+ pr_warning("failed to init libelf for %s\n", path);
+ return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
+ }
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ err = -errno;
+ pr_warning("failed to open %s: %s\n", path, strerror(errno));
+ return ERR_PTR(err);
+ }
+
+ err = -LIBBPF_ERRNO__FORMAT;
+
+ elf = elf_begin(fd, ELF_C_READ, NULL);
+ if (!elf) {
+ pr_warning("failed to open %s as ELF file\n", path);
+ goto done;
+ }
+ if (!gelf_getehdr(elf, &ehdr)) {
+ pr_warning("failed to get EHDR from %s\n", path);
+ goto done;
+ }
+ if (!btf_check_endianness(&ehdr)) {
+ pr_warning("non-native ELF endianness is not supported\n");
+ goto done;
+ }
+ if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+ pr_warning("failed to get e_shstrndx from %s\n", path);
+ goto done;
+ }
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ GElf_Shdr sh;
+ char *name;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, path);
+ goto done;
+ }
+ name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+ if (!name) {
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, path);
+ goto done;
+ }
+ if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = elf_getdata(scn, 0);
+ if (!btf_data) {
+ pr_warning("failed to get section(%d, %s) data from %s\n",
+ idx, name, path);
+ goto done;
+ }
+ continue;
+ } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+ btf_ext_data = elf_getdata(scn, 0);
+ if (!btf_ext_data) {
+ pr_warning("failed to get section(%d, %s) data from %s\n",
+ idx, name, path);
+ goto done;
+ }
+ continue;
+ }
+ }
+
+ err = 0;
+
+ if (!btf_data) {
+ err = -ENOENT;
+ goto done;
+ }
+ btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(btf))
+ goto done;
+
+ if (btf_ext && btf_ext_data) {
+ *btf_ext = btf_ext__new(btf_ext_data->d_buf,
+ btf_ext_data->d_size);
+ if (IS_ERR(*btf_ext))
+ goto done;
+ } else if (btf_ext) {
+ *btf_ext = NULL;
+ }
+done:
+ if (elf)
+ elf_end(elf);
+ close(fd);
+
+ if (err)
+ return ERR_PTR(err);
+ /*
+ * btf is always parsed before btf_ext, so no need to clean up
+ * btf_ext, if btf loading failed
+ */
+ if (IS_ERR(btf))
+ return btf;
+ if (btf_ext && IS_ERR(*btf_ext)) {
+ btf__free(btf);
+ err = PTR_ERR(*btf_ext);
+ return ERR_PTR(err);
+ }
+ return btf;
+}
+
+static int compare_vsi_off(const void *_a, const void *_b)
+{
+ const struct btf_var_secinfo *a = _a;
+ const struct btf_var_secinfo *b = _b;
+
+ return a->offset - b->offset;
+}
+
+static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
+ struct btf_type *t)
+{
+ __u32 size = 0, off = 0, i, vars = btf_vlen(t);
+ const char *name = btf__name_by_offset(btf, t->name_off);
+ const struct btf_type *t_var;
+ struct btf_var_secinfo *vsi;
+ const struct btf_var *var;
+ int ret;
+
+ if (!name) {
+ pr_debug("No name found in string section for DATASEC kind.\n");
+ return -ENOENT;
+ }
+
+ ret = bpf_object__section_size(obj, name, &size);
+ if (ret || !size || (t->size && t->size != size)) {
+ pr_debug("Invalid size for section %s: %u bytes\n", name, size);
+ return -ENOENT;
+ }
+
+ t->size = size;
+
+ for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+ t_var = btf__type_by_id(btf, vsi->type);
+ var = btf_var(t_var);
+
+ if (!btf_is_var(t_var)) {
+ pr_debug("Non-VAR type seen in section %s\n", name);
+ return -EINVAL;
+ }
+
+ if (var->linkage == BTF_VAR_STATIC)
+ continue;
+
+ name = btf__name_by_offset(btf, t_var->name_off);
+ if (!name) {
+ pr_debug("No name found in string section for VAR kind\n");
+ return -ENOENT;
+ }
+
+ ret = bpf_object__variable_offset(obj, name, &off);
+ if (ret) {
+ pr_debug("No offset found in symbol table for VAR %s\n",
+ name);
+ return -ENOENT;
+ }
+
+ vsi->offset = off;
+ }
+
+ qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off);
+ return 0;
+}
+
+int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+ int err = 0;
+ __u32 i;
+
+ for (i = 1; i <= btf->nr_types; i++) {
+ struct btf_type *t = btf->types[i];
+
+ /* Loader needs to fix up some of the things compiler
+ * couldn't get its hands on while emitting BTF. This
+ * is section size and global variable offset. We use
+ * the info from the ELF itself for this purpose.
+ */
+ if (btf_is_datasec(t)) {
+ err = btf_fixup_datasec(obj, btf, t);
+ if (err)
+ break;
+ }
+ }
+
+ return err;
+}
+
+int btf__load(struct btf *btf)
+{
+ __u32 log_buf_size = BPF_LOG_BUF_SIZE;
+ char *log_buf = NULL;
+ int err = 0;
+
+ if (btf->fd >= 0)
+ return -EEXIST;
+
+ log_buf = malloc(log_buf_size);
+ if (!log_buf)
+ return -ENOMEM;
+
+ *log_buf = 0;
+
+ btf->fd = bpf_load_btf(btf->data, btf->data_size,
+ log_buf, log_buf_size, false);
+ if (btf->fd < 0) {
+ err = -errno;
+ pr_warning("Error loading BTF: %s(%d)\n", strerror(errno), errno);
+ if (*log_buf)
+ pr_warning("%s\n", log_buf);
+ goto done;
+ }
+
+done:
+ free(log_buf);
+ return err;
+}
+
int btf__fd(const struct btf *btf)
{
return btf->fd;
}
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size)
+{
+ *size = btf->data_size;
+ return btf->data;
+}
+
const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
{
if (offset < btf->hdr->str_len)
@@ -393,3 +629,2235 @@
else
return NULL;
}
+
+int btf__get_from_id(__u32 id, struct btf **btf)
+{
+ struct bpf_btf_info btf_info = { 0 };
+ __u32 len = sizeof(btf_info);
+ __u32 last_size;
+ int btf_fd;
+ void *ptr;
+ int err;
+
+ err = 0;
+ *btf = NULL;
+ btf_fd = bpf_btf_get_fd_by_id(id);
+ if (btf_fd < 0)
+ return 0;
+
+ /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+ * let's start with a sane default - 4KiB here - and resize it only if
+ * bpf_obj_get_info_by_fd() needs a bigger buffer.
+ */
+ btf_info.btf_size = 4096;
+ last_size = btf_info.btf_size;
+ ptr = malloc(last_size);
+ if (!ptr) {
+ err = -ENOMEM;
+ goto exit_free;
+ }
+
+ memset(ptr, 0, last_size);
+ btf_info.btf = ptr_to_u64(ptr);
+ err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+ if (!err && btf_info.btf_size > last_size) {
+ void *temp_ptr;
+
+ last_size = btf_info.btf_size;
+ temp_ptr = realloc(ptr, last_size);
+ if (!temp_ptr) {
+ err = -ENOMEM;
+ goto exit_free;
+ }
+ ptr = temp_ptr;
+ memset(ptr, 0, last_size);
+ btf_info.btf = ptr_to_u64(ptr);
+ err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+ }
+
+ if (err || btf_info.btf_size > last_size) {
+ err = errno;
+ goto exit_free;
+ }
+
+ *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size);
+ if (IS_ERR(*btf)) {
+ err = PTR_ERR(*btf);
+ *btf = NULL;
+ }
+
+exit_free:
+ close(btf_fd);
+ free(ptr);
+
+ return err;
+}
+
+int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
+ __u32 expected_key_size, __u32 expected_value_size,
+ __u32 *key_type_id, __u32 *value_type_id)
+{
+ const struct btf_type *container_type;
+ const struct btf_member *key, *value;
+ const size_t max_name = 256;
+ char container_name[max_name];
+ __s64 key_size, value_size;
+ __s32 container_id;
+
+ if (snprintf(container_name, max_name, "____btf_map_%s", map_name) ==
+ max_name) {
+ pr_warning("map:%s length of '____btf_map_%s' is too long\n",
+ map_name, map_name);
+ return -EINVAL;
+ }
+
+ container_id = btf__find_by_name(btf, container_name);
+ if (container_id < 0) {
+ pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
+ map_name, container_name);
+ return container_id;
+ }
+
+ container_type = btf__type_by_id(btf, container_id);
+ if (!container_type) {
+ pr_warning("map:%s cannot find BTF type for container_id:%u\n",
+ map_name, container_id);
+ return -EINVAL;
+ }
+
+ if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) {
+ pr_warning("map:%s container_name:%s is an invalid container struct\n",
+ map_name, container_name);
+ return -EINVAL;
+ }
+
+ key = btf_members(container_type);
+ value = key + 1;
+
+ key_size = btf__resolve_size(btf, key->type);
+ if (key_size < 0) {
+ pr_warning("map:%s invalid BTF key_type_size\n", map_name);
+ return key_size;
+ }
+
+ if (expected_key_size != key_size) {
+ pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
+ map_name, (__u32)key_size, expected_key_size);
+ return -EINVAL;
+ }
+
+ value_size = btf__resolve_size(btf, value->type);
+ if (value_size < 0) {
+ pr_warning("map:%s invalid BTF value_type_size\n", map_name);
+ return value_size;
+ }
+
+ if (expected_value_size != value_size) {
+ pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
+ map_name, (__u32)value_size, expected_value_size);
+ return -EINVAL;
+ }
+
+ *key_type_id = key->type;
+ *value_type_id = value->type;
+
+ return 0;
+}
+
+struct btf_ext_sec_setup_param {
+ __u32 off;
+ __u32 len;
+ __u32 min_rec_size;
+ struct btf_ext_info *ext_info;
+ const char *desc;
+};
+
+static int btf_ext_setup_info(struct btf_ext *btf_ext,
+ struct btf_ext_sec_setup_param *ext_sec)
+{
+ const struct btf_ext_info_sec *sinfo;
+ struct btf_ext_info *ext_info;
+ __u32 info_left, record_size;
+ /* The start of the info sec (including the __u32 record_size). */
+ void *info;
+
+ if (ext_sec->len == 0)
+ return 0;
+
+ if (ext_sec->off & 0x03) {
+ pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n",
+ ext_sec->desc);
+ return -EINVAL;
+ }
+
+ info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off;
+ info_left = ext_sec->len;
+
+ if (btf_ext->data + btf_ext->data_size < info + ext_sec->len) {
+ pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
+ ext_sec->desc, ext_sec->off, ext_sec->len);
+ return -EINVAL;
+ }
+
+ /* At least a record size */
+ if (info_left < sizeof(__u32)) {
+ pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc);
+ return -EINVAL;
+ }
+
+ /* The record size needs to meet the minimum standard */
+ record_size = *(__u32 *)info;
+ if (record_size < ext_sec->min_rec_size ||
+ record_size & 0x03) {
+ pr_debug("%s section in .BTF.ext has invalid record size %u\n",
+ ext_sec->desc, record_size);
+ return -EINVAL;
+ }
+
+ sinfo = info + sizeof(__u32);
+ info_left -= sizeof(__u32);
+
+ /* If no records, return failure now so .BTF.ext won't be used. */
+ if (!info_left) {
+ pr_debug("%s section in .BTF.ext has no records", ext_sec->desc);
+ return -EINVAL;
+ }
+
+ while (info_left) {
+ unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec);
+ __u64 total_record_size;
+ __u32 num_records;
+
+ if (info_left < sec_hdrlen) {
+ pr_debug("%s section header is not found in .BTF.ext\n",
+ ext_sec->desc);
+ return -EINVAL;
+ }
+
+ num_records = sinfo->num_info;
+ if (num_records == 0) {
+ pr_debug("%s section has incorrect num_records in .BTF.ext\n",
+ ext_sec->desc);
+ return -EINVAL;
+ }
+
+ total_record_size = sec_hdrlen +
+ (__u64)num_records * record_size;
+ if (info_left < total_record_size) {
+ pr_debug("%s section has incorrect num_records in .BTF.ext\n",
+ ext_sec->desc);
+ return -EINVAL;
+ }
+
+ info_left -= total_record_size;
+ sinfo = (void *)sinfo + total_record_size;
+ }
+
+ ext_info = ext_sec->ext_info;
+ ext_info->len = ext_sec->len - sizeof(__u32);
+ ext_info->rec_size = record_size;
+ ext_info->info = info + sizeof(__u32);
+
+ return 0;
+}
+
+static int btf_ext_setup_func_info(struct btf_ext *btf_ext)
+{
+ struct btf_ext_sec_setup_param param = {
+ .off = btf_ext->hdr->func_info_off,
+ .len = btf_ext->hdr->func_info_len,
+ .min_rec_size = sizeof(struct bpf_func_info_min),
+ .ext_info = &btf_ext->func_info,
+ .desc = "func_info"
+ };
+
+ return btf_ext_setup_info(btf_ext, ¶m);
+}
+
+static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
+{
+ struct btf_ext_sec_setup_param param = {
+ .off = btf_ext->hdr->line_info_off,
+ .len = btf_ext->hdr->line_info_len,
+ .min_rec_size = sizeof(struct bpf_line_info_min),
+ .ext_info = &btf_ext->line_info,
+ .desc = "line_info",
+ };
+
+ return btf_ext_setup_info(btf_ext, ¶m);
+}
+
+static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext)
+{
+ struct btf_ext_sec_setup_param param = {
+ .off = btf_ext->hdr->offset_reloc_off,
+ .len = btf_ext->hdr->offset_reloc_len,
+ .min_rec_size = sizeof(struct bpf_offset_reloc),
+ .ext_info = &btf_ext->offset_reloc_info,
+ .desc = "offset_reloc",
+ };
+
+ return btf_ext_setup_info(btf_ext, ¶m);
+}
+
+static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
+{
+ const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+
+ if (data_size < offsetofend(struct btf_ext_header, hdr_len) ||
+ data_size < hdr->hdr_len) {
+ pr_debug("BTF.ext header not found");
+ return -EINVAL;
+ }
+
+ if (hdr->magic != BTF_MAGIC) {
+ pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
+ return -EINVAL;
+ }
+
+ if (hdr->version != BTF_VERSION) {
+ pr_debug("Unsupported BTF.ext version:%u\n", hdr->version);
+ return -ENOTSUP;
+ }
+
+ if (hdr->flags) {
+ pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags);
+ return -ENOTSUP;
+ }
+
+ if (data_size == hdr->hdr_len) {
+ pr_debug("BTF.ext has no data\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+void btf_ext__free(struct btf_ext *btf_ext)
+{
+ if (!btf_ext)
+ return;
+ free(btf_ext->data);
+ free(btf_ext);
+}
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
+{
+ struct btf_ext *btf_ext;
+ int err;
+
+ err = btf_ext_parse_hdr(data, size);
+ if (err)
+ return ERR_PTR(err);
+
+ btf_ext = calloc(1, sizeof(struct btf_ext));
+ if (!btf_ext)
+ return ERR_PTR(-ENOMEM);
+
+ btf_ext->data_size = size;
+ btf_ext->data = malloc(size);
+ if (!btf_ext->data) {
+ err = -ENOMEM;
+ goto done;
+ }
+ memcpy(btf_ext->data, data, size);
+
+ if (btf_ext->hdr->hdr_len <
+ offsetofend(struct btf_ext_header, line_info_len))
+ goto done;
+ err = btf_ext_setup_func_info(btf_ext);
+ if (err)
+ goto done;
+
+ err = btf_ext_setup_line_info(btf_ext);
+ if (err)
+ goto done;
+
+ if (btf_ext->hdr->hdr_len <
+ offsetofend(struct btf_ext_header, offset_reloc_len))
+ goto done;
+ err = btf_ext_setup_offset_reloc(btf_ext);
+ if (err)
+ goto done;
+
+done:
+ if (err) {
+ btf_ext__free(btf_ext);
+ return ERR_PTR(err);
+ }
+
+ return btf_ext;
+}
+
+const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size)
+{
+ *size = btf_ext->data_size;
+ return btf_ext->data;
+}
+
+static int btf_ext_reloc_info(const struct btf *btf,
+ const struct btf_ext_info *ext_info,
+ const char *sec_name, __u32 insns_cnt,
+ void **info, __u32 *cnt)
+{
+ __u32 sec_hdrlen = sizeof(struct btf_ext_info_sec);
+ __u32 i, record_size, existing_len, records_len;
+ struct btf_ext_info_sec *sinfo;
+ const char *info_sec_name;
+ __u64 remain_len;
+ void *data;
+
+ record_size = ext_info->rec_size;
+ sinfo = ext_info->info;
+ remain_len = ext_info->len;
+ while (remain_len > 0) {
+ records_len = sinfo->num_info * record_size;
+ info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+ if (strcmp(info_sec_name, sec_name)) {
+ remain_len -= sec_hdrlen + records_len;
+ sinfo = (void *)sinfo + sec_hdrlen + records_len;
+ continue;
+ }
+
+ existing_len = (*cnt) * record_size;
+ data = realloc(*info, existing_len + records_len);
+ if (!data)
+ return -ENOMEM;
+
+ memcpy(data + existing_len, sinfo->data, records_len);
+ /* adjust insn_off only, the rest data will be passed
+ * to the kernel.
+ */
+ for (i = 0; i < sinfo->num_info; i++) {
+ __u32 *insn_off;
+
+ insn_off = data + existing_len + (i * record_size);
+ *insn_off = *insn_off / sizeof(struct bpf_insn) +
+ insns_cnt;
+ }
+ *info = data;
+ *cnt += sinfo->num_info;
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+int btf_ext__reloc_func_info(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const char *sec_name, __u32 insns_cnt,
+ void **func_info, __u32 *cnt)
+{
+ return btf_ext_reloc_info(btf, &btf_ext->func_info, sec_name,
+ insns_cnt, func_info, cnt);
+}
+
+int btf_ext__reloc_line_info(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const char *sec_name, __u32 insns_cnt,
+ void **line_info, __u32 *cnt)
+{
+ return btf_ext_reloc_info(btf, &btf_ext->line_info, sec_name,
+ insns_cnt, line_info, cnt);
+}
+
+__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext)
+{
+ return btf_ext->func_info.rec_size;
+}
+
+__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
+{
+ return btf_ext->line_info.rec_size;
+}
+
+struct btf_dedup;
+
+static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
+ const struct btf_dedup_opts *opts);
+static void btf_dedup_free(struct btf_dedup *d);
+static int btf_dedup_strings(struct btf_dedup *d);
+static int btf_dedup_prim_types(struct btf_dedup *d);
+static int btf_dedup_struct_types(struct btf_dedup *d);
+static int btf_dedup_ref_types(struct btf_dedup *d);
+static int btf_dedup_compact_types(struct btf_dedup *d);
+static int btf_dedup_remap_types(struct btf_dedup *d);
+
+/*
+ * Deduplicate BTF types and strings.
+ *
+ * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF
+ * section with all BTF type descriptors and string data. It overwrites that
+ * memory in-place with deduplicated types and strings without any loss of
+ * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section
+ * is provided, all the strings referenced from .BTF.ext section are honored
+ * and updated to point to the right offsets after deduplication.
+ *
+ * If function returns with error, type/string data might be garbled and should
+ * be discarded.
+ *
+ * More verbose and detailed description of both problem btf_dedup is solving,
+ * as well as solution could be found at:
+ * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html
+ *
+ * Problem description and justification
+ * =====================================
+ *
+ * BTF type information is typically emitted either as a result of conversion
+ * from DWARF to BTF or directly by compiler. In both cases, each compilation
+ * unit contains information about a subset of all the types that are used
+ * in an application. These subsets are frequently overlapping and contain a lot
+ * of duplicated information when later concatenated together into a single
+ * binary. This algorithm ensures that each unique type is represented by single
+ * BTF type descriptor, greatly reducing resulting size of BTF data.
+ *
+ * Compilation unit isolation and subsequent duplication of data is not the only
+ * problem. The same type hierarchy (e.g., struct and all the type that struct
+ * references) in different compilation units can be represented in BTF to
+ * various degrees of completeness (or, rather, incompleteness) due to
+ * struct/union forward declarations.
+ *
+ * Let's take a look at an example, that we'll use to better understand the
+ * problem (and solution). Suppose we have two compilation units, each using
+ * same `struct S`, but each of them having incomplete type information about
+ * struct's fields:
+ *
+ * // CU #1:
+ * struct S;
+ * struct A {
+ * int a;
+ * struct A* self;
+ * struct S* parent;
+ * };
+ * struct B;
+ * struct S {
+ * struct A* a_ptr;
+ * struct B* b_ptr;
+ * };
+ *
+ * // CU #2:
+ * struct S;
+ * struct A;
+ * struct B {
+ * int b;
+ * struct B* self;
+ * struct S* parent;
+ * };
+ * struct S {
+ * struct A* a_ptr;
+ * struct B* b_ptr;
+ * };
+ *
+ * In case of CU #1, BTF data will know only that `struct B` exist (but no
+ * more), but will know the complete type information about `struct A`. While
+ * for CU #2, it will know full type information about `struct B`, but will
+ * only know about forward declaration of `struct A` (in BTF terms, it will
+ * have `BTF_KIND_FWD` type descriptor with name `B`).
+ *
+ * This compilation unit isolation means that it's possible that there is no
+ * single CU with complete type information describing structs `S`, `A`, and
+ * `B`. Also, we might get tons of duplicated and redundant type information.
+ *
+ * Additional complication we need to keep in mind comes from the fact that
+ * types, in general, can form graphs containing cycles, not just DAGs.
+ *
+ * While algorithm does deduplication, it also merges and resolves type
+ * information (unless disabled throught `struct btf_opts`), whenever possible.
+ * E.g., in the example above with two compilation units having partial type
+ * information for structs `A` and `B`, the output of algorithm will emit
+ * a single copy of each BTF type that describes structs `A`, `B`, and `S`
+ * (as well as type information for `int` and pointers), as if they were defined
+ * in a single compilation unit as:
+ *
+ * struct A {
+ * int a;
+ * struct A* self;
+ * struct S* parent;
+ * };
+ * struct B {
+ * int b;
+ * struct B* self;
+ * struct S* parent;
+ * };
+ * struct S {
+ * struct A* a_ptr;
+ * struct B* b_ptr;
+ * };
+ *
+ * Algorithm summary
+ * =================
+ *
+ * Algorithm completes its work in 6 separate passes:
+ *
+ * 1. Strings deduplication.
+ * 2. Primitive types deduplication (int, enum, fwd).
+ * 3. Struct/union types deduplication.
+ * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
+ * protos, and const/volatile/restrict modifiers).
+ * 5. Types compaction.
+ * 6. Types remapping.
+ *
+ * Algorithm determines canonical type descriptor, which is a single
+ * representative type for each truly unique type. This canonical type is the
+ * one that will go into final deduplicated BTF type information. For
+ * struct/unions, it is also the type that algorithm will merge additional type
+ * information into (while resolving FWDs), as it discovers it from data in
+ * other CUs. Each input BTF type eventually gets either mapped to itself, if
+ * that type is canonical, or to some other type, if that type is equivalent
+ * and was chosen as canonical representative. This mapping is stored in
+ * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that
+ * FWD type got resolved to.
+ *
+ * To facilitate fast discovery of canonical types, we also maintain canonical
+ * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash
+ * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types
+ * that match that signature. With sufficiently good choice of type signature
+ * hashing function, we can limit number of canonical types for each unique type
+ * signature to a very small number, allowing to find canonical type for any
+ * duplicated type very quickly.
+ *
+ * Struct/union deduplication is the most critical part and algorithm for
+ * deduplicating structs/unions is described in greater details in comments for
+ * `btf_dedup_is_equiv` function.
+ */
+int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
+ const struct btf_dedup_opts *opts)
+{
+ struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts);
+ int err;
+
+ if (IS_ERR(d)) {
+ pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
+ return -EINVAL;
+ }
+
+ err = btf_dedup_strings(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_strings failed:%d\n", err);
+ goto done;
+ }
+ err = btf_dedup_prim_types(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_prim_types failed:%d\n", err);
+ goto done;
+ }
+ err = btf_dedup_struct_types(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_struct_types failed:%d\n", err);
+ goto done;
+ }
+ err = btf_dedup_ref_types(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_ref_types failed:%d\n", err);
+ goto done;
+ }
+ err = btf_dedup_compact_types(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_compact_types failed:%d\n", err);
+ goto done;
+ }
+ err = btf_dedup_remap_types(d);
+ if (err < 0) {
+ pr_debug("btf_dedup_remap_types failed:%d\n", err);
+ goto done;
+ }
+
+done:
+ btf_dedup_free(d);
+ return err;
+}
+
+#define BTF_UNPROCESSED_ID ((__u32)-1)
+#define BTF_IN_PROGRESS_ID ((__u32)-2)
+
+struct btf_dedup {
+ /* .BTF section to be deduped in-place */
+ struct btf *btf;
+ /*
+ * Optional .BTF.ext section. When provided, any strings referenced
+ * from it will be taken into account when deduping strings
+ */
+ struct btf_ext *btf_ext;
+ /*
+ * This is a map from any type's signature hash to a list of possible
+ * canonical representative type candidates. Hash collisions are
+ * ignored, so even types of various kinds can share same list of
+ * candidates, which is fine because we rely on subsequent
+ * btf_xxx_equal() checks to authoritatively verify type equality.
+ */
+ struct hashmap *dedup_table;
+ /* Canonical types map */
+ __u32 *map;
+ /* Hypothetical mapping, used during type graph equivalence checks */
+ __u32 *hypot_map;
+ __u32 *hypot_list;
+ size_t hypot_cnt;
+ size_t hypot_cap;
+ /* Various option modifying behavior of algorithm */
+ struct btf_dedup_opts opts;
+};
+
+struct btf_str_ptr {
+ const char *str;
+ __u32 new_off;
+ bool used;
+};
+
+struct btf_str_ptrs {
+ struct btf_str_ptr *ptrs;
+ const char *data;
+ __u32 cnt;
+ __u32 cap;
+};
+
+static long hash_combine(long h, long value)
+{
+ return h * 31 + value;
+}
+
+#define for_each_dedup_cand(d, node, hash) \
+ hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
+
+static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
+{
+ return hashmap__append(d->dedup_table,
+ (void *)hash, (void *)(long)type_id);
+}
+
+static int btf_dedup_hypot_map_add(struct btf_dedup *d,
+ __u32 from_id, __u32 to_id)
+{
+ if (d->hypot_cnt == d->hypot_cap) {
+ __u32 *new_list;
+
+ d->hypot_cap += max(16, d->hypot_cap / 2);
+ new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
+ if (!new_list)
+ return -ENOMEM;
+ d->hypot_list = new_list;
+ }
+ d->hypot_list[d->hypot_cnt++] = from_id;
+ d->hypot_map[from_id] = to_id;
+ return 0;
+}
+
+static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
+{
+ int i;
+
+ for (i = 0; i < d->hypot_cnt; i++)
+ d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID;
+ d->hypot_cnt = 0;
+}
+
+static void btf_dedup_free(struct btf_dedup *d)
+{
+ hashmap__free(d->dedup_table);
+ d->dedup_table = NULL;
+
+ free(d->map);
+ d->map = NULL;
+
+ free(d->hypot_map);
+ d->hypot_map = NULL;
+
+ free(d->hypot_list);
+ d->hypot_list = NULL;
+
+ free(d);
+}
+
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
+{
+ return (size_t)key;
+}
+
+static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+{
+ return 0;
+}
+
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+ return k1 == k2;
+}
+
+static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
+ const struct btf_dedup_opts *opts)
+{
+ struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
+ hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
+ int i, err = 0;
+
+ if (!d)
+ return ERR_PTR(-ENOMEM);
+
+ d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
+ /* dedup_table_size is now used only to force collisions in tests */
+ if (opts && opts->dedup_table_size == 1)
+ hash_fn = btf_dedup_collision_hash_fn;
+
+ d->btf = btf;
+ d->btf_ext = btf_ext;
+
+ d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL);
+ if (IS_ERR(d->dedup_table)) {
+ err = PTR_ERR(d->dedup_table);
+ d->dedup_table = NULL;
+ goto done;
+ }
+
+ d->map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+ if (!d->map) {
+ err = -ENOMEM;
+ goto done;
+ }
+ /* special BTF "void" type is made canonical immediately */
+ d->map[0] = 0;
+ for (i = 1; i <= btf->nr_types; i++) {
+ struct btf_type *t = d->btf->types[i];
+
+ /* VAR and DATASEC are never deduped and are self-canonical */
+ if (btf_is_var(t) || btf_is_datasec(t))
+ d->map[i] = i;
+ else
+ d->map[i] = BTF_UNPROCESSED_ID;
+ }
+
+ d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+ if (!d->hypot_map) {
+ err = -ENOMEM;
+ goto done;
+ }
+ for (i = 0; i <= btf->nr_types; i++)
+ d->hypot_map[i] = BTF_UNPROCESSED_ID;
+
+done:
+ if (err) {
+ btf_dedup_free(d);
+ return ERR_PTR(err);
+ }
+
+ return d;
+}
+
+typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx);
+
+/*
+ * Iterate over all possible places in .BTF and .BTF.ext that can reference
+ * string and pass pointer to it to a provided callback `fn`.
+ */
+static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
+{
+ void *line_data_cur, *line_data_end;
+ int i, j, r, rec_size;
+ struct btf_type *t;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ t = d->btf->types[i];
+ r = fn(&t->name_off, ctx);
+ if (r)
+ return r;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ struct btf_member *m = btf_members(t);
+ __u16 vlen = btf_vlen(t);
+
+ for (j = 0; j < vlen; j++) {
+ r = fn(&m->name_off, ctx);
+ if (r)
+ return r;
+ m++;
+ }
+ break;
+ }
+ case BTF_KIND_ENUM: {
+ struct btf_enum *m = btf_enum(t);
+ __u16 vlen = btf_vlen(t);
+
+ for (j = 0; j < vlen; j++) {
+ r = fn(&m->name_off, ctx);
+ if (r)
+ return r;
+ m++;
+ }
+ break;
+ }
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *m = btf_params(t);
+ __u16 vlen = btf_vlen(t);
+
+ for (j = 0; j < vlen; j++) {
+ r = fn(&m->name_off, ctx);
+ if (r)
+ return r;
+ m++;
+ }
+ break;
+ }
+ default:
+ break;
+ }
+ }
+
+ if (!d->btf_ext)
+ return 0;
+
+ line_data_cur = d->btf_ext->line_info.info;
+ line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len;
+ rec_size = d->btf_ext->line_info.rec_size;
+
+ while (line_data_cur < line_data_end) {
+ struct btf_ext_info_sec *sec = line_data_cur;
+ struct bpf_line_info_min *line_info;
+ __u32 num_info = sec->num_info;
+
+ r = fn(&sec->sec_name_off, ctx);
+ if (r)
+ return r;
+
+ line_data_cur += sizeof(struct btf_ext_info_sec);
+ for (i = 0; i < num_info; i++) {
+ line_info = line_data_cur;
+ r = fn(&line_info->file_name_off, ctx);
+ if (r)
+ return r;
+ r = fn(&line_info->line_off, ctx);
+ if (r)
+ return r;
+ line_data_cur += rec_size;
+ }
+ }
+
+ return 0;
+}
+
+static int str_sort_by_content(const void *a1, const void *a2)
+{
+ const struct btf_str_ptr *p1 = a1;
+ const struct btf_str_ptr *p2 = a2;
+
+ return strcmp(p1->str, p2->str);
+}
+
+static int str_sort_by_offset(const void *a1, const void *a2)
+{
+ const struct btf_str_ptr *p1 = a1;
+ const struct btf_str_ptr *p2 = a2;
+
+ if (p1->str != p2->str)
+ return p1->str < p2->str ? -1 : 1;
+ return 0;
+}
+
+static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem)
+{
+ const struct btf_str_ptr *p = pelem;
+
+ if (str_ptr != p->str)
+ return (const char *)str_ptr < p->str ? -1 : 1;
+ return 0;
+}
+
+static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx)
+{
+ struct btf_str_ptrs *strs;
+ struct btf_str_ptr *s;
+
+ if (*str_off_ptr == 0)
+ return 0;
+
+ strs = ctx;
+ s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
+ sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
+ if (!s)
+ return -EINVAL;
+ s->used = true;
+ return 0;
+}
+
+static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
+{
+ struct btf_str_ptrs *strs;
+ struct btf_str_ptr *s;
+
+ if (*str_off_ptr == 0)
+ return 0;
+
+ strs = ctx;
+ s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
+ sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
+ if (!s)
+ return -EINVAL;
+ *str_off_ptr = s->new_off;
+ return 0;
+}
+
+/*
+ * Dedup string and filter out those that are not referenced from either .BTF
+ * or .BTF.ext (if provided) sections.
+ *
+ * This is done by building index of all strings in BTF's string section,
+ * then iterating over all entities that can reference strings (e.g., type
+ * names, struct field names, .BTF.ext line info, etc) and marking corresponding
+ * strings as used. After that all used strings are deduped and compacted into
+ * sequential blob of memory and new offsets are calculated. Then all the string
+ * references are iterated again and rewritten using new offsets.
+ */
+static int btf_dedup_strings(struct btf_dedup *d)
+{
+ const struct btf_header *hdr = d->btf->hdr;
+ char *start = (char *)d->btf->nohdr_data + hdr->str_off;
+ char *end = start + d->btf->hdr->str_len;
+ char *p = start, *tmp_strs = NULL;
+ struct btf_str_ptrs strs = {
+ .cnt = 0,
+ .cap = 0,
+ .ptrs = NULL,
+ .data = start,
+ };
+ int i, j, err = 0, grp_idx;
+ bool grp_used;
+
+ /* build index of all strings */
+ while (p < end) {
+ if (strs.cnt + 1 > strs.cap) {
+ struct btf_str_ptr *new_ptrs;
+
+ strs.cap += max(strs.cnt / 2, 16);
+ new_ptrs = realloc(strs.ptrs,
+ sizeof(strs.ptrs[0]) * strs.cap);
+ if (!new_ptrs) {
+ err = -ENOMEM;
+ goto done;
+ }
+ strs.ptrs = new_ptrs;
+ }
+
+ strs.ptrs[strs.cnt].str = p;
+ strs.ptrs[strs.cnt].used = false;
+
+ p += strlen(p) + 1;
+ strs.cnt++;
+ }
+
+ /* temporary storage for deduplicated strings */
+ tmp_strs = malloc(d->btf->hdr->str_len);
+ if (!tmp_strs) {
+ err = -ENOMEM;
+ goto done;
+ }
+
+ /* mark all used strings */
+ strs.ptrs[0].used = true;
+ err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs);
+ if (err)
+ goto done;
+
+ /* sort strings by context, so that we can identify duplicates */
+ qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content);
+
+ /*
+ * iterate groups of equal strings and if any instance in a group was
+ * referenced, emit single instance and remember new offset
+ */
+ p = tmp_strs;
+ grp_idx = 0;
+ grp_used = strs.ptrs[0].used;
+ /* iterate past end to avoid code duplication after loop */
+ for (i = 1; i <= strs.cnt; i++) {
+ /*
+ * when i == strs.cnt, we want to skip string comparison and go
+ * straight to handling last group of strings (otherwise we'd
+ * need to handle last group after the loop w/ duplicated code)
+ */
+ if (i < strs.cnt &&
+ !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) {
+ grp_used = grp_used || strs.ptrs[i].used;
+ continue;
+ }
+
+ /*
+ * this check would have been required after the loop to handle
+ * last group of strings, but due to <= condition in a loop
+ * we avoid that duplication
+ */
+ if (grp_used) {
+ int new_off = p - tmp_strs;
+ __u32 len = strlen(strs.ptrs[grp_idx].str);
+
+ memmove(p, strs.ptrs[grp_idx].str, len + 1);
+ for (j = grp_idx; j < i; j++)
+ strs.ptrs[j].new_off = new_off;
+ p += len + 1;
+ }
+
+ if (i < strs.cnt) {
+ grp_idx = i;
+ grp_used = strs.ptrs[i].used;
+ }
+ }
+
+ /* replace original strings with deduped ones */
+ d->btf->hdr->str_len = p - tmp_strs;
+ memmove(start, tmp_strs, d->btf->hdr->str_len);
+ end = start + d->btf->hdr->str_len;
+
+ /* restore original order for further binary search lookups */
+ qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset);
+
+ /* remap string offsets */
+ err = btf_for_each_str_off(d, btf_str_remap_offset, &strs);
+ if (err)
+ goto done;
+
+ d->btf->hdr->str_len = end - start;
+
+done:
+ free(tmp_strs);
+ free(strs.ptrs);
+ return err;
+}
+
+static long btf_hash_common(struct btf_type *t)
+{
+ long h;
+
+ h = hash_combine(0, t->name_off);
+ h = hash_combine(h, t->info);
+ h = hash_combine(h, t->size);
+ return h;
+}
+
+static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
+{
+ return t1->name_off == t2->name_off &&
+ t1->info == t2->info &&
+ t1->size == t2->size;
+}
+
+/* Calculate type signature hash of INT. */
+static long btf_hash_int(struct btf_type *t)
+{
+ __u32 info = *(__u32 *)(t + 1);
+ long h;
+
+ h = btf_hash_common(t);
+ h = hash_combine(h, info);
+ return h;
+}
+
+/* Check structural equality of two INTs. */
+static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+{
+ __u32 info1, info2;
+
+ if (!btf_equal_common(t1, t2))
+ return false;
+ info1 = *(__u32 *)(t1 + 1);
+ info2 = *(__u32 *)(t2 + 1);
+ return info1 == info2;
+}
+
+/* Calculate type signature hash of ENUM. */
+static long btf_hash_enum(struct btf_type *t)
+{
+ long h;
+
+ /* don't hash vlen and enum members to support enum fwd resolving */
+ h = hash_combine(0, t->name_off);
+ h = hash_combine(h, t->info & ~0xffff);
+ h = hash_combine(h, t->size);
+ return h;
+}
+
+/* Check structural equality of two ENUMs. */
+static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+{
+ const struct btf_enum *m1, *m2;
+ __u16 vlen;
+ int i;
+
+ if (!btf_equal_common(t1, t2))
+ return false;
+
+ vlen = btf_vlen(t1);
+ m1 = btf_enum(t1);
+ m2 = btf_enum(t2);
+ for (i = 0; i < vlen; i++) {
+ if (m1->name_off != m2->name_off || m1->val != m2->val)
+ return false;
+ m1++;
+ m2++;
+ }
+ return true;
+}
+
+static inline bool btf_is_enum_fwd(struct btf_type *t)
+{
+ return btf_is_enum(t) && btf_vlen(t) == 0;
+}
+
+static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
+{
+ if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
+ return btf_equal_enum(t1, t2);
+ /* ignore vlen when comparing */
+ return t1->name_off == t2->name_off &&
+ (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
+ t1->size == t2->size;
+}
+
+/*
+ * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
+ * as referenced type IDs equivalence is established separately during type
+ * graph equivalence check algorithm.
+ */
+static long btf_hash_struct(struct btf_type *t)
+{
+ const struct btf_member *member = btf_members(t);
+ __u32 vlen = btf_vlen(t);
+ long h = btf_hash_common(t);
+ int i;
+
+ for (i = 0; i < vlen; i++) {
+ h = hash_combine(h, member->name_off);
+ h = hash_combine(h, member->offset);
+ /* no hashing of referenced type ID, it can be unresolved yet */
+ member++;
+ }
+ return h;
+}
+
+/*
+ * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
+{
+ const struct btf_member *m1, *m2;
+ __u16 vlen;
+ int i;
+
+ if (!btf_equal_common(t1, t2))
+ return false;
+
+ vlen = btf_vlen(t1);
+ m1 = btf_members(t1);
+ m2 = btf_members(t2);
+ for (i = 0; i < vlen; i++) {
+ if (m1->name_off != m2->name_off || m1->offset != m2->offset)
+ return false;
+ m1++;
+ m2++;
+ }
+ return true;
+}
+
+/*
+ * Calculate type signature hash of ARRAY, including referenced type IDs,
+ * under assumption that they were already resolved to canonical type IDs and
+ * are not going to change.
+ */
+static long btf_hash_array(struct btf_type *t)
+{
+ const struct btf_array *info = btf_array(t);
+ long h = btf_hash_common(t);
+
+ h = hash_combine(h, info->type);
+ h = hash_combine(h, info->index_type);
+ h = hash_combine(h, info->nelems);
+ return h;
+}
+
+/*
+ * Check exact equality of two ARRAYs, taking into account referenced
+ * type IDs, under assumption that they were already resolved to canonical
+ * type IDs and are not going to change.
+ * This function is called during reference types deduplication to compare
+ * ARRAY to potential canonical representative.
+ */
+static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
+{
+ const struct btf_array *info1, *info2;
+
+ if (!btf_equal_common(t1, t2))
+ return false;
+
+ info1 = btf_array(t1);
+ info2 = btf_array(t2);
+ return info1->type == info2->type &&
+ info1->index_type == info2->index_type &&
+ info1->nelems == info2->nelems;
+}
+
+/*
+ * Check structural compatibility of two ARRAYs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
+{
+ if (!btf_equal_common(t1, t2))
+ return false;
+
+ return btf_array(t1)->nelems == btf_array(t2)->nelems;
+}
+
+/*
+ * Calculate type signature hash of FUNC_PROTO, including referenced type IDs,
+ * under assumption that they were already resolved to canonical type IDs and
+ * are not going to change.
+ */
+static long btf_hash_fnproto(struct btf_type *t)
+{
+ const struct btf_param *member = btf_params(t);
+ __u16 vlen = btf_vlen(t);
+ long h = btf_hash_common(t);
+ int i;
+
+ for (i = 0; i < vlen; i++) {
+ h = hash_combine(h, member->name_off);
+ h = hash_combine(h, member->type);
+ member++;
+ }
+ return h;
+}
+
+/*
+ * Check exact equality of two FUNC_PROTOs, taking into account referenced
+ * type IDs, under assumption that they were already resolved to canonical
+ * type IDs and are not going to change.
+ * This function is called during reference types deduplication to compare
+ * FUNC_PROTO to potential canonical representative.
+ */
+static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
+{
+ const struct btf_param *m1, *m2;
+ __u16 vlen;
+ int i;
+
+ if (!btf_equal_common(t1, t2))
+ return false;
+
+ vlen = btf_vlen(t1);
+ m1 = btf_params(t1);
+ m2 = btf_params(t2);
+ for (i = 0; i < vlen; i++) {
+ if (m1->name_off != m2->name_off || m1->type != m2->type)
+ return false;
+ m1++;
+ m2++;
+ }
+ return true;
+}
+
+/*
+ * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
+{
+ const struct btf_param *m1, *m2;
+ __u16 vlen;
+ int i;
+
+ /* skip return type ID */
+ if (t1->name_off != t2->name_off || t1->info != t2->info)
+ return false;
+
+ vlen = btf_vlen(t1);
+ m1 = btf_params(t1);
+ m2 = btf_params(t2);
+ for (i = 0; i < vlen; i++) {
+ if (m1->name_off != m2->name_off)
+ return false;
+ m1++;
+ m2++;
+ }
+ return true;
+}
+
+/*
+ * Deduplicate primitive types, that can't reference other types, by calculating
+ * their type signature hash and comparing them with any possible canonical
+ * candidate. If no canonical candidate matches, type itself is marked as
+ * canonical and is added into `btf_dedup->dedup_table` as another candidate.
+ */
+static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
+{
+ struct btf_type *t = d->btf->types[type_id];
+ struct hashmap_entry *hash_entry;
+ struct btf_type *cand;
+ /* if we don't find equivalent type, then we are canonical */
+ __u32 new_id = type_id;
+ __u32 cand_id;
+ long h;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_ARRAY:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_FUNC:
+ case BTF_KIND_FUNC_PROTO:
+ case BTF_KIND_VAR:
+ case BTF_KIND_DATASEC:
+ return 0;
+
+ case BTF_KIND_INT:
+ h = btf_hash_int(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_int(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ }
+ break;
+
+ case BTF_KIND_ENUM:
+ h = btf_hash_enum(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_enum(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ if (d->opts.dont_resolve_fwds)
+ continue;
+ if (btf_compat_enum(t, cand)) {
+ if (btf_is_enum_fwd(t)) {
+ /* resolve fwd to full enum */
+ new_id = cand_id;
+ break;
+ }
+ /* resolve canonical enum fwd to full enum */
+ d->map[cand_id] = type_id;
+ }
+ }
+ break;
+
+ case BTF_KIND_FWD:
+ h = btf_hash_common(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_common(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ }
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ d->map[type_id] = new_id;
+ if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int btf_dedup_prim_types(struct btf_dedup *d)
+{
+ int i, err;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ err = btf_dedup_prim_type(d, i);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+/*
+ * Check whether type is already mapped into canonical one (could be to itself).
+ */
+static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id)
+{
+ return d->map[type_id] <= BTF_MAX_NR_TYPES;
+}
+
+/*
+ * Resolve type ID into its canonical type ID, if any; otherwise return original
+ * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow
+ * STRUCT/UNION link and resolve it into canonical type ID as well.
+ */
+static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id)
+{
+ while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
+ type_id = d->map[type_id];
+ return type_id;
+}
+
+/*
+ * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original
+ * type ID.
+ */
+static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
+{
+ __u32 orig_type_id = type_id;
+
+ if (!btf_is_fwd(d->btf->types[type_id]))
+ return type_id;
+
+ while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
+ type_id = d->map[type_id];
+
+ if (!btf_is_fwd(d->btf->types[type_id]))
+ return type_id;
+
+ return orig_type_id;
+}
+
+
+static inline __u16 btf_fwd_kind(struct btf_type *t)
+{
+ return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
+}
+
+/*
+ * Check equivalence of BTF type graph formed by candidate struct/union (we'll
+ * call it "candidate graph" in this description for brevity) to a type graph
+ * formed by (potential) canonical struct/union ("canonical graph" for brevity
+ * here, though keep in mind that not all types in canonical graph are
+ * necessarily canonical representatives themselves, some of them might be
+ * duplicates or its uniqueness might not have been established yet).
+ * Returns:
+ * - >0, if type graphs are equivalent;
+ * - 0, if not equivalent;
+ * - <0, on error.
+ *
+ * Algorithm performs side-by-side DFS traversal of both type graphs and checks
+ * equivalence of BTF types at each step. If at any point BTF types in candidate
+ * and canonical graphs are not compatible structurally, whole graphs are
+ * incompatible. If types are structurally equivalent (i.e., all information
+ * except referenced type IDs is exactly the same), a mapping from `canon_id` to
+ * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`).
+ * If a type references other types, then those referenced types are checked
+ * for equivalence recursively.
+ *
+ * During DFS traversal, if we find that for current `canon_id` type we
+ * already have some mapping in hypothetical map, we check for two possible
+ * situations:
+ * - `canon_id` is mapped to exactly the same type as `cand_id`. This will
+ * happen when type graphs have cycles. In this case we assume those two
+ * types are equivalent.
+ * - `canon_id` is mapped to different type. This is contradiction in our
+ * hypothetical mapping, because same graph in canonical graph corresponds
+ * to two different types in candidate graph, which for equivalent type
+ * graphs shouldn't happen. This condition terminates equivalence check
+ * with negative result.
+ *
+ * If type graphs traversal exhausts types to check and find no contradiction,
+ * then type graphs are equivalent.
+ *
+ * When checking types for equivalence, there is one special case: FWD types.
+ * If FWD type resolution is allowed and one of the types (either from canonical
+ * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind
+ * flag) and their names match, hypothetical mapping is updated to point from
+ * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully,
+ * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently.
+ *
+ * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution,
+ * if there are two exactly named (or anonymous) structs/unions that are
+ * compatible structurally, one of which has FWD field, while other is concrete
+ * STRUCT/UNION, but according to C sources they are different structs/unions
+ * that are referencing different types with the same name. This is extremely
+ * unlikely to happen, but btf_dedup API allows to disable FWD resolution if
+ * this logic is causing problems.
+ *
+ * Doing FWD resolution means that both candidate and/or canonical graphs can
+ * consists of portions of the graph that come from multiple compilation units.
+ * This is due to the fact that types within single compilation unit are always
+ * deduplicated and FWDs are already resolved, if referenced struct/union
+ * definiton is available. So, if we had unresolved FWD and found corresponding
+ * STRUCT/UNION, they will be from different compilation units. This
+ * consequently means that when we "link" FWD to corresponding STRUCT/UNION,
+ * type graph will likely have at least two different BTF types that describe
+ * same type (e.g., most probably there will be two different BTF types for the
+ * same 'int' primitive type) and could even have "overlapping" parts of type
+ * graph that describe same subset of types.
+ *
+ * This in turn means that our assumption that each type in canonical graph
+ * must correspond to exactly one type in candidate graph might not hold
+ * anymore and will make it harder to detect contradictions using hypothetical
+ * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION
+ * resolution only in canonical graph. FWDs in candidate graphs are never
+ * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs
+ * that can occur:
+ * - Both types in canonical and candidate graphs are FWDs. If they are
+ * structurally equivalent, then they can either be both resolved to the
+ * same STRUCT/UNION or not resolved at all. In both cases they are
+ * equivalent and there is no need to resolve FWD on candidate side.
+ * - Both types in canonical and candidate graphs are concrete STRUCT/UNION,
+ * so nothing to resolve as well, algorithm will check equivalence anyway.
+ * - Type in canonical graph is FWD, while type in candidate is concrete
+ * STRUCT/UNION. In this case candidate graph comes from single compilation
+ * unit, so there is exactly one BTF type for each unique C type. After
+ * resolving FWD into STRUCT/UNION, there might be more than one BTF type
+ * in canonical graph mapping to single BTF type in candidate graph, but
+ * because hypothetical mapping maps from canonical to candidate types, it's
+ * alright, and we still maintain the property of having single `canon_id`
+ * mapping to single `cand_id` (there could be two different `canon_id`
+ * mapped to the same `cand_id`, but it's not contradictory).
+ * - Type in canonical graph is concrete STRUCT/UNION, while type in candidate
+ * graph is FWD. In this case we are just going to check compatibility of
+ * STRUCT/UNION and corresponding FWD, and if they are compatible, we'll
+ * assume that whatever STRUCT/UNION FWD resolves to must be equivalent to
+ * a concrete STRUCT/UNION from canonical graph. If the rest of type graphs
+ * turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from
+ * canonical graph.
+ */
+static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
+ __u32 canon_id)
+{
+ struct btf_type *cand_type;
+ struct btf_type *canon_type;
+ __u32 hypot_type_id;
+ __u16 cand_kind;
+ __u16 canon_kind;
+ int i, eq;
+
+ /* if both resolve to the same canonical, they must be equivalent */
+ if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id))
+ return 1;
+
+ canon_id = resolve_fwd_id(d, canon_id);
+
+ hypot_type_id = d->hypot_map[canon_id];
+ if (hypot_type_id <= BTF_MAX_NR_TYPES)
+ return hypot_type_id == cand_id;
+
+ if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
+ return -ENOMEM;
+
+ cand_type = d->btf->types[cand_id];
+ canon_type = d->btf->types[canon_id];
+ cand_kind = btf_kind(cand_type);
+ canon_kind = btf_kind(canon_type);
+
+ if (cand_type->name_off != canon_type->name_off)
+ return 0;
+
+ /* FWD <--> STRUCT/UNION equivalence check, if enabled */
+ if (!d->opts.dont_resolve_fwds
+ && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
+ && cand_kind != canon_kind) {
+ __u16 real_kind;
+ __u16 fwd_kind;
+
+ if (cand_kind == BTF_KIND_FWD) {
+ real_kind = canon_kind;
+ fwd_kind = btf_fwd_kind(cand_type);
+ } else {
+ real_kind = cand_kind;
+ fwd_kind = btf_fwd_kind(canon_type);
+ }
+ return fwd_kind == real_kind;
+ }
+
+ if (cand_kind != canon_kind)
+ return 0;
+
+ switch (cand_kind) {
+ case BTF_KIND_INT:
+ return btf_equal_int(cand_type, canon_type);
+
+ case BTF_KIND_ENUM:
+ if (d->opts.dont_resolve_fwds)
+ return btf_equal_enum(cand_type, canon_type);
+ else
+ return btf_compat_enum(cand_type, canon_type);
+
+ case BTF_KIND_FWD:
+ return btf_equal_common(cand_type, canon_type);
+
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ if (cand_type->info != canon_type->info)
+ return 0;
+ return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
+
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *cand_arr, *canon_arr;
+
+ if (!btf_compat_array(cand_type, canon_type))
+ return 0;
+ cand_arr = btf_array(cand_type);
+ canon_arr = btf_array(canon_type);
+ eq = btf_dedup_is_equiv(d,
+ cand_arr->index_type, canon_arr->index_type);
+ if (eq <= 0)
+ return eq;
+ return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type);
+ }
+
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *cand_m, *canon_m;
+ __u16 vlen;
+
+ if (!btf_shallow_equal_struct(cand_type, canon_type))
+ return 0;
+ vlen = btf_vlen(cand_type);
+ cand_m = btf_members(cand_type);
+ canon_m = btf_members(canon_type);
+ for (i = 0; i < vlen; i++) {
+ eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
+ if (eq <= 0)
+ return eq;
+ cand_m++;
+ canon_m++;
+ }
+
+ return 1;
+ }
+
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *cand_p, *canon_p;
+ __u16 vlen;
+
+ if (!btf_compat_fnproto(cand_type, canon_type))
+ return 0;
+ eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
+ if (eq <= 0)
+ return eq;
+ vlen = btf_vlen(cand_type);
+ cand_p = btf_params(cand_type);
+ canon_p = btf_params(canon_type);
+ for (i = 0; i < vlen; i++) {
+ eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type);
+ if (eq <= 0)
+ return eq;
+ cand_p++;
+ canon_p++;
+ }
+ return 1;
+ }
+
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * Use hypothetical mapping, produced by successful type graph equivalence
+ * check, to augment existing struct/union canonical mapping, where possible.
+ *
+ * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record
+ * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional:
+ * it doesn't matter if FWD type was part of canonical graph or candidate one,
+ * we are recording the mapping anyway. As opposed to carefulness required
+ * for struct/union correspondence mapping (described below), for FWD resolution
+ * it's not important, as by the time that FWD type (reference type) will be
+ * deduplicated all structs/unions will be deduped already anyway.
+ *
+ * Recording STRUCT/UNION mapping is purely a performance optimization and is
+ * not required for correctness. It needs to be done carefully to ensure that
+ * struct/union from candidate's type graph is not mapped into corresponding
+ * struct/union from canonical type graph that itself hasn't been resolved into
+ * canonical representative. The only guarantee we have is that canonical
+ * struct/union was determined as canonical and that won't change. But any
+ * types referenced through that struct/union fields could have been not yet
+ * resolved, so in case like that it's too early to establish any kind of
+ * correspondence between structs/unions.
+ *
+ * No canonical correspondence is derived for primitive types (they are already
+ * deduplicated completely already anyway) or reference types (they rely on
+ * stability of struct/union canonical relationship for equivalence checks).
+ */
+static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
+{
+ __u32 cand_type_id, targ_type_id;
+ __u16 t_kind, c_kind;
+ __u32 t_id, c_id;
+ int i;
+
+ for (i = 0; i < d->hypot_cnt; i++) {
+ cand_type_id = d->hypot_list[i];
+ targ_type_id = d->hypot_map[cand_type_id];
+ t_id = resolve_type_id(d, targ_type_id);
+ c_id = resolve_type_id(d, cand_type_id);
+ t_kind = btf_kind(d->btf->types[t_id]);
+ c_kind = btf_kind(d->btf->types[c_id]);
+ /*
+ * Resolve FWD into STRUCT/UNION.
+ * It's ok to resolve FWD into STRUCT/UNION that's not yet
+ * mapped to canonical representative (as opposed to
+ * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because
+ * eventually that struct is going to be mapped and all resolved
+ * FWDs will automatically resolve to correct canonical
+ * representative. This will happen before ref type deduping,
+ * which critically depends on stability of these mapping. This
+ * stability is not a requirement for STRUCT/UNION equivalence
+ * checks, though.
+ */
+ if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD)
+ d->map[c_id] = t_id;
+ else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
+ d->map[t_id] = c_id;
+
+ if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) &&
+ c_kind != BTF_KIND_FWD &&
+ is_type_mapped(d, c_id) &&
+ !is_type_mapped(d, t_id)) {
+ /*
+ * as a perf optimization, we can map struct/union
+ * that's part of type graph we just verified for
+ * equivalence. We can do that for struct/union that has
+ * canonical representative only, though.
+ */
+ d->map[t_id] = c_id;
+ }
+ }
+}
+
+/*
+ * Deduplicate struct/union types.
+ *
+ * For each struct/union type its type signature hash is calculated, taking
+ * into account type's name, size, number, order and names of fields, but
+ * ignoring type ID's referenced from fields, because they might not be deduped
+ * completely until after reference types deduplication phase. This type hash
+ * is used to iterate over all potential canonical types, sharing same hash.
+ * For each canonical candidate we check whether type graphs that they form
+ * (through referenced types in fields and so on) are equivalent using algorithm
+ * implemented in `btf_dedup_is_equiv`. If such equivalence is found and
+ * BTF_KIND_FWD resolution is allowed, then hypothetical mapping
+ * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence
+ * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to
+ * potentially map other structs/unions to their canonical representatives,
+ * if such relationship hasn't yet been established. This speeds up algorithm
+ * by eliminating some of the duplicate work.
+ *
+ * If no matching canonical representative was found, struct/union is marked
+ * as canonical for itself and is added into btf_dedup->dedup_table hash map
+ * for further look ups.
+ */
+static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
+{
+ struct btf_type *cand_type, *t;
+ struct hashmap_entry *hash_entry;
+ /* if we don't find equivalent type, then we are canonical */
+ __u32 new_id = type_id;
+ __u16 kind;
+ long h;
+
+ /* already deduped or is in process of deduping (loop detected) */
+ if (d->map[type_id] <= BTF_MAX_NR_TYPES)
+ return 0;
+
+ t = d->btf->types[type_id];
+ kind = btf_kind(t);
+
+ if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+ return 0;
+
+ h = btf_hash_struct(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ __u32 cand_id = (__u32)(long)hash_entry->value;
+ int eq;
+
+ /*
+ * Even though btf_dedup_is_equiv() checks for
+ * btf_shallow_equal_struct() internally when checking two
+ * structs (unions) for equivalence, we need to guard here
+ * from picking matching FWD type as a dedup candidate.
+ * This can happen due to hash collision. In such case just
+ * relying on btf_dedup_is_equiv() would lead to potentially
+ * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because
+ * FWD and compatible STRUCT/UNION are considered equivalent.
+ */
+ cand_type = d->btf->types[cand_id];
+ if (!btf_shallow_equal_struct(t, cand_type))
+ continue;
+
+ btf_dedup_clear_hypot_map(d);
+ eq = btf_dedup_is_equiv(d, type_id, cand_id);
+ if (eq < 0)
+ return eq;
+ if (!eq)
+ continue;
+ new_id = cand_id;
+ btf_dedup_merge_hypot_map(d);
+ break;
+ }
+
+ d->map[type_id] = new_id;
+ if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int btf_dedup_struct_types(struct btf_dedup *d)
+{
+ int i, err;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ err = btf_dedup_struct_type(d, i);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+/*
+ * Deduplicate reference type.
+ *
+ * Once all primitive and struct/union types got deduplicated, we can easily
+ * deduplicate all other (reference) BTF types. This is done in two steps:
+ *
+ * 1. Resolve all referenced type IDs into their canonical type IDs. This
+ * resolution can be done either immediately for primitive or struct/union types
+ * (because they were deduped in previous two phases) or recursively for
+ * reference types. Recursion will always terminate at either primitive or
+ * struct/union type, at which point we can "unwind" chain of reference types
+ * one by one. There is no danger of encountering cycles because in C type
+ * system the only way to form type cycle is through struct/union, so any chain
+ * of reference types, even those taking part in a type cycle, will inevitably
+ * reach struct/union at some point.
+ *
+ * 2. Once all referenced type IDs are resolved into canonical ones, BTF type
+ * becomes "stable", in the sense that no further deduplication will cause
+ * any changes to it. With that, it's now possible to calculate type's signature
+ * hash (this time taking into account referenced type IDs) and loop over all
+ * potential canonical representatives. If no match was found, current type
+ * will become canonical representative of itself and will be added into
+ * btf_dedup->dedup_table as another possible canonical representative.
+ */
+static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
+{
+ struct hashmap_entry *hash_entry;
+ __u32 new_id = type_id, cand_id;
+ struct btf_type *t, *cand;
+ /* if we don't find equivalent type, then we are representative type */
+ int ref_type_id;
+ long h;
+
+ if (d->map[type_id] == BTF_IN_PROGRESS_ID)
+ return -ELOOP;
+ if (d->map[type_id] <= BTF_MAX_NR_TYPES)
+ return resolve_type_id(d, type_id);
+
+ t = d->btf->types[type_id];
+ d->map[type_id] = BTF_IN_PROGRESS_ID;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ ref_type_id = btf_dedup_ref_type(d, t->type);
+ if (ref_type_id < 0)
+ return ref_type_id;
+ t->type = ref_type_id;
+
+ h = btf_hash_common(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_common(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ }
+ break;
+
+ case BTF_KIND_ARRAY: {
+ struct btf_array *info = btf_array(t);
+
+ ref_type_id = btf_dedup_ref_type(d, info->type);
+ if (ref_type_id < 0)
+ return ref_type_id;
+ info->type = ref_type_id;
+
+ ref_type_id = btf_dedup_ref_type(d, info->index_type);
+ if (ref_type_id < 0)
+ return ref_type_id;
+ info->index_type = ref_type_id;
+
+ h = btf_hash_array(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_array(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ }
+ break;
+ }
+
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *param;
+ __u16 vlen;
+ int i;
+
+ ref_type_id = btf_dedup_ref_type(d, t->type);
+ if (ref_type_id < 0)
+ return ref_type_id;
+ t->type = ref_type_id;
+
+ vlen = btf_vlen(t);
+ param = btf_params(t);
+ for (i = 0; i < vlen; i++) {
+ ref_type_id = btf_dedup_ref_type(d, param->type);
+ if (ref_type_id < 0)
+ return ref_type_id;
+ param->type = ref_type_id;
+ param++;
+ }
+
+ h = btf_hash_fnproto(t);
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
+ if (btf_equal_fnproto(t, cand)) {
+ new_id = cand_id;
+ break;
+ }
+ }
+ break;
+ }
+
+ default:
+ return -EINVAL;
+ }
+
+ d->map[type_id] = new_id;
+ if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+ return -ENOMEM;
+
+ return new_id;
+}
+
+static int btf_dedup_ref_types(struct btf_dedup *d)
+{
+ int i, err;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ err = btf_dedup_ref_type(d, i);
+ if (err < 0)
+ return err;
+ }
+ /* we won't need d->dedup_table anymore */
+ hashmap__free(d->dedup_table);
+ d->dedup_table = NULL;
+ return 0;
+}
+
+/*
+ * Compact types.
+ *
+ * After we established for each type its corresponding canonical representative
+ * type, we now can eliminate types that are not canonical and leave only
+ * canonical ones layed out sequentially in memory by copying them over
+ * duplicates. During compaction btf_dedup->hypot_map array is reused to store
+ * a map from original type ID to a new compacted type ID, which will be used
+ * during next phase to "fix up" type IDs, referenced from struct/union and
+ * reference types.
+ */
+static int btf_dedup_compact_types(struct btf_dedup *d)
+{
+ struct btf_type **new_types;
+ __u32 next_type_id = 1;
+ char *types_start, *p;
+ int i, len;
+
+ /* we are going to reuse hypot_map to store compaction remapping */
+ d->hypot_map[0] = 0;
+ for (i = 1; i <= d->btf->nr_types; i++)
+ d->hypot_map[i] = BTF_UNPROCESSED_ID;
+
+ types_start = d->btf->nohdr_data + d->btf->hdr->type_off;
+ p = types_start;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ if (d->map[i] != i)
+ continue;
+
+ len = btf_type_size(d->btf->types[i]);
+ if (len < 0)
+ return len;
+
+ memmove(p, d->btf->types[i], len);
+ d->hypot_map[i] = next_type_id;
+ d->btf->types[next_type_id] = (struct btf_type *)p;
+ p += len;
+ next_type_id++;
+ }
+
+ /* shrink struct btf's internal types index and update btf_header */
+ d->btf->nr_types = next_type_id - 1;
+ d->btf->types_size = d->btf->nr_types;
+ d->btf->hdr->type_len = p - types_start;
+ new_types = realloc(d->btf->types,
+ (1 + d->btf->nr_types) * sizeof(struct btf_type *));
+ if (!new_types)
+ return -ENOMEM;
+ d->btf->types = new_types;
+
+ /* make sure string section follows type information without gaps */
+ d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data;
+ memmove(p, d->btf->strings, d->btf->hdr->str_len);
+ d->btf->strings = p;
+ p += d->btf->hdr->str_len;
+
+ d->btf->data_size = p - (char *)d->btf->data;
+ return 0;
+}
+
+/*
+ * Figure out final (deduplicated and compacted) type ID for provided original
+ * `type_id` by first resolving it into corresponding canonical type ID and
+ * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map,
+ * which is populated during compaction phase.
+ */
+static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
+{
+ __u32 resolved_type_id, new_type_id;
+
+ resolved_type_id = resolve_type_id(d, type_id);
+ new_type_id = d->hypot_map[resolved_type_id];
+ if (new_type_id > BTF_MAX_NR_TYPES)
+ return -EINVAL;
+ return new_type_id;
+}
+
+/*
+ * Remap referenced type IDs into deduped type IDs.
+ *
+ * After BTF types are deduplicated and compacted, their final type IDs may
+ * differ from original ones. The map from original to a corresponding
+ * deduped type ID is stored in btf_dedup->hypot_map and is populated during
+ * compaction phase. During remapping phase we are rewriting all type IDs
+ * referenced from any BTF type (e.g., struct fields, func proto args, etc) to
+ * their final deduped type IDs.
+ */
+static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
+{
+ struct btf_type *t = d->btf->types[type_id];
+ int i, r;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ break;
+
+ case BTF_KIND_FWD:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
+ r = btf_dedup_remap_type_id(d, t->type);
+ if (r < 0)
+ return r;
+ t->type = r;
+ break;
+
+ case BTF_KIND_ARRAY: {
+ struct btf_array *arr_info = btf_array(t);
+
+ r = btf_dedup_remap_type_id(d, arr_info->type);
+ if (r < 0)
+ return r;
+ arr_info->type = r;
+ r = btf_dedup_remap_type_id(d, arr_info->index_type);
+ if (r < 0)
+ return r;
+ arr_info->index_type = r;
+ break;
+ }
+
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ struct btf_member *member = btf_members(t);
+ __u16 vlen = btf_vlen(t);
+
+ for (i = 0; i < vlen; i++) {
+ r = btf_dedup_remap_type_id(d, member->type);
+ if (r < 0)
+ return r;
+ member->type = r;
+ member++;
+ }
+ break;
+ }
+
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *param = btf_params(t);
+ __u16 vlen = btf_vlen(t);
+
+ r = btf_dedup_remap_type_id(d, t->type);
+ if (r < 0)
+ return r;
+ t->type = r;
+
+ for (i = 0; i < vlen; i++) {
+ r = btf_dedup_remap_type_id(d, param->type);
+ if (r < 0)
+ return r;
+ param->type = r;
+ param++;
+ }
+ break;
+ }
+
+ case BTF_KIND_DATASEC: {
+ struct btf_var_secinfo *var = btf_var_secinfos(t);
+ __u16 vlen = btf_vlen(t);
+
+ for (i = 0; i < vlen; i++) {
+ r = btf_dedup_remap_type_id(d, var->type);
+ if (r < 0)
+ return r;
+ var->type = r;
+ var++;
+ }
+ break;
+ }
+
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int btf_dedup_remap_types(struct btf_dedup *d)
+{
+ int i, r;
+
+ for (i = 1; i <= d->btf->nr_types; i++) {
+ r = btf_dedup_remap_type(d, i);
+ if (r < 0)
+ return r;
+ }
+ return 0;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4897e07..9cb44b4 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,26 +1,309 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
/* Copyright (c) 2018 Facebook */
-#ifndef __BPF_BTF_H
-#define __BPF_BTF_H
+#ifndef __LIBBPF_BTF_H
+#define __LIBBPF_BTF_H
+#include <stdarg.h>
+#include <linux/btf.h>
#include <linux/types.h>
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
#define BTF_ELF_SEC ".BTF"
+#define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
struct btf;
+struct btf_ext;
struct btf_type;
-typedef int (*btf_print_fn_t)(const char *, ...)
- __attribute__((format(printf, 1, 2)));
+struct bpf_object;
-void btf__free(struct btf *btf);
-struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
-__s32 btf__find_by_name(const struct btf *btf, const char *type_name);
-const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
-__s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
-int btf__resolve_type(const struct btf *btf, __u32 type_id);
-int btf__fd(const struct btf *btf);
-const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+/*
+ * The .BTF.ext ELF section layout defined as
+ * struct btf_ext_header
+ * func_info subsection
+ *
+ * The func_info subsection layout:
+ * record size for struct bpf_func_info in the func_info subsection
+ * struct btf_sec_func_info for section #1
+ * a list of bpf_func_info records for section #1
+ * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ * but may not be identical
+ * struct btf_sec_func_info for section #2
+ * a list of bpf_func_info records for section #2
+ * ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+ __u16 magic;
+ __u8 version;
+ __u8 flags;
+ __u32 hdr_len;
+ /* All offsets are in bytes relative to the end of this header */
+ __u32 func_info_off;
+ __u32 func_info_len;
+ __u32 line_info_off;
+ __u32 line_info_len;
+
+ /* optional part of .BTF.ext header */
+ __u32 offset_reloc_off;
+ __u32 offset_reloc_len;
+};
+
+LIBBPF_API void btf__free(struct btf *btf);
+LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API struct btf *btf__parse_elf(const char *path,
+ struct btf_ext **btf_ext);
+LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
+LIBBPF_API int btf__load(struct btf *btf);
+LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
+ const char *type_name);
+LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
+ __u32 id);
+LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__fd(const struct btf *btf);
+LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
+LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
+ __u32 expected_key_size,
+ __u32 expected_value_size,
+ __u32 *key_type_id, __u32 *value_type_id);
+
+LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size);
+LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
+LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext,
+ __u32 *size);
+LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const char *sec_name, __u32 insns_cnt,
+ void **func_info, __u32 *cnt);
+LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const char *sec_name, __u32 insns_cnt,
+ void **line_info, __u32 *cnt);
+LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+
+struct btf_dedup_opts {
+ unsigned int dedup_table_size;
+ bool dont_resolve_fwds;
+};
+
+LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
+ const struct btf_dedup_opts *opts);
+
+struct btf_dump;
+
+struct btf_dump_opts {
+ void *ctx;
+};
+
+typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
+
+LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const struct btf_dump_opts *opts,
+ btf_dump_printf_fn_t printf_fn);
+LIBBPF_API void btf_dump__free(struct btf_dump *d);
+
+LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
+
+/*
+ * A set of helpers for easier BTF types handling
+ */
+static inline __u16 btf_kind(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info);
+}
+
+static inline __u16 btf_vlen(const struct btf_type *t)
+{
+ return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_kflag(const struct btf_type *t)
+{
+ return BTF_INFO_KFLAG(t->info);
+}
+
+static inline bool btf_is_int(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_INT;
+}
+
+static inline bool btf_is_ptr(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_PTR;
+}
+
+static inline bool btf_is_array(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_is_struct(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_STRUCT;
+}
+
+static inline bool btf_is_union(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_composite(const struct btf_type *t)
+{
+ __u16 kind = btf_kind(t);
+
+ return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_enum(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_is_fwd(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_FWD;
+}
+
+static inline bool btf_is_typedef(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_TYPEDEF;
+}
+
+static inline bool btf_is_volatile(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_VOLATILE;
+}
+
+static inline bool btf_is_const(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_CONST;
+}
+
+static inline bool btf_is_restrict(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_mod(const struct btf_type *t)
+{
+ __u16 kind = btf_kind(t);
+
+ return kind == BTF_KIND_VOLATILE ||
+ kind == BTF_KIND_CONST ||
+ kind == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_func(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_FUNC;
+}
+
+static inline bool btf_is_func_proto(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_FUNC_PROTO;
+}
+
+static inline bool btf_is_var(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_VAR;
+}
+
+static inline bool btf_is_datasec(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_DATASEC;
+}
+
+static inline __u8 btf_int_encoding(const struct btf_type *t)
+{
+ return BTF_INT_ENCODING(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_offset(const struct btf_type *t)
+{
+ return BTF_INT_OFFSET(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+ return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
+static inline struct btf_array *btf_array(const struct btf_type *t)
+{
+ return (struct btf_array *)(t + 1);
+}
+
+static inline struct btf_enum *btf_enum(const struct btf_type *t)
+{
+ return (struct btf_enum *)(t + 1);
+}
+
+static inline struct btf_member *btf_members(const struct btf_type *t)
+{
+ return (struct btf_member *)(t + 1);
+}
+
+/* Get bit offset of a member with specified index. */
+static inline __u32 btf_member_bit_offset(const struct btf_type *t,
+ __u32 member_idx)
+{
+ const struct btf_member *m = btf_members(t) + member_idx;
+ bool kflag = btf_kflag(t);
+
+ return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+}
+/*
+ * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or
+ * BTF_KIND_UNION. If member is not a bitfield, zero is returned.
+ */
+static inline __u32 btf_member_bitfield_size(const struct btf_type *t,
+ __u32 member_idx)
+{
+ const struct btf_member *m = btf_members(t) + member_idx;
+ bool kflag = btf_kflag(t);
+
+ return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+}
+
+static inline struct btf_param *btf_params(const struct btf_type *t)
+{
+ return (struct btf_param *)(t + 1);
+}
+
+static inline struct btf_var *btf_var(const struct btf_type *t)
+{
+ return (struct btf_var *)(t + 1);
+}
+
+static inline struct btf_var_secinfo *
+btf_var_secinfos(const struct btf_type *t)
+{
+ return (struct btf_var_secinfo *)(t + 1);
+}
+
+#ifdef __cplusplus
+} /* extern "C" */
#endif
+
+#endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
new file mode 100644
index 0000000..ede55fe
--- /dev/null
+++ b/tools/lib/bpf/btf_dump.c
@@ -0,0 +1,1369 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C type converter.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include "btf.h"
+#include "hashmap.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
+static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
+
+static const char *pfx(int lvl)
+{
+ return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl];
+}
+
+enum btf_dump_type_order_state {
+ NOT_ORDERED,
+ ORDERING,
+ ORDERED,
+};
+
+enum btf_dump_type_emit_state {
+ NOT_EMITTED,
+ EMITTING,
+ EMITTED,
+};
+
+/* per-type auxiliary state */
+struct btf_dump_type_aux_state {
+ /* topological sorting state */
+ enum btf_dump_type_order_state order_state: 2;
+ /* emitting state used to determine the need for forward declaration */
+ enum btf_dump_type_emit_state emit_state: 2;
+ /* whether forward declaration was already emitted */
+ __u8 fwd_emitted: 1;
+ /* whether unique non-duplicate name was already assigned */
+ __u8 name_resolved: 1;
+ /* whether type is referenced from any other type */
+ __u8 referenced: 1;
+};
+
+struct btf_dump {
+ const struct btf *btf;
+ const struct btf_ext *btf_ext;
+ btf_dump_printf_fn_t printf_fn;
+ struct btf_dump_opts opts;
+
+ /* per-type auxiliary state */
+ struct btf_dump_type_aux_state *type_states;
+ /* per-type optional cached unique name, must be freed, if present */
+ const char **cached_names;
+
+ /* topo-sorted list of dependent type definitions */
+ __u32 *emit_queue;
+ int emit_queue_cap;
+ int emit_queue_cnt;
+
+ /*
+ * stack of type declarations (e.g., chain of modifiers, arrays,
+ * funcs, etc)
+ */
+ __u32 *decl_stack;
+ int decl_stack_cap;
+ int decl_stack_cnt;
+
+ /* maps struct/union/enum name to a number of name occurrences */
+ struct hashmap *type_names;
+ /*
+ * maps typedef identifiers and enum value names to a number of such
+ * name occurrences
+ */
+ struct hashmap *ident_names;
+};
+
+static size_t str_hash_fn(const void *key, void *ctx)
+{
+ const char *s = key;
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
+static bool str_equal_fn(const void *a, const void *b, void *ctx)
+{
+ return strcmp(a, b) == 0;
+}
+
+static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
+{
+ return btf__name_by_offset(d->btf, name_off);
+}
+
+static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ d->printf_fn(d->opts.ctx, fmt, args);
+ va_end(args);
+}
+
+struct btf_dump *btf_dump__new(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const struct btf_dump_opts *opts,
+ btf_dump_printf_fn_t printf_fn)
+{
+ struct btf_dump *d;
+ int err;
+
+ d = calloc(1, sizeof(struct btf_dump));
+ if (!d)
+ return ERR_PTR(-ENOMEM);
+
+ d->btf = btf;
+ d->btf_ext = btf_ext;
+ d->printf_fn = printf_fn;
+ d->opts.ctx = opts ? opts->ctx : NULL;
+
+ d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
+ if (IS_ERR(d->type_names)) {
+ err = PTR_ERR(d->type_names);
+ d->type_names = NULL;
+ btf_dump__free(d);
+ return ERR_PTR(err);
+ }
+ d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
+ if (IS_ERR(d->ident_names)) {
+ err = PTR_ERR(d->ident_names);
+ d->ident_names = NULL;
+ btf_dump__free(d);
+ return ERR_PTR(err);
+ }
+
+ return d;
+}
+
+void btf_dump__free(struct btf_dump *d)
+{
+ int i, cnt;
+
+ if (!d)
+ return;
+
+ free(d->type_states);
+ if (d->cached_names) {
+ /* any set cached name is owned by us and should be freed */
+ for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) {
+ if (d->cached_names[i])
+ free((void *)d->cached_names[i]);
+ }
+ }
+ free(d->cached_names);
+ free(d->emit_queue);
+ free(d->decl_stack);
+ hashmap__free(d->type_names);
+ hashmap__free(d->ident_names);
+
+ free(d);
+}
+
+static int btf_dump_mark_referenced(struct btf_dump *d);
+static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr);
+static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id);
+
+/*
+ * Dump BTF type in a compilable C syntax, including all the necessary
+ * dependent types, necessary for compilation. If some of the dependent types
+ * were already emitted as part of previous btf_dump__dump_type() invocation
+ * for another type, they won't be emitted again. This API allows callers to
+ * filter out BTF types according to user-defined criterias and emitted only
+ * minimal subset of types, necessary to compile everything. Full struct/union
+ * definitions will still be emitted, even if the only usage is through
+ * pointer and could be satisfied with just a forward declaration.
+ *
+ * Dumping is done in two high-level passes:
+ * 1. Topologically sort type definitions to satisfy C rules of compilation.
+ * 2. Emit type definitions in C syntax.
+ *
+ * Returns 0 on success; <0, otherwise.
+ */
+int btf_dump__dump_type(struct btf_dump *d, __u32 id)
+{
+ int err, i;
+
+ if (id > btf__get_nr_types(d->btf))
+ return -EINVAL;
+
+ /* type states are lazily allocated, as they might not be needed */
+ if (!d->type_states) {
+ d->type_states = calloc(1 + btf__get_nr_types(d->btf),
+ sizeof(d->type_states[0]));
+ if (!d->type_states)
+ return -ENOMEM;
+ d->cached_names = calloc(1 + btf__get_nr_types(d->btf),
+ sizeof(d->cached_names[0]));
+ if (!d->cached_names)
+ return -ENOMEM;
+
+ /* VOID is special */
+ d->type_states[0].order_state = ORDERED;
+ d->type_states[0].emit_state = EMITTED;
+
+ /* eagerly determine referenced types for anon enums */
+ err = btf_dump_mark_referenced(d);
+ if (err)
+ return err;
+ }
+
+ d->emit_queue_cnt = 0;
+ err = btf_dump_order_type(d, id, false);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i < d->emit_queue_cnt; i++)
+ btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/);
+
+ return 0;
+}
+
+/*
+ * Mark all types that are referenced from any other type. This is used to
+ * determine top-level anonymous enums that need to be emitted as an
+ * independent type declarations.
+ * Anonymous enums come in two flavors: either embedded in a struct's field
+ * definition, in which case they have to be declared inline as part of field
+ * type declaration; or as a top-level anonymous enum, typically used for
+ * declaring global constants. It's impossible to distinguish between two
+ * without knowning whether given enum type was referenced from other type:
+ * top-level anonymous enum won't be referenced by anything, while embedded
+ * one will.
+ */
+static int btf_dump_mark_referenced(struct btf_dump *d)
+{
+ int i, j, n = btf__get_nr_types(d->btf);
+ const struct btf_type *t;
+ __u16 vlen;
+
+ for (i = 1; i <= n; i++) {
+ t = btf__type_by_id(d->btf, i);
+ vlen = btf_vlen(t);
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ break;
+
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
+ d->type_states[t->type].referenced = 1;
+ break;
+
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = btf_array(t);
+
+ d->type_states[a->index_type].referenced = 1;
+ d->type_states[a->type].referenced = 1;
+ break;
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = btf_members(t);
+
+ for (j = 0; j < vlen; j++, m++)
+ d->type_states[m->type].referenced = 1;
+ break;
+ }
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+
+ for (j = 0; j < vlen; j++, p++)
+ d->type_states[p->type].referenced = 1;
+ break;
+ }
+ case BTF_KIND_DATASEC: {
+ const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+ for (j = 0; j < vlen; j++, v++)
+ d->type_states[v->type].referenced = 1;
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
+{
+ __u32 *new_queue;
+ size_t new_cap;
+
+ if (d->emit_queue_cnt >= d->emit_queue_cap) {
+ new_cap = max(16, d->emit_queue_cap * 3 / 2);
+ new_queue = realloc(d->emit_queue,
+ new_cap * sizeof(new_queue[0]));
+ if (!new_queue)
+ return -ENOMEM;
+ d->emit_queue = new_queue;
+ d->emit_queue_cap = new_cap;
+ }
+
+ d->emit_queue[d->emit_queue_cnt++] = id;
+ return 0;
+}
+
+/*
+ * Determine order of emitting dependent types and specified type to satisfy
+ * C compilation rules. This is done through topological sorting with an
+ * additional complication which comes from C rules. The main idea for C is
+ * that if some type is "embedded" into a struct/union, it's size needs to be
+ * known at the time of definition of containing type. E.g., for:
+ *
+ * struct A {};
+ * struct B { struct A x; }
+ *
+ * struct A *HAS* to be defined before struct B, because it's "embedded",
+ * i.e., it is part of struct B layout. But in the following case:
+ *
+ * struct A;
+ * struct B { struct A *x; }
+ * struct A {};
+ *
+ * it's enough to just have a forward declaration of struct A at the time of
+ * struct B definition, as struct B has a pointer to struct A, so the size of
+ * field x is known without knowing struct A size: it's sizeof(void *).
+ *
+ * Unfortunately, there are some trickier cases we need to handle, e.g.:
+ *
+ * struct A {}; // if this was forward-declaration: compilation error
+ * struct B {
+ * struct { // anonymous struct
+ * struct A y;
+ * } *x;
+ * };
+ *
+ * In this case, struct B's field x is a pointer, so it's size is known
+ * regardless of the size of (anonymous) struct it points to. But because this
+ * struct is anonymous and thus defined inline inside struct B, *and* it
+ * embeds struct A, compiler requires full definition of struct A to be known
+ * before struct B can be defined. This creates a transitive dependency
+ * between struct A and struct B. If struct A was forward-declared before
+ * struct B definition and fully defined after struct B definition, that would
+ * trigger compilation error.
+ *
+ * All this means that while we are doing topological sorting on BTF type
+ * graph, we need to determine relationships between different types (graph
+ * nodes):
+ * - weak link (relationship) between X and Y, if Y *CAN* be
+ * forward-declared at the point of X definition;
+ * - strong link, if Y *HAS* to be fully-defined before X can be defined.
+ *
+ * The rule is as follows. Given a chain of BTF types from X to Y, if there is
+ * BTF_KIND_PTR type in the chain and at least one non-anonymous type
+ * Z (excluding X, including Y), then link is weak. Otherwise, it's strong.
+ * Weak/strong relationship is determined recursively during DFS traversal and
+ * is returned as a result from btf_dump_order_type().
+ *
+ * btf_dump_order_type() is trying to avoid unnecessary forward declarations,
+ * but it is not guaranteeing that no extraneous forward declarations will be
+ * emitted.
+ *
+ * To avoid extra work, algorithm marks some of BTF types as ORDERED, when
+ * it's done with them, but not for all (e.g., VOLATILE, CONST, RESTRICT,
+ * ARRAY, FUNC_PROTO), as weak/strong semantics for those depends on the
+ * entire graph path, so depending where from one came to that BTF type, it
+ * might cause weak or strong ordering. For types like STRUCT/UNION/INT/ENUM,
+ * once they are processed, there is no need to do it again, so they are
+ * marked as ORDERED. We can mark PTR as ORDERED as well, as it semi-forces
+ * weak link, unless subsequent referenced STRUCT/UNION/ENUM is anonymous. But
+ * in any case, once those are processed, no need to do it again, as the
+ * result won't change.
+ *
+ * Returns:
+ * - 1, if type is part of strong link (so there is strong topological
+ * ordering requirements);
+ * - 0, if type is part of weak link (so can be satisfied through forward
+ * declaration);
+ * - <0, on error (e.g., unsatisfiable type loop detected).
+ */
+static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
+{
+ /*
+ * Order state is used to detect strong link cycles, but only for BTF
+ * kinds that are or could be an independent definition (i.e.,
+ * stand-alone fwd decl, enum, typedef, struct, union). Ptrs, arrays,
+ * func_protos, modifiers are just means to get to these definitions.
+ * Int/void don't need definitions, they are assumed to be always
+ * properly defined. We also ignore datasec, var, and funcs for now.
+ * So for all non-defining kinds, we never even set ordering state,
+ * for defining kinds we set ORDERING and subsequently ORDERED if it
+ * forms a strong link.
+ */
+ struct btf_dump_type_aux_state *tstate = &d->type_states[id];
+ const struct btf_type *t;
+ __u16 vlen;
+ int err, i;
+
+ /* return true, letting typedefs know that it's ok to be emitted */
+ if (tstate->order_state == ORDERED)
+ return 1;
+
+ t = btf__type_by_id(d->btf, id);
+
+ if (tstate->order_state == ORDERING) {
+ /* type loop, but resolvable through fwd declaration */
+ if (btf_is_composite(t) && through_ptr && t->name_off != 0)
+ return 0;
+ pr_warning("unsatisfiable type cycle, id:[%u]\n", id);
+ return -ELOOP;
+ }
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_INT:
+ tstate->order_state = ORDERED;
+ return 0;
+
+ case BTF_KIND_PTR:
+ err = btf_dump_order_type(d, t->type, true);
+ tstate->order_state = ORDERED;
+ return err;
+
+ case BTF_KIND_ARRAY:
+ return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = btf_members(t);
+ /*
+ * struct/union is part of strong link, only if it's embedded
+ * (so no ptr in a path) or it's anonymous (so has to be
+ * defined inline, even if declared through ptr)
+ */
+ if (through_ptr && t->name_off != 0)
+ return 0;
+
+ tstate->order_state = ORDERING;
+
+ vlen = btf_vlen(t);
+ for (i = 0; i < vlen; i++, m++) {
+ err = btf_dump_order_type(d, m->type, false);
+ if (err < 0)
+ return err;
+ }
+
+ if (t->name_off != 0) {
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err < 0)
+ return err;
+ }
+
+ tstate->order_state = ORDERED;
+ return 1;
+ }
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ /*
+ * non-anonymous or non-referenced enums are top-level
+ * declarations and should be emitted. Same logic can be
+ * applied to FWDs, it won't hurt anyways.
+ */
+ if (t->name_off != 0 || !tstate->referenced) {
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err)
+ return err;
+ }
+ tstate->order_state = ORDERED;
+ return 1;
+
+ case BTF_KIND_TYPEDEF: {
+ int is_strong;
+
+ is_strong = btf_dump_order_type(d, t->type, through_ptr);
+ if (is_strong < 0)
+ return is_strong;
+
+ /* typedef is similar to struct/union w.r.t. fwd-decls */
+ if (through_ptr && !is_strong)
+ return 0;
+
+ /* typedef is always a named definition */
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err)
+ return err;
+
+ d->type_states[id].order_state = ORDERED;
+ return 1;
+ }
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return btf_dump_order_type(d, t->type, through_ptr);
+
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+ bool is_strong;
+
+ err = btf_dump_order_type(d, t->type, through_ptr);
+ if (err < 0)
+ return err;
+ is_strong = err > 0;
+
+ vlen = btf_vlen(t);
+ for (i = 0; i < vlen; i++, p++) {
+ err = btf_dump_order_type(d, p->type, through_ptr);
+ if (err < 0)
+ return err;
+ if (err > 0)
+ is_strong = true;
+ }
+ return is_strong;
+ }
+ case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
+ case BTF_KIND_DATASEC:
+ d->type_states[id].order_state = ORDERED;
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl);
+
+static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl);
+
+static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+
+static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl);
+
+/* a local view into a shared stack */
+struct id_stack {
+ const __u32 *ids;
+ int cnt;
+};
+
+static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
+ const char *fname, int lvl);
+static void btf_dump_emit_type_chain(struct btf_dump *d,
+ struct id_stack *decl_stack,
+ const char *fname, int lvl);
+
+static const char *btf_dump_type_name(struct btf_dump *d, __u32 id);
+static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id);
+static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
+ const char *orig_name);
+
+static bool btf_dump_is_blacklisted(struct btf_dump *d, __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, id);
+
+ /* __builtin_va_list is a compiler built-in, which causes compilation
+ * errors, when compiling w/ different compiler, then used to compile
+ * original code (e.g., GCC to compile kernel, Clang to use generated
+ * C header from BTF). As it is built-in, it should be already defined
+ * properly internally in compiler.
