perf tools: filtering events using eBPF programs
Subsystems (3)
v8 cover perf tools: filtering events using eBPF programs
This is the 8th version which tries to introduce eBPF programs to perf.
Since version 7 is still being reviewed, this series keeps patch 1/49 to 37/49 identical to what they are in v7 except a small modification in patch 36/48, which prints more debug information when silent is set, and some context to rebase them onto newest tip/perf/core (a9a3cd9).
The core stuffs in this series resides in 38/49 - 49/49, which allow users to access kernel data through parameters of eBPF programs. Now it is possible to write eBPF programs like this:
SEC("get_superblock=journal_get_superblock journal->j_errno") int get_superblock(struct pt_regs *ctx, int err, int j_errno)
{
char fmt[] = "j_errno=%lx\n";
bpf_trace_printk(fmt, sizeof(fmt), j_errno);
if (j_errno)
return 1;
return 0;}
Where, 'j_errno' in that function will be dereferenced according to dwarf information by prologue generated by perf. 'err' indicates the successfulness of the dereferencing.
He Kuang posted 2 series on that idea it a month ago:
http://lkml.kernel.org/r/[email protected]
This series totally rewrite its code, the interface is also changed.
In addition, this series of patches supports setting BPF program to multiple probing points and generate different prologue for all of them if necessary. Using glob matching is also allowed. In the above example, there will be two journal_get_superblock() functions in kernel if we compile both jbd and jbd2. That BPF function tracks both of them.
In this series:
Patch 01/49 - 37/49 are identical to v7 series, except context
adjustments and a small improvement in 36/49.
Patch 38/49 - 43/49 are preparation. Where 39/49 gives libbpf the
ability to load multiple instances. New interfaces are introduced for it.
Patch 44/49 - 47/49 introduce bpf-prologue.c into perf, whcih generates
prologue according to argument list of pevs. Core functions are in 46/49. Its commit message describes the detail of prologue generation.
Patch 48/49 groups similar prologue together and only create one BPF
program instance for events which can share prologue.
Patch 49/49 adds '--vmlinux' to 'perf record' to allow it access dwarf
information.
He Kuang (4):
perf tools: Move linux/filter.h to tools/include
perf tools: Introduce arch_get_reg_info() for x86 perf tools: Add prologue for BPF programs for fetching arguments perf record: Support custom vmlinux path
Wang Nan (45):
tools build: Add feature check for eBPF API
bpf tools: Introduce 'bpf' library to tools
bpf tools: Allow caller to set printing function
bpf tools: Open eBPF object file and do basic validation bpf tools: Read eBPF object from buffer
bpf tools: Check endianess and make libbpf fail early
bpf tools: Iterate over ELF sections to collect information bpf tools: Collect version and license from ELF sections bpf tools: Collect map definitions from 'maps' section
bpf tools: Collect symbol table from SHT_SYMTAB section bpf tools: Collect eBPF programs from their own sections bpf tools: Collect relocation sections from SHT_REL sections bpf tools: Record map accessing instructions for each program bpf tools: Add bpf.c/h for common bpf operations
bpf tools: Create eBPF maps defined in an object file
bpf tools: Relocate eBPF programs
bpf tools: Introduce bpf_load_program() to bpf.c
bpf tools: Load eBPF programs in object files into kernel bpf tools: Introduce accessors for struct bpf_program
bpf tools: Introduce accessors for struct bpf_object
bpf tools: Link all bpf objects onto a list
perf tools: Make perf depend on libbpf
perf tools: Introduce llvm config options
perf tools: Call clang to compile C source to object code perf tests: Add LLVM test for eBPF on-the-fly compiling perf tools: Auto detecting kernel build directory
perf tools: Auto detecting kernel include options
perf record: Enable passing bpf object file to --event perf record: Compile scriptlets if pass '.c' to --event perf tools: Parse probe points of eBPF programs during preparation perf probe: Attach trace_probe_event with perf_probe_event perf record: Probe at kprobe points
perf record: Load all eBPF object into kernel
perf tools: Add bpf_fd field to evsel and config it
perf tools: Attach eBPF program to perf event
perf tools: Suppress probing messages when probing by BPF loading perf record: Add clang options for compiling BPF scripts bpf tools: Load instructions buffer using load_program() bpf tools: Load a program with different instance using preprocessor perf tools: Fix probe-event.h include
perf probe: Reset tev->args and tev->nargs when failure perf tools: Iterater over tev instead of pev in bpf__for_each_program perf tools: Add BPF_PROLOGUE config options for further patches perf tools: Generate prologue for BPF programs
perf tools: Use same BPF program if arguments are identical
tools/build/Makefile.feature | 6 +- tools/build/feature/Makefile | 6 +- tools/build/feature/test-bpf.c | 18 + tools/include/linux/filter.h | 237 +++++++ tools/lib/bpf/.gitignore | 2 + tools/lib/bpf/Build | 1 + tools/lib/bpf/Makefile | 195 ++++++ tools/lib/bpf/bpf.c | 84 +++ tools/lib/bpf/bpf.h | 23 + tools/lib/bpf/libbpf.c | 1173 +++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 107 +++ tools/perf/MANIFEST | 4 + tools/perf/Makefile.perf | 19 +- tools/perf/arch/x86/Makefile | 1 + tools/perf/arch/x86/util/Build | 2 + tools/perf/arch/x86/util/dwarf-regs.c | 104 ++- tools/perf/builtin-probe.c | 2 +- tools/perf/builtin-record.c | 47 +- tools/perf/config/Makefile | 31 +- tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 4 + tools/perf/tests/llvm.c | 85 +++ tools/perf/tests/make | 4 +- tools/perf/tests/tests.h | 1 + tools/perf/util/Build | 3 + tools/perf/util/bpf-loader.c | 556 ++++++++++++++++ tools/perf/util/bpf-loader.h | 46 ++ tools/perf/util/bpf-prologue.c | 425 ++++++++++++ tools/perf/util/bpf-prologue.h | 19 + tools/perf/util/config.c | 4 + tools/perf/util/debug.c | 5 + tools/perf/util/debug.h | 1 + tools/perf/util/evlist.c | 41 ++ tools/perf/util/evlist.h | 1 + tools/perf/util/evsel.c | 17 + tools/perf/util/evsel.h | 1 + tools/perf/util/include/dwarf-regs.h | 7 + tools/perf/util/llvm-utils.c | 370 +++++++++++ tools/perf/util/llvm-utils.h | 39 ++ tools/perf/util/parse-events.c | 16 + tools/perf/util/parse-events.h | 2 + tools/perf/util/parse-events.l | 6 + tools/perf/util/parse-events.y | 29 +- tools/perf/util/probe-event.c | 81 ++- tools/perf/util/probe-event.h | 7 +- tools/perf/util/probe-finder.c | 4 + 46 files changed, 3761 insertions(+), 76 deletions(-) create mode 100644 tools/build/feature/test-bpf.c create mode 100644 tools/include/linux/filter.h create mode 100644 tools/lib/bpf/.gitignore create mode 100644 tools/lib/bpf/Build create mode 100644 tools/lib/bpf/Makefile create mode 100644 tools/lib/bpf/bpf.c create mode 100644 tools/lib/bpf/bpf.h create mode 100644 tools/lib/bpf/libbpf.c create mode 100644 tools/lib/bpf/libbpf.h create mode 100644 tools/perf/tests/llvm.c create mode 100644 tools/perf/util/bpf-loader.c create mode 100644 tools/perf/util/bpf-loader.h create mode 100644 tools/perf/util/bpf-prologue.c create mode 100644 tools/perf/util/bpf-prologue.h create mode 100644 tools/perf/util/llvm-utils.c create mode 100644 tools/perf/util/llvm-utils.h
Signature · 1 line
1.8.3.4
RFC PATCH v8 1/49 tools build: Add feature check for eBPF API
In this patch, eBPF API is checked by compiling a c source file which uses fields in bpf_attr which will be used by libbpf.
--- tools/build/Makefile.feature | 6 ++++-- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-bpf.c | 18 ++++++++++++++++++ 3 files changed, 27 insertions(+), 3 deletions(-) create mode 100644 tools/build/feature/test-bpf.c
tools/build/Makefile.feature +4 -2
@@ -51,7 +51,8 @@ FEATURE_TESTS ?= \ timerfd \ libdw-dwarf-unwind \ zlib \ - lzma + lzma \ + bpf FEATURE_DISPLAY ?= \ dwarf \
@@ -67,7 +68,8 @@ FEATURE_DISPLAY ?= \ libunwind \ libdw-dwarf-unwind \ zlib \ - lzma + lzma \ + bpf # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not
tools/build/feature/Makefile +5 -1
@@ -33,7 +33,8 @@ FILES= \ test-compile-32.bin \ test-compile-x32.bin \ test-zlib.bin \ - test-lzma.bin + test-lzma.bin \ + test-bpf.bin CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -156,6 +157,9 @@ test-zlib.bin: test-lzma.bin: $(BUILD) -llzma +test-bpf.bin: + $(BUILD) + -include *.d ###############################
tools/build/feature/test-bpf.c new file +18 -0
@@ -0,0 +1,18 @@ +#include <linux/bpf.h> + +int main () +{ +union bpf_attr attr; + + attr.prog_type =BPF_PROG_TYPE_KPROBE ; + attr.insn_cnt =0 ; + attr.insns =0 ; + attr.license =0 ; + attr.log_buf =0 ; + attr.log_size =0 ; + attr.log_level =0 ; + attr.kern_version =0 ; + + attr = attr; +return 0 ; +}
Signature · 1 line
1.8.3.4
RFC PATCH v8 2/49 bpf tools: Introduce 'bpf' library to tools
In reply to Wang NanThis is the first patch of libbpf. The goal of libbpf is to create a standard way for accessing eBPF object files. This patch creates 'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and libbpf.so, 'make install' to put them into proper directories. Most part of Makefile is borrowed from traceevent.
Before building, it checks the existance of libelf in Makefile, and deny to build if not found. Instead of throwing an error if libelf not found, the error raises in a phony target "elfdep". This design is to ensure 'make clean' still workable even if libelf is not found.
Kernel BPF API is also checked. "bpfdep" is used for it.
--- tools/lib/bpf/.gitignore | 2 + tools/lib/bpf/Build | 1 + tools/lib/bpf/Makefile | 195 +++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.c | 14 ++++ tools/lib/bpf/libbpf.h | 11 +++ 5 files changed, 223 insertions(+) create mode 100644 tools/lib/bpf/.gitignore create mode 100644 tools/lib/bpf/Build create mode 100644 tools/lib/bpf/Makefile create mode 100644 tools/lib/bpf/libbpf.c create mode 100644 tools/lib/bpf/libbpf.h
tools/lib/bpf/.gitignore new file +2 -0
@@ -0,0 +1,2 @@ +libbpf_version.h +FEATURE-DUMP
tools/lib/bpf/Build new file +1 -0
@@ -0,0 +1 @@ +libbpf-y := libbpf.o
tools/lib/bpf/Makefile new file +195 -0
195 lines not on this page · raw message
tools/lib/bpf/libbpf.c new file +14 -0
@@ -0,0 +1,14 @@ +/* +* Common eBPF ELF object loading operations. +* +* Copyright (C) 2013-2015 Alexei Starovoitov <[email protected]> +* Copyright (C) 2015 Wang Nan <[email protected]> +* Copyright (C) 2015 Huawei Inc. +*/ + +#include <stdlib.h> +#include <unistd.h> +#include <asm/unistd.h> +#include <linux/bpf.h> + +#include "libbpf.h"
tools/lib/bpf/libbpf.h new file +11 -0
@@ -0,0 +1,11 @@ +/* +* Common eBPF ELF object loading operations. +* +* Copyright (C) 2013-2015 Alexei Starovoitov <[email protected]> +* Copyright (C) 2015 Wang Nan <[email protected]> +* Copyright (C) 2015 Huawei Inc. +*/ +#ifndef __BPF_LIBBPF_H +#define __BPF_LIBBPF_H + +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 3/49 bpf tools: Allow caller to set printing function
In reply to Wang NanBy libbpf_set_print(), users of libbpf are allowed to register he/she own debug, info and warning printing functions. Libbpf will use those functions to print messages. If not provided, default info and warning printing functions are fprintf(stderr, ...); default debug printing is NULL.
This API is designed to be used by perf, enables it to register its own logging functions to make all logs uniform, instead of separated logging level control.
--- tools/lib/bpf/libbpf.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 12 ++++++++++++ 2 files changed, 52 insertions(+)
tools/lib/bpf/libbpf.c +40 -0
@@ -7,8 +7,48 @@*/ #include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <string.h> #include <unistd.h> #include <asm/unistd.h> #include <linux/bpf.h> #include "libbpf.h" + +#define __printf (a, b) __attribute__((format(printf, a, b))) + +__printf(1, 2) +static int __base_pr (const char *format, ...) +{ +va_list args; +int err; + +va_start (args, format); + err =vfprintf (stderr, format, args); +va_end (args); +return err; +} + +static __printf(1, 2) 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 = NULL; + +#define __pr (func, fmt, ...) \ +do { \ + if ((func)) \ + (func)("libbpf: " fmt, ##__VA_ARGS__); \ +} while(0) + +#define pr_warning (fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__) +#define pr_info (fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__) +#define pr_debug (fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__) + +void libbpf_set_print (libbpf_print_fn_t warn, +libbpf_print_fn_t info, +libbpf_print_fn_t debug) +{ + __pr_warning = warn; + __pr_info = info; + __pr_debug = debug; +}
tools/lib/bpf/libbpf.h +12 -0
@@ -8,4 +8,16 @@#ifndef __BPF_LIBBPF_H#define __BPF_LIBBPF_H +/* +* In include/linux/compiler-gcc.h, __printf is defined. However +* it should be better if libbpf.h doesn't depend on Linux header file. +* So instead of __printf, here we use gcc attribute directly. +*/ +typedef int (*libbpf_print_fn_t )(const char *, ...) + __attribute__((format (printf,1 ,2 ))); + +void libbpf_set_print (libbpf_print_fn_t warn, +libbpf_print_fn_t info, +libbpf_print_fn_t debug); +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 4/49 bpf tools: Open eBPF object file and do basic validation
In reply to Wang NanThis patch defines basic interface of libbpf. 'struct bpf_object' will be the handler of each object file. Its internal structure is hide to user. eBPF object files are compiled by LLVM as ELF format. In this patch, libelf is used to open those files, read EHDR and do basic validation according to e_type and e_machine.
All elf related staffs are grouped together and reside in efile field of 'struct bpf_object'. bpf_object__elf_finish() is introduced to clear it.
After all eBPF programs in an object file are loaded, related ELF information is useless. Close the object file and free those memory.
zfree() and zclose() are introduced to ensure setting NULL pointers and negative file descriptors after resources are released.