+ */
+ if (t->name_off == 0)
+ return false;
+ return strcmp(btf_name_of(d, t->name_off), "__builtin_va_list") == 0;
+}
+
+/*
+ * Emit C-syntax definitions of types from chains of BTF types.
+ *
+ * High-level handling of determining necessary forward declarations are handled
+ * by btf_dump_emit_type() itself, but all nitty-gritty details of emitting type
+ * declarations/definitions in C syntax are handled by a combo of
+ * btf_dump_emit_type_decl()/btf_dump_emit_type_chain() w/ delegation to
+ * corresponding btf_dump_emit_*_{def,fwd}() functions.
+ *
+ * We also keep track of "containing struct/union type ID" to determine when
+ * we reference it from inside and thus can avoid emitting unnecessary forward
+ * declaration.
+ *
+ * This algorithm is designed in such a way, that even if some error occurs
+ * (either technical, e.g., out of memory, or logical, i.e., malformed BTF
+ * that doesn't comply to C rules completely), algorithm will try to proceed
+ * and produce as much meaningful output as possible.
+ */
+static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
+{
+ struct btf_dump_type_aux_state *tstate = &d->type_states[id];
+ bool top_level_def = cont_id == 0;
+ const struct btf_type *t;
+ __u16 kind;
+
+ if (tstate->emit_state == EMITTED)
+ return;
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind(t);
+
+ if (tstate->emit_state == EMITTING) {
+ if (tstate->fwd_emitted)
+ return;
+
+ switch (kind) {
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ /*
+ * if we are referencing a struct/union that we are
+ * part of - then no need for fwd declaration
+ */
+ if (id == cont_id)
+ return;
+ if (t->name_off == 0) {
+ pr_warning("anonymous struct/union loop, id:[%u]\n",
+ id);
+ return;
+ }
+ btf_dump_emit_struct_fwd(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->fwd_emitted = 1;
+ break;
+ case BTF_KIND_TYPEDEF:
+ /*
+ * for typedef fwd_emitted means typedef definition
+ * was emitted, but it can be used only for "weak"
+ * references through pointer only, not for embedding
+ */
+ if (!btf_dump_is_blacklisted(d, id)) {
+ btf_dump_emit_typedef_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ };
+ tstate->fwd_emitted = 1;
+ break;
+ default:
+ break;
+ }
+
+ return;
+ }
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_ENUM:
+ if (top_level_def) {
+ btf_dump_emit_enum_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ }
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_PTR:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ btf_dump_emit_type(d, t->type, cont_id);
+ break;
+ case BTF_KIND_ARRAY:
+ btf_dump_emit_type(d, btf_array(t)->type, cont_id);
+ break;
+ case BTF_KIND_FWD:
+ btf_dump_emit_fwd_def(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_TYPEDEF:
+ tstate->emit_state = EMITTING;
+ btf_dump_emit_type(d, t->type, id);
+ /*
+ * typedef can server as both definition and forward
+ * declaration; at this stage someone depends on
+ * typedef as a forward declaration (refers to it
+ * through pointer), so unless we already did it,
+ * emit typedef as a forward declaration
+ */
+ if (!tstate->fwd_emitted && !btf_dump_is_blacklisted(d, id)) {
+ btf_dump_emit_typedef_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ }
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ tstate->emit_state = EMITTING;
+ /* if it's a top-level struct/union definition or struct/union
+ * is anonymous, then in C we'll be emitting all fields and
+ * their types (as opposed to just `struct X`), so we need to
+ * make sure that all types, referenced from struct/union
+ * members have necessary forward-declarations, where
+ * applicable
+ */
+ if (top_level_def || t->name_off == 0) {
+ const struct btf_member *m = btf_members(t);
+ __u16 vlen = btf_vlen(t);
+ int i, new_cont_id;
+
+ new_cont_id = t->name_off == 0 ? cont_id : id;
+ for (i = 0; i < vlen; i++, m++)
+ btf_dump_emit_type(d, m->type, new_cont_id);
+ } else if (!tstate->fwd_emitted && id != cont_id) {
+ btf_dump_emit_struct_fwd(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->fwd_emitted = 1;
+ }
+
+ if (top_level_def) {
+ btf_dump_emit_struct_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ tstate->emit_state = EMITTED;
+ } else {
+ tstate->emit_state = NOT_EMITTED;
+ }
+ break;
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+ __u16 vlen = btf_vlen(t);
+ int i;
+
+ btf_dump_emit_type(d, t->type, cont_id);
+ for (i = 0; i < vlen; i++, p++)
+ btf_dump_emit_type(d, p->type, cont_id);
+
+ break;
+ }
+ default:
+ break;
+ }
+}
+
+static int btf_align_of(const struct btf *btf, __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
+ __u16 kind = btf_kind(t);
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ return min(sizeof(void *), t->size);
+ case BTF_KIND_PTR:
+ return sizeof(void *);
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return btf_align_of(btf, t->type);
+ case BTF_KIND_ARRAY:
+ return btf_align_of(btf, btf_array(t)->type);
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = btf_members(t);
+ __u16 vlen = btf_vlen(t);
+ int i, align = 1;
+
+ for (i = 0; i < vlen; i++, m++)
+ align = max(align, btf_align_of(btf, m->type));
+
+ return align;
+ }
+ default:
+ pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t));
+ return 1;
+ }
+}
+
+static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
+ const struct btf_type *t)
+{
+ const struct btf_member *m;
+ int align, i, bit_sz;
+ __u16 vlen;
+
+ align = btf_align_of(btf, id);
+ /* size of a non-packed struct has to be a multiple of its alignment*/
+ if (t->size % align)
+ return true;
+
+ m = btf_members(t);
+ vlen = btf_vlen(t);
+ /* all non-bitfield fields have to be naturally aligned */
+ for (i = 0; i < vlen; i++, m++) {
+ align = btf_align_of(btf, m->type);
+ bit_sz = btf_member_bitfield_size(t, i);
+ if (bit_sz == 0 && m->offset % (8 * align) != 0)
+ return true;
+ }
+
+ /*
+ * if original struct was marked as packed, but its layout is
+ * naturally aligned, we'll detect that it's not packed
+ */
+ return false;
+}
+
+static int chip_away_bits(int total, int at_most)
+{
+ return total % at_most ? : at_most;
+}
+
+static void btf_dump_emit_bit_padding(const struct btf_dump *d,
+ int cur_off, int m_off, int m_bit_sz,
+ int align, int lvl)
+{
+ int off_diff = m_off - cur_off;
+ int ptr_bits = sizeof(void *) * 8;
+
+ if (off_diff <= 0)
+ /* no gap */
+ return;
+ if (m_bit_sz == 0 && off_diff < align * 8)
+ /* natural padding will take care of a gap */
+ return;
+
+ while (off_diff > 0) {
+ const char *pad_type;
+ int pad_bits;
+
+ if (ptr_bits > 32 && off_diff > 32) {
+ pad_type = "long";
+ pad_bits = chip_away_bits(off_diff, ptr_bits);
+ } else if (off_diff > 16) {
+ pad_type = "int";
+ pad_bits = chip_away_bits(off_diff, 32);
+ } else if (off_diff > 8) {
+ pad_type = "short";
+ pad_bits = chip_away_bits(off_diff, 16);
+ } else {
+ pad_type = "char";
+ pad_bits = chip_away_bits(off_diff, 8);
+ }
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+ off_diff -= pad_bits;
+ }
+}
+
+static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ btf_dump_printf(d, "%s %s",
+ btf_is_struct(t) ? "struct" : "union",
+ btf_dump_type_name(d, id));
+}
+
+static void btf_dump_emit_struct_def(struct btf_dump *d,
+ __u32 id,
+ const struct btf_type *t,
+ int lvl)
+{
+ const struct btf_member *m = btf_members(t);
+ bool is_struct = btf_is_struct(t);
+ int align, i, packed, off = 0;
+ __u16 vlen = btf_vlen(t);
+
+ packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
+ align = packed ? 1 : btf_align_of(d->btf, id);
+
+ btf_dump_printf(d, "%s%s%s {",
+ is_struct ? "struct" : "union",
+ t->name_off ? " " : "",
+ btf_dump_type_name(d, id));
+
+ for (i = 0; i < vlen; i++, m++) {
+ const char *fname;
+ int m_off, m_sz;
+
+ fname = btf_name_of(d, m->name_off);
+ m_sz = btf_member_bitfield_size(t, i);
+ m_off = btf_member_bit_offset(t, i);
+ align = packed ? 1 : btf_align_of(d->btf, m->type);
+
+ btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+ btf_dump_printf(d, "\n%s", pfx(lvl + 1));
+ btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
+
+ if (m_sz) {
+ btf_dump_printf(d, ": %d", m_sz);
+ off = m_off + m_sz;
+ } else {
+ m_sz = max(0, btf__resolve_size(d->btf, m->type));
+ off = m_off + m_sz * 8;
+ }
+ btf_dump_printf(d, ";");
+ }
+
+ if (vlen)
+ btf_dump_printf(d, "\n");
+ btf_dump_printf(d, "%s}", pfx(lvl));
+ if (packed)
+ btf_dump_printf(d, " __attribute__((packed))");
+}
+
+static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id));
+}
+
+static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t,
+ int lvl)
+{
+ const struct btf_enum *v = btf_enum(t);
+ __u16 vlen = btf_vlen(t);
+ const char *name;
+ size_t dup_cnt;
+ int i;
+
+ btf_dump_printf(d, "enum%s%s",
+ t->name_off ? " " : "",
+ btf_dump_type_name(d, id));
+
+ if (vlen) {
+ btf_dump_printf(d, " {");
+ for (i = 0; i < vlen; i++, v++) {
+ name = btf_name_of(d, v->name_off);
+ /* enumerators share namespace with typedef idents */
+ dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
+ if (dup_cnt > 1) {
+ btf_dump_printf(d, "\n%s%s___%zu = %d,",
+ pfx(lvl + 1), name, dup_cnt,
+ (__s32)v->val);
+ } else {
+ btf_dump_printf(d, "\n%s%s = %d,",
+ pfx(lvl + 1), name,
+ (__s32)v->val);
+ }
+ }
+ btf_dump_printf(d, "\n%s}", pfx(lvl));
+ }
+}
+
+static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ const char *name = btf_dump_type_name(d, id);
+
+ if (btf_kflag(t))
+ btf_dump_printf(d, "union %s", name);
+ else
+ btf_dump_printf(d, "struct %s", name);
+}
+
+static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl)
+{
+ const char *name = btf_dump_ident_name(d, id);
+
+ btf_dump_printf(d, "typedef ");
+ btf_dump_emit_type_decl(d, t->type, name, lvl);
+}
+
+static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id)
+{
+ __u32 *new_stack;
+ size_t new_cap;
+
+ if (d->decl_stack_cnt >= d->decl_stack_cap) {
+ new_cap = max(16, d->decl_stack_cap * 3 / 2);
+ new_stack = realloc(d->decl_stack,
+ new_cap * sizeof(new_stack[0]));
+ if (!new_stack)
+ return -ENOMEM;
+ d->decl_stack = new_stack;
+ d->decl_stack_cap = new_cap;
+ }
+
+ d->decl_stack[d->decl_stack_cnt++] = id;
+
+ return 0;
+}
+
+/*
+ * Emit type declaration (e.g., field type declaration in a struct or argument
+ * declaration in function prototype) in correct C syntax.
+ *
+ * For most types it's trivial, but there are few quirky type declaration
+ * cases worth mentioning:
+ * - function prototypes (especially nesting of function prototypes);
+ * - arrays;
+ * - const/volatile/restrict for pointers vs other types.
+ *
+ * For a good discussion of *PARSING* C syntax (as a human), see
+ * Peter van der Linden's "Expert C Programming: Deep C Secrets",
+ * Ch.3 "Unscrambling Declarations in C".
+ *
+ * It won't help with BTF to C conversion much, though, as it's an opposite
+ * problem. So we came up with this algorithm in reverse to van der Linden's
+ * parsing algorithm. It goes from structured BTF representation of type
+ * declaration to a valid compilable C syntax.
+ *
+ * For instance, consider this C typedef:
+ * typedef const int * const * arr[10] arr_t;
+ * It will be represented in BTF with this chain of BTF types:
+ * [typedef] -> [array] -> [ptr] -> [const] -> [ptr] -> [const] -> [int]
+ *
+ * Notice how [const] modifier always goes before type it modifies in BTF type
+ * graph, but in C syntax, const/volatile/restrict modifiers are written to
+ * the right of pointers, but to the left of other types. There are also other
+ * quirks, like function pointers, arrays of them, functions returning other
+ * functions, etc.
+ *
+ * We handle that by pushing all the types to a stack, until we hit "terminal"
+ * type (int/enum/struct/union/fwd). Then depending on the kind of a type on
+ * top of a stack, modifiers are handled differently. Array/function pointers
+ * have also wildly different syntax and how nesting of them are done. See
+ * code for authoritative definition.
+ *
+ * To avoid allocating new stack for each independent chain of BTF types, we
+ * share one bigger stack, with each chain working only on its own local view
+ * of a stack frame. Some care is required to "pop" stack frames after
+ * processing type declaration chain.
+ */
+static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
+ const char *fname, int lvl)
+{
+ struct id_stack decl_stack;
+ const struct btf_type *t;
+ int err, stack_start;
+
+ stack_start = d->decl_stack_cnt;
+ for (;;) {
+ err = btf_dump_push_decl_stack_id(d, id);
+ if (err < 0) {
+ /*
+ * if we don't have enough memory for entire type decl
+ * chain, restore stack, emit warning, and try to
+ * proceed nevertheless
+ */
+ pr_warning("not enough memory for decl stack:%d", err);
+ d->decl_stack_cnt = stack_start;
+ return;
+ }
+
+ /* VOID */
+ if (id == 0)
+ break;
+
+ t = btf__type_by_id(d->btf, id);
+ switch (btf_kind(t)) {
+ case BTF_KIND_PTR:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_FUNC_PROTO:
+ id = t->type;
+ break;
+ case BTF_KIND_ARRAY:
+ id = btf_array(t)->type;
+ break;
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_TYPEDEF:
+ goto done;
+ default:
+ pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
+ btf_kind(t), id);
+ goto done;
+ }
+ }
+done:
+ /*
+ * We might be inside a chain of declarations (e.g., array of function
+ * pointers returning anonymous (so inlined) structs, having another
+ * array field). Each of those needs its own "stack frame" to handle
+ * emitting of declarations. Those stack frames are non-overlapping
+ * portions of shared btf_dump->decl_stack. To make it a bit nicer to
+ * handle this set of nested stacks, we create a view corresponding to
+ * our own "stack frame" and work with it as an independent stack.
+ * We'll need to clean up after emit_type_chain() returns, though.
+ */
+ decl_stack.ids = d->decl_stack + stack_start;
+ decl_stack.cnt = d->decl_stack_cnt - stack_start;
+ btf_dump_emit_type_chain(d, &decl_stack, fname, lvl);
+ /*
+ * emit_type_chain() guarantees that it will pop its entire decl_stack
+ * frame before returning. But it works with a read-only view into
+ * decl_stack, so it doesn't actually pop anything from the
+ * perspective of shared btf_dump->decl_stack, per se. We need to
+ * reset decl_stack state to how it was before us to avoid it growing
+ * all the time.
+ */
+ d->decl_stack_cnt = stack_start;
+}
+
+static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
+{
+ const struct btf_type *t;
+ __u32 id;
+
+ while (decl_stack->cnt) {
+ id = decl_stack->ids[decl_stack->cnt - 1];
+ t = btf__type_by_id(d->btf, id);
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_VOLATILE:
+ btf_dump_printf(d, "volatile ");
+ break;
+ case BTF_KIND_CONST:
+ btf_dump_printf(d, "const ");
+ break;
+ case BTF_KIND_RESTRICT:
+ btf_dump_printf(d, "restrict ");
+ break;
+ default:
+ return;
+ }
+ decl_stack->cnt--;
+ }
+}
+
+static void btf_dump_emit_name(const struct btf_dump *d,
+ const char *name, bool last_was_ptr)
+{
+ bool separate = name[0] && !last_was_ptr;
+
+ btf_dump_printf(d, "%s%s", separate ? " " : "", name);
+}
+
+static void btf_dump_emit_type_chain(struct btf_dump *d,
+ struct id_stack *decls,
+ const char *fname, int lvl)
+{
+ /*
+ * last_was_ptr is used to determine if we need to separate pointer
+ * asterisk (*) from previous part of type signature with space, so
+ * that we get `int ***`, instead of `int * * *`. We default to true
+ * for cases where we have single pointer in a chain. E.g., in ptr ->
+ * func_proto case. func_proto will start a new emit_type_chain call
+ * with just ptr, which should be emitted as (*) or (*<fname>), so we
+ * don't want to prepend space for that last pointer.
+ */
+ bool last_was_ptr = true;
+ const struct btf_type *t;
+ const char *name;
+ __u16 kind;
+ __u32 id;
+
+ while (decls->cnt) {
+ id = decls->ids[--decls->cnt];
+ if (id == 0) {
+ /* VOID is a special snowflake */
+ btf_dump_emit_mods(d, decls);
+ btf_dump_printf(d, "void");
+ last_was_ptr = false;
+ continue;
+ }
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind(t);
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ btf_dump_emit_mods(d, decls);
+ name = btf_name_of(d, t->name_off);
+ btf_dump_printf(d, "%s", name);
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ btf_dump_emit_mods(d, decls);
+ /* inline anonymous struct/union */
+ if (t->name_off == 0)
+ btf_dump_emit_struct_def(d, id, t, lvl);
+ else
+ btf_dump_emit_struct_fwd(d, id, t);
+ break;
+ case BTF_KIND_ENUM:
+ btf_dump_emit_mods(d, decls);
+ /* inline anonymous enum */
+ if (t->name_off == 0)
+ btf_dump_emit_enum_def(d, id, t, lvl);
+ else
+ btf_dump_emit_enum_fwd(d, id, t);
+ break;
+ case BTF_KIND_FWD:
+ btf_dump_emit_mods(d, decls);
+ btf_dump_emit_fwd_def(d, id, t);
+ break;
+ case BTF_KIND_TYPEDEF:
+ btf_dump_emit_mods(d, decls);
+ btf_dump_printf(d, "%s", btf_dump_ident_name(d, id));
+ break;
+ case BTF_KIND_PTR:
+ btf_dump_printf(d, "%s", last_was_ptr ? "*" : " *");
+ break;
+ case BTF_KIND_VOLATILE:
+ btf_dump_printf(d, " volatile");
+ break;
+ case BTF_KIND_CONST:
+ btf_dump_printf(d, " const");
+ break;
+ case BTF_KIND_RESTRICT:
+ btf_dump_printf(d, " restrict");
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = btf_array(t);
+ const struct btf_type *next_t;
+ __u32 next_id;
+ bool multidim;
+ /*
+ * GCC has a bug
+ * (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=8354)
+ * which causes it to emit extra const/volatile
+ * modifiers for an array, if array's element type has
+ * const/volatile modifiers. Clang doesn't do that.
+ * In general, it doesn't seem very meaningful to have
+ * a const/volatile modifier for array, so we are
+ * going to silently skip them here.
+ */
+ while (decls->cnt) {
+ next_id = decls->ids[decls->cnt - 1];
+ next_t = btf__type_by_id(d->btf, next_id);
+ if (btf_is_mod(next_t))
+ decls->cnt--;
+ else
+ break;
+ }
+
+ if (decls->cnt == 0) {
+ btf_dump_emit_name(d, fname, last_was_ptr);
+ btf_dump_printf(d, "[%u]", a->nelems);
+ return;
+ }
+
+ next_id = decls->ids[decls->cnt - 1];
+ next_t = btf__type_by_id(d->btf, next_id);
+ multidim = btf_is_array(next_t);
+ /* we need space if we have named non-pointer */
+ if (fname[0] && !last_was_ptr)
+ btf_dump_printf(d, " ");
+ /* no parentheses for multi-dimensional array */
+ if (!multidim)
+ btf_dump_printf(d, "(");
+ btf_dump_emit_type_chain(d, decls, fname, lvl);
+ if (!multidim)
+ btf_dump_printf(d, ")");
+ btf_dump_printf(d, "[%u]", a->nelems);
+ return;
+ }
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+ __u16 vlen = btf_vlen(t);
+ int i;
+
+ btf_dump_emit_mods(d, decls);
+ if (decls->cnt) {
+ btf_dump_printf(d, " (");
+ btf_dump_emit_type_chain(d, decls, fname, lvl);
+ btf_dump_printf(d, ")");
+ } else {
+ btf_dump_emit_name(d, fname, last_was_ptr);
+ }
+ btf_dump_printf(d, "(");
+ /*
+ * Clang for BPF target generates func_proto with no
+ * args as a func_proto with a single void arg (e.g.,
+ * `int (*f)(void)` vs just `int (*f)()`). We are
+ * going to pretend there are no args for such case.
+ */
+ if (vlen == 1 && p->type == 0) {
+ btf_dump_printf(d, ")");
+ return;
+ }
+
+ for (i = 0; i < vlen; i++, p++) {
+ if (i > 0)
+ btf_dump_printf(d, ", ");
+
+ /* last arg of type void is vararg */
+ if (i == vlen - 1 && p->type == 0) {
+ btf_dump_printf(d, "...");
+ break;
+ }
+
+ name = btf_name_of(d, p->name_off);
+ btf_dump_emit_type_decl(d, p->type, name, lvl);
+ }
+
+ btf_dump_printf(d, ")");
+ return;
+ }
+ default:
+ pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
+ kind, id);
+ return;
+ }
+
+ last_was_ptr = kind == BTF_KIND_PTR;
+ }
+
+ btf_dump_emit_name(d, fname, last_was_ptr);
+}
+
+/* return number of duplicates (occurrences) of a given name */
+static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
+ const char *orig_name)
+{
+ size_t dup_cnt = 0;
+
+ hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+ dup_cnt++;
+ hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL);
+
+ return dup_cnt;
+}
+
+static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id,
+ struct hashmap *name_map)
+{
+ struct btf_dump_type_aux_state *s = &d->type_states[id];
+ const struct btf_type *t = btf__type_by_id(d->btf, id);
+ const char *orig_name = btf_name_of(d, t->name_off);
+ const char **cached_name = &d->cached_names[id];
+ size_t dup_cnt;
+
+ if (t->name_off == 0)
+ return "";
+
+ if (s->name_resolved)
+ return *cached_name ? *cached_name : orig_name;
+
+ dup_cnt = btf_dump_name_dups(d, name_map, orig_name);
+ if (dup_cnt > 1) {
+ const size_t max_len = 256;
+ char new_name[max_len];
+
+ snprintf(new_name, max_len, "%s___%zu", orig_name, dup_cnt);
+ *cached_name = strdup(new_name);
+ }
+
+ s->name_resolved = 1;
+ return *cached_name ? *cached_name : orig_name;
+}
+
+static const char *btf_dump_type_name(struct btf_dump *d, __u32 id)
+{
+ return btf_dump_resolve_name(d, id, d->type_names);
+}
+
+static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id)
+{
+ return btf_dump_resolve_name(d, id, d->ident_names);
+}
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
new file mode 100644
index 0000000..6122272
--- /dev/null
+++ b/tools/lib/bpf/hashmap.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+
+/* start with 4 buckets */
+#define HASHMAP_MIN_CAP_BITS 2
+
+static void hashmap_add_entry(struct hashmap_entry **pprev,
+ struct hashmap_entry *entry)
+{
+ entry->next = *pprev;
+ *pprev = entry;
+}
+
+static void hashmap_del_entry(struct hashmap_entry **pprev,
+ struct hashmap_entry *entry)
+{
+ *pprev = entry->next;
+ entry->next = NULL;
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn, void *ctx)
+{
+ map->hash_fn = hash_fn;
+ map->equal_fn = equal_fn;
+ map->ctx = ctx;
+
+ map->buckets = NULL;
+ map->cap = 0;
+ map->cap_bits = 0;
+ map->sz = 0;
+}
+
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn,
+ void *ctx)
+{
+ struct hashmap *map = malloc(sizeof(struct hashmap));
+
+ if (!map)
+ return ERR_PTR(-ENOMEM);
+ hashmap__init(map, hash_fn, equal_fn, ctx);
+ return map;
+}
+
+void hashmap__clear(struct hashmap *map)
+{
+ free(map->buckets);
+ map->cap = map->cap_bits = map->sz = 0;
+}
+
+void hashmap__free(struct hashmap *map)
+{
+ if (!map)
+ return;
+
+ hashmap__clear(map);
+ free(map);
+}
+
+size_t hashmap__size(const struct hashmap *map)
+{
+ return map->sz;
+}
+
+size_t hashmap__capacity(const struct hashmap *map)
+{
+ return map->cap;
+}
+
+static bool hashmap_needs_to_grow(struct hashmap *map)
+{
+ /* grow if empty or more than 75% filled */
+ return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap);
+}
+
+static int hashmap_grow(struct hashmap *map)
+{
+ struct hashmap_entry **new_buckets;
+ struct hashmap_entry *cur, *tmp;
+ size_t new_cap_bits, new_cap;
+ size_t h;
+ int bkt;
+
+ new_cap_bits = map->cap_bits + 1;
+ if (new_cap_bits < HASHMAP_MIN_CAP_BITS)
+ new_cap_bits = HASHMAP_MIN_CAP_BITS;
+
+ new_cap = 1UL << new_cap_bits;
+ new_buckets = calloc(new_cap, sizeof(new_buckets[0]));
+ if (!new_buckets)
+ return -ENOMEM;
+
+ hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+ h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits);
+ hashmap_add_entry(&new_buckets[h], cur);
+ }
+
+ map->cap = new_cap;
+ map->cap_bits = new_cap_bits;
+ free(map->buckets);
+ map->buckets = new_buckets;
+
+ return 0;
+}
+
+static bool hashmap_find_entry(const struct hashmap *map,
+ const void *key, size_t hash,
+ struct hashmap_entry ***pprev,
+ struct hashmap_entry **entry)
+{
+ struct hashmap_entry *cur, **prev_ptr;
+
+ if (!map->buckets)
+ return false;
+
+ for (prev_ptr = &map->buckets[hash], cur = *prev_ptr;
+ cur;
+ prev_ptr = &cur->next, cur = cur->next) {
+ if (map->equal_fn(cur->key, key, map->ctx)) {
+ if (pprev)
+ *pprev = prev_ptr;
+ *entry = cur;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+ enum hashmap_insert_strategy strategy,
+ const void **old_key, void **old_value)
+{
+ struct hashmap_entry *entry;
+ size_t h;
+ int err;
+
+ if (old_key)
+ *old_key = NULL;
+ if (old_value)
+ *old_value = NULL;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (strategy != HASHMAP_APPEND &&
+ hashmap_find_entry(map, key, h, NULL, &entry)) {
+ if (old_key)
+ *old_key = entry->key;
+ if (old_value)
+ *old_value = entry->value;
+
+ if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) {
+ entry->key = key;
+ entry->value = value;
+ return 0;
+ } else if (strategy == HASHMAP_ADD) {
+ return -EEXIST;
+ }
+ }
+
+ if (strategy == HASHMAP_UPDATE)
+ return -ENOENT;
+
+ if (hashmap_needs_to_grow(map)) {
+ err = hashmap_grow(map);
+ if (err)
+ return err;
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ }
+
+ entry = malloc(sizeof(struct hashmap_entry));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->key = key;
+ entry->value = value;
+ hashmap_add_entry(&map->buckets[h], entry);
+ map->sz++;
+
+ return 0;
+}
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+{
+ struct hashmap_entry *entry;
+ size_t h;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (!hashmap_find_entry(map, key, h, NULL, &entry))
+ return false;
+
+ if (value)
+ *value = entry->value;
+ return true;
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+ const void **old_key, void **old_value)
+{
+ struct hashmap_entry **pprev, *entry;
+ size_t h;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (!hashmap_find_entry(map, key, h, &pprev, &entry))
+ return false;
+
+ if (old_key)
+ *old_key = entry->key;
+ if (old_value)
+ *old_value = entry->value;
+
+ hashmap_del_entry(pprev, entry);
+ free(entry);
+ map->sz--;
+
+ return true;
+}
+
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
new file mode 100644
index 0000000..bae8879
--- /dev/null
+++ b/tools/lib/bpf/hashmap.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#ifndef __LIBBPF_HASHMAP_H
+#define __LIBBPF_HASHMAP_H
+
+#include <stdbool.h>
+#include <stddef.h>
+#ifdef __GLIBC__
+#include <bits/wordsize.h>
+#else
+#include <bits/reg.h>
+#endif
+#include "libbpf_internal.h"
+
+static inline size_t hash_bits(size_t h, int bits)
+{
+ /* shuffle bits and return requested number of upper bits */
+ return (h * 11400714819323198485llu) >> (__WORDSIZE - bits);
+}
+
+typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
+typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+
+struct hashmap_entry {
+ const void *key;
+ void *value;
+ struct hashmap_entry *next;
+};
+
+struct hashmap {
+ hashmap_hash_fn hash_fn;
+ hashmap_equal_fn equal_fn;
+ void *ctx;
+
+ struct hashmap_entry **buckets;
+ size_t cap;
+ size_t cap_bits;
+ size_t sz;
+};
+
+#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \
+ .hash_fn = (hash_fn), \
+ .equal_fn = (equal_fn), \
+ .ctx = (ctx), \
+ .buckets = NULL, \
+ .cap = 0, \
+ .cap_bits = 0, \
+ .sz = 0, \
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn, void *ctx);
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn,
+ void *ctx);
+void hashmap__clear(struct hashmap *map);
+void hashmap__free(struct hashmap *map);
+
+size_t hashmap__size(const struct hashmap *map);
+size_t hashmap__capacity(const struct hashmap *map);
+
+/*
+ * Hashmap insertion strategy:
+ * - HASHMAP_ADD - only add key/value if key doesn't exist yet;
+ * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise,
+ * update value;
+ * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do
+ * nothing and return -ENOENT;
+ * - HASHMAP_APPEND - always add key/value pair, even if key already exists.
+ * This turns hashmap into a multimap by allowing multiple values to be
+ * associated with the same key. Most useful read API for such hashmap is
+ * hashmap__for_each_key_entry() iteration. If hashmap__find() is still
+ * used, it will return last inserted key/value entry (first in a bucket
+ * chain).
+ */
+enum hashmap_insert_strategy {
+ HASHMAP_ADD,
+ HASHMAP_SET,
+ HASHMAP_UPDATE,
+ HASHMAP_APPEND,
+};
+
+/*
+ * hashmap__insert() adds key/value entry w/ various semantics, depending on
+ * provided strategy value. If a given key/value pair replaced already
+ * existing key/value pair, both old key and old value will be returned
+ * through old_key and old_value to allow calling code do proper memory
+ * management.
+ */
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+ enum hashmap_insert_strategy strategy,
+ const void **old_key, void **old_value);
+
+static inline int hashmap__add(struct hashmap *map,
+ const void *key, void *value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
+}
+
+static inline int hashmap__set(struct hashmap *map,
+ const void *key, void *value,
+ const void **old_key, void **old_value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_SET,
+ old_key, old_value);
+}
+
+static inline int hashmap__update(struct hashmap *map,
+ const void *key, void *value,
+ const void **old_key, void **old_value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_UPDATE,
+ old_key, old_value);
+}
+
+static inline int hashmap__append(struct hashmap *map,
+ const void *key, void *value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+ const void **old_key, void **old_value);
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+
+/*
+ * hashmap__for_each_entry - iterate over all entries in hashmap
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry(map, cur, bkt) \
+ for (bkt = 0; bkt < map->cap; bkt++) \
+ for (cur = map->buckets[bkt]; cur; cur = cur->next)
+
+/*
+ * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
+ * against removals
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @tmp: struct hashmap_entry * used as a temporary next cursor storage
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \
+ for (bkt = 0; bkt < map->cap; bkt++) \
+ for (cur = map->buckets[bkt]; \
+ cur && ({tmp = cur->next; true; }); \
+ cur = tmp)
+
+/*
+ * hashmap__for_each_key_entry - iterate over entries associated with given key
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @key: key to iterate entries for
+ */
+#define hashmap__for_each_key_entry(map, cur, _key) \
+ for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
+ map->cap_bits); \
+ map->buckets ? map->buckets[bkt] : NULL; }); \
+ cur; \
+ cur = cur->next) \
+ if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
+ for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
+ map->cap_bits); \
+ cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ cur && ({ tmp = cur->next; true; }); \
+ cur = tmp) \
+ if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#endif /* __LIBBPF_HASHMAP_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bdb9493..e027652 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/*
* Common eBPF ELF object loading operations.
@@ -7,22 +7,12 @@
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
* Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, see <http://www.gnu.org/licenses>
+ * Copyright (C) 2019 Isovalent, Inc.
*/
+#ifndef _GNU_SOURCE
#define _GNU_SOURCE
+#endif
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
@@ -30,19 +20,26 @@
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
+#include <endian.h>
#include <fcntl.h>
#include <errno.h>
-#include <perf-sys.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/btf.h>
+#include <linux/filter.h>
#include <linux/list.h>
#include <linux/limits.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
+#include <sys/utsname.h>
#include <tools/libc_compat.h>
#include <libelf.h>
#include <gelf.h>
@@ -51,6 +48,8 @@
#include "bpf.h"
#include "btf.h"
#include "str_error.h"
+#include "libbpf_internal.h"
+#include "hashmap.h"
#ifndef EM_BPF
#define EM_BPF 247
@@ -60,41 +59,43 @@
#define BPF_FS_MAGIC 0xcafe4a11
#endif
+/* vsprintf() in __base_pr() uses nonliteral format string. It may break
+ * compilation if user enables corresponding warning. Disable it explicitly.
+ */
+#pragma GCC diagnostic ignored "-Wformat-nonliteral"
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
-__printf(1, 2)
-static int __base_pr(const char *format, ...)
+static int __base_pr(enum libbpf_print_level level, const char *format,
+ va_list args)
{
- va_list args;
- int err;
+ if (level == LIBBPF_DEBUG)
+ return 0;
- va_start(args, format);
- err = vfprintf(stderr, format, args);
- va_end(args);
- return err;
+ return vfprintf(stderr, format, args);
}
-static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
-static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
-static __printf(1, 2) libbpf_print_fn_t __pr_debug;
+static libbpf_print_fn_t __libbpf_pr = __base_pr;
-#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(libbpf_print_fn_t warn,
- libbpf_print_fn_t info,
- libbpf_print_fn_t debug)
+libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn)
{
- __pr_warning = warn;
- __pr_info = info;
- __pr_debug = debug;
+ libbpf_print_fn_t old_print_fn = __libbpf_pr;
+
+ __libbpf_pr = fn;
+ return old_print_fn;
+}
+
+__printf(2, 3)
+void libbpf_print(enum libbpf_print_level level, const char *format, ...)
+{
+ va_list args;
+
+ if (!__libbpf_pr)
+ return;
+
+ va_start(args, format);
+ __libbpf_pr(level, format, args);
+ va_end(args);
}
#define STRERR_BUFSIZE 128
@@ -126,6 +127,22 @@
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
#endif
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
+struct bpf_capabilities {
+ /* v4.14: kernel support for program & map names. */
+ __u32 name:1;
+ /* v5.2: kernel support for global data sections. */
+ __u32 global_data:1;
+ /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+ __u32 btf_func:1;
+ /* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+ __u32 btf_datasec:1;
+};
+
/*
* bpf_prog should be a better name but it has been used in
* linux/filter.h.
@@ -136,6 +153,10 @@
char *name;
int prog_ifindex;
char *section_name;
+ /* section_name with / replaced by _; makes recursive pinning
+ * in bpf_object__pin_programs easier
+ */
+ char *pin_name;
struct bpf_insn *insns;
size_t insns_cnt, main_prog_cnt;
enum bpf_prog_type type;
@@ -144,6 +165,7 @@
enum {
RELO_LD64,
RELO_CALL,
+ RELO_DATA,
} type;
int insn_idx;
union {
@@ -152,6 +174,7 @@
};
} *reloc_desc;
int nr_reloc;
+ int log_level;
struct {
int nr;
@@ -164,30 +187,64 @@
bpf_program_clear_priv_t clear_priv;
enum bpf_attach_type expected_attach_type;
+ void *func_info;
+ __u32 func_info_rec_size;
+ __u32 func_info_cnt;
+
+ struct bpf_capabilities *caps;
+
+ void *line_info;
+ __u32 line_info_rec_size;
+ __u32 line_info_cnt;
+ __u32 prog_flags;
+};
+
+enum libbpf_map_type {
+ LIBBPF_MAP_UNSPEC,
+ LIBBPF_MAP_DATA,
+ LIBBPF_MAP_BSS,
+ LIBBPF_MAP_RODATA,
+};
+
+static const char * const libbpf_type_to_btf_name[] = {
+ [LIBBPF_MAP_DATA] = ".data",
+ [LIBBPF_MAP_BSS] = ".bss",
+ [LIBBPF_MAP_RODATA] = ".rodata",
};
struct bpf_map {
int fd;
char *name;
- size_t offset;
+ int sec_idx;
+ size_t sec_offset;
int map_ifindex;
+ int inner_map_fd;
struct bpf_map_def def;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
+ enum libbpf_map_type libbpf_type;
+};
+
+struct bpf_secdata {
+ void *rodata;
+ void *data;
};
static LIST_HEAD(bpf_objects_list);
struct bpf_object {
+ char name[BPF_OBJ_NAME_LEN];
char license[64];
- u32 kern_version;
+ __u32 kern_version;
struct bpf_program *programs;
size_t nr_programs;
struct bpf_map *maps;
size_t nr_maps;
+ size_t maps_cap;
+ struct bpf_secdata sections;
bool loaded;
bool has_pseudo_calls;
@@ -203,6 +260,9 @@
Elf *elf;
GElf_Ehdr ehdr;
Elf_Data *symbols;
+ Elf_Data *data;
+ Elf_Data *rodata;
+ Elf_Data *bss;
size_t strtabidx;
struct {
GElf_Shdr shdr;
@@ -210,7 +270,11 @@
} *reloc;
int nr_reloc;
int maps_shndx;
+ int btf_maps_shndx;
int text_shndx;
+ int data_shndx;
+ int rodata_shndx;
+ int bss_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
@@ -220,15 +284,18 @@
struct list_head list;
struct btf *btf;
+ struct btf_ext *btf_ext;
void *priv;
bpf_object_clear_priv_t clear_priv;
+ struct bpf_capabilities caps;
+
char path[];
};
#define obj_elf_valid(o) ((o)->efile.elf)
-static void bpf_program__unload(struct bpf_program *prog)
+void bpf_program__unload(struct bpf_program *prog)
{
int i;
@@ -249,6 +316,9 @@
prog->instances.nr = -1;
zfree(&prog->instances.fds);
+
+ zfree(&prog->func_info);
+ zfree(&prog->line_info);
}
static void bpf_program__exit(struct bpf_program *prog)
@@ -265,6 +335,7 @@
bpf_program__unload(prog);
zfree(&prog->name);
zfree(&prog->section_name);
+ zfree(&prog->pin_name);
zfree(&prog->insns);
zfree(&prog->reloc_desc);
@@ -273,16 +344,30 @@
prog->idx = -1;
}
+static char *__bpf_program__pin_name(struct bpf_program *prog)
+{
+ char *name, *p;
+
+ name = p = strdup(prog->section_name);
+ while ((p = strchr(p, '/')))
+ *p = '_';
+
+ return name;
+}
+
static int
bpf_program__init(void *data, size_t size, char *section_name, int idx,
struct bpf_program *prog)
{
- if (size < sizeof(struct bpf_insn)) {
- pr_warning("corrupted section '%s'\n", section_name);
+ const size_t bpf_insn_sz = sizeof(struct bpf_insn);
+
+ if (size == 0 || size % bpf_insn_sz) {
+ pr_warning("corrupted section '%s', size: %zu\n",
+ section_name, size);
return -EINVAL;
}
- bzero(prog, sizeof(*prog));
+ memset(prog, 0, sizeof(*prog));
prog->section_name = strdup(section_name);
if (!prog->section_name) {
@@ -291,19 +376,25 @@
goto errout;
}
+ prog->pin_name = __bpf_program__pin_name(prog);
+ if (!prog->pin_name) {
+ pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
+ idx, section_name);
+ goto errout;
+ }
+
prog->insns = malloc(size);
if (!prog->insns) {
pr_warning("failed to alloc insns for prog under section %s\n",
section_name);
goto errout;
}
- prog->insns_cnt = size / sizeof(struct bpf_insn);
- memcpy(prog->insns, data,
- prog->insns_cnt * sizeof(struct bpf_insn));
+ prog->insns_cnt = size / bpf_insn_sz;
+ memcpy(prog->insns, data, size);
prog->idx = idx;
prog->instances.fds = NULL;
prog->instances.nr = -1;
- prog->type = BPF_PROG_TYPE_KPROBE;
+ prog->type = BPF_PROG_TYPE_UNSPEC;
return 0;
errout:
@@ -322,6 +413,7 @@
if (err)
return err;
+ prog.caps = &obj->caps;
progs = obj->programs;
nr_progs = obj->nr_programs;
@@ -404,6 +496,7 @@
size_t obj_buf_sz)
{
struct bpf_object *obj;
+ char *end;
obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
if (!obj) {
@@ -412,10 +505,15 @@
}
strcpy(obj->path, path);
- obj->efile.fd = -1;
+ /* Using basename() GNU version which doesn't modify arg. */
+ strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
+ end = strchr(obj->name, '.');
+ if (end)
+ *end = 0;
+ obj->efile.fd = -1;
/*
- * Caller of this function should also calls
+ * Caller of this function should also call
* bpf_object__elf_finish() after data collection to return
* obj_buf to user. If not, we should duplicate the buffer to
* avoid user freeing them before elf finish.
@@ -423,6 +521,10 @@
obj->efile.obj_buf = obj_buf;
obj->efile.obj_buf_sz = obj_buf_sz;
obj->efile.maps_shndx = -1;
+ obj->efile.btf_maps_shndx = -1;
+ obj->efile.data_shndx = -1;
+ obj->efile.rodata_shndx = -1;
+ obj->efile.bss_shndx = -1;
obj->loaded = false;
@@ -441,6 +543,9 @@
obj->efile.elf = NULL;
}
obj->efile.symbols = NULL;
+ obj->efile.data = NULL;
+ obj->efile.rodata = NULL;
+ obj->efile.bss = NULL;
zfree(&obj->efile.reloc);
obj->efile.nr_reloc = 0;
@@ -469,37 +574,35 @@
} else {
obj->efile.fd = open(obj->path, O_RDONLY);
if (obj->efile.fd < 0) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = str_error(errno, errmsg, sizeof(errmsg));
+ char errmsg[STRERR_BUFSIZE], *cp;
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warning("failed to open %s: %s\n", obj->path, cp);
- return -errno;
+ return err;
}
obj->efile.elf = elf_begin(obj->efile.fd,
- LIBBPF_ELF_C_READ_MMAP,
- NULL);
+ LIBBPF_ELF_C_READ_MMAP, NULL);
}
if (!obj->efile.elf) {
- pr_warning("failed to open %s as ELF file\n",
- obj->path);
+ pr_warning("failed to open %s as ELF file\n", obj->path);
err = -LIBBPF_ERRNO__LIBELF;
goto errout;
}
if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
- pr_warning("failed to get EHDR from %s\n",
- obj->path);
+ pr_warning("failed to get EHDR from %s\n", obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
ep = &obj->efile.ehdr;
/* Old LLVM set e_machine to EM_NONE */
- if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
- pr_warning("%s is not an eBPF object file\n",
- obj->path);
+ if (ep->e_type != ET_REL ||
+ (ep->e_machine && ep->e_machine != EM_BPF)) {
+ pr_warning("%s is not an eBPF object file\n", obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
@@ -510,49 +613,33 @@
return err;
}
-static int
-bpf_object__check_endianness(struct bpf_object *obj)
+static int bpf_object__check_endianness(struct bpf_object *obj)
{
- static unsigned int const endian = 1;
-
- switch (obj->efile.ehdr.e_ident[EI_DATA]) {
- case ELFDATA2LSB:
- /* We are big endian, BPF obj is little endian. */
- if (*(unsigned char const *)&endian != 1)
- goto mismatch;
- break;
-
- case ELFDATA2MSB:
- /* We are little endian, BPF obj is big endian. */
- if (*(unsigned char const *)&endian != 0)
- goto mismatch;
- break;
- default:
- return -LIBBPF_ERRNO__ENDIAN;
- }
-
- return 0;
-
-mismatch:
- pr_warning("Error: endianness mismatch.\n");
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+ return 0;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
+ return 0;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+ pr_warning("endianness mismatch.\n");
return -LIBBPF_ERRNO__ENDIAN;
}
static int
-bpf_object__init_license(struct bpf_object *obj,
- void *data, size_t size)
+bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
{
- memcpy(obj->license, data,
- min(size, sizeof(obj->license) - 1));
+ 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_object__init_kversion(struct bpf_object *obj,
- void *data, size_t size)
+bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
{
- u32 kver;
+ __u32 kver;
if (size != sizeof(kver)) {
pr_warning("invalid kver section in %s\n", obj->path);
@@ -560,8 +647,7 @@
}
memcpy(&kver, data, sizeof(kver));
obj->kern_version = kver;
- pr_debug("kernel version of %s is %x\n", obj->path,
- obj->kern_version);
+ pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version);
return 0;
}
@@ -570,19 +656,249 @@
const struct bpf_map *a = _a;
const struct bpf_map *b = _b;
- return a->offset - b->offset;
+ if (a->sec_idx != b->sec_idx)
+ return a->sec_idx - b->sec_idx;
+ return a->sec_offset - b->sec_offset;
+}
+
+static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
+{
+ if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+ type == BPF_MAP_TYPE_HASH_OF_MAPS)
+ return true;
+ return false;
+}
+
+static int bpf_object_search_section_size(const struct bpf_object *obj,
+ const char *name, size_t *d_size)
+{
+ const GElf_Ehdr *ep = &obj->efile.ehdr;
+ Elf *elf = obj->efile.elf;
+ Elf_Scn *scn = NULL;
+ int idx = 0;
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ const char *sec_name;
+ Elf_Data *data;
+ GElf_Shdr sh;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
+ if (!sec_name) {
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ if (strcmp(name, sec_name))
+ continue;
+
+ data = elf_getdata(scn, 0);
+ if (!data) {
+ pr_warning("failed to get section(%d) data from %s(%s)\n",
+ idx, name, obj->path);
+ return -EIO;
+ }
+
+ *d_size = data->d_size;
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+ __u32 *size)
+{
+ int ret = -ENOENT;
+ size_t d_size;
+
+ *size = 0;
+ if (!name) {
+ return -EINVAL;
+ } else if (!strcmp(name, ".data")) {
+ if (obj->efile.data)
+ *size = obj->efile.data->d_size;
+ } else if (!strcmp(name, ".bss")) {
+ if (obj->efile.bss)
+ *size = obj->efile.bss->d_size;
+ } else if (!strcmp(name, ".rodata")) {
+ if (obj->efile.rodata)
+ *size = obj->efile.rodata->d_size;
+ } else {
+ ret = bpf_object_search_section_size(obj, name, &d_size);
+ if (!ret)
+ *size = d_size;
+ }
+
+ return *size ? 0 : ret;
+}
+
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+ __u32 *off)
+{
+ Elf_Data *symbols = obj->efile.symbols;
+ const char *sname;
+ size_t si;
+
+ if (!name || !off)
+ return -EINVAL;
+
+ for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
+ GElf_Sym sym;
+
+ if (!gelf_getsym(symbols, si, &sym))
+ continue;
+ if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
+ GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+ continue;
+
+ sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name);
+ if (!sname) {
+ pr_warning("failed to get sym name string for var %s\n",
+ name);
+ return -EIO;
+ }
+ if (strcmp(name, sname) == 0) {
+ *off = sym.st_value;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
+{
+ struct bpf_map *new_maps;
+ size_t new_cap;
+ int i;
+
+ if (obj->nr_maps < obj->maps_cap)
+ return &obj->maps[obj->nr_maps++];
+
+ new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
+ new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
+ if (!new_maps) {
+ pr_warning("alloc maps for object failed\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ obj->maps_cap = new_cap;
+ obj->maps = new_maps;
+
+ /* zero out new maps */
+ memset(obj->maps + obj->nr_maps, 0,
+ (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
+ /*
+ * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
+ * when failure (zclose won't close negative fd)).
+ */
+ for (i = obj->nr_maps; i < obj->maps_cap; i++) {
+ obj->maps[i].fd = -1;
+ obj->maps[i].inner_map_fd = -1;
+ }
+
+ return &obj->maps[obj->nr_maps++];
}
static int
-bpf_object__init_maps(struct bpf_object *obj)
+bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
+ int sec_idx, Elf_Data *data, void **data_buff)
{
- int i, map_idx, map_def_sz, nr_maps = 0;
- Elf_Scn *scn;
- Elf_Data *data;
+ char map_name[BPF_OBJ_NAME_LEN];
+ struct bpf_map_def *def;
+ struct bpf_map *map;
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map->libbpf_type = type;
+ map->sec_idx = sec_idx;
+ map->sec_offset = 0;
+ snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
+ libbpf_type_to_btf_name[type]);
+ map->name = strdup(map_name);
+ if (!map->name) {
+ pr_warning("failed to alloc map name\n");
+ return -ENOMEM;
+ }
+ pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
+
+ def = &map->def;
+ def->type = BPF_MAP_TYPE_ARRAY;
+ def->key_size = sizeof(int);
+ def->value_size = data->d_size;
+ def->max_entries = 1;
+ def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
+ if (data_buff) {
+ *data_buff = malloc(data->d_size);
+ if (!*data_buff) {
+ zfree(&map->name);
+ pr_warning("failed to alloc map content buffer\n");
+ return -ENOMEM;
+ }
+ memcpy(*data_buff, data->d_buf, data->d_size);
+ }
+
+ pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
+ return 0;
+}
+
+static int bpf_object__init_global_data_maps(struct bpf_object *obj)
+{
+ int err;
+
+ if (!obj->caps.global_data)
+ return 0;
+ /*
+ * Populate obj->maps with libbpf internal maps.
+ */
+ if (obj->efile.data_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
+ obj->efile.data_shndx,
+ obj->efile.data,
+ &obj->sections.data);
+ if (err)
+ return err;
+ }
+ if (obj->efile.rodata_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
+ obj->efile.rodata_shndx,
+ obj->efile.rodata,
+ &obj->sections.rodata);
+ if (err)
+ return err;
+ }
+ if (obj->efile.bss_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
+ obj->efile.bss_shndx,
+ obj->efile.bss, NULL);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
+{
Elf_Data *symbols = obj->efile.symbols;
+ int i, map_def_sz = 0, nr_maps = 0, nr_syms;
+ Elf_Data *data = NULL;
+ Elf_Scn *scn;
if (obj->efile.maps_shndx < 0)
- return -EINVAL;
+ return 0;
+
if (!symbols)
return -EINVAL;
@@ -602,7 +918,8 @@
*
* TODO: Detect array of map and report error.
*/
- for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ nr_syms = symbols->d_size / sizeof(GElf_Sym);
+ for (i = 0; i < nr_syms; i++) {
GElf_Sym sym;
if (!gelf_getsym(symbols, i, &sym))
@@ -611,15 +928,10 @@
continue;
nr_maps++;
}
-
- /* Alloc obj->maps and fill nr_maps. */
- pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
- nr_maps, data->d_size);
-
- if (!nr_maps)
- return 0;
-
/* Assume equally sized map definitions */
+ pr_debug("maps in %s: %d maps in %zd bytes\n",
+ obj->path, nr_maps, data->d_size);
+
map_def_sz = data->d_size / nr_maps;
if (!data->d_size || (data->d_size % nr_maps) != 0) {
pr_warning("unable to determine map definition size "
@@ -628,51 +940,47 @@
return -EINVAL;
}
- obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
- if (!obj->maps) {
- pr_warning("alloc maps for object failed\n");
- return -ENOMEM;
- }
- obj->nr_maps = nr_maps;
-
- /*
- * fill all fd with -1 so won't close incorrect
- * fd (fd=0 is stdin) when failure (zclose won't close
- * negative fd)).
- */
- for (i = 0; i < nr_maps; i++)
- obj->maps[i].fd = -1;
-
- /*
- * Fill obj->maps using data in "maps" section.
- */
- for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ /* Fill obj->maps using data in "maps" section. */
+ for (i = 0; i < nr_syms; i++) {
GElf_Sym sym;
const char *map_name;
struct bpf_map_def *def;
+ struct bpf_map *map;
if (!gelf_getsym(symbols, i, &sym))
continue;
if (sym.st_shndx != obj->efile.maps_shndx)
continue;
- map_name = elf_strptr(obj->efile.elf,
- obj->efile.strtabidx,
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
sym.st_name);
- obj->maps[map_idx].offset = sym.st_value;
+ if (!map_name) {
+ pr_warning("failed to get map #%d name sym string for obj %s\n",
+ i, obj->path);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ map->libbpf_type = LIBBPF_MAP_UNSPEC;
+ map->sec_idx = sym.st_shndx;
+ map->sec_offset = sym.st_value;
+ pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
if (sym.st_value + map_def_sz > data->d_size) {
pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
obj->path, map_name);
return -EINVAL;
}
- obj->maps[map_idx].name = strdup(map_name);
- if (!obj->maps[map_idx].name) {
+ map->name = strdup(map_name);
+ if (!map->name) {
pr_warning("failed to alloc map name\n");
return -ENOMEM;
}
- pr_debug("map %d is \"%s\"\n", map_idx,
- obj->maps[map_idx].name);
+ pr_debug("map %d is \"%s\"\n", i, map->name);
def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
/*
* If the definition of the map in the object file fits in
@@ -681,7 +989,7 @@
* calloc above.
*/
if (map_def_sz <= sizeof(struct bpf_map_def)) {
- memcpy(&obj->maps[map_idx].def, def, map_def_sz);
+ memcpy(&map->def, def, map_def_sz);
} else {
/*
* Here the map structure being read is bigger than what
@@ -697,16 +1005,339 @@
"has unrecognized, non-zero "
"options\n",
obj->path, map_name);
- return -EINVAL;
+ if (strict)
+ return -EINVAL;
}
}
- memcpy(&obj->maps[map_idx].def, def,
- sizeof(struct bpf_map_def));
+ memcpy(&map->def, def, sizeof(struct bpf_map_def));
}
- map_idx++;
+ }
+ return 0;
+}
+
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
+
+ if (res_id)
+ *res_id = id;
+
+ while (btf_is_mod(t) || btf_is_typedef(t)) {
+ if (res_id)
+ *res_id = t->type;
+ t = btf__type_by_id(btf, t->type);
}
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
+ return t;
+}
+
+/*
+ * Fetch integer attribute of BTF map definition. Such attributes are
+ * represented using a pointer to an array, in which dimensionality of array
+ * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY];
+ * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF
+ * type definition, while using only sizeof(void *) space in ELF data section.
+ */
+static bool get_map_field_int(const char *map_name, const struct btf *btf,
+ const struct btf_type *def,
+ const struct btf_member *m, __u32 *res) {
+ const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL);
+ const char *name = btf__name_by_offset(btf, m->name_off);
+ const struct btf_array *arr_info;
+ const struct btf_type *arr_t;
+
+ if (!btf_is_ptr(t)) {
+ pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
+ map_name, name, btf_kind(t));
+ return false;
+ }
+
+ arr_t = btf__type_by_id(btf, t->type);
+ if (!arr_t) {
+ pr_warning("map '%s': attr '%s': type [%u] not found.\n",
+ map_name, name, t->type);
+ return false;
+ }
+ if (!btf_is_array(arr_t)) {
+ pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
+ map_name, name, btf_kind(arr_t));
+ return false;
+ }
+ arr_info = btf_array(arr_t);
+ *res = arr_info->nelems;
+ return true;
+}
+
+static int bpf_object__init_user_btf_map(struct bpf_object *obj,
+ const struct btf_type *sec,
+ int var_idx, int sec_idx,
+ const Elf_Data *data, bool strict)
+{
+ const struct btf_type *var, *def, *t;
+ const struct btf_var_secinfo *vi;
+ const struct btf_var *var_extra;
+ const struct btf_member *m;
+ const char *map_name;
+ struct bpf_map *map;
+ int vlen, i;
+
+ vi = btf_var_secinfos(sec) + var_idx;
+ var = btf__type_by_id(obj->btf, vi->type);
+ var_extra = btf_var(var);
+ map_name = btf__name_by_offset(obj->btf, var->name_off);
+ vlen = btf_vlen(var);
+
+ if (map_name == NULL || map_name[0] == '\0') {
+ pr_warning("map #%d: empty name.\n", var_idx);
+ return -EINVAL;
+ }
+ if ((__u64)vi->offset + vi->size > data->d_size) {
+ pr_warning("map '%s' BTF data is corrupted.\n", map_name);
+ return -EINVAL;
+ }
+ if (!btf_is_var(var)) {
+ pr_warning("map '%s': unexpected var kind %u.\n",
+ map_name, btf_kind(var));
+ return -EINVAL;
+ }
+ if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
+ var_extra->linkage != BTF_VAR_STATIC) {
+ pr_warning("map '%s': unsupported var linkage %u.\n",
+ map_name, var_extra->linkage);
+ return -EOPNOTSUPP;
+ }
+
+ def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
+ if (!btf_is_struct(def)) {
+ pr_warning("map '%s': unexpected def kind %u.\n",
+ map_name, btf_kind(var));
+ return -EINVAL;
+ }
+ if (def->size > vi->size) {
+ pr_warning("map '%s': invalid def size.\n", map_name);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+ map->name = strdup(map_name);
+ if (!map->name) {
+ pr_warning("map '%s': failed to alloc map name.\n", map_name);
+ return -ENOMEM;
+ }
+ map->libbpf_type = LIBBPF_MAP_UNSPEC;
+ map->def.type = BPF_MAP_TYPE_UNSPEC;
+ map->sec_idx = sec_idx;
+ map->sec_offset = vi->offset;
+ pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
+
+ vlen = btf_vlen(def);
+ m = btf_members(def);
+ for (i = 0; i < vlen; i++, m++) {
+ const char *name = btf__name_by_offset(obj->btf, m->name_off);
+
+ if (!name) {
+ pr_warning("map '%s': invalid field #%d.\n",
+ map_name, i);
+ return -EINVAL;
+ }
+ if (strcmp(name, "type") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.type))
+ return -EINVAL;
+ pr_debug("map '%s': found type = %u.\n",
+ map_name, map->def.type);
+ } else if (strcmp(name, "max_entries") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.max_entries))
+ return -EINVAL;
+ pr_debug("map '%s': found max_entries = %u.\n",
+ map_name, map->def.max_entries);
+ } else if (strcmp(name, "map_flags") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.map_flags))
+ return -EINVAL;
+ pr_debug("map '%s': found map_flags = %u.\n",
+ map_name, map->def.map_flags);
+ } else if (strcmp(name, "key_size") == 0) {
+ __u32 sz;
+
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &sz))
+ return -EINVAL;
+ pr_debug("map '%s': found key_size = %u.\n",
+ map_name, sz);
+ if (map->def.key_size && map->def.key_size != sz) {
+ pr_warning("map '%s': conflicting key size %u != %u.\n",
+ map_name, map->def.key_size, sz);
+ return -EINVAL;
+ }
+ map->def.key_size = sz;
+ } else if (strcmp(name, "key") == 0) {
+ __s64 sz;
+
+ t = btf__type_by_id(obj->btf, m->type);
+ if (!t) {
+ pr_warning("map '%s': key type [%d] not found.\n",
+ map_name, m->type);
+ return -EINVAL;
+ }
+ if (!btf_is_ptr(t)) {
+ pr_warning("map '%s': key spec is not PTR: %u.\n",
+ map_name, btf_kind(t));
+ return -EINVAL;
+ }
+ sz = btf__resolve_size(obj->btf, t->type);
+ if (sz < 0) {
+ pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n",
+ map_name, t->type, sz);
+ return sz;
+ }
+ pr_debug("map '%s': found key [%u], sz = %lld.\n",
+ map_name, t->type, sz);
+ if (map->def.key_size && map->def.key_size != sz) {
+ pr_warning("map '%s': conflicting key size %u != %lld.\n",
+ map_name, map->def.key_size, sz);
+ return -EINVAL;
+ }
+ map->def.key_size = sz;
+ map->btf_key_type_id = t->type;
+ } else if (strcmp(name, "value_size") == 0) {
+ __u32 sz;
+
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &sz))
+ return -EINVAL;
+ pr_debug("map '%s': found value_size = %u.\n",
+ map_name, sz);
+ if (map->def.value_size && map->def.value_size != sz) {
+ pr_warning("map '%s': conflicting value size %u != %u.\n",
+ map_name, map->def.value_size, sz);
+ return -EINVAL;
+ }
+ map->def.value_size = sz;
+ } else if (strcmp(name, "value") == 0) {
+ __s64 sz;
+
+ t = btf__type_by_id(obj->btf, m->type);
+ if (!t) {
+ pr_warning("map '%s': value type [%d] not found.\n",
+ map_name, m->type);
+ return -EINVAL;
+ }
+ if (!btf_is_ptr(t)) {
+ pr_warning("map '%s': value spec is not PTR: %u.\n",
+ map_name, btf_kind(t));
+ return -EINVAL;
+ }
+ sz = btf__resolve_size(obj->btf, t->type);
+ if (sz < 0) {
+ pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n",
+ map_name, t->type, sz);
+ return sz;
+ }
+ pr_debug("map '%s': found value [%u], sz = %lld.\n",
+ map_name, t->type, sz);
+ if (map->def.value_size && map->def.value_size != sz) {
+ pr_warning("map '%s': conflicting value size %u != %lld.\n",
+ map_name, map->def.value_size, sz);
+ return -EINVAL;
+ }
+ map->def.value_size = sz;
+ map->btf_value_type_id = t->type;
+ } else {
+ if (strict) {
+ pr_warning("map '%s': unknown field '%s'.\n",
+ map_name, name);
+ return -ENOTSUP;
+ }
+ pr_debug("map '%s': ignoring unknown field '%s'.\n",
+ map_name, name);
+ }
+ }
+
+ if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
+ pr_warning("map '%s': map type isn't specified.\n", map_name);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
+{
+ const struct btf_type *sec = NULL;
+ int nr_types, i, vlen, err;
+ const struct btf_type *t;
+ const char *name;
+ Elf_Data *data;
+ Elf_Scn *scn;
+
+ if (obj->efile.btf_maps_shndx < 0)
+ return 0;
+
+ scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx);
+ if (scn)
+ data = elf_getdata(scn, NULL);
+ if (!scn || !data) {
+ pr_warning("failed to get Elf_Data from map section %d (%s)\n",
+ obj->efile.maps_shndx, MAPS_ELF_SEC);
+ return -EINVAL;
+ }
+
+ nr_types = btf__get_nr_types(obj->btf);
+ for (i = 1; i <= nr_types; i++) {
+ t = btf__type_by_id(obj->btf, i);
+ if (!btf_is_datasec(t))
+ continue;
+ name = btf__name_by_offset(obj->btf, t->name_off);
+ if (strcmp(name, MAPS_ELF_SEC) == 0) {
+ sec = t;
+ break;
+ }
+ }
+
+ if (!sec) {
+ pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
+ return -ENOENT;
+ }
+
+ vlen = btf_vlen(sec);
+ for (i = 0; i < vlen; i++) {
+ err = bpf_object__init_user_btf_map(obj, sec, i,
+ obj->efile.btf_maps_shndx,
+ data, strict);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_maps(struct bpf_object *obj, int flags)
+{
+ bool strict = !(flags & MAPS_RELAX_COMPAT);
+ int err;
+
+ err = bpf_object__init_user_maps(obj, strict);
+ if (err)
+ return err;
+
+ err = bpf_object__init_user_btf_maps(obj, strict);
+ if (err)
+ return err;
+
+ err = bpf_object__init_global_data_maps(obj);
+ if (err)
+ return err;
+
+ if (obj->nr_maps) {
+ qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
+ compare_bpf_map);
+ }
return 0;
}
@@ -728,17 +1359,175 @@
return false;
}
-static int bpf_object__elf_collect(struct bpf_object *obj)
+static void bpf_object__sanitize_btf(struct bpf_object *obj)
+{
+ bool has_datasec = obj->caps.btf_datasec;
+ bool has_func = obj->caps.btf_func;
+ struct btf *btf = obj->btf;
+ struct btf_type *t;
+ int i, j, vlen;
+
+ if (!obj->btf || (has_func && has_datasec))
+ return;
+
+ for (i = 1; i <= btf__get_nr_types(btf); i++) {
+ t = (struct btf_type *)btf__type_by_id(btf, i);
+
+ if (!has_datasec && btf_is_var(t)) {
+ /* replace VAR with INT */
+ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
+ /*
+ * using size = 1 is the safest choice, 4 will be too
+ * big and cause kernel BTF validation failure if
+ * original variable took less than 4 bytes
+ */
+ t->size = 1;
+ *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
+ } else if (!has_datasec && btf_is_datasec(t)) {
+ /* replace DATASEC with STRUCT */
+ const struct btf_var_secinfo *v = btf_var_secinfos(t);
+ struct btf_member *m = btf_members(t);
+ struct btf_type *vt;
+ char *name;
+
+ name = (char *)btf__name_by_offset(btf, t->name_off);
+ while (*name) {
+ if (*name == '.')
+ *name = '_';
+ name++;
+ }
+
+ vlen = btf_vlen(t);
+ t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen);
+ for (j = 0; j < vlen; j++, v++, m++) {
+ /* order of field assignments is important */
+ m->offset = v->offset * 8;
+ m->type = v->type;
+ /* preserve variable name as member name */
+ vt = (void *)btf__type_by_id(btf, v->type);
+ m->name_off = vt->name_off;
+ }
+ } else if (!has_func && btf_is_func_proto(t)) {
+ /* replace FUNC_PROTO with ENUM */
+ vlen = btf_vlen(t);
+ t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen);
+ t->size = sizeof(__u32); /* kernel enforced */
+ } else if (!has_func && btf_is_func(t)) {
+ /* replace FUNC with TYPEDEF */
+ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
+ }
+ }
+}
+
+static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
+{
+ if (!obj->btf_ext)
+ return;
+
+ if (!obj->caps.btf_func) {
+ btf_ext__free(obj->btf_ext);
+ obj->btf_ext = NULL;
+ }
+}
+
+static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+{
+ return obj->efile.btf_maps_shndx >= 0;
+}
+
+static int bpf_object__init_btf(struct bpf_object *obj,
+ Elf_Data *btf_data,
+ Elf_Data *btf_ext_data)
+{
+ bool btf_required = bpf_object__is_btf_mandatory(obj);
+ int err = 0;
+
+ if (btf_data) {
+ obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(obj->btf)) {
+ pr_warning("Error loading ELF section %s: %d.\n",
+ BTF_ELF_SEC, err);
+ goto out;
+ }
+ err = btf__finalize_data(obj, obj->btf);
+ if (err) {
+ pr_warning("Error finalizing %s: %d.\n",
+ BTF_ELF_SEC, err);
+ goto out;
+ }
+ }
+ if (btf_ext_data) {
+ if (!obj->btf) {
+ pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
+ BTF_EXT_ELF_SEC, BTF_ELF_SEC);
+ goto out;
+ }
+ obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
+ btf_ext_data->d_size);
+ if (IS_ERR(obj->btf_ext)) {
+ pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
+ obj->btf_ext = NULL;
+ goto out;
+ }
+ }
+out:
+ if (err || IS_ERR(obj->btf)) {
+ if (btf_required)
+ err = err ? : PTR_ERR(obj->btf);
+ else
+ err = 0;
+ if (!IS_ERR_OR_NULL(obj->btf))
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ }
+ if (btf_required && !obj->btf) {
+ pr_warning("BTF is required, but is missing or corrupted.\n");
+ return err == 0 ? -ENOENT : err;
+ }
+ return 0;
+}
+
+static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
+{
+ int err = 0;
+
+ if (!obj->btf)
+ return 0;
+
+ bpf_object__sanitize_btf(obj);
+ bpf_object__sanitize_btf_ext(obj);
+
+ err = btf__load(obj->btf);
+ if (err) {
+ pr_warning("Error loading %s into kernel: %d.\n",
+ BTF_ELF_SEC, err);
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ /* btf_ext can't exist without btf, so free it as well */
+ if (obj->btf_ext) {
+ btf_ext__free(obj->btf_ext);
+ obj->btf_ext = NULL;
+ }
+
+ if (bpf_object__is_btf_mandatory(obj))
+ return err;
+ }
+ return 0;
+}
+
+static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
{
Elf *elf = obj->efile.elf;
GElf_Ehdr *ep = &obj->efile.ehdr;
+ Elf_Data *btf_ext_data = NULL;
+ Elf_Data *btf_data = NULL;
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);
+ pr_warning("failed to get e_shstrndx from %s\n", obj->path);
return -LIBBPF_ERRNO__FORMAT;
}
@@ -751,74 +1540,82 @@
if (gelf_getshdr(scn, &sh) != &sh) {
pr_warning("failed to get section(%d) header from %s\n",
idx, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
if (!name) {
pr_warning("failed to get section(%d) name from %s\n",
idx, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
data = elf_getdata(scn, 0);
if (!data) {
pr_warning("failed to get section(%d) data from %s(%s)\n",
idx, name, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
idx, name, (unsigned long)data->d_size,
(int)sh.sh_link, (unsigned long)sh.sh_flags,
(int)sh.sh_type);
- if (strcmp(name, "license") == 0)
+ if (strcmp(name, "license") == 0) {
err = bpf_object__init_license(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "version") == 0)
+ if (err)
+ return err;
+ } else if (strcmp(name, "version") == 0) {
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "maps") == 0)
+ if (err)
+ return err;
+ } else if (strcmp(name, "maps") == 0) {
obj->efile.maps_shndx = idx;
- else if (strcmp(name, BTF_ELF_SEC) == 0) {
- obj->btf = btf__new(data->d_buf, data->d_size,
- __pr_debug);
- if (IS_ERR(obj->btf)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_ELF_SEC, PTR_ERR(obj->btf));
- obj->btf = NULL;
- }
+ } else if (strcmp(name, MAPS_ELF_SEC) == 0) {
+ obj->efile.btf_maps_shndx = idx;
+ } else if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = data;
+ } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+ btf_ext_data = data;
} else if (sh.sh_type == SHT_SYMTAB) {
if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- } else {
- obj->efile.symbols = data;
- obj->efile.strtabidx = sh.sh_link;
+ return -LIBBPF_ERRNO__FORMAT;
}
- } else if ((sh.sh_type == SHT_PROGBITS) &&
- (sh.sh_flags & SHF_EXECINSTR) &&
- (data->d_size > 0)) {
- if (strcmp(name, ".text") == 0)
- obj->efile.text_shndx = idx;
- err = bpf_object__add_program(obj, data->d_buf,
- data->d_size, name, idx);
- if (err) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = str_error(-err, errmsg, sizeof(errmsg));
+ obj->efile.symbols = data;
+ obj->efile.strtabidx = sh.sh_link;
+ } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
+ if (sh.sh_flags & SHF_EXECINSTR) {
+ if (strcmp(name, ".text") == 0)
+ obj->efile.text_shndx = idx;
+ err = bpf_object__add_program(obj, data->d_buf,
+ data->d_size, name, idx);
+ if (err) {
+ char errmsg[STRERR_BUFSIZE];
+ char *cp = libbpf_strerror_r(-err, errmsg,
+ sizeof(errmsg));
- pr_warning("failed to alloc program %s (%s): %s",
- name, obj->path, cp);
+ pr_warning("failed to alloc program %s (%s): %s",
+ name, obj->path, cp);
+ return err;
+ }
+ } else if (strcmp(name, ".data") == 0) {
+ obj->efile.data = data;
+ obj->efile.data_shndx = idx;
+ } else if (strcmp(name, ".rodata") == 0) {
+ obj->efile.rodata = data;
+ obj->efile.rodata_shndx = idx;
+ } else {
+ pr_debug("skip section(%d) %s\n", idx, name);
}
} else if (sh.sh_type == SHT_REL) {
+ int nr_reloc = obj->efile.nr_reloc;
void *reloc = obj->efile.reloc;
- int nr_reloc = obj->efile.nr_reloc + 1;
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
@@ -828,38 +1625,37 @@
continue;
}
- reloc = reallocarray(reloc, nr_reloc,
+ reloc = reallocarray(reloc, nr_reloc + 1,
sizeof(*obj->efile.reloc));
if (!reloc) {
pr_warning("realloc failed\n");
- err = -ENOMEM;
- } else {
- int n = nr_reloc - 1;
-
- obj->efile.reloc = reloc;
- obj->efile.nr_reloc = nr_reloc;
-
- obj->efile.reloc[n].shdr = sh;
- obj->efile.reloc[n].data = data;
+ return -ENOMEM;
}
+
+ obj->efile.reloc = reloc;
+ obj->efile.nr_reloc++;
+
+ obj->efile.reloc[nr_reloc].shdr = sh;
+ obj->efile.reloc[nr_reloc].data = data;
+ } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
+ obj->efile.bss = data;
+ obj->efile.bss_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
- if (err)
- goto out;
}
if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
pr_warning("Corrupted ELF file: index of strtab invalid\n");
- return LIBBPF_ERRNO__FORMAT;
+ return -LIBBPF_ERRNO__FORMAT;
}
- if (obj->efile.maps_shndx >= 0) {
- err = bpf_object__init_maps(obj);
- if (err)
- goto out;
- }
- err = bpf_object__init_prog_names(obj);
-out:
+ err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
+ if (!err)
+ err = bpf_object__init_maps(obj, flags);
+ if (!err)
+ err = bpf_object__sanitize_and_load_btf(obj);
+ if (!err)
+ err = bpf_object__init_prog_names(obj);
return err;
}
@@ -878,7 +1674,8 @@
}
struct bpf_program *
-bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
+bpf_object__find_program_by_title(const struct bpf_object *obj,
+ const char *title)
{
struct bpf_program *pos;
@@ -889,19 +1686,52 @@
return NULL;
}
+static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.data_shndx ||
+ shndx == obj->efile.bss_shndx ||
+ shndx == obj->efile.rodata_shndx;
+}
+
+static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.maps_shndx ||
+ shndx == obj->efile.btf_maps_shndx;
+}
+
+static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.text_shndx ||
+ bpf_object__shndx_is_maps(obj, shndx) ||
+ bpf_object__shndx_is_data(obj, shndx);
+}
+
+static enum libbpf_map_type
+bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
+{
+ if (shndx == obj->efile.data_shndx)
+ return LIBBPF_MAP_DATA;
+ else if (shndx == obj->efile.bss_shndx)
+ return LIBBPF_MAP_BSS;
+ else if (shndx == obj->efile.rodata_shndx)
+ return LIBBPF_MAP_RODATA;
+ else
+ return LIBBPF_MAP_UNSPEC;
+}
+
static int
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
Elf_Data *data, struct bpf_object *obj)
{
Elf_Data *symbols = obj->efile.symbols;
- int text_shndx = obj->efile.text_shndx;
- int maps_shndx = obj->efile.maps_shndx;
struct bpf_map *maps = obj->maps;
size_t nr_maps = obj->nr_maps;
int i, nrels;
- pr_debug("collecting relocating info for: '%s'\n",
- prog->section_name);
+ 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);
@@ -912,36 +1742,49 @@
prog->nr_reloc = nrels;
for (i = 0; i < nrels; i++) {
+ struct bpf_insn *insns = prog->insns;
+ enum libbpf_map_type type;
+ unsigned int insn_idx;
+ unsigned int shdr_idx;
+ const char *name;
+ size_t map_idx;
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 -LIBBPF_ERRNO__FORMAT;
}
- if (!gelf_getsym(symbols,
- GELF_R_SYM(rel.r_info),
- &sym)) {
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
pr_warning("relocation: symbol %"PRIx64" not found\n",
GELF_R_SYM(rel.r_info));
return -LIBBPF_ERRNO__FORMAT;
}
- pr_debug("relo for %lld value %lld name %d\n",
- (long long) (rel.r_info >> 32),
- (long long) sym.st_value, sym.st_name);
- if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
- pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
- prog->section_name, sym.st_shndx);
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+
+ pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
+ (long long) (rel.r_info >> 32),
+ (long long) sym.st_value, sym.st_name, name);
+
+ shdr_idx = sym.st_shndx;
+ insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+ pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n",
+ insn_idx, shdr_idx);
+
+ if (shdr_idx >= SHN_LORESERVE) {
+ pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n",
+ name, shdr_idx, insn_idx,
+ insns[insn_idx].code);
return -LIBBPF_ERRNO__RELOC;
}
-
- insn_idx = rel.r_offset / sizeof(struct bpf_insn);
- pr_debug("relocation: insn_idx=%u\n", insn_idx);
+ if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
+ pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
+ prog->section_name, shdr_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) {
if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) {
@@ -961,97 +1804,80 @@
return -LIBBPF_ERRNO__RELOC;
}
- /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
- for (map_idx = 0; map_idx < nr_maps; map_idx++) {
- if (maps[map_idx].offset == sym.st_value) {
- pr_debug("relocation: find map %zd (%s) for insn %u\n",
- map_idx, maps[map_idx].name, insn_idx);
- break;
+ if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
+ bpf_object__shndx_is_data(obj, shdr_idx)) {
+ type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
+ if (type != LIBBPF_MAP_UNSPEC) {
+ if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
+ pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
+ name, insn_idx, insns[insn_idx].code);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+ if (!obj->caps.global_data) {
+ pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
+ name, insn_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
}
- }
- if (map_idx >= nr_maps) {
- pr_warning("bpf relocation: map_idx %d large than %d\n",
- (int)map_idx, (int)nr_maps - 1);
- return -LIBBPF_ERRNO__RELOC;
- }
+ for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+ if (maps[map_idx].libbpf_type != type)
+ continue;
+ if (type != LIBBPF_MAP_UNSPEC ||
+ (maps[map_idx].sec_idx == sym.st_shndx &&
+ maps[map_idx].sec_offset == sym.st_value)) {
+ pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n",
+ map_idx, maps[map_idx].name,
+ maps[map_idx].sec_idx,
+ maps[map_idx].sec_offset,
+ insn_idx);
+ break;
+ }
+ }
- prog->reloc_desc[i].type = RELO_LD64;
- prog->reloc_desc[i].insn_idx = insn_idx;
- prog->reloc_desc[i].map_idx = map_idx;
+ if (map_idx >= nr_maps) {
+ pr_warning("bpf relocation: map_idx %d larger than %d\n",
+ (int)map_idx, (int)nr_maps - 1);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+
+ prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
+ RELO_DATA : RELO_LD64;
+ prog->reloc_desc[i].insn_idx = insn_idx;
+ prog->reloc_desc[i].map_idx = map_idx;
+ }
}
return 0;
}
-static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
+static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
{
- const struct btf_type *container_type;
- const struct btf_member *key, *value;
struct bpf_map_def *def = &map->def;
- const size_t max_name = 256;
- char container_name[max_name];
- __s64 key_size, value_size;
- __s32 container_id;
+ __u32 key_type_id = 0, value_type_id = 0;
+ int ret;
- if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
- max_name) {
- pr_warning("map:%s length of '____btf_map_%s' is too long\n",
- map->name, map->name);
- return -EINVAL;
+ /* if it's BTF-defined map, we don't need to search for type IDs */
+ if (map->sec_idx == obj->efile.btf_maps_shndx)
+ return 0;
+
+ if (!bpf_map__is_internal(map)) {
+ ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
+ def->value_size, &key_type_id,
+ &value_type_id);
+ } else {
+ /*
+ * LLVM annotates global data differently in BTF, that is,
+ * only as '.data', '.bss' or '.rodata'.
+ */
+ ret = btf__find_by_name(obj->btf,
+ libbpf_type_to_btf_name[map->libbpf_type]);
}
+ if (ret < 0)
+ return ret;
- container_id = btf__find_by_name(btf, container_name);
- if (container_id < 0) {
- pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
- map->name, container_name);
- return container_id;
- }
-
- container_type = btf__type_by_id(btf, container_id);
- if (!container_type) {
- pr_warning("map:%s cannot find BTF type for container_id:%u\n",
- map->name, container_id);
- return -EINVAL;
- }
-
- if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
- BTF_INFO_VLEN(container_type->info) < 2) {
- pr_warning("map:%s container_name:%s is an invalid container struct\n",
- map->name, container_name);
- return -EINVAL;
- }
-
- key = (struct btf_member *)(container_type + 1);
- value = key + 1;
-
- key_size = btf__resolve_size(btf, key->type);
- if (key_size < 0) {
- pr_warning("map:%s invalid BTF key_type_size\n",
- map->name);
- return key_size;
- }
-
- if (def->key_size != key_size) {
- pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
- map->name, (__u32)key_size, def->key_size);
- return -EINVAL;
- }
-
- value_size = btf__resolve_size(btf, value->type);
- if (value_size < 0) {
- pr_warning("map:%s invalid BTF value_type_size\n", map->name);
- return value_size;
- }
-
- if (def->value_size != value_size) {
- pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
- map->name, (__u32)value_size, def->value_size);
- return -EINVAL;
- }
-
- map->btf_key_type_id = key->type;
- map->btf_value_type_id = value->type;
-
+ map->btf_key_type_id = key_type_id;
+ map->btf_value_type_id = bpf_map__is_internal(map) ?
+ ret : value_type_id;
return 0;
}
@@ -1102,10 +1928,212 @@
return -errno;
}
+int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
+{
+ if (!map || !max_entries)
+ return -EINVAL;
+
+ /* If map already created, its attributes can't be changed. */
+ if (map->fd >= 0)
+ return -EBUSY;
+
+ map->def.max_entries = max_entries;
+
+ return 0;
+}
+
+static int
+bpf_object__probe_name(struct bpf_object *obj)
+{
+ struct bpf_load_program_attr attr;
+ char *cp, errmsg[STRERR_BUFSIZE];
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int ret;
+
+ /* make sure basic loading works */
+
+ memset(&attr, 0, sizeof(attr));
+ attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ attr.insns = insns;
+ attr.insns_cnt = ARRAY_SIZE(insns);
+ attr.license = "GPL";
+
+ ret = bpf_load_program_xattr(&attr, NULL, 0);
+ if (ret < 0) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
+ __func__, cp, errno);
+ return -errno;
+ }
+ close(ret);
+
+ /* now try the same program, but with the name */
+
+ attr.name = "test";
+ ret = bpf_load_program_xattr(&attr, NULL, 0);
+ if (ret >= 0) {
+ obj->caps.name = 1;
+ close(ret);
+ }
+
+ return 0;
+}
+
+static int
+bpf_object__probe_global_data(struct bpf_object *obj)
+{
+ struct bpf_load_program_attr prg_attr;
+ struct bpf_create_map_attr map_attr;
+ char *cp, errmsg[STRERR_BUFSIZE];
+ struct bpf_insn insns[] = {
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int ret, map;
+
+ memset(&map_attr, 0, sizeof(map_attr));
+ map_attr.map_type = BPF_MAP_TYPE_ARRAY;
+ map_attr.key_size = sizeof(int);
+ map_attr.value_size = 32;
+ map_attr.max_entries = 1;
+
+ map = bpf_create_map_xattr(&map_attr);
+ if (map < 0) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
+ __func__, cp, errno);
+ return -errno;
+ }
+
+ insns[0].imm = map;
+
+ memset(&prg_attr, 0, sizeof(prg_attr));
+ prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ prg_attr.insns = insns;
+ prg_attr.insns_cnt = ARRAY_SIZE(insns);
+ prg_attr.license = "GPL";
+
+ ret = bpf_load_program_xattr(&prg_attr, NULL, 0);
+ if (ret >= 0) {
+ obj->caps.global_data = 1;
+ close(ret);
+ }
+
+ close(map);
+ return 0;
+}
+
+static int bpf_object__probe_btf_func(struct bpf_object *obj)
+{
+ const char strs[] = "\0int\0x\0a";
+ /* void x(int a) {} */
+ __u32 types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* FUNC_PROTO */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+ BTF_PARAM_ENC(7, 1),
+ /* FUNC x */ /* [3] */
+ BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
+ };
+ int btf_fd;
+
+ btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs));
+ if (btf_fd >= 0) {
+ obj->caps.btf_func = 1;
+ close(btf_fd);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
+{
+ const char strs[] = "\0x\0.data";
+ /* static int a; */
+ __u32 types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* VAR x */ /* [2] */
+ BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+ BTF_VAR_STATIC,
+ /* DATASEC val */ /* [3] */
+ BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(2, 0, 4),
+ };
+ int btf_fd;
+
+ btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs));
+ if (btf_fd >= 0) {
+ obj->caps.btf_datasec = 1;
+ close(btf_fd);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int
+bpf_object__probe_caps(struct bpf_object *obj)
+{
+ int (*probe_fn[])(struct bpf_object *obj) = {
+ bpf_object__probe_name,
+ bpf_object__probe_global_data,
+ bpf_object__probe_btf_func,
+ bpf_object__probe_btf_datasec,
+ };
+ int i, ret;
+
+ for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
+ ret = probe_fn[i](obj);
+ if (ret < 0)
+ pr_debug("Probe #%d failed with %d.\n", i, ret);
+ }
+
+ return 0;
+}
+
+static int
+bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ int err, zero = 0;
+ __u8 *data;
+
+ /* Nothing to do here since kernel already zero-initializes .bss map. */
+ if (map->libbpf_type == LIBBPF_MAP_BSS)
+ return 0;
+
+ data = map->libbpf_type == LIBBPF_MAP_DATA ?
+ obj->sections.data : obj->sections.rodata;
+
+ err = bpf_map_update_elem(map->fd, &zero, data, 0);
+ /* Freeze .rodata map as read-only from syscall side. */
+ if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
+ err = bpf_map_freeze(map->fd);
+ if (err) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error freezing map(%s) as read-only: %s\n",
+ map->name, cp);
+ err = 0;
+ }
+ }
+ return err;
+}
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
struct bpf_create_map_attr create_attr = {};
+ int nr_cpus = 0;
unsigned int i;
int err;
@@ -1121,28 +2149,49 @@
continue;
}
- create_attr.name = map->name;
+ if (obj->caps.name)
+ create_attr.name = map->name;
create_attr.map_ifindex = map->map_ifindex;
create_attr.map_type = def->type;
create_attr.map_flags = def->map_flags;
create_attr.key_size = def->key_size;
create_attr.value_size = def->value_size;
- create_attr.max_entries = def->max_entries;
+ if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+ !def->max_entries) {
+ if (!nr_cpus)
+ nr_cpus = libbpf_num_possible_cpus();
+ if (nr_cpus < 0) {
+ pr_warning("failed to determine number of system CPUs: %d\n",
+ nr_cpus);
+ err = nr_cpus;
+ goto err_out;
+ }
+ pr_debug("map '%s': setting size to %d\n",
+ map->name, nr_cpus);
+ create_attr.max_entries = nr_cpus;
+ } else {
+ create_attr.max_entries = def->max_entries;
+ }
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
+ if (bpf_map_type__is_map_in_map(def->type) &&
+ map->inner_map_fd >= 0)
+ create_attr.inner_map_fd = map->inner_map_fd;
- if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
+ if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
create_attr.btf_fd = btf__fd(obj->btf);
create_attr.btf_key_type_id = map->btf_key_type_id;
create_attr.btf_value_type_id = map->btf_value_type_id;
}
*pfd = bpf_create_map_xattr(&create_attr);
- if (*pfd < 0 && create_attr.btf_key_type_id) {
- cp = str_error(errno, errmsg, sizeof(errmsg));
+ if (*pfd < 0 && (create_attr.btf_key_type_id ||
+ create_attr.btf_value_type_id)) {
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
- map->name, cp, errno);
+ map->name, cp, err);
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
@@ -1154,27 +2203,995 @@
if (*pfd < 0) {
size_t j;
- err = *pfd;
- cp = str_error(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to create map (name: '%s'): %s\n",
- map->name, cp);
+ err = -errno;
+err_out:
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
+ pr_warning("failed to create map (name: '%s'): %s(%d)\n",
+ map->name, cp, err);
for (j = 0; j < i; j++)
zclose(obj->maps[j].fd);
return err;
}
- pr_debug("create map %s: fd=%d\n", map->name, *pfd);
+
+ if (bpf_map__is_internal(map)) {
+ err = bpf_object__populate_internal_map(obj, map);
+ if (err < 0) {
+ zclose(*pfd);
+ goto err_out;
+ }
+ }
+
+ pr_debug("created map %s: fd=%d\n", map->name, *pfd);
}
return 0;
}
static int
+check_btf_ext_reloc_err(struct bpf_program *prog, int err,
+ void *btf_prog_info, const char *info_name)
+{
+ if (err != -ENOENT) {
+ pr_warning("Error in loading %s for sec %s.\n",
+ info_name, prog->section_name);
+ return err;
+ }
+
+ /* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */
+
+ if (btf_prog_info) {
+ /*
+ * Some info has already been found but has problem
+ * in the last btf_ext reloc. Must have to error out.
+ */
+ pr_warning("Error in relocating %s for sec %s.\n",
+ info_name, prog->section_name);
+ return err;
+ }
+
+ /* Have problem loading the very first info. Ignore the rest. */
+ pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
+ info_name, prog->section_name, info_name);
+ return 0;
+}
+
+static int
+bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
+ const char *section_name, __u32 insn_offset)
+{
+ int err;
+
+ if (!insn_offset || prog->func_info) {
+ /*
+ * !insn_offset => main program
+ *
+ * For sub prog, the main program's func_info has to
+ * be loaded first (i.e. prog->func_info != NULL)
+ */
+ err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
+ section_name, insn_offset,
+ &prog->func_info,
+ &prog->func_info_cnt);
+ if (err)
+ return check_btf_ext_reloc_err(prog, err,
+ prog->func_info,
+ "bpf_func_info");
+
+ prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
+ }
+
+ if (!insn_offset || prog->line_info) {
+ err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
+ section_name, insn_offset,
+ &prog->line_info,
+ &prog->line_info_cnt);
+ if (err)
+ return check_btf_ext_reloc_err(prog, err,
+ prog->line_info,
+ "bpf_line_info");
+
+ prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
+ }
+
+ return 0;
+}
+
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+ __u32 type_id; /* struct/union type or array element type */
+ __u32 idx; /* field index or array index */
+ const char *name; /* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+ const struct btf *btf;
+ /* high-level spec: named fields and array indices only */
+ struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+ /* high-level spec length */
+ int len;
+ /* raw, low-level spec: 1-to-1 with accessor spec string */
+ int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+ /* raw spec length */
+ int raw_len;
+ /* field byte offset represented by spec */
+ __u32 offset;
+};
+
+static bool str_is_empty(const char *s)
+{
+ return !s || !s[0];
+}
+
+/*
+ * Turn bpf_offset_reloc into a low- and high-level spec representation,
+ * validating correctness along the way, as well as calculating resulting
+ * field offset (in bytes), specified by accessor string. Low-level spec
+ * captures every single level of nestedness, including traversing anonymous
+ * struct/union members. High-level one only captures semantically meaningful
+ * "turning points": named fields and array indicies.
+ * E.g., for this case:
+ *
+ * struct sample {
+ * int __unimportant;
+ * struct {
+ * int __1;
+ * int __2;
+ * int a[7];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ *
+ * int x = &s->a[3]; // access string = '0:1:2:3'
+ *
+ * Low-level spec has 1:1 mapping with each element of access string (it's
+ * just a parsed access string representation): [0, 1, 2, 3].
+ *
+ * High-level spec will capture only 3 points:
+ * - intial zero-index access by pointer (&s->... is the same as &s[0]...);
+ * - field 'a' access (corresponds to '2' in low-level spec);
+ * - array element #3 access (corresponds to '3' in low-level spec).
+ *
+ */
+static int bpf_core_spec_parse(const struct btf *btf,
+ __u32 type_id,
+ const char *spec_str,
+ struct bpf_core_spec *spec)
+{
+ int access_idx, parsed_len, i;
+ const struct btf_type *t;
+ const char *name;
+ __u32 id;
+ __s64 sz;
+
+ if (str_is_empty(spec_str) || *spec_str == ':')
+ return -EINVAL;
+
+ memset(spec, 0, sizeof(*spec));
+ spec->btf = btf;
+
+ /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */
+ while (*spec_str) {
+ if (*spec_str == ':')
+ ++spec_str;
+ if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1)
+ return -EINVAL;
+ if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+ return -E2BIG;
+ spec_str += parsed_len;
+ spec->raw_spec[spec->raw_len++] = access_idx;
+ }
+
+ if (spec->raw_len == 0)
+ return -EINVAL;
+
+ /* first spec value is always reloc type array index */
+ t = skip_mods_and_typedefs(btf, type_id, &id);
+ if (!t)
+ return -EINVAL;
+
+ access_idx = spec->raw_spec[0];
+ spec->spec[0].type_id = id;
+ spec->spec[0].idx = access_idx;
+ spec->len++;
+
+ sz = btf__resolve_size(btf, id);
+ if (sz < 0)
+ return sz;
+ spec->offset = access_idx * sz;
+
+ for (i = 1; i < spec->raw_len; i++) {
+ t = skip_mods_and_typedefs(btf, id, &id);
+ if (!t)
+ return -EINVAL;
+
+ access_idx = spec->raw_spec[i];
+
+ if (btf_is_composite(t)) {
+ const struct btf_member *m;
+ __u32 offset;
+
+ if (access_idx >= btf_vlen(t))
+ return -EINVAL;
+ if (btf_member_bitfield_size(t, access_idx))
+ return -EINVAL;
+
+ offset = btf_member_bit_offset(t, access_idx);
+ if (offset % 8)
+ return -EINVAL;
+ spec->offset += offset / 8;
+
+ m = btf_members(t) + access_idx;
+ if (m->name_off) {
+ name = btf__name_by_offset(btf, m->name_off);
+ if (str_is_empty(name))
+ return -EINVAL;
+
+ spec->spec[spec->len].type_id = id;
+ spec->spec[spec->len].idx = access_idx;
+ spec->spec[spec->len].name = name;
+ spec->len++;
+ }
+
+ id = m->type;
+ } else if (btf_is_array(t)) {
+ const struct btf_array *a = btf_array(t);
+
+ t = skip_mods_and_typedefs(btf, a->type, &id);
+ if (!t || access_idx >= a->nelems)
+ return -EINVAL;
+
+ spec->spec[spec->len].type_id = id;
+ spec->spec[spec->len].idx = access_idx;
+ spec->len++;
+
+ sz = btf__resolve_size(btf, id);
+ if (sz < 0)
+ return sz;
+ spec->offset += access_idx * sz;
+ } else {
+ pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
+ type_id, spec_str, i, id, btf_kind(t));
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+ /* check X___Y name pattern, where X and Y are not underscores */
+ return s[0] != '_' && /* X */
+ s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */
+ s[4] != '_'; /* Y */
+}
+
+/* Given 'some_struct_name___with_flavor' return the length of a name prefix
+ * before last triple underscore. Struct name part after last triple
+ * underscore is ignored by BPF CO-RE relocation during relocation matching.
+ */
+static size_t bpf_core_essential_name_len(const char *name)
+{
+ size_t n = strlen(name);
+ int i;
+
+ for (i = n - 5; i >= 0; i--) {
+ if (bpf_core_is_flavor_sep(name + i))
+ return i + 1;
+ }
+ return n;
+}
+
+/* dynamically sized list of type IDs */
+struct ids_vec {
+ __u32 *data;
+ int len;
+};
+
+static void bpf_core_free_cands(struct ids_vec *cand_ids)
+{
+ free(cand_ids->data);
+ free(cand_ids);
+}
+
+static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
+ __u32 local_type_id,
+ const struct btf *targ_btf)
+{
+ size_t local_essent_len, targ_essent_len;
+ const char *local_name, *targ_name;
+ const struct btf_type *t;
+ struct ids_vec *cand_ids;
+ __u32 *new_ids;
+ int i, err, n;
+
+ t = btf__type_by_id(local_btf, local_type_id);
+ if (!t)
+ return ERR_PTR(-EINVAL);
+
+ local_name = btf__name_by_offset(local_btf, t->name_off);
+ if (str_is_empty(local_name))
+ return ERR_PTR(-EINVAL);
+ local_essent_len = bpf_core_essential_name_len(local_name);
+
+ cand_ids = calloc(1, sizeof(*cand_ids));
+ if (!cand_ids)
+ return ERR_PTR(-ENOMEM);
+
+ n = btf__get_nr_types(targ_btf);
+ for (i = 1; i <= n; i++) {
+ t = btf__type_by_id(targ_btf, i);
+ targ_name = btf__name_by_offset(targ_btf, t->name_off);
+ if (str_is_empty(targ_name))
+ continue;
+
+ targ_essent_len = bpf_core_essential_name_len(targ_name);
+ if (targ_essent_len != local_essent_len)
+ continue;
+
+ if (strncmp(local_name, targ_name, local_essent_len) == 0) {
+ pr_debug("[%d] %s: found candidate [%d] %s\n",
+ local_type_id, local_name, i, targ_name);
+ new_ids = realloc(cand_ids->data, cand_ids->len + 1);
+ if (!new_ids) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ cand_ids->data = new_ids;
+ cand_ids->data[cand_ids->len++] = i;
+ }
+ }
+ return cand_ids;
+err_out:
+ bpf_core_free_cands(cand_ids);
+ return ERR_PTR(err);
+}
+
+/* Check two types for compatibility, skipping const/volatile/restrict and
+ * typedefs, to ensure we are relocating offset to the compatible entities:
+ * - any two STRUCTs/UNIONs are compatible and can be mixed;
+ * - any two FWDs are compatible;
+ * - any two PTRs are always compatible;
+ * - for ENUMs, check sizes, names are ignored;
+ * - for INT, size and bitness should match, signedness is ignored;
+ * - for ARRAY, dimensionality is ignored, element types are checked for
+ * compatibility recursively;
+ * - everything else shouldn't be ever a target of relocation.
+ * These rules are not set in stone and probably will be adjusted as we get
+ * more experience with using BPF CO-RE relocations.
+ */
+static int bpf_core_fields_are_compat(const struct btf *local_btf,
+ __u32 local_id,
+ const struct btf *targ_btf,
+ __u32 targ_id)
+{
+ const struct btf_type *local_type, *targ_type;
+
+recur:
+ local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id);
+ targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+ if (!local_type || !targ_type)
+ return -EINVAL;
+
+ if (btf_is_composite(local_type) && btf_is_composite(targ_type))
+ return 1;
+ if (btf_kind(local_type) != btf_kind(targ_type))
+ return 0;
+
+ switch (btf_kind(local_type)) {
+ case BTF_KIND_FWD:
+ case BTF_KIND_PTR:
+ return 1;
+ case BTF_KIND_ENUM:
+ return local_type->size == targ_type->size;
+ case BTF_KIND_INT:
+ return btf_int_offset(local_type) == 0 &&
+ btf_int_offset(targ_type) == 0 &&
+ local_type->size == targ_type->size &&
+ btf_int_bits(local_type) == btf_int_bits(targ_type);
+ case BTF_KIND_ARRAY:
+ local_id = btf_array(local_type)->type;
+ targ_id = btf_array(targ_type)->type;
+ goto recur;
+ default:
+ pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n",
+ btf_kind(local_type), local_id, targ_id);
+ return 0;
+ }
+}
+
+/*
+ * Given single high-level named field accessor in local type, find
+ * corresponding high-level accessor for a target type. Along the way,
+ * maintain low-level spec for target as well. Also keep updating target
+ * offset.
+ *
+ * Searching is performed through recursive exhaustive enumeration of all
+ * fields of a struct/union. If there are any anonymous (embedded)
+ * structs/unions, they are recursively searched as well. If field with
+ * desired name is found, check compatibility between local and target types,
+ * before returning result.
+ *
+ * 1 is returned, if field is found.
+ * 0 is returned if no compatible field is found.
+ * <0 is returned on error.
+ */
+static int bpf_core_match_member(const struct btf *local_btf,
+ const struct bpf_core_accessor *local_acc,
+ const struct btf *targ_btf,
+ __u32 targ_id,
+ struct bpf_core_spec *spec,
+ __u32 *next_targ_id)
+{
+ const struct btf_type *local_type, *targ_type;
+ const struct btf_member *local_member, *m;
+ const char *local_name, *targ_name;
+ __u32 local_id;
+ int i, n, found;
+
+ targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+ if (!targ_type)
+ return -EINVAL;
+ if (!btf_is_composite(targ_type))
+ return 0;
+
+ local_id = local_acc->type_id;
+ local_type = btf__type_by_id(local_btf, local_id);
+ local_member = btf_members(local_type) + local_acc->idx;
+ local_name = btf__name_by_offset(local_btf, local_member->name_off);
+
+ n = btf_vlen(targ_type);
+ m = btf_members(targ_type);
+ for (i = 0; i < n; i++, m++) {
+ __u32 offset;
+
+ /* bitfield relocations not supported */
+ if (btf_member_bitfield_size(targ_type, i))
+ continue;
+ offset = btf_member_bit_offset(targ_type, i);
+ if (offset % 8)
+ continue;
+
+ /* too deep struct/union/array nesting */
+ if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+ return -E2BIG;
+
+ /* speculate this member will be the good one */
+ spec->offset += offset / 8;
+ spec->raw_spec[spec->raw_len++] = i;
+
+ targ_name = btf__name_by_offset(targ_btf, m->name_off);
+ if (str_is_empty(targ_name)) {
+ /* embedded struct/union, we need to go deeper */
+ found = bpf_core_match_member(local_btf, local_acc,
+ targ_btf, m->type,
+ spec, next_targ_id);
+ if (found) /* either found or error */
+ return found;
+ } else if (strcmp(local_name, targ_name) == 0) {
+ /* matching named field */
+ struct bpf_core_accessor *targ_acc;
+
+ targ_acc = &spec->spec[spec->len++];
+ targ_acc->type_id = targ_id;
+ targ_acc->idx = i;
+ targ_acc->name = targ_name;
+
+ *next_targ_id = m->type;
+ found = bpf_core_fields_are_compat(local_btf,
+ local_member->type,
+ targ_btf, m->type);
+ if (!found)
+ spec->len--; /* pop accessor */
+ return found;
+ }
+ /* member turned out not to be what we looked for */
+ spec->offset -= offset / 8;
+ spec->raw_len--;
+ }
+
+ return 0;
+}
+
+/*
+ * Try to match local spec to a target type and, if successful, produce full
+ * target spec (high-level, low-level + offset).
+ */
+static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
+ const struct btf *targ_btf, __u32 targ_id,
+ struct bpf_core_spec *targ_spec)
+{
+ const struct btf_type *targ_type;
+ const struct bpf_core_accessor *local_acc;
+ struct bpf_core_accessor *targ_acc;
+ int i, sz, matched;
+
+ memset(targ_spec, 0, sizeof(*targ_spec));
+ targ_spec->btf = targ_btf;
+
+ local_acc = &local_spec->spec[0];
+ targ_acc = &targ_spec->spec[0];
+
+ for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) {
+ targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id,
+ &targ_id);
+ if (!targ_type)
+ return -EINVAL;
+
+ if (local_acc->name) {
+ matched = bpf_core_match_member(local_spec->btf,
+ local_acc,
+ targ_btf, targ_id,
+ targ_spec, &targ_id);
+ if (matched <= 0)
+ return matched;
+ } else {
+ /* for i=0, targ_id is already treated as array element
+ * type (because it's the original struct), for others
+ * we should find array element type first
+ */
+ if (i > 0) {
+ const struct btf_array *a;
+
+ if (!btf_is_array(targ_type))
+ return 0;
+
+ a = btf_array(targ_type);
+ if (local_acc->idx >= a->nelems)
+ return 0;
+ if (!skip_mods_and_typedefs(targ_btf, a->type,
+ &targ_id))
+ return -EINVAL;
+ }
+
+ /* too deep struct/union/array nesting */
+ if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+ return -E2BIG;
+
+ targ_acc->type_id = targ_id;
+ targ_acc->idx = local_acc->idx;
+ targ_acc->name = NULL;
+ targ_spec->len++;
+ targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx;
+ targ_spec->raw_len++;
+
+ sz = btf__resolve_size(targ_btf, targ_id);
+ if (sz < 0)
+ return sz;
+ targ_spec->offset += local_acc->idx * sz;
+ }
+ }
+
+ return 1;
+}
+
+/*
+ * Patch relocatable BPF instruction.
+ * Expected insn->imm value is provided for validation, as well as the new
+ * relocated value.
+ *
+ * Currently three kinds of BPF instructions are supported:
+ * 1. rX = <imm> (assignment with immediate operand);
+ * 2. rX += <imm> (arithmetic operations with immediate operand);
+ * 3. *(rX) = <imm> (indirect memory assignment with immediate operand).
+ *
+ * If actual insn->imm value is wrong, bail out.
+ */
+static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off,
+ __u32 orig_off, __u32 new_off)
+{
+ struct bpf_insn *insn;
+ int insn_idx;
+ __u8 class;
+
+ if (insn_off % sizeof(struct bpf_insn))
+ return -EINVAL;
+ insn_idx = insn_off / sizeof(struct bpf_insn);
+
+ insn = &prog->insns[insn_idx];
+ class = BPF_CLASS(insn->code);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ if (BPF_SRC(insn->code) != BPF_K)
+ return -EINVAL;
+ if (insn->imm != orig_off)
+ return -EINVAL;
+ insn->imm = new_off;
+ pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
+ bpf_program__title(prog, false),
+ insn_idx, orig_off, new_off);
+ } else {
+ pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
+ bpf_program__title(prog, false),
+ insn_idx, insn->code, insn->src_reg, insn->dst_reg,
+ insn->off, insn->imm);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static struct btf *btf_load_raw(const char *path)
+{
+ struct btf *btf;
+ size_t read_cnt;
+ struct stat st;
+ void *data;
+ FILE *f;
+
+ if (stat(path, &st))
+ return ERR_PTR(-errno);
+
+ data = malloc(st.st_size);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ f = fopen(path, "rb");
+ if (!f) {
+ btf = ERR_PTR(-errno);
+ goto cleanup;
+ }
+
+ read_cnt = fread(data, 1, st.st_size, f);
+ fclose(f);
+ if (read_cnt < st.st_size) {
+ btf = ERR_PTR(-EBADF);
+ goto cleanup;
+ }
+
+ btf = btf__new(data, read_cnt);
+
+cleanup:
+ free(data);
+ return btf;
+}
+
+/*
+ * Probe few well-known locations for vmlinux kernel image and try to load BTF
+ * data out of it to use for target BTF.
+ */
+static struct btf *bpf_core_find_kernel_btf(void)
+{
+ struct {
+ const char *path_fmt;
+ bool raw_btf;
+ } locations[] = {
+ /* try canonical vmlinux BTF through sysfs first */
+ { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
+ /* fall back to trying to find vmlinux ELF on disk otherwise */
+ { "/boot/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/build/vmlinux" },
+ { "/usr/lib/modules/%1$s/kernel/vmlinux" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
+ { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+ };
+ char path[PATH_MAX + 1];
+ struct utsname buf;
+ struct btf *btf;
+ int i;
+
+ uname(&buf);
+
+ for (i = 0; i < ARRAY_SIZE(locations); i++) {
+ snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+
+ if (access(path, R_OK))
+ continue;
+
+ if (locations[i].raw_btf)
+ btf = btf_load_raw(path);
+ else
+ btf = btf__parse_elf(path, NULL);
+
+ pr_debug("loading kernel BTF '%s': %ld\n",
+ path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
+ if (IS_ERR(btf))
+ continue;
+
+ return btf;
+ }
+
+ pr_warning("failed to find valid kernel BTF\n");
+ return ERR_PTR(-ESRCH);
+}
+
+/* Output spec definition in the format:
+ * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
+ * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
+ */
+static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
+{
+ const struct btf_type *t;
+ const char *s;
+ __u32 type_id;
+ int i;
+
+ type_id = spec->spec[0].type_id;
+ t = btf__type_by_id(spec->btf, type_id);
+ s = btf__name_by_offset(spec->btf, t->name_off);
+ libbpf_print(level, "[%u] %s + ", type_id, s);
+
+ for (i = 0; i < spec->raw_len; i++)
+ libbpf_print(level, "%d%s", spec->raw_spec[i],
+ i == spec->raw_len - 1 ? " => " : ":");
+
+ libbpf_print(level, "%u @ &x", spec->offset);
+
+ for (i = 0; i < spec->len; i++) {
+ if (spec->spec[i].name)
+ libbpf_print(level, ".%s", spec->spec[i].name);
+ else
+ libbpf_print(level, "[%u]", spec->spec[i].idx);
+ }
+
+}
+
+static size_t bpf_core_hash_fn(const void *key, void *ctx)
+{
+ return (size_t)key;
+}
+
+static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+ return k1 == k2;
+}
+
+static void *u32_as_hash_key(__u32 x)
+{
+ return (void *)(uintptr_t)x;
+}
+
+/*
+ * CO-RE relocate single instruction.
+ *
+ * The outline and important points of the algorithm:
+ * 1. For given local type, find corresponding candidate target types.
+ * Candidate type is a type with the same "essential" name, ignoring
+ * everything after last triple underscore (___). E.g., `sample`,
+ * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates
+ * for each other. Names with triple underscore are referred to as
+ * "flavors" and are useful, among other things, to allow to
+ * specify/support incompatible variations of the same kernel struct, which
+ * might differ between different kernel versions and/or build
+ * configurations.
+ *
+ * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C
+ * converter, when deduplicated BTF of a kernel still contains more than
+ * one different types with the same name. In that case, ___2, ___3, etc
+ * are appended starting from second name conflict. But start flavors are
+ * also useful to be defined "locally", in BPF program, to extract same
+ * data from incompatible changes between different kernel
+ * versions/configurations. For instance, to handle field renames between
+ * kernel versions, one can use two flavors of the struct name with the
+ * same common name and use conditional relocations to extract that field,
+ * depending on target kernel version.
+ * 2. For each candidate type, try to match local specification to this
+ * candidate target type. Matching involves finding corresponding
+ * high-level spec accessors, meaning that all named fields should match,
+ * as well as all array accesses should be within the actual bounds. Also,
+ * types should be compatible (see bpf_core_fields_are_compat for details).
+ * 3. It is supported and expected that there might be multiple flavors
+ * matching the spec. As long as all the specs resolve to the same set of
+ * offsets across all candidates, there is not error. If there is any
+ * ambiguity, CO-RE relocation will fail. This is necessary to accomodate
+ * imprefection of BTF deduplication, which can cause slight duplication of
+ * the same BTF type, if some directly or indirectly referenced (by
+ * pointer) type gets resolved to different actual types in different
+ * object files. If such situation occurs, deduplicated BTF will end up
+ * with two (or more) structurally identical types, which differ only in
+ * types they refer to through pointer. This should be OK in most cases and
+ * is not an error.
+ * 4. Candidate types search is performed by linearly scanning through all
+ * types in target BTF. It is anticipated that this is overall more
+ * efficient memory-wise and not significantly worse (if not better)
+ * CPU-wise compared to prebuilding a map from all local type names to
+ * a list of candidate type names. It's also sped up by caching resolved
+ * list of matching candidates per each local "root" type ID, that has at
+ * least one bpf_offset_reloc associated with it. This list is shared
+ * between multiple relocations for the same type ID and is updated as some
+ * of the candidates are pruned due to structural incompatibility.
+ */
+static int bpf_core_reloc_offset(struct bpf_program *prog,
+ const struct bpf_offset_reloc *relo,
+ int relo_idx,
+ const struct btf *local_btf,
+ const struct btf *targ_btf,
+ struct hashmap *cand_cache)
+{
+ const char *prog_name = bpf_program__title(prog, false);
+ struct bpf_core_spec local_spec, cand_spec, targ_spec;
+ const void *type_key = u32_as_hash_key(relo->type_id);
+ const struct btf_type *local_type, *cand_type;
+ const char *local_name, *cand_name;
+ struct ids_vec *cand_ids;
+ __u32 local_id, cand_id;
+ const char *spec_str;
+ int i, j, err;
+
+ local_id = relo->type_id;
+ local_type = btf__type_by_id(local_btf, local_id);
+ if (!local_type)
+ return -EINVAL;
+
+ local_name = btf__name_by_offset(local_btf, local_type->name_off);
+ if (str_is_empty(local_name))
+ return -EINVAL;
+
+ spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
+ if (str_is_empty(spec_str))
+ return -EINVAL;
+
+ err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec);
+ if (err) {
+ pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n",
+ prog_name, relo_idx, local_id, local_name, spec_str,
+ err);
+ return -EINVAL;
+ }
+
+ pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx);
+ bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
+ libbpf_print(LIBBPF_DEBUG, "\n");
+
+ if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) {
+ cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf);
+ if (IS_ERR(cand_ids)) {
+ pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld",
+ prog_name, relo_idx, local_id, local_name,
+ PTR_ERR(cand_ids));
+ return PTR_ERR(cand_ids);
+ }
+ err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL);
+ if (err) {
+ bpf_core_free_cands(cand_ids);
+ return err;
+ }
+ }
+
+ for (i = 0, j = 0; i < cand_ids->len; i++) {
+ cand_id = cand_ids->data[i];
+ cand_type = btf__type_by_id(targ_btf, cand_id);
+ cand_name = btf__name_by_offset(targ_btf, cand_type->name_off);
+
+ err = bpf_core_spec_match(&local_spec, targ_btf,
+ cand_id, &cand_spec);
+ pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ",
+ prog_name, relo_idx, i, cand_name);
+ bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
+ libbpf_print(LIBBPF_DEBUG, ": %d\n", err);
+ if (err < 0) {
+ pr_warning("prog '%s': relo #%d: matching error: %d\n",
+ prog_name, relo_idx, err);
+ return err;
+ }
+ if (err == 0)
+ continue;
+
+ if (j == 0) {
+ targ_spec = cand_spec;
+ } else if (cand_spec.offset != targ_spec.offset) {
+ /* if there are many candidates, they should all
+ * resolve to the same offset
+ */
+ pr_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n",
+ prog_name, relo_idx, cand_spec.offset,
+ targ_spec.offset);
+ return -EINVAL;
+ }
+
+ cand_ids->data[j++] = cand_spec.spec[0].type_id;
+ }
+
+ cand_ids->len = j;
+ if (cand_ids->len == 0) {
+ pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n",
+ prog_name, relo_idx, local_id, local_name, spec_str);
+ return -ESRCH;
+ }
+
+ err = bpf_core_reloc_insn(prog, relo->insn_off,
+ local_spec.offset, targ_spec.offset);
+ if (err) {
+ pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n",
+ prog_name, relo_idx, relo->insn_off, err);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path)
+{
+ const struct btf_ext_info_sec *sec;
+ const struct bpf_offset_reloc *rec;
+ const struct btf_ext_info *seg;
+ struct hashmap_entry *entry;
+ struct hashmap *cand_cache = NULL;
+ struct bpf_program *prog;
+ struct btf *targ_btf;
+ const char *sec_name;
+ int i, err = 0;
+
+ if (targ_btf_path)
+ targ_btf = btf__parse_elf(targ_btf_path, NULL);
+ else
+ targ_btf = bpf_core_find_kernel_btf();
+ if (IS_ERR(targ_btf)) {
+ pr_warning("failed to get target BTF: %ld\n",
+ PTR_ERR(targ_btf));
+ return PTR_ERR(targ_btf);
+ }
+
+ cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL);
+ if (IS_ERR(cand_cache)) {
+ err = PTR_ERR(cand_cache);
+ goto out;
+ }
+
+ seg = &obj->btf_ext->offset_reloc_info;
+ for_each_btf_ext_sec(seg, sec) {
+ sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
+ if (str_is_empty(sec_name)) {
+ err = -EINVAL;
+ goto out;
+ }
+ prog = bpf_object__find_program_by_title(obj, sec_name);
+ if (!prog) {
+ pr_warning("failed to find program '%s' for CO-RE offset relocation\n",
+ sec_name);
+ err = -EINVAL;
+ goto out;
+ }
+
+ pr_debug("prog '%s': performing %d CO-RE offset relocs\n",
+ sec_name, sec->num_info);
+
+ for_each_btf_ext_rec(seg, sec, i, rec) {
+ err = bpf_core_reloc_offset(prog, rec, i, obj->btf,
+ targ_btf, cand_cache);
+ if (err) {
+ pr_warning("prog '%s': relo #%d: failed to relocate: %d\n",
+ sec_name, i, err);
+ goto out;
+ }
+ }
+ }
+
+out:
+ btf__free(targ_btf);
+ if (!IS_ERR_OR_NULL(cand_cache)) {
+ hashmap__for_each_entry(cand_cache, entry, i) {
+ bpf_core_free_cands(entry->value);
+ }
+ hashmap__free(cand_cache);
+ }
+ return err;
+}
+
+static int
+bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
+{
+ int err = 0;
+
+ if (obj->btf_ext->offset_reloc_info.len)
+ err = bpf_core_reloc_offsets(obj, targ_btf_path);
+
+ return err;
+}
+
+static int
bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
struct reloc_desc *relo)
{
struct bpf_insn *insn, *new_insn;
struct bpf_program *text;
size_t new_cnt;
+ int err;
if (relo->type != RELO_CALL)
return -LIBBPF_ERRNO__RELOC;
@@ -1197,6 +3214,15 @@
pr_warning("oom in prog realloc\n");
return -ENOMEM;
}
+
+ if (obj->btf_ext) {
+ err = bpf_program_reloc_btf_ext(prog, obj,
+ text->section_name,
+ prog->insns_cnt);
+ if (err)
+ return err;
+ }
+
memcpy(new_insn + prog->insns_cnt, text->insns,
text->insns_cnt * sizeof(*insn));
prog->insns = new_insn;
@@ -1216,25 +3242,43 @@
{
int i, err;
- if (!prog || !prog->reloc_desc)
+ if (!prog)
+ return 0;
+
+ if (obj->btf_ext) {
+ err = bpf_program_reloc_btf_ext(prog, obj,
+ prog->section_name, 0);
+ if (err)
+ return err;
+ }
+
+ if (!prog->reloc_desc)
return 0;
for (i = 0; i < prog->nr_reloc; i++) {
- if (prog->reloc_desc[i].type == RELO_LD64) {
+ if (prog->reloc_desc[i].type == RELO_LD64 ||
+ prog->reloc_desc[i].type == RELO_DATA) {
+ bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
struct bpf_insn *insns = prog->insns;
int insn_idx, map_idx;
insn_idx = prog->reloc_desc[i].insn_idx;
map_idx = prog->reloc_desc[i].map_idx;
- if (insn_idx >= (int)prog->insns_cnt) {
+ if (insn_idx + 1 >= (int)prog->insns_cnt) {
pr_warning("relocation out of range: '%s'\n",
prog->section_name);
return -LIBBPF_ERRNO__RELOC;
}
- insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+
+ if (!relo_data) {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+ } else {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
+ insns[insn_idx + 1].imm = insns[insn_idx].imm;
+ }
insns[insn_idx].imm = obj->maps[map_idx].fd;
- } else {
+ } else if (prog->reloc_desc[i].type == RELO_CALL) {
err = bpf_program__reloc_text(prog, obj,
&prog->reloc_desc[i]);
if (err)
@@ -1247,14 +3291,21 @@
return 0;
}
-
static int
-bpf_object__relocate(struct bpf_object *obj)
+bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
{
struct bpf_program *prog;
size_t i;
int err;
+ if (obj->btf_ext) {
+ err = bpf_object__relocate_core(obj, targ_btf_path);
+ if (err) {
+ pr_warning("failed to perform CO-RE relocations: %d\n",
+ err);
+ return err;
+ }
+ }
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
@@ -1294,9 +3345,7 @@
return -LIBBPF_ERRNO__RELOC;
}
- err = bpf_program__collect_reloc(prog,
- shdr, data,
- obj);
+ err = bpf_program__collect_reloc(prog, shdr, data, obj);
if (err)
return err;
}
@@ -1304,42 +3353,65 @@
}
static int
-load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
- const char *name, struct bpf_insn *insns, int insns_cnt,
- char *license, u32 kern_version, int *pfd, int prog_ifindex)
+load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
+ char *license, __u32 kern_version, int *pfd)
{
struct bpf_load_program_attr load_attr;
char *cp, errmsg[STRERR_BUFSIZE];
+ int log_buf_size = BPF_LOG_BUF_SIZE;
char *log_buf;
- int ret;
+ int btf_fd, ret;
+
+ if (!insns || !insns_cnt)
+ return -EINVAL;
memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
- load_attr.prog_type = type;
- load_attr.expected_attach_type = expected_attach_type;
- load_attr.name = name;
+ load_attr.prog_type = prog->type;
+ load_attr.expected_attach_type = prog->expected_attach_type;
+ if (prog->caps->name)
+ load_attr.name = prog->name;
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
load_attr.kern_version = kern_version;
- load_attr.prog_ifindex = prog_ifindex;
+ load_attr.prog_ifindex = prog->prog_ifindex;
+ /* if .BTF.ext was loaded, kernel supports associated BTF for prog */
+ if (prog->obj->btf_ext)
+ btf_fd = bpf_object__btf_fd(prog->obj);
+ else
+ btf_fd = -1;
+ load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0;
+ load_attr.func_info = prog->func_info;
+ load_attr.func_info_rec_size = prog->func_info_rec_size;
+ load_attr.func_info_cnt = prog->func_info_cnt;
+ load_attr.line_info = prog->line_info;
+ load_attr.line_info_rec_size = prog->line_info_rec_size;
+ load_attr.line_info_cnt = prog->line_info_cnt;
+ load_attr.log_level = prog->log_level;
+ load_attr.prog_flags = prog->prog_flags;
- if (!load_attr.insns || !load_attr.insns_cnt)
- return -EINVAL;
-
- log_buf = malloc(BPF_LOG_BUF_SIZE);
+retry_load:
+ log_buf = malloc(log_buf_size);
if (!log_buf)
pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
- ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
+ ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
if (ret >= 0) {
+ if (load_attr.log_level)
+ pr_debug("verifier log:\n%s", log_buf);
*pfd = ret;
ret = 0;
goto out;
}
+ if (errno == ENOSPC) {
+ log_buf_size <<= 1;
+ free(log_buf);
+ goto retry_load;
+ }
ret = -LIBBPF_ERRNO__LOAD;
- cp = str_error(errno, errmsg, sizeof(errmsg));
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("load bpf program failed: %s\n", cp);
if (log_buf && log_buf[0] != '\0') {
@@ -1375,9 +3447,9 @@
return ret;
}
-static int
+int
bpf_program__load(struct bpf_program *prog,
- char *license, u32 kern_version)
+ char *license, __u32 kern_version)
{
int err = 0, fd, i;
@@ -1402,10 +3474,8 @@
pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
prog->section_name, prog->instances.nr);
}
- err = load_program(prog->type, prog->expected_attach_type,
- prog->name, prog->insns, prog->insns_cnt,
- license, kern_version, &fd,
- prog->prog_ifindex);
+ err = load_program(prog, prog->insns, prog->insns_cnt,
+ license, kern_version, &fd);
if (!err)
prog->instances.fds[0] = fd;
goto out;
@@ -1415,7 +3485,7 @@
struct bpf_prog_prep_result result;
bpf_program_prep_t preprocessor = prog->preprocessor;
- bzero(&result, sizeof(result));
+ memset(&result, 0, sizeof(result));
err = preprocessor(prog, i, prog->insns,
prog->insns_cnt, &result);
if (err) {
@@ -1433,11 +3503,9 @@
continue;
}
- err = load_program(prog->type, prog->expected_attach_type,
- prog->name, result.new_insn_ptr,
+ err = load_program(prog, result.new_insn_ptr,
result.new_insn_cnt,
- license, kern_version, &fd,
- prog->prog_ifindex);
+ license, kern_version, &fd);
if (err) {
pr_warning("Loading the %dth instance of program '%s' failed\n",
@@ -1458,14 +3526,14 @@
return err;
}
-static bool bpf_program__is_function_storage(struct bpf_program *prog,
- struct bpf_object *obj)
+static bool bpf_program__is_function_storage(const struct bpf_program *prog,
+ const struct bpf_object *obj)
{
return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
}
static int
-bpf_object__load_progs(struct bpf_object *obj)
+bpf_object__load_progs(struct bpf_object *obj, int log_level)
{
size_t i;
int err;
@@ -1473,6 +3541,7 @@
for (i = 0; i < obj->nr_programs; i++) {
if (bpf_program__is_function_storage(&obj->programs[i], obj))
continue;
+ obj->programs[i].log_level |= log_level;
err = bpf_program__load(&obj->programs[i],
obj->license,
obj->kern_version);
@@ -1502,12 +3571,16 @@
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
case BPF_PROG_TYPE_LIRC_MODE2:
case BPF_PROG_TYPE_SK_REUSEPORT:
- return false;
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_UNSPEC:
- case BPF_PROG_TYPE_KPROBE:
case BPF_PROG_TYPE_TRACEPOINT:
- case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ return false;
+ case BPF_PROG_TYPE_KPROBE:
default:
return true;
}
@@ -1525,7 +3598,7 @@
static struct bpf_object *
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
- bool needs_kver)
+ bool needs_kver, int flags)
{
struct bpf_object *obj;
int err;
@@ -1541,7 +3614,8 @@
CHECK_ERR(bpf_object__elf_init(obj), err, out);
CHECK_ERR(bpf_object__check_endianness(obj), err, out);
- CHECK_ERR(bpf_object__elf_collect(obj), err, out);
+ CHECK_ERR(bpf_object__probe_caps(obj), err, out);
+ CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
@@ -1552,7 +3626,8 @@
return ERR_PTR(err);
}
-struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
+struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
+ int flags)
{
/* param validation */
if (!attr->file)
@@ -1561,7 +3636,13 @@
pr_debug("loading %s\n", attr->file);
return __bpf_object__open(attr->file, NULL, 0,
- bpf_prog_type__needs_kver(attr->prog_type));
+ bpf_prog_type__needs_kver(attr->prog_type),
+ flags);
+}
+
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
+{
+ return __bpf_object__open_xattr(attr, 0);
}
struct bpf_object *bpf_object__open(const char *path)
@@ -1588,13 +3669,11 @@
snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
(unsigned long)obj_buf,
(unsigned long)obj_buf_sz);
- tmp_name[sizeof(tmp_name) - 1] = '\0';
name = tmp_name;
}
- pr_debug("loading object '%s' from buffer\n",
- name);
+ pr_debug("loading object '%s' from buffer\n", name);
- return __bpf_object__open(name, obj_buf, obj_buf_sz, true);
+ return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
}
int bpf_object__unload(struct bpf_object *obj)
@@ -1613,10 +3692,14 @@
return 0;
}
-int bpf_object__load(struct bpf_object *obj)
+int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
{
+ struct bpf_object *obj;
int err;
+ if (!attr)
+ return -EINVAL;
+ obj = attr->obj;
if (!obj)
return -EINVAL;
@@ -1628,8 +3711,8 @@
obj->loaded = true;
CHECK_ERR(bpf_object__create_maps(obj), err, out);
- CHECK_ERR(bpf_object__relocate(obj), err, out);
- CHECK_ERR(bpf_object__load_progs(obj), err, out);
+ CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out);
+ CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out);
return 0;
out:
@@ -1638,6 +3721,15 @@
return err;
}
+int bpf_object__load(struct bpf_object *obj)
+{
+ struct bpf_object_load_attr attr = {
+ .obj = obj,
+ };
+
+ return bpf_object__load_xattr(&attr);
+}
+
static int check_path(const char *path)
{
char *cp, errmsg[STRERR_BUFSIZE];
@@ -1654,7 +3746,7 @@
dir = dirname(dname);
if (statfs(dir, &st_fs)) {
- cp = str_error(errno, errmsg, sizeof(errmsg));
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("failed to statfs %s: %s\n", dir, cp);
err = -errno;
}
@@ -1690,7 +3782,7 @@
}
if (bpf_obj_pin(prog->instances.fds[instance], path)) {
- cp = str_error(errno, errmsg, sizeof(errmsg));
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("failed to pin program: %s\n", cp);
return -errno;
}
@@ -1699,6 +3791,34 @@
return 0;
}
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
+ int instance)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (instance < 0 || instance >= prog->instances.nr) {
+ pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->section_name, prog->instances.nr);
+ return -EINVAL;
+ }
+
+ err = unlink(path);
+ if (err != 0)
+ return -errno;
+ pr_debug("unpinned program '%s'\n", path);
+
+ return 0;
+}
+
static int make_dir(const char *path)
{
char *cp, errmsg[STRERR_BUFSIZE];
@@ -1708,7 +3828,7 @@
err = -errno;
if (err) {
- cp = str_error(-err, errmsg, sizeof(errmsg));
+ cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
pr_warning("failed to mkdir %s: %s\n", path, cp);
}
return err;
@@ -1733,6 +3853,11 @@
return -EINVAL;
}
+ if (prog->instances.nr == 1) {
+ /* don't create subdirs when pinning single instance */
+ return bpf_program__pin_instance(prog, path, 0);
+ }
+
err = make_dir(path);
if (err)
return err;
@@ -1742,16 +3867,83 @@
int len;
len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin;
+ }
+
+ err = bpf_program__pin_instance(prog, buf, i);
+ if (err)
+ goto err_unpin;
+ }
+
+ return 0;
+
+err_unpin:
+ for (i = i - 1; i >= 0; i--) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+ if (len < 0)
+ continue;
+ else if (len >= PATH_MAX)
+ continue;
+
+ bpf_program__unpin_instance(prog, buf, i);
+ }
+
+ rmdir(path);
+
+ return err;
+}
+
+int bpf_program__unpin(struct bpf_program *prog, const char *path)
+{
+ int i, err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (prog->instances.nr <= 0) {
+ pr_warning("no instances of prog %s to pin\n",
+ prog->section_name);
+ return -EINVAL;
+ }
+
+ if (prog->instances.nr == 1) {
+ /* don't create subdirs when pinning single instance */
+ return bpf_program__unpin_instance(prog, path, 0);
+ }
+
+ for (i = 0; i < prog->instances.nr; i++) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
if (len < 0)
return -EINVAL;
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
- err = bpf_program__pin_instance(prog, buf, i);
+ err = bpf_program__unpin_instance(prog, buf, i);
if (err)
return err;
}
+ err = rmdir(path);
+ if (err)
+ return -errno;
+
return 0;
}
@@ -1770,18 +3962,39 @@
}
if (bpf_obj_pin(map->fd, path)) {
- cp = str_error(errno, errmsg, sizeof(errmsg));
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("failed to pin map: %s\n", cp);
return -errno;
}
pr_debug("pinned map '%s'\n", path);
+
return 0;
}
-int bpf_object__pin(struct bpf_object *obj, const char *path)
+int bpf_map__unpin(struct bpf_map *map, const char *path)
{
- struct bpf_program *prog;
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (map == NULL) {
+ pr_warning("invalid map pointer\n");
+ return -EINVAL;
+ }
+
+ err = unlink(path);
+ if (err != 0)
+ return -errno;
+ pr_debug("unpinned map '%s'\n", path);
+
+ return 0;
+}
+
+int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
+{
struct bpf_map *map;
int err;
@@ -1797,7 +4010,54 @@
if (err)
return err;
- bpf_map__for_each(map, obj) {
+ bpf_object__for_each_map(map, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_maps;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_maps;
+ }
+
+ err = bpf_map__pin(map, buf);
+ if (err)
+ goto err_unpin_maps;
+ }
+
+ return 0;
+
+err_unpin_maps:
+ while ((map = bpf_map__prev(map, obj))) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ continue;
+ else if (len >= PATH_MAX)
+ continue;
+
+ bpf_map__unpin(map, buf);
+ }
+
+ return err;
+}
+
+int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
+{
+ struct bpf_map *map;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ bpf_object__for_each_map(map, obj) {
char buf[PATH_MAX];
int len;
@@ -1808,23 +4068,90 @@
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
- err = bpf_map__pin(map, buf);
+ err = bpf_map__unpin(map, buf);
if (err)
return err;
}
+ return 0;
+}
+
+int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
+{
+ struct bpf_program *prog;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ if (!obj->loaded) {
+ pr_warning("object not yet loaded; load it first\n");
+ return -ENOENT;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
bpf_object__for_each_program(prog, obj) {
char buf[PATH_MAX];
int len;
len = snprintf(buf, PATH_MAX, "%s/%s", path,
- prog->section_name);
+ prog->pin_name);
+ if (len < 0) {
+ err = -EINVAL;
+ goto err_unpin_programs;
+ } else if (len >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto err_unpin_programs;
+ }
+
+ err = bpf_program__pin(prog, buf);
+ if (err)
+ goto err_unpin_programs;
+ }
+
+ return 0;
+
+err_unpin_programs:
+ while ((prog = bpf_program__prev(prog, obj))) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->pin_name);
+ if (len < 0)
+ continue;
+ else if (len >= PATH_MAX)
+ continue;
+
+ bpf_program__unpin(prog, buf);
+ }
+
+ return err;
+}
+
+int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
+{
+ struct bpf_program *prog;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ bpf_object__for_each_program(prog, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->pin_name);
if (len < 0)
return -EINVAL;
else if (len >= PATH_MAX)
return -ENAMETOOLONG;
- err = bpf_program__pin(prog, buf);
+ err = bpf_program__unpin(prog, buf);
if (err)
return err;
}
@@ -1832,6 +4159,23 @@
return 0;
}
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+ int err;
+
+ err = bpf_object__pin_maps(obj, path);
+ if (err)
+ return err;
+
+ err = bpf_object__pin_programs(obj, path);
+ if (err) {
+ bpf_object__unpin_maps(obj, path);
+ return err;
+ }
+
+ return 0;
+}
+
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
@@ -1845,6 +4189,7 @@
bpf_object__elf_finish(obj);
bpf_object__unload(obj);
btf__free(obj->btf);
+ btf_ext__free(obj->btf_ext);
for (i = 0; i < obj->nr_maps; i++) {
zfree(&obj->maps[i].name);
@@ -1854,6 +4199,9 @@
obj->maps[i].priv = NULL;
obj->maps[i].clear_priv = NULL;
}
+
+ zfree(&obj->sections.rodata);
+ zfree(&obj->sections.data);
zfree(&obj->maps);
obj->nr_maps = 0;
@@ -1886,16 +4234,21 @@
return next;
}
-const char *bpf_object__name(struct bpf_object *obj)
+const char *bpf_object__name(const struct bpf_object *obj)
{
return obj ? obj->path : ERR_PTR(-EINVAL);
}
-unsigned int bpf_object__kversion(struct bpf_object *obj)
+unsigned int bpf_object__kversion(const struct bpf_object *obj)
{
return obj ? obj->kern_version : 0;
}
+struct btf *bpf_object__btf(const struct bpf_object *obj)
+{
+ return obj ? obj->btf : NULL;
+}
+
int bpf_object__btf_fd(const struct bpf_object *obj)
{
return obj->btf ? btf__fd(obj->btf) : -1;
@@ -1912,40 +4265,56 @@
return 0;
}
-void *bpf_object__priv(struct bpf_object *obj)
+void *bpf_object__priv(const struct bpf_object *obj)
{
return obj ? obj->priv : ERR_PTR(-EINVAL);
}
static struct bpf_program *
-__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
+ bool forward)
{
- size_t idx;
+ size_t nr_programs = obj->nr_programs;
+ ssize_t idx;
- if (!obj->programs)
+ if (!nr_programs)
return NULL;
- /* First handler */
- if (prev == NULL)
- return &obj->programs[0];
- if (prev->obj != obj) {
+ if (!p)
+ /* Iter from the beginning */
+ return forward ? &obj->programs[0] :
+ &obj->programs[nr_programs - 1];
+
+ if (p->obj != obj) {
pr_warning("error: program handler doesn't match object\n");
return NULL;
}
- idx = (prev - obj->programs) + 1;
- if (idx >= obj->nr_programs)
+ idx = (p - obj->programs) + (forward ? 1 : -1);
+ if (idx >= obj->nr_programs || idx < 0)
return NULL;
return &obj->programs[idx];
}
struct bpf_program *
-bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
{
struct bpf_program *prog = prev;
do {
- prog = __bpf_program__next(prog, obj);
+ prog = __bpf_program__iter(prog, obj, true);
+ } while (prog && bpf_program__is_function_storage(prog, obj));
+
+ return prog;
+}
+
+struct bpf_program *
+bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj)
+{
+ struct bpf_program *prog = next;
+
+ do {
+ prog = __bpf_program__iter(prog, obj, false);
} while (prog && bpf_program__is_function_storage(prog, obj));
return prog;
@@ -1962,7 +4331,7 @@
return 0;
}
-void *bpf_program__priv(struct bpf_program *prog)
+void *bpf_program__priv(const struct bpf_program *prog)
{
return prog ? prog->priv : ERR_PTR(-EINVAL);
}
@@ -1972,7 +4341,7 @@
prog->prog_ifindex = ifindex;
}
-const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
+const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
{
const char *title;
@@ -1988,7 +4357,7 @@
return title;
}
-int bpf_program__fd(struct bpf_program *prog)
+int bpf_program__fd(const struct bpf_program *prog)
{
return bpf_program__nth_fd(prog, 0);
}
@@ -2021,7 +4390,7 @@
return 0;
}
-int bpf_program__nth_fd(struct bpf_program *prog, int n)
+int bpf_program__nth_fd(const struct bpf_program *prog, int n)
{
int fd;
@@ -2049,25 +4418,25 @@
prog->type = type;
}
-static bool bpf_program__is_type(struct bpf_program *prog,
+static bool bpf_program__is_type(const struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
-#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
-int bpf_program__set_##NAME(struct bpf_program *prog) \
-{ \
- if (!prog) \
- return -EINVAL; \
- bpf_program__set_type(prog, TYPE); \
- return 0; \
-} \
- \
-bool bpf_program__is_##NAME(struct bpf_program *prog) \
-{ \
- return bpf_program__is_type(prog, TYPE); \
-} \
+#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
+int bpf_program__set_##NAME(struct bpf_program *prog) \
+{ \
+ if (!prog) \
+ return -EINVAL; \
+ bpf_program__set_type(prog, TYPE); \
+ return 0; \
+} \
+ \
+bool bpf_program__is_##NAME(const struct bpf_program *prog) \
+{ \
+ return bpf_program__is_type(prog, TYPE); \
+} \
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
@@ -2084,61 +4453,134 @@
prog->expected_attach_type = type;
}
-#define BPF_PROG_SEC_FULL(string, ptype, atype) \
- { string, sizeof(string) - 1, ptype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
+ { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0)
+/* Programs that can NOT be attached. */
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
-#define BPF_S_PROG_SEC(string, ptype) \
- BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype)
+/* Programs that can be attached. */
+#define BPF_APROG_SEC(string, ptype, atype) \
+ BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
-#define BPF_SA_PROG_SEC(string, ptype) \
- BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype)
+/* Programs that must specify expected attach type at load time. */
+#define BPF_EAPROG_SEC(string, ptype, eatype) \
+ BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
+
+/* Programs that can be attached but attach type can't be identified by section
+ * name. Kept for backward compatibility.
+ */
+#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
static const struct {
const char *sec;
size_t len;
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
+ int is_attachable;
+ enum bpf_attach_type attach_type;
} section_names[] = {
- BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER),
- BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE),
- BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE),
- BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS),
- BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT),
- BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT),
- BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT),
- BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
- BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
- BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB),
- BPF_PROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK),
- BPF_PROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE),
- BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
- BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT),
- BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT),
- BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL),
- BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS),
- BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
- BPF_PROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG),
- BPF_PROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2),
- BPF_SA_PROG_SEC("cgroup/bind4", BPF_CGROUP_INET4_BIND),
- BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
- BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
- BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT),
- BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG),
- BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG),
- BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND),
- BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND),
+ BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER),
+ BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE),
+ BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE),
+ BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS),
+ BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT),
+ BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT),
+ BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT),
+ BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
+ BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
+ BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
+ BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT),
+ BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT),
+ BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL),
+ BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_CGROUP_INET_INGRESS),
+ BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_CGROUP_INET_EGRESS),
+ BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB),
+ BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_CGROUP_INET_SOCK_CREATE),
+ BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_CGROUP_INET4_POST_BIND),
+ BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_CGROUP_INET6_POST_BIND),
+ BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE,
+ BPF_CGROUP_DEVICE),
+ BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS,
+ BPF_CGROUP_SOCK_OPS),
+ BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB,
+ BPF_SK_SKB_STREAM_PARSER),
+ BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB,
+ BPF_SK_SKB_STREAM_VERDICT),
+ BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB),
+ BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG,
+ BPF_SK_MSG_VERDICT),
+ BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2,
+ BPF_LIRC_MODE2),
+ BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR,
+ BPF_FLOW_DISSECTOR),
+ BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET4_BIND),
+ BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET6_BIND),
+ BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET4_CONNECT),
+ BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_INET6_CONNECT),
+ BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_UDP4_SENDMSG),
+ BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_UDP6_SENDMSG),
+ BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_UDP4_RECVMSG),
+ BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_CGROUP_UDP6_RECVMSG),
+ BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_CGROUP_SYSCTL),
+ BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_GETSOCKOPT),
+ BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_SETSOCKOPT),
};
+#undef BPF_PROG_SEC_IMPL
#undef BPF_PROG_SEC
-#undef BPF_PROG_SEC_FULL
-#undef BPF_S_PROG_SEC
-#undef BPF_SA_PROG_SEC
+#undef BPF_APROG_SEC
+#undef BPF_EAPROG_SEC
+#undef BPF_APROG_COMPAT
+
+#define MAX_TYPE_NAME_SIZE 32
+
+static char *libbpf_get_type_names(bool attach_type)
+{
+ int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE;
+ char *buf;
+
+ buf = malloc(len);
+ if (!buf)
+ return NULL;
+
+ buf[0] = '\0';
+ /* Forge string buf with all available names */
+ for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+ if (attach_type && !section_names[i].is_attachable)
+ continue;
+
+ if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) {
+ free(buf);
+ return NULL;
+ }
+ strcat(buf, " ");
+ strcat(buf, section_names[i].sec);
+ }
+
+ return buf;
+}
int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
enum bpf_attach_type *expected_attach_type)
{
+ char *type_names;
int i;
if (!name)
@@ -2151,6 +4593,40 @@
*expected_attach_type = section_names[i].expected_attach_type;
return 0;
}
+ pr_warning("failed to guess program type based on ELF section name '%s'\n", name);
+ type_names = libbpf_get_type_names(false);
+ if (type_names != NULL) {
+ pr_info("supported section(type) names are:%s\n", type_names);
+ free(type_names);
+ }
+
+ return -EINVAL;
+}
+
+int libbpf_attach_type_by_name(const char *name,
+ enum bpf_attach_type *attach_type)
+{
+ char *type_names;
+ int i;
+
+ if (!name)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+ if (strncmp(name, section_names[i].sec, section_names[i].len))
+ continue;
+ if (!section_names[i].is_attachable)
+ return -EINVAL;
+ *attach_type = section_names[i].attach_type;
+ return 0;
+ }
+ pr_warning("failed to guess attach type based on ELF section name '%s'\n", name);
+ type_names = libbpf_get_type_names(true);
+ if (type_names != NULL) {
+ pr_info("attachable section(type) names are:%s\n", type_names);
+ free(type_names);
+ }
+
return -EINVAL;
}
@@ -2163,17 +4639,17 @@
expected_attach_type);
}
-int bpf_map__fd(struct bpf_map *map)
+int bpf_map__fd(const struct bpf_map *map)
{
return map ? map->fd : -EINVAL;
}
-const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
+const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
{
return map ? &map->def : ERR_PTR(-EINVAL);
}
-const char *bpf_map__name(struct bpf_map *map)
+const char *bpf_map__name(const struct bpf_map *map)
{
return map ? map->name : NULL;
}
@@ -2204,25 +4680,44 @@
return 0;
}
-void *bpf_map__priv(struct bpf_map *map)
+void *bpf_map__priv(const struct bpf_map *map)
{
return map ? map->priv : ERR_PTR(-EINVAL);
}
-bool bpf_map__is_offload_neutral(struct bpf_map *map)
+bool bpf_map__is_offload_neutral(const struct bpf_map *map)
{
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
+bool bpf_map__is_internal(const struct bpf_map *map)
+{
+ return map->libbpf_type != LIBBPF_MAP_UNSPEC;
+}
+
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
map->map_ifindex = ifindex;
}
-struct bpf_map *
-bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
{
- size_t idx;
+ if (!bpf_map_type__is_map_in_map(map->def.type)) {
+ pr_warning("error: unsupported map type\n");
+ return -EINVAL;
+ }
+ if (map->inner_map_fd != -1) {
+ pr_warning("error: inner_map_fd already specified\n");
+ return -EINVAL;
+ }
+ map->inner_map_fd = fd;
+ return 0;
+}
+
+static struct bpf_map *
+__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
+{
+ ssize_t idx;
struct bpf_map *s, *e;
if (!obj || !obj->maps)
@@ -2231,50 +4726,66 @@
s = obj->maps;
e = obj->maps + obj->nr_maps;
- if (prev == NULL)
- return s;
-
- if ((prev < s) || (prev >= e)) {
+ if ((m < s) || (m >= e)) {
pr_warning("error in %s: map handler doesn't belong to object\n",
__func__);
return NULL;
}
- idx = (prev - obj->maps) + 1;
- if (idx >= obj->nr_maps)
+ idx = (m - obj->maps) + i;
+ if (idx >= obj->nr_maps || idx < 0)
return NULL;
return &obj->maps[idx];
}
struct bpf_map *
-bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
+bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
+{
+ if (prev == NULL)
+ return obj->maps;
+
+ return __bpf_map__iter(prev, obj, 1);
+}
+
+struct bpf_map *
+bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj)
+{
+ if (next == NULL) {
+ if (!obj->nr_maps)
+ return NULL;
+ return obj->maps + obj->nr_maps - 1;
+ }
+
+ return __bpf_map__iter(next, obj, -1);
+}
+
+struct bpf_map *
+bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
{
struct bpf_map *pos;
- bpf_map__for_each(pos, obj) {
+ bpf_object__for_each_map(pos, obj) {
if (pos->name && !strcmp(pos->name, name))
return pos;
}
return NULL;
}
+int
+bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
+{
+ return bpf_map__fd(bpf_object__find_map_by_name(obj, name));
+}
+
struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
- int i;
-
- for (i = 0; i < obj->nr_maps; i++) {
- if (obj->maps[i].offset == offset)
- return &obj->maps[i];
- }
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(-ENOTSUP);
}
long libbpf_get_error(const void *ptr)
{
- if (IS_ERR(ptr))
- return PTR_ERR(ptr);
- return 0;
+ return PTR_ERR_OR_ZERO(ptr);
}
int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -2293,10 +4804,7 @@
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd)
{
- struct bpf_object_open_attr open_attr = {
- .file = attr->file,
- .prog_type = attr->prog_type,
- };
+ struct bpf_object_open_attr open_attr = {};
struct bpf_program *prog, *first_prog = NULL;
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
@@ -2309,6 +4817,9 @@
if (!attr->file)
return -EINVAL;
+ open_attr.file = attr->file;
+ open_attr.prog_type = attr->prog_type;
+
obj = bpf_object__open_xattr(&open_attr);
if (IS_ERR_OR_NULL(obj))
return -ENOENT;
@@ -2325,8 +4836,6 @@
err = bpf_program__identify_section(prog, &prog_type,
&expected_attach_type);
if (err < 0) {
- pr_warning("failed to guess program type based on section name %s\n",
- prog->section_name);
bpf_object__close(obj);
return -EINVAL;
}
@@ -2336,11 +4845,13 @@
bpf_program__set_expected_attach_type(prog,
expected_attach_type);
- if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
+ prog->log_level = attr->log_level;
+ prog->prog_flags = attr->prog_flags;
+ if (!first_prog)
first_prog = prog;
}
- bpf_map__for_each(map, obj) {
+ bpf_object__for_each_map(map, obj) {
if (!bpf_map__is_offload_neutral(map))
map->map_ifindex = attr->ifindex;
}
@@ -2362,62 +4873,1087 @@
return 0;
}
-enum bpf_perf_event_ret
-bpf_perf_event_read_simple(void *mem, unsigned long size,
- unsigned long page_size, void **buf, size_t *buf_len,
- bpf_perf_event_print_t fn, void *priv)
+struct bpf_link {
+ int (*destroy)(struct bpf_link *link);
+};
+
+int bpf_link__destroy(struct bpf_link *link)
{
- volatile struct perf_event_mmap_page *header = mem;
+ int err;
+
+ if (!link)
+ return 0;
+
+ err = link->destroy(link);
+ free(link);
+
+ return err;
+}
+
+struct bpf_link_fd {
+ struct bpf_link link; /* has to be at the top of struct */
+ int fd; /* hook FD */
+};
+
+static int bpf_link__destroy_perf_event(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ int err;
+
+ err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+ if (err)
+ err = -errno;
+
+ close(l->fd);
+ return err;
+}
+
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
+ int pfd)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, err;
+
+ if (pfd < 0) {
+ pr_warning("program '%s': invalid perf event FD %d\n",
+ bpf_program__title(prog, false), pfd);
+ return ERR_PTR(-EINVAL);
+ }
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach BPF program w/o FD (did you load it?)\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->link.destroy = &bpf_link__destroy_perf_event;
+ link->fd = pfd;
+
+ if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to enable pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ return (struct bpf_link *)link;
+}
+
+/*
+ * this function is expected to parse integer in the range of [0, 2^31-1] from
+ * given file using scanf format string fmt. If actual parsed value is
+ * negative, the result might be indistinguishable from error
+ */
+static int parse_uint_from_file(const char *file, const char *fmt)
+{
+ char buf[STRERR_BUFSIZE];
+ int err, ret;
+ FILE *f;
+
+ f = fopen(file, "r");
+ if (!f) {
+ err = -errno;
+ pr_debug("failed to open '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ return err;
+ }
+ err = fscanf(f, fmt, &ret);
+ if (err != 1) {
+ err = err == EOF ? -EIO : -errno;
+ pr_debug("failed to parse '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ fclose(f);
+ return err;
+ }
+ fclose(f);
+ return ret;
+}
+
+static int determine_kprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/type";
+
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_uprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/type";
+
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_kprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe";
+
+ return parse_uint_from_file(file, "config:%d\n");
+}
+
+static int determine_uprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe";
+
+ return parse_uint_from_file(file, "config:%d\n");
+}
+
+static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
+ uint64_t offset, int pid)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int type, pfd, err;
+
+ type = uprobe ? determine_uprobe_perf_type()
+ : determine_kprobe_perf_type();
+ if (type < 0) {
+ pr_warning("failed to determine %s perf type: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+ return type;
+ }
+ if (retprobe) {
+ int bit = uprobe ? determine_uprobe_retprobe_bit()
+ : determine_kprobe_retprobe_bit();
+
+ if (bit < 0) {
+ pr_warning("failed to determine %s retprobe bit: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(bit, errmsg,
+ sizeof(errmsg)));
+ return bit;
+ }
+ attr.config |= 1 << bit;
+ }
+ attr.size = sizeof(attr);
+ attr.type = type;
+ attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
+ attr.config2 = offset; /* kprobe_addr or probe_offset */
+
+ /* pid filter is meaningful only for uprobes */
+ pfd = syscall(__NR_perf_event_open, &attr,
+ pid < 0 ? -1 : pid /* pid */,
+ pid == -1 ? 0 : -1 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("%s perf_event_open() failed: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+ bool retprobe,
+ const char *func_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
+ 0 /* offset */, -1 /* pid */);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+ bool retprobe, pid_t pid,
+ const char *binary_path,
+ size_t func_offset)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(true /* uprobe */, retprobe,
+ binary_path, func_offset, pid);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s:0x%zx': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+static int determine_tracepoint_id(const char *tp_category,
+ const char *tp_name)
+{
+ char file[PATH_MAX];
+ int ret;
+
+ ret = snprintf(file, sizeof(file),
+ "/sys/kernel/debug/tracing/events/%s/%s/id",
+ tp_category, tp_name);
+ if (ret < 0)
+ return -errno;
+ if (ret >= sizeof(file)) {
+ pr_debug("tracepoint %s/%s path is too long\n",
+ tp_category, tp_name);
+ return -E2BIG;
+ }
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_open_tracepoint(const char *tp_category,
+ const char *tp_name)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int tp_id, pfd, err;
+
+ tp_id = determine_tracepoint_id(tp_category, tp_name);
+ if (tp_id < 0) {
+ pr_warning("failed to determine tracepoint '%s/%s' perf event ID: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg)));
+ return tp_id;
+ }
+
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.size = sizeof(attr);
+ attr.config = tp_id;
+
+ pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_tracepoint(tp_category, tp_name);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to tracepoint '%s/%s': %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+static int bpf_link__destroy_fd(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+
+ return close(l->fd);
+}
+
+struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, pfd;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach before loaded\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->link.destroy = &bpf_link__destroy_fd;
+
+ pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
+ if (pfd < 0) {
+ pfd = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to raw tracepoint '%s': %s\n",
+ bpf_program__title(prog, false), tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link->fd = pfd;
+ return (struct bpf_link *)link;
+}
+
+enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+ void **copy_mem, size_t *copy_size,
+ bpf_perf_event_print_t fn, void *private_data)
+{
+ struct perf_event_mmap_page *header = mmap_mem;
+ __u64 data_head = ring_buffer_read_head(header);
__u64 data_tail = header->data_tail;
- __u64 data_head = header->data_head;
- int ret = LIBBPF_PERF_EVENT_ERROR;
- void *base, *begin, *end;
+ void *base = ((__u8 *)header) + page_size;
+ int ret = LIBBPF_PERF_EVENT_CONT;
+ struct perf_event_header *ehdr;
+ size_t ehdr_size;
- asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
- if (data_head == data_tail)
- return LIBBPF_PERF_EVENT_CONT;
+ while (data_head != data_tail) {
+ ehdr = base + (data_tail & (mmap_size - 1));
+ ehdr_size = ehdr->size;
- base = ((char *)header) + page_size;
+ if (((void *)ehdr) + ehdr_size > base + mmap_size) {
+ void *copy_start = ehdr;
+ size_t len_first = base + mmap_size - copy_start;
+ size_t len_secnd = ehdr_size - len_first;
- begin = base + data_tail % size;
- end = base + data_head % size;
-
- while (begin != end) {
- struct perf_event_header *ehdr;
-
- ehdr = begin;
- if (begin + ehdr->size > base + size) {
- long len = base + size - begin;
-
- if (*buf_len < ehdr->size) {
- free(*buf);
- *buf = malloc(ehdr->size);
- if (!*buf) {
+ if (*copy_size < ehdr_size) {
+ free(*copy_mem);
+ *copy_mem = malloc(ehdr_size);
+ if (!*copy_mem) {
+ *copy_size = 0;
ret = LIBBPF_PERF_EVENT_ERROR;
break;
}
- *buf_len = ehdr->size;
+ *copy_size = ehdr_size;
}
- memcpy(*buf, begin, len);
- memcpy(*buf + len, base, ehdr->size - len);
- ehdr = (void *)*buf;
- begin = base + ehdr->size - len;
- } else if (begin + ehdr->size == base + size) {
- begin = base;
- } else {
- begin += ehdr->size;
+ memcpy(*copy_mem, copy_start, len_first);
+ memcpy(*copy_mem + len_first, base, len_secnd);
+ ehdr = *copy_mem;
}
- ret = fn(ehdr, priv);
+ ret = fn(ehdr, private_data);
+ data_tail += ehdr_size;
if (ret != LIBBPF_PERF_EVENT_CONT)
break;
-
- data_tail += ehdr->size;
}
- __sync_synchronize(); /* smp_mb() */
- header->data_tail = data_tail;
-
+ ring_buffer_write_tail(header, data_tail);
return ret;
}
+
+struct perf_buffer;
+
+struct perf_buffer_params {
+ struct perf_event_attr *attr;
+ /* if event_cb is specified, it takes precendence */
+ perf_buffer_event_fn event_cb;
+ /* sample_cb and lost_cb are higher-level common-case callbacks */
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx;
+ int cpu_cnt;
+ int *cpus;
+ int *map_keys;
+};
+
+struct perf_cpu_buf {
+ struct perf_buffer *pb;
+ void *base; /* mmap()'ed memory */
+ void *buf; /* for reconstructing segmented data */
+ size_t buf_size;
+ int fd;
+ int cpu;
+ int map_key;
+};
+
+struct perf_buffer {
+ perf_buffer_event_fn event_cb;
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx; /* passed into callbacks */
+
+ size_t page_size;
+ size_t mmap_size;
+ struct perf_cpu_buf **cpu_bufs;
+ struct epoll_event *events;
+ int cpu_cnt;
+ int epoll_fd; /* perf event FD */
+ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
+};
+
+static void perf_buffer__free_cpu_buf(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ if (!cpu_buf)
+ return;
+ if (cpu_buf->base &&
+ munmap(cpu_buf->base, pb->mmap_size + pb->page_size))
+ pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu);
+ if (cpu_buf->fd >= 0) {
+ ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0);
+ close(cpu_buf->fd);
+ }
+ free(cpu_buf->buf);
+ free(cpu_buf);
+}
+
+void perf_buffer__free(struct perf_buffer *pb)
+{
+ int i;
+
+ if (!pb)
+ return;
+ if (pb->cpu_bufs) {
+ for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i];
+
+ bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key);
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ }
+ free(pb->cpu_bufs);
+ }
+ if (pb->epoll_fd >= 0)
+ close(pb->epoll_fd);
+ free(pb->events);
+ free(pb);
+}
+
+static struct perf_cpu_buf *
+perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr,
+ int cpu, int map_key)
+{
+ struct perf_cpu_buf *cpu_buf;
+ char msg[STRERR_BUFSIZE];
+ int err;
+
+ cpu_buf = calloc(1, sizeof(*cpu_buf));
+ if (!cpu_buf)
+ return ERR_PTR(-ENOMEM);
+
+ cpu_buf->pb = pb;
+ cpu_buf->cpu = cpu;
+ cpu_buf->map_key = map_key;
+
+ cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu,
+ -1, PERF_FLAG_FD_CLOEXEC);
+ if (cpu_buf->fd < 0) {
+ err = -errno;
+ pr_warning("failed to open perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size,
+ PROT_READ | PROT_WRITE, MAP_SHARED,
+ cpu_buf->fd, 0);
+ if (cpu_buf->base == MAP_FAILED) {
+ cpu_buf->base = NULL;
+ err = -errno;
+ pr_warning("failed to mmap perf buffer on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ pr_warning("failed to enable perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ return cpu_buf;
+
+error:
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ return (struct perf_cpu_buf *)ERR_PTR(err);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p);
+
+struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts)
+{
+ struct perf_buffer_params p = {};
+ struct perf_event_attr attr = { 0, };
+
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+
+ p.attr = &attr;
+ p.sample_cb = opts ? opts->sample_cb : NULL;
+ p.lost_cb = opts ? opts->lost_cb : NULL;
+ p.ctx = opts ? opts->ctx : NULL;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts)
+{
+ struct perf_buffer_params p = {};
+
+ p.attr = opts->attr;
+ p.event_cb = opts->event_cb;
+ p.ctx = opts->ctx;
+ p.cpu_cnt = opts->cpu_cnt;
+ p.cpus = opts->cpus;
+ p.map_keys = opts->map_keys;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p)
+{
+ struct bpf_map_info map = {};
+ char msg[STRERR_BUFSIZE];
+ struct perf_buffer *pb;
+ __u32 map_info_len;
+ int err, i;
+
+ if (page_cnt & (page_cnt - 1)) {
+ pr_warning("page count should be power of two, but is %zu\n",
+ page_cnt);
+ return ERR_PTR(-EINVAL);
+ }
+
+ map_info_len = sizeof(map);
+ err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to get map info for map FD %d: %s\n",
+ map_fd, libbpf_strerror_r(err, msg, sizeof(msg)));
+ return ERR_PTR(err);
+ }
+
+ if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+ pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+ map.name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pb = calloc(1, sizeof(*pb));
+ if (!pb)
+ return ERR_PTR(-ENOMEM);
+
+ pb->event_cb = p->event_cb;
+ pb->sample_cb = p->sample_cb;
+ pb->lost_cb = p->lost_cb;
+ pb->ctx = p->ctx;
+
+ pb->page_size = getpagesize();
+ pb->mmap_size = pb->page_size * page_cnt;
+ pb->map_fd = map_fd;
+
+ pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+ if (pb->epoll_fd < 0) {
+ err = -errno;
+ pr_warning("failed to create epoll instance: %s\n",
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (p->cpu_cnt > 0) {
+ pb->cpu_cnt = p->cpu_cnt;
+ } else {
+ pb->cpu_cnt = libbpf_num_possible_cpus();
+ if (pb->cpu_cnt < 0) {
+ err = pb->cpu_cnt;
+ goto error;
+ }
+ if (map.max_entries < pb->cpu_cnt)
+ pb->cpu_cnt = map.max_entries;
+ }
+
+ pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events));
+ if (!pb->events) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate events: out of memory\n");
+ goto error;
+ }
+ pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs));
+ if (!pb->cpu_bufs) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate buffers: out of memory\n");
+ goto error;
+ }
+
+ for (i = 0; i < pb->cpu_cnt; i++) {
+ struct perf_cpu_buf *cpu_buf;
+ int cpu, map_key;
+
+ cpu = p->cpu_cnt > 0 ? p->cpus[i] : i;
+ map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i;
+
+ cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key);
+ if (IS_ERR(cpu_buf)) {
+ err = PTR_ERR(cpu_buf);
+ goto error;
+ }
+
+ pb->cpu_bufs[i] = cpu_buf;
+
+ err = bpf_map_update_elem(pb->map_fd, &map_key,
+ &cpu_buf->fd, 0);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n",
+ cpu, map_key, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ pb->events[i].events = EPOLLIN;
+ pb->events[i].data.ptr = cpu_buf;
+ if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd,
+ &pb->events[i]) < 0) {
+ err = -errno;
+ pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n",
+ cpu, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+ }
+
+ return pb;
+
+error:
+ if (pb)
+ perf_buffer__free(pb);
+ return ERR_PTR(err);
+}
+
+struct perf_sample_raw {
+ struct perf_event_header header;
+ uint32_t size;
+ char data[0];
+};
+
+struct perf_sample_lost {
+ struct perf_event_header header;
+ uint64_t id;
+ uint64_t lost;
+ uint64_t sample_id;
+};
+
+static enum bpf_perf_event_ret
+perf_buffer__process_record(struct perf_event_header *e, void *ctx)
+{
+ struct perf_cpu_buf *cpu_buf = ctx;
+ struct perf_buffer *pb = cpu_buf->pb;
+ void *data = e;
+
+ /* user wants full control over parsing perf event */
+ if (pb->event_cb)
+ return pb->event_cb(pb->ctx, cpu_buf->cpu, e);
+
+ switch (e->type) {
+ case PERF_RECORD_SAMPLE: {
+ struct perf_sample_raw *s = data;
+
+ if (pb->sample_cb)
+ pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size);
+ break;
+ }
+ case PERF_RECORD_LOST: {
+ struct perf_sample_lost *s = data;
+
+ if (pb->lost_cb)
+ pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost);
+ break;
+ }
+ default:
+ pr_warning("unknown perf sample type %d\n", e->type);
+ return LIBBPF_PERF_EVENT_ERROR;
+ }
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static int perf_buffer__process_records(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ enum bpf_perf_event_ret ret;
+
+ ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size,
+ pb->page_size, &cpu_buf->buf,
+ &cpu_buf->buf_size,
+ perf_buffer__process_record, cpu_buf);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ return ret;
+ return 0;
+}
+
+int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
+{
+ int i, cnt, err;
+
+ cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
+ for (i = 0; i < cnt; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
+
+ err = perf_buffer__process_records(pb, cpu_buf);
+ if (err) {
+ pr_warning("error while processing records: %d\n", err);
+ return err;
+ }
+ }
+ return cnt < 0 ? -errno : cnt;
+}
+
+struct bpf_prog_info_array_desc {
+ int array_offset; /* e.g. offset of jited_prog_insns */
+ int count_offset; /* e.g. offset of jited_prog_len */
+ int size_offset; /* > 0: offset of rec size,
+ * < 0: fix size of -size_offset
+ */
+};
+
+static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = {
+ [BPF_PROG_INFO_JITED_INSNS] = {
+ offsetof(struct bpf_prog_info, jited_prog_insns),
+ offsetof(struct bpf_prog_info, jited_prog_len),
+ -1,
+ },
+ [BPF_PROG_INFO_XLATED_INSNS] = {
+ offsetof(struct bpf_prog_info, xlated_prog_insns),
+ offsetof(struct bpf_prog_info, xlated_prog_len),
+ -1,
+ },
+ [BPF_PROG_INFO_MAP_IDS] = {
+ offsetof(struct bpf_prog_info, map_ids),
+ offsetof(struct bpf_prog_info, nr_map_ids),
+ -(int)sizeof(__u32),
+ },
+ [BPF_PROG_INFO_JITED_KSYMS] = {
+ offsetof(struct bpf_prog_info, jited_ksyms),
+ offsetof(struct bpf_prog_info, nr_jited_ksyms),
+ -(int)sizeof(__u64),
+ },
+ [BPF_PROG_INFO_JITED_FUNC_LENS] = {
+ offsetof(struct bpf_prog_info, jited_func_lens),
+ offsetof(struct bpf_prog_info, nr_jited_func_lens),
+ -(int)sizeof(__u32),
+ },
+ [BPF_PROG_INFO_FUNC_INFO] = {
+ offsetof(struct bpf_prog_info, func_info),
+ offsetof(struct bpf_prog_info, nr_func_info),
+ offsetof(struct bpf_prog_info, func_info_rec_size),
+ },
+ [BPF_PROG_INFO_LINE_INFO] = {
+ offsetof(struct bpf_prog_info, line_info),
+ offsetof(struct bpf_prog_info, nr_line_info),
+ offsetof(struct bpf_prog_info, line_info_rec_size),
+ },
+ [BPF_PROG_INFO_JITED_LINE_INFO] = {
+ offsetof(struct bpf_prog_info, jited_line_info),
+ offsetof(struct bpf_prog_info, nr_jited_line_info),
+ offsetof(struct bpf_prog_info, jited_line_info_rec_size),
+ },
+ [BPF_PROG_INFO_PROG_TAGS] = {
+ offsetof(struct bpf_prog_info, prog_tags),
+ offsetof(struct bpf_prog_info, nr_prog_tags),
+ -(int)sizeof(__u8) * BPF_TAG_SIZE,
+ },
+
+};
+
+static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
+{
+ __u32 *array = (__u32 *)info;
+
+ if (offset >= 0)
+ return array[offset / sizeof(__u32)];
+ return -(int)offset;
+}
+
+static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
+{
+ __u64 *array = (__u64 *)info;
+
+ if (offset >= 0)
+ return array[offset / sizeof(__u64)];
+ return -(int)offset;
+}
+
+static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset,
+ __u32 val)
+{
+ __u32 *array = (__u32 *)info;
+
+ if (offset >= 0)
+ array[offset / sizeof(__u32)] = val;
+}
+
+static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset,
+ __u64 val)
+{
+ __u64 *array = (__u64 *)info;
+
+ if (offset >= 0)
+ array[offset / sizeof(__u64)] = val;
+}
+
+struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays)
+{
+ struct bpf_prog_info_linear *info_linear;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ __u32 data_len = 0;
+ int i, err;
+ void *ptr;
+
+ if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
+ return ERR_PTR(-EINVAL);
+
+ /* step 1: get array dimensions */
+ err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+ if (err) {
+ pr_debug("can't get prog info: %s", strerror(errno));
+ return ERR_PTR(-EFAULT);
+ }
+
+ /* step 2: calculate total size of all arrays */
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ bool include_array = (arrays & (1UL << i)) > 0;
+ struct bpf_prog_info_array_desc *desc;
+ __u32 count, size;
+
+ desc = bpf_prog_info_array_desc + i;
+
+ /* kernel is too old to support this field */
+ if (info_len < desc->array_offset + sizeof(__u32) ||
+ info_len < desc->count_offset + sizeof(__u32) ||
+ (desc->size_offset > 0 && info_len < desc->size_offset))
+ include_array = false;
+
+ if (!include_array) {
+ arrays &= ~(1UL << i); /* clear the bit */
+ continue;
+ }
+
+ count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+
+ data_len += count * size;
+ }
+
+ /* step 3: allocate continuous memory */
+ data_len = roundup(data_len, sizeof(__u64));
+ info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
+ if (!info_linear)
+ return ERR_PTR(-ENOMEM);
+
+ /* step 4: fill data to info_linear->info */
+ info_linear->arrays = arrays;
+ memset(&info_linear->info, 0, sizeof(info));
+ ptr = info_linear->data;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u32 count, size;
+
+ if ((arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+ bpf_prog_info_set_offset_u32(&info_linear->info,
+ desc->count_offset, count);
+ bpf_prog_info_set_offset_u32(&info_linear->info,
+ desc->size_offset, size);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset,
+ ptr_to_u64(ptr));
+ ptr += count * size;
+ }
+
+ /* step 5: call syscall again to get required arrays */
+ err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len);
+ if (err) {
+ pr_debug("can't get prog info: %s", strerror(errno));
+ free(info_linear);
+ return ERR_PTR(-EFAULT);
+ }
+
+ /* step 6: verify the data */
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u32 v1, v2;
+
+ if ((arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ desc->count_offset);
+ if (v1 != v2)
+ pr_warning("%s: mismatch in element count\n", __func__);
+
+ v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+ v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ desc->size_offset);
+ if (v1 != v2)
+ pr_warning("%s: mismatch in rec size\n", __func__);
+ }
+
+ /* step 7: update info_len and data_len */
+ info_linear->info_len = sizeof(struct bpf_prog_info);
+ info_linear->data_len = data_len;
+
+ return info_linear;
+}
+
+void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear)
+{
+ int i;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u64 addr, offs;
+
+ if ((info_linear->arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ addr = bpf_prog_info_read_offset_u64(&info_linear->info,
+ desc->array_offset);
+ offs = addr - ptr_to_u64(info_linear->data);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset, offs);
+ }
+}
+
+void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
+{
+ int i;
+
+ for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+ struct bpf_prog_info_array_desc *desc;
+ __u64 addr, offs;
+
+ if ((info_linear->arrays & (1UL << i)) == 0)
+ continue;
+
+ desc = bpf_prog_info_array_desc + i;
+ offs = bpf_prog_info_read_offset_u64(&info_linear->info,
+ desc->array_offset);
+ addr = offs + ptr_to_u64(info_linear->data);
+ bpf_prog_info_set_offset_u64(&info_linear->info,
+ desc->array_offset, addr);
+ }
+}
+
+int libbpf_num_possible_cpus(void)
+{
+ static const char *fcpu = "/sys/devices/system/cpu/possible";
+ int len = 0, n = 0, il = 0, ir = 0;
+ unsigned int start = 0, end = 0;
+ int tmp_cpus = 0;
+ static int cpus;
+ char buf[128];
+ int error = 0;
+ int fd = -1;
+
+ tmp_cpus = READ_ONCE(cpus);
+ if (tmp_cpus > 0)
+ return tmp_cpus;
+
+ fd = open(fcpu, O_RDONLY);
+ if (fd < 0) {
+ error = errno;
+ pr_warning("Failed to open file %s: %s\n",
+ fcpu, strerror(error));
+ return -error;
+ }
+ len = read(fd, buf, sizeof(buf));
+ close(fd);
+ if (len <= 0) {
+ error = len ? errno : EINVAL;
+ pr_warning("Failed to read # of possible cpus from %s: %s\n",
+ fcpu, strerror(error));
+ return -error;
+ }
+ if (len == sizeof(buf)) {
+ pr_warning("File %s size overflow\n", fcpu);
+ return -EOVERFLOW;
+ }
+ buf[len] = '\0';
+
+ for (ir = 0, tmp_cpus = 0; ir <= len; ir++) {
+ /* Each sub string separated by ',' has format \d+-\d+ or \d+ */
+ if (buf[ir] == ',' || buf[ir] == '\0') {
+ buf[ir] = '\0';
+ n = sscanf(&buf[il], "%u-%u", &start, &end);
+ if (n <= 0) {
+ pr_warning("Failed to get # CPUs from %s\n",
+ &buf[il]);
+ return -EINVAL;
+ } else if (n == 1) {
+ end = start;
+ }
+ tmp_cpus += end - start + 1;
+ il = ir + 1;
+ }
+ }
+ if (tmp_cpus <= 0) {
+ pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu);
+ return -EINVAL;
+ }
+
+ WRITE_ONCE(cpus, tmp_cpus);
+ return tmp_cpus;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 96c55fa..e8f7097 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
/*
* Common eBPF ELF object loading operations.
@@ -6,29 +6,25 @@
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, see <http://www.gnu.org/licenses>
*/
-#ifndef __BPF_LIBBPF_H
-#define __BPF_LIBBPF_H
+#ifndef __LIBBPF_LIBBPF_H
+#define __LIBBPF_LIBBPF_H
+#include <stdarg.h>
#include <stdio.h>
#include <stdint.h>
#include <stdbool.h>
#include <sys/types.h> // for size_t
#include <linux/bpf.h>
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
enum libbpf_errno {
__LIBBPF_ERRNO__START = 4000,
@@ -46,22 +42,22 @@
LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */
LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */
LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */
+ LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */
__LIBBPF_ERRNO__END,
};
-int libbpf_strerror(int err, char *buf, size_t size);
+LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
-/*
- * __printf is defined in include/linux/compiler-gcc.h. However,
- * it would be better if libbpf.h didn't depend on Linux header files.
- * So instead of __printf, here we use gcc attribute directly.
- */
-typedef int (*libbpf_print_fn_t)(const char *, ...)
- __attribute__((format(printf, 1, 2)));
+enum libbpf_print_level {
+ LIBBPF_WARN,
+ LIBBPF_INFO,
+ LIBBPF_DEBUG,
+};
-void libbpf_set_print(libbpf_print_fn_t warn,
- libbpf_print_fn_t info,
- libbpf_print_fn_t debug);
+typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
+ const char *, va_list ap);
+
+LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn);
/* Hide internal to user */
struct bpf_object;
@@ -71,25 +67,50 @@
enum bpf_prog_type prog_type;
};
-struct bpf_object *bpf_object__open(const char *path);
-struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
-struct bpf_object *bpf_object__open_buffer(void *obj_buf,
- size_t obj_buf_sz,
- const char *name);
-int bpf_object__pin(struct bpf_object *object, const char *path);
-void bpf_object__close(struct bpf_object *object);
+LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
+LIBBPF_API struct bpf_object *
+bpf_object__open_xattr(struct bpf_object_open_attr *attr);
+struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
+ int flags);
+LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
+ size_t obj_buf_sz,
+ const char *name);
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+ __u32 *size);
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+ __u32 *off);
+LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
+ const char *path);
+LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
+ const char *path);
+LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
+ const char *path);
+LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
+LIBBPF_API void bpf_object__close(struct bpf_object *object);
+
+struct bpf_object_load_attr {
+ struct bpf_object *obj;
+ int log_level;
+ const char *target_btf_path;
+};
/* Load/unload object into/from kernel */
-int bpf_object__load(struct bpf_object *obj);
-int bpf_object__unload(struct bpf_object *obj);
-const char *bpf_object__name(struct bpf_object *obj);
-unsigned int bpf_object__kversion(struct bpf_object *obj);
-int bpf_object__btf_fd(const struct bpf_object *obj);
+LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
+LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
+LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
+LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
-struct bpf_program *
-bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
+struct btf;
+LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
+LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
-struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API struct bpf_program *
+bpf_object__find_program_by_title(const struct bpf_object *obj,
+ const char *title);
+
+LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
#define bpf_object__for_each_safe(pos, tmp) \
for ((pos) = bpf_object__next(NULL), \
(tmp) = bpf_object__next(pos); \
@@ -97,38 +118,74 @@
(pos) = (tmp), (tmp) = bpf_object__next(tmp))
typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
-int bpf_object__set_priv(struct bpf_object *obj, void *priv,
- bpf_object_clear_priv_t clear_priv);
-void *bpf_object__priv(struct bpf_object *prog);
+LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+ bpf_object_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog);
-int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
- enum bpf_attach_type *expected_attach_type);
+LIBBPF_API int
+libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type);
+LIBBPF_API int libbpf_attach_type_by_name(const char *name,
+ enum bpf_attach_type *attach_type);
/* Accessors of bpf_program */
struct bpf_program;
-struct bpf_program *bpf_program__next(struct bpf_program *prog,
- struct bpf_object *obj);
+LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
+ const struct bpf_object *obj);
#define bpf_object__for_each_program(pos, obj) \
for ((pos) = bpf_program__next(NULL, (obj)); \
(pos) != NULL; \
(pos) = bpf_program__next((pos), (obj)))
-typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
- void *);
+LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+ const struct bpf_object *obj);
-int bpf_program__set_priv(struct bpf_program *prog, void *priv,
- bpf_program_clear_priv_t clear_priv);
+typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
-void *bpf_program__priv(struct bpf_program *prog);
-void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
+LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
+ bpf_program_clear_priv_t clear_priv);
-const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
+LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
+ __u32 ifindex);
-int bpf_program__fd(struct bpf_program *prog);
-int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
- int instance);
-int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
+ bool needs_copy);
+
+LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
+ __u32 kern_version);
+LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
+LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
+ const char *path,
+ int instance);
+LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
+ const char *path,
+ int instance);
+LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
+LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
+
+struct bpf_link;
+
+LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+ const char *func_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+ pid_t pid, const char *binary_path,
+ size_t func_offset);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name);
struct bpf_insn;
@@ -189,34 +246,36 @@
struct bpf_insn *insns, int insns_cnt,
struct bpf_prog_prep_result *res);
-int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
- bpf_program_prep_t prep);
+LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+ bpf_program_prep_t prep);
-int bpf_program__nth_fd(struct bpf_program *prog, int n);
+LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
/*
* Adjust type of BPF program. Default is kprobe.