--- tools/lib/bpf/libbpf.c | 158 +++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 8 +++ 2 files changed, 166 insertions(+)
tools/lib/bpf/libbpf.c +158 -0
@@ -11,8 +11,12 @@#include <stdarg.h> #include <string.h> #include <unistd.h> +#include <fcntl.h> +#include <errno.h> #include <asm/unistd.h> #include <linux/bpf.h> +#include <libelf.h> +#include <gelf.h> #include "libbpf.h"
@@ -52,3 +56,157 @@ void libbpf_set_print(libbpf_print_fn_t warn, __pr_info = info; __pr_debug = debug; } + +/* Copied from tools/perf/util/util.h */ +#ifndef zfree +# define zfree (ptr) ({ free(*ptr); *ptr = NULL; }) +#endif + +#ifndef zclose +# define zclose (fd) ({ \ + int ___err = 0; \ + if ((fd) >= 0) \ + ___err = close((fd)); \ + fd = -1; \ + ___err;}) +#endif + +#ifdef HAVE_LIBELF_MMAP_SUPPORT +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP +#else +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ +#endif + +struct bpf_object { +/* +* Information when doing elf related work. Only valid if fd +* is valid. +*/ +struct { +int fd; +Elf *elf; +GElf_Ehdr ehdr; + } efile; +char path[]; +}; +#define obj_elf_valid (o) ((o)->efile.elf) + +static struct bpf_object *bpf_object__new (const char *path) +{ +struct bpf_object *obj; + + obj =calloc (1 ,sizeof (struct bpf_object ) +strlen (path) +1 ); +if (!obj) { +pr_warning ("alloc memory failed for %s\n" , path); +return NULL ; + } + +strcpy (obj->path, path); + obj->efile.fd =-1 ; +return obj; +} + +static void bpf_object__elf_finish (struct bpf_object *obj) +{ +if (!obj_elf_valid (obj)) +return ; + +if (obj->efile.elf) { +elf_end (obj->efile.elf); + obj->efile.elf =NULL ; + } +zclose (obj->efile.fd); +} + +static int bpf_object__elf_init (struct bpf_object *obj) +{ +int err =0 ; +GElf_Ehdr *ep; + +if (obj_elf_valid (obj)) { +pr_warning ("elf init: internal error\n" ); +return -EEXIST ; + } + + obj->efile.fd =open (obj->path,O_RDONLY ); +if (obj->efile.fd <0 ) { +pr_warning ("failed to open %s: %s\n" , obj->path, +strerror (errno)); +return -errno; + } + + obj->efile.elf =elf_begin (obj->efile.fd, +LIBBPF_ELF_C_READ_MMAP , +NULL ); +if (!obj->efile.elf) { +pr_warning ("failed to open %s as ELF file\n" , + obj->path); + err = -EINVAL ; + goto errout; + } + +if (!gelf_getehdr (obj->efile.elf, &obj->efile.ehdr)) { +pr_warning ("failed to get EHDR from %s\n" , + obj->path); + err = -EINVAL ; + goto errout; + } + ep = &obj->efile.ehdr; + +if ((ep->e_type !=ET_REL ) || (ep->e_machine !=0 )) { +pr_warning ("%s is not an eBPF object file\n" , + obj->path); + err = -EINVAL ; + goto errout; + } + +return 0 ; +errout: +bpf_object__elf_finish (obj); +return err; +} + +static struct bpf_object * +__bpf_object__open (const char *path) +{ +struct bpf_object *obj; + +if (elf_version (EV_CURRENT ) ==EV_NONE ) { +pr_warning ("failed to init libelf for %s\n" , path); +return NULL ; + } + + obj =bpf_object__new (path); +if (!obj) +return NULL ; + +if (bpf_object__elf_init (obj)) + goto out; + +bpf_object__elf_finish (obj); +return obj; +out: +bpf_object__close (obj); +return NULL ; +} + +struct bpf_object *bpf_object__open (const char *path) +{ +/* param validation */ +if (!path) +return NULL ; + +pr_debug ("loading %s\n" , path); + +return __bpf_object__open (path); +} + +void bpf_object__close (struct bpf_object *obj) +{ +if (!obj) +return ; + +bpf_object__elf_finish (obj); + +free (obj); +}
tools/lib/bpf/libbpf.h +8 -0
@@ -8,6 +8,8 @@#ifndef __BPF_LIBBPF_H#define __BPF_LIBBPF_H +#include <stdio.h> +/* * In include/linux/compiler-gcc.h, __printf is defined. However * it should be better if libbpf.h doesn't depend on Linux header file.
@@ -20,4 +22,10 @@ void libbpf_set_print(libbpf_print_fn_t warn,libbpf_print_fn_t info, libbpf_print_fn_t debug); +/* Hide internal to user */ +struct bpf_object ; + +struct bpf_object *bpf_object__open (const char *path); +void bpf_object__close (struct bpf_object *object); +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 5/49 bpf tools: Read eBPF object from buffer
In reply to Wang NanTo support dynamic compiling, this patch allows caller to pass a in-memory buffer to libbpf by bpf_object__open_buffer(). libbpf calls elf_memory() to open it as ELF object file.
Because __bpf_object__open() collects all required data and won't need that buffer anymore, libbpf uses that buffer directly instead of clone a new buffer. Caller of libbpf can free that buffer or use it do other things after bpf_object__open_buffer() return.
--- tools/lib/bpf/libbpf.c | 62 ++++++++++++++++++++++++++++++++++++++++---------- tools/lib/bpf/libbpf.h | 2 ++ 2 files changed, 52 insertions(+), 12 deletions(-)
tools/lib/bpf/libbpf.c +50 -12
@@ -84,6 +84,8 @@ struct bpf_object {*/ struct {int fd; +void *obj_buf; +size_t obj_buf_sz;Elf *elf;GElf_Ehdr ehdr; } efile;
@@ -91,7 +93,9 @@ struct bpf_object { };#define obj_elf_valid (o) ((o)->efile.elf) -static struct bpf_object *bpf_object__new (const char *path) +static struct bpf_object *bpf_object__new (const char *path, +void *obj_buf, +size_t obj_buf_sz) {struct bpf_object *obj;
@@ -103,6 +107,16 @@ static struct bpf_object *bpf_object__new(const char *path)strcpy (obj->path, path); obj->efile.fd =-1 ; + +/* +* Caller of this function should also calls +* 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. +*/ + obj->efile.obj_buf = obj_buf; + obj->efile.obj_buf_sz = obj_buf_sz; +return obj; }
@@ -116,6 +130,8 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf =NULL ; }zclose (obj->efile.fd); + obj->efile.obj_buf =NULL ; + obj->efile.obj_buf_sz =0 ; }static int bpf_object__elf_init (struct bpf_object *obj)
@@ -128,16 +144,26 @@ static int bpf_object__elf_init(struct bpf_object *obj)return -EEXIST ; } - obj->efile.fd =open (obj->path,O_RDONLY ); -if (obj->efile.fd <0 ) { -pr_warning ("failed to open %s: %s\n" , obj->path, -strerror (errno)); -return -errno; +if (obj->efile.obj_buf_sz >0 ) { +/* +* obj_buf should have been validated by +* bpf_object__open_buffer(). +*/ + obj->efile.elf =elf_memory (obj->efile.obj_buf, + obj->efile.obj_buf_sz); + }else { + obj->efile.fd =open (obj->path,O_RDONLY ); +if (obj->efile.fd <0 ) { +pr_warning ("failed to open %s: %s\n" , obj->path, +strerror (errno)); +return -errno; + } + + obj->efile.elf =elf_begin (obj->efile.fd, +LIBBPF_ELF_C_READ_MMAP , +NULL ); } - obj->efile.elf =elf_begin (obj->efile.fd, -LIBBPF_ELF_C_READ_MMAP , -NULL );if (!obj->efile.elf) {pr_warning ("failed to open %s as ELF file\n" , obj->path);
@@ -167,7 +193,7 @@ errout: }static struct bpf_object * -__bpf_object__open (const char *path) +__bpf_object__open (const char *path,void *obj_buf,size_t obj_buf_sz) {struct bpf_object *obj;
@@ -176,7 +202,7 @@ __bpf_object__open(const char *path)return NULL ; } - obj =bpf_object__new (path); + obj =bpf_object__new (path, obj_buf, obj_buf_sz);if (!obj)return NULL ;
@@ -198,7 +224,19 @@ struct bpf_object *bpf_object__open(const char *path)pr_debug ("loading %s\n" , path); -return __bpf_object__open (path); +return __bpf_object__open (path,NULL ,0 ); +} + +struct bpf_object *bpf_object__open_buffer (void *obj_buf, +size_t obj_buf_sz) +{ +/* param validation */ +if (!obj_buf || obj_buf_sz <=0 ) +return NULL ; + +pr_debug ("loading object from buffer\n" ); + +return __bpf_object__open ("[buffer]" , obj_buf, obj_buf_sz); }void bpf_object__close (struct bpf_object *obj)
tools/lib/bpf/libbpf.h +2 -0
@@ -26,6 +26,8 @@ void libbpf_set_print(libbpf_print_fn_t warn,struct bpf_object ;struct bpf_object *bpf_object__open (const char *path); +struct bpf_object *bpf_object__open_buffer (void *obj_buf, +size_t obj_buf_sz);void bpf_object__close (struct bpf_object *object);#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 6/49 bpf tools: Check endianess and make libbpf fail early
In reply to Wang NanCheck endianess according to EHDR. Code is taken from tools/perf/util/symbol-elf.c.
Libbpf doesn't magically convert missmatched endianess. Even if we swap eBPF instructions to correct byte order, we are unable to deal with endianess in code logical generated by LLVM.
Therefore, libbpf should simply reject missmatched ELF object, and let LLVM to create good code.
--- tools/lib/bpf/libbpf.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+)
tools/lib/bpf/libbpf.c +30 -0
@@ -192,6 +192,34 @@ errout:return err; } +static int +bpf_object__check_endianess (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 -EINVAL ; + } + +return 0 ; + +mismatch: +pr_warning ("Error: endianess mismatch.\n" ); +return -EINVAL ; +} +static struct bpf_object *__bpf_object__open (const char *path,void *obj_buf,size_t obj_buf_sz) {
@@ -208,6 +236,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)if (bpf_object__elf_init (obj)) goto out; +if (bpf_object__check_endianess (obj)) + goto out;bpf_object__elf_finish (obj);return obj;
Signature · 1 line
1.8.3.4
RFC PATCH v8 7/49 bpf tools: Iterate over ELF sections to collect information
In reply to Wang Nanbpf_obj_elf_collect() is introduced to iterate over each elf sections to collection informations in eBPF object files. This function will futher enhanced to collect license, kernel version, programs, configs and map information.
--- tools/lib/bpf/libbpf.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+)
tools/lib/bpf/libbpf.c +53 -0
@@ -220,6 +220,57 @@ mismatch:return -EINVAL ; } +static int bpf_object__elf_collect (struct bpf_object *obj) +{ +Elf *elf = obj->efile.elf; +GElf_Ehdr *ep = &obj->efile.ehdr; +Elf_Scn *scn =NULL ; +int idx =0 , err =0 ; + +/* Elf is corrupted/truncated, avoid calling elf_strptr. */ +if (!elf_rawdata (elf_getscn (elf, ep->e_shstrndx),NULL )) { +pr_warning ("failed to get e_shstrndx from %s\n" , + obj->path); +return -EINVAL ; + } + +while ((scn =elf_nextscn (elf, scn)) !=NULL ) { +char *name; +GElf_Shdr sh; +Elf_Data *data; + + idx++; +if (gelf_getshdr (scn, &sh) != &sh) { +pr_warning ("failed to get section header from %s\n" , + obj->path); + err = -EINVAL ; + goto out; + } + + name =elf_strptr (elf, ep->e_shstrndx, sh.sh_name); +if (!name) { +pr_warning ("failed to get section name from %s\n" , + obj->path); + err = -EINVAL ; + goto out; + } + + data =elf_getdata (scn,0 ); +if (!data) { +pr_warning ("failed to get section data from %s(%s)\n" , + name, obj->path); + err = -EINVAL ; + goto out; + } +pr_debug ("section %s, size %ld, link %d, flags %lx, type=%d\n" , + name, (unsigned long )data->d_size, + (int )sh.sh_link, (unsigned long )sh.sh_flags, + (int )sh.sh_type); + } +out: +return err; +} +static struct bpf_object *__bpf_object__open (const char *path,void *obj_buf,size_t obj_buf_sz) {
@@ -238,6 +289,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) goto out;if (bpf_object__check_endianess (obj)) goto out; +if (bpf_object__elf_collect (obj)) + goto out;bpf_object__elf_finish (obj);return obj;
Signature · 1 line
1.8.3.4
RFC PATCH v8 8/49 bpf tools: Collect version and license from ELF sections
In reply to Wang NanExpand bpf_obj_elf_collect() to collect license and kernel version information in eBPF object file. eBPF object file should have a section named 'license', which contains a string. It should also have a section named 'version', contains a u32 LINUX_VERSION_CODE.
bpf_obj_validate() is introduced to validate object file after loaded. Currently it only check existance of 'version' section.
--- tools/lib/bpf/libbpf.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
tools/lib/bpf/libbpf.c +52 -0
@@ -14,6 +14,7 @@#include <fcntl.h> #include <errno.h> #include <asm/unistd.h> +#include <linux/kernel.h> #include <linux/bpf.h> #include <libelf.h> #include <gelf.h>
@@ -78,6 +79,8 @@ void libbpf_set_print(libbpf_print_fn_t warn,#endif struct bpf_object { +char license[64 ]; +u32 kern_version;/* * Information when doing elf related work. Only valid if fd * is valid.
@@ -220,6 +223,32 @@ mismatch:return -EINVAL ; } +static int +bpf_object__init_license (struct bpf_object *obj, +void *data,size_t size) +{ +memcpy (obj->license, data, +min (size,sizeof (obj->license) -1 )); +pr_debug ("license of %s is %s\n" , obj->path, obj->license); +return 0 ; +} + +static int +bpf_object__init_kversion (struct bpf_object *obj, +void *data,size_t size) +{ +u32 kver; +if (size !=sizeof (kver)) { +pr_warning ("invalid kver section in %s\n" , obj->path); +return -EINVAL ; + } +memcpy (&kver, data,sizeof (kver)); + obj->kern_version = kver; +pr_debug ("kernel version of %s is %x\n" , obj->path, + obj->kern_version); +return 0 ; +} +static int bpf_object__elf_collect (struct bpf_object *obj) {Elf *elf = obj->efile.elf;
@@ -266,11 +295,32 @@ static int bpf_object__elf_collect(struct bpf_object *obj) name, (unsigned long )data->d_size, (int )sh.sh_link, (unsigned long )sh.sh_flags, (int)sh.sh_type); + +if (strcmp (name,"license" ) ==0 ) + err =bpf_object__init_license (obj, + data->d_buf, + data->d_size); +else if (strcmp (name,"version" ) ==0 ) + err =bpf_object__init_kversion (obj, + data->d_buf, + data->d_size); +if (err) + goto out; } out:return err; } +static int bpf_object__validate (struct bpf_object *obj) +{ +if (obj->kern_version ==0 ) { +pr_warning ("%s doesn't provide kernel version\n" , + obj->path); +return -EINVAL ; + } +return 0 ; +} +static struct bpf_object *__bpf_object__open (const char *path,void *obj_buf,size_t obj_buf_sz) {
@@ -291,6 +341,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) goto out;if (bpf_object__elf_collect (obj)) goto out; +if (bpf_object__validate (obj)) + goto out;bpf_object__elf_finish (obj);return obj;
Signature · 1 line
1.8.3.4
RFC PATCH v8 9/49 bpf tools: Collect map definitions from 'maps' section
In reply to Wang NanIf maps are used by eBPF programs, corresponding object file(s) should contain a section named 'map'. Which contains map definitions. This patch copies the data of the whole section. Map data parsing should be acted just before map loading.
--- tools/lib/bpf/libbpf.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+)
tools/lib/bpf/libbpf.c +29 -0
@@ -81,6 +81,9 @@ void libbpf_set_print(libbpf_print_fn_t warn,struct bpf_object {char license[64 ];u32 kern_version; +void *maps_buf; +size_t maps_buf_sz; +/* * Information when doing elf related work. Only valid if fd * is valid.
@@ -249,6 +252,28 @@ bpf_object__init_kversion(struct bpf_object *obj,return 0 ; } +static int +bpf_object__init_maps (struct bpf_object *obj,void *data, +size_t size) +{ +if (size ==0 ) { +pr_debug ("%s doesn't need map definition\n" , + obj->path); +return 0 ; + } + + obj->maps_buf =malloc (size); +if (!obj->maps_buf) { +pr_warning ("malloc maps failed: %s\n" , obj->path); +return -ENOMEM ; + } + + obj->maps_buf_sz = size; +memcpy (obj->maps_buf, data, size); +pr_debug ("maps in %s: %ld bytes\n" , obj->path, (long )size); +return 0 ; +} +static int bpf_object__elf_collect (struct bpf_object *obj) {Elf *elf = obj->efile.elf;
@@ -304,6 +329,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj) err =bpf_object__init_kversion (obj, data->d_buf, data->d_size); + else if (strcmp(name, "maps") == 0) + err =bpf_object__init_maps (obj, data->d_buf, + data->d_size);if (err) goto out; }
@@ -381,5 +409,6 @@ void bpf_object__close(struct bpf_object *obj)bpf_object__elf_finish (obj); +zfree (&obj->maps_buf);free (obj); }
Signature · 1 line
1.8.3.4
RFC PATCH v8 10/49 bpf tools: Collect symbol table from SHT_SYMTAB section
In reply to Wang NanThis patch collects symbols section. This section is useful when linking ELF maps.
--- tools/lib/bpf/libbpf.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
tools/lib/bpf/libbpf.c +10 -0
@@ -94,6 +94,7 @@ struct bpf_object {size_t obj_buf_sz;Elf *elf;GElf_Ehdr ehdr; +Elf_Data *symbols; } efile;char path[]; };
@@ -135,6 +136,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)elf_end (obj->efile.elf); obj->efile.elf =NULL ; } + obj->efile.symbols =NULL ;zclose (obj->efile.fd); obj->efile.obj_buf =NULL ; obj->efile.obj_buf_sz =0 ;
@@ -332,6 +334,14 @@ static int bpf_object__elf_collect(struct bpf_object *obj)else if (strcmp (name,"maps" ) ==0 ) err =bpf_object__init_maps (obj, data->d_buf, data->d_size); +else if (sh.sh_type ==SHT_SYMTAB ) { +if (obj->efile.symbols) { +pr_warning ("bpf: multiple SYMTAB in %s\n" , + obj->path); + err = -EEXIST ; + }else + obj->efile.symbols = data; + }if (err) goto out; }
Signature · 1 line
1.8.3.4
RFC PATCH v8 11/49 bpf tools: Collect eBPF programs from their own sections
In reply to Wang NanThis patch collects all programs in an object file into an array of 'struct bpf_program' for further processing. That structure is for representing each eBPF program. 'bpf_prog' should be a better name, but it has been used by linux/filter.h. Although it is a kernel space name, I still prefer to call it 'bpf_program' to prevent possible confusion.
--- tools/lib/bpf/libbpf.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+)
tools/lib/bpf/libbpf.c +107 -0
@@ -78,12 +78,27 @@ void libbpf_set_print(libbpf_print_fn_t warn,# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ#endif +/* +* bpf_prog should be a better name but it has been used in +* linux/filter.h. +*/ +struct bpf_program { +/* Index in elf obj file, for relocation use. */ +int idx; +char *section_name; +struct bpf_insn *insns; +size_t insns_cnt; +}; +struct bpf_object {char license[64 ];u32 kern_version;void *maps_buf;size_t maps_buf_sz; +struct bpf_program *programs; +size_t nr_programs; +/* * Information when doing elf related work. Only valid if fd * is valid.
@@ -100,6 +115,74 @@ struct bpf_object { };#define obj_elf_valid (o) ((o)->efile.elf) +static void bpf_program__clear (struct bpf_program *prog) +{ +if (!prog) +return ; + +zfree (&prog->section_name); +zfree (&prog->insns); + prog->insns_cnt =0 ; + prog->idx =-1 ; +} + +static struct bpf_program * +bpf_program__new (struct bpf_object *obj,void *data,size_t size, +char *name,int idx) +{ +struct bpf_program *prog, *progs; +int nr_progs; + +if (size <sizeof (struct bpf_insn )) { +pr_warning ("corrupted section '%s'\n" , name); +return NULL ; + } + + progs = obj->programs; + nr_progs = obj->nr_programs; + + progs =realloc (progs,sizeof (*prog) * (nr_progs +1 )); +if (!progs) { +/* +* In this case the original obj->programs +* is still valid, so don't need special treat for +* bpf_close_object(). +*/ +pr_warning ("failed to alloc a new program '%s'\n" , + name); +return NULL ; + } + + obj->programs = progs; + + prog = &progs[nr_progs]; +bzero (prog,sizeof (*prog)); + + obj->nr_programs = nr_progs +1 ; + + prog->section_name =strdup (name); +if (!prog->section_name) { +pr_warning ("failed to alloc name for prog %s\n" , + name); + goto out; + } + + prog->insns =malloc (size); +if (!prog->insns) { +pr_warning ("failed to alloc insns for %s\n" , name); + goto out; + } + prog->insns_cnt = size /sizeof (struct bpf_insn ); +memcpy (prog->insns, data, + prog->insns_cnt *sizeof (struct bpf_insn )); + prog->idx = idx; + +return prog; +out: +bpf_program__clear (prog); +return NULL ; +} +static struct bpf_object *bpf_object__new (const char *path,void *obj_buf,size_t obj_buf_sz)
@@ -341,6 +424,21 @@ static int bpf_object__elf_collect(struct bpf_object *obj) err = -EEXIST ; }else obj->efile.symbols = data; + }else if ((sh.sh_type ==SHT_PROGBITS ) && + (sh.sh_flags &SHF_EXECINSTR ) && + (data->d_size >0 )) { +struct bpf_program *prog; + + prog =bpf_program__new (obj, data->d_buf, + data->d_size, name, + idx); +if (!prog) { +pr_warning ("failed to alloc program %s (%s)" , + name, obj->path); + err = -ENOMEM ; + }else +pr_debug ("found program %s\n" , + prog->section_name); }if (err) goto out;
@@ -414,11 +512,20 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,void bpf_object__close (struct bpf_object *obj) { +size_t i; +if (!obj)return ;bpf_object__elf_finish (obj);zfree (&obj->maps_buf); + +if (obj->programs && obj->nr_programs) { +for (i =0 ; i < obj->nr_programs; i++) +bpf_program__clear (&obj->programs[i]); + } +zfree (&obj->programs); +free (obj); }
Signature · 1 line
1.8.3.4
RFC PATCH v8 12/49 bpf tools: Collect relocation sections from SHT_REL sections
In reply to Wang NanThis patch collects relocation sections into 'struct object'. Such sections are used for connecting maps to bpf programs. 'reloc' field in 'struct bpf_object' is introduced for storing such informations.
This patch simply store the data into 'reloc' field. Following patch will parse them to know the exact instructions which are needed to be relocated.
Note that the collected data will be invalid after ELF object file is closed.
--- tools/lib/bpf/libbpf.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)
tools/lib/bpf/libbpf.c +26 -0
@@ -110,6 +110,11 @@ struct bpf_object {Elf *elf;GElf_Ehdr ehdr;Elf_Data *symbols; +struct { +GElf_Shdr shdr; +Elf_Data *data; + } *reloc; +int nr_reloc; } efile;char path[]; };
@@ -220,6 +225,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf =NULL ; } obj->efile.symbols =NULL ; + +zfree (&obj->efile.reloc); + obj->efile.nr_reloc =0 ;zclose (obj->efile.fd); obj->efile.obj_buf =NULL ; obj->efile.obj_buf_sz =0 ;
@@ -439,6 +447,24 @@ static int bpf_object__elf_collect(struct bpf_object *obj) }else pr_debug ("found program %s\n" , prog->section_name); + }else if (sh.sh_type ==SHT_REL ) { +void *reloc = obj->efile.reloc; +int nr_reloc = obj->efile.nr_reloc; + + reloc =realloc (reloc, +sizeof (*obj->efile.reloc) * (++nr_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; + } }if (err) goto out;
Signature · 1 line
1.8.3.4
RFC PATCH v8 13/49 bpf tools: Record map accessing instructions for each program
In reply to Wang NanThis patch records the indics of instructions which are needed to be relocated. Those information are saved in 'reloc_desc' field in 'struct bpf_program'. In loading phase (this patch takes effect in opening phase), the collected instructions will be replaced by map loading instructions.
Since we are going to close the ELF file and clear all data at the end of 'opening' phase, ELF information will no longer be valid in 'loading' phase. We have to locate the instructions before maps are loaded, instead of directly modifying the instruction.
'struct bpf_map_def' is introduce in this patch to let us know how many maps defined in the object.
--- tools/lib/bpf/libbpf.c | 124 +++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 13 ++++++ 2 files changed, 137 insertions(+)
tools/lib/bpf/libbpf.c +124 -0
@@ -9,6 +9,7 @@#include <stdlib.h> #include <stdio.h> #include <stdarg.h> +#include <inttypes.h> #include <string.h> #include <unistd.h> #include <fcntl.h>
@@ -88,6 +89,12 @@ struct bpf_program {char *section_name;struct bpf_insn *insns;size_t insns_cnt; + +struct { +int insn_idx; +int map_idx; + } *reloc_desc; +int nr_reloc; };struct bpf_object {
@@ -127,6 +134,9 @@ static void bpf_program__clear(struct bpf_program *prog)zfree (&prog->section_name);zfree (&prog->insns); +zfree (&prog->reloc_desc); + + prog->nr_reloc =0 ; prog->insns_cnt =0 ; prog->idx =-1 ; }
@@ -473,6 +483,118 @@ out:return err; } +static struct bpf_program * +bpf_object__find_prog_by_idx (struct bpf_object *obj,int idx) +{ +struct bpf_program *prog; +size_t i; + +for (i =0 ; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; +if (prog->idx == idx) +return prog; + } +return NULL ; +} + +static int +bpf_program__collect_reloc (struct bpf_program *prog, +size_t nr_maps,GElf_Shdr *shdr, +Elf_Data *data,Elf_Data *symbols) +{ +int i, nrels; + +pr_debug ("collecting relocating info for: '%s'\n" , + prog->section_name); + nrels = shdr->sh_size / shdr->sh_entsize; + + prog->reloc_desc =malloc (sizeof (*prog->reloc_desc) * nrels); +if (!prog->reloc_desc) { +pr_warning ("failed to alloc memory in relocation\n" ); +return -ENOMEM ; + } + prog->nr_reloc = nrels; + +for (i =0 ; i < nrels; i++) { +GElf_Sym sym; +GElf_Rel rel; +unsigned int insn_idx; +struct bpf_insn *insns = prog->insns; +size_t map_idx; + +if (!gelf_getrel (data, i, &rel)) { +pr_warning ("relocation: failed to get %d reloc\n" , i); +return -EINVAL ; + } + + insn_idx = rel.r_offset /sizeof (struct bpf_insn ); +pr_debug ("relocation: insn_idx=%u\n" , insn_idx); + +if (!gelf_getsym (symbols, +GELF_R_SYM (rel.r_info), + &sym)) { +pr_warning ("relocation: symbol %" PRIx64" not found\n" , +GELF_R_SYM (rel.r_info)); +return -EINVAL ; + } + +if (insns[insn_idx].code != (BPF_LD |BPF_IMM |BPF_DW )) { +pr_warning ("bpf: relocation: invalid relo for insns[%d].code 0x%x\n" , + insn_idx, insns[insn_idx].code); +return -EINVAL ; + } + + map_idx = sym.st_value /sizeof (struct bpf_map_def ); +if (map_idx >= nr_maps) { +pr_warning ("bpf relocation: map_idx %d large than %d\n" , + (int )map_idx, (int )nr_maps -1 ); +return -EINVAL ; + } + + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].map_idx = map_idx; + } +return 0 ; +} + +static int bpf_object__collect_reloc (struct bpf_object *obj) +{ +int i, err; + +if (!obj_elf_valid (obj)) { +pr_warning ("Internal error: elf object is closed\n" ); +return -EINVAL ; + } + +for (i =0 ; i < obj->efile.nr_reloc; i++) { +GElf_Shdr *shdr = &obj->efile.reloc[i].shdr; +Elf_Data *data = obj->efile.reloc[i].data; +int idx = shdr->sh_info; +struct bpf_program *prog; +size_t nr_maps = obj->maps_buf_sz / +sizeof (struct bpf_map_def ); + +if (shdr->sh_type !=SHT_REL ) { +pr_warning ("internal error at %d\n" , __LINE__); +return -EINVAL ; + } + + prog =bpf_object__find_prog_by_idx (obj, idx); +if (!prog) { +pr_warning ("relocation failed: no %d section\n" , + idx); +return -ENOENT ; + } + + err =bpf_program__collect_reloc (prog, nr_maps, + shdr, data, + obj->efile.symbols); +if (err) +return -EINVAL ; + } +return 0 ; +} +static int bpf_object__validate (struct bpf_object *obj) {if (obj->kern_version ==0 ) {
@@ -503,6 +625,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) goto out;if (bpf_object__elf_collect (obj)) goto out; +if (bpf_object__collect_reloc (obj)) + goto out;if (bpf_object__validate (obj)) goto out;
tools/lib/bpf/libbpf.h +13 -0
@@ -30,4 +30,17 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz);void bpf_object__close (struct bpf_object *object); +/* +* We don't need __attribute__((packed)) now since it is +* unnecessary for 'bpf_map_def' because they are all aligned. +* In addition, using it will trigger -Wpacked warning message, +* and will be treated as an error due to -Werror. +*/ +struct bpf_map_def { +unsigned int type; +unsigned int key_size; +unsigned int value_size; +unsigned int max_entries; +}; +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 14/49 bpf tools: Add bpf.c/h for common bpf operations
In reply to Wang NanThis patch introduces bpf.c and bpf.h, which hold common functions issuing bpf syscall. The goal of these two files is to hide syscall completly from user. Note that bpf.c and bpf.h only deal with kernel interface. Things like structure of 'map' section in the ELF object is not cared by of bpf.[ch].