*/
-int bpf_program__set_socket_filter(struct bpf_program *prog);
-int bpf_program__set_tracepoint(struct bpf_program *prog);
-int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
-int bpf_program__set_kprobe(struct bpf_program *prog);
-int bpf_program__set_sched_cls(struct bpf_program *prog);
-int bpf_program__set_sched_act(struct bpf_program *prog);
-int bpf_program__set_xdp(struct bpf_program *prog);
-int bpf_program__set_perf_event(struct bpf_program *prog);
-void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
-void bpf_program__set_expected_attach_type(struct bpf_program *prog,
- enum bpf_attach_type type);
+LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
+ enum bpf_prog_type type);
+LIBBPF_API void
+bpf_program__set_expected_attach_type(struct bpf_program *prog,
+ enum bpf_attach_type type);
-bool bpf_program__is_socket_filter(struct bpf_program *prog);
-bool bpf_program__is_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_kprobe(struct bpf_program *prog);
-bool bpf_program__is_sched_cls(struct bpf_program *prog);
-bool bpf_program__is_sched_act(struct bpf_program *prog);
-bool bpf_program__is_xdp(struct bpf_program *prog);
-bool bpf_program__is_perf_event(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -237,53 +296,88 @@
* so no need to worry about a name clash.
*/
struct bpf_map;
-struct bpf_map *
-bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
+LIBBPF_API struct bpf_map *
+bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
+
+LIBBPF_API int
+bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
/*
* Get bpf_map through the offset of corresponding struct bpf_map_def
* in the BPF object file.
*/
-struct bpf_map *
+LIBBPF_API struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
-struct bpf_map *
-bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
-#define bpf_map__for_each(pos, obj) \
+LIBBPF_API struct bpf_map *
+bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
+#define bpf_object__for_each_map(pos, obj) \
for ((pos) = bpf_map__next(NULL, (obj)); \
(pos) != NULL; \
(pos) = bpf_map__next((pos), (obj)))
+#define bpf_map__for_each bpf_object__for_each_map
-int bpf_map__fd(struct bpf_map *map);
-const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
-const char *bpf_map__name(struct bpf_map *map);
-__u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
-__u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
+LIBBPF_API struct bpf_map *
+bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
+
+LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
+LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
+LIBBPF_API const char *bpf_map__name(const struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
-int bpf_map__set_priv(struct bpf_map *map, void *priv,
- bpf_map_clear_priv_t clear_priv);
-void *bpf_map__priv(struct bpf_map *map);
-int bpf_map__reuse_fd(struct bpf_map *map, int fd);
-bool bpf_map__is_offload_neutral(struct bpf_map *map);
-void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
-int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
+ bpf_map_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
+LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
+LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
+LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
-long libbpf_get_error(const void *ptr);
+LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
+
+LIBBPF_API long libbpf_get_error(const void *ptr);
struct bpf_prog_load_attr {
const char *file;
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
int ifindex;
+ int log_level;
+ int prog_flags;
};
-int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
- struct bpf_object **pobj, int *prog_fd);
-int bpf_prog_load(const char *file, enum bpf_prog_type type,
- struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
+ struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
+ struct bpf_object **pobj, int *prog_fd);
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+
+struct perf_buffer;
+
+typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu,
+ void *data, __u32 size);
+typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt);
+
+/* common use perf buffer options */
+struct perf_buffer_opts {
+ /* if specified, sample_cb is called for each sample */
+ perf_buffer_sample_fn sample_cb;
+ /* if specified, lost_cb is called for each batch of lost samples */
+ perf_buffer_lost_fn lost_cb;
+ /* ctx is provided to sample_cb and lost_cb */
+ void *ctx;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts);
enum bpf_perf_event_ret {
LIBBPF_PERF_EVENT_DONE = 0,
@@ -291,10 +385,164 @@
LIBBPF_PERF_EVENT_CONT = -2,
};
-typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
- void *priv);
-int bpf_perf_event_read_simple(void *mem, unsigned long size,
- unsigned long page_size,
- void **buf, size_t *buf_len,
- bpf_perf_event_print_t fn, void *priv);
+struct perf_event_header;
+
+typedef enum bpf_perf_event_ret
+(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event);
+
+/* raw perf buffer options, giving most power and control */
+struct perf_buffer_raw_opts {
+ /* perf event attrs passed directly into perf_event_open() */
+ struct perf_event_attr *attr;
+ /* raw event callback */
+ perf_buffer_event_fn event_cb;
+ /* ctx is provided to event_cb */
+ void *ctx;
+ /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of
+ * max_entries of given PERF_EVENT_ARRAY map)
+ */
+ int cpu_cnt;
+ /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */
+ int *cpus;
+ /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */
+ int *map_keys;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts);
+
+LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
+LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
+
+typedef enum bpf_perf_event_ret
+ (*bpf_perf_event_print_t)(struct perf_event_header *hdr,
+ void *private_data);
+LIBBPF_API enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+ void **copy_mem, size_t *copy_size,
+ bpf_perf_event_print_t fn, void *private_data);
+
+struct nlattr;
+typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+int libbpf_netlink_open(unsigned int *nl_pid);
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+ libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+ libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+ libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+ libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+
+struct bpf_prog_linfo;
+struct bpf_prog_info;
+
+LIBBPF_API void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo);
+LIBBPF_API struct bpf_prog_linfo *
+bpf_prog_linfo__new(const struct bpf_prog_info *info);
+LIBBPF_API const struct bpf_line_info *
+bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
+ __u64 addr, __u32 func_idx, __u32 nr_skip);
+LIBBPF_API const struct bpf_line_info *
+bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
+ __u32 insn_off, __u32 nr_skip);
+
+/*
+ * Probe for supported system features
+ *
+ * Note that running many of these probes in a short amount of time can cause
+ * the kernel to reach the maximal size of lockable memory allowed for the
+ * user, causing subsequent probes to fail. In this case, the caller may want
+ * to adjust that limit with setrlimit().
+ */
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
+ __u32 ifindex);
+LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
+ enum bpf_prog_type prog_type, __u32 ifindex);
+
+/*
+ * Get bpf_prog_info in continuous memory
+ *
+ * struct bpf_prog_info has multiple arrays. The user has option to choose
+ * arrays to fetch from kernel. The following APIs provide an uniform way to
+ * fetch these data. All arrays in bpf_prog_info are stored in a single
+ * continuous memory region. This makes it easy to store the info in a
+ * file.
+ *
+ * Before writing bpf_prog_info_linear to files, it is necessary to
+ * translate pointers in bpf_prog_info to offsets. Helper functions
+ * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr()
+ * are introduced to switch between pointers and offsets.
+ *
+ * Examples:
+ * # To fetch map_ids and prog_tags:
+ * __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) |
+ * (1UL << BPF_PROG_INFO_PROG_TAGS);
+ * struct bpf_prog_info_linear *info_linear =
+ * bpf_program__get_prog_info_linear(fd, arrays);
+ *
+ * # To save data in file
+ * bpf_program__bpil_addr_to_offs(info_linear);
+ * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len);
+ *
+ * # To read data from file
+ * read(f, info_linear, <proper_size>);
+ * bpf_program__bpil_offs_to_addr(info_linear);
+ */
+enum bpf_prog_info_array {
+ BPF_PROG_INFO_FIRST_ARRAY = 0,
+ BPF_PROG_INFO_JITED_INSNS = 0,
+ BPF_PROG_INFO_XLATED_INSNS,
+ BPF_PROG_INFO_MAP_IDS,
+ BPF_PROG_INFO_JITED_KSYMS,
+ BPF_PROG_INFO_JITED_FUNC_LENS,
+ BPF_PROG_INFO_FUNC_INFO,
+ BPF_PROG_INFO_LINE_INFO,
+ BPF_PROG_INFO_JITED_LINE_INFO,
+ BPF_PROG_INFO_PROG_TAGS,
+ BPF_PROG_INFO_LAST_ARRAY,
+};
+
+struct bpf_prog_info_linear {
+ /* size of struct bpf_prog_info, when the tool is compiled */
+ __u32 info_len;
+ /* total bytes allocated for data, round up to 8 bytes */
+ __u32 data_len;
+ /* which arrays are included in data */
+ __u64 arrays;
+ struct bpf_prog_info info;
+ __u8 data[];
+};
+
+LIBBPF_API struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays);
+
+LIBBPF_API void
+bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
+
+LIBBPF_API void
+bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
+
+/*
+ * A helper function to get the number of possible CPUs before looking up
+ * per-CPU maps. Negative errno is returned on failure.
+ *
+ * Example usage:
+ *
+ * int ncpus = libbpf_num_possible_cpus();
+ * if (ncpus < 0) {
+ * // error handling
+ * }
+ * long values[ncpus];
+ * bpf_map_lookup_elem(per_cpu_map_fd, key, values);
+ *
+ */
+LIBBPF_API int libbpf_num_possible_cpus(void);
+
+#ifdef __cplusplus
+} /* extern "C" */
#endif
+
+#endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
new file mode 100644
index 0000000..d04c7cb
--- /dev/null
+++ b/tools/lib/bpf/libbpf.map
@@ -0,0 +1,192 @@
+LIBBPF_0.0.1 {
+ global:
+ bpf_btf_get_fd_by_id;
+ bpf_create_map;
+ bpf_create_map_in_map;
+ bpf_create_map_in_map_node;
+ bpf_create_map_name;
+ bpf_create_map_node;
+ bpf_create_map_xattr;
+ bpf_load_btf;
+ bpf_load_program;
+ bpf_load_program_xattr;
+ bpf_map__btf_key_type_id;
+ bpf_map__btf_value_type_id;
+ bpf_map__def;
+ bpf_map__fd;
+ bpf_map__is_offload_neutral;
+ bpf_map__name;
+ bpf_map__next;
+ bpf_map__pin;
+ bpf_map__prev;
+ bpf_map__priv;
+ bpf_map__reuse_fd;
+ bpf_map__set_ifindex;
+ bpf_map__set_inner_map_fd;
+ bpf_map__set_priv;
+ bpf_map__unpin;
+ bpf_map_delete_elem;
+ bpf_map_get_fd_by_id;
+ bpf_map_get_next_id;
+ bpf_map_get_next_key;
+ bpf_map_lookup_and_delete_elem;
+ bpf_map_lookup_elem;
+ bpf_map_update_elem;
+ bpf_obj_get;
+ bpf_obj_get_info_by_fd;
+ bpf_obj_pin;
+ bpf_object__btf_fd;
+ bpf_object__close;
+ bpf_object__find_map_by_name;
+ bpf_object__find_map_by_offset;
+ bpf_object__find_program_by_title;
+ bpf_object__kversion;
+ bpf_object__load;
+ bpf_object__name;
+ bpf_object__next;
+ bpf_object__open;
+ bpf_object__open_buffer;
+ bpf_object__open_xattr;
+ bpf_object__pin;
+ bpf_object__pin_maps;
+ bpf_object__pin_programs;
+ bpf_object__priv;
+ bpf_object__set_priv;
+ bpf_object__unload;
+ bpf_object__unpin_maps;
+ bpf_object__unpin_programs;
+ bpf_perf_event_read_simple;
+ bpf_prog_attach;
+ bpf_prog_detach;
+ bpf_prog_detach2;
+ bpf_prog_get_fd_by_id;
+ bpf_prog_get_next_id;
+ bpf_prog_load;
+ bpf_prog_load_xattr;
+ bpf_prog_query;
+ bpf_prog_test_run;
+ bpf_prog_test_run_xattr;
+ bpf_program__fd;
+ bpf_program__is_kprobe;
+ bpf_program__is_perf_event;
+ bpf_program__is_raw_tracepoint;
+ bpf_program__is_sched_act;
+ bpf_program__is_sched_cls;
+ bpf_program__is_socket_filter;
+ bpf_program__is_tracepoint;
+ bpf_program__is_xdp;
+ bpf_program__load;
+ bpf_program__next;
+ bpf_program__nth_fd;
+ bpf_program__pin;
+ bpf_program__pin_instance;
+ bpf_program__prev;
+ bpf_program__priv;
+ bpf_program__set_expected_attach_type;
+ bpf_program__set_ifindex;
+ bpf_program__set_kprobe;
+ bpf_program__set_perf_event;
+ bpf_program__set_prep;
+ bpf_program__set_priv;
+ bpf_program__set_raw_tracepoint;
+ bpf_program__set_sched_act;
+ bpf_program__set_sched_cls;
+ bpf_program__set_socket_filter;
+ bpf_program__set_tracepoint;
+ bpf_program__set_type;
+ bpf_program__set_xdp;
+ bpf_program__title;
+ bpf_program__unload;
+ bpf_program__unpin;
+ bpf_program__unpin_instance;
+ bpf_prog_linfo__free;
+ bpf_prog_linfo__new;
+ bpf_prog_linfo__lfind_addr_func;
+ bpf_prog_linfo__lfind;
+ bpf_raw_tracepoint_open;
+ bpf_set_link_xdp_fd;
+ bpf_task_fd_query;
+ bpf_verify_program;
+ btf__fd;
+ btf__find_by_name;
+ btf__free;
+ btf__get_from_id;
+ btf__name_by_offset;
+ btf__new;
+ btf__resolve_size;
+ btf__resolve_type;
+ btf__type_by_id;
+ libbpf_attach_type_by_name;
+ libbpf_get_error;
+ libbpf_prog_type_by_name;
+ libbpf_set_print;
+ libbpf_strerror;
+ local:
+ *;
+};
+
+LIBBPF_0.0.2 {
+ global:
+ bpf_probe_helper;
+ bpf_probe_map_type;
+ bpf_probe_prog_type;
+ bpf_map__resize;
+ bpf_map_lookup_elem_flags;
+ bpf_object__btf;
+ bpf_object__find_map_fd_by_name;
+ bpf_get_link_xdp_id;
+ btf__dedup;
+ btf__get_map_kv_tids;
+ btf__get_nr_types;
+ btf__get_raw_data;
+ btf__load;
+ btf_ext__free;
+ btf_ext__func_info_rec_size;
+ btf_ext__get_raw_data;
+ btf_ext__line_info_rec_size;
+ btf_ext__new;
+ btf_ext__reloc_func_info;
+ btf_ext__reloc_line_info;
+ xsk_umem__create;
+ xsk_socket__create;
+ xsk_umem__delete;
+ xsk_socket__delete;
+ xsk_umem__fd;
+ xsk_socket__fd;
+ bpf_program__get_prog_info_linear;
+ bpf_program__bpil_addr_to_offs;
+ bpf_program__bpil_offs_to_addr;
+} LIBBPF_0.0.1;
+
+LIBBPF_0.0.3 {
+ global:
+ bpf_map__is_internal;
+ bpf_map_freeze;
+ btf__finalize_data;
+} LIBBPF_0.0.2;
+
+LIBBPF_0.0.4 {
+ global:
+ bpf_link__destroy;
+ bpf_object__load_xattr;
+ bpf_program__attach_kprobe;
+ bpf_program__attach_perf_event;
+ bpf_program__attach_raw_tracepoint;
+ bpf_program__attach_tracepoint;
+ bpf_program__attach_uprobe;
+ btf_dump__dump_type;
+ btf_dump__free;
+ btf_dump__new;
+ btf__parse_elf;
+ libbpf_num_possible_cpus;
+ perf_buffer__free;
+ perf_buffer__new;
+ perf_buffer__new_raw;
+ perf_buffer__poll;
+ xsk_umem__create;
+} LIBBPF_0.0.3;
+
+LIBBPF_0.0.5 {
+ global:
+ bpf_btf_get_next_id;
+} LIBBPF_0.0.4;
diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template
new file mode 100644
index 0000000..ac17fce
--- /dev/null
+++ b/tools/lib/bpf/libbpf.pc.template
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libbpf
+Description: BPF library
+Version: @VERSION@
+Libs: -L${libdir} -lbpf
+Requires.private: libelf
+Cflags: -I${includedir}
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index d9ba851..4343e40 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -1,25 +1,13 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/*
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
* Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, see <http://www.gnu.org/licenses>
*/
+#undef _GNU_SOURCE
#include <stdio.h>
#include <string.h>
@@ -42,6 +30,7 @@
[ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
[ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
[ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
+ [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing",
};
int libbpf_strerror(int err, char *buf, size_t size)
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
new file mode 100644
index 0000000..98216a6
--- /dev/null
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Internal libbpf helpers.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+
+#ifndef __LIBBPF_LIBBPF_INTERNAL_H
+#define __LIBBPF_LIBBPF_INTERNAL_H
+
+#include "libbpf.h"
+
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+ ((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+ BTF_INT_ENC(encoding, bits_offset, bits)
+#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset)
+#define BTF_PARAM_ENC(name, type) (name), (type)
+#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
+
+#ifndef min
+# define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#ifndef max
+# define max(x, y) ((x) < (y) ? (y) : (x))
+#endif
+#ifndef offsetofend
+# define offsetofend(TYPE, FIELD) \
+ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
+#endif
+
+/* Symbol versioning is different between static and shared library.
+ * Properly versioned symbols are needed for shared library, but
+ * only the symbol of the new version is needed for static library.
+ */
+#ifdef SHARED
+# define COMPAT_VERSION(internal_name, api_name, version) \
+ asm(".symver " #internal_name "," #api_name "@" #version);
+# define DEFAULT_VERSION(internal_name, api_name, version) \
+ asm(".symver " #internal_name "," #api_name "@@" #version);
+#else
+# define COMPAT_VERSION(internal_name, api_name, version)
+# define DEFAULT_VERSION(internal_name, api_name, version) \
+ extern typeof(internal_name) api_name \
+ __attribute__((alias(#internal_name)));
+#endif
+
+extern void libbpf_print(enum libbpf_print_level level,
+ const char *format, ...)
+ __attribute__((format(printf, 2, 3)));
+
+#define __pr(level, fmt, ...) \
+do { \
+ libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+ const char *str_sec, size_t str_len);
+
+struct btf_ext_info {
+ /*
+ * info points to the individual info section (e.g. func_info and
+ * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
+ */
+ void *info;
+ __u32 rec_size;
+ __u32 len;
+};
+
+#define for_each_btf_ext_sec(seg, sec) \
+ for (sec = (seg)->info; \
+ (void *)sec < (seg)->info + (seg)->len; \
+ sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \
+ (seg)->rec_size * sec->num_info)
+
+#define for_each_btf_ext_rec(seg, sec, i, rec) \
+ for (i = 0, rec = (void *)&(sec)->data; \
+ i < (sec)->num_info; \
+ i++, rec = (void *)rec + (seg)->rec_size)
+
+struct btf_ext {
+ union {
+ struct btf_ext_header *hdr;
+ void *data;
+ };
+ struct btf_ext_info func_info;
+ struct btf_ext_info line_info;
+ struct btf_ext_info offset_reloc_info;
+ __u32 data_size;
+};
+
+struct btf_ext_info_sec {
+ __u32 sec_name_off;
+ __u32 num_info;
+ /* Followed by num_info * record_size number of bytes */
+ __u8 data[0];
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+ __u32 insn_off;
+ __u32 type_id;
+};
+
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+ __u32 insn_off;
+ __u32 file_name_off;
+ __u32 line_off;
+ __u32 line_col;
+};
+
+/* The minimum bpf_offset_reloc checked by the loader
+ *
+ * Offset relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual offset;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * offset;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * itself encodes an accessed field using a sequence of field and array
+ * indicies, separated by colon (:). It's conceptually very close to LLVM's
+ * getelementptr ([0]) instruction's arguments for identifying offset to
+ * a field.
+ *
+ * Example to provide a better feel.
+ *
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int x = &s->a; // encoded as "0:0" (a is field #0)
+ * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit offset relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_offset_reloc {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+};
+
+#endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
new file mode 100644
index 0000000..4b0b036
--- /dev/null
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2019 Netronome Systems, Inc. */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <net/if.h>
+#include <sys/utsname.h>
+
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+static bool grep(const char *buffer, const char *pattern)
+{
+ return !!strstr(buffer, pattern);
+}
+
+static int get_vendor_id(int ifindex)
+{
+ char ifname[IF_NAMESIZE], path[64], buf[8];
+ ssize_t len;
+ int fd;
+
+ if (!if_indextoname(ifindex, ifname))
+ return -1;
+
+ snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ len = read(fd, buf, sizeof(buf));
+ close(fd);
+ if (len < 0)
+ return -1;
+ if (len >= (ssize_t)sizeof(buf))
+ return -1;
+ buf[len] = '\0';
+
+ return strtol(buf, NULL, 0);
+}
+
+static int get_kernel_version(void)
+{
+ int version, subversion, patchlevel;
+ struct utsname utsn;
+
+ /* Return 0 on failure, and attempt to probe with empty kversion */
+ if (uname(&utsn))
+ return 0;
+
+ if (sscanf(utsn.release, "%d.%d.%d",
+ &version, &subversion, &patchlevel) != 3)
+ return 0;
+
+ return (version << 16) + (subversion << 8) + patchlevel;
+}
+
+static void
+probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
+ size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
+{
+ struct bpf_load_program_attr xattr = {};
+ int fd;
+
+ switch (prog_type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+ break;
+ case BPF_PROG_TYPE_KPROBE:
+ xattr.kern_version = get_kernel_version();
+ break;
+ case BPF_PROG_TYPE_UNSPEC:
+ case BPF_PROG_TYPE_SOCKET_FILTER:
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_XDP:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_SK_MSG:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+ case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ default:
+ break;
+ }
+
+ xattr.prog_type = prog_type;
+ xattr.insns = insns;
+ xattr.insns_cnt = insns_cnt;
+ xattr.license = "GPL";
+ xattr.prog_ifindex = ifindex;
+
+ fd = bpf_load_program_xattr(&xattr, buf, buf_len);
+ if (fd >= 0)
+ close(fd);
+}
+
+bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
+{
+ struct bpf_insn insns[2] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN()
+ };
+
+ if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
+ /* nfp returns -EINVAL on exit(0) with TC offload */
+ insns[0].imm = 2;
+
+ errno = 0;
+ probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+
+ return errno != EINVAL && errno != EOPNOTSUPP;
+}
+
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+ const char *str_sec, size_t str_len)
+{
+ struct btf_header hdr = {
+ .magic = BTF_MAGIC,
+ .version = BTF_VERSION,
+ .hdr_len = sizeof(struct btf_header),
+ .type_len = types_len,
+ .str_off = types_len,
+ .str_len = str_len,
+ };
+ int btf_fd, btf_len;
+ __u8 *raw_btf;
+
+ btf_len = hdr.hdr_len + hdr.type_len + hdr.str_len;
+ raw_btf = malloc(btf_len);
+ if (!raw_btf)
+ return -ENOMEM;
+
+ memcpy(raw_btf, &hdr, sizeof(hdr));
+ memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
+ memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
+
+ btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false);
+
+ free(raw_btf);
+ return btf_fd;
+}
+
+static int load_sk_storage_btf(void)
+{
+ const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l";
+ /* struct bpf_spin_lock {
+ * int val;
+ * };
+ * struct val {
+ * int cnt;
+ * struct bpf_spin_lock l;
+ * };
+ */
+ __u32 types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* struct bpf_spin_lock */ /* [2] */
+ BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4),
+ BTF_MEMBER_ENC(15, 1, 0), /* int val; */
+ /* struct val */ /* [3] */
+ BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
+ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+ };
+
+ return libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs));
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+ int key_size, value_size, max_entries, map_flags;
+ __u32 btf_key_type_id = 0, btf_value_type_id = 0;
+ struct bpf_create_map_attr attr = {};
+ int fd = -1, btf_fd = -1, fd_inner;
+
+ key_size = sizeof(__u32);
+ value_size = sizeof(__u32);
+ max_entries = 1;
+ map_flags = 0;
+
+ switch (map_type) {
+ case BPF_MAP_TYPE_STACK_TRACE:
+ value_size = sizeof(__u64);
+ break;
+ case BPF_MAP_TYPE_LPM_TRIE:
+ key_size = sizeof(__u64);
+ value_size = sizeof(__u64);
+ map_flags = BPF_F_NO_PREALLOC;
+ break;
+ case BPF_MAP_TYPE_CGROUP_STORAGE:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
+ key_size = sizeof(struct bpf_cgroup_storage_key);
+ value_size = sizeof(__u64);
+ max_entries = 0;
+ break;
+ case BPF_MAP_TYPE_QUEUE:
+ case BPF_MAP_TYPE_STACK:
+ key_size = 0;
+ break;
+ case BPF_MAP_TYPE_SK_STORAGE:
+ btf_key_type_id = 1;
+ btf_value_type_id = 3;
+ value_size = 8;
+ max_entries = 0;
+ map_flags = BPF_F_NO_PREALLOC;
+ btf_fd = load_sk_storage_btf();
+ if (btf_fd < 0)
+ return false;
+ break;
+ case BPF_MAP_TYPE_UNSPEC:
+ case BPF_MAP_TYPE_HASH:
+ case BPF_MAP_TYPE_ARRAY:
+ case BPF_MAP_TYPE_PROG_ARRAY:
+ case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+ case BPF_MAP_TYPE_PERCPU_HASH:
+ case BPF_MAP_TYPE_PERCPU_ARRAY:
+ case BPF_MAP_TYPE_CGROUP_ARRAY:
+ case BPF_MAP_TYPE_LRU_HASH:
+ case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+ case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+ case BPF_MAP_TYPE_HASH_OF_MAPS:
+ case BPF_MAP_TYPE_DEVMAP:
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ case BPF_MAP_TYPE_SOCKMAP:
+ case BPF_MAP_TYPE_CPUMAP:
+ case BPF_MAP_TYPE_XSKMAP:
+ case BPF_MAP_TYPE_SOCKHASH:
+ case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ default:
+ break;
+ }
+
+ if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+ map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ /* TODO: probe for device, once libbpf has a function to create
+ * map-in-map for offload
+ */
+ if (ifindex)
+ return false;
+
+ fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH,
+ sizeof(__u32), sizeof(__u32), 1, 0);
+ if (fd_inner < 0)
+ return false;
+ fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32),
+ fd_inner, 1, 0);
+ close(fd_inner);
+ } else {
+ /* Note: No other restriction on map type probes for offload */
+ attr.map_type = map_type;
+ attr.key_size = key_size;
+ attr.value_size = value_size;
+ attr.max_entries = max_entries;
+ attr.map_flags = map_flags;
+ attr.map_ifindex = ifindex;
+ if (btf_fd >= 0) {
+ attr.btf_fd = btf_fd;
+ attr.btf_key_type_id = btf_key_type_id;
+ attr.btf_value_type_id = btf_value_type_id;
+ }
+
+ fd = bpf_create_map_xattr(&attr);
+ }
+ if (fd >= 0)
+ close(fd);
+ if (btf_fd >= 0)
+ close(btf_fd);
+
+ return fd >= 0;
+}
+
+bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
+ __u32 ifindex)
+{
+ struct bpf_insn insns[2] = {
+ BPF_EMIT_CALL(id),
+ BPF_EXIT_INSN()
+ };
+ char buf[4096] = {};
+ bool res;
+
+ probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
+ ifindex);
+ res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
+
+ if (ifindex) {
+ switch (get_vendor_id(ifindex)) {
+ case 0x19ee: /* Netronome specific */
+ res = res && !grep(buf, "not supported by FW") &&
+ !grep(buf, "unsupported function id");
+ break;
+ default:
+ break;
+ }
+ }
+
+ return res;
+}
diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
new file mode 100644
index 0000000..59c779c
--- /dev/null
+++ b/tools/lib/bpf/libbpf_util.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2019 Facebook */
+
+#ifndef __LIBBPF_LIBBPF_UTIL_H
+#define __LIBBPF_LIBBPF_UTIL_H
+
+#include <stdbool.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use these barrier functions instead of smp_[rw]mb() when they are
+ * used in a libbpf header file. That way they can be built into the
+ * application that uses libbpf.
+ */
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_rmb() asm volatile("" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("" : : : "memory")
+# define libbpf_smp_mb() \
+ asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
+/* Hinders stores to be observed before older loads. */
+# define libbpf_smp_rwmb() asm volatile("" : : : "memory")
+#elif defined(__aarch64__)
+# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#elif defined(__arm__)
+/* These are only valid for armv7 and above */
+# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_rwmb() libbpf_smp_mb()
+#else
+/* Architecture missing native barrier functions. */
+# define libbpf_smp_rmb() __sync_synchronize()
+# define libbpf_smp_wmb() __sync_synchronize()
+# define libbpf_smp_mb() __sync_synchronize()
+# define libbpf_smp_rwmb() __sync_synchronize()
+#endif
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
new file mode 100644
index 0000000..ce3ec81
--- /dev/null
+++ b/tools/lib/bpf/netlink.c
@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+#include <time.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
+ void *cookie);
+
+struct xdp_id_md {
+ int ifindex;
+ __u32 flags;
+ __u32 id;
+};
+
+int libbpf_netlink_open(__u32 *nl_pid)
+{
+ struct sockaddr_nl sa;
+ socklen_t addrlen;
+ int one = 1, ret;
+ int sock;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.nl_family = AF_NETLINK;
+
+ sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (sock < 0)
+ return -errno;
+
+ if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+ &one, sizeof(one)) < 0) {
+ fprintf(stderr, "Netlink error reporting not supported\n");
+ }
+
+ if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+
+ addrlen = sizeof(sa);
+ if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+
+ if (addrlen != sizeof(sa)) {
+ ret = -LIBBPF_ERRNO__INTERNAL;
+ goto cleanup;
+ }
+
+ *nl_pid = sa.nl_pid;
+ return sock;
+
+cleanup:
+ close(sock);
+ return ret;
+}
+
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+ __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ bool multipart = true;
+ struct nlmsgerr *err;
+ struct nlmsghdr *nh;
+ char buf[4096];
+ int len, ret;
+
+ while (multipart) {
+ multipart = false;
+ len = recv(sock, buf, sizeof(buf), 0);
+ if (len < 0) {
+ ret = -errno;
+ goto done;
+ }
+
+ if (len == 0)
+ break;
+
+ for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+ nh = NLMSG_NEXT(nh, len)) {
+ if (nh->nlmsg_pid != nl_pid) {
+ ret = -LIBBPF_ERRNO__WRNGPID;
+ goto done;
+ }
+ if (nh->nlmsg_seq != seq) {
+ ret = -LIBBPF_ERRNO__INVSEQ;
+ goto done;
+ }
+ if (nh->nlmsg_flags & NLM_F_MULTI)
+ multipart = true;
+ switch (nh->nlmsg_type) {
+ case NLMSG_ERROR:
+ err = (struct nlmsgerr *)NLMSG_DATA(nh);
+ if (!err->error)
+ continue;
+ ret = err->error;
+ libbpf_nla_dump_errormsg(nh);
+ goto done;
+ case NLMSG_DONE:
+ return 0;
+ default:
+ break;
+ }
+ if (_fn) {
+ ret = _fn(nh, fn, cookie);
+ if (ret)
+ return ret;
+ }
+ }
+ }
+ ret = 0;
+done:
+ return ret;
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+ int sock, seq = 0, ret;
+ struct nlattr *nla, *nla_xdp;
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifinfo;
+ char attrbuf[64];
+ } req;
+ __u32 nl_pid;
+
+ sock = libbpf_netlink_open(&nl_pid);
+ if (sock < 0)
+ return sock;
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_type = RTM_SETLINK;
+ req.nh.nlmsg_pid = 0;
+ req.nh.nlmsg_seq = ++seq;
+ req.ifinfo.ifi_family = AF_UNSPEC;
+ req.ifinfo.ifi_index = ifindex;
+
+ /* started nested attribute for XDP */
+ nla = (struct nlattr *)(((char *)&req)
+ + NLMSG_ALIGN(req.nh.nlmsg_len));
+ nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+ nla->nla_len = NLA_HDRLEN;
+
+ /* add XDP fd */
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = IFLA_XDP_FD;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+ nla->nla_len += nla_xdp->nla_len;
+
+ /* if user passed in any flags, add those too */
+ if (flags) {
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = IFLA_XDP_FLAGS;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+ nla->nla_len += nla_xdp->nla_len;
+ }
+
+ req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+ if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+ ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
+
+cleanup:
+ close(sock);
+ return ret;
+}
+
+static int __dump_link_nlmsg(struct nlmsghdr *nlh,
+ libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
+{
+ struct nlattr *tb[IFLA_MAX + 1], *attr;
+ struct ifinfomsg *ifi = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+ attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+ if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_link_nlmsg(cookie, ifi, tb);
+}
+
+static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags)
+{
+ if (mode != XDP_ATTACHED_MULTI)
+ return IFLA_XDP_PROG_ID;
+ if (flags & XDP_FLAGS_DRV_MODE)
+ return IFLA_XDP_DRV_PROG_ID;
+ if (flags & XDP_FLAGS_HW_MODE)
+ return IFLA_XDP_HW_PROG_ID;
+ if (flags & XDP_FLAGS_SKB_MODE)
+ return IFLA_XDP_SKB_PROG_ID;
+
+ return IFLA_XDP_UNSPEC;
+}
+
+static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
+{
+ struct nlattr *xdp_tb[IFLA_XDP_MAX + 1];
+ struct xdp_id_md *xdp_id = cookie;
+ struct ifinfomsg *ifinfo = msg;
+ unsigned char mode, xdp_attr;
+ int ret;
+
+ if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index)
+ return 0;
+
+ if (!tb[IFLA_XDP])
+ return 0;
+
+ ret = libbpf_nla_parse_nested(xdp_tb, IFLA_XDP_MAX, tb[IFLA_XDP], NULL);
+ if (ret)
+ return ret;
+
+ if (!xdp_tb[IFLA_XDP_ATTACHED])
+ return 0;
+
+ mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]);
+ if (mode == XDP_ATTACHED_NONE)
+ return 0;
+
+ xdp_attr = get_xdp_id_attr(mode, xdp_id->flags);
+ if (!xdp_attr || !xdp_tb[xdp_attr])
+ return 0;
+
+ xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]);
+
+ return 0;
+}
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+ struct xdp_id_md xdp_id = {};
+ int sock, ret;
+ __u32 nl_pid;
+ __u32 mask;
+
+ if (flags & ~XDP_FLAGS_MASK)
+ return -EINVAL;
+
+ /* Check whether the single {HW,DRV,SKB} mode is set */
+ flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
+ mask = flags - 1;
+ if (flags && flags & mask)
+ return -EINVAL;
+
+ sock = libbpf_netlink_open(&nl_pid);
+ if (sock < 0)
+ return sock;
+
+ xdp_id.ifindex = ifindex;
+ xdp_id.flags = flags;
+
+ ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id);
+ if (!ret)
+ *prog_id = xdp_id.id;
+
+ close(sock);
+ return ret;
+}
+
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+ libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct ifinfomsg ifm;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+ .nlh.nlmsg_type = RTM_GETLINK,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .ifm.ifi_family = AF_PACKET,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
+ dump_link_nlmsg, cookie);
+}
+
+static int __dump_class_nlmsg(struct nlmsghdr *nlh,
+ libbpf_dump_nlmsg_t dump_class_nlmsg,
+ void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_class_nlmsg(cookie, t, tb);
+}
+
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+ libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETTCLASS,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg,
+ dump_class_nlmsg, cookie);
+}
+
+static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
+ libbpf_dump_nlmsg_t dump_qdisc_nlmsg,
+ void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_qdisc_nlmsg(cookie, t, tb);
+}
+
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+ libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETQDISC,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg,
+ dump_qdisc_nlmsg, cookie);
+}
+
+static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
+ libbpf_dump_nlmsg_t dump_filter_nlmsg,
+ void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_filter_nlmsg(cookie, t, tb);
+}
+
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+ libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETTFILTER,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ .t.tcm_parent = handle,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg,
+ dump_filter_nlmsg, cookie);
+}
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 4719434..1e69c0c 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -1,13 +1,8 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/*
* NETLINK Netlink attributes
*
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation version 2.1
- * of the License.
- *
* Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
*/
@@ -17,20 +12,15 @@
#include <string.h>
#include <stdio.h>
-static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
- [NLA_U8] = sizeof(uint8_t),
- [NLA_U16] = sizeof(uint16_t),
- [NLA_U32] = sizeof(uint32_t),
- [NLA_U64] = sizeof(uint64_t),
- [NLA_STRING] = 1,
- [NLA_FLAG] = 0,
+static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
+ [LIBBPF_NLA_U8] = sizeof(uint8_t),
+ [LIBBPF_NLA_U16] = sizeof(uint16_t),
+ [LIBBPF_NLA_U32] = sizeof(uint32_t),
+ [LIBBPF_NLA_U64] = sizeof(uint64_t),
+ [LIBBPF_NLA_STRING] = 1,
+ [LIBBPF_NLA_FLAG] = 0,
};
-static int nla_len(const struct nlattr *nla)
-{
- return nla->nla_len - NLA_HDRLEN;
-}
-
static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
{
int totlen = NLA_ALIGN(nla->nla_len);
@@ -46,20 +36,15 @@
nla->nla_len <= remaining;
}
-static void *nla_data(const struct nlattr *nla)
-{
- return (char *) nla + NLA_HDRLEN;
-}
-
static int nla_type(const struct nlattr *nla)
{
return nla->nla_type & NLA_TYPE_MASK;
}
static int validate_nla(struct nlattr *nla, int maxtype,
- struct nla_policy *policy)
+ struct libbpf_nla_policy *policy)
{
- struct nla_policy *pt;
+ struct libbpf_nla_policy *pt;
unsigned int minlen = 0;
int type = nla_type(nla);
@@ -68,23 +53,24 @@
pt = &policy[type];
- if (pt->type > NLA_TYPE_MAX)
+ if (pt->type > LIBBPF_NLA_TYPE_MAX)
return 0;
if (pt->minlen)
minlen = pt->minlen;
- else if (pt->type != NLA_UNSPEC)
+ else if (pt->type != LIBBPF_NLA_UNSPEC)
minlen = nla_attr_minlen[pt->type];
- if (nla_len(nla) < minlen)
+ if (libbpf_nla_len(nla) < minlen)
return -1;
- if (pt->maxlen && nla_len(nla) > pt->maxlen)
+ if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen)
return -1;
- if (pt->type == NLA_STRING) {
- char *data = nla_data(nla);
- if (data[nla_len(nla) - 1] != '\0')
+ if (pt->type == LIBBPF_NLA_STRING) {
+ char *data = libbpf_nla_data(nla);
+
+ if (data[libbpf_nla_len(nla) - 1] != '\0')
return -1;
}
@@ -114,15 +100,15 @@
* @see nla_validate
* @return 0 on success or a negative error code.
*/
-static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
- struct nla_policy *policy)
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+ int len, struct libbpf_nla_policy *policy)
{
struct nlattr *nla;
int rem, err;
memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
- nla_for_each_attr(nla, head, len, rem) {
+ libbpf_nla_for_each_attr(nla, head, len, rem) {
int type = nla_type(nla);
if (type > maxtype)
@@ -146,12 +132,33 @@
return err;
}
-/* dump netlink extended ack error message */
-int nla_dump_errormsg(struct nlmsghdr *nlh)
+/**
+ * Create attribute index based on nested attribute
+ * @arg tb Index array to be filled (maxtype+1 elements).
+ * @arg maxtype Maximum attribute type expected and accepted.
+ * @arg nla Nested Attribute.
+ * @arg policy Attribute validation policy.
+ *
+ * Feeds the stream of attributes nested into the specified attribute
+ * to libbpf_nla_parse().
+ *
+ * @see libbpf_nla_parse
+ * @return 0 on success or a negative error code.
+ */
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+ struct nlattr *nla,
+ struct libbpf_nla_policy *policy)
{
- struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
- [NLMSGERR_ATTR_MSG] = { .type = NLA_STRING },
- [NLMSGERR_ATTR_OFFS] = { .type = NLA_U32 },
+ return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla),
+ libbpf_nla_len(nla), policy);
+}
+
+/* dump netlink extended ack error message */
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
+{
+ struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+ [NLMSGERR_ATTR_MSG] = { .type = LIBBPF_NLA_STRING },
+ [NLMSGERR_ATTR_OFFS] = { .type = LIBBPF_NLA_U32 },
};
struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
struct nlmsgerr *err;
@@ -172,14 +179,15 @@
attr = (struct nlattr *) ((void *) err + hlen);
alen = nlh->nlmsg_len - hlen;
- if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+ if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
+ extack_policy) != 0) {
fprintf(stderr,
"Failed to parse extended error attributes\n");
return 0;
}
if (tb[NLMSGERR_ATTR_MSG])
- errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+ errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
fprintf(stderr, "Kernel error message: %s\n", errmsg);
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 931a71f..6cc3ac9 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -1,18 +1,13 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
/*
* NETLINK Netlink attributes
*
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation version 2.1
- * of the License.
- *
* Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
*/
-#ifndef __NLATTR_H
-#define __NLATTR_H
+#ifndef __LIBBPF_NLATTR_H
+#define __LIBBPF_NLATTR_H
#include <stdint.h>
#include <linux/netlink.h>
@@ -23,19 +18,19 @@
* Standard attribute types to specify validation policy
*/
enum {
- NLA_UNSPEC, /**< Unspecified type, binary data chunk */
- NLA_U8, /**< 8 bit integer */
- NLA_U16, /**< 16 bit integer */
- NLA_U32, /**< 32 bit integer */
- NLA_U64, /**< 64 bit integer */
- NLA_STRING, /**< NUL terminated character string */
- NLA_FLAG, /**< Flag */
- NLA_MSECS, /**< Micro seconds (64bit) */
- NLA_NESTED, /**< Nested attributes */
- __NLA_TYPE_MAX,
+ LIBBPF_NLA_UNSPEC, /**< Unspecified type, binary data chunk */
+ LIBBPF_NLA_U8, /**< 8 bit integer */
+ LIBBPF_NLA_U16, /**< 16 bit integer */
+ LIBBPF_NLA_U32, /**< 32 bit integer */
+ LIBBPF_NLA_U64, /**< 64 bit integer */
+ LIBBPF_NLA_STRING, /**< NUL terminated character string */
+ LIBBPF_NLA_FLAG, /**< Flag */
+ LIBBPF_NLA_MSECS, /**< Micro seconds (64bit) */
+ LIBBPF_NLA_NESTED, /**< Nested attributes */
+ __LIBBPF_NLA_TYPE_MAX,
};
-#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1)
/**
* @ingroup attr
@@ -43,8 +38,8 @@
*
* See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
*/
-struct nla_policy {
- /** Type of attribute or NLA_UNSPEC */
+struct libbpf_nla_policy {
+ /** Type of attribute or LIBBPF_NLA_UNSPEC */
uint16_t type;
/** Minimal length of payload required */
@@ -62,11 +57,50 @@
* @arg len length of attribute stream
* @arg rem initialized to len, holds bytes currently remaining in stream
*/
-#define nla_for_each_attr(pos, head, len, rem) \
+#define libbpf_nla_for_each_attr(pos, head, len, rem) \
for (pos = head, rem = len; \
nla_ok(pos, rem); \
pos = nla_next(pos, &(rem)))
-int nla_dump_errormsg(struct nlmsghdr *nlh);
+/**
+ * libbpf_nla_data - head of payload
+ * @nla: netlink attribute
+ */
+static inline void *libbpf_nla_data(const struct nlattr *nla)
+{
+ return (char *) nla + NLA_HDRLEN;
+}
-#endif /* __NLATTR_H */
+static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
+{
+ return *(uint8_t *)libbpf_nla_data(nla);
+}
+
+static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
+{
+ return *(uint32_t *)libbpf_nla_data(nla);
+}
+
+static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
+{
+ return (const char *)libbpf_nla_data(nla);
+}
+
+/**
+ * libbpf_nla_len - length of payload
+ * @nla: netlink attribute
+ */
+static inline int libbpf_nla_len(const struct nlattr *nla)
+{
+ return nla->nla_len - NLA_HDRLEN;
+}
+
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+ int len, struct libbpf_nla_policy *policy);
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+ struct nlattr *nla,
+ struct libbpf_nla_policy *policy);
+
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
+
+#endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b879811..b8064ee 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
#undef _GNU_SOURCE
#include <string.h>
#include <stdio.h>
@@ -9,9 +9,9 @@
* libc, while checking strerror_r() return to avoid having to check this in
* all places calling it.
*/
-char *str_error(int err, char *dst, int len)
+char *libbpf_strerror_r(int err, char *dst, int len)
{
- int ret = strerror_r(err, dst, len);
+ int ret = strerror_r(err < 0 ? -err : err, dst, len);
if (ret)
snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
return dst;
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 355b1db..a139334 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: LGPL-2.1
-#ifndef BPF_STR_ERROR
-#define BPF_STR_ERROR
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __LIBBPF_STR_ERROR_H
+#define __LIBBPF_STR_ERROR_H
-char *str_error(int err, char *dst, int len);
-#endif // BPF_STR_ERROR
+char *libbpf_strerror_r(int err, char *dst, int len);
+#endif /* __LIBBPF_STR_ERROR_H */
diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp
new file mode 100644
index 0000000..fc13487
--- /dev/null
+++ b/tools/lib/bpf/test_libbpf.cpp
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#include "libbpf.h"
+#include "bpf.h"
+#include "btf.h"
+
+/* do nothing, just make sure we can link successfully */
+
+int main(int argc, char *argv[])
+{
+ /* libbpf.h */
+ libbpf_set_print(NULL);
+
+ /* bpf.h */
+ bpf_prog_get_fd_by_id(0);
+
+ /* btf.h */
+ btf__new(NULL, 0);
+}
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
new file mode 100644
index 0000000..a902838
--- /dev/null
+++ b/tools/lib/bpf/xsk.c
@@ -0,0 +1,700 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * AF_XDP user-space access library.
+ *
+ * Copyright(c) 2018 - 2019 Intel Corporation.
+ *
+ * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <asm/barrier.h>
+#include <linux/compiler.h>
+#include <linux/ethtool.h>
+#include <linux/filter.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_xdp.h>
+#include <linux/sockios.h>
+#include <net/if.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "xsk.h"
+
+#ifndef SOL_XDP
+ #define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+ #define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+ #define PF_XDP AF_XDP
+#endif
+
+struct xsk_umem {
+ struct xsk_ring_prod *fill;
+ struct xsk_ring_cons *comp;
+ char *umem_area;
+ struct xsk_umem_config config;
+ int fd;
+ int refcount;
+};
+
+struct xsk_socket {
+ struct xsk_ring_cons *rx;
+ struct xsk_ring_prod *tx;
+ __u64 outstanding_tx;
+ struct xsk_umem *umem;
+ struct xsk_socket_config config;
+ int fd;
+ int ifindex;
+ int prog_fd;
+ int xsks_map_fd;
+ __u32 queue_id;
+ char ifname[IFNAMSIZ];
+};
+
+struct xsk_nl_info {
+ bool xdp_prog_attached;
+ int ifindex;
+ int fd;
+};
+
+int xsk_umem__fd(const struct xsk_umem *umem)
+{
+ return umem ? umem->fd : -EINVAL;
+}
+
+int xsk_socket__fd(const struct xsk_socket *xsk)
+{
+ return xsk ? xsk->fd : -EINVAL;
+}
+
+static bool xsk_page_aligned(void *buffer)
+{
+ unsigned long addr = (unsigned long)buffer;
+
+ return !(addr & (getpagesize() - 1));
+}
+
+static void xsk_set_umem_config(struct xsk_umem_config *cfg,
+ const struct xsk_umem_config *usr_cfg)
+{
+ if (!usr_cfg) {
+ cfg->fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+ cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+ cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+ cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
+ cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+ return;
+ }
+
+ cfg->fill_size = usr_cfg->fill_size;
+ cfg->comp_size = usr_cfg->comp_size;
+ cfg->frame_size = usr_cfg->frame_size;
+ cfg->frame_headroom = usr_cfg->frame_headroom;
+ cfg->flags = usr_cfg->flags;
+}
+
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+ const struct xsk_socket_config *usr_cfg)
+{
+ if (!usr_cfg) {
+ cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+ cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+ cfg->libbpf_flags = 0;
+ cfg->xdp_flags = 0;
+ cfg->bind_flags = 0;
+ return 0;
+ }
+
+ if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
+ return -EINVAL;
+
+ cfg->rx_size = usr_cfg->rx_size;
+ cfg->tx_size = usr_cfg->tx_size;
+ cfg->libbpf_flags = usr_cfg->libbpf_flags;
+ cfg->xdp_flags = usr_cfg->xdp_flags;
+ cfg->bind_flags = usr_cfg->bind_flags;
+
+ return 0;
+}
+
+int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
+ __u64 size, struct xsk_ring_prod *fill,
+ struct xsk_ring_cons *comp,
+ const struct xsk_umem_config *usr_config)
+{
+ struct xdp_mmap_offsets off;
+ struct xdp_umem_reg mr;
+ struct xsk_umem *umem;
+ socklen_t optlen;
+ void *map;
+ int err;
+
+ if (!umem_area || !umem_ptr || !fill || !comp)
+ return -EFAULT;
+ if (!size && !xsk_page_aligned(umem_area))
+ return -EINVAL;
+
+ umem = calloc(1, sizeof(*umem));
+ if (!umem)
+ return -ENOMEM;
+
+ umem->fd = socket(AF_XDP, SOCK_RAW, 0);
+ if (umem->fd < 0) {
+ err = -errno;
+ goto out_umem_alloc;
+ }
+
+ umem->umem_area = umem_area;
+ xsk_set_umem_config(&umem->config, usr_config);
+
+ mr.addr = (uintptr_t)umem_area;
+ mr.len = size;
+ mr.chunk_size = umem->config.frame_size;
+ mr.headroom = umem->config.frame_headroom;
+ mr.flags = umem->config.flags;
+
+ err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+ err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_FILL_RING,
+ &umem->config.fill_size,
+ sizeof(umem->config.fill_size));
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+ err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_COMPLETION_RING,
+ &umem->config.comp_size,
+ sizeof(umem->config.comp_size));
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+
+ optlen = sizeof(off);
+ err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+
+ map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64),
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,
+ XDP_UMEM_PGOFF_FILL_RING);
+ if (map == MAP_FAILED) {
+ err = -errno;
+ goto out_socket;
+ }
+
+ umem->fill = fill;
+ fill->mask = umem->config.fill_size - 1;
+ fill->size = umem->config.fill_size;
+ fill->producer = map + off.fr.producer;
+ fill->consumer = map + off.fr.consumer;
+ fill->flags = map + off.fr.flags;
+ fill->ring = map + off.fr.desc;
+ fill->cached_cons = umem->config.fill_size;
+
+ map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64),
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,
+ XDP_UMEM_PGOFF_COMPLETION_RING);
+ if (map == MAP_FAILED) {
+ err = -errno;
+ goto out_mmap;
+ }
+
+ umem->comp = comp;
+ comp->mask = umem->config.comp_size - 1;
+ comp->size = umem->config.comp_size;
+ comp->producer = map + off.cr.producer;
+ comp->consumer = map + off.cr.consumer;
+ comp->flags = map + off.cr.flags;
+ comp->ring = map + off.cr.desc;
+
+ *umem_ptr = umem;
+ return 0;
+
+out_mmap:
+ munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64));
+out_socket:
+ close(umem->fd);
+out_umem_alloc:
+ free(umem);
+ return err;
+}
+
+struct xsk_umem_config_v1 {
+ __u32 fill_size;
+ __u32 comp_size;
+ __u32 frame_size;
+ __u32 frame_headroom;
+};
+
+int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
+ __u64 size, struct xsk_ring_prod *fill,
+ struct xsk_ring_cons *comp,
+ const struct xsk_umem_config *usr_config)
+{
+ struct xsk_umem_config config;
+
+ memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1));
+ config.flags = 0;
+
+ return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
+ &config);
+}
+COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
+DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
+
+static int xsk_load_xdp_prog(struct xsk_socket *xsk)
+{
+ static const int log_buf_size = 16 * 1024;
+ char log_buf[log_buf_size];
+ int err, prog_fd;
+
+ /* This is the C-program:
+ * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
+ * {
+ * int index = ctx->rx_queue_index;
+ *
+ * // A set entry here means that the correspnding queue_id
+ * // has an active AF_XDP socket bound to it.
+ * if (bpf_map_lookup_elem(&xsks_map, &index))
+ * return bpf_redirect_map(&xsks_map, index, 0);
+ *
+ * return XDP_PASS;
+ * }
+ */
+ struct bpf_insn prog[] = {
+ /* r1 = *(u32 *)(r1 + 16) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 16),
+ /* *(u32 *)(r10 - 4) = r1 */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_MOV32_IMM(BPF_REG_0, 2),
+ /* if r1 == 0 goto +5 */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
+ /* r2 = *(u32 *)(r10 - 4) */
+ BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4),
+ BPF_MOV32_IMM(BPF_REG_3, 0),
+ BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+ /* The jumps are to this instruction */
+ BPF_EXIT_INSN(),
+ };
+ size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+ prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
+ "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
+ log_buf_size);
+ if (prog_fd < 0) {
+ pr_warning("BPF log buffer:\n%s", log_buf);
+ return prog_fd;
+ }
+
+ err = bpf_set_link_xdp_fd(xsk->ifindex, prog_fd, xsk->config.xdp_flags);
+ if (err) {
+ close(prog_fd);
+ return err;
+ }
+
+ xsk->prog_fd = prog_fd;
+ return 0;
+}
+
+static int xsk_get_max_queues(struct xsk_socket *xsk)
+{
+ struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
+ struct ifreq ifr = {};
+ int fd, err, ret;
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0)
+ return -errno;
+
+ ifr.ifr_data = (void *)&channels;
+ memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+ ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+ err = ioctl(fd, SIOCETHTOOL, &ifr);
+ if (err && errno != EOPNOTSUPP) {
+ ret = -errno;
+ goto out;
+ }
+
+ if (err || channels.max_combined == 0)
+ /* If the device says it has no channels, then all traffic
+ * is sent to a single stream, so max queues = 1.
+ */
+ ret = 1;
+ else
+ ret = channels.max_combined;
+
+out:
+ close(fd);
+ return ret;
+}
+
+static int xsk_create_bpf_maps(struct xsk_socket *xsk)
+{
+ int max_queues;
+ int fd;
+
+ max_queues = xsk_get_max_queues(xsk);
+ if (max_queues < 0)
+ return max_queues;
+
+ fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
+ sizeof(int), sizeof(int), max_queues, 0);
+ if (fd < 0)
+ return fd;
+
+ xsk->xsks_map_fd = fd;
+
+ return 0;
+}
+
+static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
+{
+ bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
+ close(xsk->xsks_map_fd);
+}
+
+static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
+{
+ __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info);
+ __u32 map_len = sizeof(struct bpf_map_info);
+ struct bpf_prog_info prog_info = {};
+ struct bpf_map_info map_info;
+ int fd, err;
+
+ err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len);
+ if (err)
+ return err;
+
+ num_maps = prog_info.nr_map_ids;
+
+ map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids));
+ if (!map_ids)
+ return -ENOMEM;
+
+ memset(&prog_info, 0, prog_len);
+ prog_info.nr_map_ids = num_maps;
+ prog_info.map_ids = (__u64)(unsigned long)map_ids;
+
+ err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len);
+ if (err)
+ goto out_map_ids;
+
+ xsk->xsks_map_fd = -1;
+
+ for (i = 0; i < prog_info.nr_map_ids; i++) {
+ fd = bpf_map_get_fd_by_id(map_ids[i]);
+ if (fd < 0)
+ continue;
+
+ err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
+ if (err) {
+ close(fd);
+ continue;
+ }
+
+ if (!strcmp(map_info.name, "xsks_map")) {
+ xsk->xsks_map_fd = fd;
+ continue;
+ }
+
+ close(fd);
+ }
+
+ err = 0;
+ if (xsk->xsks_map_fd == -1)
+ err = -ENOENT;
+
+out_map_ids:
+ free(map_ids);
+ return err;
+}
+
+static int xsk_set_bpf_maps(struct xsk_socket *xsk)
+{
+ return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id,
+ &xsk->fd, 0);
+}
+
+static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
+{
+ __u32 prog_id = 0;
+ int err;
+
+ err = bpf_get_link_xdp_id(xsk->ifindex, &prog_id,
+ xsk->config.xdp_flags);
+ if (err)
+ return err;
+
+ if (!prog_id) {
+ err = xsk_create_bpf_maps(xsk);
+ if (err)
+ return err;
+
+ err = xsk_load_xdp_prog(xsk);
+ if (err) {
+ xsk_delete_bpf_maps(xsk);
+ return err;
+ }
+ } else {
+ xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+ err = xsk_lookup_bpf_maps(xsk);
+ if (err) {
+ close(xsk->prog_fd);
+ return err;
+ }
+ }
+
+ err = xsk_set_bpf_maps(xsk);
+ if (err) {
+ xsk_delete_bpf_maps(xsk);
+ close(xsk->prog_fd);
+ return err;
+ }
+
+ return 0;
+}
+
+int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
+ __u32 queue_id, struct xsk_umem *umem,
+ struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
+ const struct xsk_socket_config *usr_config)
+{
+ void *rx_map = NULL, *tx_map = NULL;
+ struct sockaddr_xdp sxdp = {};
+ struct xdp_mmap_offsets off;
+ struct xsk_socket *xsk;
+ socklen_t optlen;
+ int err;
+
+ if (!umem || !xsk_ptr || !rx || !tx)
+ return -EFAULT;
+
+ if (umem->refcount) {
+ pr_warning("Error: shared umems not supported by libbpf.\n");
+ return -EBUSY;
+ }
+
+ xsk = calloc(1, sizeof(*xsk));
+ if (!xsk)
+ return -ENOMEM;
+
+ if (umem->refcount++ > 0) {
+ xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
+ if (xsk->fd < 0) {
+ err = -errno;
+ goto out_xsk_alloc;
+ }
+ } else {
+ xsk->fd = umem->fd;
+ }
+
+ xsk->outstanding_tx = 0;
+ xsk->queue_id = queue_id;
+ xsk->umem = umem;
+ xsk->ifindex = if_nametoindex(ifname);
+ if (!xsk->ifindex) {
+ err = -errno;
+ goto out_socket;
+ }
+ memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+ xsk->ifname[IFNAMSIZ - 1] = '\0';
+
+ err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+ if (err)
+ goto out_socket;
+
+ if (rx) {
+ err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
+ &xsk->config.rx_size,
+ sizeof(xsk->config.rx_size));
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+ }
+ if (tx) {
+ err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
+ &xsk->config.tx_size,
+ sizeof(xsk->config.tx_size));
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+ }
+
+ optlen = sizeof(off);
+ err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ if (err) {
+ err = -errno;
+ goto out_socket;
+ }
+
+ if (rx) {
+ rx_map = mmap(NULL, off.rx.desc +
+ xsk->config.rx_size * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
+ xsk->fd, XDP_PGOFF_RX_RING);
+ if (rx_map == MAP_FAILED) {
+ err = -errno;
+ goto out_socket;
+ }
+
+ rx->mask = xsk->config.rx_size - 1;
+ rx->size = xsk->config.rx_size;
+ rx->producer = rx_map + off.rx.producer;
+ rx->consumer = rx_map + off.rx.consumer;
+ rx->flags = rx_map + off.rx.flags;
+ rx->ring = rx_map + off.rx.desc;
+ }
+ xsk->rx = rx;
+
+ if (tx) {
+ tx_map = mmap(NULL, off.tx.desc +
+ xsk->config.tx_size * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
+ xsk->fd, XDP_PGOFF_TX_RING);
+ if (tx_map == MAP_FAILED) {
+ err = -errno;
+ goto out_mmap_rx;
+ }
+
+ tx->mask = xsk->config.tx_size - 1;
+ tx->size = xsk->config.tx_size;
+ tx->producer = tx_map + off.tx.producer;
+ tx->consumer = tx_map + off.tx.consumer;
+ tx->flags = tx_map + off.tx.flags;
+ tx->ring = tx_map + off.tx.desc;
+ tx->cached_cons = xsk->config.tx_size;
+ }
+ xsk->tx = tx;
+
+ sxdp.sxdp_family = PF_XDP;
+ sxdp.sxdp_ifindex = xsk->ifindex;
+ sxdp.sxdp_queue_id = xsk->queue_id;
+ sxdp.sxdp_flags = xsk->config.bind_flags;
+
+ err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp));
+ if (err) {
+ err = -errno;
+ goto out_mmap_tx;
+ }
+
+ xsk->prog_fd = -1;
+
+ if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
+ err = xsk_setup_xdp_prog(xsk);
+ if (err)
+ goto out_mmap_tx;
+ }
+
+ *xsk_ptr = xsk;
+ return 0;
+
+out_mmap_tx:
+ if (tx)
+ munmap(tx_map, off.tx.desc +
+ xsk->config.tx_size * sizeof(struct xdp_desc));
+out_mmap_rx:
+ if (rx)
+ munmap(rx_map, off.rx.desc +
+ xsk->config.rx_size * sizeof(struct xdp_desc));
+out_socket:
+ if (--umem->refcount)
+ close(xsk->fd);
+out_xsk_alloc:
+ free(xsk);
+ return err;
+}
+
+int xsk_umem__delete(struct xsk_umem *umem)
+{
+ struct xdp_mmap_offsets off;
+ socklen_t optlen;
+ int err;
+
+ if (!umem)
+ return 0;
+
+ if (umem->refcount)
+ return -EBUSY;
+
+ optlen = sizeof(off);
+ err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ if (!err) {
+ munmap(umem->fill->ring - off.fr.desc,
+ off.fr.desc + umem->config.fill_size * sizeof(__u64));
+ munmap(umem->comp->ring - off.cr.desc,
+ off.cr.desc + umem->config.comp_size * sizeof(__u64));
+ }
+
+ close(umem->fd);
+ free(umem);
+
+ return 0;
+}
+
+void xsk_socket__delete(struct xsk_socket *xsk)
+{
+ size_t desc_sz = sizeof(struct xdp_desc);
+ struct xdp_mmap_offsets off;
+ socklen_t optlen;
+ int err;
+
+ if (!xsk)
+ return;
+
+ if (xsk->prog_fd != -1) {
+ xsk_delete_bpf_maps(xsk);
+ close(xsk->prog_fd);
+ }
+
+ optlen = sizeof(off);
+ err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+ if (!err) {
+ if (xsk->rx) {
+ munmap(xsk->rx->ring - off.rx.desc,
+ off.rx.desc + xsk->config.rx_size * desc_sz);
+ }
+ if (xsk->tx) {
+ munmap(xsk->tx->ring - off.tx.desc,
+ off.tx.desc + xsk->config.tx_size * desc_sz);
+ }
+
+ }
+
+ xsk->umem->refcount--;
+ /* Do not close an fd that also has an associated umem connected
+ * to it.
+ */
+ if (xsk->fd != xsk->umem->fd)
+ close(xsk->fd);
+ free(xsk);
+}
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
new file mode 100644
index 0000000..584f682
--- /dev/null
+++ b/tools/lib/bpf/xsk.h
@@ -0,0 +1,246 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * AF_XDP user-space access library.
+ *
+ * Copyright(c) 2018 - 2019 Intel Corporation.
+ *
+ * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef __LIBBPF_XSK_H
+#define __LIBBPF_XSK_H
+
+#include <stdio.h>
+#include <stdint.h>
+#include <linux/if_xdp.h>
+
+#include "libbpf.h"
+#include "libbpf_util.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Do not access these members directly. Use the functions below. */
+#define DEFINE_XSK_RING(name) \
+struct name { \
+ __u32 cached_prod; \
+ __u32 cached_cons; \
+ __u32 mask; \
+ __u32 size; \
+ __u32 *producer; \
+ __u32 *consumer; \
+ void *ring; \
+ __u32 *flags; \
+}
+
+DEFINE_XSK_RING(xsk_ring_prod);
+DEFINE_XSK_RING(xsk_ring_cons);
+
+/* For a detailed explanation on the memory barriers associated with the
+ * ring, please take a look at net/xdp/xsk_queue.h.
+ */
+
+struct xsk_umem;
+struct xsk_socket;
+
+static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill,
+ __u32 idx)
+{
+ __u64 *addrs = (__u64 *)fill->ring;
+
+ return &addrs[idx & fill->mask];
+}
+
+static inline const __u64 *
+xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx)
+{
+ const __u64 *addrs = (const __u64 *)comp->ring;
+
+ return &addrs[idx & comp->mask];
+}
+
+static inline struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx,
+ __u32 idx)
+{
+ struct xdp_desc *descs = (struct xdp_desc *)tx->ring;
+
+ return &descs[idx & tx->mask];
+}
+
+static inline const struct xdp_desc *
+xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx)
+{
+ const struct xdp_desc *descs = (const struct xdp_desc *)rx->ring;
+
+ return &descs[idx & rx->mask];
+}
+
+static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r)
+{
+ return *r->flags & XDP_RING_NEED_WAKEUP;
+}
+
+static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
+{
+ __u32 free_entries = r->cached_cons - r->cached_prod;
+
+ if (free_entries >= nb)
+ return free_entries;
+
+ /* Refresh the local tail pointer.
+ * cached_cons is r->size bigger than the real consumer pointer so
+ * that this addition can be avoided in the more frequently
+ * executed code that computs free_entries in the beginning of
+ * this function. Without this optimization it whould have been
+ * free_entries = r->cached_prod - r->cached_cons + r->size.
+ */
+ r->cached_cons = *r->consumer + r->size;
+
+ return r->cached_cons - r->cached_prod;
+}
+
+static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
+{
+ __u32 entries = r->cached_prod - r->cached_cons;
+
+ if (entries == 0) {
+ r->cached_prod = *r->producer;
+ entries = r->cached_prod - r->cached_cons;
+ }
+
+ return (entries > nb) ? nb : entries;
+}
+
+static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
+ size_t nb, __u32 *idx)
+{
+ if (xsk_prod_nb_free(prod, nb) < nb)
+ return 0;
+
+ *idx = prod->cached_prod;
+ prod->cached_prod += nb;
+
+ return nb;
+}
+
+static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
+{
+ /* Make sure everything has been written to the ring before indicating
+ * this to the kernel by writing the producer pointer.
+ */
+ libbpf_smp_wmb();
+
+ *prod->producer += nb;
+}
+
+static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
+ size_t nb, __u32 *idx)
+{
+ size_t entries = xsk_cons_nb_avail(cons, nb);
+
+ if (entries > 0) {
+ /* Make sure we do not speculatively read the data before
+ * we have received the packet buffers from the ring.
+ */
+ libbpf_smp_rmb();
+
+ *idx = cons->cached_cons;
+ cons->cached_cons += entries;
+ }
+
+ return entries;
+}
+
+static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
+{
+ /* Make sure data has been read before indicating we are done
+ * with the entries by updating the consumer pointer.
+ */
+ libbpf_smp_rwmb();
+
+ *cons->consumer += nb;
+}
+
+static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
+{
+ return &((char *)umem_area)[addr];
+}
+
+static inline __u64 xsk_umem__extract_addr(__u64 addr)
+{
+ return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+}
+
+static inline __u64 xsk_umem__extract_offset(__u64 addr)
+{
+ return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
+}
+
+static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
+{
+ return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
+}
+
+LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+
+#define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048
+#define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
+#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
+#define XSK_UMEM__DEFAULT_FLAGS 0
+
+struct xsk_umem_config {
+ __u32 fill_size;
+ __u32 comp_size;
+ __u32 frame_size;
+ __u32 frame_headroom;
+ __u32 flags;
+};
+
+/* Flags for the libbpf_flags field. */
+#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
+
+struct xsk_socket_config {
+ __u32 rx_size;
+ __u32 tx_size;
+ __u32 libbpf_flags;
+ __u32 xdp_flags;
+ __u16 bind_flags;
+};
+
+/* Set config to NULL to get the default configuration. */
+LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
+ void *umem_area, __u64 size,
+ struct xsk_ring_prod *fill,
+ struct xsk_ring_cons *comp,
+ const struct xsk_umem_config *config);
+LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
+ void *umem_area, __u64 size,
+ struct xsk_ring_prod *fill,
+ struct xsk_ring_cons *comp,
+ const struct xsk_umem_config *config);
+LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
+ void *umem_area, __u64 size,
+ struct xsk_ring_prod *fill,
+ struct xsk_ring_cons *comp,
+ const struct xsk_umem_config *config);
+LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
+ const char *ifname, __u32 queue_id,
+ struct xsk_umem *umem,
+ struct xsk_ring_cons *rx,
+ struct xsk_ring_prod *tx,
+ const struct xsk_socket_config *config);
+
+/* Returns 0 for success and -EBUSY if the umem is still in use. */
+LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __LIBBPF_XSK_H */
diff --git a/tools/lib/ctype.c b/tools/lib/ctype.c
new file mode 100644
index 0000000..4d2e05f
--- /dev/null
+++ b/tools/lib/ctype.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/lib/ctype.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#include <linux/ctype.h>
+#include <linux/compiler.h>
+
+const unsigned char _ctype[] = {
+_C,_C,_C,_C,_C,_C,_C,_C, /* 0-7 */
+_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C, /* 8-15 */
+_C,_C,_C,_C,_C,_C,_C,_C, /* 16-23 */
+_C,_C,_C,_C,_C,_C,_C,_C, /* 24-31 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P, /* 32-39 */
+_P,_P,_P,_P,_P,_P,_P,_P, /* 40-47 */
+_D,_D,_D,_D,_D,_D,_D,_D, /* 48-55 */
+_D,_D,_P,_P,_P,_P,_P,_P, /* 56-63 */
+_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U, /* 64-71 */
+_U,_U,_U,_U,_U,_U,_U,_U, /* 72-79 */
+_U,_U,_U,_U,_U,_U,_U,_U, /* 80-87 */
+_U,_U,_U,_P,_P,_P,_P,_P, /* 88-95 */
+_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L, /* 96-103 */
+_L,_L,_L,_L,_L,_L,_L,_L, /* 104-111 */
+_L,_L,_L,_L,_L,_L,_L,_L, /* 112-119 */
+_L,_L,_L,_P,_P,_P,_P,_C, /* 120-127 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 128-143 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 144-159 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 160-175 */
+_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 176-191 */
+_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U, /* 192-207 */
+_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L, /* 208-223 */
+_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L, /* 224-239 */
+_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L}; /* 240-255 */
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index a88bd50..ac37022 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* bit search implementation
*
* Copied from lib/find_bit.c to tools/lib/find_bit.c
@@ -11,11 +12,6 @@
*
* Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
* size and improve performance, 2015.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/bitops.h>
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index 8862da8..a81d91d 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -44,6 +44,9 @@
struct lockdep_map *nest_lock, unsigned long ip);
void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip);
+void lockdep_reset_lock(struct lockdep_map *lock);
+void lockdep_register_key(struct lock_class_key *key);
+void lockdep_unregister_key(struct lock_class_key *key);
extern void debug_check_no_locks_freed(const void *from, unsigned long len);
#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
index a80ac39..783dd0d 100644
--- a/tools/lib/lockdep/include/liblockdep/mutex.h
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -7,6 +7,7 @@
struct liblockdep_pthread_mutex {
pthread_mutex_t mutex;
+ struct lock_class_key key;
struct lockdep_map dep_map;
};
@@ -27,11 +28,10 @@
return pthread_mutex_init(&lock->mutex, __mutexattr);
}
-#define liblockdep_pthread_mutex_init(mutex, mutexattr) \
-({ \
- static struct lock_class_key __key; \
- \
- __mutex_init((mutex), #mutex, &__key, (mutexattr)); \
+#define liblockdep_pthread_mutex_init(mutex, mutexattr) \
+({ \
+ lockdep_register_key(&(mutex)->key); \
+ __mutex_init((mutex), #mutex, &(mutex)->key, (mutexattr)); \
})
static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
@@ -54,6 +54,8 @@
static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock)
{
+ lockdep_reset_lock(&lock->dep_map);
+ lockdep_unregister_key(&lock->key);
return pthread_mutex_destroy(&lock->mutex);
}
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
index a96c3bf..365762e 100644
--- a/tools/lib/lockdep/include/liblockdep/rwlock.h
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -60,10 +60,10 @@
return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
}
-static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
+static inline int liblockdep_pthread_rwlock_trywrlock(liblockdep_pthread_rwlock_t *lock)
{
lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
- return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
+ return pthread_rwlock_trywrlock(&lock->rwlock) == 0 ? 1 : 0;
}
static inline int liblockdep_rwlock_destroy(liblockdep_pthread_rwlock_t *lock)
@@ -79,7 +79,7 @@
#define pthread_rwlock_unlock liblockdep_pthread_rwlock_unlock
#define pthread_rwlock_wrlock liblockdep_pthread_rwlock_wrlock
#define pthread_rwlock_tryrdlock liblockdep_pthread_rwlock_tryrdlock
-#define pthread_rwlock_trywlock liblockdep_pthread_rwlock_trywlock
+#define pthread_rwlock_trywrlock liblockdep_pthread_rwlock_trywrlock
#define pthread_rwlock_destroy liblockdep_rwlock_destroy
#endif
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
index 6002fcf..348a9d0 100644
--- a/tools/lib/lockdep/lockdep.c
+++ b/tools/lib/lockdep/lockdep.c
@@ -15,6 +15,11 @@
abort();
}
+void print_irqtrace_events(struct task_struct *curr)
+{
+ abort();
+}
+
static struct new_utsname *init_utsname(void)
{
static struct new_utsname n = (struct new_utsname) {
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
index 2e570a1..11f4256 100755
--- a/tools/lib/lockdep/run_tests.sh
+++ b/tools/lib/lockdep/run_tests.sh
@@ -1,32 +1,47 @@
#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
-make &> /dev/null
+if ! make >/dev/null; then
+ echo "Building liblockdep failed."
+ echo "FAILED!"
+ exit 1
+fi
-for i in `ls tests/*.c`; do
+find tests -name '*.c' | sort | while read -r i; do
testname=$(basename "$i" .c)
- gcc -o tests/$testname -pthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null
echo -ne "$testname... "
- if [ $(timeout 1 ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then
+ if gcc -o "tests/$testname" -pthread "$i" liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &&
+ timeout 1 "tests/$testname" 2>&1 | /bin/bash "tests/${testname}.sh"; then
echo "PASSED!"
else
echo "FAILED!"
fi
- if [ -f "tests/$testname" ]; then
- rm tests/$testname
- fi
+ rm -f "tests/$testname"
done
-for i in `ls tests/*.c`; do
+find tests -name '*.c' | sort | while read -r i; do
testname=$(basename "$i" .c)
- gcc -o tests/$testname -pthread -Iinclude $i &> /dev/null
echo -ne "(PRELOAD) $testname... "
- if [ $(timeout 1 ./lockdep ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then
+ if gcc -o "tests/$testname" -pthread -Iinclude "$i" &&
+ timeout 1 ./lockdep "tests/$testname" 2>&1 |
+ /bin/bash "tests/${testname}.sh"; then
echo "PASSED!"
else
echo "FAILED!"
fi
- if [ -f "tests/$testname" ]; then
- rm tests/$testname
+ rm -f "tests/$testname"
+done
+
+find tests -name '*.c' | sort | while read -r i; do
+ testname=$(basename "$i" .c)
+ echo -ne "(PRELOAD + Valgrind) $testname... "
+ if gcc -o "tests/$testname" -pthread -Iinclude "$i" &&
+ { timeout 10 valgrind --read-var-info=yes ./lockdep "./tests/$testname" >& "tests/${testname}.vg.out"; true; } &&
+ /bin/bash "tests/${testname}.sh" < "tests/${testname}.vg.out" &&
+ ! grep -Eq '(^==[0-9]*== (Invalid |Uninitialised ))|Mismatched free|Source and destination overlap| UME ' "tests/${testname}.vg.out"; then
+ echo "PASSED!"
+ else
+ echo "FAILED!"
fi
+ rm -f "tests/$testname"
done
diff --git a/tools/lib/lockdep/tests/AA.sh b/tools/lib/lockdep/tests/AA.sh
new file mode 100644
index 0000000..f39b328
--- /dev/null
+++ b/tools/lib/lockdep/tests/AA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible recursive locking detected'
diff --git a/tools/lib/lockdep/tests/ABA.sh b/tools/lib/lockdep/tests/ABA.sh
new file mode 100644
index 0000000..f39b328
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible recursive locking detected'
diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c
index 1460afd..543789b 100644
--- a/tools/lib/lockdep/tests/ABBA.c
+++ b/tools/lib/lockdep/tests/ABBA.c
@@ -11,4 +11,16 @@
LOCK_UNLOCK_2(a, b);
LOCK_UNLOCK_2(b, a);
+
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
+
+ pthread_mutex_init(&a, NULL);
+ pthread_mutex_init(&b, NULL);
+
+ LOCK_UNLOCK_2(a, b);
+ LOCK_UNLOCK_2(b, a);
+
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABBA.sh b/tools/lib/lockdep/tests/ABBA.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABBA_2threads.sh b/tools/lib/lockdep/tests/ABBA_2threads.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA_2threads.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABBCCA.c b/tools/lib/lockdep/tests/ABBCCA.c
index a54c1b2..4844612 100644
--- a/tools/lib/lockdep/tests/ABBCCA.c
+++ b/tools/lib/lockdep/tests/ABBCCA.c
@@ -13,4 +13,8 @@
LOCK_UNLOCK_2(a, b);
LOCK_UNLOCK_2(b, c);
LOCK_UNLOCK_2(c, a);
+
+ pthread_mutex_destroy(&c);
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABBCCA.sh b/tools/lib/lockdep/tests/ABBCCA.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABBCCDDA.c b/tools/lib/lockdep/tests/ABBCCDDA.c
index aa5d194..3570bf7 100644
--- a/tools/lib/lockdep/tests/ABBCCDDA.c
+++ b/tools/lib/lockdep/tests/ABBCCDDA.c
@@ -15,4 +15,9 @@
LOCK_UNLOCK_2(b, c);
LOCK_UNLOCK_2(c, d);
LOCK_UNLOCK_2(d, a);
+
+ pthread_mutex_destroy(&d);
+ pthread_mutex_destroy(&c);
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABBCCDDA.sh b/tools/lib/lockdep/tests/ABBCCDDA.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCDDA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABCABC.c b/tools/lib/lockdep/tests/ABCABC.c
index b54a08e..a1c4659 100644
--- a/tools/lib/lockdep/tests/ABCABC.c
+++ b/tools/lib/lockdep/tests/ABCABC.c
@@ -13,4 +13,8 @@
LOCK_UNLOCK_2(a, b);
LOCK_UNLOCK_2(c, a);
LOCK_UNLOCK_2(b, c);
+
+ pthread_mutex_destroy(&c);
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABCABC.sh b/tools/lib/lockdep/tests/ABCABC.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCABC.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABCDBCDA.c b/tools/lib/lockdep/tests/ABCDBCDA.c
index a567422..335af1c 100644
--- a/tools/lib/lockdep/tests/ABCDBCDA.c
+++ b/tools/lib/lockdep/tests/ABCDBCDA.c
@@ -15,4 +15,9 @@
LOCK_UNLOCK_2(c, d);
LOCK_UNLOCK_2(b, c);
LOCK_UNLOCK_2(d, a);
+
+ pthread_mutex_destroy(&d);
+ pthread_mutex_destroy(&c);
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABCDBCDA.sh b/tools/lib/lockdep/tests/ABCDBCDA.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBCDA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/ABCDBDDA.c b/tools/lib/lockdep/tests/ABCDBDDA.c
index 238a335..3c59728 100644
--- a/tools/lib/lockdep/tests/ABCDBDDA.c
+++ b/tools/lib/lockdep/tests/ABCDBDDA.c
@@ -15,4 +15,9 @@
LOCK_UNLOCK_2(c, d);
LOCK_UNLOCK_2(b, d);
LOCK_UNLOCK_2(d, a);
+
+ pthread_mutex_destroy(&d);
+ pthread_mutex_destroy(&c);
+ pthread_mutex_destroy(&b);
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/ABCDBDDA.sh b/tools/lib/lockdep/tests/ABCDBDDA.sh
new file mode 100644
index 0000000..fc31c60
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBDDA.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible circular locking dependency detected'
diff --git a/tools/lib/lockdep/tests/WW.sh b/tools/lib/lockdep/tests/WW.sh
new file mode 100644
index 0000000..f39b328
--- /dev/null
+++ b/tools/lib/lockdep/tests/WW.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: possible recursive locking detected'
diff --git a/tools/lib/lockdep/tests/unlock_balance.c b/tools/lib/lockdep/tests/unlock_balance.c
index 34cf32f..dba2506 100644
--- a/tools/lib/lockdep/tests/unlock_balance.c
+++ b/tools/lib/lockdep/tests/unlock_balance.c
@@ -10,4 +10,6 @@
pthread_mutex_lock(&a);
pthread_mutex_unlock(&a);
pthread_mutex_unlock(&a);
+
+ pthread_mutex_destroy(&a);
}
diff --git a/tools/lib/lockdep/tests/unlock_balance.sh b/tools/lib/lockdep/tests/unlock_balance.sh
new file mode 100644
index 0000000..c6e3952
--- /dev/null
+++ b/tools/lib/lockdep/tests/unlock_balance.sh
@@ -0,0 +1,2 @@
+#!/bin/bash
+grep -q 'WARNING: bad unlock balance detected'
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
index 17c2b59..2548ff8 100644
--- a/tools/lib/rbtree.c
+++ b/tools/lib/rbtree.c
@@ -1,27 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
Red Black Trees
(C) 1999 Andrea Arcangeli <andrea@suse.de>
(C) 2002 David Woodhouse <dwmw2@infradead.org>
(C) 2012 Michel Lespinasse <walken@google.com>
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2 of the License, or
- (at your option) any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
linux/lib/rbtree.c
*/
#include <linux/rbtree_augmented.h>
+#include <linux/export.h>
/*
* red-black trees properties: http://en.wikipedia.org/wiki/Rbtree
@@ -43,6 +32,30 @@
* parentheses and have some accompanying text comment.
*/
+/*
+ * Notes on lockless lookups:
+ *
+ * All stores to the tree structure (rb_left and rb_right) must be done using
+ * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the
+ * tree structure as seen in program order.
+ *
+ * These two requirements will allow lockless iteration of the tree -- not
+ * correct iteration mind you, tree rotations are not atomic so a lookup might
+ * miss entire subtrees.
+ *
+ * But they do guarantee that any such traversal will only see valid elements
+ * and that it will indeed complete -- does not get stuck in a loop.
+ *
+ * It also guarantees that if the lookup returns an element it is the 'correct'
+ * one. But not returning an element does _NOT_ mean it's not present.
+ *
+ * NOTE:
+ *
+ * Stores to __rb_parent_color are not important for simple lookups so those
+ * are left undone as of now. Nor did I check for loops involving parent
+ * pointers.
+ */
+
static inline void rb_set_black(struct rb_node *rb)
{
rb->__rb_parent_color |= RB_BLACK;
@@ -76,16 +89,25 @@
while (true) {
/*
- * Loop invariant: node is red
- *
- * If there is a black parent, we are done.
- * Otherwise, take some corrective action as we don't
- * want a red root or two consecutive red nodes.
+ * Loop invariant: node is red.
*/
- if (!parent) {
+ if (unlikely(!parent)) {
+ /*
+ * The inserted node is root. Either this is the
+ * first node, or we recursed at Case 1 below and
+ * are no longer violating 4).
+ */
rb_set_parent_color(node, NULL, RB_BLACK);
break;
- } else if (rb_is_black(parent))
+ }
+
+ /*
+ * If there is a black parent, we are done.
+ * Otherwise, take some corrective action as,
+ * per 4), we don't want a red root or two
+ * consecutive red nodes.
+ */
+ if(rb_is_black(parent))
break;
gparent = rb_red_parent(parent);
@@ -94,7 +116,7 @@
if (parent != tmp) { /* parent == gparent->rb_left */
if (tmp && rb_is_red(tmp)) {
/*
- * Case 1 - color flips
+ * Case 1 - node's uncle is red (color flips).
*
* G g
* / \ / \
@@ -117,7 +139,8 @@
tmp = parent->rb_right;
if (node == tmp) {
/*
- * Case 2 - left rotate at parent
+ * Case 2 - node's uncle is black and node is
+ * the parent's right child (left rotate at parent).
*
* G G
* / \ / \
@@ -128,8 +151,9 @@
* This still leaves us in violation of 4), the
* continuation into Case 3 will fix that.
*/
- parent->rb_right = tmp = node->rb_left;
- node->rb_left = parent;
+ tmp = node->rb_left;
+ WRITE_ONCE(parent->rb_right, tmp);
+ WRITE_ONCE(node->rb_left, parent);
if (tmp)
rb_set_parent_color(tmp, parent,
RB_BLACK);
@@ -140,7 +164,8 @@
}
/*
- * Case 3 - right rotate at gparent
+ * Case 3 - node's uncle is black and node is
+ * the parent's left child (right rotate at gparent).
*
* G P
* / \ / \
@@ -148,8 +173,8 @@
* / \
* n U
*/
- gparent->rb_left = tmp; /* == parent->rb_right */
- parent->rb_right = gparent;
+ WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */
+ WRITE_ONCE(parent->rb_right, gparent);
if (tmp)
rb_set_parent_color(tmp, gparent, RB_BLACK);
__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -170,8 +195,9 @@
tmp = parent->rb_left;
if (node == tmp) {
/* Case 2 - right rotate at parent */
- parent->rb_left = tmp = node->rb_right;
- node->rb_right = parent;
+ tmp = node->rb_right;
+ WRITE_ONCE(parent->rb_left, tmp);
+ WRITE_ONCE(node->rb_right, parent);
if (tmp)
rb_set_parent_color(tmp, parent,
RB_BLACK);
@@ -182,8 +208,8 @@
}
/* Case 3 - left rotate at gparent */
- gparent->rb_right = tmp; /* == parent->rb_left */
- parent->rb_left = gparent;
+ WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */
+ WRITE_ONCE(parent->rb_left, gparent);
if (tmp)
rb_set_parent_color(tmp, gparent, RB_BLACK);
__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -223,8 +249,9 @@
* / \ / \
* Sl Sr N Sl
*/
- parent->rb_right = tmp1 = sibling->rb_left;
- sibling->rb_left = parent;
+ tmp1 = sibling->rb_left;
+ WRITE_ONCE(parent->rb_right, tmp1);
+ WRITE_ONCE(sibling->rb_left, parent);
rb_set_parent_color(tmp1, parent, RB_BLACK);
__rb_rotate_set_parents(parent, sibling, root,
RB_RED);
@@ -268,15 +295,31 @@
*
* (p) (p)
* / \ / \
- * N S --> N Sl
+ * N S --> N sl
* / \ \
- * sl Sr s
+ * sl Sr S
* \
* Sr
+ *
+ * Note: p might be red, and then both
+ * p and sl are red after rotation(which
+ * breaks property 4). This is fixed in
+ * Case 4 (in __rb_rotate_set_parents()
+ * which set sl the color of p
+ * and set p RB_BLACK)
+ *
+ * (p) (sl)
+ * / \ / \
+ * N sl --> P S
+ * \ / \
+ * S N Sr
+ * \
+ * Sr
*/
- sibling->rb_left = tmp1 = tmp2->rb_right;
- tmp2->rb_right = sibling;
- parent->rb_right = tmp2;
+ tmp1 = tmp2->rb_right;
+ WRITE_ONCE(sibling->rb_left, tmp1);
+ WRITE_ONCE(tmp2->rb_right, sibling);
+ WRITE_ONCE(parent->rb_right, tmp2);
if (tmp1)
rb_set_parent_color(tmp1, sibling,
RB_BLACK);
@@ -296,8 +339,9 @@
* / \ / \
* (sl) sr N (sl)
*/
- parent->rb_right = tmp2 = sibling->rb_left;
- sibling->rb_left = parent;
+ tmp2 = sibling->rb_left;
+ WRITE_ONCE(parent->rb_right, tmp2);
+ WRITE_ONCE(sibling->rb_left, parent);
rb_set_parent_color(tmp1, sibling, RB_BLACK);
if (tmp2)
rb_set_parent(tmp2, parent);
@@ -309,8 +353,9 @@
sibling = parent->rb_left;
if (rb_is_red(sibling)) {
/* Case 1 - right rotate at parent */
- parent->rb_left = tmp1 = sibling->rb_right;
- sibling->rb_right = parent;
+ tmp1 = sibling->rb_right;
+ WRITE_ONCE(parent->rb_left, tmp1);
+ WRITE_ONCE(sibling->rb_right, parent);
rb_set_parent_color(tmp1, parent, RB_BLACK);
__rb_rotate_set_parents(parent, sibling, root,
RB_RED);
@@ -334,10 +379,11 @@
}
break;
}
- /* Case 3 - right rotate at sibling */
- sibling->rb_right = tmp1 = tmp2->rb_left;
- tmp2->rb_left = sibling;
- parent->rb_left = tmp2;
+ /* Case 3 - left rotate at sibling */
+ tmp1 = tmp2->rb_left;
+ WRITE_ONCE(sibling->rb_right, tmp1);
+ WRITE_ONCE(tmp2->rb_left, sibling);
+ WRITE_ONCE(parent->rb_left, tmp2);
if (tmp1)
rb_set_parent_color(tmp1, sibling,
RB_BLACK);
@@ -345,9 +391,10 @@
tmp1 = sibling;
sibling = tmp2;
}
- /* Case 4 - left rotate at parent + color flips */
- parent->rb_left = tmp2 = sibling->rb_right;
- sibling->rb_right = parent;
+ /* Case 4 - right rotate at parent + color flips */
+ tmp2 = sibling->rb_right;
+ WRITE_ONCE(parent->rb_left, tmp2);
+ WRITE_ONCE(sibling->rb_right, parent);
rb_set_parent_color(tmp1, sibling, RB_BLACK);
if (tmp2)
rb_set_parent(tmp2, parent);
@@ -378,7 +425,9 @@
static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
static const struct rb_augment_callbacks dummy_callbacks = {
- dummy_propagate, dummy_copy, dummy_rotate
+ .propagate = dummy_propagate,
+ .copy = dummy_copy,
+ .rotate = dummy_rotate
};
void rb_insert_color(struct rb_node *node, struct rb_root *root)
@@ -498,15 +547,15 @@
{
struct rb_node *parent = rb_parent(victim);
+ /* Copy the pointers/colour from the victim to the replacement */
+ *new = *victim;
+
/* Set the surrounding nodes to point to the replacement */
- __rb_change_child(victim, new, parent, root);
if (victim->rb_left)
rb_set_parent(victim->rb_left, new);
if (victim->rb_right)
rb_set_parent(victim->rb_right, new);
-
- /* Copy the pointers/colour from the victim to the replacement */
- *new = *victim;
+ __rb_change_child(victim, new, parent, root);
}
static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
diff --git a/tools/lib/string.c b/tools/lib/string.c
index 93b3d4b..f2ae1b8 100644
--- a/tools/lib/string.c
+++ b/tools/lib/string.c
@@ -17,6 +17,7 @@
#include <string.h>
#include <errno.h>
#include <linux/string.h>
+#include <linux/ctype.h>
#include <linux/compiler.h>
/**
@@ -106,3 +107,57 @@
}
return ret;
}
+
+/**
+ * skip_spaces - Removes leading whitespace from @str.