We first introduce bpf_create_map().
Note that, since functions in bpf.[ch] are wrapper of sys_bpf, they don't use OO style naming.
--- tools/lib/bpf/Build | 2 +- tools/lib/bpf/bpf.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/bpf.h | 16 ++++++++++++++++ 3 files changed, 67 insertions(+), 1 deletion(-) create mode 100644 tools/lib/bpf/bpf.c create mode 100644 tools/lib/bpf/bpf.h
tools/lib/bpf/Build +1 -1
@@ -1 +1 @@ -libbpf-y := libbpf.o +libbpf-y := libbpf.o bpf.o
tools/lib/bpf/bpf.c new file +50 -0
50 lines not on this page · raw message
tools/lib/bpf/bpf.h new file +16 -0
@@ -0,0 +1,16 @@ +/* +* common eBPF ELF operations. +* +* Copyright (C) 2013-2015 Alexei Starovoitov <[email protected]> +* Copyright (C) 2015 Wang Nan <[email protected]> +* Copyright (C) 2015 Huawei Inc. +*/ +#ifndef __BPF_BPF_H +#define __BPF_BPF_H + +#include <linux/bpf.h> + +int bpf_create_map (enum bpf_map_type map_type,int key_size,int value_size, +int max_entries); + +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 15/49 bpf tools: Create eBPF maps defined in an object file
In reply to Wang NanThis patch creates maps based on 'map' section in object file using bpf_create_map(), and stores the fds into an array in 'struct bpf_object'.
Previous patches parse ELF object file and collecte required data, but doesn't play with kernel. They belong to 'opening' phase. This patch is the first patch in 'loading' phase. 'loaded' field is introduced to 'struct bpf_object' to avoid loading one object twice, because loading phase clears resources collected during opening which become useless after loading. In this patch, maps_buf is cleared.
--- tools/lib/bpf/libbpf.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 4 ++ 2 files changed, 106 insertions(+)
tools/lib/bpf/libbpf.c +102 -0
@@ -21,6 +21,7 @@#include <gelf.h> #include "libbpf.h" +#include "bpf.h" #define __printf (a, b) __attribute__((format(printf, a, b)))
@@ -105,6 +106,13 @@ struct bpf_object {struct bpf_program *programs;size_t nr_programs; +int *map_fds; +/* +* This field is required because maps_buf will be freed and +* maps_buf_sz will be set to 0 after loaded. +*/ +size_t nr_map_fds; +bool loaded;/* * Information when doing elf related work. Only valid if fd
@@ -222,6 +230,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; + obj->loaded = false;return obj; }
@@ -557,6 +566,62 @@ bpf_program__collect_reloc(struct bpf_program *prog,return 0 ; } +static int +bpf_object__create_maps (struct bpf_object *obj) +{ +unsigned int i; +size_t nr_maps; +int *pfd; + + nr_maps = obj->maps_buf_sz /sizeof (struct bpf_map_def ); +if (!obj->maps_buf || !nr_maps) { +pr_debug ("don't need create maps for %s\n" , + obj->path); +return 0 ; + } + + obj->map_fds =malloc (sizeof (int ) * nr_maps); +if (!obj->map_fds) { +pr_warning ("realloc perf_bpf_map_fds failed\n" ); +return -ENOMEM ; + } + obj->nr_map_fds = nr_maps; + +/* fill all fd with -1 */ +memset (obj->map_fds,0xff ,sizeof (int ) * nr_maps); + + pfd = obj->map_fds; +for (i =0 ; i < nr_maps; i++) { +struct bpf_map_def def; + + def = *(struct bpf_map_def *)(obj->maps_buf + + i *sizeof (struct bpf_map_def )); + + *pfd =bpf_create_map (def.type, + def.key_size, + def.value_size, + def.max_entries); +if (*pfd <0 ) { +size_t j; +int err = *pfd; + +pr_warning ("failed to create map: %s\n" , +strerror (errno)); +for (j =0 ; j < i; j++) +zclose (obj->map_fds[j]); + obj->nr_map_fds =0 ; +zfree (&obj->map_fds); +return err; + } +pr_debug ("create map: fd=%d\n" , *pfd); + pfd ++; + } + +zfree (&obj->maps_buf); + obj->maps_buf_sz =0 ; +return 0 ; +} +static int bpf_object__collect_reloc (struct bpf_object *obj) {int i, err;
@@ -660,6 +725,42 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,return __bpf_object__open ("[buffer]" , obj_buf, obj_buf_sz); } +int bpf_object__unload (struct bpf_object *obj) +{ +size_t i; + +if (!obj) +return -EINVAL ; + +for (i =0 ; i < obj->nr_map_fds; i++) +zclose (obj->map_fds[i]); +zfree (&obj->map_fds); + obj->nr_map_fds =0 ; + +return 0 ; +} + +int bpf_object__load (struct bpf_object *obj) +{ +if (!obj) +return -EINVAL ; + +if (obj->loaded) { +pr_warning ("object should not be loaded twice\n" ); +return -EINVAL ; + } + + obj->loaded = true; +if (bpf_object__create_maps (obj)) + goto out; + +return 0 ; +out: +bpf_object__unload (obj); +pr_warning ("failed to load object '%s'\n" , obj->path); +return -EINVAL ; +} +void bpf_object__close (struct bpf_object *obj) {size_t i;
@@ -668,6 +769,7 @@ void bpf_object__close(struct bpf_object *obj)return ;bpf_object__elf_finish (obj); +bpf_object__unload (obj);zfree (&obj->maps_buf);
tools/lib/bpf/libbpf.h +4 -0
@@ -30,6 +30,10 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz);void bpf_object__close (struct bpf_object *object); +/* Load/unload object into/from kernel */ +int bpf_object__load (struct bpf_object *obj); +int bpf_object__unload (struct bpf_object *obj); +/* * We don't need __attribute__((packed)) now since it is * unnecessary for 'bpf_map_def' because they are all aligned.
Signature · 1 line
1.8.3.4
RFC PATCH v8 16/49 bpf tools: Relocate eBPF programs
In reply to Wang NanIf an eBPF program accesses a map, LLVM generates a load instruction which loads an absolute address into a register, like this:
ld_64 r1, <MCOperand Expr:(mymap)>
...
call 2
That ld_64 instruction will be recorded in relocation section. To enable the usage of that map, relocation must be done by replacing the immediate value by real map file descriptor so it can be found by eBPF map functions.
This patch to the relocation work based on information collected by patch 'bpf tools: Collect relocation sections from SHT_REL sections'. For each instruction which needs relocation, it inject corresponding file descriptor to imm field. As a part of protocol, src_reg is set to BPF_PSEUDO_MAP_FD to notify kernel this is a map loading instruction.
--- tools/lib/bpf/libbpf.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+)
tools/lib/bpf/libbpf.c +51 -0
@@ -622,6 +622,55 @@ bpf_object__create_maps(struct bpf_object *obj)return 0 ; } +static int +bpf_program__relocate (struct bpf_program *prog,int *map_fds) +{ +int i; + +if (!prog || !prog->reloc_desc) +return 0 ; + +for (i =0 ; i < prog->nr_reloc; i++) { +int insn_idx, map_idx; +struct bpf_insn *insns = prog->insns; + + insn_idx = prog->reloc_desc[i].insn_idx; + map_idx = prog->reloc_desc[i].map_idx; + +if (insn_idx >= (int )prog->insns_cnt) { +pr_warning ("relocation out of range: '%s'\n" , + prog->section_name); +return -ERANGE ; + } + insns[insn_idx].src_reg =BPF_PSEUDO_MAP_FD ; + insns[insn_idx].imm = map_fds[map_idx]; + } + +zfree (&prog->reloc_desc); + prog->nr_reloc =0 ; +return 0 ; +} + + +static int +bpf_object__relocate (struct bpf_object *obj) +{ +struct bpf_program *prog; +size_t i; +int err; + +for (i =0 ; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + +if ((err =bpf_program__relocate (prog, obj->map_fds))) { +pr_warning ("failed to relocate '%s'\n" , + prog->section_name); +return err; + } + } +return 0 ; +} +static int bpf_object__collect_reloc (struct bpf_object *obj) {int i, err;
@@ -753,6 +802,8 @@ int bpf_object__load(struct bpf_object *obj) obj->loaded = true;if (bpf_object__create_maps (obj)) goto out; +if (bpf_object__relocate (obj)) + goto out;return 0 ; out:
Signature · 1 line
1.8.3.4
RFC PATCH v8 17/49 bpf tools: Introduce bpf_load_program() to bpf.c
In reply to Wang Nanbpf_load_program() can be used to load bpf program into kernel. To make loading faster, first try to load without logbuf. Try again with logbuf if the first try failed.
--- tools/lib/bpf/bpf.c | 34 ++++++++++++++++++++++++++++++++++ tools/lib/bpf/bpf.h | 7 +++++++ 2 files changed, 41 insertions(+)
tools/lib/bpf/bpf.c +34 -0
@@ -29,6 +29,11 @@# endif #endif +static __u64 ptr_to_u64 (void *ptr) +{ +return (__u64 ) (unsigned long ) ptr; +} +static int sys_bpf (enum bpf_cmd cmd,union bpf_attr *attr,unsigned int size) {
@@ -48,3 +53,32 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,return sys_bpf (BPF_MAP_CREATE , &attr,sizeof (attr)); } + +int bpf_load_program (enum bpf_prog_type type,struct bpf_insn *insns, +size_t insns_cnt,char *license, +u32 kern_version,char *log_buf,size_t log_buf_sz) +{ +int fd; +union bpf_attr attr; + +bzero (&attr,sizeof (attr)); + attr.prog_type = type; + attr.insn_cnt = (__u32 )insns_cnt; + attr.insns =ptr_to_u64 (insns); + attr.license =ptr_to_u64 (license); + attr.log_buf =ptr_to_u64 (NULL ); + attr.log_size =0 ; + attr.log_level =0 ; + attr.kern_version = kern_version; + + fd =sys_bpf (BPF_PROG_LOAD , &attr,sizeof (attr)); +if (fd >=0 || !log_buf || !log_buf_sz) +return fd; + +/* Try again with log */ + attr.log_buf =ptr_to_u64 (log_buf); + attr.log_size = log_buf_sz; + attr.log_level =1 ; + log_buf[0 ] =0 ; +return sys_bpf (BPF_PROG_LOAD , &attr,sizeof (attr)); +}
tools/lib/bpf/bpf.h +7 -0
@@ -13,4 +13,11 @@int bpf_create_map (enum bpf_map_type map_type,int key_size,int value_size,int max_entries); +/* Recommend log buffer size */ +#define BPF_LOG_BUF_SIZE 65536 +int bpf_load_program (enum bpf_prog_type type,struct bpf_insn *insns, +size_t insns_cnt,char *license, +u32 kern_version,char *log_buf, +size_t log_buf_sz); +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 18/49 bpf tools: Load eBPF programs in object files into kernel
In reply to Wang NanThis patch utilizes previous introduced bpf_load_program to load programs in the ELF file into kernel. Result is stored in 'fd' field in 'struct bpf_program'.
During loading, it allocs a log buffer and free it before return. Note that that buffer is not passed to bpf_load_program() if the first loading try is successful. Doesn't use a statically allocated log buffer to avoid potention multi-thread problem.
Instructions collected during opening is cleared after loading.
--- tools/lib/bpf/libbpf.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+)
tools/lib/bpf/libbpf.c +80 -0
@@ -96,6 +96,8 @@ struct bpf_program {int map_idx; } *reloc_desc;int nr_reloc; + +int fd; };struct bpf_object {
@@ -135,11 +137,20 @@ struct bpf_object { };#define obj_elf_valid (o) ((o)->efile.elf) +static void bpf_program__unload (struct bpf_program *prog) +{ +if (!prog) +return ; + +zclose (prog->fd); +} +static void bpf_program__clear (struct bpf_program *prog) {if (!prog)return ; +bpf_program__unload (prog);zfree (&prog->section_name);zfree (&prog->insns);zfree (&prog->reloc_desc);
@@ -199,6 +210,7 @@ bpf_program__new(struct bpf_object *obj, void *data, size_t size,memcpy (prog->insns, data, prog->insns_cnt *sizeof (struct bpf_insn )); prog->idx = idx; + prog->fd =-1 ;return prog; out:
@@ -709,6 +721,69 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)return 0 ; } +static int +bpf_program__load (struct bpf_program *prog, +char *license,u32 kern_version) +{ +int fd, err; +char *log_buf; + +if (!prog->insns || !prog->insns_cnt) +return -EINVAL ; + + log_buf =malloc (BPF_LOG_BUF_SIZE ); +if (!log_buf) +pr_warning ("Alloc log buffer for bpf loader error, continue without log\n" ); + + fd =bpf_load_program (BPF_PROG_TYPE_KPROBE , prog->insns, + prog->insns_cnt, license, + kern_version, log_buf, +BPF_LOG_BUF_SIZE ); + +if (fd >=0 ) { + prog->fd = fd; +pr_debug ("load bpf program '%s': fd = %d\n" , + prog->section_name, prog->fd); + err =0 ; + goto out; + } + + err = -EINVAL ; +pr_warning ("load bpf program '%s' failed: %s\n" , + prog->section_name,strerror (errno)); + +if (log_buf) { +pr_warning ("bpf: load: failed to load program '%s':\n" , + prog->section_name); +pr_warning ("-- BEGIN DUMP LOG ---\n" ); +pr_warning ("%s\n" , log_buf); +pr_warning ("-- END LOG --\n" ); + } + +out: +zfree (&prog->insns); + prog->insns_cnt =0 ; +free (log_buf); +return err; +} + +static int +bpf_object__load_progs (struct bpf_object *obj) +{ +size_t i; +int err; + +for (i =0 ; i < obj->nr_programs; i++) { + err =bpf_program__load (&obj->programs[i], + obj->license, + obj->kern_version); +if (err) +return err; + } +return 0 ; +} + +static int bpf_object__validate (struct bpf_object *obj) {if (obj->kern_version ==0 ) {
@@ -786,6 +861,9 @@ int bpf_object__unload(struct bpf_object *obj)zfree (&obj->map_fds); obj->nr_map_fds =0 ; +for (i =0 ; i < obj->nr_programs; i++) +bpf_program__unload (&obj->programs[i]); +return 0 ; }
@@ -804,6 +882,8 @@ int bpf_object__load(struct bpf_object *obj) goto out;if (bpf_object__relocate (obj)) goto out; +if (bpf_object__load_progs (obj)) + goto out;return 0 ; out:
Signature · 1 line
1.8.3.4
RFC PATCH v8 19/49 bpf tools: Introduce accessors for struct bpf_program
In reply to Wang NanThis patch introduces accessors for user of libbpf to retrive section name and fd of a opened/loaded eBPF program. 'struct bpf_prog_handler' is used for that purpose. Accessors of programs section name and file descriptor are provided. Set/get private data are also impelmented.
--- tools/lib/bpf/libbpf.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 25 +++++++++++++++ 2 files changed, 107 insertions(+)
tools/lib/bpf/libbpf.c +82 -0
@@ -98,6 +98,10 @@ struct bpf_program {int nr_reloc;int fd; + +struct bpf_object *obj; +void *priv; +bpf_program_clear_priv_t clear_priv; };struct bpf_object {
@@ -150,6 +154,12 @@ static void bpf_program__clear(struct bpf_program *prog)if (!prog)return ; +if (prog->clear_priv) + prog->clear_priv (prog, prog->priv); + + prog->priv =NULL ; + prog->clear_priv =NULL ; +bpf_program__unload (prog);zfree (&prog->section_name);zfree (&prog->insns);
@@ -211,6 +221,7 @@ bpf_program__new(struct bpf_object *obj, void *data, size_t size, prog->insns_cnt * sizeof(struct bpf_insn)); prog->idx = idx; prog->fd =-1 ; + prog->obj = obj;return prog; out:
@@ -912,3 +923,74 @@ void bpf_object__close(struct bpf_object *obj)free (obj); } + +struct bpf_program * +bpf_program__next (struct bpf_program *prev,struct bpf_object *obj) +{ +size_t idx; + +if (!obj->programs) +return NULL ; +/* First handler */ +if (prev ==NULL ) +return (&obj->programs[0 ]); + +if (prev->obj != obj) { +pr_warning ("error: program handler doesn't match object\n" ); +return NULL ; + } + + idx = (prev - obj->programs) +1 ; +if (idx >= obj->nr_programs) +return NULL ; +return &obj->programs[idx]; +} + +int bpf_program__set_private (struct bpf_program *prog, +void *priv, +bpf_program_clear_priv_t clear_priv) +{ +if (prog->priv && prog->clear_priv) + prog->clear_priv (prog, prog->priv); + + prog->priv = priv; + prog->clear_priv = clear_priv; +return 0 ; +} + +int bpf_program__get_private (struct bpf_program *prog,void **ppriv) +{ + *ppriv = prog->priv; +return 0 ; +} + +int bpf_program__get_title (struct bpf_program *prog, +const char **ptitle,bool dup) +{ +const char *title; + +if (!ptitle) +return -EINVAL ; + + title = prog->section_name; +if (dup) { + title =strdup (title); +if (!title) { +pr_warning ("failed to strdup program title\n" ); + *ptitle =NULL ; +return -ENOMEM ; + } + } + + *ptitle = title; +return 0 ; +} + +int bpf_program__get_fd (struct bpf_program *prog,int *pfd) +{ +if (!pfd) +return -EINVAL ; + + *pfd = prog->fd; +return 0 ; +}
tools/lib/bpf/libbpf.h +25 -0
@@ -9,6 +9,7 @@#define __BPF_LIBBPF_H#include <stdio.h> +#include <stdbool.h> /* * In include/linux/compiler-gcc.h, __printf is defined. However
@@ -34,6 +35,30 @@ void bpf_object__close(struct bpf_object *object);int bpf_object__load (struct bpf_object *obj);int bpf_object__unload (struct bpf_object *obj); +/* Accessors of bpf_program. */ +struct bpf_program ; +struct bpf_program *bpf_program__next (struct bpf_program *prog, +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 *); + +int bpf_program__set_private (struct bpf_program *prog,void *priv, +bpf_program_clear_priv_t clear_priv); + +int bpf_program__get_private (struct bpf_program *prog, +void **ppriv); + +int bpf_program__get_title (struct bpf_program *prog, +const char **ptitle,bool dup); + +int bpf_program__get_fd (struct bpf_program *prog,int *pfd); +/* * We don't need __attribute__((packed)) now since it is * unnecessary for 'bpf_map_def' because they are all aligned.
Signature · 1 line
1.8.3.4
RFC PATCH v8 20/49 bpf tools: Introduce accessors for struct bpf_object
In reply to Wang NanThis patch add an accessor which allows caller to get count of programs in an object file.
--- tools/lib/bpf/libbpf.c | 9 +++++++++ tools/lib/bpf/libbpf.h | 3 +++ 2 files changed, 12 insertions(+)
tools/lib/bpf/libbpf.c +9 -0
@@ -924,6 +924,15 @@ void bpf_object__close(struct bpf_object *obj)free (obj); } +int bpf_object__get_prog_cnt (struct bpf_object *obj,size_t *pcnt) +{ +if (!obj || !pcnt) +return -EINVAL ; + + *pcnt = obj->nr_programs; +return 0 ; +} +struct bpf_program *bpf_program__next (struct bpf_program *prev,struct bpf_object *obj) {
tools/lib/bpf/libbpf.h +3 -0
@@ -35,6 +35,9 @@ void bpf_object__close(struct bpf_object *object);int bpf_object__load (struct bpf_object *obj);int bpf_object__unload (struct bpf_object *obj); +/* Accessors of bpf_object */ +int bpf_object__get_prog_cnt (struct bpf_object *obj,size_t *pcnt); +/* Accessors of bpf_program. */ struct bpf_program ; struct bpf_program *bpf_program__next(struct bpf_program *prog,
Signature · 1 line
1.8.3.4
RFC PATCH v8 21/49 bpf tools: Link all bpf objects onto a list
In reply to Wang NanTo prevent caller from creating additional structures to hold pointers of 'struct bpf_object', this patch link all such structures onto a list (hidden to user). bpf_object__for_each() is introduced to allow users iterate over each objects. bpf_object__for_each() is safe even user close the object during iteration.
--- tools/lib/bpf/libbpf.c | 32 ++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 7 +++++++ 2 files changed, 39 insertions(+)
tools/lib/bpf/libbpf.c +32 -0
@@ -17,6 +17,7 @@#include <asm/unistd.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/list.h> #include <libelf.h> #include <gelf.h>
@@ -104,6 +105,8 @@ struct bpf_program {bpf_program_clear_priv_t clear_priv; }; +static LIST_HEAD (bpf_objects_list); +struct bpf_object {char license[64 ];u32 kern_version;
@@ -137,6 +140,12 @@ struct bpf_object { } *reloc;int nr_reloc; } efile; +/* +* All loaded bpf_object is linked in a list, which is +* hidden to caller. bpf_objects__<func> handlers deal with +* all objects. +*/ +struct list_head list;char path[]; };#define obj_elf_valid (o) ((o)->efile.elf)
@@ -254,6 +263,9 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->loaded = false; + +INIT_LIST_HEAD (&obj->list); +list_add (&obj->list, &bpf_objects_list);return obj; }
@@ -921,6 +933,7 @@ void bpf_object__close(struct bpf_object *obj) }zfree (&obj->programs); +list_del (&obj->list);free (obj); }
@@ -933,6 +946,25 @@ int bpf_object__get_prog_cnt(struct bpf_object *obj, size_t *pcnt)return 0 ; } +struct bpf_object * +bpf_object__next (struct bpf_object *prev) +{ +struct bpf_object *next; + +if (!prev) + next =list_first_entry (&bpf_objects_list, + struct bpf_object, + list); +else + next =list_next_entry (prev, list); + +/* Empty list is noticed here so don't need checking on entry. */ +if (&next->list == &bpf_objects_list) +return NULL ; + +return next; +} +struct bpf_program *bpf_program__next (struct bpf_program *prev,struct bpf_object *obj) {
tools/lib/bpf/libbpf.h +7 -0
@@ -38,6 +38,13 @@ int bpf_object__unload(struct bpf_object *obj);/* Accessors of bpf_object */ int bpf_object__get_prog_cnt (struct bpf_object *obj,size_t *pcnt); +struct bpf_object *bpf_object__next (struct bpf_object *prev); +#define bpf_object__for_each (pos, tmp) \ + for ((pos) = bpf_object__next(NULL), \ + (tmp) = bpf_object__next(pos); \ + (pos) != NULL; \ + (pos) = (tmp), (tmp) = bpf_object__next(tmp)) +/* Accessors of bpf_program. */ struct bpf_program ; struct bpf_program *bpf_program__next(struct bpf_program *prog,
Signature · 1 line
1.8.3.4
RFC PATCH v8 22/49 perf tools: Make perf depend on libbpf
In reply to Wang NanBy adding libbpf into perf's Makefile, this patch enables perf to build libbpf during building if libelf is found and neither NO_LIBELF nor NO_LIBBPF is set. The newly introduced code is similar to libapi and libtraceevent building in Makefile.perf.
MANIFEST is also updated for 'make perf-*-src-pkg'.
Append make_no_libbpf to tools/perf/tests/make.
Error messages are also updated to notify users about the disable of BPF support of 'perf record' if libelf is missed or BPF API check failed.
--- tools/perf/MANIFEST | 3 +++ tools/perf/Makefile.perf | 19 +++++++++++++++++-- tools/perf/config/Makefile | 19 ++++++++++++++++++- tools/perf/tests/make | 4 +++- 4 files changed, 41 insertions(+), 4 deletions(-)
tools/perf/MANIFEST +3 -0
@@ -17,6 +17,7 @@ tools/build tools/arch/x86/include/asm/atomic.h tools/arch/x86/include/asm/rmwcc.h tools/lib/traceevent +tools/lib/bpf tools/lib/api tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h
@@ -67,6 +68,8 @@ include/linux/poison.h include/linux/hw_breakpoint.h include/linux/rbtree_augmented.h include/uapi/linux/perf_event.h +include/uapi/linux/bpf.h +include/uapi/linux/bpf_common.h include/uapi/linux/const.h include/uapi/linux/swab.h include/uapi/linux/hw_breakpoint.h
tools/perf/Makefile.perf +17 -2
@@ -125,6 +125,7 @@ STRIP = strip LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ +BPF_DIR = $(srctree)/tools/lib/bpf/ # include config/Makefile by default and rule out # non-config cases
@@ -160,6 +161,7 @@ strip-libs = $(filter-out -l%,$(1)) ifneq ($(OUTPUT),) TE_PATH=$(OUTPUT) + BPF_PATH=$(OUTPUT) ifneq ($(subdir),) LIB_PATH=$(OUTPUT)/../lib/api/ else
@@ -168,6 +170,7 @@ endif else TE_PATH=$(TRACE_EVENT_DIR) LIB_PATH=$(LIB_DIR) + BPF_PATH=$(BPF_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -179,6 +182,8 @@ LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYN LIBAPI = $(LIB_PATH)libapi.a export LIBAPI +LIBBPF = $(BPF_PATH)libbpf.a + # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
@@ -231,6 +236,9 @@ export PERL_PATH LIB_FILE=$(OUTPUT)libperf.a PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) +ifndef NO_LIBBPF + PERFLIBS += $(LIBBPF) +endif # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If
@@ -400,6 +408,13 @@ $(LIBAPI)-clean: $(call QUIET_CLEAN, libapi) $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null +$(LIBBPF): FORCE + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a + +$(LIBBPF)-clean: + $(call QUIET_CLEAN, libbpf) + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null + help: @echo 'Perf make targets:' @echo ' doc - make *all* documentation (see below)'
@@ -439,7 +454,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html $(DOC_TARGETS): $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) -TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol +TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol ../lib/bpf TAG_FILES= ../../include/uapi/linux/perf_event.h TAGS:
@@ -542,7 +557,7 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null -clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean +clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) .config-detected
tools/perf/config/Makefile +18 -1
@@ -106,6 +106,7 @@ ifdef LIBBABELTRACE FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf endif +FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile
@@ -233,6 +234,7 @@ ifdef NO_LIBELF NO_DEMANGLE := 1 NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 + NO_LIBBPF := 1 else ifeq ($(feature-libelf), 0) ifeq ($(feature-glibc), 1)
@@ -242,13 +244,14 @@ else LIBC_SUPPORT := 1 endif ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev); + msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install elfutils-libelf-devel/libelf-dev); NO_LIBELF := 1 NO_DWARF := 1 NO_DEMANGLE := 1 NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 + NO_LIBBPF := 1 else ifneq ($(filter s% -static%,$(LDFLAGS),),) msg := $(error No static glibc found, please install glibc-static);
@@ -301,6 +304,13 @@ ifndef NO_LIBELF $(call detected,CONFIG_DWARF) endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF + + ifndef NO_LIBBPF + ifeq ($(feature-bpf), 1) + CFLAGS += -DHAVE_LIBBPF_SUPPORT + $(call detected,CONFIG_LIBBPF) + endif + endif # NO_LIBBPF endif # NO_LIBELF ifeq ($(ARCH),powerpc)
@@ -316,6 +326,13 @@ ifndef NO_LIBUNWIND endif endif +ifndef NO_LIBBPF + ifneq ($(feature-bpf), 1) + msg := $(warning BPF API too old. Please install recent kernel headers. BPF support in 'perf record' is disabled.) + NO_LIBBPF := 1 + endif +endif + dwarf-post-unwind := 1 dwarf-post-unwind-text := BUG
tools/perf/tests/make +3 -1
@@ -33,6 +33,7 @@ make_no_libnuma := NO_LIBNUMA=1 make_no_libaudit := NO_LIBAUDIT=1 make_no_libbionic := NO_LIBBIONIC=1 make_no_auxtrace := NO_AUXTRACE=1 +make_no_libbpf := NO_LIBBPF=1 make_tags := tags make_cscope := cscope make_help := help
@@ -53,7 +54,7 @@ make_static := LDFLAGS=-static make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 -make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 +make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 # $(run) contains all available tests run := make_pure
@@ -76,6 +77,7 @@ run += make_no_libnuma run += make_no_libaudit run += make_no_libbionic run += make_no_auxtrace +run += make_no_libbpf run += make_help run += make_doc run += make_perf_o
Signature · 1 line
1.8.3.4
RFC PATCH v8 23/49 perf tools: Introduce llvm config options
In reply to Wang NanThis patch introduces [llvm] config section with 5 options. Following patches will use then to config llvm dynamica compiling.
'llvm-utils.[ch]' is introduced in this patch for holding all llvm/clang related stuffs.