+ * @str: The string to be stripped.
+ *
+ * Returns a pointer to the first non-whitespace character in @str.
+ */
+char *skip_spaces(const char *str)
+{
+ while (isspace(*str))
+ ++str;
+ return (char *)str;
+}
+
+/**
+ * strim - Removes leading and trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns a pointer to the first non-whitespace
+ * character in @s.
+ */
+char *strim(char *s)
+{
+ size_t size;
+ char *end;
+
+ size = strlen(s);
+ if (!size)
+ return s;
+
+ end = s + size - 1;
+ while (end >= s && isspace(*end))
+ end--;
+ *(end + 1) = '\0';
+
+ return skip_spaces(s);
+}
+
+/**
+ * strreplace - Replace all occurrences of character in string.
+ * @s: The string to operate on.
+ * @old: The character being replaced.
+ * @new: The character @old is replaced with.
+ *
+ * Returns pointer to the nul byte at the end of @s.
+ */
+char *strreplace(char *s, char old, char new)
+{
+ for (; *s; ++s)
+ if (*s == old)
+ *s = new;
+ return s;
+}
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index 95563b8..5b2cd5e 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -20,7 +20,13 @@
LIBFILE = $(OUTPUT)libsubcmd.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -fPIC
+
+ifeq ($(DEBUG),0)
+ ifeq ($(feature-fortify-source), 1)
+ CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2
+ endif
+endif
ifeq ($(CC_NO_CLANG), 0)
CFLAGS += -O3
@@ -36,8 +42,6 @@
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/include/uapi
-CFLAGS += -I$(srctree)/include
SUBCMD_IN := $(OUTPUT)libsubcmd-in.o
diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c
index 9997a88..e3d47b59 100644
--- a/tools/lib/subcmd/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -23,6 +23,13 @@
subcmd_config.pager_env = pager_env;
}
+static const char *forced_pager;
+
+void force_pager(const char *pager)
+{
+ forced_pager = pager;
+}
+
static void pager_preexec(void)
{
/*
@@ -66,7 +73,9 @@
const char *pager = getenv(subcmd_config.pager_env);
struct winsize sz;
- if (!isatty(1))
+ if (forced_pager)
+ pager = forced_pager;
+ if (!isatty(1) && !forced_pager)
return;
if (ioctl(1, TIOCGWINSZ, &sz) == 0)
pager_columns = sz.ws_col;
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
index f1a53cf..a818964 100644
--- a/tools/lib/subcmd/pager.h
+++ b/tools/lib/subcmd/pager.h
@@ -7,5 +7,6 @@
extern void setup_pager(void);
extern int pager_in_use(void);
extern int pager_get_columns(void);
+extern void force_pager(const char *);
#endif /* __SUBCMD_PAGER_H */
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index cb7154e..dbb9efb 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -116,6 +116,7 @@
case OPTION_INTEGER:
case OPTION_UINTEGER:
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
default:
break;
@@ -166,6 +167,7 @@
case OPTION_INTEGER:
case OPTION_UINTEGER:
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
default:
break;
@@ -295,6 +297,22 @@
return opterror(opt, "expects a numerical value", flags);
return 0;
+ case OPTION_ULONG:
+ if (unset) {
+ *(unsigned long *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(unsigned long *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ *(unsigned long *)opt->value = strtoul(arg, (char **)&s, 10);
+ if (*s)
+ return opterror(opt, "expects a numerical value", flags);
+ return 0;
+
case OPTION_U64:
if (unset) {
*(u64 *)opt->value = 0;
@@ -703,6 +721,7 @@
case OPTION_ARGUMENT:
break;
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
case OPTION_INTEGER:
case OPTION_UINTEGER:
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 92fdbe1..af9def5 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -25,6 +25,7 @@
OPTION_STRING,
OPTION_INTEGER,
OPTION_LONG,
+ OPTION_ULONG,
OPTION_CALLBACK,
OPTION_U64,
OPTION_UINTEGER,
@@ -70,7 +71,7 @@
*
* `argh`::
* token to explain the kind of argument this option wants. Keep it
- * homogenous across the repository.
+ * homogeneous across the repository.
*
* `help`::
* the short help associated to what the option does.
@@ -79,7 +80,7 @@
*
* `flags`::
* mask of parse_opt_option_flags.
- * PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs)
+ * PARSE_OPT_OPTARG: says that the argument is optional (not for BOOLEANs)
* PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs
* PARSE_OPT_NONEG: says that this option cannot be negated
* PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in
@@ -133,6 +134,7 @@
#define OPT_INTEGER(s, l, v, h) { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_ULONG(s, l, v, h) { .type = OPTION_ULONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 96d8305..1a7a9f8 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -1,5 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
-#include <ctype.h>
#include "symbol/kallsyms.h"
#include <stdio.h>
#include <stdlib.h>
@@ -16,6 +15,19 @@
return symbol_type == 'T' || symbol_type == 'W';
}
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+ char *p;
+
+ *long_val = strtoull(ptr, &p, 16);
+
+ return p - ptr;
+}
+
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start))
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index 72ab987..bd988f7 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -18,6 +18,8 @@
return isupper(type) ? STB_GLOBAL : STB_LOCAL;
}
+int hex2u64(const char *ptr, u64 *long_val);
+
u8 kallsyms2elf_type(char type);
bool kallsyms__is_function(char symbol_type);
diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build
index c681d05..f9a5d79 100644
--- a/tools/lib/traceevent/Build
+++ b/tools/lib/traceevent/Build
@@ -4,14 +4,5 @@
libtraceevent-y += parse-filter.o
libtraceevent-y += parse-utils.o
libtraceevent-y += kbuffer-parse.o
-
-plugin_jbd2-y += plugin_jbd2.o
-plugin_hrtimer-y += plugin_hrtimer.o
-plugin_kmem-y += plugin_kmem.o
-plugin_kvm-y += plugin_kvm.o
-plugin_mac80211-y += plugin_mac80211.o
-plugin_sched_switch-y += plugin_sched_switch.o
-plugin_function-y += plugin_function.o
-plugin_xen-y += plugin_xen.o
-plugin_scsi-y += plugin_scsi.o
-plugin_cfg80211-y += plugin_cfg80211.o
+libtraceevent-y += tep_strerror.o
+libtraceevent-y += event-parse-api.o
diff --git a/tools/lib/traceevent/Documentation/Makefile b/tools/lib/traceevent/Documentation/Makefile
new file mode 100644
index 0000000..aa72ab9
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/Makefile
@@ -0,0 +1,207 @@
+include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
+
+# This Makefile and manpage XSL files were taken from tools/perf/Documentation
+# and modified for libtraceevent.
+
+MAN3_TXT= \
+ $(wildcard libtraceevent-*.txt) \
+ libtraceevent.txt
+
+MAN_TXT = $(MAN3_TXT)
+_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
+_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
+_DOC_MAN3=$(patsubst %.txt,%.3,$(MAN3_TXT))
+
+MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML))
+MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML))
+DOC_MAN3=$(addprefix $(OUTPUT),$(_DOC_MAN3))
+
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
+prefix?=$(HOME)
+endif
+bindir?=$(prefix)/bin
+htmldir?=$(prefix)/share/doc/libtraceevent-doc
+pdfdir?=$(prefix)/share/doc/libtraceevent-doc
+mandir?=$(prefix)/share/man
+man3dir=$(mandir)/man3
+
+ASCIIDOC=asciidoc
+ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf
+ASCIIDOC_HTML = xhtml11
+MANPAGE_XSL = manpage-normal.xsl
+XMLTO_EXTRA =
+INSTALL?=install
+RM ?= rm -f
+
+ifdef USE_ASCIIDOCTOR
+ASCIIDOC = asciidoctor
+ASCIIDOC_EXTRA = -a compat-mode
+ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions
+ASCIIDOC_EXTRA += -a mansource="libtraceevent" -a manmanual="libtraceevent Manual"
+ASCIIDOC_HTML = xhtml5
+endif
+
+XMLTO=xmlto
+
+_tmp_tool_path := $(call get-executable,$(ASCIIDOC))
+ifeq ($(_tmp_tool_path),)
+ missing_tools = $(ASCIIDOC)
+endif
+
+ifndef USE_ASCIIDOCTOR
+_tmp_tool_path := $(call get-executable,$(XMLTO))
+ifeq ($(_tmp_tool_path),)
+ missing_tools += $(XMLTO)
+endif
+endif
+
+#
+# For asciidoc ...
+# -7.1.2, no extra settings are needed.
+# 8.0-, set ASCIIDOC8.
+#
+
+#
+# For docbook-xsl ...
+# -1.68.1, set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0)
+# 1.69.0, no extra settings are needed?
+# 1.69.1-1.71.0, set DOCBOOK_SUPPRESS_SP?
+# 1.71.1, no extra settings are needed?
+# 1.72.0, set DOCBOOK_XSL_172.
+# 1.73.0-, set ASCIIDOC_NO_ROFF
+#
+
+#
+# If you had been using DOCBOOK_XSL_172 in an attempt to get rid
+# of 'the ".ft C" problem' in your generated manpages, and you
+# instead ended up with weird characters around callouts, try
+# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8).
+#
+
+ifdef ASCIIDOC8
+ASCIIDOC_EXTRA += -a asciidoc7compatible
+endif
+ifdef DOCBOOK_XSL_172
+ASCIIDOC_EXTRA += -a libtraceevent-asciidoc-no-roff
+MANPAGE_XSL = manpage-1.72.xsl
+else
+ ifdef ASCIIDOC_NO_ROFF
+ # docbook-xsl after 1.72 needs the regular XSL, but will not
+ # pass-thru raw roff codes from asciidoc.conf, so turn them off.
+ ASCIIDOC_EXTRA += -a libtraceevent-asciidoc-no-roff
+ endif
+endif
+ifdef MAN_BOLD_LITERAL
+XMLTO_EXTRA += -m manpage-bold-literal.xsl
+endif
+ifdef DOCBOOK_SUPPRESS_SP
+XMLTO_EXTRA += -m manpage-suppress-sp.xsl
+endif
+
+SHELL_PATH ?= $(SHELL)
+# Shell quote;
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
+
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+export DESTDIR DESTDIR_SQ
+
+#
+# Please note that there is a minor bug in asciidoc.
+# The version after 6.0.3 _will_ include the patch found here:
+# http://marc.theaimsgroup.com/?l=libtraceevent&m=111558757202243&w=2
+#
+# Until that version is released you may have to apply the patch
+# yourself - yes, all 6 characters of it!
+#
+QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir
+QUIET_SUBDIR1 =
+
+ifneq ($(findstring $(MAKEFLAGS),w),w)
+PRINT_DIR = --no-print-directory
+else # "make -w"
+NO_SUBDIR = :
+endif
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifneq ($(V),1)
+ QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@;
+ QUIET_XMLTO = @echo ' XMLTO '$@;
+ QUIET_SUBDIR0 = +@subdir=
+ QUIET_SUBDIR1 = ;$(NO_SUBDIR) \
+ echo ' SUBDIR ' $$subdir; \
+ $(MAKE) $(PRINT_DIR) -C $$subdir
+ export V
+endif
+endif
+
+all: html man
+
+man: man3
+man3: $(DOC_MAN3)
+
+html: $(MAN_HTML)
+
+$(MAN_HTML) $(DOC_MAN3): asciidoc.conf
+
+install: install-man
+
+check-man-tools:
+ifdef missing_tools
+ $(error "You need to install $(missing_tools) for man pages")
+endif
+
+do-install-man: man
+ $(call QUIET_INSTALL, Documentation-man) \
+ $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \
+ $(INSTALL) -m 644 $(DOC_MAN3) $(DESTDIR)$(man3dir);
+
+install-man: check-man-tools man do-install-man
+
+uninstall: uninstall-man
+
+uninstall-man:
+ $(call QUIET_UNINST, Documentation-man) \
+ $(Q)$(RM) $(addprefix $(DESTDIR)$(man3dir)/,$(DOC_MAN3))
+
+
+ifdef missing_tools
+ DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed)
+else
+ DO_INSTALL_MAN = do-install-man
+endif
+
+CLEAN_FILES = \
+ $(MAN_XML) $(addsuffix +,$(MAN_XML)) \
+ $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \
+ $(DOC_MAN3) *.3
+
+clean:
+ $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES)
+
+ifdef USE_ASCIIDOCTOR
+$(OUTPUT)%.3 : $(OUTPUT)%.txt
+ $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+ $(ASCIIDOC) -b manpage -d manpage \
+ $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \
+ mv $@+ $@
+endif
+
+$(OUTPUT)%.3 : $(OUTPUT)%.xml
+ $(QUIET_XMLTO)$(RM) $@ && \
+ $(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+
+$(OUTPUT)%.xml : %.txt
+ $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+ $(ASCIIDOC) -b docbook -d manpage \
+ $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \
+ mv $@+ $@
+
+$(MAN_HTML): $(OUTPUT)%.html : %.txt
+ $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+ $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \
+ $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \
+ mv $@+ $@
diff --git a/tools/lib/traceevent/Documentation/asciidoc.conf b/tools/lib/traceevent/Documentation/asciidoc.conf
new file mode 100644
index 0000000..0759571
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/asciidoc.conf
@@ -0,0 +1,120 @@
+## linktep: macro
+#
+# Usage: linktep:command[manpage-section]
+#
+# Note, {0} is the manpage section, while {target} is the command.
+#
+# Show TEP link as: <command>(<section>); if section is defined, else just show
+# the command.
+
+[macros]
+(?su)[\\]?(?P<name>linktep):(?P<target>\S*?)\[(?P<attrlist>.*?)\]=
+
+[attributes]
+asterisk=*
+plus=+
+caret=^
+startsb=[
+endsb=]
+tilde=~
+
+ifdef::backend-docbook[]
+[linktep-inlinemacro]
+{0%{target}}
+{0#<citerefentry>}
+{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>}
+{0#</citerefentry>}
+endif::backend-docbook[]
+
+ifdef::backend-docbook[]
+ifndef::tep-asciidoc-no-roff[]
+# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this.
+# v1.72 breaks with this because it replaces dots not in roff requests.
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+ifdef::doctype-manpage[]
+ .ft C
+endif::doctype-manpage[]
+|
+ifdef::doctype-manpage[]
+ .ft
+endif::doctype-manpage[]
+</literallayout>
+{title#}</example>
+endif::tep-asciidoc-no-roff[]
+
+ifdef::tep-asciidoc-no-roff[]
+ifdef::doctype-manpage[]
+# The following two small workarounds insert a simple paragraph after screen
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+|
+</literallayout><simpara></simpara>
+{title#}</example>
+
+[verseblock]
+<formalpara{id? id="{id}"}><title>{title}</title><para>
+{title%}<literallayout{id? id="{id}"}>
+{title#}<literallayout>
+|
+</literallayout>
+{title#}</para></formalpara>
+{title%}<simpara></simpara>
+endif::doctype-manpage[]
+endif::tep-asciidoc-no-roff[]
+endif::backend-docbook[]
+
+ifdef::doctype-manpage[]
+ifdef::backend-docbook[]
+[header]
+template::[header-declarations]
+<refentry>
+<refmeta>
+<refentrytitle>{mantitle}</refentrytitle>
+<manvolnum>{manvolnum}</manvolnum>
+<refmiscinfo class="source">libtraceevent</refmiscinfo>
+<refmiscinfo class="version">{libtraceevent_version}</refmiscinfo>
+<refmiscinfo class="manual">libtraceevent Manual</refmiscinfo>
+</refmeta>
+<refnamediv>
+ <refname>{manname1}</refname>
+ <refname>{manname2}</refname>
+ <refname>{manname3}</refname>
+ <refname>{manname4}</refname>
+ <refname>{manname5}</refname>
+ <refname>{manname6}</refname>
+ <refname>{manname7}</refname>
+ <refname>{manname8}</refname>
+ <refname>{manname9}</refname>
+ <refname>{manname10}</refname>
+ <refname>{manname11}</refname>
+ <refname>{manname12}</refname>
+ <refname>{manname13}</refname>
+ <refname>{manname14}</refname>
+ <refname>{manname15}</refname>
+ <refname>{manname16}</refname>
+ <refname>{manname17}</refname>
+ <refname>{manname18}</refname>
+ <refname>{manname19}</refname>
+ <refname>{manname20}</refname>
+ <refname>{manname21}</refname>
+ <refname>{manname22}</refname>
+ <refname>{manname23}</refname>
+ <refname>{manname24}</refname>
+ <refname>{manname25}</refname>
+ <refname>{manname26}</refname>
+ <refname>{manname27}</refname>
+ <refname>{manname28}</refname>
+ <refname>{manname29}</refname>
+ <refname>{manname30}</refname>
+ <refpurpose>{manpurpose}</refpurpose>
+</refnamediv>
+endif::backend-docbook[]
+endif::doctype-manpage[]
+
+ifdef::backend-xhtml11[]
+[linktep-inlinemacro]
+<a href="{target}.html">{target}{0?({0})}</a>
+endif::backend-xhtml11[]
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-commands.txt b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt
new file mode 100644
index 0000000..bec5520
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt
@@ -0,0 +1,153 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_register_comm, tep_override_comm, tep_pid_is_registered,
+tep_data_comm_from_pid, tep_data_pid_from_comm, tep_cmdline_pid -
+Manage pid to process name mappings.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_);
+int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_);
+bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_);
+const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_pevent_, int _pid_);
+struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_pevent_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_);
+int *tep_cmdline_pid*(struct tep_handle pass:[*]_pevent_, struct cmdline pass:[*]_cmdline_);
+--
+
+DESCRIPTION
+-----------
+These functions can be used to handle the mapping between pid and process name.
+The library builds a cache of these mappings, which is used to display the name
+of the process, instead of its pid. This information can be retrieved from
+tracefs/saved_cmdlines file.
+
+The _tep_register_comm()_ function registers a _pid_ / process name mapping.
+If a command with the same _pid_ is already registered, an error is returned.
+The _pid_ argument is the process ID, the _comm_ argument is the process name,
+_tep_ is the event context. The _comm_ is duplicated internally.
+
+The _tep_override_comm()_ function registers a _pid_ / process name mapping.
+If a process with the same pid is already registered, the process name string is
+udapted with the new one. The _pid_ argument is the process ID, the _comm_
+argument is the process name, _tep_ is the event context. The _comm_ is
+duplicated internally.
+
+The _tep_is_pid_registered()_ function checks if a pid has a process name
+mapping registered. The _pid_ argument is the process ID, _tep_ is the event
+context.
+
+The _tep_data_comm_from_pid()_ function returns the process name for a given
+pid. The _pid_ argument is the process ID, _tep_ is the event context.
+The returned string should not be freed, but will be freed when the _tep_
+handler is closed.
+
+The _tep_data_pid_from_comm()_ function returns a pid for a given process name.
+The _comm_ argument is the process name, _tep_ is the event context.
+The argument _next_ is the cmdline structure to search for the next pid.
+As there may be more than one pid for a given process, the result of this call
+can be passed back into a recurring call in the _next_ parameter, to search for
+the next pid. If _next_ is NULL, it will return the first pid associated with
+the _comm_. The function performs a linear search, so it may be slow.
+
+The _tep_cmdline_pid()_ function returns the pid associated with a given
+_cmdline_. The _tep_ argument is the event context.
+
+RETURN VALUE
+------------
+_tep_register_comm()_ function returns 0 on success. In case of an error -1 is
+returned and errno is set to indicate the cause of the problem: ENOMEM, if there
+is not enough memory to duplicate the _comm_ or EEXIST if a mapping for this
+_pid_ is already registered.
+
+_tep_override_comm()_ function returns 0 on success. In case of an error -1 is
+returned and errno is set to indicate the cause of the problem: ENOMEM, if there
+is not enough memory to duplicate the _comm_.
+
+_tep_is_pid_registered()_ function returns true if the _pid_ has a process name
+mapped to it, false otherwise.
+
+_tep_data_comm_from_pid()_ function returns the process name as string, or the
+string "<...>" if there is no mapping for the given pid.
+
+_tep_data_pid_from_comm()_ function returns a pointer to a struct cmdline, that
+holds a pid for a given process, or NULL if none is found. This result can be
+passed back into a recurring call as the _next_ parameter of the function.
+
+_tep_cmdline_pid()_ functions returns the pid for the give cmdline. If _cmdline_
+ is NULL, then -1 is returned.
+
+EXAMPLE
+-------
+The following example registers pid for command "ls", in context of event _tep_
+and performs various searches for pid / process name mappings:
+[source,c]
+--
+#include <event-parse.h>
+...
+int ret;
+int ls_pid = 1021;
+struct tep_handle *tep = tep_alloc();
+...
+ ret = tep_register_comm(tep, "ls", ls_pid);
+ if (ret != 0 && errno == EEXIST)
+ ret = tep_override_comm(tep, "ls", ls_pid);
+ if (ret != 0) {
+ /* Failed to register pid / command mapping */
+ }
+...
+ if (tep_is_pid_registered(tep, ls_pid) == 0) {
+ /* Command mapping for ls_pid is not registered */
+ }
+...
+ const char *comm = tep_data_comm_from_pid(tep, ls_pid);
+ if (comm) {
+ /* Found process name for ls_pid */
+ }
+...
+ int pid;
+ struct cmdline *cmd = tep_data_pid_from_comm(tep, "ls", NULL);
+ while (cmd) {
+ pid = tep_cmdline_pid(tep, cmd);
+ /* Found pid for process "ls" */
+ cmd = tep_data_pid_from_comm(tep, "ls", cmd);
+ }
+--
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt
new file mode 100644
index 0000000..5ad70e4
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt
@@ -0,0 +1,77 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_cpus, tep_set_cpus - Get / set the number of CPUs, which have a tracing
+buffer representing it. Note, the buffer may be empty.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_get_cpus*(struct tep_handle pass:[*]_tep_);
+void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_);
+--
+
+DESCRIPTION
+-----------
+The _tep_get_cpus()_ function gets the number of CPUs, which have a tracing
+buffer representing it. The _tep_ argument is trace event parser context.
+
+The _tep_set_cpus()_ function sets the number of CPUs, which have a tracing
+buffer representing it. The _tep_ argument is trace event parser context.
+The _cpu_ argument is the number of CPUs with tracing data.
+
+RETURN VALUE
+------------
+The _tep_get_cpus()_ functions returns the number of CPUs, which have tracing
+data recorded.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+ tep_set_cpus(tep, 5);
+...
+ printf("We have tracing data for %d CPUs", tep_get_cpus(tep));
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt
new file mode 100644
index 0000000..e64851b
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt
@@ -0,0 +1,78 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_read_number - Reads a number from raw data.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_);
+--
+
+DESCRIPTION
+-----------
+The _tep_read_number()_ function reads an integer from raw data, taking into
+account the endianness of the raw data and the current host. The _tep_ argument
+is the trace event parser context. The _ptr_ is a pointer to the raw data, where
+the integer is, and the _size_ is the size of the integer.
+
+RETURN VALUE
+------------
+The _tep_read_number()_ function returns the integer in the byte order of
+the current host. In case of an error, 0 is returned.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+void process_record(struct tep_record *record)
+{
+ int offset = 24;
+ int data = tep_read_number(tep, record->data + offset, 4);
+
+ /* Read the 4 bytes at the offset 24 of data as an integer */
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt
new file mode 100644
index 0000000..7bc062c
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt
@@ -0,0 +1,103 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_find_event,tep_find_event_by_name,tep_find_event_by_record -
+Find events by given key.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_);
+struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_);
+struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_);
+--
+
+DESCRIPTION
+-----------
+This set of functions can be used to search for an event, based on a given
+criteria. All functions require a pointer to a _tep_, trace event parser
+context.
+
+The _tep_find_event()_ function searches for an event by given event _id_. The
+event ID is assigned dynamically and can be viewed in event's format file,
+"ID" field.
+
+The tep_find_event_by_name()_ function searches for an event by given
+event _name_, under the system _sys_. If the _sys_ is NULL (not specified),
+the first event with _name_ is returned.
+
+The tep_find_event_by_record()_ function searches for an event from a given
+_record_.
+
+RETURN VALUE
+------------
+All these functions return a pointer to the found event, or NULL if there is no
+such event.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct tep_event *event;
+
+event = tep_find_event(tep, 1857);
+if (event == NULL) {
+ /* There is no event with ID 1857 */
+}
+
+event = tep_find_event_by_name(tep, "kvm", "kvm_exit");
+if (event == NULL) {
+ /* There is no kvm_exit event, from kvm system */
+}
+
+void event_from_record(struct tep_record *record)
+{
+ struct tep_event *event = tep_find_event_by_record(tep, record);
+ if (event == NULL) {
+ /* There is no event from given record */
+ }
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt
new file mode 100644
index 0000000..6525092
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt
@@ -0,0 +1,99 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_event, tep_get_first_event, tep_get_events_count - Access events.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_);
+struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_);
+int *tep_get_events_count*(struct tep_handle pass:[*]_tep_);
+--
+
+DESCRIPTION
+-----------
+The _tep_get_event()_ function returns a pointer to event at the given _index_.
+The _tep_ argument is trace event parser context, the _index_ is the index of
+the requested event.
+
+The _tep_get_first_event()_ function returns a pointer to the first event.
+As events are stored in an array, this function returns the pointer to the
+beginning of the array. The _tep_ argument is trace event parser context.
+
+The _tep_get_events_count()_ function returns the number of the events
+in the array. The _tep_ argument is trace event parser context.
+
+RETURN VALUE
+------------
+The _tep_get_event()_ returns a pointer to the event located at _index_.
+NULL is returned in case of error, in case there are no events or _index_ is
+out of range.
+
+The _tep_get_first_event()_ returns a pointer to the first event. NULL is
+returned in case of error, or in case there are no events.
+
+The _tep_get_events_count()_ returns the number of the events. 0 is
+returned in case of error, or in case there are no events.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+int i,count = tep_get_events_count(tep);
+struct tep_event *event, *events = tep_get_first_event(tep);
+
+if (events == NULL) {
+ /* There are no events */
+} else {
+ for (i = 0; i < count; i++) {
+ event = (events+i);
+ /* process events[i] */
+ }
+
+ /* Get the last event */
+ event = tep_get_event(tep, count-1);
+}
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt
new file mode 100644
index 0000000..fba350e
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt
@@ -0,0 +1,122 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_list_events, tep_list_events_copy -
+Get list of events, sorted by given criteria.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_event_sort_type* {
+ _TEP_EVENT_SORT_ID_,
+ _TEP_EVENT_SORT_NAME_,
+ _TEP_EVENT_SORT_SYSTEM_,
+};
+
+struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
+struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
+--
+
+DESCRIPTION
+-----------
+The _tep_list_events()_ function returns an array of pointers to the events,
+sorted by the _sort_type_ criteria. The last element of the array is NULL.
+The returned memory must not be freed, it is managed by the library.
+The function is not thread safe. The _tep_ argument is trace event parser
+context. The _sort_type_ argument is the required sort criteria:
+[verse]
+--
+ _TEP_EVENT_SORT_ID_ - sort by the event ID.
+ _TEP_EVENT_SORT_NAME_ - sort by the event (name, system, id) triplet.
+ _TEP_EVENT_SORT_SYSTEM_ - sort by the event (system, name, id) triplet.
+--
+
+The _tep_list_events_copy()_ is a thread safe version of _tep_list_events()_.
+It has the same behavior, but the returned array is allocated internally and
+must be freed by the caller. Note that the content of the array must not be
+freed (see the EXAMPLE below).
+
+RETURN VALUE
+------------
+The _tep_list_events()_ function returns an array of pointers to events.
+In case of an error, NULL is returned. The returned array must not be freed,
+it is managed by the library.
+
+The _tep_list_events_copy()_ function returns an array of pointers to events.
+In case of an error, NULL is returned. The returned array must be freed by
+the caller.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+int i;
+struct tep_event_format **events;
+
+i=0;
+events = tep_list_events(tep, TEP_EVENT_SORT_ID);
+if (events == NULL) {
+ /* Failed to get the events, sorted by ID */
+} else {
+ while(events[i]) {
+ /* walk through the list of the events, sorted by ID */
+ i++;
+ }
+}
+
+i=0;
+events = tep_list_events_copy(tep, TEP_EVENT_SORT_NAME);
+if (events == NULL) {
+ /* Failed to get the events, sorted by name */
+} else {
+ while(events[i]) {
+ /* walk through the list of the events, sorted by name */
+ i++;
+ }
+ free(events);
+}
+
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt
new file mode 100644
index 0000000..2c6a618
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt
@@ -0,0 +1,130 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_print_event - Writes event information into a trace sequence.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+*#include <trace-seq.h>*
+
+void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seqpass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._)
+--
+
+DESCRIPTION
+-----------
+
+The _tep_print_event()_ function parses the event information of the given
+_record_ and writes it into the trace sequence _s_, according to the format
+string _fmt_. The desired information is specified after the format string.
+The _fmt_ is printf-like format string, following arguments are supported:
+[verse]
+--
+ TEP_PRINT_PID, "%d" - PID of the event.
+ TEP_PRINT_CPU, "%d" - Event CPU.
+ TEP_PRINT_COMM, "%s" - Event command string.
+ TEP_PRINT_NAME, "%s" - Event name.
+ TEP_PRINT_LATENCY, "%s" - Latency of the event. It prints 4 or more
+ fields - interrupt state, scheduling state,
+ current context, and preemption count.
+ Field 1 is the interrupt enabled state:
+ d : Interrupts are disabled
+ . : Interrupts are enabled
+ X : The architecture does not support this
+ information
+ Field 2 is the "need resched" state.
+ N : The task is set to call the scheduler when
+ possible, as another higher priority task
+ may need to be scheduled in.
+ . : The task is not set to call the scheduler.
+ Field 3 is the context state.
+ . : Normal context
+ s : Soft interrupt context
+ h : Hard interrupt context
+ H : Hard interrupt context which triggered
+ during soft interrupt context.
+ z : NMI context
+ Z : NMI context which triggered during hard
+ interrupt context
+ Field 4 is the preemption count.
+ . : The preempt count is zero.
+ On preemptible kernels (where the task can be scheduled
+ out in arbitrary locations while in kernel context), the
+ preempt count, when non zero, will prevent the kernel
+ from scheduling out the current task. The preempt count
+ number is displayed when it is not zero.
+ Depending on the kernel, it may show other fields
+ (lock depth, or migration disabled, which are unique to
+ specialized kernels).
+ TEP_PRINT_TIME, %d - event time stamp. A divisor and precision can be
+ specified as part of this format string:
+ "%precision.divisord". Example:
+ "%3.1000d" - divide the time by 1000 and print the first
+ 3 digits before the dot. Thus, the time stamp
+ "123456000" will be printed as "123.456"
+ TEP_PRINT_INFO, "%s" - event information.
+ TEP_PRINT_INFO_RAW, "%s" - event information, in raw format.
+
+--
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct trace_seq seq;
+trace_seq_init(&seq);
+struct tep_handle *tep = tep_alloc();
+...
+void print_my_event(struct tep_record *record)
+{
+ trace_seq_reset(&seq);
+ tep_print_event(tep, s, record, "%16s-%-5d [%03d] %s %6.1000d %s %s",
+ TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_CPU,
+ TEP_PRINT_LATENCY, TEP_PRINT_TIME, TEP_PRINT_NAME,
+ TEP_PRINT_INFO);
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences related APIs.
+ Trace sequences are used to allow a function to call several other functions
+ to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt
new file mode 100644
index 0000000..0896af5
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt
@@ -0,0 +1,118 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_find_common_field, tep_find_field, tep_find_any_field -
+Search for a field in an event.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_);
+struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_);
+struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_);
+--
+
+DESCRIPTION
+-----------
+These functions search for a field with given name in an event. The field
+returned can be used to find the field content from within a data record.
+
+The _tep_find_common_field()_ function searches for a common field with _name_
+in the _event_.
+
+The _tep_find_field()_ function searches for an event specific field with
+_name_ in the _event_.
+
+The _tep_find_any_field()_ function searches for any field with _name_ in the
+_event_.
+
+RETURN VALUE
+------------
+The _tep_find_common_field(), _tep_find_field()_ and _tep_find_any_field()_
+functions return a pointer to the found field, or NULL in case there is no field
+with the requested name.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+void get_htimer_info(struct tep_handle *tep, struct tep_record *record)
+{
+ struct tep_format_field *field;
+ struct tep_event *event;
+ long long softexpires;
+ int mode;
+ int pid;
+
+ event = tep_find_event_by_name(tep, "timer", "hrtimer_start");
+
+ field = tep_find_common_field(event, "common_pid");
+ if (field == NULL) {
+ /* Cannot find "common_pid" field in the event */
+ } else {
+ /* Get pid from the data record */
+ pid = tep_read_number(tep, record->data + field->offset,
+ field->size);
+ }
+
+ field = tep_find_field(event, "softexpires");
+ if (field == NULL) {
+ /* Cannot find "softexpires" event specific field in the event */
+ } else {
+ /* Get softexpires parameter from the data record */
+ softexpires = tep_read_number(tep, record->data + field->offset,
+ field->size);
+ }
+
+ field = tep_find_any_field(event, "mode");
+ if (field == NULL) {
+ /* Cannot find "mode" field in the event */
+ } else
+ {
+ /* Get mode parameter from the data record */
+ mode = tep_read_number(tep, record->data + field->offset,
+ field->size);
+ }
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt
new file mode 100644
index 0000000..6324f0d
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt
@@ -0,0 +1,122 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_any_field_val, tep_get_common_field_val, tep_get_field_val,
+tep_get_field_raw - Get value of a field.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+*#include <trace-seq.h>*
+
+int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_);
+--
+
+DESCRIPTION
+-----------
+These functions can be used to find a field and retrieve its value.
+
+The _tep_get_any_field_val()_ function searches in the _record_ for a field
+with _name_, part of the _event_. If the field is found, its value is stored in
+_val_. If there is an error and _err_ is not zero, then an error string is
+written into _s_.
+
+The _tep_get_common_field_val()_ function does the same as
+_tep_get_any_field_val()_, but searches only in the common fields. This works
+for any event as all events include the common fields.
+
+The _tep_get_field_val()_ function does the same as _tep_get_any_field_val()_,
+but searches only in the event specific fields.
+
+The _tep_get_field_raw()_ function searches in the _record_ for a field with
+_name_, part of the _event_. If the field is found, a pointer to where the field
+exists in the record's raw data is returned. The size of the data is stored in
+_len_. If there is an error and _err_ is not zero, then an error string is
+written into _s_.
+
+RETURN VALUE
+------------
+The _tep_get_any_field_val()_, _tep_get_common_field_val()_ and
+_tep_get_field_val()_ functions return 0 on success, or -1 in case of an error.
+
+The _tep_get_field_raw()_ function returns a pointer to field's raw data, and
+places the length of this data in _len_. In case of an error NULL is returned.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit");
+...
+void process_record(struct tep_record *record)
+{
+ int len;
+ char *comm;
+ struct tep_event_format *event;
+ unsigned long long val;
+
+ event = tep_find_event_by_record(pevent, record);
+ if (event != NULL) {
+ if (tep_get_common_field_val(NULL, event, "common_type",
+ record, &val, 0) == 0) {
+ /* Got the value of common type field */
+ }
+ if (tep_get_field_val(NULL, event, "pid", record, &val, 0) == 0) {
+ /* Got the value of pid specific field */
+ }
+ comm = tep_get_field_raw(NULL, event, "comm", record, &len, 0);
+ if (comm != NULL) {
+ /* Got a pointer to the comm event specific field */
+ }
+ }
+}
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences
+ related APIs. Trace sequences are used to allow a function to call
+ several other functions to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt
new file mode 100644
index 0000000..9a9df98
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt
@@ -0,0 +1,126 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_print_field, tep_print_fields, tep_print_num_field, tep_print_func_field -
+Print the field content.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+*#include <trace-seq.h>*
+
+void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_);
+void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_);
+int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_);
+int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_);
+--
+
+DESCRIPTION
+-----------
+These functions print recorded field's data, according to the field's type.
+
+The _tep_print_field()_ function extracts from the recorded raw _data_ value of
+the _field_ and prints it into _s_, according to the field type.
+
+The _tep_print_fields()_ prints each field name followed by the record's field
+value according to the field's type:
+[verse]
+--
+"field1_name=field1_value field2_name=field2_value ..."
+--
+It iterates all fields of the _event_, and calls _tep_print_field()_ for each of
+them.
+
+The _tep_print_num_field()_ function prints a numeric field with given format
+string. A search is performed in the _event_ for a field with _name_. If such
+field is found, its value is extracted from the _record_ and is printed in the
+_s_, according to the given format string _fmt_. If the argument _err_ is
+non-zero, and an error occures - it is printed in the _s_.
+
+The _tep_print_func_field()_ function prints a function field with given format
+string. A search is performed in the _event_ for a field with _name_. If such
+field is found, its value is extracted from the _record_. The value is assumed
+to be a function address, and a search is perform to find the name of this
+function. The function name (if found) and its address are printed in the _s_,
+according to the given format string _fmt_. If the argument _err_ is non-zero,
+and an error occures - it is printed in _s_.
+
+RETURN VALUE
+------------
+The _tep_print_num_field()_ and _tep_print_func_field()_ functions return 1
+on success, -1 in case of an error or 0 if the print buffer _s_ is full.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct trace_seq seq;
+trace_seq_init(&seq);
+struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start");
+...
+void process_record(struct tep_record *record)
+{
+ struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid");
+
+ trace_seq_reset(&seq);
+
+ /* Print the value of "common_pid" */
+ tep_print_field(&seq, record->data, field_pid);
+
+ /* Print all fields of the "hrtimer_start" event */
+ tep_print_fields(&seq, record->data, record->size, event);
+
+ /* Print the value of "expires" field with custom format string */
+ tep_print_num_field(&seq, " timer expires in %llu ", event, "expires", record, 0);
+
+ /* Print the address and the name of "function" field with custom format string */
+ tep_print_func_field(&seq, " timer function is %s ", event, "function", record, 0);
+ }
+ ...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences related APIs.
+ Trace sequences are used to allow a function to call several other functions
+ to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt
new file mode 100644
index 0000000..64e9e25
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt
@@ -0,0 +1,81 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_read_number_field - Reads a number from raw data.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_);
+--
+
+DESCRIPTION
+-----------
+The _tep_read_number_field()_ function reads the value of the _field_ from the
+raw _data_ and stores it in the _value_. The function sets the _value_ according
+to the endianness of the raw data and the current machine and stores it in
+_value_.
+
+RETURN VALUE
+------------
+The _tep_read_number_field()_ function retunrs 0 in case of success, or -1 in
+case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start");
+...
+void process_record(struct tep_record *record)
+{
+ unsigned long long pid;
+ struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid");
+
+ if (tep_read_number_field(field_pid, record->data, &pid) != 0) {
+ /* Failed to get "common_pid" value */
+ }
+}
+...
+--
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-fields.txt b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt
new file mode 100644
index 0000000..1ccb531
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt
@@ -0,0 +1,105 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_event_common_fields, tep_event_fields - Get a list of fields for an event.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_);
+struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_);
+--
+
+DESCRIPTION
+-----------
+The _tep_event_common_fields()_ function returns an array of pointers to common
+fields for the _event_. The array is allocated in the function and must be freed
+by free(). The last element of the array is NULL.
+
+The _tep_event_fields()_ function returns an array of pointers to event specific
+fields for the _event_. The array is allocated in the function and must be freed
+by free(). The last element of the array is NULL.
+
+RETURN VALUE
+------------
+Both _tep_event_common_fields()_ and _tep_event_fields()_ functions return
+an array of pointers to tep_format_field structures in case of success, or
+NULL in case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+int i;
+struct tep_format_field **fields;
+struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit");
+if (event != NULL) {
+ fields = tep_event_common_fields(event);
+ if (fields != NULL) {
+ i = 0;
+ while (fields[i]) {
+ /*
+ walk through the list of the common fields
+ of the kvm_exit event
+ */
+ i++;
+ }
+ free(fields);
+ }
+ fields = tep_event_fields(event);
+ if (fields != NULL) {
+ i = 0;
+ while (fields[i]) {
+ /*
+ walk through the list of the event specific
+ fields of the kvm_exit event
+ */
+ i++;
+ }
+ free(fields);
+ }
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt
new file mode 100644
index 0000000..f401ad3
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt
@@ -0,0 +1,91 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_is_file_bigendian, tep_set_file_bigendian - Get / set the endianness of the
+raw data being accessed by the tep handler.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_endian* {
+ TEP_LITTLE_ENDIAN = 0,
+ TEP_BIG_ENDIAN
+};
+
+bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_);
+void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_);
+
+--
+DESCRIPTION
+-----------
+The _tep_is_file_bigendian()_ function gets the endianness of the raw data,
+being accessed by the tep handler. The _tep_ argument is trace event parser
+context.
+
+The _tep_set_file_bigendian()_ function sets the endianness of raw data being
+accessed by the tep handler. The _tep_ argument is trace event parser context.
+[verse]
+--
+The _endian_ argument is the endianness:
+ _TEP_LITTLE_ENDIAN_ - the raw data is in little endian format,
+ _TEP_BIG_ENDIAN_ - the raw data is in big endian format.
+--
+RETURN VALUE
+------------
+The _tep_is_file_bigendian()_ function returns true if the data is in bigendian
+format, false otherwise.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+ tep_set_file_bigendian(tep, TEP_LITTLE_ENDIAN);
+...
+ if (tep_is_file_bigendian(tep)) {
+ /* The raw data is in big endian */
+ } else {
+ /* The raw data is in little endian */
+ }
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-filter.txt b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt
new file mode 100644
index 0000000..4a9962d
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt
@@ -0,0 +1,209 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_filter_alloc, tep_filter_free, tep_filter_reset, tep_filter_make_string,
+tep_filter_copy, tep_filter_compare, tep_filter_match, tep_event_filtered,
+tep_filter_remove_event, tep_filter_strerror, tep_filter_add_filter_str -
+Event filter related APIs.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_);
+void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_);
+void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_);
+enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_);
+int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_);
+int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_);
+int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_);
+char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_);
+--
+
+DESCRIPTION
+-----------
+Filters can be attached to traced events. They can be used to filter out various
+events when outputting them. Each event can be filtered based on its parameters,
+described in the event's format file. This set of functions can be used to
+create, delete, modify and attach event filters.
+
+The _tep_filter_alloc()_ function creates a new event filter. The _tep_ argument
+is the trace event parser context.
+
+The _tep_filter_free()_ function frees an event filter and all resources that it
+had used.
+
+The _tep_filter_reset()_ function removes all rules from an event filter and
+resets it.
+
+The _tep_filter_add_filter_str()_ function adds a new rule to the _filter_. The
+_filter_str_ argument is the filter string, that contains the rule.
+
+The _tep_event_filtered()_ function checks if the event with _event_id_ has
+_filter_.
+
+The _tep_filter_remove_event()_ function removes a _filter_ for an event with
+_event_id_.
+
+The _tep_filter_match()_ function tests if a _record_ matches given _filter_.
+
+The _tep_filter_copy()_ function copies a _source_ filter into a _dest_ filter.
+
+The _tep_filter_compare()_ function compares two filers - _filter1_ and _filter2_.
+
+The _tep_filter_make_string()_ function constructs a string, displaying
+the _filter_ contents for given _event_id_.
+
+The _tep_filter_strerror()_ function copies the _filter_ error buffer into the
+given _buf_ with the size _buflen_. If the error buffer is empty, in the _buf_
+is copied a string, describing the error _err_.
+
+RETURN VALUE
+------------
+The _tep_filter_alloc()_ function returns a pointer to the newly created event
+filter, or NULL in case of an error.
+
+The _tep_filter_add_filter_str()_ function returns 0 if the rule was
+successfully added or a negative error code. Use _tep_filter_strerror()_ to see
+actual error message in case of an error.
+
+The _tep_event_filtered()_ function returns 1 if the filter is found for given
+event, or 0 otherwise.
+
+The _tep_filter_remove_event()_ function returns 1 if the vent was removed, or
+0 if the event was not found.
+
+The _tep_filter_match()_ function returns _tep_errno_, according to the result:
+[verse]
+--
+_pass:[TEP_ERRNO__FILTER_MATCH]_ - filter found for event, the record matches.
+_pass:[TEP_ERRNO__FILTER_MISS]_ - filter found for event, the record does not match.
+_pass:[TEP_ERRNO__FILTER_NOT_FOUND]_ - no filter found for record's event.
+_pass:[TEP_ERRNO__NO_FILTER]_ - no rules in the filter.
+--
+or any other _tep_errno_, if an error occurred during the test.
+
+The _tep_filter_copy()_ function returns 0 on success or -1 if not all rules
+ were copied.
+
+The _tep_filter_compare()_ function returns 1 if the two filters hold the same
+content, or 0 if they do not.
+
+The _tep_filter_make_string()_ function returns a string, which must be freed
+with free(), or NULL in case of an error.
+
+The _tep_filter_strerror()_ function returns 0 if message was filled
+successfully, or -1 in case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+char errstr[200];
+int ret;
+
+struct tep_event_filter *filter = tep_filter_alloc(tep);
+struct tep_event_filter *filter1 = tep_filter_alloc(tep);
+ret = tep_filter_add_filter_str(filter, "sched/sched_wakeup:target_cpu==1");
+if(ret < 0) {
+ tep_filter_strerror(filter, ret, errstr, sizeof(errstr));
+ /* Failed to add a new rule to the filter, the error string is in errstr */
+}
+if (tep_filter_copy(filter1, filter) != 0) {
+ /* Failed to copy filter in filter1 */
+}
+...
+if (tep_filter_compare(filter, filter1) != 1) {
+ /* Both filters are different */
+}
+...
+void process_record(struct tep_handle *tep, struct tep_record *record)
+{
+ struct tep_event *event;
+ char *fstring;
+
+ event = tep_find_event_by_record(tep, record);
+
+ if (tep_event_filtered(filter, event->id) == 1) {
+ /* The event has filter */
+ fstring = tep_filter_make_string(filter, event->id);
+ if (fstring != NULL) {
+ /* The filter for the event is in fstring */
+ free(fstring);
+ }
+ }
+
+ switch (tep_filter_match(filter, record)) {
+ case TEP_ERRNO__FILTER_MATCH:
+ /* The filter matches the record */
+ break;
+ case TEP_ERRNO__FILTER_MISS:
+ /* The filter does not match the record */
+ break;
+ case TEP_ERRNO__FILTER_NOT_FOUND:
+ /* No filter found for record's event */
+ break;
+ case TEP_ERRNO__NO_FILTER:
+ /* There are no rules in the filter */
+ break
+ default:
+ /* An error occurred during the test */
+ break;
+ }
+
+ if (tep_filter_remove_event(filter, event->id) == 1) {
+ /* The event was removed from the filter */
+ }
+}
+
+...
+tep_filter_reset(filter);
+...
+tep_filter_free(filter);
+tep_filter_free(filter1);
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt
new file mode 100644
index 0000000..f6aca0d
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt
@@ -0,0 +1,183 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_find_function, tep_find_function_address, tep_set_function_resolver,
+tep_reset_function_resolver, tep_register_function, tep_register_print_string -
+function related tep APIs
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+typedef char pass:[*](*tep_func_resolver_t*)(void pass:[*]_priv_, unsigned long long pass:[*]_addrp_, char pass:[**]_modp_);
+int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_);
+void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_);
+const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_);
+int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_);
+--
+
+DESCRIPTION
+-----------
+Some tools may have already a way to resolve the kernel functions. These APIs
+allow them to keep using it instead of duplicating all the entries inside.
+
+The _tep_func_resolver_t_ type is the prototype of the alternative kernel
+functions resolver. This function receives a pointer to its custom context
+(set with the _tep_set_function_resolver()_ call ) and the address of a kernel
+function, which has to be resolved. In case of success, it should return
+the name of the function and its module (if any) in _modp_.
+
+The _tep_set_function_resolver()_ function registers _func_ as an alternative
+kernel functions resolver. The _tep_ argument is trace event parser context.
+The _priv_ argument is a custom context of the _func_ function. The function
+resolver is used by the APIs _tep_find_function()_,
+_tep_find_function_address()_, and _tep_print_func_field()_ to resolve
+a function address to a function name.
+
+The _tep_reset_function_resolver()_ function resets the kernel functions
+resolver to the default function. The _tep_ argument is trace event parser
+context.
+
+
+These APIs can be used to find function name and start address, by given
+address. The given address does not have to be exact, it will select
+the function that would contain it.
+
+The _tep_find_function()_ function returns the function name, which contains the
+given address _addr_. The _tep_ argument is the trace event parser context.
+
+The _tep_find_function_address()_ function returns the function start address,
+by given address _addr_. The _addr_ does not have to be exact, it will select
+the function that would contain it. The _tep_ argument is the trace event
+parser context.
+
+The _tep_register_function()_ function registers a function name mapped to an
+address and (optional) module. This mapping is used in case the function tracer
+or events have "%pS" parameter in its format string. It is common to pass in
+the kallsyms function names with their corresponding addresses with this
+function. The _tep_ argument is the trace event parser context. The _name_ is
+the name of the function, the string is copied internally. The _addr_ is the
+start address of the function. The _mod_ is the kernel module the function may
+be in (NULL for none).
+
+The _tep_register_print_string()_ function registers a string by the address
+it was stored in the kernel. Some strings internal to the kernel with static
+address are passed to certain events. The "%s" in the event's format field
+which has an address needs to know what string would be at that address. The
+tep_register_print_string() supplies the parsing with the mapping between kernel
+addresses and those strings. The _tep_ argument is the trace event parser
+context. The _fmt_ is the string to register, it is copied internally.
+The _addr_ is the address the string was located at.
+
+
+RETURN VALUE
+------------
+The _tep_set_function_resolver()_ function returns 0 in case of success, or -1
+in case of an error.
+
+The _tep_find_function()_ function returns the function name, or NULL in case
+it cannot be found.
+
+The _tep_find_function_address()_ function returns the function start address,
+or 0 in case it cannot be found.
+
+The _tep_register_function()_ function returns 0 in case of success. In case of
+an error -1 is returned, and errno is set to the appropriate error number.
+
+The _tep_register_print_string()_ function returns 0 in case of success. In case
+of an error -1 is returned, and errno is set to the appropriate error number.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+char *my_resolve_kernel_addr(void *context,
+ unsigned long long *addrp, char **modp)
+{
+ struct db *function_database = context;
+ struct symbol *sym = sql_lookup(function_database, *addrp);
+
+ if (!sym)
+ return NULL;
+
+ *modp = sym->module_name;
+ return sym->name;
+}
+
+void show_function( unsigned long long addr)
+{
+ unsigned long long fstart;
+ const char *fname;
+
+ if (tep_set_function_resolver(tep, my_resolve_kernel_addr,
+ function_database) != 0) {
+ /* failed to register my_resolve_kernel_addr */
+ }
+
+ /* These APIs use my_resolve_kernel_addr() to resolve the addr */
+ fname = tep_find_function(tep, addr);
+ fstart = tep_find_function_address(tep, addr);
+
+ /*
+ addr is in function named fname, starting at fstart address,
+ at offset (addr - fstart)
+ */
+
+ tep_reset_function_resolver(tep);
+
+}
+...
+ if (tep_register_function(tep, "kvm_exit",
+ (unsigned long long) 0x12345678, "kvm") != 0) {
+ /* Failed to register kvm_exit address mapping */
+ }
+...
+ if (tep_register_print_string(tep, "print string",
+ (unsigned long long) 0x87654321, NULL) != 0) {
+ /* Failed to register "print string" address mapping */
+ }
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt
new file mode 100644
index 0000000..04840e2
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt
@@ -0,0 +1,88 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_find_function,tep_find_function_address - Find function name / start address.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+--
+
+DESCRIPTION
+-----------
+These functions can be used to find function name and start address, by given
+address. The given address does not have to be exact, it will select the function
+that would contain it.
+
+The _tep_find_function()_ function returns the function name, which contains the
+given address _addr_. The _tep_ argument is the trace event parser context.
+
+The _tep_find_function_address()_ function returns the function start address,
+by given address _addr_. The _addr_ does not have to be exact, it will select the
+function that would contain it. The _tep_ argument is the trace event parser context.
+
+RETURN VALUE
+------------
+The _tep_find_function()_ function returns the function name, or NULL in case
+it cannot be found.
+
+The _tep_find_function_address()_ function returns the function start address,
+or 0 in case it cannot be found.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+void show_function( unsigned long long addr)
+{
+ const char *fname = tep_find_function(tep, addr);
+ unsigned long long fstart = tep_find_function_address(tep, addr);
+
+ /* addr is in function named fname, starting at fstart address, at offset (addr - fstart) */
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt
new file mode 100644
index 0000000..45b2017
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt
@@ -0,0 +1,101 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_alloc, tep_free,tep_ref, tep_unref,tep_get_ref - Create, destroy, manage
+references of trace event parser context.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_handle pass:[*]*tep_alloc*(void);
+void *tep_free*(struct tep_handle pass:[*]_tep_);
+void *tep_ref*(struct tep_handle pass:[*]_tep_);
+void *tep_unref*(struct tep_handle pass:[*]_tep_);
+int *tep_get_ref*(struct tep_handle pass:[*]_tep_);
+--
+
+DESCRIPTION
+-----------
+These are the main functions to create and destroy tep_handle - the main
+structure, representing the trace event parser context. This context is used as
+the input parameter of most library APIs.
+
+The _tep_alloc()_ function allocates and initializes the tep context.
+
+The _tep_free()_ function will decrement the reference of the _tep_ handler.
+When there is no more references, then it will free the handler, as well
+as clean up all its resources that it had used. The argument _tep_ is
+the pointer to the trace event parser context.
+
+The _tep_ref()_ function adds a reference to the _tep_ handler.
+
+The _tep_unref()_ function removes a reference from the _tep_ handler. When
+the last reference is removed, the _tep_ is destroyed, and all resources that
+it had used are cleaned up.
+
+The _tep_ref_get()_ functions gets the current references of the _tep_ handler.
+
+RETURN VALUE
+------------
+_tep_alloc()_ returns a pointer to a newly created tep_handle structure.
+NULL is returned in case there is not enough free memory to allocate it.
+
+_tep_ref_get()_ returns the current references of _tep_.
+If _tep_ is NULL, 0 is returned.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+
+...
+struct tep_handle *tep = tep_alloc();
+...
+int ref = tep_get_ref(tep);
+tep_ref(tep);
+if ( (ref+1) != tep_get_ref(tep)) {
+ /* Something wrong happened, the counter is not incremented by 1 */
+}
+tep_unref(tep);
+...
+tep_free(tep);
+...
+--
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt
new file mode 100644
index 0000000..615d117
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt
@@ -0,0 +1,102 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_header_page_size, tep_get_header_timestamp_size, tep_is_old_format -
+Get the data stored in the header page, in kernel context.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_);
+int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_);
+bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_);
+--
+DESCRIPTION
+-----------
+These functions retrieve information from kernel context, stored in tracefs
+events/header_page. Old kernels do not have header page info, so default values
+from user space context are used.
+
+The _tep_get_header_page_size()_ function returns the size of a long integer,
+in kernel context. The _tep_ argument is trace event parser context.
+This information is retrieved from tracefs events/header_page, "commit" field.
+
+The _tep_get_header_timestamp_size()_ function returns the size of timestamps,
+in kernel context. The _tep_ argument is trace event parser context. This
+information is retrieved from tracefs events/header_page, "timestamp" field.
+
+The _tep_is_old_format()_ function returns true if the kernel predates
+the addition of events/header_page, otherwise it returns false.
+
+RETURN VALUE
+------------
+The _tep_get_header_page_size()_ function returns the size of a long integer,
+in bytes.
+
+The _tep_get_header_timestamp_size()_ function returns the size of timestamps,
+in bytes.
+
+The _tep_is_old_format()_ function returns true, if an old kernel is used to
+generate the tracing data, which has no event/header_page. If the kernel is new,
+or _tep_ is NULL, false is returned.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+ int longsize;
+ int timesize;
+ bool old;
+
+ longsize = tep_get_header_page_size(tep);
+ timesize = tep_get_header_timestamp_size(tep);
+ old = tep_is_old_format(tep);
+
+ printf ("%s kernel is used to generate the tracing data.\n",
+ old?"Old":"New");
+ printf("The size of a long integer is %d bytes.\n", longsize);
+ printf("The timestamps size is %d bytes.\n", timesize);
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt
new file mode 100644
index 0000000..d5d375e
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt
@@ -0,0 +1,104 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_is_bigendian, tep_is_local_bigendian, tep_set_local_bigendian - Get / set
+the endianness of the local machine.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_endian* {
+ TEP_LITTLE_ENDIAN = 0,
+ TEP_BIG_ENDIAN
+};
+
+int *tep_is_bigendian*(void);
+bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_);
+void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_);
+--
+
+DESCRIPTION
+-----------
+
+The _tep_is_bigendian()_ gets the endianness of the machine, executing
+the function.
+
+The _tep_is_local_bigendian()_ function gets the endianness of the local
+machine, saved in the _tep_ handler. The _tep_ argument is the trace event
+parser context. This API is a bit faster than _tep_is_bigendian()_, as it
+returns cached endianness of the local machine instead of checking it each time.
+
+The _tep_set_local_bigendian()_ function sets the endianness of the local
+machine in the _tep_ handler. The _tep_ argument is trace event parser context.
+The _endian_ argument is the endianness:
+[verse]
+--
+ _TEP_LITTLE_ENDIAN_ - the machine is little endian,
+ _TEP_BIG_ENDIAN_ - the machine is big endian.
+--
+
+RETURN VALUE
+------------
+The _tep_is_bigendian()_ function returns non zero if the endianness of the
+machine, executing the code, is big endian and zero otherwise.
+
+The _tep_is_local_bigendian()_ function returns true, if the endianness of the
+local machine, saved in the _tep_ handler, is big endian, or false otherwise.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+ if (tep_is_bigendian())
+ tep_set_local_bigendian(tep, TEP_BIG_ENDIAN);
+ else
+ tep_set_local_bigendian(tep, TEP_LITTLE_ENDIAN);
+...
+ if (tep_is_local_bigendian(tep))
+ printf("This machine you are running on is bigendian\n");
+ else
+ printf("This machine you are running on is little endian\n");
+
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt
new file mode 100644
index 0000000..01d78ea
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt
@@ -0,0 +1,78 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_long_size, tep_set_long_size - Get / set the size of a long integer on
+the machine, where the trace is generated, in bytes
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_);
+void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_);
+--
+
+DESCRIPTION
+-----------
+The _tep_get_long_size()_ function returns the size of a long integer on the machine,
+where the trace is generated. The _tep_ argument is trace event parser context.
+
+The _tep_set_long_size()_ function sets the size of a long integer on the machine,
+where the trace is generated. The _tep_ argument is trace event parser context.
+The _long_size_ is the size of a long integer, in bytes.
+
+RETURN VALUE
+------------
+The _tep_get_long_size()_ function returns the size of a long integer on the machine,
+where the trace is generated, in bytes.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+tep_set_long_size(tep, 4);
+...
+int long_size = tep_get_long_size(tep);
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt
new file mode 100644
index 0000000..452c0cf
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt
@@ -0,0 +1,82 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_get_page_size, tep_set_page_size - Get / set the size of a memory page on
+the machine, where the trace is generated
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_get_page_size*(struct tep_handle pass:[*]_tep_);
+void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_);
+--
+
+DESCRIPTION
+-----------
+The _tep_get_page_size()_ function returns the size of a memory page on
+the machine, where the trace is generated. The _tep_ argument is trace
+event parser context.
+
+The _tep_set_page_size()_ function stores in the _tep_ context the size of a
+memory page on the machine, where the trace is generated.
+The _tep_ argument is trace event parser context.
+The _page_size_ argument is the size of a memory page, in bytes.
+
+RETURN VALUE
+------------
+The _tep_get_page_size()_ function returns size of the memory page, in bytes.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <unistd.h>
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+ int page_size = getpagesize();
+
+ tep_set_page_size(tep, page_size);
+
+ printf("The page size for this machine is %d\n", tep_get_page_size(tep));
+
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt
new file mode 100644
index 0000000..f248114
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt
@@ -0,0 +1,90 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_parse_event, tep_parse_format - Parse the event format information
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_);
+enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_);
+--
+
+DESCRIPTION
+-----------
+The _tep_parse_event()_ function parses the event format and creates an event
+structure to quickly parse raw data for a given event. The _tep_ argument is
+the trace event parser context. The created event structure is stored in the
+_tep_ context. The _buf_ argument is a buffer with _size_, where the event
+format data is. The event format data can be taken from
+tracefs/events/.../.../format files. The _sys_ argument is the system of
+the event.
+
+The _tep_parse_format()_ function does the same as _tep_parse_event()_. The only
+difference is in the extra _eventp_ argument, where the newly created event
+structure is returned.
+
+RETURN VALUE
+------------
+Both _tep_parse_event()_ and _tep_parse_format()_ functions return 0 on success,
+or TEP_ERRNO__... in case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+char *buf;
+int size;
+struct tep_event *event = NULL;
+buf = read_file("/sys/kernel/tracing/events/ftrace/print/format", &size);
+if (tep_parse_event(tep, buf, size, "ftrace") != 0) {
+ /* Failed to parse the ftrace print format */
+}
+
+if (tep_parse_format(tep, &event, buf, size, "ftrace") != 0) {
+ /* Failed to parse the ftrace print format */
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt
new file mode 100644
index 0000000..c90f16c
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt
@@ -0,0 +1,82 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_parse_header_page - Parses the data stored in the header page.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_);
+--
+
+DESCRIPTION
+-----------
+The _tep_parse_header_page()_ function parses the header page data from _buf_,
+and initializes the _tep_, trace event parser context, with it. The buffer
+_buf_ is with _size_, and is supposed to be copied from
+tracefs/events/header_page.
+
+Some old kernels do not have header page info, in this case the
+_tep_parse_header_page()_ function can be called with _size_ equal to 0. The
+_tep_ context is initialized with default values. The _long_size_ can be used in
+this use case, to set the size of a long integer to be used.
+
+RETURN VALUE
+------------
+The _tep_parse_header_page()_ function returns 0 in case of success, or -1
+in case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+char *buf;
+int size;
+buf = read_file("/sys/kernel/tracing/events/header_page", &size);
+if (tep_parse_header_page(tep, buf, size, sizeof(unsigned long)) != 0) {
+ /* Failed to parse the header page */
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt
new file mode 100644
index 0000000..596032a
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt
@@ -0,0 +1,99 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_load_plugins, tep_unload_plugins - Load / unload traceevent plugins.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_);
+void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_);
+--
+
+DESCRIPTION
+-----------
+The _tep_load_plugins()_ function loads all plugins, located in the plugin
+directories. The _tep_ argument is trace event parser context.
+The plugin directories are :
+[verse]
+--
+ - System's plugin directory, defined at the library compile time. It
+ depends on the library installation prefix and usually is
+ _(install_preffix)/lib/traceevent/plugins_
+ - Directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_
+ - User's plugin directory, located at _~/.local/lib/traceevent/plugins_
+--
+Loading of plugins can be controlled by the _tep_flags_, using the
+_tep_set_flag()_ API:
+[verse]
+--
+ _TEP_DISABLE_SYS_PLUGINS_ - do not load plugins, located in
+ the system's plugin directory.
+ _TEP_DISABLE_PLUGINS_ - do not load any plugins.
+--
+The _tep_set_flag()_ API needs to be called before _tep_load_plugins()_, if
+loading of all plugins is not the desired case.
+
+The _tep_unload_plugins()_ function unloads the plugins, previously loaded by
+_tep_load_plugins()_. The _tep_ argument is trace event parser context. The
+_plugin_list_ is the list of loaded plugins, returned by
+the _tep_load_plugins()_ function.
+
+RETURN VALUE
+------------
+The _tep_load_plugins()_ function returns a list of successfully loaded plugins,
+or NULL in case no plugins are loaded.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct tep_plugin_list *plugins = tep_load_plugins(tep);
+if (plugins == NULL) {
+ /* no plugins are loaded */
+}
+...
+tep_unload_plugins(plugins, tep);
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_, _tep_set_flag(3)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt
new file mode 100644
index 0000000..e9a6911
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt
@@ -0,0 +1,137 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_data_type, tep_data_pid,tep_data_preempt_count, tep_data_flags -
+Extract common fields from a record.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *trace_flag_type* {
+ _TRACE_FLAG_IRQS_OFF_,
+ _TRACE_FLAG_IRQS_NOSUPPORT_,
+ _TRACE_FLAG_NEED_RESCHED_,
+ _TRACE_FLAG_HARDIRQ_,
+ _TRACE_FLAG_SOFTIRQ_,
+};
+
+int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+--
+
+DESCRIPTION
+-----------
+This set of functions can be used to extract common fields from a record.
+
+The _tep_data_type()_ function gets the event id from the record _rec_.
+It reads the "common_type" field. The _tep_ argument is the trace event parser
+context.
+
+The _tep_data_pid()_ function gets the process id from the record _rec_.
+It reads the "common_pid" field. The _tep_ argument is the trace event parser
+context.
+
+The _tep_data_preempt_count()_ function gets the preemption count from the
+record _rec_. It reads the "common_preempt_count" field. The _tep_ argument is
+the trace event parser context.
+
+The _tep_data_flags()_ function gets the latency flags from the record _rec_.
+It reads the "common_flags" field. The _tep_ argument is the trace event parser
+context. Supported latency flags are:
+[verse]
+--
+ _TRACE_FLAG_IRQS_OFF_, Interrupts are disabled.
+ _TRACE_FLAG_IRQS_NOSUPPORT_, Reading IRQ flag is not supported by the architecture.
+ _TRACE_FLAG_NEED_RESCHED_, Task needs rescheduling.
+ _TRACE_FLAG_HARDIRQ_, Hard IRQ is running.
+ _TRACE_FLAG_SOFTIRQ_, Soft IRQ is running.
+--
+
+RETURN VALUE
+------------
+The _tep_data_type()_ function returns an integer, representing the event id.
+
+The _tep_data_pid()_ function returns an integer, representing the process id
+
+The _tep_data_preempt_count()_ function returns an integer, representing the
+preemption count.
+
+The _tep_data_flags()_ function returns an integer, representing the latency
+flags. Look at the _trace_flag_type_ enum for supported flags.
+
+All these functions in case of an error return a negative integer.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+void process_record(struct tep_record *record)
+{
+ int data;
+
+ data = tep_data_type(tep, record);
+ if (data >= 0) {
+ /* Got the ID of the event */
+ }
+
+ data = tep_data_pid(tep, record);
+ if (data >= 0) {
+ /* Got the process ID */
+ }
+
+ data = tep_data_preempt_count(tep, record);
+ if (data >= 0) {
+ /* Got the preemption count */
+ }
+
+ data = tep_data_flags(tep, record);
+ if (data >= 0) {
+ /* Got the latency flags */
+ }
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt
new file mode 100644
index 0000000..53d37d7
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt
@@ -0,0 +1,156 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_register_event_handler, tep_unregister_event_handler - Register /
+unregisters a callback function to parse an event information.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_reg_handler* {
+ _TEP_REGISTER_SUCCESS_,
+ _TEP_REGISTER_SUCCESS_OVERWRITE_,
+};
+
+int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_);
+int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_);
+
+typedef int (*pass:[*]tep_event_handler_func*)(struct trace_seq pass:[*]s, struct tep_record pass:[*]record, struct tep_event pass:[*]event, void pass:[*]context);
+--
+
+DESCRIPTION
+-----------
+The _tep_register_event_handler()_ function registers a handler function,
+which is going to be called to parse the information for a given event.
+The _tep_ argument is the trace event parser context. The _id_ argument is
+the id of the event. The _sys_name_ argument is the name of the system,
+the event belongs to. The _event_name_ argument is the name of the event.
+If _id_ is >= 0, it is used to find the event, otherwise _sys_name_ and
+_event_name_ are used. The _func_ is a pointer to the function, which is going
+to be called to parse the event information. The _context_ argument is a pointer
+to the context data, which will be passed to the _func_. If a handler function
+for the same event is already registered, it will be overridden with the new
+one. This mechanism allows a developer to override the parsing of a given event.
+If for some reason the default print format is not sufficient, the developer
+can register a function for an event to be used to parse the data instead.
+
+The _tep_unregister_event_handler()_ function unregisters the handler function,
+previously registered with _tep_register_event_handler()_. The _tep_ argument
+is the trace event parser context. The _id_, _sys_name_, _event_name_, _func_,
+and _context_ are the same arguments, as when the callback function _func_ was
+registered.
+
+The _tep_event_handler_func_ is the type of the custom event handler
+function. The _s_ argument is the trace sequence, it can be used to create a
+custom string, describing the event. A _record_ to get the event from is passed
+as input parameter and also the _event_ - the handle to the record's event. The
+_context_ is custom context, set when the custom event handler is registered.
+
+RETURN VALUE
+------------
+The _tep_register_event_handler()_ function returns _TEP_REGISTER_SUCCESS_
+if the new handler is registered successfully or
+_TEP_REGISTER_SUCCESS_OVERWRITE_ if an existing handler is overwritten.
+If there is not enough memory to complete the registration,
+TEP_ERRNO__MEM_ALLOC_FAILED is returned.
+
+The _tep_unregister_event_handler()_ function returns 0 if _func_ was removed
+successful or, -1 if the event was not found.
+
+The _tep_event_handler_func_ should return -1 in case of an error,
+or 0 otherwise.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+int timer_expire_handler(struct trace_seq *s, struct tep_record *record,
+ struct tep_event *event, void *context)
+{
+ trace_seq_printf(s, "hrtimer=");
+
+ if (tep_print_num_field(s, "0x%llx", event, "timer", record, 0) == -1)
+ tep_print_num_field(s, "0x%llx", event, "hrtimer", record, 1);
+
+ trace_seq_printf(s, " now=");
+
+ tep_print_num_field(s, "%llu", event, "now", record, 1);
+
+ tep_print_func_field(s, " function=%s", event, "function", record, 0);
+
+ return 0;
+}
+...
+ int ret;
+
+ ret = tep_register_event_handler(tep, -1, "timer", "hrtimer_expire_entry",
+ timer_expire_handler, NULL);
+ if (ret < 0) {
+ char buf[32];
+
+ tep_strerror(tep, ret, buf, 32)
+ printf("Failed to register handler for hrtimer_expire_entry: %s\n", buf);
+ } else {
+ switch (ret) {
+ case TEP_REGISTER_SUCCESS:
+ printf ("Registered handler for hrtimer_expire_entry\n");
+ break;
+ case TEP_REGISTER_SUCCESS_OVERWRITE:
+ printf ("Overwrote handler for hrtimer_expire_entry\n");
+ break;
+ }
+ }
+...
+ ret = tep_unregister_event_handler(tep, -1, "timer", "hrtimer_expire_entry",
+ timer_expire_handler, NULL);
+ if ( ret )
+ printf ("Failed to unregister handler for hrtimer_expire_entry\n");
+
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences
+ related APIs. Trace sequences are used to allow a function to call
+ several other functions to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt
new file mode 100644
index 0000000..708dce9
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt
@@ -0,0 +1,155 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_register_print_function,tep_unregister_print_function -
+Registers / Unregisters a helper function.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_func_arg_type* {
+ TEP_FUNC_ARG_VOID,
+ TEP_FUNC_ARG_INT,
+ TEP_FUNC_ARG_LONG,
+ TEP_FUNC_ARG_STRING,
+ TEP_FUNC_ARG_PTR,
+ TEP_FUNC_ARG_MAX_TYPES
+};
+
+typedef unsigned long long (*pass:[*]tep_func_handler*)(struct trace_seq pass:[*]s, unsigned long long pass:[*]args);
+
+int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._);
+int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_);
+--
+
+DESCRIPTION
+-----------
+Some events may have helper functions in the print format arguments.
+This allows a plugin to dynamically create a way to process one of
+these functions.
+
+The _tep_register_print_function()_ registers such helper function. The _tep_
+argument is the trace event parser context. The _func_ argument is a pointer
+to the helper function. The _ret_type_ argument is the return type of the
+helper function, value from the _tep_func_arg_type_ enum. The _name_ is the name
+of the helper function, as seen in the print format arguments. The _..._ is a
+variable list of _tep_func_arg_type_ enums, the _func_ function arguments.
+This list must end with _TEP_FUNC_ARG_VOID_. See 'EXAMPLE' section.
+
+The _tep_unregister_print_function()_ unregisters a helper function, previously
+registered with _tep_register_print_function()_. The _tep_ argument is the
+trace event parser context. The _func_ and _name_ arguments are the same, used
+when the helper function was registered.
+
+The _tep_func_handler_ is the type of the helper function. The _s_ argument is
+the trace sequence, it can be used to create a custom string.
+The _args_ is a list of arguments, defined when the helper function was
+registered.
+
+RETURN VALUE
+------------
+The _tep_register_print_function()_ function returns 0 in case of success.
+In case of an error, TEP_ERRNO_... code is returned.
+
+The _tep_unregister_print_function()_ returns 0 in case of success, or -1 in
+case of an error.
+
+EXAMPLE
+-------
+Some events have internal functions calls, that appear in the print format
+output. For example "tracefs/events/i915/g4x_wm/format" has:
+[source,c]
+--
+print fmt: "pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s",
+ ((REC->pipe) + 'A'), REC->frame, REC->scanline, REC->primary,
+ REC->sprite, REC->cursor, yesno(REC->cxsr), REC->sr_plane,
+ REC->sr_cursor, REC->sr_fbc, yesno(REC->hpll), REC->hpll_plane,
+ REC->hpll_cursor, REC->hpll_fbc, yesno(REC->fbc)
+--
+Notice the call to function _yesno()_ in the print arguments. In the kernel
+context, this function has the following implementation:
+[source,c]
+--
+static const char *yesno(int x)
+{
+ static const char *yes = "yes";
+ static const char *no = "no";
+
+ return x ? yes : no;
+}
+--
+The user space event parser has no idea how to handle this _yesno()_ function.
+The _tep_register_print_function()_ API can be used to register a user space
+helper function, mapped to the kernel's _yesno()_:
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+static const char *yes_no_helper(int x)
+{
+ return x ? "yes" : "no";
+}
+...
+ if ( tep_register_print_function(tep,
+ yes_no_helper,
+ TEP_FUNC_ARG_STRING,
+ "yesno",
+ TEP_FUNC_ARG_INT,
+ TEP_FUNC_ARG_VOID) != 0) {
+ /* Failed to register yes_no_helper function */
+ }
+
+/*
+ Now, when the event parser encounters this yesno() function, it will know
+ how to handle it.
+*/
+...
+ if (tep_unregister_print_function(tep, yes_no_helper, "yesno") != 0) {
+ /* Failed to unregister yes_no_helper function */
+ }
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences
+ related APIs. Trace sequences are used to allow a function to call
+ several other functions to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt
new file mode 100644
index 0000000..b059978
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt
@@ -0,0 +1,104 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_set_flag, tep_clear_flag, tep_test_flag -
+Manage flags of trace event parser context.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+enum *tep_flag* {
+ _TEP_NSEC_OUTPUT_,
+ _TEP_DISABLE_SYS_PLUGINS_,
+ _TEP_DISABLE_PLUGINS_
+};
+void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
+void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
+bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
+--
+
+DESCRIPTION
+-----------
+Trace event parser context flags are defined in *enum tep_flag*:
+[verse]
+--
+_TEP_NSEC_OUTPUT_ - print event's timestamp in nano seconds, instead of micro seconds.
+_TEP_DISABLE_SYS_PLUGINS_ - disable plugins, located in system's plugin
+ directory. This directory is defined at library compile
+ time, and usually depends on library installation
+ prefix: (install_preffix)/lib/traceevent/plugins
+_TEP_DISABLE_PLUGINS_ - disable all library plugins:
+ - in system's plugin directory
+ - in directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_
+ - in user's home directory, _~/.traceevent/plugins_
+--
+Note: plugin related flags must me set before calling _tep_load_plugins()_ API.
+
+The _tep_set_flag()_ function sets _flag_ to _tep_ context.
+
+The _tep_clear_flag()_ function clears _flag_ from _tep_ context.
+
+The _tep_test_flag()_ function tests if _flag_ is set to _tep_ context.
+
+RETURN VALUE
+------------
+_tep_test_flag()_ function returns true if _flag_ is set, false otherwise.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+/* Print timestamps in nanoseconds */
+tep_set_flag(tep, TEP_NSEC_OUTPUT);
+...
+if (tep_test_flag(tep, TEP_NSEC_OUTPUT)) {
+ /* print timestamps in nanoseconds */
+} else {
+ /* print timestamps in microseconds */
+}
+...
+/* Print timestamps in microseconds */
+tep_clear_flag(tep, TEP_NSEC_OUTPUT);
+...
+--
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt
new file mode 100644
index 0000000..ee4062a
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt
@@ -0,0 +1,85 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_strerror - Returns a string describing regular errno and tep error number.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_);
+
+--
+DESCRIPTION
+-----------
+The _tep_strerror()_ function converts tep error number into a human
+readable string.
+The _tep_ argument is trace event parser context. The _errnum_ is a regular
+errno, defined in errno.h, or a tep error number. The string, describing this
+error number is copied in the _buf_ argument. The _buflen_ argument is
+the size of the _buf_.
+
+It as a thread safe wrapper around strerror_r(). The library function has two
+different behaviors - POSIX and GNU specific. The _tep_strerror()_ API always
+behaves as the POSIX version - the error string is copied in the user supplied
+buffer.
+
+RETURN VALUE
+------------
+The _tep_strerror()_ function returns 0, if a valid _errnum_ is passed and the
+string is copied into _buf_. If _errnum_ is not a valid error number,
+-1 is returned and _buf_ is not modified.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+char buf[32];
+char *pool = calloc(1, 128);
+if (tep == NULL) {
+ tep_strerror(tep, TEP_ERRNO__MEM_ALLOC_FAILED, buf, 32);
+ printf ("The pool is not initialized, %s", buf);
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt
new file mode 100644
index 0000000..8ac6aa1
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt
@@ -0,0 +1,158 @@
+libtraceevent(3)
+================
+
+NAME
+----
+trace_seq_init, trace_seq_destroy, trace_seq_reset, trace_seq_terminate,
+trace_seq_putc, trace_seq_puts, trace_seq_printf, trace_seq_vprintf,
+trace_seq_do_fprintf, trace_seq_do_printf -
+Initialize / destroy a trace sequence.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+*#include <trace-seq.h>*
+
+void *trace_seq_init*(struct trace_seq pass:[*]_s_);
+void *trace_seq_destroy*(struct trace_seq pass:[*]_s_);
+void *trace_seq_reset*(struct trace_seq pass:[*]_s_);
+void *trace_seq_terminate*(struct trace_seq pass:[*]_s_);
+int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_);
+int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_);
+int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, _..._);
+int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_);
+int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_);
+int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_);
+--
+
+DESCRIPTION
+-----------
+Trace sequences are used to allow a function to call several other functions
+to create a string of data to use.
+
+The _trace_seq_init()_ function initializes the trace sequence _s_.
+
+The _trace_seq_destroy()_ function destroys the trace sequence _s_ and frees
+all its resources that it had used.
+
+The _trace_seq_reset()_ function re-initializes the trace sequence _s_. All
+characters already written in _s_ will be deleted.
+
+The _trace_seq_terminate()_ function terminates the trace sequence _s_. It puts
+the null character pass:['\0'] at the end of the buffer.
+
+The _trace_seq_putc()_ function puts a single character _c_ in the trace
+sequence _s_.
+
+The _trace_seq_puts()_ function puts a NULL terminated string _str_ in the
+trace sequence _s_.
+
+The _trace_seq_printf()_ function puts a formated string _fmt _with
+variable arguments _..._ in the trace sequence _s_.
+
+The _trace_seq_vprintf()_ function puts a formated string _fmt _with
+list of arguments _args_ in the trace sequence _s_.
+
+The _trace_seq_do_printf()_ function prints the buffer of trace sequence _s_ to
+the standard output stdout.
+
+The _trace_seq_do_fprintf()_ function prints the buffer of trace sequence _s_
+to the given file _fp_.
+
+RETURN VALUE
+------------
+Both _trace_seq_putc()_ and _trace_seq_puts()_ functions return the number of
+characters put in the trace sequence, or 0 in case of an error
+
+Both _trace_seq_printf()_ and _trace_seq_vprintf()_ functions return 0 if the
+trace oversizes the buffer's free space, the number of characters printed, or
+a negative value in case of an error.
+
+Both _trace_seq_do_printf()_ and _trace_seq_do_fprintf()_ functions return the
+number of printed characters, or -1 in case of an error.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct trace_seq seq;
+trace_seq_init(&seq);
+...
+void foo_seq_print(struct trace_seq *tseq, char *format, ...)
+{
+ va_list ap;
+ va_start(ap, format);
+ if (trace_seq_vprintf(tseq, format, ap) <= 0) {
+ /* Failed to print in the trace sequence */
+ }
+ va_end(ap);
+}
+
+trace_seq_reset(&seq);
+
+char *str = " MAN page example";
+if (trace_seq_puts(&seq, str) != strlen(str)) {
+ /* Failed to put str in the trace sequence */
+}
+if (trace_seq_putc(&seq, ':') != 1) {
+ /* Failed to put ':' in the trace sequence */
+}
+if (trace_seq_printf(&seq, " trace sequence: %d", 1) <= 0) {
+ /* Failed to print in the trace sequence */
+}
+foo_seq_print( &seq, " %d\n", 2);
+
+trace_seq_terminate(&seq);
+...
+
+if (trace_seq_do_printf(&seq) < 0 ) {
+ /* Failed to print the sequence buffer to the standard output */
+}
+FILE *fp = fopen("trace.txt", "w");
+if (trace_seq_do_fprintf(&seq, fp) < 0 ) [
+ /* Failed to print the sequence buffer to the trace.txt file */
+}
+
+trace_seq_destroy(&seq);
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences related APIs.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/libtraceevent.txt b/tools/lib/traceevent/Documentation/libtraceevent.txt
new file mode 100644
index 0000000..d530a7c
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/libtraceevent.txt
@@ -0,0 +1,192 @@
+libtraceevent(3)
+================
+
+NAME
+----
+libtraceevent - Linux kernel trace event library
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+Management of tep handler data structure and access of its members:
+ struct tep_handle pass:[*]*tep_alloc*(void);
+ void *tep_free*(struct tep_handle pass:[*]_tep_);
+ void *tep_ref*(struct tep_handle pass:[*]_tep_);
+ void *tep_unref*(struct tep_handle pass:[*]_tep_);
+ int *tep_get_ref*(struct tep_handle pass:[*]_tep_);
+ void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
+ void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
+ bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flags_);
+ int *tep_get_cpus*(struct tep_handle pass:[*]_tep_);
+ void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_);
+ int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_);
+ void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_);
+ int *tep_get_page_size*(struct tep_handle pass:[*]_tep_);
+ void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_);
+ int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_);
+ int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_);
+ bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_);
+ int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_);
+
+Register / unregister APIs:
+ int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_);
+ int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_);
+ int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_);
+ int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_);
+ int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._);
+ int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_);
+
+Plugins management:
+ struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_);
+ void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_);
+ char pass:[*]pass:[*]*tep_plugin_list_options*(void);
+ void *tep_plugin_free_options_list*(char pass:[*]pass:[*]_list_);
+ int *tep_plugin_add_options*(const char pass:[*]_name_, struct tep_plugin_option pass:[*]_options_);
+ void *tep_plugin_remove_options*(struct tep_plugin_option pass:[*]_options_);
+ void *tep_print_plugins*(struct trace_seq pass:[*]_s_, const char pass:[*]_prefix_, const char pass:[*]_suffix_, const struct tep_plugin_list pass:[*]_list_);
+
+Event related APIs:
+ struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_);
+ struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_);
+ int *tep_get_events_count*(struct tep_handle pass:[*]_tep_);
+ struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
+ struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
+ void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._);
+
+Event finding:
+ struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_);
+ struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_);
+ struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_);
+
+Parsing of event files:
+ int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_);
+ enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_);
+ enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_);
+
+APIs related to fields from event's format files:
+ struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_);
+ struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_);
+ void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_);
+ int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+ int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+ int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_);
+ int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_);
+
+Event fields printing:
+ void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_);
+ void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_);
+ int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_);
+ int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_);
+
+Event fields finding:
+ struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_);
+ struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_);
+ struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_);
+
+Functions resolver:
+ int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_);
+ void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_);
+ const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+ unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_);
+
+Filter management:
+ struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_);
+ enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_);
+ enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_);
+ int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_);
+ int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+ void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_);
+ void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_);
+ char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+ int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_);
+ int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_);
+ int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_);
+
+Parsing various data from the records:
+ int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+ int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+ int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+ int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
+
+Command and task related APIs:
+ const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_tep_, int _pid_);
+ struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_);
+ int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_);
+ int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_);
+ bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_);
+ int *tep_cmdline_pid*(struct tep_handle pass:[*]_tep_, struct cmdline pass:[*]_cmdline_);
+
+Endian related APIs:
+ int *tep_is_bigendian*(void);
+ unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_);
+ bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_);
+ void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_);
+ bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_);
+ void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_);
+
+Trace sequences:
+*#include <trace-seq.h>*
+ void *trace_seq_init*(struct trace_seq pass:[*]_s_);
+ void *trace_seq_reset*(struct trace_seq pass:[*]_s_);
+ void *trace_seq_destroy*(struct trace_seq pass:[*]_s_);
+ int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, ...);
+ int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_);
+ int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_);
+ int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_);
+ void *trace_seq_terminate*(struct trace_seq pass:[*]_s_);
+ int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_);
+ int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_);
+--
+
+DESCRIPTION
+-----------
+The libtraceevent(3) library provides APIs to access kernel tracepoint events,
+located in the tracefs file system under the events directory.
+
+ENVIRONMENT
+-----------
+[verse]
+--
+TRACEEVENT_PLUGIN_DIR
+ Additional plugin directory. All shared object files, located in this directory will be loaded as traceevent plugins.
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+ Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+ Header file to include in order to have access to trace sequences related APIs.
+ Trace sequences are used to allow a function to call several other functions
+ to create a string of data to use.