Example:
[llvm]
# Path to clang. If omit, search it from $PATH. clang-path = "/path/to/clang"
# Cmdline template. Following line shows its default value.
# Environment variable is used to passing options.
clang-bpf-cmd-template = "$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c $CLANG_SOURCE -target bpf -O2 -o -"
# Options passed to clang, will be passed to cmdline by $CLANG_OPTIONS. clang-opt = "-Wno-unused-value -Wno-pointer-sign"
# kbuild directory. If not set, use /lib/modules/uname -r/build. # If set to "" deliberately, skip kernel header auto-detector. kbuild-dir = "/path/to/kernel/build"
# Options passed to 'make' when detecting kernel header options. kbuild-opts = "ARCH=x86_64"
--- tools/perf/util/Build | 1 + tools/perf/util/config.c | 4 ++++ tools/perf/util/llvm-utils.c | 45 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/llvm-utils.h | 36 +++++++++++++++++++++++++++++++++++ 4 files changed, 86 insertions(+) create mode 100644 tools/perf/util/llvm-utils.c create mode 100644 tools/perf/util/llvm-utils.h
tools/perf/util/Build +1 -0
@@ -14,6 +14,7 @@ libperf-y += find_next_bit.o libperf-y += help.o libperf-y += kallsyms.o libperf-y += levenshtein.o +libperf-y += llvm-utils.o libperf-y += parse-options.o libperf-y += parse-events.o libperf-y += path.o
tools/perf/util/config.c +4 -0
@@ -12,6 +12,7 @@#include "cache.h" #include "exec_cmd.h" #include "util/hist.h" /* perf_hist_config */ +#include "util/llvm-utils.h" /* perf_llvm_config */ #define MAXNAME (256)
@@ -408,6 +409,9 @@ int perf_default_config(const char *var, const char *value,if (!prefixcmp (var,"call-graph." ))return perf_callchain_config (var, value); +if (!prefixcmp (var,"llvm." )) +return perf_llvm_config (var, value); +/* Add other config variables here. */ return 0 ; }
tools/perf/util/llvm-utils.c new file +45 -0
45 lines not on this page · raw message
tools/perf/util/llvm-utils.h new file +36 -0
@@ -0,0 +1,36 @@ +/* +* Copyright (C) 2015, Wang Nan <[email protected]> +* Copyright (C) 2015, Huawei Inc. +*/ +#ifndef __LLVM_UTILS_H +#define __LLVM_UTILS_H + +#include "debug.h" + +struct llvm_param { +/* Path of clang executable */ +const char *clang_path; +/* +* Template of clang bpf compiling. 5 env variables +* can be used: +* $CLANG_EXEC: Path to clang. +* $CLANG_OPTIONS: Extra options to clang. +* $KERNEL_INC_OPTIONS: Kernel include directories. +* $WORKING_DIR: Kernel source directory. +* $CLANG_SOURCE: Source file to be compiled. +*/ +const char *clang_bpf_cmd_template; +/* Will be filled in $CLANG_OPTIONS */ +const char *clang_opt; +/* Where to find kbuild system */ +const char *kbuild_dir; +/* +* Arguments passed to make, like 'ARCH=arm' if doing cross +* compiling. Should not be used for dynamic compiling. +*/ +const char *kbuild_opts; +}; + +extern struct llvm_param llvm_param; +extern int perf_llvm_config (const char *var,const char *value); +#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 24/49 perf tools: Call clang to compile C source to object code
In reply to Wang NanThis is the core patch for supporting eBPF on-the-fly compiling, does the following work:
1. Search clang compiler using search_program().
2. Run command template defined in llvm-bpf-cmd-template option in [llvm] config section using read_from_pipe(). Patch of clang and source code path is injected into shell command using environment variable using force_set_env().
--- tools/perf/util/llvm-utils.c | 222 +++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/llvm-utils.h | 3 + 2 files changed, 225 insertions(+)
tools/perf/util/llvm-utils.c +222 -0
@@ -43,3 +43,225 @@ int perf_llvm_config(const char *var, const char *value)return -1 ;return 0 ; } + +static int +search_program (const char *def,const char *name, +char *output) +{ +char *env, *path, *tmp; +char buf[PATH_MAX ]; +int ret; + + output[0 ] ='\0' ; +if (def && def[0 ] !='\0' ) { +if (def[0 ] =='/' ) { +if (access (def,F_OK ) ==0 ) { +strlcpy (output, def,PATH_MAX ); +return 0 ; + } + }else if (def[0 ] !='\0' ) + name = def; + } + + env =getenv ("PATH" ); +if (!env) +return -1 ; + env =strdup (env); +if (!env) +return -1 ; + + ret = -ENOENT ; + path =strtok_r (env,":" , &tmp); +while (path) { +scnprintf (buf,sizeof (buf),"%s/%s" , path, name); +if (access (buf,F_OK ) ==0 ) { +strlcpy (output, buf,PATH_MAX ); + ret =0 ; +break ; + } + path =strtok_r (NULL ,":" , &tmp); + } + +free (env); +return ret; +} + +#define READ_SIZE 4096 +static int +read_from_pipe (const char *cmd,void **p_buf,size_t *p_read_sz) +{ +int err =0 ; +void *buf =NULL ; +FILE *file =NULL ; +size_t read_sz =0 , buf_sz =0 ; + + file =popen (cmd,"r" ); +if (!file) { +pr_err ("ERROR: unable to popen cmd: %s\n" , +strerror (errno)); +return -EINVAL ; + } + +while (!feof (file) && !ferror (file)) { +/* +* Make buf_sz always have obe byte extra space so we +* can put '\0' there. +*/ +if (buf_sz - read_sz <READ_SIZE +1 ) { +void *new_buf; + + buf_sz = read_sz +READ_SIZE +1 ; + new_buf =realloc (buf, buf_sz); + +if (!new_buf) { +pr_err ("ERROR: failed to realloc memory\n" ); + err = -ENOMEM ; + goto errout; + } + + buf = new_buf; + } + read_sz +=fread (buf + read_sz,1 ,READ_SIZE , file); + } + +if (buf_sz - read_sz <1 ) { +pr_err ("ERROR: internal error\n" ); + err = -EINVAL ; + goto errout; + } + +if (ferror (file)) { +pr_err ("ERROR: error occured when reading from pipe: %s\n" , +strerror (errno)); + err = -EIO ; + goto errout; + } + + err =WEXITSTATUS (pclose (file)); + file =NULL ; +if (err) { + err = -EINVAL ; + goto errout; + } + +/* +* If buf is string, give it terminal '\0' to make our life +* easier. If buf is not string, that '\0' is out of space +* indicated by read_sz so caller won't even notice it. +*/ + ((char *)buf)[read_sz] ='\0' ; + +if (!p_buf) +free (buf); +else + *p_buf = buf; + +if (p_read_sz) + *p_read_sz = read_sz; +return 0 ; + +errout: +if (file) +pclose (file); +free (buf); +if (p_buf) + *p_buf =NULL ; +if (p_read_sz) + *p_read_sz =0 ; +return err; +} + +static inline void +force_set_env (const char *var,const char *value) +{ +if (value) { +setenv (var, value,1 ); +pr_debug ("set env: %s=%s\n" , var, value); + }else { +unsetenv (var); +pr_debug ("unset env: %s\n" , var); + } +} + +static void +version_notice (void ) +{ +pr_err ( +" \tLLVM 3.7 or newer is required. Which can be found from http://llvm.org\n" +" \tYou may want to try git trunk:\n" +" \t\tgit clone http://llvm.org/git/llvm.git\n" +" \t\t and\n" +" \t\tgit clone http://llvm.org/git/clang.git\n\n" +" \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n" +" \toption in [llvm] section of ~/.perfconfig to:\n\n" +" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n" +" \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n" +" \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n" +" \t(Replace /path/to/llc with path to your llc)\n\n" +); +} + +int llvm__compile_bpf (const char *path,void **p_obj_buf, +size_t *p_obj_buf_sz) +{ +int err; +char clang_path[PATH_MAX ]; +const char *clang_opt = llvm_param.clang_opt; +const char *template = llvm_param.clang_bpf_cmd_template; +void *obj_buf =NULL ; +size_t obj_buf_sz; + +if (!template) + template =CLANG_BPF_CMD_DEFAULT_TEMPLATE ; + + err =search_program (llvm_param.clang_path, +"clang" , clang_path); +if (err) { +pr_err ( +"ERROR:\tunable to find clang.\n" +"Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n" +" \tand 'clang-path' option in [llvm] section of ~/.perfconfig.\n" ); +version_notice (); +return -ENOENT ; + } + +force_set_env ("CLANG_EXEC" , clang_path); +force_set_env ("CLANG_OPTIONS" , clang_opt); +force_set_env ("KERNEL_INC_OPTIONS" ,NULL ); +force_set_env ("WORKING_DIR" ,"." ); + +/* +* Since we may reset clang's working dir, path of source file +* should be transfered into absolute path, except we want +* stdin to be source file (testing). +*/ +force_set_env ("CLANG_SOURCE" , + (path[0 ] =='-' ) ? path : +make_nonrelative_path (path)); + +pr_debug ("llvm compiling command template: %s\n" , template); + err =read_from_pipe (template, &obj_buf, &obj_buf_sz); +if (err) { +pr_err ("ERROR:\tunable to compile %s\n" , path); +pr_err ("Hint:\tCheck error message shown above.\n" ); +version_notice (); +pr_err ("Hint:\tYou can also pre-compile it into .o\n" ); + goto errout; + } + +if (!p_obj_buf) +free (obj_buf); +else + *p_obj_buf = obj_buf; + +if (p_obj_buf_sz) + *p_obj_buf_sz = obj_buf_sz; +return 0 ; +errout: +free (obj_buf); +if (p_obj_buf) + *p_obj_buf =NULL ; +if (p_obj_buf_sz) + *p_obj_buf_sz =0 ; +return err; +}
tools/perf/util/llvm-utils.h +3 -0
@@ -33,4 +33,7 @@ struct llvm_param {extern struct llvm_param llvm_param;extern int perf_llvm_config (const char *var,const char *value); + +extern int llvm__compile_bpf (const char *path,void **p_obj_buf, +size_t *p_obj_buf_sz);#endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 25/49 perf tests: Add LLVM test for eBPF on-the-fly compiling
In reply to Wang NanPrevious patch introduces llvm__compile_bpf() to compile source file to eBPF object. This patch adds testcase to test it. It also test libbpf by opening generated object.
--- tools/perf/tests/Build | 1 + tools/perf/tests/builtin-test.c | 4 ++ tools/perf/tests/llvm.c | 85 +++++++++++++++++++++++++++++++++++++++++ tools/perf/tests/tests.h | 1 + 4 files changed, 91 insertions(+) create mode 100644 tools/perf/tests/llvm.c
tools/perf/tests/Build +1 -0
@@ -31,6 +31,7 @@ perf-y += code-reading.o perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o +perf-y += llvm.o perf-$(CONFIG_X86) += perf-time-to-tsc.o
tools/perf/tests/builtin-test.c +4 -0
@@ -171,6 +171,10 @@ static struct test { .func = test__kmod_path__parse, }, { + .desc = "Test LLVM searching and compiling", + .func = test__llvm, + }, + { .func = NULL, }, };
tools/perf/tests/llvm.c new file +85 -0
85 lines not on this page · raw message
tools/perf/tests/tests.h +1 -0
@@ -61,6 +61,7 @@ int test__switch_tracking(void);int test__fdarray__filter (void );int test__fdarray__add (void );int test__kmod_path__parse (void ); +int test__llvm (void );#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)#ifdef HAVE_DWARF_UNWIND_SUPPORT
Signature · 1 line
1.8.3.4
RFC PATCH v8 26/49 perf tools: Auto detecting kernel build directory
In reply to Wang NanThis patch detects kernel build directory using a embedded shell script 'kbuild_detector', which does this by checking existance of include/generated/autoconf.h.
clang working directory is changed to kbuild directory if it is found, to help user use relative include path. Following patch will detect kernel include directory, which contains relative include patch so this workdir changing is needed.
Users are allowed to set 'kbuild-dir = ""' manually to disable this checking.
--- tools/perf/util/llvm-utils.c | 56 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-)
tools/perf/util/llvm-utils.c +55 -1
@@ -201,6 +201,51 @@ version_notice(void) ); } +static const char *kbuild_detector = +"#!/usr/bin/env sh\n" +"DEFAULT_KBUILD_DIR=/lib/modules/`uname -r`/build\n" +"if test -z \"$KBUILD_DIR\"\n" +"then\n" +" KBUILD_DIR=$DEFAULT_KBUILD_DIR\n" +"fi\n" +"if test -f $KBUILD_DIR/include/generated/autoconf.h\n" +"then\n" +" echo -n $KBUILD_DIR\n" +" exit 0\n" +"fi\n" +"exit -1\n" ; + +static inline void +get_kbuild_opts (char **kbuild_dir) +{ +int err; + +if (!kbuild_dir) +return ; + + *kbuild_dir =NULL ; + +if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0 ]) { +pr_debug ("[llvm.kbuild-dir] is set to \"\" deliberately.\n" ); +pr_debug ("Skip kbuild options detection.\n" ); +return ; + } + +force_set_env ("KBUILD_DIR" , llvm_param.kbuild_dir); +force_set_env ("KBUILD_OPTS" ,llvm_param.kbuild_opts); + err =read_from_pipe (kbuild_detector, + ((void **)kbuild_dir), +NULL ); +if (err) { +pr_warning ( +"WARNING:\tunable to get correct kernel building directory.\n" +"Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n" +" \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n" +" \tdetection.\n\n" ); +return ; + } +} +int llvm__compile_bpf (const char *path,void **p_obj_buf,size_t *p_obj_buf_sz) {
@@ -208,6 +253,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,char clang_path[PATH_MAX ];const char *clang_opt = llvm_param.clang_opt;const char *template = llvm_param.clang_bpf_cmd_template; +char *kbuild_dir =NULL ;void *obj_buf =NULL ;size_t obj_buf_sz;
@@ -225,10 +271,16 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,return -ENOENT ; } +/* +* This is an optional work. Even it fail we can continue our +* work. Needn't to check error return. +*/ +get_kbuild_opts (&kbuild_dir); +force_set_env ("CLANG_EXEC" , clang_path);force_set_env ("CLANG_OPTIONS" , clang_opt);force_set_env ("KERNEL_INC_OPTIONS" ,NULL ); -force_set_env ("WORKING_DIR" ,"." ); +force_set_env ("WORKING_DIR" , kbuild_dir ? :"." );/* * Since we may reset clang's working dir, path of source file
@@ -249,6 +301,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, goto errout; } +free (kbuild_dir);if (!p_obj_buf)free (obj_buf);else
@@ -258,6 +311,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, *p_obj_buf_sz = obj_buf_sz;return 0 ; errout: +free (kbuild_dir);free (obj_buf);if (p_obj_buf) *p_obj_buf =NULL ;
Signature · 1 line
1.8.3.4
RFC PATCH v8 27/49 perf tools: Auto detecting kernel include options
In reply to Wang NanTo help user find correct kernel include options, this patch extracts them from kbuild system by an embedded script kinc_fetch_script, which creates a temporary directory, generates Makefile and an empty dummy.o then use the Makefile to fetch $(NOSTDINC_FLAGS), $(LINUXINCLUDE) and $(EXTRA_CFLAGS) options. The result is passed to compiler script using 'KERNEL_INC_OPTIONS' environment variable.