+*-ltraceevent*
+ Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to <linux-trace-devel@vger.kernel.org>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/tools/lib/traceevent/Documentation/manpage-1.72.xsl b/tools/lib/traceevent/Documentation/manpage-1.72.xsl
new file mode 100644
index 0000000..b4d315c
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/manpage-1.72.xsl
@@ -0,0 +1,14 @@
+<!-- manpage-1.72.xsl:
+ special settings for manpages rendered from asciidoc+docbook
+ handles peculiarities in docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the special values for the roff control characters
+ needed for docbook-xsl 1.72.0 -->
+<xsl:param name="git.docbook.backslash">▓</xsl:param>
+<xsl:param name="git.docbook.dot" >⌂</xsl:param>
+
+</xsl:stylesheet>
diff --git a/tools/lib/traceevent/Documentation/manpage-base.xsl b/tools/lib/traceevent/Documentation/manpage-base.xsl
new file mode 100644
index 0000000..a264fa6
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/manpage-base.xsl
@@ -0,0 +1,35 @@
+<!-- manpage-base.xsl:
+ special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<!-- these params silence some output from xmlto -->
+<xsl:param name="man.output.quietly" select="1"/>
+<xsl:param name="refentry.meta.get.quietly" select="1"/>
+
+<!-- convert asciidoc callouts to man page format;
+ git.docbook.backslash and git.docbook.dot params
+ must be supplied by another XSL file or other means -->
+<xsl:template match="co">
+ <xsl:value-of select="concat(
+ $git.docbook.backslash,'fB(',
+ substring-after(@id,'-'),')',
+ $git.docbook.backslash,'fR')"/>
+</xsl:template>
+<xsl:template match="calloutlist">
+ <xsl:value-of select="$git.docbook.dot"/>
+ <xsl:text>sp </xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+</xsl:template>
+<xsl:template match="callout">
+ <xsl:value-of select="concat(
+ $git.docbook.backslash,'fB',
+ substring-after(@arearefs,'-'),
+ '. ',$git.docbook.backslash,'fR')"/>
+ <xsl:apply-templates/>
+ <xsl:value-of select="$git.docbook.dot"/>
+ <xsl:text>br </xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl
new file mode 100644
index 0000000..608eb5d
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl
@@ -0,0 +1,17 @@
+<!-- manpage-bold-literal.xsl:
+ special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<!-- render literal text as bold (instead of plain or monospace);
+ this makes literal text easier to distinguish in manpages
+ viewed on a tty -->
+<xsl:template match="literal">
+ <xsl:value-of select="$git.docbook.backslash"/>
+ <xsl:text>fB</xsl:text>
+ <xsl:apply-templates/>
+ <xsl:value-of select="$git.docbook.backslash"/>
+ <xsl:text>fR</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/lib/traceevent/Documentation/manpage-normal.xsl b/tools/lib/traceevent/Documentation/manpage-normal.xsl
new file mode 100644
index 0000000..a48f5b1
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/manpage-normal.xsl
@@ -0,0 +1,13 @@
+<!-- manpage-normal.xsl:
+ special settings for manpages rendered from asciidoc+docbook
+ handles anything we want to keep away from docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the normal values for the roff control characters -->
+<xsl:param name="git.docbook.backslash">\</xsl:param>
+<xsl:param name="git.docbook.dot" >.</xsl:param>
+
+</xsl:stylesheet>
diff --git a/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl
new file mode 100644
index 0000000..a63c763
--- /dev/null
+++ b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl
@@ -0,0 +1,21 @@
+<!-- manpage-suppress-sp.xsl:
+ special settings for manpages rendered from asciidoc+docbook
+ handles erroneous, inline .sp in manpage output of some
+ versions of docbook-xsl -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ version="1.0">
+
+<!-- attempt to work around spurious .sp at the tail of the line
+ that some versions of docbook stylesheets seem to add -->
+<xsl:template match="simpara">
+ <xsl:variable name="content">
+ <xsl:apply-templates/>
+ </xsl:variable>
+ <xsl:value-of select="normalize-space($content)"/>
+ <xsl:if test="not(ancestor::authorblurb) and
+ not(ancestor::personblurb)">
+ <xsl:text> </xsl:text>
+ </xsl:if>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 0b4e833..5315f37 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -25,6 +25,7 @@
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,AR,$(CROSS_COMPILE)ar)
$(call allow-override,NM,$(CROSS_COMPILE)nm)
+$(call allow-override,PKG_CONFIG,pkg-config)
EXT = -std=gnu99
INSTALL = install
@@ -47,33 +48,15 @@
libdir = $(prefix)/$(libdir_relative)
man_dir = $(prefix)/share/man
man_dir_SQ = '$(subst ','\'',$(man_dir))'
+pkgconfig_dir ?= $(word 1,$(shell $(PKG_CONFIG) \
+ --variable pc_path pkg-config | tr ":" " "))
+includedir_relative = traceevent
+includedir = $(prefix)/include/$(includedir_relative)
+includedir_SQ = '$(subst ','\'',$(includedir))'
export man_dir man_dir_SQ INSTALL
export DESTDIR DESTDIR_SQ
-
-set_plugin_dir := 1
-
-# Set plugin_dir to preffered global plugin location
-# If we install under $HOME directory we go under
-# $(HOME)/.traceevent/plugins
-#
-# We dont set PLUGIN_DIR in case we install under $HOME
-# directory, because by default the code looks under:
-# $(HOME)/.traceevent/plugins by default.
-#
-ifeq ($(plugin_dir),)
-ifeq ($(prefix),$(HOME))
-override plugin_dir = $(HOME)/.traceevent/plugins
-set_plugin_dir := 0
-else
-override plugin_dir = $(libdir)/traceevent/plugins
-endif
-endif
-
-ifeq ($(set_plugin_dir),1)
-PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
-PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
-endif
+export EVENT_PARSE_VERSION
include ../../scripts/Makefile.include
@@ -98,7 +81,6 @@
# Shell quotes
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
CONFIG_INCLUDES =
CONFIG_LIBS =
@@ -144,29 +126,14 @@
export srctree OUTPUT CC LD CFLAGS V
build := -f $(srctree)/tools/build/Makefile.build dir=. obj
-PLUGINS = plugin_jbd2.so
-PLUGINS += plugin_hrtimer.so
-PLUGINS += plugin_kmem.so
-PLUGINS += plugin_kvm.so
-PLUGINS += plugin_mac80211.so
-PLUGINS += plugin_sched_switch.so
-PLUGINS += plugin_function.so
-PLUGINS += plugin_xen.so
-PLUGINS += plugin_scsi.so
-PLUGINS += plugin_cfg80211.so
-
-PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS))
-PLUGINS_IN := $(PLUGINS:.so=-in.o)
-
TE_IN := $(OUTPUT)libtraceevent-in.o
LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
-DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
-CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE)
+CMD_TARGETS = $(LIB_TARGET)
TARGETS = $(CMD_TARGETS)
-all: all_cmd
+all: all_cmd plugins
all_cmd: $(CMD_TARGETS)
@@ -174,26 +141,15 @@
$(Q)$(MAKE) $(build)=libtraceevent
$(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN)
- $(QUIET_LINK)$(CC) --shared $^ -Wl,-soname,libtraceevent.so.$(EP_VERSION) -o $@
+ $(QUIET_LINK)$(CC) --shared $(LDFLAGS) $^ -Wl,-soname,libtraceevent.so.$(EP_VERSION) -o $@
@ln -sf $(@F) $(OUTPUT)libtraceevent.so
@ln -sf $(@F) $(OUTPUT)libtraceevent.so.$(EP_VERSION)
$(OUTPUT)libtraceevent.a: $(TE_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
-$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
- $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
-
-plugins: $(PLUGINS)
-
-__plugin_obj = $(notdir $@)
- plugin_obj = $(__plugin_obj:-in.o=)
-
-$(PLUGINS_IN): force
- $(Q)$(MAKE) $(build)=$(plugin_obj)
-
$(OUTPUT)%.so: $(OUTPUT)%-in.o
- $(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $^
+ $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^
define make_version.h
(echo '/* This file is automatically generated. Do not modify. */'; \
@@ -251,48 +207,89 @@
$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
-define do_install_plugins
- for plugin in $1; do \
- $(call do_install,$$plugin,$(plugin_dir_SQ)); \
- done
-endef
-
-define do_generate_dynamic_list_file
- symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
- xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
- if [ "$$symbol_type" = "U W w" ];then \
- (echo '{'; \
- $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
- echo '};'; \
- ) > $2; \
- else \
- (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+PKG_CONFIG_FILE = libtraceevent.pc
+define do_install_pkgconfig_file
+ if [ -n "${pkgconfig_dir}" ]; then \
+ cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \
+ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \
+ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \
+ sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \
+ sed -i "s|HEADER_DIR|$(includedir)|g" ${PKG_CONFIG_FILE}; \
+ $(call do_install,$(PKG_CONFIG_FILE),$(pkgconfig_dir),644); \
+ else \
+ (echo Failed to locate pkg-config directory) 1>&2; \
fi
endef
-install_lib: all_cmd install_plugins
+install_lib: all_cmd install_plugins install_headers install_pkgconfig
$(call QUIET_INSTALL, $(LIB_TARGET)) \
$(call do_install_mkdir,$(libdir_SQ)); \
cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ)
-install_plugins: $(PLUGINS)
- $(call QUIET_INSTALL, trace_plugins) \
- $(call do_install_plugins, $(PLUGINS))
+install_pkgconfig:
+ $(call QUIET_INSTALL, $(PKG_CONFIG_FILE)) \
+ $(call do_install_pkgconfig_file,$(prefix))
install_headers:
$(call QUIET_INSTALL, headers) \
- $(call do_install,event-parse.h,$(prefix)/include/traceevent,644); \
- $(call do_install,event-utils.h,$(prefix)/include/traceevent,644); \
- $(call do_install,kbuffer.h,$(prefix)/include/traceevent,644)
+ $(call do_install,event-parse.h,$(DESTDIR)$(includedir_SQ),644); \
+ $(call do_install,event-utils.h,$(DESTDIR)$(includedir_SQ),644); \
+ $(call do_install,trace-seq.h,$(DESTDIR)$(includedir_SQ),644); \
+ $(call do_install,kbuffer.h,$(DESTDIR)$(includedir_SQ),644)
install: install_lib
-clean:
+clean: clean_plugins
$(call QUIET_CLEAN, libtraceevent) \
- $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
- $(RM) TRACEEVENT-CFLAGS tags TAGS
+ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \
+ $(RM) TRACEEVENT-CFLAGS tags TAGS; \
+ $(RM) $(PKG_CONFIG_FILE)
-PHONY += force plugins
+PHONY += doc
+doc:
+ $(call descend,Documentation)
+
+PHONY += doc-clean
+doc-clean:
+ $(call descend,Documentation,clean)
+
+PHONY += doc-install
+doc-install:
+ $(call descend,Documentation,install)
+
+PHONY += doc-uninstall
+doc-uninstall:
+ $(call descend,Documentation,uninstall)
+
+PHONY += help
+help:
+ @echo 'Possible targets:'
+ @echo''
+ @echo ' all - default, compile the library and the'\
+ 'plugins'
+ @echo ' plugins - compile the plugins'
+ @echo ' install - install the library, the plugins,'\
+ 'the header and pkgconfig files'
+ @echo ' clean - clean the library and the plugins object files'
+ @echo ' doc - compile the documentation files - man'\
+ 'and html pages, in the Documentation directory'
+ @echo ' doc-clean - clean the documentation files'
+ @echo ' doc-install - install the man pages'
+ @echo ' doc-uninstall - uninstall the man pages'
+ @echo''
+
+PHONY += plugins
+plugins:
+ $(call descend,plugins)
+
+PHONY += install_plugins
+install_plugins:
+ $(call descend,plugins,install)
+
+PHONY += clean_plugins
+clean_plugins:
+ $(call descend,plugins,clean)
+
force:
# Declare the contents of the .PHONY variable as phony. We keep that
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
new file mode 100644
index 0000000..4faf52a
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#include "event-parse.h"
+#include "event-parse-local.h"
+#include "event-utils.h"
+
+/**
+ * tep_get_event - returns the event with the given index
+ * @tep: a handle to the tep_handle
+ * @index: index of the requested event, in the range 0 .. nr_events
+ *
+ * This returns pointer to the element of the events array with the given index
+ * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned.
+ */
+struct tep_event *tep_get_event(struct tep_handle *tep, int index)
+{
+ if (tep && tep->events && index < tep->nr_events)
+ return tep->events[index];
+
+ return NULL;
+}
+
+/**
+ * tep_get_first_event - returns the first event in the events array
+ * @tep: a handle to the tep_handle
+ *
+ * This returns pointer to the first element of the events array
+ * If @tep is NULL, NULL is returned.
+ */
+struct tep_event *tep_get_first_event(struct tep_handle *tep)
+{
+ return tep_get_event(tep, 0);
+}
+
+/**
+ * tep_get_events_count - get the number of defined events
+ * @tep: a handle to the tep_handle
+ *
+ * This returns number of elements in event array
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_events_count(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->nr_events;
+ return 0;
+}
+
+/**
+ * tep_set_flag - set event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag, or combination of flags to be set
+ * can be any combination from enum tep_flag
+ *
+ * This sets a flag or combination of flags from enum tep_flag
+ */
+void tep_set_flag(struct tep_handle *tep, int flag)
+{
+ if (tep)
+ tep->flags |= flag;
+}
+
+/**
+ * tep_clear_flag - clear event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be cleared
+ *
+ * This clears a tep flag
+ */
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ tep->flags &= ~flag;
+}
+
+/**
+ * tep_test_flag - check the state of event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be checked
+ *
+ * This returns the state of the requested tep flag.
+ * Returns: true if the flag is set, false otherwise.
+ */
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ return tep->flags & flag;
+ return false;
+}
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data)
+{
+ unsigned short swap;
+
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
+ return data;
+
+ swap = ((data & 0xffULL) << 8) |
+ ((data & (0xffULL << 8)) >> 8);
+
+ return swap;
+}
+
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data)
+{
+ unsigned int swap;
+
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
+ return data;
+
+ swap = ((data & 0xffULL) << 24) |
+ ((data & (0xffULL << 8)) << 8) |
+ ((data & (0xffULL << 16)) >> 8) |
+ ((data & (0xffULL << 24)) >> 24);
+
+ return swap;
+}
+
+unsigned long long
+tep_data2host8(struct tep_handle *tep, unsigned long long data)
+{
+ unsigned long long swap;
+
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
+ return data;
+
+ swap = ((data & 0xffULL) << 56) |
+ ((data & (0xffULL << 8)) << 40) |
+ ((data & (0xffULL << 16)) << 24) |
+ ((data & (0xffULL << 24)) << 8) |
+ ((data & (0xffULL << 32)) >> 8) |
+ ((data & (0xffULL << 40)) >> 24) |
+ ((data & (0xffULL << 48)) >> 40) |
+ ((data & (0xffULL << 56)) >> 56);
+
+ return swap;
+}
+
+/**
+ * tep_get_header_page_size - get size of the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the header page
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->header_page_size_size;
+ return 0;
+}
+
+/**
+ * tep_get_header_timestamp_size - get size of the timestamp in the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the timestamp in the header page
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_timestamp_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->header_page_ts_size;
+ return 0;
+}
+
+/**
+ * tep_get_cpus - get the number of CPUs
+ * @tep: a handle to the tep_handle
+ *
+ * This returns the number of CPUs
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_cpus(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->cpus;
+ return 0;
+}
+
+/**
+ * tep_set_cpus - set the number of CPUs
+ * @tep: a handle to the tep_handle
+ *
+ * This sets the number of CPUs
+ */
+void tep_set_cpus(struct tep_handle *tep, int cpus)
+{
+ if (tep)
+ tep->cpus = cpus;
+}
+
+/**
+ * tep_get_long_size - get the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
+ *
+ * This returns the size of a long integer on the traced machine
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_long_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->long_size;
+ return 0;
+}
+
+/**
+ * tep_set_long_size - set the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
+ * @size: size, in bytes, of a long integer
+ *
+ * This sets the size of a long integer on the traced machine
+ */
+void tep_set_long_size(struct tep_handle *tep, int long_size)
+{
+ if (tep)
+ tep->long_size = long_size;
+}
+
+/**
+ * tep_get_page_size - get the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
+ *
+ * This returns the size of a memory page on the traced machine
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_page_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->page_size;
+ return 0;
+}
+
+/**
+ * tep_set_page_size - set the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
+ * @_page_size: size of a memory page, in bytes
+ *
+ * This sets the size of a memory page on the traced machine
+ */
+void tep_set_page_size(struct tep_handle *tep, int _page_size)
+{
+ if (tep)
+ tep->page_size = _page_size;
+}
+
+/**
+ * tep_is_file_bigendian - return the endian of the file
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true if the file is in big endian order
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_file_bigendian(struct tep_handle *tep)
+{
+ if (tep)
+ return (tep->file_bigendian == TEP_BIG_ENDIAN);
+ return false;
+}
+
+/**
+ * tep_set_file_bigendian - set if the file is in big endian order
+ * @tep: a handle to the tep_handle
+ * @endian: non zero, if the file is in big endian order
+ *
+ * This sets if the file is in big endian order
+ */
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian)
+{
+ if (tep)
+ tep->file_bigendian = endian;
+}
+
+/**
+ * tep_is_local_bigendian - return the endian of the saved local machine
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true if the saved local machine in @tep is big endian.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_local_bigendian(struct tep_handle *tep)
+{
+ if (tep)
+ return (tep->host_bigendian == TEP_BIG_ENDIAN);
+ return 0;
+}
+
+/**
+ * tep_set_local_bigendian - set the stored local machine endian order
+ * @tep: a handle to the tep_handle
+ * @endian: non zero, if the local host has big endian order
+ *
+ * This sets the endian order for the local machine.
+ */
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
+{
+ if (tep)
+ tep->host_bigendian = endian;
+}
+
+/**
+ * tep_is_old_format - get if an old kernel is used
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true, if an old kernel is used to generate the tracing events or
+ * false if a new kernel is used. Old kernels did not have header page info.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_old_format(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->old_format;
+ return false;
+}
+
+/**
+ * tep_set_test_filters - set a flag to test a filter string
+ * @tep: a handle to the tep_handle
+ * @test_filters: the new value of the test_filters flag
+ *
+ * This sets a flag to test a filter string. If this flag is set, when
+ * tep_filter_add_filter_str() API as called,it will print the filter string
+ * instead of adding it.
+ */
+void tep_set_test_filters(struct tep_handle *tep, int test_filters)
+{
+ if (tep)
+ tep->test_filters = test_filters;
+}
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
new file mode 100644
index 0000000..cee4698
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _PARSE_EVENTS_INT_H
+#define _PARSE_EVENTS_INT_H
+
+struct tep_cmdline;
+struct cmdline_list;
+struct func_map;
+struct func_list;
+struct event_handler;
+struct func_resolver;
+
+struct tep_handle {
+ int ref_count;
+
+ int header_page_ts_offset;
+ int header_page_ts_size;
+ int header_page_size_offset;
+ int header_page_size_size;
+ int header_page_data_offset;
+ int header_page_data_size;
+ int header_page_overwrite;
+
+ enum tep_endian file_bigendian;
+ enum tep_endian host_bigendian;
+
+ int old_format;
+
+ int cpus;
+ int long_size;
+ int page_size;
+
+ struct tep_cmdline *cmdlines;
+ struct cmdline_list *cmdlist;
+ int cmdline_count;
+
+ struct func_map *func_map;
+ struct func_resolver *func_resolver;
+ struct func_list *funclist;
+ unsigned int func_count;
+
+ struct printk_map *printk_map;
+ struct printk_list *printklist;
+ unsigned int printk_count;
+
+
+ struct tep_event **events;
+ int nr_events;
+ struct tep_event **sort_events;
+ enum tep_event_sort_type last_type;
+
+ int type_offset;
+ int type_size;
+
+ int pid_offset;
+ int pid_size;
+
+ int pc_offset;
+ int pc_size;
+
+ int flags_offset;
+ int flags_size;
+
+ int ld_offset;
+ int ld_size;
+
+ int test_filters;
+
+ int flags;
+
+ struct tep_format_field *bprint_ip_field;
+ struct tep_format_field *bprint_fmt_field;
+ struct tep_format_field *bprint_buf_field;
+
+ struct event_handler *handlers;
+ struct tep_function_handler *func_handlers;
+
+ /* cache */
+ struct tep_event *last_event;
+};
+
+void tep_free_event(struct tep_event *event);
+void tep_free_format_field(struct tep_format_field *field);
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data);
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data);
+unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data);
+
+#endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index ce1e202..d948475 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -18,12 +18,14 @@
#include <errno.h>
#include <stdint.h>
#include <limits.h>
-#include <linux/string.h>
#include <linux/time64.h>
#include <netinet/in.h>
#include "event-parse.h"
+
+#include "event-parse-local.h"
#include "event-utils.h"
+#include "trace-seq.h"
static const char *input_buf;
static unsigned long long input_buf_ptr;
@@ -94,7 +96,7 @@
static unsigned long long
process_defined_func(struct trace_seq *s, void *data, int size,
- struct event_format *event, struct print_arg *arg);
+ struct tep_event *event, struct tep_print_arg *arg);
static void free_func_handle(struct tep_function_handler *func);
@@ -117,20 +119,20 @@
x++;
}
-struct print_arg *alloc_arg(void)
+struct tep_print_arg *alloc_arg(void)
{
- return calloc(1, sizeof(struct print_arg));
+ return calloc(1, sizeof(struct tep_print_arg));
}
-struct cmdline {
+struct tep_cmdline {
char *comm;
int pid;
};
static int cmdline_cmp(const void *a, const void *b)
{
- const struct cmdline *ca = a;
- const struct cmdline *cb = b;
+ const struct tep_cmdline *ca = a;
+ const struct tep_cmdline *cb = b;
if (ca->pid < cb->pid)
return -1;
@@ -140,20 +142,39 @@
return 0;
}
+/* Looking for where to place the key */
+static int cmdline_slot_cmp(const void *a, const void *b)
+{
+ const struct tep_cmdline *ca = a;
+ const struct tep_cmdline *cb = b;
+ const struct tep_cmdline *cb1 = cb + 1;
+
+ if (ca->pid < cb->pid)
+ return -1;
+
+ if (ca->pid > cb->pid) {
+ if (ca->pid <= cb1->pid)
+ return 0;
+ return 1;
+ }
+
+ return 0;
+}
+
struct cmdline_list {
struct cmdline_list *next;
char *comm;
int pid;
};
-static int cmdline_init(struct tep_handle *pevent)
+static int cmdline_init(struct tep_handle *tep)
{
- struct cmdline_list *cmdlist = pevent->cmdlist;
+ struct cmdline_list *cmdlist = tep->cmdlist;
struct cmdline_list *item;
- struct cmdline *cmdlines;
+ struct tep_cmdline *cmdlines;
int i;
- cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+ cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count);
if (!cmdlines)
return -1;
@@ -167,29 +188,29 @@
free(item);
}
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+ qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
- pevent->cmdlist = NULL;
+ tep->cmdlines = cmdlines;
+ tep->cmdlist = NULL;
return 0;
}
-static const char *find_cmdline(struct tep_handle *pevent, int pid)
+static const char *find_cmdline(struct tep_handle *tep, int pid)
{
- const struct cmdline *comm;
- struct cmdline key;
+ const struct tep_cmdline *comm;
+ struct tep_cmdline key;
if (!pid)
return "<idle>";
- if (!pevent->cmdlines && cmdline_init(pevent))
+ if (!tep->cmdlines && cmdline_init(tep))
return "<not enough memory for cmdlines!>";
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
return comm->comm;
@@ -197,32 +218,32 @@
}
/**
- * tep_pid_is_registered - return if a pid has a cmdline registered
- * @pevent: handle for the pevent
+ * tep_is_pid_registered - return if a pid has a cmdline registered
+ * @tep: a handle to the trace event parser context
* @pid: The pid to check if it has a cmdline registered with.
*
- * Returns 1 if the pid has a cmdline mapped to it
- * 0 otherwise.
+ * Returns true if the pid has a cmdline mapped to it
+ * false otherwise.
*/
-int tep_pid_is_registered(struct tep_handle *pevent, int pid)
+bool tep_is_pid_registered(struct tep_handle *tep, int pid)
{
- const struct cmdline *comm;
- struct cmdline key;
+ const struct tep_cmdline *comm;
+ struct tep_cmdline key;
if (!pid)
- return 1;
+ return true;
- if (!pevent->cmdlines && cmdline_init(pevent))
- return 0;
+ if (!tep->cmdlines && cmdline_init(tep))
+ return false;
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
- return 1;
- return 0;
+ return true;
+ return false;
}
/*
@@ -230,11 +251,14 @@
* we must add this pid. This is much slower than when cmdlines
* are added before the array is initialized.
*/
-static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int add_new_comm(struct tep_handle *tep,
+ const char *comm, int pid, bool override)
{
- struct cmdline *cmdlines = pevent->cmdlines;
- const struct cmdline *cmdline;
- struct cmdline key;
+ struct tep_cmdline *cmdlines = tep->cmdlines;
+ struct tep_cmdline *cmdline;
+ struct tep_cmdline key;
+ char *new_comm;
+ int cnt;
if (!pid)
return 0;
@@ -242,52 +266,77 @@
/* avoid duplicates */
key.pid = pid;
- cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (cmdline) {
- errno = EEXIST;
- return -1;
+ if (!override) {
+ errno = EEXIST;
+ return -1;
+ }
+ new_comm = strdup(comm);
+ if (!new_comm) {
+ errno = ENOMEM;
+ return -1;
+ }
+ free(cmdline->comm);
+ cmdline->comm = new_comm;
+
+ return 0;
}
- cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
+ cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1));
if (!cmdlines) {
errno = ENOMEM;
return -1;
}
+ tep->cmdlines = cmdlines;
- cmdlines[pevent->cmdline_count].comm = strdup(comm);
- if (!cmdlines[pevent->cmdline_count].comm) {
- free(cmdlines);
+ key.comm = strdup(comm);
+ if (!key.comm) {
errno = ENOMEM;
return -1;
}
- cmdlines[pevent->cmdline_count].pid = pid;
-
- if (cmdlines[pevent->cmdline_count].comm)
- pevent->cmdline_count++;
+ if (!tep->cmdline_count) {
+ /* no entries yet */
+ tep->cmdlines[0] = key;
+ tep->cmdline_count++;
+ return 0;
+ }
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
+ /* Now find where we want to store the new cmdline */
+ cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count - 1,
+ sizeof(*tep->cmdlines), cmdline_slot_cmp);
+
+ cnt = tep->cmdline_count;
+ if (cmdline) {
+ /* cmdline points to the one before the spot we want */
+ cmdline++;
+ cnt -= cmdline - tep->cmdlines;
+
+ } else {
+ /* The new entry is either before or after the list */
+ if (key.pid > tep->cmdlines[tep->cmdline_count - 1].pid) {
+ tep->cmdlines[tep->cmdline_count++] = key;
+ return 0;
+ }
+ cmdline = &tep->cmdlines[0];
+ }
+ memmove(cmdline + 1, cmdline, (cnt * sizeof(*cmdline)));
+ *cmdline = key;
+
+ tep->cmdline_count++;
return 0;
}
-/**
- * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
- * @comm: the command line to register
- * @pid: the pid to map the command line to
- *
- * This adds a mapping to search for command line names with
- * a given pid. The comm is duplicated.
- */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int _tep_register_comm(struct tep_handle *tep,
+ const char *comm, int pid, bool override)
{
struct cmdline_list *item;
- if (pevent->cmdlines)
- return add_new_comm(pevent, comm, pid);
+ if (tep->cmdlines)
+ return add_new_comm(tep, comm, pid, override);
item = malloc(sizeof(*item));
if (!item)
@@ -302,22 +351,46 @@
return -1;
}
item->pid = pid;
- item->next = pevent->cmdlist;
+ item->next = tep->cmdlist;
- pevent->cmdlist = item;
- pevent->cmdline_count++;
+ tep->cmdlist = item;
+ tep->cmdline_count++;
return 0;
}
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
+/**
+ * tep_register_comm - register a pid / comm mapping
+ * @tep: a handle to the trace event parser context
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, -1 is returned and errno is set to EEXIST
+ */
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid)
{
- pevent->trace_clock = strdup(trace_clock);
- if (!pevent->trace_clock) {
+ return _tep_register_comm(tep, comm, pid, false);
+}
+
+/**
+ * tep_override_comm - register a pid / comm mapping
+ * @tep: a handle to the trace event parser context
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, the command string is udapted with the new one
+ */
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
+{
+ if (!tep->cmdlines && cmdline_init(tep)) {
errno = ENOMEM;
return -1;
}
- return 0;
+ return _tep_register_comm(tep, comm, pid, true);
}
struct func_map {
@@ -367,18 +440,18 @@
return 1;
}
-static int func_map_init(struct tep_handle *pevent)
+static int func_map_init(struct tep_handle *tep)
{
struct func_list *funclist;
struct func_list *item;
struct func_map *func_map;
int i;
- func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+ func_map = malloc(sizeof(*func_map) * (tep->func_count + 1));
if (!func_map)
return -1;
- funclist = pevent->funclist;
+ funclist = tep->funclist;
i = 0;
while (funclist) {
@@ -391,34 +464,34 @@
free(item);
}
- qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp);
+ qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp);
/*
* Add a special record at the end.
*/
- func_map[pevent->func_count].func = NULL;
- func_map[pevent->func_count].addr = 0;
- func_map[pevent->func_count].mod = NULL;
+ func_map[tep->func_count].func = NULL;
+ func_map[tep->func_count].addr = 0;
+ func_map[tep->func_count].mod = NULL;
- pevent->func_map = func_map;
- pevent->funclist = NULL;
+ tep->func_map = func_map;
+ tep->funclist = NULL;
return 0;
}
static struct func_map *
-__find_func(struct tep_handle *pevent, unsigned long long addr)
+__find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *func;
struct func_map key;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
key.addr = addr;
- func = bsearch(&key, pevent->func_map, pevent->func_count,
- sizeof(*pevent->func_map), func_bcmp);
+ func = bsearch(&key, tep->func_map, tep->func_count,
+ sizeof(*tep->func_map), func_bcmp);
return func;
}
@@ -431,15 +504,14 @@
/**
* tep_set_function_resolver - set an alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @resolver: function to be used
* @priv: resolver function private state.
*
* Some tools may have already a way to resolve kernel functions, allow them to
- * keep using it instead of duplicating all the entries inside
- * pevent->funclist.
+ * keep using it instead of duplicating all the entries inside tep->funclist.
*/
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv)
{
struct func_resolver *resolver = malloc(sizeof(*resolver));
@@ -450,38 +522,38 @@
resolver->func = func;
resolver->priv = priv;
- free(pevent->func_resolver);
- pevent->func_resolver = resolver;
+ free(tep->func_resolver);
+ tep->func_resolver = resolver;
return 0;
}
/**
* tep_reset_function_resolver - reset alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* Stop using whatever alternative resolver was set, use the default
* one instead.
*/
-void tep_reset_function_resolver(struct tep_handle *pevent)
+void tep_reset_function_resolver(struct tep_handle *tep)
{
- free(pevent->func_resolver);
- pevent->func_resolver = NULL;
+ free(tep->func_resolver);
+ tep->func_resolver = NULL;
}
static struct func_map *
-find_func(struct tep_handle *pevent, unsigned long long addr)
+find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- if (!pevent->func_resolver)
- return __find_func(pevent, addr);
+ if (!tep->func_resolver)
+ return __find_func(tep, addr);
- map = &pevent->func_resolver->map;
+ map = &tep->func_resolver->map;
map->mod = NULL;
map->addr = addr;
- map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
- &map->addr, &map->mod);
+ map->func = tep->func_resolver->func(tep->func_resolver->priv,
+ &map->addr, &map->mod);
if (map->func == NULL)
return NULL;
@@ -490,18 +562,18 @@
/**
* tep_find_function - find a function by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns a pointer to the function stored that has the given
* address. Note, the address does not have to be exact, it
* will select the function that would contain the address.
*/
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr)
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return NULL;
@@ -510,7 +582,7 @@
/**
* tep_find_function_address - find a function address by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns the address the function starts at. This can be used in
@@ -518,11 +590,11 @@
* name and the function offset.
*/
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return 0;
@@ -531,7 +603,7 @@
/**
* tep_register_function - register a function with a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @function: the function name to register
* @addr: the address the function starts at
* @mod: the kernel module the function may be in (NULL for none)
@@ -539,7 +611,7 @@
* This registers a function name with an address and module.
* The @func passed in is duplicated.
*/
-int tep_register_function(struct tep_handle *pevent, char *func,
+int tep_register_function(struct tep_handle *tep, char *func,
unsigned long long addr, char *mod)
{
struct func_list *item = malloc(sizeof(*item));
@@ -547,7 +619,7 @@
if (!item)
return -1;
- item->next = pevent->funclist;
+ item->next = tep->funclist;
item->func = strdup(func);
if (!item->func)
goto out_free;
@@ -560,8 +632,8 @@
item->mod = NULL;
item->addr = addr;
- pevent->funclist = item;
- pevent->func_count++;
+ tep->funclist = item;
+ tep->func_count++;
return 0;
@@ -576,23 +648,23 @@
/**
* tep_print_funcs - print out the stored functions
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints out the stored functions.
*/
-void tep_print_funcs(struct tep_handle *pevent)
+void tep_print_funcs(struct tep_handle *tep)
{
int i;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
- for (i = 0; i < (int)pevent->func_count; i++) {
+ for (i = 0; i < (int)tep->func_count; i++) {
printf("%016llx %s",
- pevent->func_map[i].addr,
- pevent->func_map[i].func);
- if (pevent->func_map[i].mod)
- printf(" [%s]\n", pevent->func_map[i].mod);
+ tep->func_map[i].addr,
+ tep->func_map[i].func);
+ if (tep->func_map[i].mod)
+ printf(" [%s]\n", tep->func_map[i].mod);
else
printf("\n");
}
@@ -622,18 +694,18 @@
return 0;
}
-static int printk_map_init(struct tep_handle *pevent)
+static int printk_map_init(struct tep_handle *tep)
{
struct printk_list *printklist;
struct printk_list *item;
struct printk_map *printk_map;
int i;
- printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+ printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1));
if (!printk_map)
return -1;
- printklist = pevent->printklist;
+ printklist = tep->printklist;
i = 0;
while (printklist) {
@@ -645,41 +717,41 @@
free(item);
}
- qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp);
+ qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp);
- pevent->printk_map = printk_map;
- pevent->printklist = NULL;
+ tep->printk_map = printk_map;
+ tep->printklist = NULL;
return 0;
}
static struct printk_map *
-find_printk(struct tep_handle *pevent, unsigned long long addr)
+find_printk(struct tep_handle *tep, unsigned long long addr)
{
struct printk_map *printk;
struct printk_map key;
- if (!pevent->printk_map && printk_map_init(pevent))
+ if (!tep->printk_map && printk_map_init(tep))
return NULL;
key.addr = addr;
- printk = bsearch(&key, pevent->printk_map, pevent->printk_count,
- sizeof(*pevent->printk_map), printk_cmp);
+ printk = bsearch(&key, tep->printk_map, tep->printk_count,
+ sizeof(*tep->printk_map), printk_cmp);
return printk;
}
/**
* tep_register_print_string - register a string by its address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @fmt: the string format to register
* @addr: the address the string was located at
*
* This registers a string by the address it was stored in the kernel.
* The @fmt passed in is duplicated.
*/
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr)
{
struct printk_list *item = malloc(sizeof(*item));
@@ -688,7 +760,7 @@
if (!item)
return -1;
- item->next = pevent->printklist;
+ item->next = tep->printklist;
item->addr = addr;
/* Strip off quotes and '\n' from the end */
@@ -706,8 +778,8 @@
if (strcmp(p, "\\n") == 0)
*p = 0;
- pevent->printklist = item;
- pevent->printk_count++;
+ tep->printklist = item;
+ tep->printk_count++;
return 0;
@@ -719,70 +791,70 @@
/**
* tep_print_printk - print out the stored strings
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints the string formats that were stored.
*/
-void tep_print_printk(struct tep_handle *pevent)
+void tep_print_printk(struct tep_handle *tep)
{
int i;
- if (!pevent->printk_map)
- printk_map_init(pevent);
+ if (!tep->printk_map)
+ printk_map_init(tep);
- for (i = 0; i < (int)pevent->printk_count; i++) {
+ for (i = 0; i < (int)tep->printk_count; i++) {
printf("%016llx %s\n",
- pevent->printk_map[i].addr,
- pevent->printk_map[i].printk);
+ tep->printk_map[i].addr,
+ tep->printk_map[i].printk);
}
}
-static struct event_format *alloc_event(void)
+static struct tep_event *alloc_event(void)
{
- return calloc(1, sizeof(struct event_format));
+ return calloc(1, sizeof(struct tep_event));
}
-static int add_event(struct tep_handle *pevent, struct event_format *event)
+static int add_event(struct tep_handle *tep, struct tep_event *event)
{
int i;
- struct event_format **events = realloc(pevent->events, sizeof(event) *
- (pevent->nr_events + 1));
+ struct tep_event **events = realloc(tep->events, sizeof(event) *
+ (tep->nr_events + 1));
if (!events)
return -1;
- pevent->events = events;
+ tep->events = events;
- for (i = 0; i < pevent->nr_events; i++) {
- if (pevent->events[i]->id > event->id)
+ for (i = 0; i < tep->nr_events; i++) {
+ if (tep->events[i]->id > event->id)
break;
}
- if (i < pevent->nr_events)
- memmove(&pevent->events[i + 1],
- &pevent->events[i],
- sizeof(event) * (pevent->nr_events - i));
+ if (i < tep->nr_events)
+ memmove(&tep->events[i + 1],
+ &tep->events[i],
+ sizeof(event) * (tep->nr_events - i));
- pevent->events[i] = event;
- pevent->nr_events++;
+ tep->events[i] = event;
+ tep->nr_events++;
- event->pevent = pevent;
+ event->tep = tep;
return 0;
}
-static int event_item_type(enum event_type type)
+static int event_item_type(enum tep_event_type type)
{
switch (type) {
- case EVENT_ITEM ... EVENT_SQUOTE:
+ case TEP_EVENT_ITEM ... TEP_EVENT_SQUOTE:
return 1;
- case EVENT_ERROR ... EVENT_DELIM:
+ case TEP_EVENT_ERROR ... TEP_EVENT_DELIM:
default:
return 0;
}
}
-static void free_flag_sym(struct print_flag_sym *fsym)
+static void free_flag_sym(struct tep_print_flag_sym *fsym)
{
- struct print_flag_sym *next;
+ struct tep_print_flag_sym *next;
while (fsym) {
next = fsym->next;
@@ -793,60 +865,60 @@
}
}
-static void free_arg(struct print_arg *arg)
+static void free_arg(struct tep_print_arg *arg)
{
- struct print_arg *farg;
+ struct tep_print_arg *farg;
if (!arg)
return;
switch (arg->type) {
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
free(arg->atom.atom);
break;
- case PRINT_FIELD:
+ case TEP_PRINT_FIELD:
free(arg->field.name);
break;
- case PRINT_FLAGS:
+ case TEP_PRINT_FLAGS:
free_arg(arg->flags.field);
free(arg->flags.delim);
free_flag_sym(arg->flags.flags);
break;
- case PRINT_SYMBOL:
+ case TEP_PRINT_SYMBOL:
free_arg(arg->symbol.field);
free_flag_sym(arg->symbol.symbols);
break;
- case PRINT_HEX:
- case PRINT_HEX_STR:
+ case TEP_PRINT_HEX:
+ case TEP_PRINT_HEX_STR:
free_arg(arg->hex.field);
free_arg(arg->hex.size);
break;
- case PRINT_INT_ARRAY:
+ case TEP_PRINT_INT_ARRAY:
free_arg(arg->int_array.field);
free_arg(arg->int_array.count);
free_arg(arg->int_array.el_size);
break;
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
free(arg->typecast.type);
free_arg(arg->typecast.item);
break;
- case PRINT_STRING:
- case PRINT_BSTRING:
+ case TEP_PRINT_STRING:
+ case TEP_PRINT_BSTRING:
free(arg->string.string);
break;
- case PRINT_BITMASK:
+ case TEP_PRINT_BITMASK:
free(arg->bitmask.bitmask);
break;
- case PRINT_DYNAMIC_ARRAY:
- case PRINT_DYNAMIC_ARRAY_LEN:
+ case TEP_PRINT_DYNAMIC_ARRAY:
+ case TEP_PRINT_DYNAMIC_ARRAY_LEN:
free(arg->dynarray.index);
break;
- case PRINT_OP:
+ case TEP_PRINT_OP:
free(arg->op.op);
free_arg(arg->op.left);
free_arg(arg->op.right);
break;
- case PRINT_FUNC:
+ case TEP_PRINT_FUNC:
while (arg->func.args) {
farg = arg->func.args;
arg->func.args = farg->next;
@@ -854,7 +926,7 @@
}
break;
- case PRINT_NULL:
+ case TEP_PRINT_NULL:
default:
break;
}
@@ -862,24 +934,24 @@
free(arg);
}
-static enum event_type get_type(int ch)
+static enum tep_event_type get_type(int ch)
{
if (ch == '\n')
- return EVENT_NEWLINE;
+ return TEP_EVENT_NEWLINE;
if (isspace(ch))
- return EVENT_SPACE;
+ return TEP_EVENT_SPACE;
if (isalnum(ch) || ch == '_')
- return EVENT_ITEM;
+ return TEP_EVENT_ITEM;
if (ch == '\'')
- return EVENT_SQUOTE;
+ return TEP_EVENT_SQUOTE;
if (ch == '"')
- return EVENT_DQUOTE;
+ return TEP_EVENT_DQUOTE;
if (!isprint(ch))
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
if (ch == '(' || ch == ')' || ch == ',')
- return EVENT_DELIM;
+ return TEP_EVENT_DELIM;
- return EVENT_OP;
+ return TEP_EVENT_OP;
}
static int __read_char(void)
@@ -927,38 +999,38 @@
return 0;
}
-static enum event_type force_token(const char *str, char **tok);
+static enum tep_event_type force_token(const char *str, char **tok);
-static enum event_type __read_token(char **tok)
+static enum tep_event_type __read_token(char **tok)
{
char buf[BUFSIZ];
int ch, last_ch, quote_ch, next_ch;
int i = 0;
int tok_size = 0;
- enum event_type type;
+ enum tep_event_type type;
*tok = NULL;
ch = __read_char();
if (ch < 0)
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
type = get_type(ch);
- if (type == EVENT_NONE)
+ if (type == TEP_EVENT_NONE)
return type;
buf[i++] = ch;
switch (type) {
- case EVENT_NEWLINE:
- case EVENT_DELIM:
+ case TEP_EVENT_NEWLINE:
+ case TEP_EVENT_DELIM:
if (asprintf(tok, "%c", ch) < 0)
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
return type;
- case EVENT_OP:
+ case TEP_EVENT_OP:
switch (ch) {
case '-':
next_ch = __peek_char();
@@ -1001,8 +1073,8 @@
buf[i++] = __read_char();
goto out;
- case EVENT_DQUOTE:
- case EVENT_SQUOTE:
+ case TEP_EVENT_DQUOTE:
+ case TEP_EVENT_SQUOTE:
/* don't keep quotes */
i--;
quote_ch = ch;
@@ -1014,7 +1086,7 @@
tok_size += BUFSIZ;
if (extend_token(tok, buf, tok_size) < 0)
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
i = 0;
}
last_ch = ch;
@@ -1031,7 +1103,7 @@
* For strings (double quotes) check the next token.
* If it is another string, concatinate the two.
*/
- if (type == EVENT_DQUOTE) {
+ if (type == TEP_EVENT_DQUOTE) {
unsigned long long save_input_buf_ptr = input_buf_ptr;
do {
@@ -1044,8 +1116,8 @@
goto out;
- case EVENT_ERROR ... EVENT_SPACE:
- case EVENT_ITEM:
+ case TEP_EVENT_ERROR ... TEP_EVENT_SPACE:
+ case TEP_EVENT_ITEM:
default:
break;
}
@@ -1056,7 +1128,7 @@
tok_size += BUFSIZ;
if (extend_token(tok, buf, tok_size) < 0)
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
i = 0;
}
ch = __read_char();
@@ -1066,9 +1138,9 @@
out:
buf[i] = 0;
if (extend_token(tok, buf, tok_size + i + 1) < 0)
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
- if (type == EVENT_ITEM) {
+ if (type == TEP_EVENT_ITEM) {
/*
* Older versions of the kernel has a bug that
* creates invalid symbols and will break the mac80211
@@ -1095,12 +1167,12 @@
return type;
}
-static enum event_type force_token(const char *str, char **tok)
+static enum tep_event_type force_token(const char *str, char **tok)
{
const char *save_input_buf;
unsigned long long save_input_buf_ptr;
unsigned long long save_input_buf_siz;
- enum event_type type;
+ enum tep_event_type type;
/* save off the current input pointers */
save_input_buf = input_buf;
@@ -1125,13 +1197,13 @@
free(tok);
}
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
for (;;) {
type = __read_token(tok);
- if (type != EVENT_SPACE)
+ if (type != TEP_EVENT_SPACE)
return type;
free_token(*tok);
@@ -1139,11 +1211,11 @@
/* not reached */
*tok = NULL;
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
}
/**
- * tep_read_token - access to utilites to use the pevent parser
+ * tep_read_token - access to utilities to use the tep parser
* @tok: The token to return
*
* This will parse tokens from the string given by
@@ -1151,7 +1223,7 @@
*
* Returns the token type.
*/
-enum event_type tep_read_token(char **tok)
+enum tep_event_type tep_read_token(char **tok)
{
return read_token(tok);
}
@@ -1166,13 +1238,13 @@
}
/* no newline */
-static enum event_type read_token_item(char **tok)
+static enum tep_event_type read_token_item(char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
for (;;) {
type = __read_token(tok);
- if (type != EVENT_SPACE && type != EVENT_NEWLINE)
+ if (type != TEP_EVENT_SPACE && type != TEP_EVENT_NEWLINE)
return type;
free_token(*tok);
*tok = NULL;
@@ -1180,10 +1252,10 @@
/* not reached */
*tok = NULL;
- return EVENT_NONE;
+ return TEP_EVENT_NONE;
}
-static int test_type(enum event_type type, enum event_type expect)
+static int test_type(enum tep_event_type type, enum tep_event_type expect)
{
if (type != expect) {
do_warning("Error: expected type %d but read %d",
@@ -1193,8 +1265,8 @@
return 0;
}
-static int test_type_token(enum event_type type, const char *token,
- enum event_type expect, const char *expect_tok)
+static int test_type_token(enum tep_event_type type, const char *token,
+ enum tep_event_type expect, const char *expect_tok)
{
if (type != expect) {
do_warning("Error: expected type %d but read %d",
@@ -1210,9 +1282,9 @@
return 0;
}
-static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
+static int __read_expect_type(enum tep_event_type expect, char **tok, int newline_ok)
{
- enum event_type type;
+ enum tep_event_type type;
if (newline_ok)
type = read_token(tok);
@@ -1221,15 +1293,15 @@
return test_type(type, expect);
}
-static int read_expect_type(enum event_type expect, char **tok)
+static int read_expect_type(enum tep_event_type expect, char **tok)
{
return __read_expect_type(expect, tok, 1);
}
-static int __read_expected(enum event_type expect, const char *str,
+static int __read_expected(enum tep_event_type expect, const char *str,
int newline_ok)
{
- enum event_type type;
+ enum tep_event_type type;
char *token;
int ret;
@@ -1245,12 +1317,12 @@
return ret;
}
-static int read_expected(enum event_type expect, const char *str)
+static int read_expected(enum tep_event_type expect, const char *str)
{
return __read_expected(expect, str, 1);
}
-static int read_expected_item(enum event_type expect, const char *str)
+static int read_expected_item(enum tep_event_type expect, const char *str)
{
return __read_expected(expect, str, 0);
}
@@ -1259,13 +1331,13 @@
{
char *token;
- if (read_expected(EVENT_ITEM, "name") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "name") < 0)
return NULL;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return NULL;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
return token;
@@ -1280,13 +1352,13 @@
char *token;
int id;
- if (read_expected_item(EVENT_ITEM, "ID") < 0)
+ if (read_expected_item(TEP_EVENT_ITEM, "ID") < 0)
return -1;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return -1;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
id = strtoul(token, NULL, 0);
@@ -1298,9 +1370,9 @@
return -1;
}
-static int field_is_string(struct format_field *field)
+static int field_is_string(struct tep_format_field *field)
{
- if ((field->flags & FIELD_IS_ARRAY) &&
+ if ((field->flags & TEP_FIELD_IS_ARRAY) &&
(strstr(field->type, "char") || strstr(field->type, "u8") ||
strstr(field->type, "s8")))
return 1;
@@ -1308,7 +1380,7 @@
return 0;
}
-static int field_is_dynamic(struct format_field *field)
+static int field_is_dynamic(struct tep_format_field *field)
{
if (strncmp(field->type, "__data_loc", 10) == 0)
return 1;
@@ -1316,7 +1388,7 @@
return 0;
}
-static int field_is_long(struct format_field *field)
+static int field_is_long(struct tep_format_field *field)
{
/* includes long long */
if (strstr(field->type, "long"))
@@ -1327,7 +1399,7 @@
static unsigned int type_size(const char *name)
{
- /* This covers all FIELD_IS_STRING types. */
+ /* This covers all TEP_FIELD_IS_STRING types. */
static struct {
const char *type;
unsigned int size;
@@ -1353,10 +1425,10 @@
return 0;
}
-static int event_read_fields(struct event_format *event, struct format_field **fields)
+static int event_read_fields(struct tep_event *event, struct tep_format_field **fields)
{
- struct format_field *field = NULL;
- enum event_type type;
+ struct tep_format_field *field = NULL;
+ enum tep_event_type type;
char *token;
char *last_token;
int count = 0;
@@ -1365,14 +1437,14 @@
unsigned int size_dynamic = 0;
type = read_token(&token);
- if (type == EVENT_NEWLINE) {
+ if (type == TEP_EVENT_NEWLINE) {
free_token(token);
return count;
}
count++;
- if (test_type_token(type, token, EVENT_ITEM, "field"))
+ if (test_type_token(type, token, TEP_EVENT_ITEM, "field"))
goto fail;
free_token(token);
@@ -1381,17 +1453,17 @@
* The ftrace fields may still use the "special" name.
* Just ignore it.
*/
- if (event->flags & EVENT_FL_ISFTRACE &&
- type == EVENT_ITEM && strcmp(token, "special") == 0) {
+ if (event->flags & TEP_EVENT_FL_ISFTRACE &&
+ type == TEP_EVENT_ITEM && strcmp(token, "special") == 0) {
free_token(token);
type = read_token(&token);
}
- if (test_type_token(type, token, EVENT_OP, ":") < 0)
+ if (test_type_token(type, token, TEP_EVENT_OP, ":") < 0)
goto fail;
free_token(token);
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
last_token = token;
@@ -1405,17 +1477,17 @@
/* read the rest of the type */
for (;;) {
type = read_token(&token);
- if (type == EVENT_ITEM ||
- (type == EVENT_OP && strcmp(token, "*") == 0) ||
+ if (type == TEP_EVENT_ITEM ||
+ (type == TEP_EVENT_OP && strcmp(token, "*") == 0) ||
/*
* Some of the ftrace fields are broken and have
* an illegal "." in them.
*/
- (event->flags & EVENT_FL_ISFTRACE &&
- type == EVENT_OP && strcmp(token, ".") == 0)) {
+ (event->flags & TEP_EVENT_FL_ISFTRACE &&
+ type == TEP_EVENT_OP && strcmp(token, ".") == 0)) {
if (strcmp(token, "*") == 0)
- field->flags |= FIELD_IS_POINTER;
+ field->flags |= TEP_FIELD_IS_POINTER;
if (field->type) {
char *new_type;
@@ -1445,27 +1517,27 @@
}
field->name = field->alias = last_token;
- if (test_type(type, EVENT_OP))
+ if (test_type(type, TEP_EVENT_OP))
goto fail;
if (strcmp(token, "[") == 0) {
- enum event_type last_type = type;
+ enum tep_event_type last_type = type;
char *brackets = token;
char *new_brackets;
int len;
- field->flags |= FIELD_IS_ARRAY;
+ field->flags |= TEP_FIELD_IS_ARRAY;
type = read_token(&token);
- if (type == EVENT_ITEM)
+ if (type == TEP_EVENT_ITEM)
field->arraylen = strtoul(token, NULL, 0);
else
field->arraylen = 0;
while (strcmp(token, "]") != 0) {
- if (last_type == EVENT_ITEM &&
- type == EVENT_ITEM)
+ if (last_type == TEP_EVENT_ITEM &&
+ type == TEP_EVENT_ITEM)
len = 2;
else
len = 1;
@@ -1486,7 +1558,7 @@
field->arraylen = strtoul(token, NULL, 0);
free_token(token);
type = read_token(&token);
- if (type == EVENT_NONE) {
+ if (type == TEP_EVENT_NONE) {
do_warning_event(event, "failed to find token");
goto fail;
}
@@ -1509,7 +1581,7 @@
* If the next token is not an OP, then it is of
* the format: type [] item;
*/
- if (type == EVENT_ITEM) {
+ if (type == TEP_EVENT_ITEM) {
char *new_type;
new_type = realloc(field->type,
strlen(field->type) +
@@ -1543,81 +1615,81 @@
}
if (field_is_string(field))
- field->flags |= FIELD_IS_STRING;
+ field->flags |= TEP_FIELD_IS_STRING;
if (field_is_dynamic(field))
- field->flags |= FIELD_IS_DYNAMIC;
+ field->flags |= TEP_FIELD_IS_DYNAMIC;
if (field_is_long(field))
- field->flags |= FIELD_IS_LONG;
+ field->flags |= TEP_FIELD_IS_LONG;
- if (test_type_token(type, token, EVENT_OP, ";"))
+ if (test_type_token(type, token, TEP_EVENT_OP, ";"))
goto fail;
free_token(token);
- if (read_expected(EVENT_ITEM, "offset") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
goto fail_expect;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
goto fail_expect;
- if (read_expect_type(EVENT_ITEM, &token))
+ if (read_expect_type(TEP_EVENT_ITEM, &token))
goto fail;
field->offset = strtoul(token, NULL, 0);
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
goto fail_expect;
- if (read_expected(EVENT_ITEM, "size") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "size") < 0)
goto fail_expect;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
goto fail_expect;
- if (read_expect_type(EVENT_ITEM, &token))
+ if (read_expect_type(TEP_EVENT_ITEM, &token))
goto fail;
field->size = strtoul(token, NULL, 0);
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
goto fail_expect;
type = read_token(&token);
- if (type != EVENT_NEWLINE) {
+ if (type != TEP_EVENT_NEWLINE) {
/* newer versions of the kernel have a "signed" type */
- if (test_type_token(type, token, EVENT_ITEM, "signed"))
+ if (test_type_token(type, token, TEP_EVENT_ITEM, "signed"))
goto fail;
free_token(token);
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
goto fail_expect;
- if (read_expect_type(EVENT_ITEM, &token))
+ if (read_expect_type(TEP_EVENT_ITEM, &token))
goto fail;
if (strtoul(token, NULL, 0))
- field->flags |= FIELD_IS_SIGNED;
+ field->flags |= TEP_FIELD_IS_SIGNED;
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
goto fail_expect;
- if (read_expect_type(EVENT_NEWLINE, &token))
+ if (read_expect_type(TEP_EVENT_NEWLINE, &token))
goto fail;
}
free_token(token);
- if (field->flags & FIELD_IS_ARRAY) {
+ if (field->flags & TEP_FIELD_IS_ARRAY) {
if (field->arraylen)
field->elementsize = field->size / field->arraylen;
- else if (field->flags & FIELD_IS_DYNAMIC)
+ else if (field->flags & TEP_FIELD_IS_DYNAMIC)
field->elementsize = size_dynamic;
- else if (field->flags & FIELD_IS_STRING)
+ else if (field->flags & TEP_FIELD_IS_STRING)
field->elementsize = 1;
- else if (field->flags & FIELD_IS_LONG)
- field->elementsize = event->pevent ?
- event->pevent->long_size :
+ else if (field->flags & TEP_FIELD_IS_LONG)
+ field->elementsize = event->tep ?
+ event->tep->long_size :
sizeof(long);
} else
field->elementsize = field->size;
@@ -1640,18 +1712,18 @@
return -1;
}
-static int event_read_format(struct event_format *event)
+static int event_read_format(struct tep_event *event)
{
char *token;
int ret;
- if (read_expected_item(EVENT_ITEM, "format") < 0)
+ if (read_expected_item(TEP_EVENT_ITEM, "format") < 0)
return -1;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return -1;
- if (read_expect_type(EVENT_NEWLINE, &token))
+ if (read_expect_type(TEP_EVENT_NEWLINE, &token))
goto fail;
free_token(token);
@@ -1672,14 +1744,14 @@
return -1;
}
-static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
- char **tok, enum event_type type);
+static enum tep_event_type
+process_arg_token(struct tep_event *event, struct tep_print_arg *arg,
+ char **tok, enum tep_event_type type);
-static enum event_type
-process_arg(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_arg(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
char *token;
type = read_token(&token);
@@ -1688,32 +1760,32 @@
return process_arg_token(event, arg, tok, type);
}
-static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok);
+static enum tep_event_type
+process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok);
/*
* For __print_symbolic() and __print_flags, we need to completely
* evaluate the first argument, which defines what to print next.
*/
-static enum event_type
-process_field_arg(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_field_arg(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
type = process_arg(event, arg, tok);
- while (type == EVENT_OP) {
+ while (type == TEP_EVENT_OP) {
type = process_op(event, arg, tok);
}
return type;
}
-static enum event_type
-process_cond(struct event_format *event, struct print_arg *top, char **tok)
+static enum tep_event_type
+process_cond(struct tep_event *event, struct tep_print_arg *top, char **tok)
{
- struct print_arg *arg, *left, *right;
- enum event_type type;
+ struct tep_print_arg *arg, *left, *right;
+ enum tep_event_type type;
char *token = NULL;
arg = alloc_arg();
@@ -1728,7 +1800,7 @@
goto out_free;
}
- arg->type = PRINT_OP;
+ arg->type = TEP_PRINT_OP;
arg->op.left = left;
arg->op.right = right;
@@ -1736,16 +1808,16 @@
type = process_arg(event, left, &token);
again:
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
goto out_free;
/* Handle other operations in the arguments */
- if (type == EVENT_OP && strcmp(token, ":") != 0) {
+ if (type == TEP_EVENT_OP && strcmp(token, ":") != 0) {
type = process_op(event, left, &token);
goto again;
}
- if (test_type_token(type, token, EVENT_OP, ":"))
+ if (test_type_token(type, token, TEP_EVENT_OP, ":"))
goto out_free;
arg->op.op = token;
@@ -1762,14 +1834,14 @@
top->op.right = NULL;
free_token(token);
free_arg(arg);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_array(struct event_format *event, struct print_arg *top, char **tok)
+static enum tep_event_type
+process_array(struct tep_event *event, struct tep_print_arg *top, char **tok)
{
- struct print_arg *arg;
- enum event_type type;
+ struct tep_print_arg *arg;
+ enum tep_event_type type;
char *token = NULL;
arg = alloc_arg();
@@ -1777,12 +1849,12 @@
do_warning_event(event, "%s: not enough memory!", __func__);
/* '*tok' is set to top->op.op. No need to free. */
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
*tok = NULL;
type = process_arg(event, arg, &token);
- if (test_type_token(type, token, EVENT_OP, "]"))
+ if (test_type_token(type, token, TEP_EVENT_OP, "]"))
goto out_free;
top->op.right = arg;
@@ -1796,7 +1868,7 @@
out_free:
free_token(token);
free_arg(arg);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
static int get_op_prio(char *op)
@@ -1854,11 +1926,11 @@
}
}
-static int set_op_prio(struct print_arg *arg)
+static int set_op_prio(struct tep_print_arg *arg)
{
/* single ops are the greatest */
- if (!arg->op.left || arg->op.left->type == PRINT_NULL)
+ if (!arg->op.left || arg->op.left->type == TEP_PRINT_NULL)
arg->op.prio = 0;
else
arg->op.prio = get_op_prio(arg->op.op);
@@ -1867,17 +1939,17 @@
}
/* Note, *tok does not get freed, but will most likely be saved */
-static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- struct print_arg *left, *right = NULL;
- enum event_type type;
+ struct tep_print_arg *left, *right = NULL;
+ enum tep_event_type type;
char *token;
/* the op is passed in via tok */
token = *tok;
- if (arg->type == PRINT_OP && !arg->op.left) {
+ if (arg->type == TEP_PRINT_OP && !arg->op.left) {
/* handle single op */
if (token[1]) {
do_warning_event(event, "bad op token %s", token);
@@ -1900,7 +1972,7 @@
if (!left)
goto out_warn_free;
- left->type = PRINT_NULL;
+ left->type = TEP_PRINT_NULL;
arg->op.left = left;
right = alloc_arg();
@@ -1922,7 +1994,7 @@
/* copy the top arg to the left */
*left = *arg;
- arg->type = PRINT_OP;
+ arg->type = TEP_PRINT_OP;
arg->op.op = token;
arg->op.left = left;
arg->op.prio = 0;
@@ -1956,13 +2028,13 @@
/* copy the top arg to the left */
*left = *arg;
- arg->type = PRINT_OP;
+ arg->type = TEP_PRINT_OP;
arg->op.op = token;
arg->op.left = left;
arg->op.right = NULL;
if (set_op_prio(arg) == -1) {
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
/* arg->op.op (= token) will be freed at out_free */
arg->op.op = NULL;
goto out_free;
@@ -1973,10 +2045,10 @@
/* could just be a type pointer */
if ((strcmp(arg->op.op, "*") == 0) &&
- type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
+ type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
char *new_atom;
- if (left->type != PRINT_ATOM) {
+ if (left->type != TEP_PRINT_ATOM) {
do_warning_event(event, "bad pointer type");
goto out_free;
}
@@ -1999,16 +2071,16 @@
goto out_warn_free;
type = process_arg_token(event, right, tok, type);
- if (type == EVENT_ERROR) {
+ if (type == TEP_EVENT_ERROR) {
free_arg(right);
/* token was freed in process_arg_token() via *tok */
token = NULL;
goto out_free;
}
- if (right->type == PRINT_OP &&
+ if (right->type == TEP_PRINT_OP &&
get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
- struct print_arg tmp;
+ struct tep_print_arg tmp;
/* rotate ops according to the priority */
arg->op.right = right->op.left;
@@ -2030,7 +2102,7 @@
*left = *arg;
- arg->type = PRINT_OP;
+ arg->type = TEP_PRINT_OP;
arg->op.op = token;
arg->op.left = left;
@@ -2041,12 +2113,12 @@
} else {
do_warning_event(event, "unknown op '%s'", token);
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
/* the arg is now the left side */
goto out_free;
}
- if (type == EVENT_OP && strcmp(*tok, ":") != 0) {
+ if (type == TEP_EVENT_OP && strcmp(*tok, ":") != 0) {
int prio;
/* higher prios need to be closer to the root */
@@ -2065,34 +2137,34 @@
out_free:
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
+static enum tep_event_type
+process_entry(struct tep_event *event __maybe_unused, struct tep_print_arg *arg,
char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
char *field;
char *token;
- if (read_expected(EVENT_OP, "->") < 0)
+ if (read_expected(TEP_EVENT_OP, "->") < 0)
goto out_err;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto out_free;
field = token;
- arg->type = PRINT_FIELD;
+ arg->type = TEP_PRINT_FIELD;
arg->field.name = field;
if (is_flag_field) {
arg->field.field = tep_find_any_field(event, arg->field.name);
- arg->field.field->flags |= FIELD_IS_FLAG;
+ arg->field.field->flags |= TEP_FIELD_IS_FLAG;
is_flag_field = 0;
} else if (is_symbolic_field) {
arg->field.field = tep_find_any_field(event, arg->field.name);
- arg->field.field->flags |= FIELD_IS_SYMBOLIC;
+ arg->field.field->flags |= TEP_FIELD_IS_SYMBOLIC;
is_symbolic_field = 0;
}
@@ -2105,14 +2177,14 @@
free_token(token);
out_err:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static int alloc_and_process_delim(struct event_format *event, char *next_token,
- struct print_arg **print_arg)
+static int alloc_and_process_delim(struct tep_event *event, char *next_token,
+ struct tep_print_arg **print_arg)
{
- struct print_arg *field;
- enum event_type type;
+ struct tep_print_arg *field;
+ enum tep_event_type type;
char *token;
int ret = 0;
@@ -2125,7 +2197,7 @@
type = process_arg(event, field, &token);
- if (test_type_token(type, token, EVENT_DELIM, next_token)) {
+ if (test_type_token(type, token, TEP_EVENT_DELIM, next_token)) {
errno = EINVAL;
ret = -1;
free_arg(field);
@@ -2140,7 +2212,7 @@
return ret;
}
-static char *arg_eval (struct print_arg *arg);
+static char *arg_eval (struct tep_print_arg *arg);
static unsigned long long
eval_type_str(unsigned long long val, const char *type, int pointer)
@@ -2192,7 +2264,7 @@
return val & 0xffffffff;
if (strcmp(type, "u64") == 0 ||
- strcmp(type, "s64"))
+ strcmp(type, "s64") == 0)
return val;
if (strcmp(type, "s8") == 0)
@@ -2237,9 +2309,9 @@
* Try to figure out the type.
*/
static unsigned long long
-eval_type(unsigned long long val, struct print_arg *arg, int pointer)
+eval_type(unsigned long long val, struct tep_print_arg *arg, int pointer)
{
- if (arg->type != PRINT_TYPE) {
+ if (arg->type != TEP_PRINT_TYPE) {
do_warning("expected type argument");
return 0;
}
@@ -2247,22 +2319,22 @@
return eval_type_str(val, arg->typecast.type, pointer);
}
-static int arg_num_eval(struct print_arg *arg, long long *val)
+static int arg_num_eval(struct tep_print_arg *arg, long long *val)
{
long long left, right;
int ret = 1;
switch (arg->type) {
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
*val = strtoll(arg->atom.atom, NULL, 0);
break;
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
ret = arg_num_eval(arg->typecast.item, val);
if (!ret)
break;
*val = eval_type(*val, arg, 0);
break;
- case PRINT_OP:
+ case TEP_PRINT_OP:
switch (arg->op.op[0]) {
case '|':
ret = arg_num_eval(arg->op.left, &left);
@@ -2365,7 +2437,7 @@
break;
case '-':
/* check for negative */
- if (arg->op.left->type == PRINT_NULL)
+ if (arg->op.left->type == TEP_PRINT_NULL)
left = 0;
else
ret = arg_num_eval(arg->op.left, &left);
@@ -2377,7 +2449,7 @@
*val = left - right;
break;
case '+':
- if (arg->op.left->type == PRINT_NULL)
+ if (arg->op.left->type == TEP_PRINT_NULL)
left = 0;
else
ret = arg_num_eval(arg->op.left, &left);
@@ -2400,11 +2472,11 @@
}
break;
- case PRINT_NULL:
- case PRINT_FIELD ... PRINT_SYMBOL:
- case PRINT_STRING:
- case PRINT_BSTRING:
- case PRINT_BITMASK:
+ case TEP_PRINT_NULL:
+ case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+ case TEP_PRINT_STRING:
+ case TEP_PRINT_BSTRING:
+ case TEP_PRINT_BITMASK:
default:
do_warning("invalid eval type %d", arg->type);
ret = 0;
@@ -2413,27 +2485,27 @@
return ret;
}
-static char *arg_eval (struct print_arg *arg)
+static char *arg_eval (struct tep_print_arg *arg)
{
long long val;
- static char buf[20];
+ static char buf[24];
switch (arg->type) {
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
return arg->atom.atom;
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
return arg_eval(arg->typecast.item);
- case PRINT_OP:
+ case TEP_PRINT_OP:
if (!arg_num_eval(arg, &val))
break;
sprintf(buf, "%lld", val);
return buf;
- case PRINT_NULL:
- case PRINT_FIELD ... PRINT_SYMBOL:
- case PRINT_STRING:
- case PRINT_BSTRING:
- case PRINT_BITMASK:
+ case TEP_PRINT_NULL:
+ case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+ case TEP_PRINT_STRING:
+ case TEP_PRINT_BSTRING:
+ case TEP_PRINT_BITMASK:
default:
do_warning("invalid eval type %d", arg->type);
break;
@@ -2442,19 +2514,19 @@
return NULL;
}
-static enum event_type
-process_fields(struct event_format *event, struct print_flag_sym **list, char **tok)
+static enum tep_event_type
+process_fields(struct tep_event *event, struct tep_print_flag_sym **list, char **tok)
{
- enum event_type type;
- struct print_arg *arg = NULL;
- struct print_flag_sym *field;
+ enum tep_event_type type;
+ struct tep_print_arg *arg = NULL;
+ struct tep_print_flag_sym *field;
char *token = *tok;
char *value;
do {
free_token(token);
type = read_token_item(&token);
- if (test_type_token(type, token, EVENT_OP, "{"))
+ if (test_type_token(type, token, TEP_EVENT_OP, "{"))
break;
arg = alloc_arg();
@@ -2464,13 +2536,13 @@
free_token(token);
type = process_arg(event, arg, &token);
- if (type == EVENT_OP)
+ if (type == TEP_EVENT_OP)
type = process_op(event, arg, &token);
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
goto out_free;
- if (test_type_token(type, token, EVENT_DELIM, ","))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
goto out_free;
field = calloc(1, sizeof(*field));
@@ -2491,7 +2563,7 @@
free_token(token);
type = process_arg(event, arg, &token);
- if (test_type_token(type, token, EVENT_OP, "}"))
+ if (test_type_token(type, token, TEP_EVENT_OP, "}"))
goto out_free_field;
value = arg_eval(arg);
@@ -2508,7 +2580,7 @@
free_token(token);
type = read_token_item(&token);
- } while (type == EVENT_DELIM && strcmp(token, ",") == 0);
+ } while (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0);
*tok = token;
return type;
@@ -2520,18 +2592,18 @@
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_flags(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_flags(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- struct print_arg *field;
- enum event_type type;
+ struct tep_print_arg *field;
+ enum tep_event_type type;
char *token = NULL;
memset(arg, 0, sizeof(*arg));
- arg->type = PRINT_FLAGS;
+ arg->type = TEP_PRINT_FLAGS;
field = alloc_arg();
if (!field) {
@@ -2542,10 +2614,10 @@
type = process_field_arg(event, field, &token);
/* Handle operations in the first argument */
- while (type == EVENT_OP)
+ while (type == TEP_EVENT_OP)
type = process_op(event, field, &token);
- if (test_type_token(type, token, EVENT_DELIM, ","))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
goto out_free_field;
free_token(token);
@@ -2557,11 +2629,11 @@
type = read_token_item(&token);
}
- if (test_type_token(type, token, EVENT_DELIM, ","))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
goto out_free;
type = process_fields(event, &arg->flags.flags, &token);
- if (test_type_token(type, token, EVENT_DELIM, ")"))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
goto out_free;
free_token(token);
@@ -2573,18 +2645,18 @@
out_free:
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_symbols(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- struct print_arg *field;
- enum event_type type;
+ struct tep_print_arg *field;
+ enum tep_event_type type;
char *token = NULL;
memset(arg, 0, sizeof(*arg));
- arg->type = PRINT_SYMBOL;
+ arg->type = TEP_PRINT_SYMBOL;
field = alloc_arg();
if (!field) {
@@ -2594,13 +2666,13 @@
type = process_field_arg(event, field, &token);
- if (test_type_token(type, token, EVENT_DELIM, ","))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
goto out_free_field;
arg->symbol.field = field;
type = process_fields(event, &arg->symbol.symbols, &token);
- if (test_type_token(type, token, EVENT_DELIM, ")"))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
goto out_free;
free_token(token);
@@ -2612,12 +2684,12 @@
out_free:
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_hex_common(struct event_format *event, struct print_arg *arg,
- char **tok, enum print_arg_type type)
+static enum tep_event_type
+process_hex_common(struct tep_event *event, struct tep_print_arg *arg,
+ char **tok, enum tep_print_arg_type type)
{
memset(arg, 0, sizeof(*arg));
arg->type = type;
@@ -2635,27 +2707,27 @@
arg->hex.field = NULL;
out:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_hex(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- return process_hex_common(event, arg, tok, PRINT_HEX);
+ return process_hex_common(event, arg, tok, TEP_PRINT_HEX);
}
-static enum event_type
-process_hex_str(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_hex_str(struct tep_event *event, struct tep_print_arg *arg,
char **tok)
{
- return process_hex_common(event, arg, tok, PRINT_HEX_STR);
+ return process_hex_common(event, arg, tok, TEP_PRINT_HEX_STR);
}
-static enum event_type
-process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_int_array(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
memset(arg, 0, sizeof(*arg));
- arg->type = PRINT_INT_ARRAY;
+ arg->type = TEP_PRINT_INT_ARRAY;
if (alloc_and_process_delim(event, ",", &arg->int_array.field))
goto out;
@@ -2676,18 +2748,18 @@
arg->int_array.field = NULL;
out:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_dynamic_array(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- struct format_field *field;
- enum event_type type;
+ struct tep_format_field *field;
+ enum tep_event_type type;
char *token;
memset(arg, 0, sizeof(*arg));
- arg->type = PRINT_DYNAMIC_ARRAY;
+ arg->type = TEP_PRINT_DYNAMIC_ARRAY;
/*
* The item within the parenthesis is another field that holds
@@ -2695,7 +2767,7 @@
*/
type = read_token(&token);
*tok = token;
- if (type != EVENT_ITEM)
+ if (type != TEP_EVENT_ITEM)
goto out_free;
/* Find the field */
@@ -2707,13 +2779,13 @@
arg->dynarray.field = field;
arg->dynarray.index = 0;
- if (read_expected(EVENT_DELIM, ")") < 0)
+ if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_free;
free_token(token);
type = read_token_item(&token);
*tok = token;
- if (type != EVENT_OP || strcmp(token, "[") != 0)
+ if (type != TEP_EVENT_OP || strcmp(token, "[") != 0)
return type;
free_token(token);
@@ -2721,14 +2793,14 @@
if (!arg) {
do_warning_event(event, "%s: not enough memory!", __func__);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
type = process_arg(event, arg, &token);
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
goto out_free_arg;
- if (!test_type_token(type, token, EVENT_OP, "]"))
+ if (!test_type_token(type, token, TEP_EVENT_OP, "]"))
goto out_free_arg;
free_token(token);
@@ -2740,21 +2812,21 @@
out_free:
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg,
char **tok)
{
- struct format_field *field;
- enum event_type type;
+ struct tep_format_field *field;
+ enum tep_event_type type;
char *token;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto out_free;
- arg->type = PRINT_DYNAMIC_ARRAY_LEN;
+ arg->type = TEP_PRINT_DYNAMIC_ARRAY_LEN;
/* Find the field */
field = tep_find_field(event, token);
@@ -2764,7 +2836,7 @@
arg->dynarray.field = field;
arg->dynarray.index = 0;
- if (read_expected(EVENT_DELIM, ")") < 0)
+ if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_err;
type = read_token(&token);
@@ -2776,28 +2848,28 @@
free_token(token);
out_err:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_paren(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_paren(struct tep_event *event, struct tep_print_arg *arg, char **tok)
{
- struct print_arg *item_arg;
- enum event_type type;
+ struct tep_print_arg *item_arg;
+ enum tep_event_type type;
char *token;
type = process_arg(event, arg, &token);
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
goto out_free;
- if (type == EVENT_OP)
+ if (type == TEP_EVENT_OP)
type = process_op(event, arg, &token);
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
goto out_free;
- if (test_type_token(type, token, EVENT_DELIM, ")"))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
goto out_free;
free_token(token);
@@ -2808,13 +2880,13 @@
* this was a typecast.
*/
if (event_item_type(type) ||
- (type == EVENT_DELIM && strcmp(token, "(") == 0)) {
+ (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0)) {
/* make this a typecast and contine */
/* prevous must be an atom */
- if (arg->type != PRINT_ATOM) {
- do_warning_event(event, "previous needed to be PRINT_ATOM");
+ if (arg->type != TEP_PRINT_ATOM) {
+ do_warning_event(event, "previous needed to be TEP_PRINT_ATOM");
goto out_free;
}
@@ -2825,7 +2897,7 @@
goto out_free;
}
- arg->type = PRINT_TYPE;
+ arg->type = TEP_PRINT_TYPE;
arg->typecast.type = arg->atom.atom;
arg->typecast.item = item_arg;
type = process_arg_token(event, item_arg, &token, type);
@@ -2838,25 +2910,25 @@
out_free:
free_token(token);
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
+static enum tep_event_type
+process_str(struct tep_event *event __maybe_unused, struct tep_print_arg *arg,
char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
char *token;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto out_free;
- arg->type = PRINT_STRING;
+ arg->type = TEP_PRINT_STRING;
arg->string.string = token;
arg->string.offset = -1;
- if (read_expected(EVENT_DELIM, ")") < 0)
+ if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_err;
type = read_token(&token);
@@ -2868,24 +2940,24 @@
free_token(token);
out_err:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
- char **tok)
+static enum tep_event_type
+process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *arg,
+ char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
char *token;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto out_free;
- arg->type = PRINT_BITMASK;
+ arg->type = TEP_PRINT_BITMASK;
arg->bitmask.bitmask = token;
arg->bitmask.offset = -1;
- if (read_expected(EVENT_DELIM, ")") < 0)
+ if (read_expected(TEP_EVENT_DELIM, ")") < 0)
goto out_err;
type = read_token(&token);
@@ -2897,18 +2969,18 @@
free_token(token);
out_err:
*tok = NULL;
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
static struct tep_function_handler *
-find_func_handler(struct tep_handle *pevent, char *func_name)
+find_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
- if (!pevent)
+ if (!tep)
return NULL;
- for (func = pevent->func_handlers; func; func = func->next) {
+ for (func = tep->func_handlers; func; func = func->next) {
if (strcmp(func->name, func_name) == 0)
break;
}
@@ -2916,12 +2988,12 @@
return func;
}
-static void remove_func_handler(struct tep_handle *pevent, char *func_name)
+static void remove_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
struct tep_function_handler **next;
- next = &pevent->func_handlers;
+ next = &tep->func_handlers;
while ((func = *next)) {
if (strcmp(func->name, func_name) == 0) {
*next = func->next;
@@ -2932,17 +3004,17 @@
}
}
-static enum event_type
-process_func_handler(struct event_format *event, struct tep_function_handler *func,
- struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_func_handler(struct tep_event *event, struct tep_function_handler *func,
+ struct tep_print_arg *arg, char **tok)
{
- struct print_arg **next_arg;
- struct print_arg *farg;
- enum event_type type;
+ struct tep_print_arg **next_arg;
+ struct tep_print_arg *farg;
+ enum tep_event_type type;
char *token;
int i;
- arg->type = PRINT_FUNC;
+ arg->type = TEP_PRINT_FUNC;
arg->func.func = func;
*tok = NULL;
@@ -2953,12 +3025,12 @@
if (!farg) {
do_warning_event(event, "%s: not enough memory!",
__func__);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
type = process_arg(event, farg, &token);
if (i < (func->nr_args - 1)) {
- if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+ if (type != TEP_EVENT_DELIM || strcmp(token, ",") != 0) {
do_warning_event(event,
"Error: function '%s()' expects %d arguments but event %s only uses %d",
func->name, func->nr_args,
@@ -2966,7 +3038,7 @@
goto err;
}
} else {
- if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+ if (type != TEP_EVENT_DELIM || strcmp(token, ")") != 0) {
do_warning_event(event,
"Error: function '%s()' only expects %d arguments but event %s has more",
func->name, func->nr_args, event->name);
@@ -2987,11 +3059,11 @@
err:
free_arg(farg);
free_token(token);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_function(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_function(struct tep_event *event, struct tep_print_arg *arg,
char *token, char **tok)
{
struct tep_function_handler *func;
@@ -3035,7 +3107,7 @@
return process_dynamic_array_len(event, arg, tok);
}
- func = find_func_handler(event->pevent, token);
+ func = find_func_handler(event->tep, token);
if (func) {
free_token(token);
return process_func_handler(event, func, arg, tok);
@@ -3043,12 +3115,12 @@
do_warning_event(event, "function %s not defined", token);
free_token(token);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
-static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
- char **tok, enum event_type type)
+static enum tep_event_type
+process_arg_token(struct tep_event *event, struct tep_print_arg *arg,
+ char **tok, enum tep_event_type type)
{
char *token;
char *atom;
@@ -3056,7 +3128,7 @@
token = *tok;
switch (type) {
- case EVENT_ITEM:
+ case TEP_EVENT_ITEM:
if (strcmp(token, "REC") == 0) {
free_token(token);
type = process_entry(event, arg, &token);
@@ -3070,7 +3142,7 @@
* If the next token is a parenthesis, then this
* is a function.
*/
- if (type == EVENT_DELIM && strcmp(token, "(") == 0) {
+ if (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0) {
free_token(token);
token = NULL;
/* this will free atom. */
@@ -3078,7 +3150,7 @@
break;
}
/* atoms can be more than one token long */
- while (type == EVENT_ITEM) {
+ while (type == TEP_EVENT_ITEM) {
char *new_atom;
new_atom = realloc(atom,
strlen(atom) + strlen(token) + 2);
@@ -3086,7 +3158,7 @@
free(atom);
*tok = NULL;
free_token(token);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
atom = new_atom;
strcat(atom, " ");
@@ -3095,55 +3167,55 @@
type = read_token_item(&token);
}
- arg->type = PRINT_ATOM;
+ arg->type = TEP_PRINT_ATOM;
arg->atom.atom = atom;
break;
- case EVENT_DQUOTE:
- case EVENT_SQUOTE:
- arg->type = PRINT_ATOM;
+ case TEP_EVENT_DQUOTE:
+ case TEP_EVENT_SQUOTE:
+ arg->type = TEP_PRINT_ATOM;
arg->atom.atom = token;
type = read_token_item(&token);
break;
- case EVENT_DELIM:
+ case TEP_EVENT_DELIM:
if (strcmp(token, "(") == 0) {
free_token(token);
type = process_paren(event, arg, &token);
break;
}
- case EVENT_OP:
+ case TEP_EVENT_OP:
/* handle single ops */
- arg->type = PRINT_OP;
+ arg->type = TEP_PRINT_OP;
arg->op.op = token;
arg->op.left = NULL;
type = process_op(event, arg, &token);
/* On error, the op is freed */
- if (type == EVENT_ERROR)
+ if (type == TEP_EVENT_ERROR)
arg->op.op = NULL;
/* return error type if errored */
break;
- case EVENT_ERROR ... EVENT_NEWLINE:
+ case TEP_EVENT_ERROR ... TEP_EVENT_NEWLINE:
default:
do_warning_event(event, "unexpected type %d", type);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
*tok = token;
return type;
}
-static int event_read_print_args(struct event_format *event, struct print_arg **list)
+static int event_read_print_args(struct tep_event *event, struct tep_print_arg **list)
{
- enum event_type type = EVENT_ERROR;
- struct print_arg *arg;
+ enum tep_event_type type = TEP_EVENT_ERROR;
+ struct tep_print_arg *arg;
char *token;
int args = 0;
do {
- if (type == EVENT_NEWLINE) {
+ if (type == TEP_EVENT_NEWLINE) {
type = read_token_item(&token);
continue;
}
@@ -3157,7 +3229,7 @@
type = process_arg(event, arg, &token);
- if (type == EVENT_ERROR) {
+ if (type == TEP_EVENT_ERROR) {
free_token(token);
free_arg(arg);
return -1;
@@ -3166,10 +3238,10 @@
*list = arg;
args++;
- if (type == EVENT_OP) {
+ if (type == TEP_EVENT_OP) {
type = process_op(event, arg, &token);
free_token(token);
- if (type == EVENT_ERROR) {
+ if (type == TEP_EVENT_ERROR) {
*list = NULL;
free_arg(arg);
return -1;
@@ -3178,37 +3250,37 @@
continue;
}
- if (type == EVENT_DELIM && strcmp(token, ",") == 0) {
+ if (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0) {
free_token(token);
*list = arg;
list = &arg->next;
continue;
}
break;
- } while (type != EVENT_NONE);
+ } while (type != TEP_EVENT_NONE);
- if (type != EVENT_NONE && type != EVENT_ERROR)
+ if (type != TEP_EVENT_NONE && type != TEP_EVENT_ERROR)
free_token(token);
return args;
}
-static int event_read_print(struct event_format *event)
+static int event_read_print(struct tep_event *event)
{
- enum event_type type;
+ enum tep_event_type type;
char *token;
int ret;
- if (read_expected_item(EVENT_ITEM, "print") < 0)
+ if (read_expected_item(TEP_EVENT_ITEM, "print") < 0)
return -1;
- if (read_expected(EVENT_ITEM, "fmt") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "fmt") < 0)
return -1;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return -1;
- if (read_expect_type(EVENT_DQUOTE, &token) < 0)
+ if (read_expect_type(TEP_EVENT_DQUOTE, &token) < 0)
goto fail;
concat:
@@ -3218,11 +3290,11 @@
/* ok to have no arg */
type = read_token_item(&token);
- if (type == EVENT_NONE)
+ if (type == TEP_EVENT_NONE)
return 0;
/* Handle concatenation of print lines */
- if (type == EVENT_DQUOTE) {
+ if (type == TEP_EVENT_DQUOTE) {
char *cat;
if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0)
@@ -3234,7 +3306,7 @@
goto concat;
}
- if (test_type_token(type, token, EVENT_DELIM, ","))
+ if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
goto fail;
free_token(token);
@@ -3256,12 +3328,12 @@
* @name: the name of the common field to return
*
* Returns a common field from the event by the given @name.
- * This only searchs the common fields and not all field.
+ * This only searches the common fields and not all field.
*/
-struct format_field *
-tep_find_common_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_common_field(struct tep_event *event, const char *name)
{
- struct format_field *format;
+ struct tep_format_field *format;
for (format = event->format.common_fields;
format; format = format->next) {
@@ -3280,10 +3352,10 @@
* Returns a non-common field by the given @name.
* This does not search common fields.
*/
-struct format_field *
-tep_find_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_field(struct tep_event *event, const char *name)
{
- struct format_field *format;
+ struct tep_format_field *format;
for (format = event->format.fields;
format; format = format->next) {
@@ -3300,13 +3372,13 @@
* @name: the name of the field
*
* Returns a field by the given @name.
- * This searchs the common field names first, then
+ * This searches the common field names first, then
* the non-common ones if a common one was not found.
*/
-struct format_field *
-tep_find_any_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_any_field(struct tep_event *event, const char *name)
{
- struct format_field *format;
+ struct tep_format_field *format;
format = tep_find_common_field(event, name);
if (format)
@@ -3316,25 +3388,28 @@
/**
* tep_read_number - read a number from data
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @ptr: the raw data
* @size: the size of the data that holds the number
*
* Returns the number (converted to host) from the
* raw data.
*/
-unsigned long long tep_read_number(struct tep_handle *pevent,
+unsigned long long tep_read_number(struct tep_handle *tep,
const void *ptr, int size)
{
+ unsigned long long val;
+
switch (size) {
case 1:
return *(unsigned char *)ptr;
case 2:
- return data2host2(pevent, ptr);
+ return tep_data2host2(tep, *(unsigned short *)ptr);
case 4:
- return data2host4(pevent, ptr);
+ return tep_data2host4(tep, *(unsigned int *)ptr);
case 8:
- return data2host8(pevent, ptr);
+ memcpy(&val, (ptr), sizeof(unsigned long long));
+ return tep_data2host8(tep, val);
default:
/* BUG! */
return 0;
@@ -3352,7 +3427,7 @@
*
* Returns 0 on success, -1 otherwise.
*/
-int tep_read_number_field(struct format_field *field, const void *data,
+int tep_read_number_field(struct tep_format_field *field, const void *data,
unsigned long long *value)
{
if (!field)
@@ -3362,7 +3437,7 @@
case 2:
case 4:
case 8:
- *value = tep_read_number(field->event->pevent,
+ *value = tep_read_number(field->event->tep,
data + field->offset, field->size);
return 0;
default:
@@ -3370,22 +3445,22 @@
}
}
-static int get_common_info(struct tep_handle *pevent,
+static int get_common_info(struct tep_handle *tep,
const char *type, int *offset, int *size)
{
- struct event_format *event;
- struct format_field *field;
+ struct tep_event *event;
+ struct tep_format_field *field;
/*
* All events should have the same common elements.
* Pick any event to find where the type is;
*/
- if (!pevent->events) {
+ if (!tep->events) {
do_warning("no event_list!");
return -1;
}
- event = pevent->events[0];
+ event = tep->events[0];
field = tep_find_common_field(event, type);
if (!field)
return -1;
@@ -3396,58 +3471,58 @@
return 0;
}
-static int __parse_common(struct tep_handle *pevent, void *data,
+static int __parse_common(struct tep_handle *tep, void *data,
int *size, int *offset, const char *name)
{
int ret;
if (!*size) {
- ret = get_common_info(pevent, name, offset, size);
+ ret = get_common_info(tep, name, offset, size);
if (ret < 0)
return ret;
}
- return tep_read_number(pevent, data + *offset, *size);
+ return tep_read_number(tep, data + *offset, *size);
}
-static int trace_parse_common_type(struct tep_handle *pevent, void *data)
+static int trace_parse_common_type(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->type_size, &pevent->type_offset,
+ return __parse_common(tep, data,
+ &tep->type_size, &tep->type_offset,
"common_type");
}
-static int parse_common_pid(struct tep_handle *pevent, void *data)
+static int parse_common_pid(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pid_size, &pevent->pid_offset,
+ return __parse_common(tep, data,
+ &tep->pid_size, &tep->pid_offset,
"common_pid");
}
-static int parse_common_pc(struct tep_handle *pevent, void *data)
+static int parse_common_pc(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pc_size, &pevent->pc_offset,
+ return __parse_common(tep, data,
+ &tep->pc_size, &tep->pc_offset,
"common_preempt_count");
}
-static int parse_common_flags(struct tep_handle *pevent, void *data)
+static int parse_common_flags(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->flags_size, &pevent->flags_offset,
+ return __parse_common(tep, data,
+ &tep->flags_size, &tep->flags_offset,
"common_flags");
}
-static int parse_common_lock_depth(struct tep_handle *pevent, void *data)
+static int parse_common_lock_depth(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_lock_depth");
}
-static int parse_common_migrate_disable(struct tep_handle *pevent, void *data)
+static int parse_common_migrate_disable(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_migrate_disable");
}
@@ -3455,28 +3530,28 @@
/**
* tep_find_event - find an event by given id
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event
*
* Returns an event that has a given @id.