Because options from kbuild contains relative path like 'Iinclude/generated/uapi', the work directory must be changed. This is done by previous patch.
--- tools/perf/util/llvm-utils.c | 59 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 54 insertions(+), 5 deletions(-)
tools/perf/util/llvm-utils.c +54 -5
@@ -215,15 +215,42 @@ static const char *kbuild_detector ="fi\n" "exit -1\n" ; +static const char *kinc_fetch_script = +"#!/usr/bin/env sh\n" +"if ! test -d \"$KBUILD_DIR\"\n" +"then\n" +" exit -1\n" +"fi\n" +"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n" +"then\n" +" exit -1\n" +"fi\n" +"TMPDIR=`mktemp -d`\n" +"if test -z \"$TMPDIR\"\n" +"then\n" +" exit -1\n" +"fi\n" +"cat << EOF > $TMPDIR/Makefile\n" +"obj-y := dummy.o\n" +"\\$(obj)/%.o: \\$(src)/%.c\n" +"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" +"EOF\n" +"touch $TMPDIR/dummy.c\n" +"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" +"RET=$?\n" +"rm -rf $TMPDIR\n" +"exit $RET\n" ; +static inline void -get_kbuild_opts (char **kbuild_dir) +get_kbuild_opts (char **kbuild_dir,char **kbuild_include_opts) {int err; -if (!kbuild_dir) +if (!kbuild_dir || !kbuild_include_opts)return ; *kbuild_dir =NULL ; + *kbuild_include_opts =NULL ;if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0 ]) {pr_debug ("[llvm.kbuild-dir] is set to \"\" deliberately.\n" );
@@ -244,6 +271,26 @@ get_kbuild_opts(char **kbuild_dir) " \tdetection.\n\n");return ; } + +pr_debug ("Kernel build dir is set to %s\n" , *kbuild_dir); +force_set_env ("KBUILD_DIR" , *kbuild_dir); + err =read_from_pipe (kinc_fetch_script, + (void **)kbuild_include_opts, +NULL ); +if (err) { +pr_warning ( +"WARNING:\tunable to get kernel include directories from '%s'\n" +"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n" +" \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n" +" \toption in [llvm] to \"\" to suppress this detection.\n\n" , + *kbuild_dir); + +free (*kbuild_dir); + *kbuild_dir =NULL ; +return ; + } + +pr_debug ("include option is set to %s\n" , *kbuild_include_opts); } int llvm__compile_bpf(const char *path, void **p_obj_buf,
@@ -253,7 +300,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,char clang_path[PATH_MAX ];const char *clang_opt = llvm_param.clang_opt;const char *template = llvm_param.clang_bpf_cmd_template; -char *kbuild_dir =NULL ; +char *kbuild_dir =NULL , *kbuild_include_opts =NULL ;void *obj_buf =NULL ;size_t obj_buf_sz;
@@ -275,11 +322,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,* This is an optional work. Even it fail we can continue our * work. Needn't to check error return. */ -get_kbuild_opts (&kbuild_dir); +get_kbuild_opts (&kbuild_dir, &kbuild_include_opts);force_set_env ("CLANG_EXEC" , clang_path);force_set_env ("CLANG_OPTIONS" , clang_opt); -force_set_env ("KERNEL_INC_OPTIONS" ,NULL ); +force_set_env ("KERNEL_INC_OPTIONS" , kbuild_include_opts);force_set_env ("WORKING_DIR" , kbuild_dir ? :"." );/*
@@ -302,6 +349,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, }free (kbuild_dir); +free (kbuild_include_opts);if (!p_obj_buf)free (obj_buf);else
@@ -312,6 +360,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,return 0 ; errout:free (kbuild_dir); +free (kbuild_include_opts);free (obj_buf);if (p_obj_buf) *p_obj_buf =NULL ;
Signature · 1 line
1.8.3.4
RFC PATCH v8 28/49 perf record: Enable passing bpf object file to --event
In reply to Wang NanBy introducing new rules in tools/perf/util/parse-events.[ly], this patch enables 'perf record --event bpf_file.o' to select events by an eBPF object file. It calls parse_events_load_bpf() to load that file, which uses bpf__prepare_load() and finally calls bpf_object__open() for the object files.
Instead of introducing evsel to evlist during parsing, events selected by eBPF object files are appended separately. The reason is:
1. During parsing, the probing points have not been initialized.
2. Currently we are unable to call add_perf_probe_events() twice, therefore we have to wait until all such events are collected, then probe all points by one call.
The real probing and selecting is reside in following patches.
'bpf-loader.[ch]' are introduced in this patch. Which will be the interface between perf and libbpf. bpf__prepare_load() resides in bpf-loader.c. Dummy functions should be used because bpf-loader.c is available only when CONFIG_LIBBPF is on.
--- tools/perf/util/Build | 1 + tools/perf/util/bpf-loader.c | 60 ++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/bpf-loader.h | 24 +++++++++++++++++ tools/perf/util/debug.c | 5 ++++ tools/perf/util/debug.h | 1 + tools/perf/util/parse-events.c | 16 +++++++++++ tools/perf/util/parse-events.h | 2 ++ tools/perf/util/parse-events.l | 3 +++ tools/perf/util/parse-events.y | 18 ++++++++++++- 9 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 tools/perf/util/bpf-loader.c create mode 100644 tools/perf/util/bpf-loader.h
tools/perf/util/Build +1 -0
@@ -79,6 +79,7 @@ libperf-y += thread-stack.o libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-y += parse-branch-options.o +libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_LIBELF) += symbol-elf.o libperf-$(CONFIG_LIBELF) += probe-event.o
tools/perf/util/bpf-loader.c new file +60 -0
60 lines not on this page · raw message
tools/perf/util/bpf-loader.h new file +24 -0
@@ -0,0 +1,24 @@ +/* +* Copyright (C) 2015, Wang Nan <[email protected]> +* Copyright (C) 2015, Huawei Inc. +*/ +#ifndef __BPF_LOADER_H +#define __BPF_LOADER_H + +#include <linux/compiler.h> +#include "debug.h" + +#ifdef HAVE_LIBBPF_SUPPORT +int bpf__prepare_load (const char *filename); + +void bpf__clear (void ); +#else +static inline int bpf__prepare_load (const char *filename__maybe_unused ) +{ +pr_err ("ERROR: eBPF object loading is disabled during compiling.\n" ); +return -1 ; +} + +static inline void bpf__clear (void ) { } +#endif +#endif
tools/perf/util/debug.c +5 -0
@@ -36,6 +36,11 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)return ret; } +int veprintf (int level,int var,const char *fmt,va_list args) +{ +return _eprintf (level, var, fmt, args); +} +int eprintf (int level,int var,const char *fmt, ...) {va_list args;
tools/perf/util/debug.h +1 -0
@@ -50,6 +50,7 @@ void pr_stat(const char *fmt, ...);int eprintf (int level,int var,const char *fmt, ...) __attribute__((format (printf,3 ,4 )));int eprintf_time (int level,int var,u64 t,const char *fmt, ...) __attribute__((format (printf,4 ,5 ))); +int veprintf (int level,int var,const char *fmt,va_list args);int perf_debug_option (const char *str);
tools/perf/util/parse-events.c +16 -0
@@ -18,6 +18,7 @@#include "pmu.h" #include "thread_map.h" #include "asm/bug.h" +#include "bpf-loader.h" #define MAX_NAME_LEN 100
@@ -472,6 +473,21 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,return add_tracepoint_event (list, idx, sys, event); } +int parse_events_load_bpf (struct list_head *list__maybe_unused , +int *idx__maybe_unused , +char *bpf_file_name) +{ +/* +* Currently don't link any event to list. BPF object files +* should be saved to a seprated list and processed together. +* +* Things could be changed if we solve perf probe reentering +* problem. After that probe events file by file is possible. +* However, probing cost is still need to be considered. +*/ +return bpf__prepare_load (bpf_file_name); +} +static int parse_breakpoint_type (const char *type,struct perf_event_attr *attr) {
tools/perf/util/parse-events.h +2 -0
@@ -114,6 +114,8 @@ int parse_events__modifier_group(struct list_head *list, char *event_mod);int parse_events_name (struct list_head *list,char *name);int parse_events_add_tracepoint (struct list_head *list,int *idx,char *sys,char *event); +int parse_events_load_bpf (struct list_head *list,int *idx, +char *bpf_file_name); int parse_events_add_numeric(struct parse_events_evlist *data, struct list_head *list, u32 type, u64 config,
tools/perf/util/parse-events.l +3 -0
@@ -115,6 +115,7 @@ do { \ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ +bpf_object .*\.(o|bpf) num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+
@@ -159,6 +160,7 @@ modifier_bp [rwx]{1,3} } {event_pmu} | +{bpf_object} | {event} { BEGIN(INITIAL); REWIND(1);
@@ -262,6 +264,7 @@ r{num_raw_hex} { return raw(yyscanner); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {name} { return pmu_str_check(yyscanner); } +{bpf_object} { return str(yyscanner, PE_BPF_OBJECT); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; }
tools/perf/util/parse-events.y +17 -1
@@ -42,6 +42,7 @@ static inc_group_count(struct list_head *list, %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM %token PE_EVENT_NAME %token PE_NAME +%token PE_BPF_OBJECT %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
@@ -53,6 +54,7 @@ static inc_group_count(struct list_head *list, %type <num> PE_RAW %type <num> PE_TERM %type <str> PE_NAME +%type <str> PE_BPF_OBJECT %type <str> PE_NAME_CACHE_TYPE %type <str> PE_NAME_CACHE_OP_RESULT %type <str> PE_MODIFIER_EVENT
@@ -69,6 +71,7 @@ static inc_group_count(struct list_head *list, %type <head> event_legacy_tracepoint %type <head> event_legacy_numeric %type <head> event_legacy_raw +%type <head> event_bpf_file %type <head> event_def %type <head> event_mod %type <head> event_name
@@ -198,7 +201,8 @@ event_def: event_pmu | event_legacy_mem | event_legacy_tracepoint sep_dc | event_legacy_numeric sep_dc | - event_legacy_raw sep_dc + event_legacy_raw sep_dc | + event_bpf_file event_pmu: PE_NAME '/' event_config '/'
@@ -420,6 +424,18 @@ PE_RAW $$ = list; } +event_bpf_file: +PE_BPF_OBJECT +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_load_bpf(list, &data->idx, $1)); + $$ = list; +} + + start_terms: event_config { struct parse_events_terms *data = _data;
Signature · 1 line
1.8.3.4
RFC PATCH v8 29/49 perf record: Compile scriptlets if pass '.c' to --event
In reply to Wang NanThis patch enables passing source files to --event directly using:
# perf record --event bpf-file.c command
This patch does following works:
1) Allow passing '.c' file to '--event'. parse_events_load_bpf() is expanded to allow caller tell it whether the passed file is source file or object.
2) llvm__compile_bpf() is called to compile the '.c' file, the result is saved into memory. Use bpf_object__open_buffer() to load the in-memory object.
--- tools/perf/util/bpf-loader.c | 17 +++++++++++++++-- tools/perf/util/bpf-loader.h | 5 +++-- tools/perf/util/parse-events.c | 4 ++-- tools/perf/util/parse-events.h | 2 +- tools/perf/util/parse-events.l | 3 +++ tools/perf/util/parse-events.y | 15 +++++++++++++-- 6 files changed, 37 insertions(+), 9 deletions(-)
tools/perf/util/bpf-loader.c +15 -2
@@ -9,6 +9,7 @@#include "perf.h" #include "debug.h" #include "bpf-loader.h" +#include "llvm-utils.h" #define DEFINE_PRINT_FN (name, level) \ static int libbpf_##name(const char *fmt, ...) \
@@ -28,7 +29,7 @@ DEFINE_PRINT_FN(debug, 1)static bool libbpf_initialized = false; -int bpf__prepare_load (const char *filename) +int bpf__prepare_load (const char *filename,bool source) {struct bpf_object *obj;
@@ -37,7 +38,19 @@ int bpf__prepare_load(const char *filename) libbpf_info, libbpf_debug); - obj =bpf_object__open (filename); +if (source) { +void *obj_buf; +size_t obj_buf_sz; +int err; + + err =llvm__compile_bpf (filename, &obj_buf, &obj_buf_sz); +if (err) +return err; + obj =bpf_object__open_buffer (obj_buf, obj_buf_sz); +free (obj_buf); + }else + obj =bpf_object__open (filename); +if (!obj) {pr_err ("bpf: failed to load %s\n" , filename);return -EINVAL ;
tools/perf/util/bpf-loader.h +3 -2
@@ -9,11 +9,12 @@#include "debug.h" #ifdef HAVE_LIBBPF_SUPPORT -int bpf__prepare_load (const char *filename); +int bpf__prepare_load (const char *filename,bool source);void bpf__clear (void );#else -static inline int bpf__prepare_load (const char *filename__maybe_unused ) +static inline int bpf__prepare_load (const char *filename__maybe_unused , +bool source__maybe_unused ) {pr_err ("ERROR: eBPF object loading is disabled during compiling.\n" );return -1 ;
tools/perf/util/parse-events.c +2 -2
@@ -475,7 +475,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,int parse_events_load_bpf (struct list_head *list__maybe_unused ,int *idx__maybe_unused , -char *bpf_file_name) +char *bpf_file_name,bool source) {/* * Currently don't link any event to list. BPF object files
@@ -485,7 +485,7 @@ int parse_events_load_bpf(struct list_head *list __maybe_unused,* problem. After that probe events file by file is possible. * However, probing cost is still need to be considered. */ -return bpf__prepare_load (bpf_file_name); +return bpf__prepare_load (bpf_file_name, source); } static int
tools/perf/util/parse-events.h +1 -1
@@ -115,7 +115,7 @@ int parse_events_name(struct list_head *list, char *name);int parse_events_add_tracepoint (struct list_head *list,int *idx,char *sys,char *event);int parse_events_load_bpf (struct list_head *list,int *idx, -char *bpf_file_name); +char *bpf_file_name,bool source); int parse_events_add_numeric(struct parse_events_evlist *data, struct list_head *list, u32 type, u64 config,
tools/perf/util/parse-events.l +3 -0
@@ -116,6 +116,7 @@ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ bpf_object .*\.(o|bpf) +bpf_source .*\.c num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+
@@ -161,6 +162,7 @@ modifier_bp [rwx]{1,3} {event_pmu} | {bpf_object} | +{bpf_source} | {event} { BEGIN(INITIAL); REWIND(1);
@@ -265,6 +267,7 @@ r{num_raw_hex} { return raw(yyscanner); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {name} { return pmu_str_check(yyscanner); } {bpf_object} { return str(yyscanner, PE_BPF_OBJECT); } +{bpf_source} { return str(yyscanner, PE_BPF_SOURCE); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; }
tools/perf/util/parse-events.y +13 -2
@@ -42,7 +42,7 @@ static inc_group_count(struct list_head *list, %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM %token PE_EVENT_NAME %token PE_NAME -%token PE_BPF_OBJECT +%token PE_BPF_OBJECT PE_BPF_SOURCE %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
@@ -55,6 +55,7 @@ static inc_group_count(struct list_head *list, %type <num> PE_TERM %type <str> PE_NAME %type <str> PE_BPF_OBJECT +%type <str> PE_BPF_SOURCE %type <str> PE_NAME_CACHE_TYPE %type <str> PE_NAME_CACHE_OP_RESULT %type <str> PE_MODIFIER_EVENT
@@ -431,7 +432,17 @@ PE_BPF_OBJECT struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(list, &data->idx, $1)); + ABORT_ON(parse_events_load_bpf(list, &data->idx, $1, false)); + $$ = list; +} +| +PE_BPF_SOURCE +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_load_bpf(list, &data->idx, $1, true)); $$ = list; }
Signature · 1 line
1.8.3.4
RFC PATCH v8 30/49 perf tools: Parse probe points of eBPF programs during preparation
In reply to Wang NanThis patch parses section name of each program, and creates corresponding 'struct perf_probe_event' structure.
parse_perf_probe_command() is used to do the main parsing works. Parsing result is stored into a global array. This is because add_perf_probe_events() is non-reentrantable. In following patch, add_perf_probe_events will be introduced to insert kprobes. It accepts an array of 'struct perf_probe_event' and do all works in one call.