*/
-struct event_format *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event *tep_find_event(struct tep_handle *tep, int id)
{
- struct event_format **eventptr;
- struct event_format key;
- struct event_format *pkey = &key;
+ struct tep_event **eventptr;
+ struct tep_event key;
+ struct tep_event *pkey = &key;
/* Check cache first */
- if (pevent->last_event && pevent->last_event->id == id)
- return pevent->last_event;
+ if (tep->last_event && tep->last_event->id == id)
+ return tep->last_event;
key.id = id;
- eventptr = bsearch(&pkey, pevent->events, pevent->nr_events,
- sizeof(*pevent->events), events_id_cmp);
+ eventptr = bsearch(&pkey, tep->events, tep->nr_events,
+ sizeof(*tep->events), events_id_cmp);
if (eventptr) {
- pevent->last_event = *eventptr;
+ tep->last_event = *eventptr;
return *eventptr;
}
@@ -3485,27 +3560,27 @@
/**
* tep_find_event_by_name - find an event by given name
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @sys: the system name to search for
* @name: the name of the event to search for
*
* This returns an event with a given @name and under the system
* @sys. If @sys is NULL the first event with @name is returned.
*/
-struct event_format *
-tep_find_event_by_name(struct tep_handle *pevent,
+struct tep_event *
+tep_find_event_by_name(struct tep_handle *tep,
const char *sys, const char *name)
{
- struct event_format *event;
+ struct tep_event *event = NULL;
int i;
- if (pevent->last_event &&
- strcmp(pevent->last_event->name, name) == 0 &&
- (!sys || strcmp(pevent->last_event->system, sys) == 0))
- return pevent->last_event;
+ if (tep->last_event &&
+ strcmp(tep->last_event->name, name) == 0 &&
+ (!sys || strcmp(tep->last_event->system, sys) == 0))
+ return tep->last_event;
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (strcmp(event->name, name) == 0) {
if (!sys)
break;
@@ -3513,31 +3588,31 @@
break;
}
}
- if (i == pevent->nr_events)
+ if (i == tep->nr_events)
event = NULL;
- pevent->last_event = event;
+ tep->last_event = event;
return event;
}
static unsigned long long
-eval_num_arg(void *data, int size, struct event_format *event, struct print_arg *arg)
+eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long val = 0;
unsigned long long left, right;
- struct print_arg *typearg = NULL;
- struct print_arg *larg;
+ struct tep_print_arg *typearg = NULL;
+ struct tep_print_arg *larg;
unsigned long offset;
unsigned int field_size;
switch (arg->type) {
- case PRINT_NULL:
+ case TEP_PRINT_NULL:
/* ?? */
return 0;
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
return strtoull(arg->atom.atom, NULL, 0);
- case PRINT_FIELD:
+ case TEP_PRINT_FIELD:
if (!arg->field.field) {
arg->field.field = tep_find_any_field(event, arg->field.name);
if (!arg->field.field)
@@ -3545,30 +3620,30 @@
}
/* must be a number */
- val = tep_read_number(pevent, data + arg->field.field->offset,
+ val = tep_read_number(tep, data + arg->field.field->offset,
arg->field.field->size);
break;
- case PRINT_FLAGS:
- case PRINT_SYMBOL:
- case PRINT_INT_ARRAY:
- case PRINT_HEX:
- case PRINT_HEX_STR:
+ case TEP_PRINT_FLAGS:
+ case TEP_PRINT_SYMBOL:
+ case TEP_PRINT_INT_ARRAY:
+ case TEP_PRINT_HEX:
+ case TEP_PRINT_HEX_STR:
break;
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
val = eval_num_arg(data, size, event, arg->typecast.item);
return eval_type(val, arg, 0);
- case PRINT_STRING:
- case PRINT_BSTRING:
- case PRINT_BITMASK:
+ case TEP_PRINT_STRING:
+ case TEP_PRINT_BSTRING:
+ case TEP_PRINT_BITMASK:
return 0;
- case PRINT_FUNC: {
+ case TEP_PRINT_FUNC: {
struct trace_seq s;
trace_seq_init(&s);
val = process_defined_func(&s, data, size, event, arg);
trace_seq_destroy(&s);
return val;
}
- case PRINT_OP:
+ case TEP_PRINT_OP:
if (strcmp(arg->op.op, "[") == 0) {
/*
* Arrays are special, since we don't want
@@ -3578,18 +3653,18 @@
/* handle typecasts */
larg = arg->op.left;
- while (larg->type == PRINT_TYPE) {
+ while (larg->type == TEP_PRINT_TYPE) {
if (!typearg)
typearg = larg;
larg = larg->typecast.item;
}
/* Default to long size */
- field_size = pevent->long_size;
+ field_size = tep->long_size;
switch (larg->type) {
- case PRINT_DYNAMIC_ARRAY:
- offset = tep_read_number(pevent,
+ case TEP_PRINT_DYNAMIC_ARRAY:
+ offset = tep_read_number(tep,
data + larg->dynarray.field->offset,
larg->dynarray.field->size);
if (larg->dynarray.field->elementsize)
@@ -3602,7 +3677,7 @@
offset &= 0xffff;
offset += right;
break;
- case PRINT_FIELD:
+ case TEP_PRINT_FIELD:
if (!larg->field.field) {
larg->field.field =
tep_find_any_field(event, larg->field.name);
@@ -3618,7 +3693,7 @@
default:
goto default_op; /* oops, all bets off */
}
- val = tep_read_number(pevent,
+ val = tep_read_number(tep,
data + offset, field_size);
if (typearg)
val = eval_type(val, typearg, 1);
@@ -3718,8 +3793,8 @@
goto out_warning_op;
}
break;
- case PRINT_DYNAMIC_ARRAY_LEN:
- offset = tep_read_number(pevent,
+ case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
@@ -3729,9 +3804,9 @@
*/
val = (unsigned long long)(offset >> 16);
break;
- case PRINT_DYNAMIC_ARRAY:
+ case TEP_PRINT_DYNAMIC_ARRAY:
/* Without [], we pass the address to the dynamic data */
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
@@ -3806,7 +3881,7 @@
trace_seq_printf(s, format, str);
}
-static void print_bitmask_to_seq(struct tep_handle *pevent,
+static void print_bitmask_to_seq(struct tep_handle *tep,
struct trace_seq *s, const char *format,
int len_arg, const void *data, int size)
{
@@ -3836,9 +3911,9 @@
/*
* data points to a bit mask of size bytes.
* In the kernel, this is an array of long words, thus
- * endianess is very important.
+ * endianness is very important.
*/
- if (pevent->file_bigendian)
+ if (tep->file_bigendian)
index = size - (len + 1);
else
index = len;
@@ -3861,12 +3936,12 @@
}
static void print_str_arg(struct trace_seq *s, void *data, int size,
- struct event_format *event, const char *format,
- int len_arg, struct print_arg *arg)
+ struct tep_event *event, const char *format,
+ int len_arg, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
- struct print_flag_sym *flag;
- struct format_field *field;
+ struct tep_handle *tep = event->tep;
+ struct tep_print_flag_sym *flag;
+ struct tep_format_field *field;
struct printk_map *printk;
long long val, fval;
unsigned long long addr;
@@ -3876,13 +3951,13 @@
int i, len;
switch (arg->type) {
- case PRINT_NULL:
+ case TEP_PRINT_NULL:
/* ?? */
return;
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
print_str_to_seq(s, format, len_arg, arg->atom.atom);
return;
- case PRINT_FIELD:
+ case TEP_PRINT_FIELD:
field = arg->field.field;
if (!field) {
field = tep_find_any_field(event, arg->field.name);
@@ -3900,8 +3975,8 @@
* and the size is the same as long_size, assume that it
* is a pointer.
*/
- if (!(field->flags & FIELD_IS_ARRAY) &&
- field->size == pevent->long_size) {
+ if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
+ field->size == tep->long_size) {
/* Handle heterogeneous recording and processing
* architectures
@@ -3916,12 +3991,12 @@
* on 32-bit devices:
* In this case, 64 bits must be read.
*/
- addr = (pevent->long_size == 8) ?
+ addr = (tep->long_size == 8) ?
*(unsigned long long *)(data + field->offset) :
(unsigned long long)*(unsigned int *)(data + field->offset);
/* Check if it matches a print format */
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (printk)
trace_seq_puts(s, printk->printk);
else
@@ -3939,7 +4014,7 @@
print_str_to_seq(s, format, len_arg, str);
free(str);
break;
- case PRINT_FLAGS:
+ case TEP_PRINT_FLAGS:
val = eval_num_arg(data, size, event, arg->flags.field);
print = 0;
for (flag = arg->flags.flags; flag; flag = flag->next) {
@@ -3962,7 +4037,7 @@
trace_seq_printf(s, "0x%llx", val);
}
break;
- case PRINT_SYMBOL:
+ case TEP_PRINT_SYMBOL:
val = eval_num_arg(data, size, event, arg->symbol.field);
for (flag = arg->symbol.symbols; flag; flag = flag->next) {
fval = eval_flag(flag->value);
@@ -3974,11 +4049,11 @@
if (!flag)
trace_seq_printf(s, "0x%llx", val);
break;
- case PRINT_HEX:
- case PRINT_HEX_STR:
- if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
+ case TEP_PRINT_HEX:
+ case TEP_PRINT_HEX_STR:
+ if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
unsigned long offset;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->hex.field->dynarray.field->offset,
arg->hex.field->dynarray.field->size);
hex = data + (offset & 0xffff);
@@ -3995,21 +4070,21 @@
}
len = eval_num_arg(data, size, event, arg->hex.size);
for (i = 0; i < len; i++) {
- if (i && arg->type == PRINT_HEX)
+ if (i && arg->type == TEP_PRINT_HEX)
trace_seq_putc(s, ' ');
trace_seq_printf(s, "%02x", hex[i]);
}
break;
- case PRINT_INT_ARRAY: {
+ case TEP_PRINT_INT_ARRAY: {
void *num;
int el_size;
- if (arg->int_array.field->type == PRINT_DYNAMIC_ARRAY) {
+ if (arg->int_array.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
unsigned long offset;
- struct format_field *field =
+ struct tep_format_field *field =
arg->int_array.field->dynarray.field;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + field->offset,
field->size);
num = data + (offset & 0xffff);
@@ -4049,43 +4124,43 @@
}
break;
}
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
break;
- case PRINT_STRING: {
+ case TEP_PRINT_STRING: {
int str_offset;
if (arg->string.offset == -1) {
- struct format_field *f;
+ struct tep_format_field *f;
f = tep_find_any_field(event, arg->string.string);
arg->string.offset = f->offset;
}
- str_offset = data2host4(pevent, data + arg->string.offset);
+ str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset));
str_offset &= 0xffff;
print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
break;
}
- case PRINT_BSTRING:
+ case TEP_PRINT_BSTRING:
print_str_to_seq(s, format, len_arg, arg->string.string);
break;
- case PRINT_BITMASK: {
+ case TEP_PRINT_BITMASK: {
int bitmask_offset;
int bitmask_size;
if (arg->bitmask.offset == -1) {
- struct format_field *f;
+ struct tep_format_field *f;
f = tep_find_any_field(event, arg->bitmask.bitmask);
arg->bitmask.offset = f->offset;
}
- bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+ bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
bitmask_size = bitmask_offset >> 16;
bitmask_offset &= 0xffff;
- print_bitmask_to_seq(pevent, s, format, len_arg,
+ print_bitmask_to_seq(tep, s, format, len_arg,
data + bitmask_offset, bitmask_size);
break;
}
- case PRINT_OP:
+ case TEP_PRINT_OP:
/*
* The only op for string should be ? :
*/
@@ -4099,7 +4174,7 @@
print_str_arg(s, data, size, event,
format, len_arg, arg->op.right->op.right);
break;
- case PRINT_FUNC:
+ case TEP_PRINT_FUNC:
process_defined_func(s, data, size, event, arg);
break;
default:
@@ -4116,13 +4191,13 @@
static unsigned long long
process_defined_func(struct trace_seq *s, void *data, int size,
- struct event_format *event, struct print_arg *arg)
+ struct tep_event *event, struct tep_print_arg *arg)
{
struct tep_function_handler *func_handle = arg->func.func;
struct func_params *param;
unsigned long long *args;
unsigned long long ret;
- struct print_arg *farg;
+ struct tep_print_arg *farg;
struct trace_seq str;
struct save_str {
struct save_str *next;
@@ -4199,9 +4274,9 @@
return ret;
}
-static void free_args(struct print_arg *args)
+static void free_args(struct tep_print_arg *args)
{
- struct print_arg *next;
+ struct tep_print_arg *next;
while (args) {
next = args->next;
@@ -4211,18 +4286,18 @@
}
}
-static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event_format *event)
+static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
- struct format_field *field, *ip_field;
- struct print_arg *args, *arg, **next;
+ struct tep_handle *tep = event->tep;
+ struct tep_format_field *field, *ip_field;
+ struct tep_print_arg *args, *arg, **next;
unsigned long long ip, val;
char *ptr;
void *bptr;
- int vsize;
+ int vsize = 0;
- field = pevent->bprint_buf_field;
- ip_field = pevent->bprint_ip_field;
+ field = tep->bprint_buf_field;
+ ip_field = tep->bprint_ip_field;
if (!field) {
field = tep_find_field(event, "buf");
@@ -4235,11 +4310,11 @@
do_warning_event(event, "can't find ip field for binary printk");
return NULL;
}
- pevent->bprint_buf_field = field;
- pevent->bprint_ip_field = ip_field;
+ tep->bprint_buf_field = field;
+ tep->bprint_ip_field = ip_field;
}
- ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size);
+ ip = tep_read_number(tep, data + ip_field->offset, ip_field->size);
/*
* The first arg is the IP pointer.
@@ -4254,7 +4329,7 @@
arg->next = NULL;
next = &arg->next;
- arg->type = PRINT_ATOM;
+ arg->type = TEP_PRINT_ATOM;
if (asprintf(&arg->atom.atom, "%lld", ip) < 0)
goto out_free;
@@ -4292,9 +4367,20 @@
switch (*ptr) {
case 's':
case 'S':
+ case 'x':
+ break;
case 'f':
case 'F':
- break;
+ /*
+ * Pre-5.5 kernels use %pf and
+ * %pF for printing symbols
+ * while kernels since 5.5 use
+ * %pfw for fwnodes. So check
+ * %p[fF] isn't followed by 'w'.
+ */
+ if (ptr[1] != 'w')
+ break;
+ /* fall through */
default:
/*
* Older kernels do not process
@@ -4316,7 +4402,7 @@
vsize = 4;
break;
case 1:
- vsize = pevent->long_size;
+ vsize = tep->long_size;
break;
case 2:
vsize = 8;
@@ -4333,7 +4419,7 @@
/* the pointers are always 4 bytes aligned */
bptr = (void *)(((unsigned long)bptr + 3) &
~3);
- val = tep_read_number(pevent, bptr, vsize);
+ val = tep_read_number(tep, bptr, vsize);
bptr += vsize;
arg = alloc_arg();
if (!arg) {
@@ -4342,7 +4428,7 @@
goto out_free;
}
arg->next = NULL;
- arg->type = PRINT_ATOM;
+ arg->type = TEP_PRINT_ATOM;
if (asprintf(&arg->atom.atom, "%lld", val) < 0) {
free(arg);
goto out_free;
@@ -4366,7 +4452,7 @@
goto out_free;
}
arg->next = NULL;
- arg->type = PRINT_BSTRING;
+ arg->type = TEP_PRINT_BSTRING;
arg->string.string = strdup(bptr);
if (!arg->string.string)
goto out_free;
@@ -4388,15 +4474,15 @@
static char *
get_bprint_format(void *data, int size __maybe_unused,
- struct event_format *event)
+ struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long addr;
- struct format_field *field;
+ struct tep_format_field *field;
struct printk_map *printk;
char *format;
- field = pevent->bprint_fmt_field;
+ field = tep->bprint_fmt_field;
if (!field) {
field = tep_find_field(event, "fmt");
@@ -4404,36 +4490,36 @@
do_warning_event(event, "can't find format field for binary printk");
return NULL;
}
- pevent->bprint_fmt_field = field;
+ tep->bprint_fmt_field = field;
}
- addr = tep_read_number(pevent, data + field->offset, field->size);
+ addr = tep_read_number(tep, data + field->offset, field->size);
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (!printk) {
- if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
+ if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0)
return NULL;
return format;
}
- if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0)
+ if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0)
return NULL;
return format;
}
static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
- struct event_format *event, struct print_arg *arg)
+ struct tep_event *event, struct tep_print_arg *arg)
{
unsigned char *buf;
const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
- if (arg->type == PRINT_FUNC) {
+ if (arg->type == TEP_PRINT_FUNC) {
process_defined_func(s, data, size, event, arg);
return;
}
- if (arg->type != PRINT_FIELD) {
+ if (arg->type != TEP_PRINT_FIELD) {
trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d",
arg->type);
return;
@@ -4576,17 +4662,17 @@
* %pISpc print an IP address based on sockaddr; p adds port.
*/
static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
- void *data, int size, struct event_format *event,
- struct print_arg *arg)
+ void *data, int size, struct tep_event *event,
+ struct tep_print_arg *arg)
{
unsigned char *buf;
- if (arg->type == PRINT_FUNC) {
+ if (arg->type == TEP_PRINT_FUNC) {
process_defined_func(s, data, size, event, arg);
return 0;
}
- if (arg->type != PRINT_FIELD) {
+ if (arg->type != TEP_PRINT_FIELD) {
trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
return 0;
}
@@ -4613,8 +4699,8 @@
}
static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
- void *data, int size, struct event_format *event,
- struct print_arg *arg)
+ void *data, int size, struct tep_event *event,
+ struct tep_print_arg *arg)
{
char have_c = 0;
unsigned char *buf;
@@ -4627,12 +4713,12 @@
rc++;
}
- if (arg->type == PRINT_FUNC) {
+ if (arg->type == TEP_PRINT_FUNC) {
process_defined_func(s, data, size, event, arg);
return rc;
}
- if (arg->type != PRINT_FIELD) {
+ if (arg->type != TEP_PRINT_FIELD) {
trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
return rc;
}
@@ -4663,8 +4749,8 @@
}
static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
- void *data, int size, struct event_format *event,
- struct print_arg *arg)
+ void *data, int size, struct tep_event *event,
+ struct tep_print_arg *arg)
{
char have_c = 0, have_p = 0;
unsigned char *buf;
@@ -4685,12 +4771,12 @@
}
}
- if (arg->type == PRINT_FUNC) {
+ if (arg->type == TEP_PRINT_FUNC) {
process_defined_func(s, data, size, event, arg);
return rc;
}
- if (arg->type != PRINT_FIELD) {
+ if (arg->type != TEP_PRINT_FIELD) {
trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
return rc;
}
@@ -4745,8 +4831,8 @@
}
static int print_ip_arg(struct trace_seq *s, const char *ptr,
- void *data, int size, struct event_format *event,
- struct print_arg *arg)
+ void *data, int size, struct tep_event *event,
+ struct tep_print_arg *arg)
{
char i = *ptr; /* 'i' or 'I' */
char ver;
@@ -4787,22 +4873,22 @@
}
void tep_print_field(struct trace_seq *s, void *data,
- struct format_field *field)
+ struct tep_format_field *field)
{
unsigned long long val;
unsigned int offset, len, i;
- struct tep_handle *pevent = field->event->pevent;
+ struct tep_handle *tep = field->event->tep;
- if (field->flags & FIELD_IS_ARRAY) {
+ if (field->flags & TEP_FIELD_IS_ARRAY) {
offset = field->offset;
len = field->size;
- if (field->flags & FIELD_IS_DYNAMIC) {
- val = tep_read_number(pevent, data + offset, len);
+ if (field->flags & TEP_FIELD_IS_DYNAMIC) {
+ val = tep_read_number(tep, data + offset, len);
offset = val;
len = offset >> 16;
offset &= 0xffff;
}
- if (field->flags & FIELD_IS_STRING &&
+ if (field->flags & TEP_FIELD_IS_STRING &&
is_printable_array(data + offset, len)) {
trace_seq_printf(s, "%s", (char *)data + offset);
} else {
@@ -4814,21 +4900,21 @@
*((unsigned char *)data + offset + i));
}
trace_seq_putc(s, ']');
- field->flags &= ~FIELD_IS_STRING;
+ field->flags &= ~TEP_FIELD_IS_STRING;
}
} else {
- val = tep_read_number(pevent, data + field->offset,
+ val = tep_read_number(tep, data + field->offset,
field->size);
- if (field->flags & FIELD_IS_POINTER) {
+ if (field->flags & TEP_FIELD_IS_POINTER) {
trace_seq_printf(s, "0x%llx", val);
- } else if (field->flags & FIELD_IS_SIGNED) {
+ } else if (field->flags & TEP_FIELD_IS_SIGNED) {
switch (field->size) {
case 4:
/*
* If field is long then print it in hex.
* A long usually stores pointers.
*/
- if (field->flags & FIELD_IS_LONG)
+ if (field->flags & TEP_FIELD_IS_LONG)
trace_seq_printf(s, "0x%x", (int)val);
else
trace_seq_printf(s, "%d", (int)val);
@@ -4843,7 +4929,7 @@
trace_seq_printf(s, "%lld", val);
}
} else {
- if (field->flags & FIELD_IS_LONG)
+ if (field->flags & TEP_FIELD_IS_LONG)
trace_seq_printf(s, "0x%llx", val);
else
trace_seq_printf(s, "%llu", val);
@@ -4852,9 +4938,9 @@
}
void tep_print_fields(struct trace_seq *s, void *data,
- int size __maybe_unused, struct event_format *event)
+ int size __maybe_unused, struct tep_event *event)
{
- struct format_field *field;
+ struct tep_format_field *field;
field = event->format.fields;
while (field) {
@@ -4864,12 +4950,12 @@
}
}
-static void pretty_print(struct trace_seq *s, void *data, int size, struct event_format *event)
+static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
- struct print_fmt *print_fmt = &event->print_fmt;
- struct print_arg *arg = print_fmt->args;
- struct print_arg *args = NULL;
+ struct tep_handle *tep = event->tep;
+ struct tep_print_fmt *print_fmt = &event->print_fmt;
+ struct tep_print_arg *arg = print_fmt->args;
+ struct tep_print_arg *args = NULL;
const char *ptr = print_fmt->format;
unsigned long long val;
struct func_map *func;
@@ -4879,17 +4965,17 @@
char format[32];
int show_func;
int len_as_arg;
- int len_arg;
+ int len_arg = 0;
int len;
int ls;
- if (event->flags & EVENT_FL_FAILED) {
+ if (event->flags & TEP_EVENT_FL_FAILED) {
trace_seq_printf(s, "[FAILED TO PARSE]");
tep_print_fields(s, data, size, event);
return;
}
- if (event->flags & EVENT_FL_ISBPRINT) {
+ if (event->flags & TEP_EVENT_FL_ISBPRINT) {
bprint_fmt = get_bprint_format(data, size, event);
args = make_bprint_args(bprint_fmt, data, size, event);
arg = args;
@@ -4944,7 +5030,7 @@
/* The argument is the length. */
if (!arg) {
do_warning_event(event, "no argument match");
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
goto out_failed;
}
len_arg = eval_num_arg(data, size, event, arg);
@@ -4958,7 +5044,7 @@
case '-':
goto cont_process;
case 'p':
- if (pevent->long_size == 4)
+ if (tep->long_size == 4)
ls = 1;
else
ls = 2;
@@ -4966,8 +5052,9 @@
if (isalnum(ptr[1]))
ptr++;
- if (arg->type == PRINT_BSTRING) {
+ if (arg->type == TEP_PRINT_BSTRING) {
trace_seq_puts(s, arg->string.string);
+ arg = arg->next;
break;
}
@@ -4997,7 +5084,7 @@
case 'u':
if (!arg) {
do_warning_event(event, "no argument match");
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
goto out_failed;
}
@@ -5007,7 +5094,7 @@
/* should never happen */
if (len > 31) {
do_warning_event(event, "bad format!");
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
len = 31;
}
@@ -5018,7 +5105,7 @@
arg = arg->next;
if (show_func) {
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func) {
trace_seq_puts(s, func->func);
if (show_func == 'F')
@@ -5028,7 +5115,7 @@
break;
}
}
- if (pevent->long_size == 8 && ls == 1 &&
+ if (tep->long_size == 8 && ls == 1 &&
sizeof(long) != 8) {
char *p;
@@ -5073,13 +5160,13 @@
break;
default:
do_warning_event(event, "bad count (%d)", ls);
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
}
break;
case 's':
if (!arg) {
do_warning_event(event, "no matching argument");
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
goto out_failed;
}
@@ -5089,7 +5176,7 @@
/* should never happen */
if (len > 31) {
do_warning_event(event, "bad format!");
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
len = 31;
}
@@ -5114,7 +5201,7 @@
trace_seq_putc(s, *ptr);
}
- if (event->flags & EVENT_FL_FAILED) {
+ if (event->flags & TEP_EVENT_FL_FAILED) {
out_failed:
trace_seq_printf(s, "[FAILED TO PARSE]");
}
@@ -5125,38 +5212,35 @@
}
}
-/**
- * tep_data_lat_fmt - parse the data for the latency format
- * @pevent: a handle to the pevent
- * @s: the trace_seq to write to
- * @record: the record to read from
- *
+/*
* This parses out the Latency format (interrupts disabled,
* need rescheduling, in hard/soft interrupt, preempt count
* and lock depth) and places it into the trace_seq.
*/
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record)
+static void data_latency_format(struct tep_handle *tep, struct trace_seq *s,
+ char *format, struct tep_record *record)
{
static int check_lock_depth = 1;
static int check_migrate_disable = 1;
static int lock_depth_exists;
static int migrate_disable_exists;
unsigned int lat_flags;
+ struct trace_seq sq;
unsigned int pc;
- int lock_depth;
- int migrate_disable;
+ int lock_depth = 0;
+ int migrate_disable = 0;
int hardirq;
int softirq;
void *data = record->data;
- lat_flags = parse_common_flags(pevent, data);
- pc = parse_common_pc(pevent, data);
+ trace_seq_init(&sq);
+ lat_flags = parse_common_flags(tep, data);
+ pc = parse_common_pc(tep, data);
/* lock_depth may not always exist */
if (lock_depth_exists)
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
else if (check_lock_depth) {
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
if (lock_depth < 0)
check_lock_depth = 0;
else
@@ -5165,9 +5249,9 @@
/* migrate_disable may not always exist */
if (migrate_disable_exists)
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
else if (check_migrate_disable) {
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
if (migrate_disable < 0)
check_migrate_disable = 0;
else
@@ -5177,7 +5261,7 @@
hardirq = lat_flags & TRACE_FLAG_HARDIRQ;
softirq = lat_flags & TRACE_FLAG_SOFTIRQ;
- trace_seq_printf(s, "%c%c%c",
+ trace_seq_printf(&sq, "%c%c%c",
(lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
(lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
'X' : '.',
@@ -5187,162 +5271,158 @@
hardirq ? 'h' : softirq ? 's' : '.');
if (pc)
- trace_seq_printf(s, "%x", pc);
+ trace_seq_printf(&sq, "%x", pc);
else
- trace_seq_putc(s, '.');
+ trace_seq_printf(&sq, ".");
if (migrate_disable_exists) {
if (migrate_disable < 0)
- trace_seq_putc(s, '.');
+ trace_seq_printf(&sq, ".");
else
- trace_seq_printf(s, "%d", migrate_disable);
+ trace_seq_printf(&sq, "%d", migrate_disable);
}
if (lock_depth_exists) {
if (lock_depth < 0)
- trace_seq_putc(s, '.');
+ trace_seq_printf(&sq, ".");
else
- trace_seq_printf(s, "%d", lock_depth);
+ trace_seq_printf(&sq, "%d", lock_depth);
}
+ if (sq.state == TRACE_SEQ__MEM_ALLOC_FAILED) {
+ s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
+ return;
+ }
+
+ trace_seq_terminate(&sq);
+ trace_seq_puts(s, sq.buffer);
+ trace_seq_destroy(&sq);
trace_seq_terminate(s);
}
/**
* tep_data_type - parse out the given event type
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to read from
*
* This returns the event id from the @rec.
*/
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec)
{
- return trace_parse_common_type(pevent, rec->data);
-}
-
-/**
- * tep_data_event_from_type - find the event by a given type
- * @pevent: a handle to the pevent
- * @type: the type of the event.
- *
- * This returns the event form a given @type;
- */
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type)
-{
- return tep_find_event(pevent, type);
+ return trace_parse_common_type(tep, rec->data);
}
/**
* tep_data_pid - parse the PID from record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the PID from a record.
*/
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pid(pevent, rec->data);
+ return parse_common_pid(tep, rec->data);
}
/**
* tep_data_preempt_count - parse the preempt count from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the preempt count from a record.
*/
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pc(pevent, rec->data);
+ return parse_common_pc(tep, rec->data);
}
/**
* tep_data_flags - parse the latency flags from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the latency flags from a record.
*
* Use trace_flag_type enum for the flags (see event-parse.h).
*/
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_flags(pevent, rec->data);
+ return parse_common_flags(tep, rec->data);
}
/**
* tep_data_comm_from_pid - return the command line from PID
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @pid: the PID of the task to search for
*
* This returns a pointer to the command line that has the given
* @pid.
*/
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid)
{
const char *comm;
- comm = find_cmdline(pevent, pid);
+ comm = find_cmdline(tep, pid);
return comm;
}
-static struct cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *next)
+static struct tep_cmdline *
+pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)next;
if (cmdlist)
cmdlist = cmdlist->next;
else
- cmdlist = pevent->cmdlist;
+ cmdlist = tep->cmdlist;
while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
cmdlist = cmdlist->next;
- return (struct cmdline *)cmdlist;
+ return (struct tep_cmdline *)cmdlist;
}
/**
* tep_data_pid_from_comm - return the pid from a given comm
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the cmdline to find the pid from
* @next: the cmdline structure to find the next comm
*
* This returns the cmdline structure that holds a pid for a given
* comm, or NULL if none found. As there may be more than one pid for
* a given comm, the result of this call can be passed back into
- * a recurring call in the @next paramater, and then it will find the
+ * a recurring call in the @next parameter, and then it will find the
* next pid.
- * Also, it does a linear seach, so it may be slow.
+ * Also, it does a linear search, so it may be slow.
*/
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
- struct cmdline *next)
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
+ struct tep_cmdline *next)
{
- struct cmdline *cmdline;
+ struct tep_cmdline *cmdline;
/*
* If the cmdlines have not been converted yet, then use
* the list.
*/
- if (!pevent->cmdlines)
- return pid_from_cmdlist(pevent, comm, next);
+ if (!tep->cmdlines)
+ return pid_from_cmdlist(tep, comm, next);
if (next) {
/*
* The next pointer could have been still from
* a previous call before cmdlines were created
*/
- if (next < pevent->cmdlines ||
- next >= pevent->cmdlines + pevent->cmdline_count)
+ if (next < tep->cmdlines ||
+ next >= tep->cmdlines + tep->cmdline_count)
next = NULL;
else
cmdline = next++;
}
if (!next)
- cmdline = pevent->cmdlines;
+ cmdline = tep->cmdlines;
- while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+ while (cmdline < tep->cmdlines + tep->cmdline_count) {
if (strcmp(cmdline->comm, comm) == 0)
return cmdline;
cmdline++;
@@ -5352,12 +5432,13 @@
/**
* tep_cmdline_pid - return the pid associated to a given cmdline
+ * @tep: a handle to the trace event parser context
* @cmdline: The cmdline structure to get the pid from
*
* Returns the pid for a give cmdline. If @cmdline is NULL, then
* -1 is returned.
*/
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
@@ -5368,33 +5449,28 @@
* If cmdlines have not been created yet, or cmdline is
* not part of the array, then treat it as a cmdlist instead.
*/
- if (!pevent->cmdlines ||
- cmdline < pevent->cmdlines ||
- cmdline >= pevent->cmdlines + pevent->cmdline_count)
+ if (!tep->cmdlines ||
+ cmdline < tep->cmdlines ||
+ cmdline >= tep->cmdlines + tep->cmdline_count)
return cmdlist->pid;
return cmdline->pid;
}
-/**
- * tep_event_info - parse the data into the print format
- * @s: the trace_seq to write to
- * @event: the handle to the event
- * @record: the record to read from
- *
+/*
* This parses the raw @data using the given @event information and
* writes the print format into the trace_seq.
*/
-void tep_event_info(struct trace_seq *s, struct event_format *event,
- struct tep_record *record)
+static void print_event_info(struct trace_seq *s, char *format, bool raw,
+ struct tep_event *event, struct tep_record *record)
{
int print_pretty = 1;
- if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
+ if (raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
tep_print_fields(s, record->data, record->size, event);
else {
- if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
+ if (event->handler && !(event->flags & TEP_EVENT_FL_NOHANDLE))
print_pretty = event->handler(s, record, event,
event->context);
@@ -5405,29 +5481,16 @@
trace_seq_terminate(s);
}
-static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
-{
- if (!use_trace_clock)
- return true;
-
- if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
- || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
- return true;
-
- /* trace_clock is setting in tsc or counter mode */
- return false;
-}
-
/**
* tep_find_event_by_record - return the event from a given record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @record: The record to get the event from
*
* Returns the associated event for a given record, or NULL if non is
* is found.
*/
-struct event_format *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
+struct tep_event *
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
{
int type;
@@ -5436,142 +5499,208 @@
return NULL;
}
- type = trace_parse_common_type(pevent, record->data);
+ type = trace_parse_common_type(tep, record->data);
- return tep_find_event(pevent, type);
+ return tep_find_event(tep, type);
}
-/**
- * tep_print_event_task - Write the event task comm, pid and CPU
- * @pevent: a handle to the pevent
- * @s: the trace_seq to write to
- * @event: the handle to the record's event
- * @record: The record to get the event from
- *
- * Writes the tasks comm, pid and CPU to @s.
+/*
+ * Writes the timestamp of the record into @s. Time divisor and precision can be
+ * specified as part of printf @format string. Example:
+ * "%3.1000d" - divide the time by 1000 and print the first 3 digits
+ * before the dot. Thus, the timestamp "123456000" will be printed as
+ * "123.456"
*/
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record)
+static void print_event_time(struct tep_handle *tep, struct trace_seq *s,
+ char *format, struct tep_event *event,
+ struct tep_record *record)
{
- void *data = record->data;
+ unsigned long long time;
+ char *divstr;
+ int prec = 0, pr;
+ int div = 0;
+ int p10 = 1;
+
+ if (isdigit(*(format + 1)))
+ prec = atoi(format + 1);
+ divstr = strchr(format, '.');
+ if (divstr && isdigit(*(divstr + 1)))
+ div = atoi(divstr + 1);
+ time = record->ts;
+ if (div) {
+ time += div / 2;
+ time /= div;
+ }
+ pr = prec;
+ while (pr--)
+ p10 *= 10;
+
+ if (p10 > 1 && p10 < time)
+ trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10);
+ else
+ trace_seq_printf(s, "%12llu\n", time);
+}
+
+struct print_event_type {
+ enum {
+ EVENT_TYPE_INT = 1,
+ EVENT_TYPE_STRING,
+ EVENT_TYPE_UNKNOWN,
+ } type;
+ char format[32];
+};
+
+static void print_string(struct tep_handle *tep, struct trace_seq *s,
+ struct tep_record *record, struct tep_event *event,
+ const char *arg, struct print_event_type *type)
+{
const char *comm;
int pid;
- pid = parse_common_pid(pevent, data);
- comm = find_cmdline(pevent, pid);
-
- if (pevent->latency_format) {
- trace_seq_printf(s, "%8.8s-%-5d %3d",
- comm, pid, record->cpu);
- } else
- trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
-}
-
-/**
- * tep_print_event_time - Write the event timestamp
- * @pevent: a handle to the pevent
- * @s: the trace_seq to write to
- * @event: the handle to the record's event
- * @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @pevent->trace_clock
- *
- * Writes the timestamp of the record into @s.
- */
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record,
- bool use_trace_clock)
-{
- unsigned long secs;
- unsigned long usecs;
- unsigned long nsecs;
- int p;
- bool use_usec_format;
-
- use_usec_format = is_timestamp_in_us(pevent->trace_clock,
- use_trace_clock);
- if (use_usec_format) {
- secs = record->ts / NSEC_PER_SEC;
- nsecs = record->ts - secs * NSEC_PER_SEC;
+ if (strncmp(arg, TEP_PRINT_LATENCY, strlen(TEP_PRINT_LATENCY)) == 0) {
+ data_latency_format(tep, s, type->format, record);
+ } else if (strncmp(arg, TEP_PRINT_COMM, strlen(TEP_PRINT_COMM)) == 0) {
+ pid = parse_common_pid(tep, record->data);
+ comm = find_cmdline(tep, pid);
+ trace_seq_printf(s, type->format, comm);
+ } else if (strncmp(arg, TEP_PRINT_INFO_RAW, strlen(TEP_PRINT_INFO_RAW)) == 0) {
+ print_event_info(s, type->format, true, event, record);
+ } else if (strncmp(arg, TEP_PRINT_INFO, strlen(TEP_PRINT_INFO)) == 0) {
+ print_event_info(s, type->format, false, event, record);
+ } else if (strncmp(arg, TEP_PRINT_NAME, strlen(TEP_PRINT_NAME)) == 0) {
+ trace_seq_printf(s, type->format, event->name);
+ } else {
+ trace_seq_printf(s, "[UNKNOWN TEP TYPE %s]", arg);
}
- if (pevent->latency_format) {
- tep_data_lat_fmt(pevent, s, record);
- }
-
- if (use_usec_format) {
- if (pevent->flags & TEP_NSEC_OUTPUT) {
- usecs = nsecs;
- p = 9;
- } else {
- usecs = (nsecs + 500) / NSEC_PER_USEC;
- /* To avoid usecs larger than 1 sec */
- if (usecs >= USEC_PER_SEC) {
- usecs -= USEC_PER_SEC;
- secs++;
- }
- p = 6;
- }
-
- trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs);
- } else
- trace_seq_printf(s, " %12llu:", record->ts);
}
-/**
- * tep_print_event_data - Write the event data section
- * @pevent: a handle to the pevent
- * @s: the trace_seq to write to
- * @event: the handle to the record's event
- * @record: The record to get the event from
- *
- * Writes the parsing of the record's data to @s.
- */
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record)
+static void print_int(struct tep_handle *tep, struct trace_seq *s,
+ struct tep_record *record, struct tep_event *event,
+ int arg, struct print_event_type *type)
{
- static const char *spaces = " "; /* 20 spaces */
- int len;
+ int param;
- trace_seq_printf(s, " %s: ", event->name);
-
- /* Space out the event names evenly. */
- len = strlen(event->name);
- if (len < 20)
- trace_seq_printf(s, "%.*s", 20 - len, spaces);
-
- tep_event_info(s, event, record);
-}
-
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
- struct tep_record *record, bool use_trace_clock)
-{
- struct event_format *event;
-
- event = tep_find_event_by_record(pevent, record);
- if (!event) {
- int i;
- int type = trace_parse_common_type(pevent, record->data);
-
- do_warning("ug! no event found for type %d", type);
- trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
- for (i = 0; i < record->size; i++)
- trace_seq_printf(s, " %02x",
- ((unsigned char *)record->data)[i]);
+ switch (arg) {
+ case TEP_PRINT_CPU:
+ param = record->cpu;
+ break;
+ case TEP_PRINT_PID:
+ param = parse_common_pid(tep, record->data);
+ break;
+ case TEP_PRINT_TIME:
+ return print_event_time(tep, s, type->format, event, record);
+ default:
return;
}
+ trace_seq_printf(s, type->format, param);
+}
- tep_print_event_task(pevent, s, event, record);
- tep_print_event_time(pevent, s, event, record, use_trace_clock);
- tep_print_event_data(pevent, s, event, record);
+static int tep_print_event_param_type(char *format,
+ struct print_event_type *type)
+{
+ char *str = format + 1;
+ int i = 1;
+
+ type->type = EVENT_TYPE_UNKNOWN;
+ while (*str) {
+ switch (*str) {
+ case 'd':
+ case 'u':
+ case 'i':
+ case 'x':
+ case 'X':
+ case 'o':
+ type->type = EVENT_TYPE_INT;
+ break;
+ case 's':
+ type->type = EVENT_TYPE_STRING;
+ break;
+ }
+ str++;
+ i++;
+ if (type->type != EVENT_TYPE_UNKNOWN)
+ break;
+ }
+ memset(type->format, 0, 32);
+ memcpy(type->format, format, i < 32 ? i : 31);
+ return i;
+}
+
+/**
+ * tep_print_event - Write various event information
+ * @tep: a handle to the trace event parser context
+ * @s: the trace_seq to write to
+ * @record: The record to get the event from
+ * @format: a printf format string. Supported event fileds:
+ * TEP_PRINT_PID, "%d" - event PID
+ * TEP_PRINT_CPU, "%d" - event CPU
+ * TEP_PRINT_COMM, "%s" - event command string
+ * TEP_PRINT_NAME, "%s" - event name
+ * TEP_PRINT_LATENCY, "%s" - event latency
+ * TEP_PRINT_TIME, %d - event time stamp. A divisor and precision
+ * can be specified as part of this format string:
+ * "%precision.divisord". Example:
+ * "%3.1000d" - divide the time by 1000 and print the first
+ * 3 digits before the dot. Thus, the time stamp
+ * "123456000" will be printed as "123.456"
+ * TEP_PRINT_INFO, "%s" - event information. If any width is specified in
+ * the format string, the event information will be printed
+ * in raw format.
+ * Writes the specified event information into @s.
+ */
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
+ struct tep_record *record, const char *fmt, ...)
+{
+ struct print_event_type type;
+ char *format = strdup(fmt);
+ char *current = format;
+ char *str = format;
+ int offset;
+ va_list args;
+ struct tep_event *event;
+
+ if (!format)
+ return;
+
+ event = tep_find_event_by_record(tep, record);
+ va_start(args, fmt);
+ while (*current) {
+ current = strchr(str, '%');
+ if (!current) {
+ trace_seq_puts(s, str);
+ break;
+ }
+ memset(&type, 0, sizeof(type));
+ offset = tep_print_event_param_type(current, &type);
+ *current = '\0';
+ trace_seq_puts(s, str);
+ current += offset;
+ switch (type.type) {
+ case EVENT_TYPE_STRING:
+ print_string(tep, s, record, event,
+ va_arg(args, char*), &type);
+ break;
+ case EVENT_TYPE_INT:
+ print_int(tep, s, record, event,
+ va_arg(args, int), &type);
+ break;
+ case EVENT_TYPE_UNKNOWN:
+ default:
+ trace_seq_printf(s, "[UNKNOWN TYPE]");
+ break;
+ }
+ str = current;
+
+ }
+ va_end(args);
+ free(format);
}
static int events_id_cmp(const void *a, const void *b)
{
- struct event_format * const * ea = a;
- struct event_format * const * eb = b;
+ struct tep_event * const * ea = a;
+ struct tep_event * const * eb = b;
if ((*ea)->id < (*eb)->id)
return -1;
@@ -5584,8 +5713,8 @@
static int events_name_cmp(const void *a, const void *b)
{
- struct event_format * const * ea = a;
- struct event_format * const * eb = b;
+ struct tep_event * const * ea = a;
+ struct tep_event * const * eb = b;
int res;
res = strcmp((*ea)->name, (*eb)->name);
@@ -5601,8 +5730,8 @@
static int events_system_cmp(const void *a, const void *b)
{
- struct event_format * const * ea = a;
- struct event_format * const * eb = b;
+ struct tep_event * const * ea = a;
+ struct tep_event * const * eb = b;
int res;
res = strcmp((*ea)->system, (*eb)->system);
@@ -5616,59 +5745,124 @@
return events_id_cmp(a, b);
}
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type sort_type)
+static struct tep_event **list_events_copy(struct tep_handle *tep)
{
- struct event_format **events;
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = malloc(sizeof(*events) * (tep->nr_events + 1));
+ if (!events)
+ return NULL;
+
+ memcpy(events, tep->events, sizeof(*events) * tep->nr_events);
+ events[tep->nr_events] = NULL;
+ return events;
+}
+
+static void list_events_sort(struct tep_event **events, int nr_events,
+ enum tep_event_sort_type sort_type)
+{
int (*sort)(const void *a, const void *b);
- events = pevent->sort_events;
+ switch (sort_type) {
+ case TEP_EVENT_SORT_ID:
+ sort = events_id_cmp;
+ break;
+ case TEP_EVENT_SORT_NAME:
+ sort = events_name_cmp;
+ break;
+ case TEP_EVENT_SORT_SYSTEM:
+ sort = events_system_cmp;
+ break;
+ default:
+ sort = NULL;
+ }
- if (events && pevent->last_type == sort_type)
+ if (sort)
+ qsort(events, nr_events, sizeof(*events), sort);
+}
+
+/**
+ * tep_list_events - Get events, sorted by given criteria.
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * memory must not be freed, it is managed by the library.
+ * The function is not thread safe.
+ */
+struct tep_event **tep_list_events(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
+{
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = tep->sort_events;
+ if (events && tep->last_type == sort_type)
return events;
if (!events) {
- events = malloc(sizeof(*events) * (pevent->nr_events + 1));
+ events = list_events_copy(tep);
if (!events)
return NULL;
- memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events);
- events[pevent->nr_events] = NULL;
-
- pevent->sort_events = events;
+ tep->sort_events = events;
/* the internal events are sorted by id */
- if (sort_type == EVENT_SORT_ID) {
- pevent->last_type = sort_type;
+ if (sort_type == TEP_EVENT_SORT_ID) {
+ tep->last_type = sort_type;
return events;
}
}
- switch (sort_type) {
- case EVENT_SORT_ID:
- sort = events_id_cmp;
- break;
- case EVENT_SORT_NAME:
- sort = events_name_cmp;
- break;
- case EVENT_SORT_SYSTEM:
- sort = events_system_cmp;
- break;
- default:
- return events;
- }
-
- qsort(events, pevent->nr_events, sizeof(*events), sort);
- pevent->last_type = sort_type;
+ list_events_sort(events, tep->nr_events, sort_type);
+ tep->last_type = sort_type;
return events;
}
-static struct format_field **
-get_event_fields(const char *type, const char *name,
- int count, struct format_field *list)
+
+/**
+ * tep_list_events_copy - Thread safe version of tep_list_events()
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * array is newly allocated inside the function and must be freed by the caller
+ */
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
{
- struct format_field **fields;
- struct format_field *field;
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = list_events_copy(tep);
+ if (!events)
+ return NULL;
+
+ /* the internal events are sorted by id */
+ if (sort_type == TEP_EVENT_SORT_ID)
+ return events;
+
+ list_events_sort(events, tep->nr_events, sort_type);
+
+ return events;
+}
+
+static struct tep_format_field **
+get_event_fields(const char *type, const char *name,
+ int count, struct tep_format_field *list)
+{
+ struct tep_format_field **fields;
+ struct tep_format_field *field;
int i = 0;
fields = malloc(sizeof(*fields) * (count + 1));
@@ -5701,7 +5895,7 @@
* Returns an allocated array of fields. The last item in the array is NULL.
* The array must be freed with free().
*/
-struct format_field **tep_event_common_fields(struct event_format *event)
+struct tep_format_field **tep_event_common_fields(struct tep_event *event)
{
return get_event_fields("common", event->name,
event->format.nr_common,
@@ -5715,14 +5909,14 @@
* Returns an allocated array of fields. The last item in the array is NULL.
* The array must be freed with free().
*/
-struct format_field **tep_event_fields(struct event_format *event)
+struct tep_format_field **tep_event_fields(struct tep_event *event)
{
return get_event_fields("event", event->name,
event->format.nr_fields,
event->format.fields);
}
-static void print_fields(struct trace_seq *s, struct print_flag_sym *field)
+static void print_fields(struct trace_seq *s, struct tep_print_flag_sym *field)
{
trace_seq_printf(s, "{ %s, %s }", field->value, field->str);
if (field->next) {
@@ -5732,22 +5926,22 @@
}
/* for debugging */
-static void print_args(struct print_arg *args)
+static void print_args(struct tep_print_arg *args)
{
int print_paren = 1;
struct trace_seq s;
switch (args->type) {
- case PRINT_NULL:
+ case TEP_PRINT_NULL:
printf("null");
break;
- case PRINT_ATOM:
+ case TEP_PRINT_ATOM:
printf("%s", args->atom.atom);
break;
- case PRINT_FIELD:
+ case TEP_PRINT_FIELD:
printf("REC->%s", args->field.name);
break;
- case PRINT_FLAGS:
+ case TEP_PRINT_FLAGS:
printf("__print_flags(");
print_args(args->flags.field);
printf(", %s, ", args->flags.delim);
@@ -5757,7 +5951,7 @@
trace_seq_destroy(&s);
printf(")");
break;
- case PRINT_SYMBOL:
+ case TEP_PRINT_SYMBOL:
printf("__print_symbolic(");
print_args(args->symbol.field);
printf(", ");
@@ -5767,21 +5961,21 @@
trace_seq_destroy(&s);
printf(")");
break;
- case PRINT_HEX:
+ case TEP_PRINT_HEX:
printf("__print_hex(");
print_args(args->hex.field);
printf(", ");
print_args(args->hex.size);
printf(")");
break;
- case PRINT_HEX_STR:
+ case TEP_PRINT_HEX_STR:
printf("__print_hex_str(");
print_args(args->hex.field);
printf(", ");
print_args(args->hex.size);
printf(")");
break;
- case PRINT_INT_ARRAY:
+ case TEP_PRINT_INT_ARRAY:
printf("__print_array(");
print_args(args->int_array.field);
printf(", ");
@@ -5790,18 +5984,18 @@
print_args(args->int_array.el_size);
printf(")");
break;
- case PRINT_STRING:
- case PRINT_BSTRING:
+ case TEP_PRINT_STRING:
+ case TEP_PRINT_BSTRING:
printf("__get_str(%s)", args->string.string);
break;
- case PRINT_BITMASK:
+ case TEP_PRINT_BITMASK:
printf("__get_bitmask(%s)", args->bitmask.bitmask);
break;
- case PRINT_TYPE:
+ case TEP_PRINT_TYPE:
printf("(%s)", args->typecast.type);
print_args(args->typecast.item);
break;
- case PRINT_OP:
+ case TEP_PRINT_OP:
if (strcmp(args->op.op, ":") == 0)
print_paren = 0;
if (print_paren)
@@ -5833,13 +6027,13 @@
save_input_buf_ptr = input_buf_ptr;
save_input_buf_siz = input_buf_siz;
- if (read_expected(EVENT_ITEM, "field") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "field") < 0)
return;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return;
/* type */
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
free_token(token);
@@ -5847,42 +6041,42 @@
* If this is not a mandatory field, then test it first.
*/
if (mandatory) {
- if (read_expected(EVENT_ITEM, field) < 0)
+ if (read_expected(TEP_EVENT_ITEM, field) < 0)
return;
} else {
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
if (strcmp(token, field) != 0)
goto discard;
free_token(token);
}
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
return;
- if (read_expected(EVENT_ITEM, "offset") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
return;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
*offset = atoi(token);
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
return;
- if (read_expected(EVENT_ITEM, "size") < 0)
+ if (read_expected(TEP_EVENT_ITEM, "size") < 0)
return;
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return;
- if (read_expect_type(EVENT_ITEM, &token) < 0)
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
goto fail;
*size = atoi(token);
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
return;
type = read_token(&token);
- if (type != EVENT_NEWLINE) {
+ if (type != TEP_EVENT_NEWLINE) {
/* newer versions of the kernel have a "signed" type */
- if (type != EVENT_ITEM)
+ if (type != TEP_EVENT_ITEM)
goto fail;
if (strcmp(token, "signed") != 0)
@@ -5890,17 +6084,17 @@
free_token(token);
- if (read_expected(EVENT_OP, ":") < 0)
+ if (read_expected(TEP_EVENT_OP, ":") < 0)
return;
- if (read_expect_type(EVENT_ITEM, &token))
+ if (read_expect_type(TEP_EVENT_ITEM, &token))
goto fail;
free_token(token);
- if (read_expected(EVENT_OP, ";") < 0)
+ if (read_expected(TEP_EVENT_OP, ";") < 0)
return;
- if (read_expect_type(EVENT_NEWLINE, &token))
+ if (read_expect_type(TEP_EVENT_NEWLINE, &token))
goto fail;
}
fail:
@@ -5917,7 +6111,7 @@
/**
* tep_parse_header_page - parse the data stored in the header page
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the header page format string
* @size: the size of @buf
* @long_size: the long size to use if there is no header
@@ -5927,7 +6121,7 @@
*
* /sys/kernel/debug/tracing/events/header_page
*/
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size)
{
int ignore;
@@ -5937,27 +6131,27 @@
* Old kernels did not have header page info.
* Sorry but we just use what we find here in user space.
*/
- pevent->header_page_ts_size = sizeof(long long);
- pevent->header_page_size_size = long_size;
- pevent->header_page_data_offset = sizeof(long long) + long_size;
- pevent->old_format = 1;
+ tep->header_page_ts_size = sizeof(long long);
+ tep->header_page_size_size = long_size;
+ tep->header_page_data_offset = sizeof(long long) + long_size;
+ tep->old_format = 1;
return -1;
}
init_input_buf(buf, size);
- parse_header_field("timestamp", &pevent->header_page_ts_offset,
- &pevent->header_page_ts_size, 1);
- parse_header_field("commit", &pevent->header_page_size_offset,
- &pevent->header_page_size_size, 1);
- parse_header_field("overwrite", &pevent->header_page_overwrite,
+ parse_header_field("timestamp", &tep->header_page_ts_offset,
+ &tep->header_page_ts_size, 1);
+ parse_header_field("commit", &tep->header_page_size_offset,
+ &tep->header_page_size_size, 1);
+ parse_header_field("overwrite", &tep->header_page_overwrite,
&ignore, 0);
- parse_header_field("data", &pevent->header_page_data_offset,
- &pevent->header_page_data_size, 1);
+ parse_header_field("data", &tep->header_page_data_offset,
+ &tep->header_page_data_size, 1);
return 0;
}
-static int event_matches(struct event_format *event,
+static int event_matches(struct tep_event *event,
int id, const char *sys_name,
const char *event_name)
{
@@ -5980,11 +6174,11 @@
free(handle);
}
-static int find_event_handle(struct tep_handle *pevent, struct event_format *event)
+static int find_event_handle(struct tep_handle *tep, struct tep_event *event)
{
struct event_handler *handle, **next;
- for (next = &pevent->handlers; *next;
+ for (next = &tep->handlers; *next;
next = &(*next)->next) {
handle = *next;
if (event_matches(event, handle->id,
@@ -6021,11 +6215,11 @@
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno __tep_parse_format(struct event_format **eventp,
- struct tep_handle *pevent, const char *buf,
+enum tep_errno __tep_parse_format(struct tep_event **eventp,
+ struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
- struct event_format *event;
+ struct tep_event *event;
int ret;
init_input_buf(buf, size);
@@ -6042,10 +6236,10 @@
}
if (strcmp(sys, "ftrace") == 0) {
- event->flags |= EVENT_FL_ISFTRACE;
+ event->flags |= TEP_EVENT_FL_ISFTRACE;
if (strcmp(event->name, "bprint") == 0)
- event->flags |= EVENT_FL_ISBPRINT;
+ event->flags |= TEP_EVENT_FL_ISBPRINT;
}
event->id = event_read_id();
@@ -6064,8 +6258,8 @@
goto event_alloc_failed;
}
- /* Add pevent to event so that it can be referenced */
- event->pevent = pevent;
+ /* Add tep to event so that it can be referenced */
+ event->tep = tep;
ret = event_read_format(event);
if (ret < 0) {
@@ -6077,7 +6271,7 @@
* If the event has an override, don't print warnings if the event
* print format fails to parse.
*/
- if (pevent && find_event_handle(pevent, event))
+ if (tep && find_event_handle(tep, event))
show_warning = 0;
ret = event_read_print(event);
@@ -6088,22 +6282,22 @@
goto event_parse_failed;
}
- if (!ret && (event->flags & EVENT_FL_ISFTRACE)) {
- struct format_field *field;
- struct print_arg *arg, **list;
+ if (!ret && (event->flags & TEP_EVENT_FL_ISFTRACE)) {
+ struct tep_format_field *field;
+ struct tep_print_arg *arg, **list;
/* old ftrace had no args */
list = &event->print_fmt.args;
for (field = event->format.fields; field; field = field->next) {
arg = alloc_arg();
if (!arg) {
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
}
- arg->type = PRINT_FIELD;
+ arg->type = TEP_PRINT_FIELD;
arg->field.name = strdup(field->name);
if (!arg->field.name) {
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
free_arg(arg);
return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
}
@@ -6117,7 +6311,7 @@
return 0;
event_parse_failed:
- event->flags |= EVENT_FL_FAILED;
+ event->flags |= TEP_EVENT_FL_FAILED;
return ret;
event_alloc_failed:
@@ -6129,18 +6323,18 @@
}
static enum tep_errno
-__parse_event(struct tep_handle *pevent,
- struct event_format **eventp,
+__parse_event(struct tep_handle *tep,
+ struct tep_event **eventp,
const char *buf, unsigned long size,
const char *sys)
{
- int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
- struct event_format *event = *eventp;
+ int ret = __tep_parse_format(eventp, tep, buf, size, sys);
+ struct tep_event *event = *eventp;
if (event == NULL)
return ret;
- if (pevent && add_event(pevent, event)) {
+ if (tep && add_event(tep, event)) {
ret = TEP_ERRNO__MEM_ALLOC_FAILED;
goto event_add_failed;
}
@@ -6152,13 +6346,13 @@
return 0;
event_add_failed:
- tep_free_format(event);
+ tep_free_event(event);
return ret;
}
/**
* tep_parse_format - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @eventp: returned format
* @buf: the buffer storing the event format string
* @size: the size of @buf
@@ -6171,17 +6365,17 @@
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
- struct event_format **eventp,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
+ struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys)
{
- return __parse_event(pevent, eventp, buf, size, sys);
+ return __parse_event(tep, eventp, buf, size, sys);
}
/**
* tep_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the event format string
* @size: the size of @buf
* @sys: the system the event belongs to
@@ -6193,43 +6387,14 @@
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
- struct event_format *event = NULL;
- return __parse_event(pevent, &event, buf, size, sys);
+ struct tep_event *event = NULL;
+ return __parse_event(tep, &event, buf, size, sys);
}
-#undef _PE
-#define _PE(code, str) str
-static const char * const tep_error_str[] = {
- TEP_ERRORS
-};
-#undef _PE
-
-int tep_strerror(struct tep_handle *pevent __maybe_unused,
- enum tep_errno errnum, char *buf, size_t buflen)
-{
- int idx;
- const char *msg;
-
- if (errnum >= 0) {
- str_error_r(errnum, buf, buflen);
- return 0;
- }
-
- if (errnum <= __TEP_ERRNO__START ||
- errnum >= __TEP_ERRNO__END)
- return -1;
-
- idx = errnum - __TEP_ERRNO__START - 1;
- msg = tep_error_str[idx];
- snprintf(buf, buflen, "%s", msg);
-
- return 0;
-}
-
-int get_field_val(struct trace_seq *s, struct format_field *field,
+int get_field_val(struct trace_seq *s, struct tep_format_field *field,
const char *name, struct tep_record *record,
unsigned long long *val, int err)
{
@@ -6262,11 +6427,11 @@
*
* On failure, it returns NULL.
*/
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
int *len, int err)
{
- struct format_field *field;
+ struct tep_format_field *field;
void *data = record->data;
unsigned offset;
int dummy;
@@ -6287,9 +6452,9 @@
len = &dummy;
offset = field->offset;
- if (field->flags & FIELD_IS_DYNAMIC) {
- offset = tep_read_number(event->pevent,
- data + offset, field->size);
+ if (field->flags & TEP_FIELD_IS_DYNAMIC) {
+ offset = tep_read_number(event->tep,
+ data + offset, field->size);
*len = offset >> 16;
offset &= 0xffff;
} else
@@ -6309,11 +6474,11 @@
*
* Returns 0 on success -1 on field not found.
*/
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err)
{
- struct format_field *field;
+ struct tep_format_field *field;
if (!event)
return -1;
@@ -6334,11 +6499,11 @@
*
* Returns 0 on success -1 on field not found.
*/
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err)
{
- struct format_field *field;
+ struct tep_format_field *field;
if (!event)
return -1;
@@ -6359,11 +6524,11 @@
*
* Returns 0 on success -1 on field not found.
*/
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err)
{
- struct format_field *field;
+ struct tep_format_field *field;
if (!event)
return -1;
@@ -6382,13 +6547,14 @@
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_num_field(struct trace_seq *s, const char *fmt,
- struct event_format *event, const char *name,
+ struct tep_event *event, const char *name,
struct tep_record *record, int err)
{
- struct format_field *field = tep_find_field(event, name);
+ struct tep_format_field *field = tep_find_field(event, name);
unsigned long long val;
if (!field)
@@ -6414,14 +6580,15 @@
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_func_field(struct trace_seq *s, const char *fmt,
- struct event_format *event, const char *name,
+ struct tep_event *event, const char *name,
struct tep_record *record, int err)
{
- struct format_field *field = tep_find_field(event, name);
- struct tep_handle *pevent = event->pevent;
+ struct tep_format_field *field = tep_find_field(event, name);
+ struct tep_handle *tep = event->tep;
unsigned long long val;
struct func_map *func;
char tmp[128];
@@ -6432,7 +6599,7 @@
if (tep_read_number_field(field, record->data, &val))
goto failed;
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func)
snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
@@ -6464,7 +6631,7 @@
/**
* tep_register_print_function - register a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @ret_type: the return type of the helper function
* @name: the name of the helper function
@@ -6477,7 +6644,7 @@
* The @parameters is a variable list of tep_func_arg_type enums that
* must end with TEP_FUNC_ARG_VOID.
*/
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...)
@@ -6489,7 +6656,7 @@
va_list ap;
int ret;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle) {
/*
* This is most like caused by the users own
@@ -6497,7 +6664,7 @@
* system defaults.
*/
pr_stat("override of function helper '%s'", name);
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
}
func_handle = calloc(1, sizeof(*func_handle));
@@ -6544,8 +6711,8 @@
}
va_end(ap);
- func_handle->next = pevent->func_handlers;
- pevent->func_handlers = func_handle;
+ func_handle->next = tep->func_handlers;
+ tep->func_handlers = func_handle;
return 0;
out_free:
@@ -6556,7 +6723,7 @@
/**
* tep_unregister_print_function - unregister a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @name: the name of the helper function
*
@@ -6564,28 +6731,28 @@
*
* Returns 0 if the handler was removed successully, -1 otherwise.
*/
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name)
{
struct tep_function_handler *func_handle;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle && func_handle->func == func) {
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
return 0;
}
return -1;
}
-static struct event_format *search_event(struct tep_handle *pevent, int id,
- const char *sys_name,
- const char *event_name)
+static struct tep_event *search_event(struct tep_handle *tep, int id,
+ const char *sys_name,
+ const char *event_name)
{
- struct event_format *event;
+ struct tep_event *event;
if (id >= 0) {
/* search by id */
- event = tep_find_event(pevent, id);
+ event = tep_find_event(tep, id);
if (!event)
return NULL;
if (event_name && (strcmp(event_name, event->name) != 0))
@@ -6593,7 +6760,7 @@
if (sys_name && (strcmp(sys_name, event->system) != 0))
return NULL;
} else {
- event = tep_find_event_by_name(pevent, sys_name, event_name);
+ event = tep_find_event_by_name(tep, sys_name, event_name);
if (!event)
return NULL;
}
@@ -6602,7 +6769,7 @@
/**
* tep_register_event_handler - register a way to parse an event
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to register
* @sys_name: the system name the event belongs to
* @event_name: the name of the event
@@ -6616,15 +6783,21 @@
*
* If @id is >= 0, then it is used to find the event.
* else @sys_name and @event_name are used.
+ *
+ * Returns:
+ * TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten
+ * TEP_REGISTER_SUCCESS if a new handler is registered successfully
+ * negative TEP_ERRNO_... in case of an error
+ *
*/
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
- struct event_format *event;
+ struct tep_event *event;
struct event_handler *handle;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
@@ -6633,7 +6806,7 @@
event->handler = func;
event->context = context;
- return 0;
+ return TEP_REGISTER_SUCCESS_OVERWRITE;
not_found:
/* Save for later use. */
@@ -6659,11 +6832,11 @@
}
handle->func = func;
- handle->next = pevent->handlers;
- pevent->handlers = handle;
+ handle->next = tep->handlers;
+ tep->handlers = handle;
handle->context = context;
- return -1;
+ return TEP_REGISTER_SUCCESS;
}
static int handle_matches(struct event_handler *handler, int id,
@@ -6687,7 +6860,7 @@
/**
* tep_unregister_event_handler - unregister an existing event handler
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to unregister
* @sys_name: the system name the handler belongs to
* @event_name: the name of the event handler
@@ -6701,15 +6874,15 @@
*
* Returns 0 if handler was removed successfully, -1 if event was not found.
*/
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
- struct event_format *event;
+ struct tep_event *event;
struct event_handler *handle;
struct event_handler **next;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
@@ -6723,7 +6896,7 @@
}
not_found:
- for (next = &pevent->handlers; *next; next = &(*next)->next) {
+ for (next = &tep->handlers; *next; next = &(*next)->next) {
handle = *next;
if (handle_matches(handle, id, sys_name, event_name,
func, context))
@@ -6740,24 +6913,33 @@
}
/**
- * tep_alloc - create a pevent handle
+ * tep_alloc - create a tep handle
*/
struct tep_handle *tep_alloc(void)
{
- struct tep_handle *pevent = calloc(1, sizeof(*pevent));
+ struct tep_handle *tep = calloc(1, sizeof(*tep));
- if (pevent)
- pevent->ref_count = 1;
+ if (tep) {
+ tep->ref_count = 1;
+ tep->host_bigendian = tep_is_bigendian();
+ }
- return pevent;
+ return tep;
}
-void tep_ref(struct tep_handle *pevent)
+void tep_ref(struct tep_handle *tep)
{
- pevent->ref_count++;
+ tep->ref_count++;
}
-void tep_free_format_field(struct format_field *field)
+int tep_get_ref(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->ref_count;
+ return 0;
+}
+
+void tep_free_format_field(struct tep_format_field *field)
{
free(field->type);
if (field->alias != field->name)
@@ -6766,9 +6948,9 @@
free(field);
}
-static void free_format_fields(struct format_field *field)
+static void free_format_fields(struct tep_format_field *field)
{
- struct format_field *next;
+ struct tep_format_field *next;
while (field) {
next = field->next;
@@ -6777,13 +6959,13 @@
}
}
-static void free_formats(struct format *format)
+static void free_formats(struct tep_format *format)
{
free_format_fields(format->common_fields);
free_format_fields(format->fields);
}
-void tep_free_format(struct event_format *event)
+void tep_free_event(struct tep_event *event)
{
free(event->name);
free(event->system);
@@ -6797,10 +6979,10 @@
}
/**
- * tep_free - free a pevent handle
- * @pevent: the pevent handle to free
+ * tep_free - free a tep handle
+ * @tep: the tep handle to free
*/
-void tep_free(struct tep_handle *pevent)
+void tep_free(struct tep_handle *tep)
{
struct cmdline_list *cmdlist, *cmdnext;
struct func_list *funclist, *funcnext;
@@ -6809,21 +6991,21 @@
struct event_handler *handle;
int i;
- if (!pevent)
+ if (!tep)
return;
- cmdlist = pevent->cmdlist;
- funclist = pevent->funclist;
- printklist = pevent->printklist;
+ cmdlist = tep->cmdlist;
+ funclist = tep->funclist;
+ printklist = tep->printklist;
- pevent->ref_count--;
- if (pevent->ref_count)
+ tep->ref_count--;
+ if (tep->ref_count)
return;
- if (pevent->cmdlines) {
- for (i = 0; i < pevent->cmdline_count; i++)
- free(pevent->cmdlines[i].comm);
- free(pevent->cmdlines);
+ if (tep->cmdlines) {
+ for (i = 0; i < tep->cmdline_count; i++)
+ free(tep->cmdlines[i].comm);
+ free(tep->cmdlines);
}
while (cmdlist) {
@@ -6833,12 +7015,12 @@
cmdlist = cmdnext;
}
- if (pevent->func_map) {
- for (i = 0; i < (int)pevent->func_count; i++) {
- free(pevent->func_map[i].func);
- free(pevent->func_map[i].mod);
+ if (tep->func_map) {
+ for (i = 0; i < (int)tep->func_count; i++) {
+ free(tep->func_map[i].func);
+ free(tep->func_map[i].mod);
}
- free(pevent->func_map);
+ free(tep->func_map);
}
while (funclist) {
@@ -6849,16 +7031,16 @@
funclist = funcnext;
}
- while (pevent->func_handlers) {
- func_handler = pevent->func_handlers;
- pevent->func_handlers = func_handler->next;
+ while (tep->func_handlers) {
+ func_handler = tep->func_handlers;
+ tep->func_handlers = func_handler->next;
free_func_handle(func_handler);
}
- if (pevent->printk_map) {
- for (i = 0; i < (int)pevent->printk_count; i++)
- free(pevent->printk_map[i].printk);
- free(pevent->printk_map);
+ if (tep->printk_map) {
+ for (i = 0; i < (int)tep->printk_count; i++)
+ free(tep->printk_map[i].printk);
+ free(tep->printk_map);
}
while (printklist) {
@@ -6868,24 +7050,23 @@
printklist = printknext;
}
- for (i = 0; i < pevent->nr_events; i++)
- tep_free_format(pevent->events[i]);
+ for (i = 0; i < tep->nr_events; i++)
+ tep_free_event(tep->events[i]);
- while (pevent->handlers) {
- handle = pevent->handlers;
- pevent->handlers = handle->next;
+ while (tep->handlers) {
+ handle = tep->handlers;
+ tep->handlers = handle->next;
free_handler(handle);
}
- free(pevent->trace_clock);
- free(pevent->events);
- free(pevent->sort_events);
- free(pevent->func_resolver);
+ free(tep->events);
+ free(tep->sort_events);
+ free(tep->func_resolver);
- free(pevent);
+ free(tep);
}
-void tep_unref(struct tep_handle *pevent)
+void tep_unref(struct tep_handle *tep)
{
- tep_free(pevent);
+ tep_free(tep);
}
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 44b7c2d..b77837f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -26,17 +26,12 @@
#include <regex.h>
#include <string.h>
+#include "trace-seq.h"
+
#ifndef __maybe_unused
#define __maybe_unused __attribute__((unused))
#endif
-/* ----------------------- trace_seq ----------------------- */
-
-
-#ifndef TRACE_SEQ_BUF_SIZE
-#define TRACE_SEQ_BUF_SIZE 4096
-#endif
-
#ifndef DEBUG_RECORD
#define DEBUG_RECORD 0
#endif
@@ -59,55 +54,18 @@
#endif
};
-enum trace_seq_fail {
- TRACE_SEQ__GOOD,
- TRACE_SEQ__BUFFER_POISONED,
- TRACE_SEQ__MEM_ALLOC_FAILED,
-};
-
-/*
- * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
- */
-
-struct trace_seq {
- char *buffer;
- unsigned int buffer_size;
- unsigned int len;
- unsigned int readpos;
- enum trace_seq_fail state;
-};
-
-void trace_seq_init(struct trace_seq *s);
-void trace_seq_reset(struct trace_seq *s);
-void trace_seq_destroy(struct trace_seq *s);
-
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
- __attribute__ ((format (printf, 2, 3)));
-extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
- __attribute__ ((format (printf, 2, 0)));
-
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-
-extern void trace_seq_terminate(struct trace_seq *s);
-
-extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
-extern int trace_seq_do_printf(struct trace_seq *s);
-
-
-/* ----------------------- pevent ----------------------- */
+/* ----------------------- tep ----------------------- */
struct tep_handle;
-struct event_format;
+struct tep_event;
typedef int (*tep_event_handler_func)(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event,
+ struct tep_event *event,
void *context);
-typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
-typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent);
+typedef int (*tep_plugin_load_func)(struct tep_handle *tep);
+typedef int (*tep_plugin_unload_func)(struct tep_handle *tep);
struct tep_plugin_option {
struct tep_plugin_option *next;
@@ -127,12 +85,12 @@
* TEP_PLUGIN_LOADER: (required)
* The function name to initialized the plugin.
*
- * int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_LOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_UNLOADER: (optional)
* The function called just before unloading
*
- * int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_OPTIONS: (optional)
* Plugin options that can be set before loading
@@ -172,20 +130,20 @@
#define TEP_PLUGIN_OPTIONS_NAME MAKE_STR(TEP_PLUGIN_OPTIONS)
#define TEP_PLUGIN_ALIAS_NAME MAKE_STR(TEP_PLUGIN_ALIAS)
-enum format_flags {
- FIELD_IS_ARRAY = 1,
- FIELD_IS_POINTER = 2,
- FIELD_IS_SIGNED = 4,
- FIELD_IS_STRING = 8,
- FIELD_IS_DYNAMIC = 16,
- FIELD_IS_LONG = 32,
- FIELD_IS_FLAG = 64,
- FIELD_IS_SYMBOLIC = 128,
+enum tep_format_flags {
+ TEP_FIELD_IS_ARRAY = 1,
+ TEP_FIELD_IS_POINTER = 2,
+ TEP_FIELD_IS_SIGNED = 4,
+ TEP_FIELD_IS_STRING = 8,
+ TEP_FIELD_IS_DYNAMIC = 16,
+ TEP_FIELD_IS_LONG = 32,
+ TEP_FIELD_IS_FLAG = 64,
+ TEP_FIELD_IS_SYMBOLIC = 128,
};
-struct format_field {
- struct format_field *next;
- struct event_format *event;
+struct tep_format_field {
+ struct tep_format_field *next;
+ struct tep_event *event;
char *type;
char *name;
char *alias;
@@ -196,169 +154,169 @@
unsigned long flags;
};
-struct format {
+struct tep_format {
int nr_common;
int nr_fields;
- struct format_field *common_fields;
- struct format_field *fields;
+ struct tep_format_field *common_fields;
+ struct tep_format_field *fields;
};
-struct print_arg_atom {
+struct tep_print_arg_atom {
char *atom;
};
-struct print_arg_string {
+struct tep_print_arg_string {
char *string;
int offset;
};
-struct print_arg_bitmask {
+struct tep_print_arg_bitmask {
char *bitmask;
int offset;
};
-struct print_arg_field {
+struct tep_print_arg_field {
char *name;
- struct format_field *field;
+ struct tep_format_field *field;
};
-struct print_flag_sym {
- struct print_flag_sym *next;
- char *value;
- char *str;
+struct tep_print_flag_sym {
+ struct tep_print_flag_sym *next;
+ char *value;
+ char *str;
};
-struct print_arg_typecast {
+struct tep_print_arg_typecast {
char *type;
- struct print_arg *item;
+ struct tep_print_arg *item;
};
-struct print_arg_flags {
- struct print_arg *field;
- char *delim;
- struct print_flag_sym *flags;
+struct tep_print_arg_flags {
+ struct tep_print_arg *field;
+ char *delim;
+ struct tep_print_flag_sym *flags;
};
-struct print_arg_symbol {
- struct print_arg *field;
- struct print_flag_sym *symbols;
+struct tep_print_arg_symbol {
+ struct tep_print_arg *field;
+ struct tep_print_flag_sym *symbols;
};
-struct print_arg_hex {
- struct print_arg *field;
- struct print_arg *size;
+struct tep_print_arg_hex {
+ struct tep_print_arg *field;
+ struct tep_print_arg *size;
};
-struct print_arg_int_array {
- struct print_arg *field;
- struct print_arg *count;
- struct print_arg *el_size;
+struct tep_print_arg_int_array {
+ struct tep_print_arg *field;
+ struct tep_print_arg *count;
+ struct tep_print_arg *el_size;
};
-struct print_arg_dynarray {
- struct format_field *field;
- struct print_arg *index;
+struct tep_print_arg_dynarray {
+ struct tep_format_field *field;
+ struct tep_print_arg *index;
};
-struct print_arg;
+struct tep_print_arg;
-struct print_arg_op {
+struct tep_print_arg_op {
char *op;
int prio;
- struct print_arg *left;
- struct print_arg *right;
+ struct tep_print_arg *left;
+ struct tep_print_arg *right;
};
struct tep_function_handler;
-struct print_arg_func {
+struct tep_print_arg_func {
struct tep_function_handler *func;
- struct print_arg *args;
+ struct tep_print_arg *args;
};
-enum print_arg_type {
- PRINT_NULL,
- PRINT_ATOM,
- PRINT_FIELD,
- PRINT_FLAGS,
- PRINT_SYMBOL,
- PRINT_HEX,
- PRINT_INT_ARRAY,
- PRINT_TYPE,
- PRINT_STRING,
- PRINT_BSTRING,
- PRINT_DYNAMIC_ARRAY,
- PRINT_OP,
- PRINT_FUNC,
- PRINT_BITMASK,
- PRINT_DYNAMIC_ARRAY_LEN,
- PRINT_HEX_STR,
+enum tep_print_arg_type {
+ TEP_PRINT_NULL,
+ TEP_PRINT_ATOM,
+ TEP_PRINT_FIELD,
+ TEP_PRINT_FLAGS,
+ TEP_PRINT_SYMBOL,
+ TEP_PRINT_HEX,
+ TEP_PRINT_INT_ARRAY,
+ TEP_PRINT_TYPE,
+ TEP_PRINT_STRING,
+ TEP_PRINT_BSTRING,
+ TEP_PRINT_DYNAMIC_ARRAY,
+ TEP_PRINT_OP,
+ TEP_PRINT_FUNC,
+ TEP_PRINT_BITMASK,
+ TEP_PRINT_DYNAMIC_ARRAY_LEN,
+ TEP_PRINT_HEX_STR,
};
-struct print_arg {
- struct print_arg *next;
- enum print_arg_type type;
+struct tep_print_arg {
+ struct tep_print_arg *next;
+ enum tep_print_arg_type type;
union {
- struct print_arg_atom atom;
- struct print_arg_field field;
- struct print_arg_typecast typecast;
- struct print_arg_flags flags;
- struct print_arg_symbol symbol;
- struct print_arg_hex hex;
- struct print_arg_int_array int_array;
- struct print_arg_func func;
- struct print_arg_string string;
- struct print_arg_bitmask bitmask;
- struct print_arg_op op;
- struct print_arg_dynarray dynarray;
+ struct tep_print_arg_atom atom;
+ struct tep_print_arg_field field;
+ struct tep_print_arg_typecast typecast;
+ struct tep_print_arg_flags flags;
+ struct tep_print_arg_symbol symbol;
+ struct tep_print_arg_hex hex;
+ struct tep_print_arg_int_array int_array;
+ struct tep_print_arg_func func;
+ struct tep_print_arg_string string;
+ struct tep_print_arg_bitmask bitmask;
+ struct tep_print_arg_op op;
+ struct tep_print_arg_dynarray dynarray;
};
};
-struct print_fmt {
+struct tep_print_fmt {
char *format;
- struct print_arg *args;
+ struct tep_print_arg *args;
};
-struct event_format {
- struct tep_handle *pevent;
+struct tep_event {
+ struct tep_handle *tep;
char *name;
int id;
int flags;
- struct format format;
- struct print_fmt print_fmt;
+ struct tep_format format;
+ struct tep_print_fmt print_fmt;
char *system;
tep_event_handler_func handler;
void *context;
};
enum {
- EVENT_FL_ISFTRACE = 0x01,
- EVENT_FL_ISPRINT = 0x02,
- EVENT_FL_ISBPRINT = 0x04,
- EVENT_FL_ISFUNCENT = 0x10,
- EVENT_FL_ISFUNCRET = 0x20,
- EVENT_FL_NOHANDLE = 0x40,
- EVENT_FL_PRINTRAW = 0x80,
+ TEP_EVENT_FL_ISFTRACE = 0x01,
+ TEP_EVENT_FL_ISPRINT = 0x02,
+ TEP_EVENT_FL_ISBPRINT = 0x04,
+ TEP_EVENT_FL_ISFUNCENT = 0x10,
+ TEP_EVENT_FL_ISFUNCRET = 0x20,
+ TEP_EVENT_FL_NOHANDLE = 0x40,
+ TEP_EVENT_FL_PRINTRAW = 0x80,
- EVENT_FL_FAILED = 0x80000000
+ TEP_EVENT_FL_FAILED = 0x80000000
};
-enum event_sort_type {
- EVENT_SORT_ID,
- EVENT_SORT_NAME,
- EVENT_SORT_SYSTEM,
+enum tep_event_sort_type {
+ TEP_EVENT_SORT_ID,
+ TEP_EVENT_SORT_NAME,
+ TEP_EVENT_SORT_SYSTEM,
};
-enum event_type {
- EVENT_ERROR,
- EVENT_NONE,
- EVENT_SPACE,
- EVENT_NEWLINE,
- EVENT_OP,
- EVENT_DELIM,
- EVENT_ITEM,
- EVENT_DQUOTE,
- EVENT_SQUOTE,
+enum tep_event_type {
+ TEP_EVENT_ERROR,
+ TEP_EVENT_NONE,
+ TEP_EVENT_SPACE,
+ TEP_EVENT_NEWLINE,
+ TEP_EVENT_OP,
+ TEP_EVENT_DELIM,
+ TEP_EVENT_ITEM,
+ TEP_EVENT_DQUOTE,
+ TEP_EVENT_SQUOTE,
};
typedef unsigned long long (*tep_func_handler)(struct trace_seq *s,
@@ -431,13 +389,13 @@
};
#undef _PE
-struct plugin_list;
+struct tep_plugin_list;
#define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1))
-struct plugin_list *tep_load_plugins(struct tep_handle *pevent);
-void tep_unload_plugins(struct plugin_list *plugin_list,
- struct tep_handle *pevent);
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep);
+void tep_unload_plugins(struct tep_plugin_list *plugin_list,
+ struct tep_handle *tep);
char **tep_plugin_list_options(void);
void tep_plugin_free_options_list(char **list);
int tep_plugin_add_options(const char *name,
@@ -445,159 +403,16 @@
void tep_plugin_remove_options(struct tep_plugin_option *options);
void tep_print_plugins(struct trace_seq *s,
const char *prefix, const char *suffix,
- const struct plugin_list *list);
+ const struct tep_plugin_list *list);
-struct cmdline;
-struct cmdline_list;
-struct func_map;
-struct func_list;
-struct event_handler;
-struct func_resolver;
-
+/* tep_handle */
typedef char *(tep_func_resolver_t)(void *priv,
unsigned long long *addrp, char **modp);
+void tep_set_flag(struct tep_handle *tep, int flag);
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag);
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags);
-struct tep_handle {
- int ref_count;
-
- int header_page_ts_offset;
- int header_page_ts_size;
- int header_page_size_offset;
- int header_page_size_size;
- int header_page_data_offset;
- int header_page_data_size;
- int header_page_overwrite;
-
- int file_bigendian;
- int host_bigendian;
-
- int latency_format;
-
- int old_format;
-
- int cpus;
- int long_size;
- int page_size;
-
- struct cmdline *cmdlines;
- struct cmdline_list *cmdlist;
- int cmdline_count;
-
- struct func_map *func_map;
- struct func_resolver *func_resolver;
- struct func_list *funclist;
- unsigned int func_count;
-
- struct printk_map *printk_map;
- struct printk_list *printklist;
- unsigned int printk_count;
-
-
- struct event_format **events;
- int nr_events;
- struct event_format **sort_events;
- enum event_sort_type last_type;
-
- int type_offset;
- int type_size;
-
- int pid_offset;
- int pid_size;
-
- int pc_offset;
- int pc_size;
-
- int flags_offset;
- int flags_size;
-
- int ld_offset;
- int ld_size;
-
- int print_raw;
-
- int test_filters;
-
- int flags;
-
- struct format_field *bprint_ip_field;
- struct format_field *bprint_fmt_field;
- struct format_field *bprint_buf_field;
-
- struct event_handler *handlers;
- struct tep_function_handler *func_handlers;
-
- /* cache */
- struct event_format *last_event;
-
- char *trace_clock;
-};
-
-static inline void tep_set_flag(struct tep_handle *pevent, int flag)
-{
- pevent->flags |= flag;
-}
-
-static inline unsigned short
-__data2host2(struct tep_handle *pevent, unsigned short data)
-{
- unsigned short swap;
-
- if (pevent->host_bigendian == pevent->file_bigendian)
- return data;
-
- swap = ((data & 0xffULL) << 8) |
- ((data & (0xffULL << 8)) >> 8);
-
- return swap;
-}
-
-static inline unsigned int
-__data2host4(struct tep_handle *pevent, unsigned int data)
-{
- unsigned int swap;
-
- if (pevent->host_bigendian == pevent->file_bigendian)
- return data;
-
- swap = ((data & 0xffULL) << 24) |
- ((data & (0xffULL << 8)) << 8) |
- ((data & (0xffULL << 16)) >> 8) |
- ((data & (0xffULL << 24)) >> 24);
-
- return swap;
-}
-
-static inline unsigned long long
-__data2host8(struct tep_handle *pevent, unsigned long long data)
-{
- unsigned long long swap;
-
- if (pevent->host_bigendian == pevent->file_bigendian)
- return data;
-
- swap = ((data & 0xffULL) << 56) |
- ((data & (0xffULL << 8)) << 40) |
- ((data & (0xffULL << 16)) << 24) |
- ((data & (0xffULL << 24)) << 8) |
- ((data & (0xffULL << 32)) >> 8) |
- ((data & (0xffULL << 40)) >> 24) |
- ((data & (0xffULL << 48)) >> 40) |
- ((data & (0xffULL << 56)) >> 56);
-
- return swap;
-}
-
-#define data2host2(pevent, ptr) __data2host2(pevent, *(unsigned short *)(ptr))
-#define data2host4(pevent, ptr) __data2host4(pevent, *(unsigned int *)(ptr))
-#define data2host8(pevent, ptr) \
-({ \
- unsigned long long __val; \
- \
- memcpy(&__val, (ptr), sizeof(unsigned long long)); \
- __data2host8(pevent, __val); \
-})
-
-static inline int tep_host_bigendian(void)
+static inline int tep_is_bigendian(void)
{
unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
unsigned int val;
@@ -615,331 +430,294 @@
TRACE_FLAG_SOFTIRQ = 0x10,
};
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv);
-void tep_reset_function_resolver(struct tep_handle *pevent);
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
-int tep_register_function(struct tep_handle *pevent, char *name,
+void tep_reset_function_resolver(struct tep_handle *tep);
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_register_function(struct tep_handle *tep, char *name,
unsigned long long addr, char *mod);
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr);
-int tep_pid_is_registered(struct tep_handle *pevent, int pid);
+bool tep_is_pid_registered(struct tep_handle *tep, int pid);
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record);
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record,
- bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
- struct event_format *event,
- struct tep_record *record);
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
- struct tep_record *record, bool use_trace_clock);
+struct tep_event *tep_get_event(struct tep_handle *tep, int index);
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+#define TEP_PRINT_INFO "INFO"
+#define TEP_PRINT_INFO_RAW "INFO_RAW"
+#define TEP_PRINT_COMM "COMM"
+#define TEP_PRINT_LATENCY "LATENCY"
+#define TEP_PRINT_NAME "NAME"
+#define TEP_PRINT_PID 1U
+#define TEP_PRINT_TIME 2U
+#define TEP_PRINT_CPU 3U
+
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
+ struct tep_record *record, const char *fmt, ...)
+ __attribute__ ((format (printf, 4, 5)));
+
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size);
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys);
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
- struct event_format **eventp,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
+ struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys);
-void tep_free_format(struct event_format *event);
-void tep_free_format_field(struct format_field *field);
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
int *len, int err);
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err);
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err);
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event,
const char *name, struct tep_record *record,
unsigned long long *val, int err);
int tep_print_num_field(struct trace_seq *s, const char *fmt,
- struct event_format *event, const char *name,
- struct tep_record *record, int err);
+ struct tep_event *event, const char *name,
+ struct tep_record *record, int err);
int tep_print_func_field(struct trace_seq *s, const char *fmt,
- struct event_format *event, const char *name,
+ struct tep_event *event, const char *name,
struct tep_record *record, int err);
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+enum tep_reg_handler {
+ TEP_REGISTER_SUCCESS = 0,
+ TEP_REGISTER_SUCCESS_OVERWRITE,
+};
+
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...);
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name);
-struct format_field *tep_find_common_field(struct event_format *event, const char *name);
-struct format_field *tep_find_field(struct event_format *event, const char *name);
-struct format_field *tep_find_any_field(struct event_format *event, const char *name);
+struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name);
+struct tep_format_field *tep_find_field(struct tep_event *event, const char *name);
+struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name);
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr);
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
-unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
-int tep_read_number_field(struct format_field *field, const void *data,
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr);
+unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size);
+int tep_read_number_field(struct tep_format_field *field, const void *data,
unsigned long long *value);
-struct event_format *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event *tep_get_first_event(struct tep_handle *tep);
+int tep_get_events_count(struct tep_handle *tep);
+struct tep_event *tep_find_event(struct tep_handle *tep, int id);
-struct event_format *
-tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
+struct tep_event *
+tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name);
+struct tep_event *
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
-struct event_format *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
-
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record);
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type);
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
-struct cmdline;
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
- struct cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec);
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid);
+struct tep_cmdline;
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
+ struct tep_cmdline *next);
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline);
void tep_print_field(struct trace_seq *s, void *data,
- struct format_field *field);
+ struct tep_format_field *field);
void tep_print_fields(struct trace_seq *s, void *data,
- int size __maybe_unused, struct event_format *event);
-void tep_event_info(struct trace_seq *s, struct event_format *event,
- struct tep_record *record);
-int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
- char *buf, size_t buflen);
+ int size __maybe_unused, struct tep_event *event);
+int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
+ char *buf, size_t buflen);
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
-struct format_field **tep_event_common_fields(struct event_format *event);
-struct format_field **tep_event_fields(struct event_format *event);
+struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type);
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type);
+struct tep_format_field **tep_event_common_fields(struct tep_event *event);
+struct tep_format_field **tep_event_fields(struct tep_event *event);
-static inline int tep_get_cpus(struct tep_handle *pevent)
-{
- return pevent->cpus;
-}
-
-static inline void tep_set_cpus(struct tep_handle *pevent, int cpus)
-{
- pevent->cpus = cpus;
-}
-
-static inline int tep_get_long_size(struct tep_handle *pevent)
-{
- return pevent->long_size;
-}
-
-static inline void tep_set_long_size(struct tep_handle *pevent, int long_size)
-{
- pevent->long_size = long_size;
-}
-
-static inline int tep_get_page_size(struct tep_handle *pevent)
-{
- return pevent->page_size;
-}
-
-static inline void tep_set_page_size(struct tep_handle *pevent, int _page_size)
-{
- pevent->page_size = _page_size;
-}
-
-static inline int tep_is_file_bigendian(struct tep_handle *pevent)
-{
- return pevent->file_bigendian;
-}
-
-static inline void tep_set_file_bigendian(struct tep_handle *pevent, int endian)
-{
- pevent->file_bigendian = endian;
-}
-
-static inline int tep_is_host_bigendian(struct tep_handle *pevent)
-{
- return pevent->host_bigendian;
-}
-
-static inline void tep_set_host_bigendian(struct tep_handle *pevent, int endian)
-{
- pevent->host_bigendian = endian;
-}
-
-static inline int tep_is_latency_format(struct tep_handle *pevent)
-{
- return pevent->latency_format;
-}
-
-static inline void tep_set_latency_format(struct tep_handle *pevent, int lat)
-{
- pevent->latency_format = lat;
-}
+enum tep_endian {
+ TEP_LITTLE_ENDIAN = 0,
+ TEP_BIG_ENDIAN
+};
+int tep_get_cpus(struct tep_handle *tep);
+void tep_set_cpus(struct tep_handle *tep, int cpus);
+int tep_get_long_size(struct tep_handle *tep);
+void tep_set_long_size(struct tep_handle *tep, int long_size);
+int tep_get_page_size(struct tep_handle *tep);
+void tep_set_page_size(struct tep_handle *tep, int _page_size);
+bool tep_is_file_bigendian(struct tep_handle *tep);
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_local_bigendian(struct tep_handle *tep);
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
+int tep_get_header_page_size(struct tep_handle *tep);
+int tep_get_header_timestamp_size(struct tep_handle *tep);
+bool tep_is_old_format(struct tep_handle *tep);
+void tep_set_test_filters(struct tep_handle *tep, int test_filters);
struct tep_handle *tep_alloc(void);
-void tep_free(struct tep_handle *pevent);
-void tep_ref(struct tep_handle *pevent);
-void tep_unref(struct tep_handle *pevent);
+void tep_free(struct tep_handle *tep);
+void tep_ref(struct tep_handle *tep);
+void tep_unref(struct tep_handle *tep);
+int tep_get_ref(struct tep_handle *tep);
/* access to the internal parser */
void tep_buffer_init(const char *buf, unsigned long long size);
-enum event_type tep_read_token(char **tok);
+enum tep_event_type tep_read_token(char **tok);
void tep_free_token(char *token);
int tep_peek_char(void);
const char *tep_get_input_buf(void);
unsigned long long tep_get_input_buf_ptr(void);
/* for debugging */
-void tep_print_funcs(struct tep_handle *pevent);
-void tep_print_printk(struct tep_handle *pevent);
+void tep_print_funcs(struct tep_handle *tep);
+void tep_print_printk(struct tep_handle *tep);
/* ----------------------- filtering ----------------------- */
-enum filter_boolean_type {
- FILTER_FALSE,
- FILTER_TRUE,
+enum tep_filter_boolean_type {
+ TEP_FILTER_FALSE,
+ TEP_FILTER_TRUE,
};
-enum filter_op_type {
- FILTER_OP_AND = 1,
- FILTER_OP_OR,
- FILTER_OP_NOT,
+enum tep_filter_op_type {
+ TEP_FILTER_OP_AND = 1,
+ TEP_FILTER_OP_OR,
+ TEP_FILTER_OP_NOT,
};
-enum filter_cmp_type {
- FILTER_CMP_NONE,
- FILTER_CMP_EQ,
- FILTER_CMP_NE,
- FILTER_CMP_GT,
- FILTER_CMP_LT,
- FILTER_CMP_GE,
- FILTER_CMP_LE,
- FILTER_CMP_MATCH,
- FILTER_CMP_NOT_MATCH,
- FILTER_CMP_REGEX,
- FILTER_CMP_NOT_REGEX,
+enum tep_filter_cmp_type {
+ TEP_FILTER_CMP_NONE,
+ TEP_FILTER_CMP_EQ,
+ TEP_FILTER_CMP_NE,
+ TEP_FILTER_CMP_GT,
+ TEP_FILTER_CMP_LT,
+ TEP_FILTER_CMP_GE,
+ TEP_FILTER_CMP_LE,
+ TEP_FILTER_CMP_MATCH,
+ TEP_FILTER_CMP_NOT_MATCH,
+ TEP_FILTER_CMP_REGEX,
+ TEP_FILTER_CMP_NOT_REGEX,
};
-enum filter_exp_type {
- FILTER_EXP_NONE,
- FILTER_EXP_ADD,
- FILTER_EXP_SUB,
- FILTER_EXP_MUL,
- FILTER_EXP_DIV,
- FILTER_EXP_MOD,
- FILTER_EXP_RSHIFT,
- FILTER_EXP_LSHIFT,
- FILTER_EXP_AND,
- FILTER_EXP_OR,
- FILTER_EXP_XOR,
- FILTER_EXP_NOT,
+enum tep_filter_exp_type {
+ TEP_FILTER_EXP_NONE,
+ TEP_FILTER_EXP_ADD,
+ TEP_FILTER_EXP_SUB,
+ TEP_FILTER_EXP_MUL,
+ TEP_FILTER_EXP_DIV,
+ TEP_FILTER_EXP_MOD,
+ TEP_FILTER_EXP_RSHIFT,
+ TEP_FILTER_EXP_LSHIFT,
+ TEP_FILTER_EXP_AND,
+ TEP_FILTER_EXP_OR,
+ TEP_FILTER_EXP_XOR,
+ TEP_FILTER_EXP_NOT,
};
-enum filter_arg_type {
- FILTER_ARG_NONE,
- FILTER_ARG_BOOLEAN,
- FILTER_ARG_VALUE,
- FILTER_ARG_FIELD,
- FILTER_ARG_EXP,
- FILTER_ARG_OP,
- FILTER_ARG_NUM,
- FILTER_ARG_STR,
+enum tep_filter_arg_type {
+ TEP_FILTER_ARG_NONE,
+ TEP_FILTER_ARG_BOOLEAN,
+ TEP_FILTER_ARG_VALUE,
+ TEP_FILTER_ARG_FIELD,
+ TEP_FILTER_ARG_EXP,
+ TEP_FILTER_ARG_OP,
+ TEP_FILTER_ARG_NUM,
+ TEP_FILTER_ARG_STR,
};
-enum filter_value_type {
- FILTER_NUMBER,
- FILTER_STRING,
- FILTER_CHAR
+enum tep_filter_value_type {
+ TEP_FILTER_NUMBER,
+ TEP_FILTER_STRING,
+ TEP_FILTER_CHAR
};
-struct fliter_arg;
+struct tep_filter_arg;
-struct filter_arg_boolean {
- enum filter_boolean_type value;
+struct tep_filter_arg_boolean {
+ enum tep_filter_boolean_type value;
};
-struct filter_arg_field {
- struct format_field *field;
+struct tep_filter_arg_field {
+ struct tep_format_field *field;
};
-struct filter_arg_value {
- enum filter_value_type type;
+struct tep_filter_arg_value {
+ enum tep_filter_value_type type;
union {
char *str;
unsigned long long val;
};
};
-struct filter_arg_op {
- enum filter_op_type type;
- struct filter_arg *left;
- struct filter_arg *right;
+struct tep_filter_arg_op {
+ enum tep_filter_op_type type;
+ struct tep_filter_arg *left;
+ struct tep_filter_arg *right;
};
-struct filter_arg_exp {
- enum filter_exp_type type;
- struct filter_arg *left;
- struct filter_arg *right;
+struct tep_filter_arg_exp {
+ enum tep_filter_exp_type type;
+ struct tep_filter_arg *left;
+ struct tep_filter_arg *right;
};
-struct filter_arg_num {
- enum filter_cmp_type type;
- struct filter_arg *left;
- struct filter_arg *right;
+struct tep_filter_arg_num {
+ enum tep_filter_cmp_type type;
+ struct tep_filter_arg *left;
+ struct tep_filter_arg *right;
};
-struct filter_arg_str {
- enum filter_cmp_type type;
- struct format_field *field;
- char *val;
- char *buffer;
- regex_t reg;
+struct tep_filter_arg_str {
+ enum tep_filter_cmp_type type;
+ struct tep_format_field *field;
+ char *val;
+ char *buffer;
+ regex_t reg;
};
-struct filter_arg {
- enum filter_arg_type type;
+struct tep_filter_arg {
+ enum tep_filter_arg_type type;
union {
- struct filter_arg_boolean boolean;
- struct filter_arg_field field;
- struct filter_arg_value value;
- struct filter_arg_op op;
- struct filter_arg_exp exp;
- struct filter_arg_num num;
- struct filter_arg_str str;
+ struct tep_filter_arg_boolean boolean;
+ struct tep_filter_arg_field field;
+ struct tep_filter_arg_value value;
+ struct tep_filter_arg_op op;
+ struct tep_filter_arg_exp exp;
+ struct tep_filter_arg_num num;
+ struct tep_filter_arg_str str;
};
};
-struct filter_type {
+struct tep_filter_type {
int event_id;
- struct event_format *event;
- struct filter_arg *filter;
+ struct tep_event *event;
+ struct tep_filter_arg *filter;
};
#define TEP_FILTER_ERROR_BUFSZ 1024
-struct event_filter {
- struct tep_handle *pevent;
+struct tep_event_filter {
+ struct tep_handle *tep;
int filters;
- struct filter_type *event_filters;
+ struct tep_filter_type *event_filters;
char error_buffer[TEP_FILTER_ERROR_BUFSZ];
};
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep);
/* for backward compatibility */
#define FILTER_NONE TEP_ERRNO__NO_FILTER
@@ -947,45 +725,29 @@
#define FILTER_MISS TEP_ERRNO__FILTER_MISS
#define FILTER_MATCH TEP_ERRNO__FILTER_MATCH
-enum filter_trivial_type {
- FILTER_TRIVIAL_FALSE,
- FILTER_TRIVIAL_TRUE,
- FILTER_TRIVIAL_BOTH,
-};
-
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str);
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
struct tep_record *record);
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
char *buf, size_t buflen);
-int tep_event_filtered(struct event_filter *filter,
+int tep_event_filtered(struct tep_event_filter *filter,
int event_id);
-void tep_filter_reset(struct event_filter *filter);
+void tep_filter_reset(struct tep_event_filter *filter);
-int tep_filter_clear_trivial(struct event_filter *filter,
- enum filter_trivial_type type);
+void tep_filter_free(struct tep_event_filter *filter);
-void tep_filter_free(struct event_filter *filter);
+char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
-char *tep_filter_make_string(struct event_filter *filter, int event_id);
-
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
int event_id);
-int tep_filter_event_has_trivial(struct event_filter *filter,
- int event_id,
- enum filter_trivial_type type);
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source);
-
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
- enum filter_trivial_type type);
-
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2);
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
#endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index f17e250..e1f7ddd 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -14,9 +14,11 @@
#include <unistd.h>
#include <dirent.h>
#include "event-parse.h"
+#include "event-parse-local.h"
#include "event-utils.h"
+#include "trace-seq.h"
-#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+#define LOCAL_PLUGIN_DIR ".local/lib/traceevent/plugins/"
static struct registered_plugin_options {
struct registered_plugin_options *next;
@@ -30,8 +32,8 @@
char *value;
} *trace_plugin_options;
-struct plugin_list {
- struct plugin_list *next;
+struct tep_plugin_list {
+ struct tep_plugin_list *next;
char *name;
void *handle;
};
@@ -258,7 +260,7 @@
*/
void tep_print_plugins(struct trace_seq *s,
const char *prefix, const char *suffix,
- const struct plugin_list *list)
+ const struct tep_plugin_list *list)
{
while (list) {
trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
@@ -267,12 +269,12 @@
}
static void
-load_plugin(struct tep_handle *pevent, const char *path,
+load_plugin(struct tep_handle *tep, const char *path,
const char *file, void *data)
{
- struct plugin_list **plugin_list = data;
+ struct tep_plugin_list **plugin_list = data;
tep_plugin_load_func func;
- struct plugin_list *list;
+ struct tep_plugin_list *list;
const char *alias;
char *plugin;
void *handle;
@@ -314,7 +316,7 @@
*plugin_list = list;
pr_stat("registering plugin: %s", plugin);
- func(pevent);
+ func(tep);
return;
out_free:
@@ -322,9 +324,9 @@
}
static void
-load_plugins_dir(struct tep_handle *pevent, const char *suffix,
+load_plugins_dir(struct tep_handle *tep, const char *suffix,
const char *path,
- void (*load_plugin)(struct tep_handle *pevent,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
@@ -357,15 +359,15 @@
if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
continue;
- load_plugin(pevent, path, name, data);
+ load_plugin(tep, path, name, data);
}
closedir(dir);
}
static void
-load_plugins(struct tep_handle *pevent, const char *suffix,
- void (*load_plugin)(struct tep_handle *pevent,
+load_plugins(struct tep_handle *tep, const char *suffix,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
@@ -376,7 +378,7 @@
char *envdir;
int ret;
- if (pevent->flags & TEP_DISABLE_PLUGINS)
+ if (tep->flags & TEP_DISABLE_PLUGINS)
return;
/*
@@ -384,8 +386,8 @@
* check that first.
*/
#ifdef PLUGIN_DIR
- if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS))
- load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+ if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS))
+ load_plugins_dir(tep, suffix, PLUGIN_DIR,
load_plugin, data);
#endif
@@ -395,7 +397,7 @@
*/
envdir = getenv("TRACEEVENT_PLUGIN_DIR");
if (envdir)
- load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+ load_plugins_dir(tep, suffix, envdir, load_plugin, data);
/*
* Now let the home directory override the environment
@@ -411,32 +413,32 @@
return;
}
- load_plugins_dir(pevent, suffix, path, load_plugin, data);
+ load_plugins_dir(tep, suffix, path, load_plugin, data);
free(path);
}
-struct plugin_list*
-tep_load_plugins(struct tep_handle *pevent)
+struct tep_plugin_list*
+tep_load_plugins(struct tep_handle *tep)
{
- struct plugin_list *list = NULL;
+ struct tep_plugin_list *list = NULL;
- load_plugins(pevent, ".so", load_plugin, &list);
+ load_plugins(tep, ".so", load_plugin, &list);
return list;
}
void
-tep_unload_plugins(struct plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep)
{
tep_plugin_unload_func func;
- struct plugin_list *list;
+ struct tep_plugin_list *list;
while (plugin_list) {
list = plugin_list;
plugin_list = list->next;
func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME);
if (func)
- func(pevent);
+ func(tep);
dlclose(list->handle);
free(list->name);
free(list);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index af2a1f3..b887e74 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -727,3 +727,52 @@
{
return kbuf->start;
}
+
+/**
+ * kbuffer_raw_get - get raw buffer info
+ * @kbuf: The kbuffer
+ * @subbuf: Start of mapped subbuffer
+ * @info: Info descriptor to fill in
+ *
+ * For debugging. This can return internals of the ring buffer.
+ * Expects to have info->next set to what it will read.
+ * The type, length and timestamp delta will be filled in, and
+ * @info->next will be updated to the next element.
+ * The @subbuf is used to know if the info is passed the end of
+ * data and NULL will be returned if it is.
+ */
+struct kbuffer_raw_info *
+kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info)
+{
+ unsigned long long flags;
+ unsigned long long delta;
+ unsigned int type_len;
+ unsigned int size;
+ int start;
+ int length;
+ void *ptr = info->next;
+
+ if (!kbuf || !subbuf)
+ return NULL;
+
+ if (kbuf->flags & KBUFFER_FL_LONG_8)
+ start = 16;
+ else
+ start = 12;
+
+ flags = read_long(kbuf, subbuf + 8);
+ size = (unsigned int)flags & COMMIT_MASK;
+
+ if (ptr < subbuf || ptr >= subbuf + start + size)
+ return NULL;
+
+ type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
+
+ info->next = ptr + length;
+
+ info->type = type_len;
+ info->delta = delta;
+ info->length = length;
+
+ return info;
+}
diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h
index 03dce75..ed4d697 100644
--- a/tools/lib/traceevent/kbuffer.h
+++ b/tools/lib/traceevent/kbuffer.h
@@ -65,4 +65,17 @@
void kbuffer_set_old_format(struct kbuffer *kbuf);
int kbuffer_start_of_data(struct kbuffer *kbuf);
+/* Debugging */
+
+struct kbuffer_raw_info {
+ int type;
+ int length;
+ unsigned long long delta;
+ void *next;
+};
+
+/* Read raw data */
+struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf,
+ struct kbuffer_raw_info *info);
+
#endif /* _K_BUFFER_H */
diff --git a/tools/lib/traceevent/libtraceevent.pc.template b/tools/lib/traceevent/libtraceevent.pc.template
new file mode 100644
index 0000000..86384fc
--- /dev/null
+++ b/tools/lib/traceevent/libtraceevent.pc.template
@@ -0,0 +1,10 @@
+prefix=INSTALL_PREFIX
+libdir=LIB_DIR
+includedir=HEADER_DIR
+
+Name: libtraceevent
+URL: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+Description: Linux kernel trace event library
+Version: LIB_VERSION
+Cflags: -I${includedir}
+Libs: -L${libdir} -ltraceevent
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index e76154c..552592d 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -11,22 +11,23 @@
#include <sys/types.h>
#include "event-parse.h"
+#include "event-parse-local.h"
#include "event-utils.h"
#define COMM "COMM"
#define CPU "CPU"
-static struct format_field comm = {
+static struct tep_format_field comm = {
.name = "COMM",
};
-static struct format_field cpu = {
+static struct tep_format_field cpu = {
.name = "CPU",
};
struct event_list {
struct event_list *next;
- struct event_format *event;
+ struct tep_event *event;
};
static void show_error(char *error_buf, const char *fmt, ...)
@@ -61,15 +62,15 @@
tep_free_token(token);
}
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
{
- enum event_type type;
+ enum tep_event_type type;
char *token = NULL;
do {
free_token(token);
type = tep_read_token(&token);
- } while (type == EVENT_NEWLINE || type == EVENT_SPACE);
+ } while (type == TEP_EVENT_NEWLINE || type == TEP_EVENT_SPACE);
/* If token is = or ! check to see if the next char is ~ */
if (token &&
@@ -79,7 +80,7 @@
*tok = malloc(3);
if (*tok == NULL) {
free_token(token);
- return EVENT_ERROR;
+ return TEP_EVENT_ERROR;
}
sprintf(*tok, "%c%c", *token, '~');
free_token(token);
@@ -94,8 +95,8 @@
static int filter_cmp(const void *a, const void *b)
{
- const struct filter_type *ea = a;
- const struct filter_type *eb = b;
+ const struct tep_filter_type *ea = a;
+ const struct tep_filter_type *eb = b;
if (ea->event_id < eb->event_id)
return -1;
@@ -106,11 +107,11 @@
return 0;
}
-static struct filter_type *
-find_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+find_filter_type(struct tep_event_filter *filter, int id)
{
- struct filter_type *filter_type;
- struct filter_type key;
+ struct tep_filter_type *filter_type;
+ struct tep_filter_type key;
key.event_id = id;
@@ -122,10 +123,10 @@
return filter_type;
}
-static struct filter_type *
-add_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+add_filter_type(struct tep_event_filter *filter, int id)
{
- struct filter_type *filter_type;
+ struct tep_filter_type *filter_type;
int i;
filter_type = find_filter_type(filter, id);
@@ -153,7 +154,7 @@
filter_type = &filter->event_filters[i];
filter_type->event_id = id;
- filter_type->event = tep_find_event(filter->pevent, id);
+ filter_type->event = tep_find_event(filter->tep, id);
filter_type->filter = NULL;
filter->filters++;
@@ -163,61 +164,61 @@
/**
* tep_filter_alloc - create a new event filter
- * @pevent: The pevent that this filter is associated with
+ * @tep: The tep that this filter is associated with
*/
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep)
{
- struct event_filter *filter;
+ struct tep_event_filter *filter;
filter = malloc(sizeof(*filter));
if (filter == NULL)
return NULL;
memset(filter, 0, sizeof(*filter));
- filter->pevent = pevent;
- tep_ref(pevent);
+ filter->tep = tep;
+ tep_ref(tep);
return filter;
}
-static struct filter_arg *allocate_arg(void)
+static struct tep_filter_arg *allocate_arg(void)
{
- return calloc(1, sizeof(struct filter_arg));
+ return calloc(1, sizeof(struct tep_filter_arg));
}
-static void free_arg(struct filter_arg *arg)
+static void free_arg(struct tep_filter_arg *arg)
{
if (!arg)
return;
switch (arg->type) {
- case FILTER_ARG_NONE:
- case FILTER_ARG_BOOLEAN:
+ case TEP_FILTER_ARG_NONE:
+ case TEP_FILTER_ARG_BOOLEAN:
break;
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
free_arg(arg->num.left);
free_arg(arg->num.right);
break;
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
free_arg(arg->exp.left);
free_arg(arg->exp.right);
break;
- case FILTER_ARG_STR:
+ case TEP_FILTER_ARG_STR:
free(arg->str.val);
regfree(&arg->str.reg);
free(arg->str.buffer);
break;
- case FILTER_ARG_VALUE:
- if (arg->value.type == FILTER_STRING ||
- arg->value.type == FILTER_CHAR)
+ case TEP_FILTER_ARG_VALUE:
+ if (arg->value.type == TEP_FILTER_STRING ||
+ arg->value.type == TEP_FILTER_CHAR)
free(arg->value.str);
break;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
free_arg(arg->op.left);
free_arg(arg->op.right);
default:
@@ -228,7 +229,7 @@
}
static int add_event(struct event_list **events,
- struct event_format *event)
+ struct tep_event *event)
{
struct event_list *list;
@@ -242,7 +243,7 @@
return 0;
}
-static int event_match(struct event_format *event,
+static int event_match(struct tep_event *event,
regex_t *sreg, regex_t *ereg)
{
if (sreg) {
@@ -255,10 +256,10 @@
}
static enum tep_errno
-find_event(struct tep_handle *pevent, struct event_list **events,
+find_event(struct tep_handle *tep, struct event_list **events,
char *sys_name, char *event_name)
{
- struct event_format *event;
+ struct tep_event *event;
regex_t ereg;
regex_t sreg;
int match = 0;
@@ -298,8 +299,8 @@
}
}
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
match = 1;
if (add_event(events, event) < 0) {
@@ -333,11 +334,11 @@
}
static enum tep_errno
-create_arg_item(struct event_format *event, const char *token,
- enum event_type type, struct filter_arg **parg, char *error_str)
+create_arg_item(struct tep_event *event, const char *token,
+ enum tep_event_type type, struct tep_filter_arg **parg, char *error_str)
{
- struct format_field *field;
- struct filter_arg *arg;
+ struct tep_format_field *field;
+ struct tep_filter_arg *arg;
arg = allocate_arg();
if (arg == NULL) {
@@ -347,11 +348,11 @@
switch (type) {
- case EVENT_SQUOTE:
- case EVENT_DQUOTE:
- arg->type = FILTER_ARG_VALUE;
+ case TEP_EVENT_SQUOTE:
+ case TEP_EVENT_DQUOTE:
+ arg->type = TEP_FILTER_ARG_VALUE;
arg->value.type =
- type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
+ type == TEP_EVENT_DQUOTE ? TEP_FILTER_STRING : TEP_FILTER_CHAR;
arg->value.str = strdup(token);
if (!arg->value.str) {
free_arg(arg);
@@ -359,11 +360,11 @@
return TEP_ERRNO__MEM_ALLOC_FAILED;
}
break;
- case EVENT_ITEM:
+ case TEP_EVENT_ITEM:
/* if it is a number, then convert it */
if (isdigit(token[0])) {
- arg->type = FILTER_ARG_VALUE;
- arg->value.type = FILTER_NUMBER;
+ arg->type = TEP_FILTER_ARG_VALUE;
+ arg->value.type = TEP_FILTER_NUMBER;
arg->value.val = strtoull(token, NULL, 0);
break;
}
@@ -377,12 +378,12 @@
field = &cpu;
} else {
/* not a field, Make it false */
- arg->type = FILTER_ARG_BOOLEAN;
- arg->boolean.value = FILTER_FALSE;
+ arg->type = TEP_FILTER_ARG_BOOLEAN;
+ arg->boolean.value = TEP_FILTER_FALSE;
break;
}
}
- arg->type = FILTER_ARG_FIELD;
+ arg->type = TEP_FILTER_ARG_FIELD;
arg->field.field = field;
break;
default:
@@ -394,82 +395,82 @@
return 0;
}
-static struct filter_arg *
-create_arg_op(enum filter_op_type btype)
+static struct tep_filter_arg *
+create_arg_op(enum tep_filter_op_type btype)
{
- struct filter_arg *arg;
+ struct tep_filter_arg *arg;
arg = allocate_arg();
if (!arg)
return NULL;
- arg->type = FILTER_ARG_OP;
+ arg->type = TEP_FILTER_ARG_OP;
arg->op.type = btype;
return arg;
}
-static struct filter_arg *
-create_arg_exp(enum filter_exp_type etype)
+static struct tep_filter_arg *
+create_arg_exp(enum tep_filter_exp_type etype)
{
- struct filter_arg *arg;
+ struct tep_filter_arg *arg;
arg = allocate_arg();
if (!arg)
return NULL;
- arg->type = FILTER_ARG_EXP;
+ arg->type = TEP_FILTER_ARG_EXP;
arg->exp.type = etype;
return arg;
}
-static struct filter_arg *
-create_arg_cmp(enum filter_cmp_type ctype)
+static struct tep_filter_arg *
+create_arg_cmp(enum tep_filter_cmp_type ctype)
{
- struct filter_arg *arg;
+ struct tep_filter_arg *arg;
arg = allocate_arg();
if (!arg)
return NULL;
/* Use NUM and change if necessary */
- arg->type = FILTER_ARG_NUM;
+ arg->type = TEP_FILTER_ARG_NUM;
arg->num.type = ctype;
return arg;
}
static enum tep_errno
-add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
+add_right(struct tep_filter_arg *op, struct tep_filter_arg *arg, char *error_str)
{
- struct filter_arg *left;
+ struct tep_filter_arg *left;
char *str;
int op_type;
int ret;
switch (op->type) {
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
if (op->exp.right)
goto out_fail;
op->exp.right = arg;
break;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
if (op->op.right)
goto out_fail;
op->op.right = arg;
break;
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
if (op->op.right)
goto out_fail;
/*
* The arg must be num, str, or field
*/
switch (arg->type) {
- case FILTER_ARG_VALUE:
- case FILTER_ARG_FIELD:
+ case TEP_FILTER_ARG_VALUE:
+ case TEP_FILTER_ARG_FIELD:
break;
default:
show_error(error_str, "Illegal rvalue");
@@ -481,20 +482,20 @@
* convert this to a string or regex.
*/
switch (arg->value.type) {
- case FILTER_CHAR:
+ case TEP_FILTER_CHAR:
/*
* A char should be converted to number if
* the string is 1 byte, and the compare
* is not a REGEX.
*/
if (strlen(arg->value.str) == 1 &&
- op->num.type != FILTER_CMP_REGEX &&
- op->num.type != FILTER_CMP_NOT_REGEX) {
- arg->value.type = FILTER_NUMBER;
+ op->num.type != TEP_FILTER_CMP_REGEX &&
+ op->num.type != TEP_FILTER_CMP_NOT_REGEX) {
+ arg->value.type = TEP_FILTER_NUMBER;
goto do_int;
}
/* fall through */
- case FILTER_STRING:
+ case TEP_FILTER_STRING:
/* convert op to a string arg */
op_type = op->num.type;
@@ -508,16 +509,16 @@
* If left arg was a field not found then
* NULL the entire op.
*/
- if (left->type == FILTER_ARG_BOOLEAN) {
+ if (left->type == TEP_FILTER_ARG_BOOLEAN) {
free_arg(left);
free_arg(arg);
- op->type = FILTER_ARG_BOOLEAN;
- op->boolean.value = FILTER_FALSE;
+ op->type = TEP_FILTER_ARG_BOOLEAN;
+ op->boolean.value = TEP_FILTER_FALSE;
break;
}
/* Left arg must be a field */
- if (left->type != FILTER_ARG_FIELD) {
+ if (left->type != TEP_FILTER_ARG_FIELD) {
show_error(error_str,
"Illegal lvalue for string comparison");
return TEP_ERRNO__ILLEGAL_LVALUE;
@@ -525,15 +526,15 @@
/* Make sure this is a valid string compare */
switch (op_type) {
- case FILTER_CMP_EQ:
- op_type = FILTER_CMP_MATCH;
+ case TEP_FILTER_CMP_EQ:
+ op_type = TEP_FILTER_CMP_MATCH;
break;
- case FILTER_CMP_NE:
- op_type = FILTER_CMP_NOT_MATCH;
+ case TEP_FILTER_CMP_NE:
+ op_type = TEP_FILTER_CMP_NOT_MATCH;
break;
- case FILTER_CMP_REGEX:
- case FILTER_CMP_NOT_REGEX:
+ case TEP_FILTER_CMP_REGEX:
+ case TEP_FILTER_CMP_NOT_REGEX:
ret = regcomp(&op->str.reg, str, REG_ICASE|REG_NOSUB);
if (ret) {
show_error(error_str,
@@ -548,7 +549,7 @@
return TEP_ERRNO__ILLEGAL_STRING_CMP;
}
- op->type = FILTER_ARG_STR;
+ op->type = TEP_FILTER_ARG_STR;
op->str.type = op_type;
op->str.field = left->field.field;
op->str.val = strdup(str);
@@ -573,12 +574,12 @@
break;
- case FILTER_NUMBER:
+ case TEP_FILTER_NUMBER:
do_int:
switch (op->num.type) {
- case FILTER_CMP_REGEX:
- case FILTER_CMP_NOT_REGEX:
+ case TEP_FILTER_CMP_REGEX:
+ case TEP_FILTER_CMP_NOT_REGEX:
show_error(error_str,
"Op not allowed with integers");
return TEP_ERRNO__ILLEGAL_INTEGER_CMP;
@@ -605,35 +606,35 @@
return TEP_ERRNO__SYNTAX_ERROR;
}
-static struct filter_arg *
-rotate_op_right(struct filter_arg *a, struct filter_arg *b)
+static struct tep_filter_arg *
+rotate_op_right(struct tep_filter_arg *a, struct tep_filter_arg *b)
{
- struct filter_arg *arg;
+ struct tep_filter_arg *arg;
arg = a->op.right;
a->op.right = b;
return arg;
}
-static enum tep_errno add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum tep_errno add_left(struct tep_filter_arg *op, struct tep_filter_arg *arg)
{
switch (op->type) {
- case FILTER_ARG_EXP:
- if (arg->type == FILTER_ARG_OP)
+ case TEP_FILTER_ARG_EXP:
+ if (arg->type == TEP_FILTER_ARG_OP)
arg = rotate_op_right(arg, op);
op->exp.left = arg;
break;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
op->op.left = arg;
break;
- case FILTER_ARG_NUM:
- if (arg->type == FILTER_ARG_OP)
+ case TEP_FILTER_ARG_NUM:
+ if (arg->type == TEP_FILTER_ARG_OP)
arg = rotate_op_right(arg, op);
/* left arg of compares must be a field */
- if (arg->type != FILTER_ARG_FIELD &&
- arg->type != FILTER_ARG_BOOLEAN)
+ if (arg->type != TEP_FILTER_ARG_FIELD &&
+ arg->type != TEP_FILTER_ARG_BOOLEAN)
return TEP_ERRNO__INVALID_ARG_TYPE;
op->num.left = arg;
break;
@@ -652,91 +653,91 @@
};
static enum op_type process_op(const char *token,
- enum filter_op_type *btype,
- enum filter_cmp_type *ctype,
- enum filter_exp_type *etype)
+ enum tep_filter_op_type *btype,
+ enum tep_filter_cmp_type *ctype,
+ enum tep_filter_exp_type *etype)
{
- *btype = FILTER_OP_NOT;
- *etype = FILTER_EXP_NONE;
- *ctype = FILTER_CMP_NONE;
+ *btype = TEP_FILTER_OP_NOT;
+ *etype = TEP_FILTER_EXP_NONE;
+ *ctype = TEP_FILTER_CMP_NONE;
if (strcmp(token, "&&") == 0)
- *btype = FILTER_OP_AND;
+ *btype = TEP_FILTER_OP_AND;
else if (strcmp(token, "||") == 0)
- *btype = FILTER_OP_OR;
+ *btype = TEP_FILTER_OP_OR;
else if (strcmp(token, "!") == 0)
return OP_NOT;
- if (*btype != FILTER_OP_NOT)
+ if (*btype != TEP_FILTER_OP_NOT)
return OP_BOOL;
/* Check for value expressions */
if (strcmp(token, "+") == 0) {
- *etype = FILTER_EXP_ADD;
+ *etype = TEP_FILTER_EXP_ADD;
} else if (strcmp(token, "-") == 0) {
- *etype = FILTER_EXP_SUB;
+ *etype = TEP_FILTER_EXP_SUB;
} else if (strcmp(token, "*") == 0) {
- *etype = FILTER_EXP_MUL;
+ *etype = TEP_FILTER_EXP_MUL;
} else if (strcmp(token, "/") == 0) {
- *etype = FILTER_EXP_DIV;
+ *etype = TEP_FILTER_EXP_DIV;
} else if (strcmp(token, "%") == 0) {
- *etype = FILTER_EXP_MOD;
+ *etype = TEP_FILTER_EXP_MOD;
} else if (strcmp(token, ">>") == 0) {
- *etype = FILTER_EXP_RSHIFT;
+ *etype = TEP_FILTER_EXP_RSHIFT;
} else if (strcmp(token, "<<") == 0) {
- *etype = FILTER_EXP_LSHIFT;
+ *etype = TEP_FILTER_EXP_LSHIFT;
} else if (strcmp(token, "&") == 0) {
- *etype = FILTER_EXP_AND;
+ *etype = TEP_FILTER_EXP_AND;
} else if (strcmp(token, "|") == 0) {
- *etype = FILTER_EXP_OR;
+ *etype = TEP_FILTER_EXP_OR;
} else if (strcmp(token, "^") == 0) {
- *etype = FILTER_EXP_XOR;
+ *etype = TEP_FILTER_EXP_XOR;
} else if (strcmp(token, "~") == 0)
- *etype = FILTER_EXP_NOT;
+ *etype = TEP_FILTER_EXP_NOT;
- if (*etype != FILTER_EXP_NONE)
+ if (*etype != TEP_FILTER_EXP_NONE)
return OP_EXP;
/* Check for compares */
if (strcmp(token, "==") == 0)
- *ctype = FILTER_CMP_EQ;
+ *ctype = TEP_FILTER_CMP_EQ;
else if (strcmp(token, "!=") == 0)
- *ctype = FILTER_CMP_NE;
+ *ctype = TEP_FILTER_CMP_NE;
else if (strcmp(token, "<") == 0)
- *ctype = FILTER_CMP_LT;
+ *ctype = TEP_FILTER_CMP_LT;
else if (strcmp(token, ">") == 0)
- *ctype = FILTER_CMP_GT;
+ *ctype = TEP_FILTER_CMP_GT;
else if (strcmp(token, "<=") == 0)
- *ctype = FILTER_CMP_LE;
+ *ctype = TEP_FILTER_CMP_LE;
else if (strcmp(token, ">=") == 0)
- *ctype = FILTER_CMP_GE;
+ *ctype = TEP_FILTER_CMP_GE;
else if (strcmp(token, "=~") == 0)
- *ctype = FILTER_CMP_REGEX;
+ *ctype = TEP_FILTER_CMP_REGEX;
else if (strcmp(token, "!~") == 0)
- *ctype = FILTER_CMP_NOT_REGEX;
+ *ctype = TEP_FILTER_CMP_NOT_REGEX;
else
return OP_NONE;
return OP_CMP;
}
-static int check_op_done(struct filter_arg *arg)
+static int check_op_done(struct tep_filter_arg *arg)
{
switch (arg->type) {
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
return arg->exp.right != NULL;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
return arg->op.right != NULL;
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
return arg->num.right != NULL;
- case FILTER_ARG_STR:
+ case TEP_FILTER_ARG_STR:
/* A string conversion is always done */
return 1;
- case FILTER_ARG_BOOLEAN:
+ case TEP_FILTER_ARG_BOOLEAN:
/* field not found, is ok */
return 1;
@@ -752,14 +753,14 @@
};
static enum tep_errno
-reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
- struct filter_arg *arg, char *error_str)
+reparent_op_arg(struct tep_filter_arg *parent, struct tep_filter_arg *old_child,
+ struct tep_filter_arg *arg, char *error_str)
{
- struct filter_arg *other_child;
- struct filter_arg **ptr;
+ struct tep_filter_arg *other_child;
+ struct tep_filter_arg **ptr;
- if (parent->type != FILTER_ARG_OP &&
- arg->type != FILTER_ARG_OP) {
+ if (parent->type != TEP_FILTER_ARG_OP &&
+ arg->type != TEP_FILTER_ARG_OP) {
show_error(error_str, "can not reparent other than OP");
return TEP_ERRNO__REPARENT_NOT_OP;
}
@@ -804,7 +805,7 @@
}
/* Returns either filter_vals (success) or tep_errno (failfure) */
-static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+static int test_arg(struct tep_filter_arg *parent, struct tep_filter_arg *arg,
char *error_str)
{
int lval, rval;
@@ -812,16 +813,16 @@
switch (arg->type) {
/* bad case */
- case FILTER_ARG_BOOLEAN:
+ case TEP_FILTER_ARG_BOOLEAN:
return FILTER_VAL_FALSE + arg->boolean.value;
/* good cases: */
- case FILTER_ARG_STR:
- case FILTER_ARG_VALUE:
- case FILTER_ARG_FIELD:
+ case TEP_FILTER_ARG_STR:
+ case TEP_FILTER_ARG_VALUE:
+ case TEP_FILTER_ARG_FIELD:
return FILTER_VAL_NORM;
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
lval = test_arg(arg, arg->exp.left, error_str);
if (lval != FILTER_VAL_NORM)
return lval;
@@ -830,7 +831,7 @@
return rval;
return FILTER_VAL_NORM;
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
lval = test_arg(arg, arg->num.left, error_str);
if (lval != FILTER_VAL_NORM)
return lval;
@@ -839,14 +840,14 @@
return rval;
return FILTER_VAL_NORM;
- case FILTER_ARG_OP:
- if (arg->op.type != FILTER_OP_NOT) {
+ case TEP_FILTER_ARG_OP:
+ if (arg->op.type != TEP_FILTER_OP_NOT) {
lval = test_arg(arg, arg->op.left, error_str);
switch (lval) {
case FILTER_VAL_NORM:
break;
case FILTER_VAL_TRUE:
- if (arg->op.type == FILTER_OP_OR)
+ if (arg->op.type == TEP_FILTER_OP_OR)
return FILTER_VAL_TRUE;
rval = test_arg(arg, arg->op.right, error_str);
if (rval != FILTER_VAL_NORM)
@@ -856,7 +857,7 @@
error_str);
case FILTER_VAL_FALSE:
- if (arg->op.type == FILTER_OP_AND)
+ if (arg->op.type == TEP_FILTER_OP_AND)
return FILTER_VAL_FALSE;
rval = test_arg(arg, arg->op.right, error_str);
if (rval != FILTER_VAL_NORM)
@@ -877,18 +878,18 @@
break;
case FILTER_VAL_TRUE:
- if (arg->op.type == FILTER_OP_OR)
+ if (arg->op.type == TEP_FILTER_OP_OR)
return FILTER_VAL_TRUE;
- if (arg->op.type == FILTER_OP_NOT)
+ if (arg->op.type == TEP_FILTER_OP_NOT)
return FILTER_VAL_FALSE;
return reparent_op_arg(parent, arg, arg->op.left,
error_str);
case FILTER_VAL_FALSE:
- if (arg->op.type == FILTER_OP_AND)
+ if (arg->op.type == TEP_FILTER_OP_AND)
return FILTER_VAL_FALSE;
- if (arg->op.type == FILTER_OP_NOT)
+ if (arg->op.type == TEP_FILTER_OP_NOT)
return FILTER_VAL_TRUE;
return reparent_op_arg(parent, arg, arg->op.left,
@@ -904,8 +905,8 @@
}
/* Remove any unknown event fields */
-static int collapse_tree(struct filter_arg *arg,
- struct filter_arg **arg_collapsed, char *error_str)
+static int collapse_tree(struct tep_filter_arg *arg,
+ struct tep_filter_arg **arg_collapsed, char *error_str)
{
int ret;
@@ -919,7 +920,7 @@
free_arg(arg);
arg = allocate_arg();
if (arg) {
- arg->type = FILTER_ARG_BOOLEAN;
+ arg->type = TEP_FILTER_ARG_BOOLEAN;
arg->boolean.value = ret == FILTER_VAL_TRUE;
} else {
show_error(error_str, "Failed to allocate filter arg");
@@ -939,19 +940,19 @@
}
static enum tep_errno
-process_filter(struct event_format *event, struct filter_arg **parg,
+process_filter(struct tep_event *event, struct tep_filter_arg **parg,
char *error_str, int not)
{
- enum event_type type;
+ enum tep_event_type type;
char *token = NULL;
- struct filter_arg *current_op = NULL;
- struct filter_arg *current_exp = NULL;
- struct filter_arg *left_item = NULL;
- struct filter_arg *arg = NULL;
+ struct tep_filter_arg *current_op = NULL;
+ struct tep_filter_arg *current_exp = NULL;
+ struct tep_filter_arg *left_item = NULL;
+ struct tep_filter_arg *arg = NULL;
enum op_type op_type;
- enum filter_op_type btype;
- enum filter_exp_type etype;
- enum filter_cmp_type ctype;
+ enum tep_filter_op_type btype;
+ enum tep_filter_exp_type etype;
+ enum tep_filter_cmp_type ctype;
enum tep_errno ret;
*parg = NULL;
@@ -960,9 +961,9 @@
free(token);
type = read_token(&token);
switch (type) {
- case EVENT_SQUOTE:
- case EVENT_DQUOTE:
- case EVENT_ITEM:
+ case TEP_EVENT_SQUOTE:
+ case TEP_EVENT_DQUOTE:
+ case TEP_EVENT_ITEM:
ret = create_arg_item(event, token, type, &arg, error_str);
if (ret < 0)
goto fail;
@@ -987,7 +988,7 @@
arg = NULL;
break;
- case EVENT_DELIM:
+ case TEP_EVENT_DELIM:
if (*token == ',') {
show_error(error_str, "Illegal token ','");
ret = TEP_ERRNO__ILLEGAL_TOKEN;
@@ -1054,7 +1055,7 @@
}
break;
- case EVENT_OP:
+ case TEP_EVENT_OP:
op_type = process_op(token, &btype, &ctype, &etype);
/* All expect a left arg except for NOT */
@@ -1139,14 +1140,14 @@
if (ret < 0)
goto fail_syntax;
break;
- case EVENT_NONE:
+ case TEP_EVENT_NONE:
break;
- case EVENT_ERROR:
+ case TEP_EVENT_ERROR:
goto fail_alloc;
default:
goto fail_syntax;
}
- } while (type != EVENT_NONE);
+ } while (type != TEP_EVENT_NONE);
if (!current_op && !current_exp)
goto fail_syntax;
@@ -1179,8 +1180,8 @@
}
static enum tep_errno
-process_event(struct event_format *event, const char *filter_str,
- struct filter_arg **parg, char *error_str)
+process_event(struct tep_event *event, const char *filter_str,
+ struct tep_filter_arg **parg, char *error_str)
{
int ret;
@@ -1196,19 +1197,19 @@
if (*parg == NULL)
return TEP_ERRNO__MEM_ALLOC_FAILED;
- (*parg)->type = FILTER_ARG_BOOLEAN;
- (*parg)->boolean.value = FILTER_FALSE;
+ (*parg)->type = TEP_FILTER_ARG_BOOLEAN;
+ (*parg)->boolean.value = TEP_FILTER_FALSE;
}
return 0;
}
static enum tep_errno
-filter_event(struct event_filter *filter, struct event_format *event,
+filter_event(struct tep_event_filter *filter, struct tep_event *event,
const char *filter_str, char *error_str)
{
- struct filter_type *filter_type;
- struct filter_arg *arg;
+ struct tep_filter_type *filter_type;
+ struct tep_filter_arg *arg;
enum tep_errno ret;
if (filter_str) {
@@ -1222,8 +1223,8 @@
if (arg == NULL)
return TEP_ERRNO__MEM_ALLOC_FAILED;
- arg->type = FILTER_ARG_BOOLEAN;
- arg->boolean.value = FILTER_TRUE;
+ arg->type = TEP_FILTER_ARG_BOOLEAN;
+ arg->boolean.value = TEP_FILTER_TRUE;
}
filter_type = add_filter_type(filter, event->id);
@@ -1237,7 +1238,7 @@
return 0;
}
-static void filter_init_error_buf(struct event_filter *filter)
+static void filter_init_error_buf(struct tep_event_filter *filter)
{
/* clear buffer to reset show error */
tep_buffer_init("", 0);
@@ -1253,10 +1254,10 @@
* negative error code. Use tep_filter_strerror() to see
* actual error message in case of error.
*/
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str)
{
- struct tep_handle *pevent = filter->pevent;
+ struct tep_handle *tep = filter->tep;
struct event_list *event;
struct event_list *events = NULL;
const char *filter_start;
@@ -1312,7 +1313,7 @@
}
/* Find this event */
- ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
+ ret = find_event(tep, &events, strim(sys_name), strim(event_name));
if (ret < 0) {
free_events(events);
free(this_event);
@@ -1333,7 +1334,7 @@
if (ret < 0)
rtn = ret;
- if (ret >= 0 && pevent->test_filters) {
+ if (ret >= 0 && tep->test_filters) {
char *test;
test = tep_filter_make_string(filter, event->event->id);
if (test) {
@@ -1345,13 +1346,10 @@
free_events(events);
- if (rtn >= 0 && pevent->test_filters)
- exit(0);
-
return rtn;
}
-static void free_filter_type(struct filter_type *filter_type)
+static void free_filter_type(struct tep_filter_type *filter_type)
{
free_arg(filter_type->filter);
}
@@ -1365,7 +1363,7 @@
*
* Returns 0 if message was filled successfully, -1 if error
*/
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
char *buf, size_t buflen)
{
if (err <= __TEP_ERRNO__START || err >= __TEP_ERRNO__END)
@@ -1379,7 +1377,7 @@
return 0;
}
- return tep_strerror(filter->pevent, err, buf, buflen);
+ return tep_strerror(filter->tep, err, buf, buflen);
}
/**
@@ -1393,10 +1391,10 @@
* Returns 1: if an event was removed
* 0: if the event was not found
*/
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
int event_id)
{
- struct filter_type *filter_type;
+ struct tep_filter_type *filter_type;
unsigned long len;
if (!filter->filters)
@@ -1428,7 +1426,7 @@
*
* Removes all filters from a filter and resets it.
*/
-void tep_filter_reset(struct event_filter *filter)
+void tep_filter_reset(struct tep_event_filter *filter)
{
int i;
@@ -1440,31 +1438,31 @@
filter->event_filters = NULL;
}
-void tep_filter_free(struct event_filter *filter)
+void tep_filter_free(struct tep_event_filter *filter)
{
- tep_unref(filter->pevent);
+ tep_unref(filter->tep);
tep_filter_reset(filter);
free(filter);
}
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg);
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg);
-static int copy_filter_type(struct event_filter *filter,
- struct event_filter *source,
- struct filter_type *filter_type)
+static int copy_filter_type(struct tep_event_filter *filter,
+ struct tep_event_filter *source,
+ struct tep_filter_type *filter_type)
{
- struct filter_arg *arg;
- struct event_format *event;
+ struct tep_filter_arg *arg;
+ struct tep_event *event;
const char *sys;
const char *name;
char *str;
- /* Can't assume that the pevent's are the same */
+ /* Can't assume that the tep's are the same */
sys = filter_type->event->system;
name = filter_type->event->name;
- event = tep_find_event_by_name(filter->pevent, sys, name);
+ event = tep_find_event_by_name(filter->tep, sys, name);
if (!event)
return -1;
@@ -1478,7 +1476,7 @@
if (arg == NULL)
return -1;
- arg->type = FILTER_ARG_BOOLEAN;
+ arg->type = TEP_FILTER_ARG_BOOLEAN;
if (strcmp(str, "TRUE") == 0)
arg->boolean.value = 1;
else
@@ -1507,7 +1505,7 @@
*
* Returns 0 on success and -1 if not all filters were copied
*/
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source)
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source)
{
int ret = 0;
int i;
@@ -1521,184 +1519,23 @@
return ret;
}
-
-/**
- * tep_update_trivial - update the trivial filters with the given filter
- * @dest - the filter to update
- * @source - the filter as the source of the update
- * @type - the type of trivial filter to update.
- *
- * Scan dest for trivial events matching @type to replace with the source.
- *
- * Returns 0 on success and -1 if there was a problem updating, but
- * events may have still been updated on error.
- */
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
- enum filter_trivial_type type)
-{
- struct tep_handle *src_pevent;
- struct tep_handle *dest_pevent;
- struct event_format *event;
- struct filter_type *filter_type;
- struct filter_arg *arg;
- char *str;
- int i;
-
- src_pevent = source->pevent;
- dest_pevent = dest->pevent;
-
- /* Do nothing if either of the filters has nothing to filter */
- if (!dest->filters || !source->filters)
- return 0;
-
- for (i = 0; i < dest->filters; i++) {
- filter_type = &dest->event_filters[i];
- arg = filter_type->filter;
- if (arg->type != FILTER_ARG_BOOLEAN)
- continue;
- if ((arg->boolean.value && type == FILTER_TRIVIAL_FALSE) ||
- (!arg->boolean.value && type == FILTER_TRIVIAL_TRUE))
- continue;
-
- event = filter_type->event;
-
- if (src_pevent != dest_pevent) {
- /* do a look up */
- event = tep_find_event_by_name(src_pevent,
- event->system,
- event->name);
- if (!event)
- return -1;
- }
-
- str = tep_filter_make_string(source, event->id);
- if (!str)
- continue;
-
- /* Don't bother if the filter is trivial too */
- if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0)
- filter_event(dest, event, str, NULL);
- free(str);
- }
- return 0;
-}
-
-/**
- * tep_filter_clear_trivial - clear TRUE and FALSE filters
- * @filter: the filter to remove trivial filters from
- * @type: remove only true, false, or both
- *
- * Removes filters that only contain a TRUE or FALES boolean arg.
- *
- * Returns 0 on success and -1 if there was a problem.
- */
-int tep_filter_clear_trivial(struct event_filter *filter,
- enum filter_trivial_type type)
-{
- struct filter_type *filter_type;
- int count = 0;
- int *ids = NULL;
- int i;
-
- if (!filter->filters)
- return 0;
-
- /*
- * Two steps, first get all ids with trivial filters.
- * then remove those ids.
- */
- for (i = 0; i < filter->filters; i++) {
- int *new_ids;
-
- filter_type = &filter->event_filters[i];
- if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
- continue;
- switch (type) {
- case FILTER_TRIVIAL_FALSE:
- if (filter_type->filter->boolean.value)
- continue;
- break;
- case FILTER_TRIVIAL_TRUE:
- if (!filter_type->filter->boolean.value)
- continue;
- default:
- break;
- }
-
- new_ids = realloc(ids, sizeof(*ids) * (count + 1));
- if (!new_ids) {
- free(ids);
- return -1;
- }
-
- ids = new_ids;
- ids[count++] = filter_type->event_id;
- }
-
- if (!count)
- return 0;
-
- for (i = 0; i < count; i++)
- tep_filter_remove_event(filter, ids[i]);
-
- free(ids);
- return 0;
-}
-
-/**
- * tep_filter_event_has_trivial - return true event contains trivial filter
- * @filter: the filter with the information
- * @event_id: the id of the event to test
- * @type: trivial type to test for (TRUE, FALSE, EITHER)
- *
- * Returns 1 if the event contains a matching trivial type
- * otherwise 0.
- */
-int tep_filter_event_has_trivial(struct event_filter *filter,
- int event_id,
- enum filter_trivial_type type)
-{
- struct filter_type *filter_type;
-
- if (!filter->filters)
- return 0;
-
- filter_type = find_filter_type(filter, event_id);
-
- if (!filter_type)
- return 0;
-
- if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
- return 0;
-
- switch (type) {
- case FILTER_TRIVIAL_FALSE:
- return !filter_type->filter->boolean.value;
-
- case FILTER_TRIVIAL_TRUE:
- return filter_type->filter->boolean.value;
- default:
- return 1;
- }
-}
-
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err);
static const char *
-get_comm(struct event_format *event, struct tep_record *record)
+get_comm(struct tep_event *event, struct tep_record *record)
{
const char *comm;
int pid;
- pid = tep_data_pid(event->pevent, record);
- comm = tep_data_comm_from_pid(event->pevent, pid);
+ pid = tep_data_pid(event->tep, record);
+ comm = tep_data_comm_from_pid(event->tep, pid);
return comm;
}
static unsigned long long
-get_value(struct event_format *event,
- struct format_field *field, struct tep_record *record)
+get_value(struct tep_event *event,
+ struct tep_format_field *field, struct tep_record *record)
{
unsigned long long val;
@@ -1716,7 +1553,7 @@
tep_read_number_field(field, record->data, &val);
- if (!(field->flags & FIELD_IS_SIGNED))
+ if (!(field->flags & TEP_FIELD_IS_SIGNED))
return val;
switch (field->size) {
@@ -1733,11 +1570,11 @@
}
static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err);
static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg,
+get_exp_value(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
unsigned long long lval, rval;
@@ -1753,37 +1590,37 @@
}
switch (arg->exp.type) {
- case FILTER_EXP_ADD:
+ case TEP_FILTER_EXP_ADD:
return lval + rval;
- case FILTER_EXP_SUB:
+ case TEP_FILTER_EXP_SUB:
return lval - rval;
- case FILTER_EXP_MUL:
+ case TEP_FILTER_EXP_MUL:
return lval * rval;
- case FILTER_EXP_DIV:
+ case TEP_FILTER_EXP_DIV:
return lval / rval;
- case FILTER_EXP_MOD:
+ case TEP_FILTER_EXP_MOD:
return lval % rval;
- case FILTER_EXP_RSHIFT:
+ case TEP_FILTER_EXP_RSHIFT:
return lval >> rval;
- case FILTER_EXP_LSHIFT:
+ case TEP_FILTER_EXP_LSHIFT:
return lval << rval;
- case FILTER_EXP_AND:
+ case TEP_FILTER_EXP_AND:
return lval & rval;
- case FILTER_EXP_OR:
+ case TEP_FILTER_EXP_OR:
return lval | rval;
- case FILTER_EXP_XOR:
+ case TEP_FILTER_EXP_XOR:
return lval ^ rval;
- case FILTER_EXP_NOT:
+ case TEP_FILTER_EXP_NOT:
default:
if (!*err)
*err = TEP_ERRNO__INVALID_EXP_TYPE;
@@ -1792,21 +1629,21 @@
}
static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
switch (arg->type) {
- case FILTER_ARG_FIELD:
+ case TEP_FILTER_ARG_FIELD:
return get_value(event, arg->field.field, record);
- case FILTER_ARG_VALUE:
- if (arg->value.type != FILTER_NUMBER) {
+ case TEP_FILTER_ARG_VALUE:
+ if (arg->value.type != TEP_FILTER_NUMBER) {
if (!*err)
*err = TEP_ERRNO__NOT_A_NUMBER;
}
return arg->value.val;
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
return get_exp_value(event, arg, record, err);
default:
@@ -1816,7 +1653,7 @@
return 0;
}
-static int test_num(struct event_format *event, struct filter_arg *arg,
+static int test_num(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
unsigned long long lval, rval;
@@ -1832,22 +1669,22 @@
}
switch (arg->num.type) {
- case FILTER_CMP_EQ:
+ case TEP_FILTER_CMP_EQ:
return lval == rval;
- case FILTER_CMP_NE:
+ case TEP_FILTER_CMP_NE:
return lval != rval;
- case FILTER_CMP_GT:
+ case TEP_FILTER_CMP_GT:
return lval > rval;
- case FILTER_CMP_LT:
+ case TEP_FILTER_CMP_LT:
return lval < rval;
- case FILTER_CMP_GE:
+ case TEP_FILTER_CMP_GE:
return lval >= rval;
- case FILTER_CMP_LE:
+ case TEP_FILTER_CMP_LE:
return lval <= rval;
default:
@@ -1857,21 +1694,21 @@
}
}
-static const char *get_field_str(struct filter_arg *arg, struct tep_record *record)
+static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
{
- struct event_format *event;
- struct tep_handle *pevent;
+ struct tep_event *event;
+ struct tep_handle *tep;
unsigned long long addr;
const char *val = NULL;
unsigned int size;
char hex[64];
/* If the field is not a string convert it */
- if (arg->str.field->flags & FIELD_IS_STRING) {
+ if (arg->str.field->flags & TEP_FIELD_IS_STRING) {
val = record->data + arg->str.field->offset;
size = arg->str.field->size;
- if (arg->str.field->flags & FIELD_IS_DYNAMIC) {
+ if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) {
addr = *(unsigned int *)val;
val = record->data + (addr & 0xffff);
size = addr >> 16;
@@ -1890,12 +1727,12 @@
} else {
event = arg->str.field->event;
- pevent = event->pevent;
+ tep = event->tep;
addr = get_value(event, arg->str.field, record);
- if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG))
+ if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
/* convert to a kernel symbol */
- val = tep_find_function(pevent, addr);
+ val = tep_find_function(tep, addr);
if (val == NULL) {
/* just use the hex of the string name */
@@ -1907,7 +1744,7 @@
return val;
}
-static int test_str(struct event_format *event, struct filter_arg *arg,
+static int test_str(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
const char *val;
@@ -1918,17 +1755,17 @@
val = get_field_str(arg, record);
switch (arg->str.type) {
- case FILTER_CMP_MATCH:
+ case TEP_FILTER_CMP_MATCH:
return strcmp(val, arg->str.val) == 0;
- case FILTER_CMP_NOT_MATCH:
+ case TEP_FILTER_CMP_NOT_MATCH:
return strcmp(val, arg->str.val) != 0;
- case FILTER_CMP_REGEX:
+ case TEP_FILTER_CMP_REGEX:
/* Returns zero on match */
return !regexec(&arg->str.reg, val, 0, NULL, 0);
- case FILTER_CMP_NOT_REGEX:
+ case TEP_FILTER_CMP_NOT_REGEX:
return regexec(&arg->str.reg, val, 0, NULL, 0);
default:
@@ -1938,19 +1775,19 @@
}
}
-static int test_op(struct event_format *event, struct filter_arg *arg,
+static int test_op(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
switch (arg->op.type) {
- case FILTER_OP_AND:
+ case TEP_FILTER_OP_AND:
return test_filter(event, arg->op.left, record, err) &&
test_filter(event, arg->op.right, record, err);
- case FILTER_OP_OR:
+ case TEP_FILTER_OP_OR:
return test_filter(event, arg->op.left, record, err) ||
test_filter(event, arg->op.right, record, err);
- case FILTER_OP_NOT:
+ case TEP_FILTER_OP_NOT:
return !test_filter(event, arg->op.right, record, err);
default:
@@ -1960,7 +1797,7 @@
}
}
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err)
{
if (*err) {
@@ -1971,22 +1808,22 @@
}
switch (arg->type) {
- case FILTER_ARG_BOOLEAN:
+ case TEP_FILTER_ARG_BOOLEAN:
/* easy case */
return arg->boolean.value;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
return test_op(event, arg, record, err);
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
return test_num(event, arg, record, err);
- case FILTER_ARG_STR:
+ case TEP_FILTER_ARG_STR:
return test_str(event, arg, record, err);
- case FILTER_ARG_EXP:
- case FILTER_ARG_VALUE:
- case FILTER_ARG_FIELD:
+ case TEP_FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_VALUE:
+ case TEP_FILTER_ARG_FIELD:
/*
* Expressions, fields and values evaluate
* to true if they return non zero
@@ -2008,9 +1845,9 @@
* Returns 1 if filter found for @event_id
* otherwise 0;
*/
-int tep_event_filtered(struct event_filter *filter, int event_id)
+int tep_event_filtered(struct tep_event_filter *filter, int event_id)
{
- struct filter_type *filter_type;
+ struct tep_filter_type *filter_type;
if (!filter->filters)
return 0;
@@ -2032,11 +1869,11 @@
* NO_FILTER - if no filters exist
* otherwise - error occurred during test
*/
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
struct tep_record *record)
{
- struct tep_handle *pevent = filter->pevent;
- struct filter_type *filter_type;
+ struct tep_handle *tep = filter->tep;
+ struct tep_filter_type *filter_type;
int event_id;
int ret;
enum tep_errno err = 0;
@@ -2046,7 +1883,7 @@
if (!filter->filters)
return TEP_ERRNO__NO_FILTER;
- event_id = tep_data_type(pevent, record);
+ event_id = tep_data_type(tep, record);
filter_type = find_filter_type(filter, event_id);
if (!filter_type)
@@ -2059,7 +1896,7 @@
return ret ? TEP_ERRNO__FILTER_MATCH : TEP_ERRNO__FILTER_MISS;
}
-static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *str = NULL;
char *left = NULL;
@@ -2070,10 +1907,10 @@
int val;
switch (arg->op.type) {
- case FILTER_OP_AND:
+ case TEP_FILTER_OP_AND:
op = "&&";
/* fall through */
- case FILTER_OP_OR:
+ case TEP_FILTER_OP_OR:
if (!op)
op = "||";
@@ -2094,8 +1931,8 @@
right_val = 0;
if (left_val >= 0) {
- if ((arg->op.type == FILTER_OP_AND && !left_val) ||
- (arg->op.type == FILTER_OP_OR && left_val)) {
+ if ((arg->op.type == TEP_FILTER_OP_AND && !left_val) ||
+ (arg->op.type == TEP_FILTER_OP_OR && left_val)) {
/* Just return left value */
str = left;
left = NULL;
@@ -2105,10 +1942,10 @@
/* just evaluate this. */
val = 0;
switch (arg->op.type) {
- case FILTER_OP_AND:
+ case TEP_FILTER_OP_AND:
val = left_val && right_val;
break;
- case FILTER_OP_OR:
+ case TEP_FILTER_OP_OR:
val = left_val || right_val;
break;
default:
@@ -2119,8 +1956,8 @@
}
}
if (right_val >= 0) {
- if ((arg->op.type == FILTER_OP_AND && !right_val) ||
- (arg->op.type == FILTER_OP_OR && right_val)) {
+ if ((arg->op.type == TEP_FILTER_OP_AND && !right_val) ||
+ (arg->op.type == TEP_FILTER_OP_OR && right_val)) {
/* Just return right value */
str = right;
right = NULL;
@@ -2135,7 +1972,7 @@
asprintf(&str, "(%s) %s (%s)", left, op, right);
break;
- case FILTER_OP_NOT:
+ case TEP_FILTER_OP_NOT:
op = "!";
right = arg_to_str(filter, arg->op.right);
if (!right)
@@ -2163,7 +2000,7 @@
return str;
}
-static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *val_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *str = NULL;
@@ -2172,12 +2009,12 @@
return str;
}
-static char *field_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *field_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
return strdup(arg->field.field->name);
}
-static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *exp_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *lstr;
char *rstr;
@@ -2190,34 +2027,34 @@
goto out;
switch (arg->exp.type) {
- case FILTER_EXP_ADD:
+ case TEP_FILTER_EXP_ADD:
op = "+";
break;
- case FILTER_EXP_SUB:
+ case TEP_FILTER_EXP_SUB:
op = "-";
break;
- case FILTER_EXP_MUL:
+ case TEP_FILTER_EXP_MUL:
op = "*";
break;
- case FILTER_EXP_DIV:
+ case TEP_FILTER_EXP_DIV:
op = "/";
break;
- case FILTER_EXP_MOD:
+ case TEP_FILTER_EXP_MOD:
op = "%";
break;
- case FILTER_EXP_RSHIFT:
+ case TEP_FILTER_EXP_RSHIFT:
op = ">>";
break;
- case FILTER_EXP_LSHIFT:
+ case TEP_FILTER_EXP_LSHIFT:
op = "<<";
break;
- case FILTER_EXP_AND:
+ case TEP_FILTER_EXP_AND:
op = "&";
break;
- case FILTER_EXP_OR:
+ case TEP_FILTER_EXP_OR:
op = "|";
break;
- case FILTER_EXP_XOR:
+ case TEP_FILTER_EXP_XOR:
op = "^";
break;
default:
@@ -2233,7 +2070,7 @@
return str;
}
-static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *num_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *lstr;
char *rstr;
@@ -2246,26 +2083,26 @@
goto out;
switch (arg->num.type) {
- case FILTER_CMP_EQ:
+ case TEP_FILTER_CMP_EQ:
op = "==";
/* fall through */
- case FILTER_CMP_NE:
+ case TEP_FILTER_CMP_NE:
if (!op)
op = "!=";
/* fall through */
- case FILTER_CMP_GT:
+ case TEP_FILTER_CMP_GT:
if (!op)
op = ">";
/* fall through */
- case FILTER_CMP_LT:
+ case TEP_FILTER_CMP_LT:
if (!op)
op = "<";
/* fall through */
- case FILTER_CMP_GE:
+ case TEP_FILTER_CMP_GE:
if (!op)
op = ">=";
/* fall through */
- case FILTER_CMP_LE:
+ case TEP_FILTER_CMP_LE:
if (!op)
op = "<=";
@@ -2283,24 +2120,24 @@
return str;
}
-static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *str_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *str = NULL;
char *op = NULL;
switch (arg->str.type) {
- case FILTER_CMP_MATCH:
+ case TEP_FILTER_CMP_MATCH:
op = "==";
/* fall through */
- case FILTER_CMP_NOT_MATCH:
+ case TEP_FILTER_CMP_NOT_MATCH:
if (!op)
op = "!=";
/* fall through */
- case FILTER_CMP_REGEX:
+ case TEP_FILTER_CMP_REGEX:
if (!op)
op = "=~";
/* fall through */
- case FILTER_CMP_NOT_REGEX:
+ case TEP_FILTER_CMP_NOT_REGEX:
if (!op)
op = "!~";
@@ -2315,31 +2152,31 @@
return str;
}
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
{
char *str = NULL;
switch (arg->type) {
- case FILTER_ARG_BOOLEAN:
+ case TEP_FILTER_ARG_BOOLEAN:
asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
return str;
- case FILTER_ARG_OP:
+ case TEP_FILTER_ARG_OP:
return op_to_str(filter, arg);
- case FILTER_ARG_NUM:
+ case TEP_FILTER_ARG_NUM:
return num_to_str(filter, arg);
- case FILTER_ARG_STR:
+ case TEP_FILTER_ARG_STR:
return str_to_str(filter, arg);
- case FILTER_ARG_VALUE:
+ case TEP_FILTER_ARG_VALUE:
return val_to_str(filter, arg);
- case FILTER_ARG_FIELD:
+ case TEP_FILTER_ARG_FIELD:
return field_to_str(filter, arg);
- case FILTER_ARG_EXP:
+ case TEP_FILTER_ARG_EXP:
return exp_to_str(filter, arg);
default:
@@ -2359,9 +2196,9 @@
* NULL is returned if no filter is found or allocation failed.
*/
char *
-tep_filter_make_string(struct event_filter *filter, int event_id)
+tep_filter_make_string(struct tep_event_filter *filter, int event_id)
{
- struct filter_type *filter_type;
+ struct tep_filter_type *filter_type;
if (!filter->filters)
return NULL;
@@ -2383,10 +2220,10 @@
* 1 if the two filters hold the same content.
* 0 if they do not.
*/
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2)
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2)
{
- struct filter_type *filter_type1;
- struct filter_type *filter_type2;
+ struct tep_filter_type *filter_type1;
+ struct tep_filter_type *filter_type2;
char *str1, *str2;
int result;
int i;
@@ -2408,14 +2245,6 @@
break;
if (filter_type1->filter->type != filter_type2->filter->type)
break;
- switch (filter_type1->filter->type) {
- case FILTER_TRIVIAL_FALSE:
- case FILTER_TRIVIAL_TRUE:
- /* trivial types just need the type compared */
- continue;
- default:
- break;
- }
/* The best way to compare complex filters is with strings */
str1 = arg_to_str(filter1, filter_type1->filter);
str2 = arg_to_str(filter2, filter_type2->filter);
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6..e998671 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
void __vwarning(const char *fmt, va_list ap)
{
if (errno)
- perror("trace-cmd");
+ perror("libtraceevent");
errno = 0;
fprintf(stderr, " ");
diff --git a/tools/lib/traceevent/plugins/Build b/tools/lib/traceevent/plugins/Build
new file mode 100644
index 0000000..210d269
--- /dev/null
+++ b/tools/lib/traceevent/plugins/Build
@@ -0,0 +1,10 @@
+plugin_jbd2-y += plugin_jbd2.o
+plugin_hrtimer-y += plugin_hrtimer.o
+plugin_kmem-y += plugin_kmem.o
+plugin_kvm-y += plugin_kvm.o
+plugin_mac80211-y += plugin_mac80211.o
+plugin_sched_switch-y += plugin_sched_switch.o
+plugin_function-y += plugin_function.o
+plugin_xen-y += plugin_xen.o
+plugin_scsi-y += plugin_scsi.o
+plugin_cfg80211-y += plugin_cfg80211.o
diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile
new file mode 100644
index 0000000..f440989
--- /dev/null
+++ b/tools/lib/traceevent/plugins/Makefile
@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+
+#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,$(CROSS_COMPILE)ar)
+$(call allow-override,NM,$(CROSS_COMPILE)nm)
+$(call allow-override,PKG_CONFIG,pkg-config)
+
+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)
+
+set_plugin_dir := 1
+
+# Set plugin_dir to preffered global plugin location
+# If we install under $HOME directory we go under
+# $(HOME)/.local/lib/traceevent/plugins
+#
+# We dont set PLUGIN_DIR in case we install under $HOME
+# directory, because by default the code looks under:
+# $(HOME)/.local/lib/traceevent/plugins by default.
+#
+ifeq ($(plugin_dir),)
+ifeq ($(prefix),$(HOME))
+override plugin_dir = $(HOME)/.local/lib/traceevent/plugins
+set_plugin_dir := 0
+else
+override plugin_dir = $(libdir)/traceevent/plugins
+endif
+endif
+
+ifeq ($(set_plugin_dir),1)
+PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
+PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
+endif
+
+include ../../../scripts/Makefile.include
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+ VERBOSE = $(V)
+endif
+ifndef VERBOSE
+ VERBOSE = 0
+endif
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+export prefix libdir src obj
+
+# Shell quotes
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
+
+CONFIG_INCLUDES =
+CONFIG_LIBS =
+CONFIG_FLAGS =
+
+OBJ = $@
+N =
+
+INCLUDES = -I. -I.. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+ CFLAGS := $(EXTRA_CFLAGS)
+else
+ CFLAGS := -g -Wall
+endif
+
+# Append required CFLAGS
+override CFLAGS += -fPIC
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
+
+ifeq ($(VERBOSE),1)
+ Q =
+else
+ Q = @
+endif
+
+# Disable command line variables (CFLAGS) override 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
+
+DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
+
+PLUGINS = plugin_jbd2.so
+PLUGINS += plugin_hrtimer.so
+PLUGINS += plugin_kmem.so
+PLUGINS += plugin_kvm.so
+PLUGINS += plugin_mac80211.so
+PLUGINS += plugin_sched_switch.so
+PLUGINS += plugin_function.so
+PLUGINS += plugin_xen.so
+PLUGINS += plugin_scsi.so
+PLUGINS += plugin_cfg80211.so
+
+PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS))
+PLUGINS_IN := $(PLUGINS:.so=-in.o)
+
+plugins: $(PLUGINS) $(DYNAMIC_LIST_FILE)
+
+__plugin_obj = $(notdir $@)
+ plugin_obj = $(__plugin_obj:-in.o=)
+
+$(PLUGINS_IN): force
+ $(Q)$(MAKE) $(build)=$(plugin_obj)
+
+$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
+ $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
+
+$(OUTPUT)%.so: $(OUTPUT)%-in.o
+ $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^
+
+define update_dir
+ (echo $1 > $@.tmp; \
+ if [ -r $@ ] && cmp -s $@ $@.tmp; then \
+ rm -f $@.tmp; \
+ else \
+ echo ' UPDATE $@'; \
+ mv -f $@.tmp $@; \
+ fi);
+endef
+
+tags: force
+ $(RM) tags
+ find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+ --regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/'
+
+TAGS: force
+ $(RM) TAGS
+ find . -name '*.[ch]' | xargs etags \
+ --regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/'
+
+define do_install_mkdir
+ if [ ! -d '$(DESTDIR_SQ)$1' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+ fi
+endef
+
+define do_install
+ $(call do_install_mkdir,$2); \
+ $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
+endef
+
+define do_install_plugins
+ for plugin in $1; do \
+ $(call do_install,$$plugin,$(plugin_dir_SQ)); \
+ done
+endef
+
+define do_generate_dynamic_list_file
+ symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
+ xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
+ if [ "$$symbol_type" = "U W" ];then \
+ (echo '{'; \
+ $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+ echo '};'; \
+ ) > $2; \
+ else \
+ (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+ fi
+endef
+
+install: $(PLUGINS)
+ $(call QUIET_INSTALL, trace_plugins) \
+ $(call do_install_plugins, $(PLUGINS))
+
+clean:
+ $(call QUIET_CLEAN, trace_plugins) \
+ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \
+ $(RM) $(OUTPUT)libtraceevent-dynamic-list \
+ $(RM) TRACEEVENT-CFLAGS tags TAGS;
+
+PHONY += force plugins
+force:
+
+# 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/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugins/plugin_cfg80211.c
similarity index 79%
rename from tools/lib/traceevent/plugin_cfg80211.c
rename to tools/lib/traceevent/plugins/plugin_cfg80211.c
index a51b366..3d43b56 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugins/plugin_cfg80211.c
@@ -25,9 +25,9 @@
return val ? (long long) le16toh(*val) : 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process___le16_to_cpup,
TEP_FUNC_ARG_INT,
"__le16_to_cpup",
@@ -36,8 +36,8 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process___le16_to_cpup,
+ tep_unregister_print_function(tep, process___le16_to_cpup,
"__le16_to_cpup");
}
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugins/plugin_function.c
similarity index 90%
rename from tools/lib/traceevent/plugin_function.c
rename to tools/lib/traceevent/plugins/plugin_function.c
index 4247474..7770fcb 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugins/plugin_function.c
@@ -23,6 +23,7 @@
#include "event-parse.h"
#include "event-utils.h"
+#include "trace-seq.h"
static struct func_stack {
int size;
@@ -123,9 +124,9 @@
}
static int function_handler(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long function;
unsigned long long pfunction;
const char *func;
@@ -135,12 +136,12 @@
if (tep_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');
- func = tep_find_function(pevent, function);
+ func = tep_find_function(tep, function);
if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
return trace_seq_putc(s, '!');
- parent = tep_find_function(pevent, pfunction);
+ parent = tep_find_function(tep, pfunction);
if (parent && ftrace_indent->set)
index = add_and_get_index(parent, func, record->cpu);
@@ -163,9 +164,9 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "ftrace", "function",
+ tep_register_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
tep_plugin_add_options("ftrace", plugin_options);
@@ -173,11 +174,11 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
int i, x;
- tep_unregister_event_handler(pevent, -1, "ftrace", "function",
+ tep_unregister_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
for (i = 0; i <= cpus; i++) {
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugins/plugin_hrtimer.c
similarity index 84%
rename from tools/lib/traceevent/plugin_hrtimer.c
rename to tools/lib/traceevent/plugins/plugin_hrtimer.c
index b43bfec..bb434e0 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugins/plugin_hrtimer.c
@@ -23,10 +23,11 @@
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static int timer_expire_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
trace_seq_printf(s, "hrtimer=");
@@ -46,7 +47,7 @@
static int timer_start_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
trace_seq_printf(s, "hrtimer=");
@@ -66,23 +67,23 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_register_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugins/plugin_jbd2.c
similarity index 85%
rename from tools/lib/traceevent/plugin_jbd2.c
rename to tools/lib/traceevent/plugins/plugin_jbd2.c
index 45a9acd..04fc125 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugins/plugin_jbd2.c
@@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define MINORBITS 20
#define MINORMASK ((1U << MINORBITS) - 1)
@@ -47,16 +48,16 @@
return jiffies;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jbd2_dev_to_name,
TEP_FUNC_ARG_STRING,
"jbd2_dev_to_name",
TEP_FUNC_ARG_INT,
TEP_FUNC_ARG_VOID);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jiffies_to_msecs,
TEP_FUNC_ARG_LONG,
"jiffies_to_msecs",
@@ -65,11 +66,11 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_jbd2_dev_to_name,
+ tep_unregister_print_function(tep, process_jbd2_dev_to_name,
"jbd2_dev_to_name");
- tep_unregister_print_function(pevent, process_jiffies_to_msecs,
+ tep_unregister_print_function(tep, process_jiffies_to_msecs,
"jiffies_to_msecs");
}
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugins/plugin_kmem.c
similarity index 64%
rename from tools/lib/traceevent/plugin_kmem.c
rename to tools/lib/traceevent/plugins/plugin_kmem.c
index 73966b0..edaec5d 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugins/plugin_kmem.c
@@ -22,11 +22,12 @@
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static int call_site_handler(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
- struct format_field *field;
+ struct tep_format_field *field;
unsigned long long val, addr;
void *data = record->data;
const char *func;
@@ -38,57 +39,57 @@
if (tep_read_number_field(field, data, &val))
return 1;
- func = tep_find_function(event->pevent, val);
+ func = tep_find_function(event->tep, val);
if (!func)
return 1;
- addr = tep_find_function_address(event->pevent, val);
+ addr = tep_find_function_address(event->tep, val);
trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
return 1;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "kmem", "kfree",
+ tep_register_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem",
+ tep_register_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kmem", "kfree",
+ tep_unregister_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem",
+ tep_unregister_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugins/plugin_kvm.c
similarity index 86%
rename from tools/lib/traceevent/plugin_kvm.c
rename to tools/lib/traceevent/plugins/plugin_kvm.c
index 1d0d159..c8e6230 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugins/plugin_kvm.c
@@ -23,6 +23,7 @@
#include <stdint.h>
#include "event-parse.h"
+#include "trace-seq.h"
#ifdef HAVE_UDIS86
@@ -248,7 +249,7 @@
}
static int print_exit_reason(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, const char *field)
+ struct tep_event *event, const char *field)
{
unsigned long long isa;
unsigned long long val;
@@ -269,7 +270,7 @@
}
static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
unsigned long long info1 = 0, info2 = 0;
@@ -292,7 +293,7 @@
static int kvm_emulate_insn_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
unsigned long long rip, csbase, len, flags, failed;
int llen;
@@ -331,7 +332,7 @@
static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
if (print_exit_reason(s, record, event, "exit_code") < 0)
return -1;
@@ -345,7 +346,7 @@
}
static int kvm_nested_vmexit_handler(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
tep_print_num_field(s, "rip %llx ", event, "rip", record, 1);
@@ -371,7 +372,7 @@
};
static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
unsigned long long val;
static const char *access_str[] = {
@@ -386,10 +387,10 @@
/*
* We can only use the structure if file is of the same
- * endianess.
+ * endianness.
*/
- if (tep_is_file_bigendian(event->pevent) ==
- tep_is_host_bigendian(event->pevent)) {
+ if (tep_is_file_bigendian(event->tep) ==
+ tep_is_local_bigendian(event->tep)) {
trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
role.level,
@@ -418,7 +419,7 @@
static int kvm_mmu_get_page_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
unsigned long long val;
@@ -444,40 +445,40 @@
return pte & PT_WRITABLE_MASK;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
init_disassembler();
- tep_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu",
+ tep_register_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_is_writable_pte,
TEP_FUNC_ARG_INT,
"is_writable_pte",
@@ -486,37 +487,37 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu",
+ tep_unregister_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_unregister_print_function(pevent, process_is_writable_pte,
+ tep_unregister_print_function(tep, process_is_writable_pte,
"is_writable_pte");
}
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugins/plugin_mac80211.c
similarity index 86%
rename from tools/lib/traceevent/plugin_mac80211.c
rename to tools/lib/traceevent/plugins/plugin_mac80211.c
index de50a53..884303c 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugins/plugin_mac80211.c
@@ -22,13 +22,14 @@
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define INDENT 65
-static void print_string(struct trace_seq *s, struct event_format *event,
+static void print_string(struct trace_seq *s, struct tep_event *event,
const char *name, const void *data)
{
- struct format_field *f = tep_find_field(event, name);
+ struct tep_format_field *f = tep_find_field(event, name);
int offset;
int length;
@@ -59,7 +60,7 @@
static int drv_bss_info_changed(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
void *data = record->data;
@@ -86,17 +87,17 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "mac80211",
+ tep_register_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "mac80211",
+ tep_unregister_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
}
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugins/plugin_sched_switch.c
similarity index 82%
rename from tools/lib/traceevent/plugin_sched_switch.c
rename to tools/lib/traceevent/plugins/plugin_sched_switch.c
index eecb4bd..957389a 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugins/plugin_sched_switch.c
@@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static void write_state(struct trace_seq *s, int val)
{
@@ -44,7 +45,7 @@
trace_seq_putc(s, 'R');
}
-static void write_and_save_comm(struct format_field *field,
+static void write_and_save_comm(struct tep_format_field *field,
struct tep_record *record,
struct trace_seq *s, int pid)
{
@@ -61,14 +62,14 @@
comm = &s->buffer[len];
/* Help out the comm to ids. This will handle dups */
- tep_register_comm(field->event->pevent, comm, pid);
+ tep_register_comm(field->event->tep, comm, pid);
}
static int sched_wakeup_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
- struct format_field *field;
+ struct tep_format_field *field;
unsigned long long val;
if (tep_get_field_val(s, event, "pid", record, &val, 1))
@@ -95,9 +96,9 @@
static int sched_switch_handler(struct trace_seq *s,
struct tep_record *record,
- struct event_format *event, void *context)
+ struct tep_event *event, void *context)
{
- struct format_field *field;
+ struct tep_format_field *field;
unsigned long long val;
if (tep_get_field_val(s, event, "prev_pid", record, &val, 1))
@@ -134,27 +135,27 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_register_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
}
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugins/plugin_scsi.c
similarity index 97%
rename from tools/lib/traceevent/plugin_scsi.c
rename to tools/lib/traceevent/plugins/plugin_scsi.c
index 5ec346f..5d0387a 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugins/plugin_scsi.c
@@ -3,6 +3,7 @@
#include <string.h>
#include <inttypes.h>
#include "event-parse.h"
+#include "trace-seq.h"
typedef unsigned long sector_t;
typedef uint64_t u64;
@@ -413,9 +414,9 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_scsi_trace_parse_cdb,
TEP_FUNC_ARG_STRING,
"scsi_trace_parse_cdb",
@@ -426,8 +427,8 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+ tep_unregister_print_function(tep, process_scsi_trace_parse_cdb,
"scsi_trace_parse_cdb");
}
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugins/plugin_xen.c
similarity index 93%
rename from tools/lib/traceevent/plugin_xen.c
rename to tools/lib/traceevent/plugins/plugin_xen.c
index b2acbd6..993b208 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugins/plugin_xen.c
@@ -3,6 +3,7 @@
#include <stdlib.h>
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define __HYPERVISOR_set_trap_table 0
#define __HYPERVISOR_mmu_update 1
@@ -119,9 +120,9 @@
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_xen_hypercall_name,
TEP_FUNC_ARG_STRING,
"xen_hypercall_name",
@@ -130,8 +131,8 @@
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_xen_hypercall_name,
+ tep_unregister_print_function(tep, process_xen_hypercall_name,
"xen_hypercall_name");
}
diff --git a/tools/lib/traceevent/tep_strerror.c b/tools/lib/traceevent/tep_strerror.c
new file mode 100644
index 0000000..4ac2644
--- /dev/null
+++ b/tools/lib/traceevent/tep_strerror.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: LGPL-2.1
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+
+#include "event-parse.h"
+
+#undef _PE
+#define _PE(code, str) str
+static const char * const tep_error_str[] = {
+ TEP_ERRORS
+};
+#undef _PE
+
+/*
+ * The tools so far have been using the strerror_r() GNU variant, that returns
+ * a string, be it the buffer passed or something else.
+ *
+ * But that, besides being tricky in cases where we expect that the function
+ * using strerror_r() returns the error formatted in a provided buffer (we have
+ * to check if it returned something else and copy that instead), breaks the
+ * build on systems not using glibc, like Alpine Linux, where musl libc is
+ * used.
+ *
+ * So, introduce yet another wrapper, str_error_r(), that has the GNU
+ * interface, but uses the portable XSI variant of strerror_r(), so that users
+ * rest asured that the provided buffer is used and it is what is returned.
+ */
+int tep_strerror(struct tep_handle *tep __maybe_unused,
+ enum tep_errno errnum, char *buf, size_t buflen)
+{
+ const char *msg;
+ int idx;
+
+ if (!buflen)
+ return 0;
+
+ if (errnum >= 0) {
+ int err = strerror_r(errnum, buf, buflen);
+ buf[buflen - 1] = 0;
+ return err;
+ }
+
+ if (errnum <= __TEP_ERRNO__START ||
+ errnum >= __TEP_ERRNO__END)
+ return -1;
+
+ idx = errnum - __TEP_ERRNO__START - 1;
+ msg = tep_error_str[idx];
+ snprintf(buf, buflen, "%s", msg);
+
+ return 0;
+}
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index e3bac45..8d5ecd2 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -3,6 +3,8 @@
* Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
+#include "trace-seq.h"
+
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@@ -98,7 +100,8 @@
* @fmt: printf format string
*
* It returns 0 if the trace oversizes the buffer's free
- * space, 1 otherwise.
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
*
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formating of a trace
@@ -127,9 +130,10 @@
goto try_again;
}
- s->len += ret;
+ if (ret > 0)
+ s->len += ret;
- return 1;
+ return ret;
}
/**
@@ -137,6 +141,10 @@
* @s: trace sequence descriptor
* @fmt: printf format string
*
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
+ * *
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formating of a trace
* trace_seq_printf is used to store strings into a special
@@ -161,9 +169,10 @@
goto try_again;
}
- s->len += ret;
+ if (ret > 0)
+ s->len += ret;
- return len;
+ return ret;
}
/**
diff --git a/tools/lib/traceevent/trace-seq.h b/tools/lib/traceevent/trace-seq.h
new file mode 100644
index 0000000..d68ec69
--- /dev/null
+++ b/tools/lib/traceevent/trace-seq.h
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _TRACE_SEQ_H
+#define _TRACE_SEQ_H
+
+#include <stdarg.h>
+#include <stdio.h>
+
+/* ----------------------- trace_seq ----------------------- */
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+enum trace_seq_fail {
+ TRACE_SEQ__GOOD,
+ TRACE_SEQ__BUFFER_POISONED,
+ TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+ char *buffer;
+ unsigned int buffer_size;
+ unsigned int len;
+ unsigned int readpos;
+ enum trace_seq_fail state;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+ __attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+ __attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+#endif /* _TRACE_SEQ_H */
diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c
index e08ee14..8780b4c 100644
--- a/tools/lib/vsprintf.c
+++ b/tools/lib/vsprintf.c
@@ -23,3 +23,22 @@
return (i >= ssize) ? (ssize - 1) : i;
}
+
+int scnprintf_pad(char * buf, size_t size, const char * fmt, ...)
+{
+ ssize_t ssize = size;
+ va_list args;
+ int i;
+
+ va_start(args, fmt);
+ i = vscnprintf(buf, size, fmt, args);
+ va_end(args);
+
+ if (i < (int) size) {
+ for (; i < (int) size; i++)
+ buf[i] = ' ';
+ buf[i] = 0x0;
+ }
+
+ return (i >= ssize) ? (ssize - 1) : i;
+}
diff --git a/tools/lib/zalloc.c b/tools/lib/zalloc.c
new file mode 100644
index 0000000..9c856d5
--- /dev/null
+++ b/tools/lib/zalloc.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+#include <stdlib.h>
+#include <linux/zalloc.h>
+
+void *zalloc(size_t size)
+{
+ return calloc(1, size);
+}
+
+void __zfree(void **ptr)
+{
+ free(*ptr);
+ *ptr = NULL;
+}