Define PERF_BPF_PROBE_GROUP as "perf_bpf_probe", which will be used as group name of all eBPF probing points.
This patch utilizes bpf_program__set_private(), bind perf_probe_event with bpf program by private field.
--- tools/perf/util/bpf-loader.c | 124 ++++++++++++++++++++++++++++++++++++++++++- tools/perf/util/bpf-loader.h | 2 + 2 files changed, 124 insertions(+), 2 deletions(-)
tools/perf/util/bpf-loader.c +122 -2
@@ -10,6 +10,8 @@#include "debug.h" #include "bpf-loader.h" #include "llvm-utils.h" +#include "probe-event.h" +#include "probe-finder.h" #define DEFINE_PRINT_FN (name, level) \ static int libbpf_##name(const char *fmt, ...) \
@@ -29,9 +31,120 @@ DEFINE_PRINT_FN(debug, 1)static bool libbpf_initialized = false; +static struct perf_probe_event probe_event_array[MAX_PROBES ]; +static size_t nr_probe_events; + +static struct perf_probe_event * +alloc_perf_probe_event (void ) +{ +struct perf_probe_event *pev; +int n = nr_probe_events; +if (n >=MAX_PROBES ) { +pr_err ("bpf: too many events, increase MAX_PROBES\n" ); +return NULL ; + } + + nr_probe_events = n +1 ; + pev = &probe_event_array[n]; +bzero (pev,sizeof (*pev)); +return pev; +} + +struct bpf_prog_priv { +struct perf_probe_event *pev; +}; + +static void +bpf_prog_priv__clear (struct bpf_program *prog__maybe_unused , +void *_priv) +{ +struct bpf_prog_priv *priv = _priv; +if (priv->pev) +clear_perf_probe_event (priv->pev); +free (priv); +} + +static int +config_bpf_program (struct bpf_program *prog) +{ +struct perf_probe_event *pev =alloc_perf_probe_event (); +struct bpf_prog_priv *priv =NULL ; +const char *config_str; +int err; + +/* pr_err has been done by alloc_perf_probe_event */ +if (!pev) +return -ENOMEM ; + + err =bpf_program__get_title (prog, &config_str, false); +if (err || !config_str) { +pr_err ("bpf: unable to get title for program\n" ); +return -EINVAL ; + } + +pr_debug ("bpf: config program '%s'\n" , config_str); + err =parse_perf_probe_command (config_str, pev); +if (err <0 ) { +pr_err ("bpf: '%s' is not a valid config string\n" , + config_str); +/* parse failed, don't need clear pev. */ +return -EINVAL ; + } + +if (pev->group &&strcmp (pev->group,PERF_BPF_PROBE_GROUP )) { +pr_err ("bpf: '%s': group for event is set and not '%s'.\n" , + config_str,PERF_BPF_PROBE_GROUP ); + err = -EINVAL ; + goto errout; + }else if (!pev->group) + pev->group =strdup (PERF_BPF_PROBE_GROUP ); + +if (!pev->group) { +pr_err ("bpf: strdup failed\n" ); + err = -ENOMEM ; + goto errout; + } + +if (!pev->event) { +pr_err ("bpf: '%s': event name is missing\n" , + config_str); + err = -EINVAL ; + goto errout; + } + +pr_debug ("bpf: config '%s' is ok\n" , config_str); + + priv =calloc (1 ,sizeof (*priv)); +if (!priv) { +pr_err ("bpf: failed to alloc memory\n" ); + err = -ENOMEM ; + goto errout; + } + + priv->pev = pev; + + err =bpf_program__set_private (prog, priv, + bpf_prog_priv__clear); +if (err) { +pr_err ("bpf: set program private failed\n" ); + err = -ENOMEM ; + goto errout; + } +return 0 ; + +errout: +if (pev) +clear_perf_probe_event (pev); +if (priv) +free (priv); +return err; +} +int bpf__prepare_load (const char *filename,bool source) {struct bpf_object *obj; +struct bpf_program *prog; +int err =0 ;if (!libbpf_initialized) libbpf_set_print(libbpf_warning,
@@ -41,7 +154,6 @@ int bpf__prepare_load(const char *filename, bool source)if (source) {void *obj_buf;size_t obj_buf_sz; -int err; err =llvm__compile_bpf (filename, &obj_buf, &obj_buf_sz);if (err)
@@ -56,12 +168,20 @@ int bpf__prepare_load(const char *filename, bool source)return -EINVAL ; } +bpf_object__for_each_program (prog, obj) { + err =config_bpf_program (prog); +if (err) + goto errout; + } +/* * Throw object pointer away: it will be retrived using * bpf_objects iterater. */ -return 0 ; +errout: +bpf_object__close (obj); +return err; }void bpf__clear (void )
tools/perf/util/bpf-loader.h +2 -0
@@ -8,6 +8,8 @@#include <linux/compiler.h> #include "debug.h" +#define PERF_BPF_PROBE_GROUP "perf_bpf_probe" +#ifdef HAVE_LIBBPF_SUPPORT int bpf__prepare_load (const char *filename,bool source);
Signature · 1 line
1.8.3.4
RFC PATCH v8 31/49 perf probe: Attach trace_probe_event with perf_probe_event
In reply to Wang NanThis patch drops struct __event_package structure. Instead, it adds trace_probe_event into 'struct perf_probe_event'.
trace_probe_event information give further patches a chance to access actual probe points and actual arguments. Using them, bpf_loader will be able to attach one bpf program to different probing points of a inline functions (which has multiple probing points) and glob functions. Moreover, by reading arguments information, bpf code for reading those arguments can be generated.
--- tools/perf/builtin-probe.c | 2 +- tools/perf/util/probe-event.c | 59 +++++++++++++++++++++---------------------- tools/perf/util/probe-event.h | 5 +++- 3 files changed, 34 insertions(+), 32 deletions(-)
tools/perf/builtin-probe.c +1 -1
@@ -497,7 +497,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)usage_with_options (probe_usage, options); } - ret =add_perf_probe_events (params.events, params.nevents); + ret =add_perf_probe_events (params.events, params.nevents, true);if (ret <0 ) {pr_err_with_code (" Error: Failed to add events." , ret);return ret;
tools/perf/util/probe-event.c +29 -30
96 lines not on this page · raw message
tools/perf/util/probe-event.h +4 -1
@@ -86,6 +86,8 @@ struct perf_probe_event {bool uprobes;/* Uprobe event flag */ char *target;/* Target binary */ struct perf_probe_arg *args;/* Arguments */ +struct probe_trace_event *tevs; +int ntevs; };/* Line range */
@@ -131,8 +133,9 @@ extern void line_range__clear(struct line_range *lr);/* Initialize line range */ extern int line_range__init (struct line_range *lr); -extern int add_perf_probe_events (struct perf_probe_event *pevs,int npevs); +extern int add_perf_probe_events (struct perf_probe_event *pevs,int npevs,bool cleanup);extern int del_perf_probe_events (struct strfilter *filter); +extern int cleanup_perf_probe_event (struct perf_probe_event *pev);extern int show_perf_probe_events (struct strfilter *filter);extern int show_line_range (struct line_range *lr,const char *module,bool user);
Signature · 1 line
1.8.3.4
RFC PATCH v8 32/49 perf record: Probe at kprobe points
In reply to Wang NanIn this patch, kprobe points are created using add_perf_probe_events. Since all events are already grouped together in an array, calling add_perf_probe_events() once creates all of them.
probe_conf.max_probes is set to MAX_PROBES to support glob matching.
--- tools/perf/builtin-record.c | 18 ++++++++++++++++- tools/perf/util/bpf-loader.c | 48 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/bpf-loader.h | 4 ++++ 3 files changed, 69 insertions(+), 1 deletion(-)
tools/perf/builtin-record.c +17 -1
@@ -29,6 +29,7 @@#include "util/data.h" #include "util/auxtrace.h" #include "util/parse-branch-options.h" +#include "util/bpf-loader.h" #include <unistd.h> #include <sched.h>
@@ -1109,7 +1110,21 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)if (err)return err; - err = -ENOMEM ; +/* +* bpf__probe must be called before symbol__init() because we +* need init_symbol_maps. If called after symbol__init, +* symbol_conf.sort_by_name won't take effect. +* +* bpf__unprobe() is safe even if bpf__probe() failed, and it +* also calls symbol__init. Therefore, goto out_symbol_exit +* is safe when probe failed. +*/ + err =bpf__probe (); +if (err) { +pr_err ("Probing at events in BPF object failed.\n" ); +pr_err ("Try perf probe -d '*' to remove existing probe events.\n" ); + goto out_symbol_exit; + }symbol__init (NULL );
@@ -1170,6 +1185,7 @@ out_symbol_exit:perf_evlist__delete (rec->evlist);symbol__exit ();auxtrace_record__free (rec->itr); +bpf__unprobe ();return err; }
tools/perf/util/bpf-loader.c +48 -0
51 lines not on this page · raw message
tools/perf/util/bpf-loader.h +4 -0
@@ -12,6 +12,8 @@#ifdef HAVE_LIBBPF_SUPPORT int bpf__prepare_load (const char *filename,bool source); +int bpf__probe (void ); +int bpf__unprobe (void );void bpf__clear (void );#else
@@ -22,6 +24,8 @@ static inline int bpf__prepare_load(const char *filename __maybe_unused,return -1 ; } +static inline int bpf__probe (void ) {return 0 ; } +static inline int bpf__unprobe (void ) {return 0 ; }static inline void bpf__clear (void ) { }#endif #endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 33/49 perf record: Load all eBPF object into kernel
In reply to Wang NanThis patch utilizes bpf_load_object() provided by libbpf to load all objects into kernel.
--- tools/perf/builtin-record.c | 12 ++++++++++++ tools/perf/util/bpf-loader.c | 19 +++++++++++++++++++ tools/perf/util/bpf-loader.h | 2 ++ 3 files changed, 33 insertions(+)
tools/perf/builtin-record.c +12 -0
@@ -1126,6 +1126,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) goto out_symbol_exit; } +/* +* bpf__probe() also calls symbol__init() if there are probe +* events in bpf objects, so calling symbol_exit when failuer +* is safe. If there is no probe event, bpf__load() always +* success. +*/ + err =bpf__load (); +if (err) { +pr_err ("Loading BPF programs failed\n" ); + goto out_symbol_exit; + } +symbol__init (NULL );if (symbol_conf.kptr_restrict)
tools/perf/util/bpf-loader.c +19 -0
@@ -239,3 +239,22 @@ int bpf__probe(void)return err <0 ? err :0 ; } + +int bpf__load (void ) +{ +struct bpf_object *obj, *tmp; +int err =0 ; + +bpf_object__for_each (obj, tmp) { + err =bpf_object__load (obj); +if (err) { +pr_err ("bpf: load objects failed\n" ); + goto errout; + } + } +return 0 ; +errout: +bpf_object__for_each (obj, tmp) +bpf_object__unload (obj); +return err; +}
tools/perf/util/bpf-loader.h +2 -0
@@ -14,6 +14,7 @@int bpf__prepare_load (const char *filename,bool source);int bpf__probe (void );int bpf__unprobe (void ); +int bpf__load (void );void bpf__clear (void );#else
@@ -26,6 +27,7 @@ static inline int bpf__prepare_load(const char *filename __maybe_unused,static inline int bpf__probe (void ) {return 0 ; }static inline int bpf__unprobe (void ) {return 0 ; } +static inline int bpf__load (void ) {return 0 ; }static inline void bpf__clear (void ) { }#endif #endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 34/49 perf tools: Add bpf_fd field to evsel and config it
In reply to Wang NanThis patch adds a bpf_fd field to 'struct evsel' then introduces method to config it. In bpf-loader, a bpf__for_each_program() function is added. Which calls the callback function for each eBPF programs with their event structure and file descriptors. In evlist.c, perf_evlist__add_bpf() is added to add all bpf events into evlist. The event names are found from probe_trace_event structure. 'perf record' calls perf_evlist__add_bpf().
Since bpf-loader.c will not be built if libbpf is turned off, an empty bpf__for_each_program() is defined in bpf-loader.h to avoid compiling error.
--- tools/perf/builtin-record.c | 6 ++++++ tools/perf/util/bpf-loader.c | 36 +++++++++++++++++++++++++++++++ tools/perf/util/bpf-loader.h | 13 +++++++++++ tools/perf/util/evlist.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 1 + tools/perf/util/evsel.c | 1 + tools/perf/util/evsel.h | 1 + 7 files changed, 109 insertions(+)
tools/perf/builtin-record.c +6 -0
@@ -1138,6 +1138,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) goto out_symbol_exit; } + err =perf_evlist__add_bpf (rec->evlist); +if (err <0 ) { +pr_err ("Failed to add events from BPF object(s)\n" ); + goto out_symbol_exit; + } +symbol__init (NULL );if (symbol_conf.kptr_restrict)
tools/perf/util/bpf-loader.c +36 -0
@@ -258,3 +258,39 @@ errout:bpf_object__unload (obj);return err; } + +int +bpf__for_each_program (bpf_prog_iter_callback_t func, +void *arg) +{ +struct bpf_object *obj, *tmp; +struct bpf_program *prog; +int err; + +bpf_object__for_each (obj, tmp) { +bpf_object__for_each_program (prog, obj) { +struct bpf_prog_priv *priv; +int fd; + + err =bpf_program__get_private (prog, + (void **)&priv); +if (err || !priv) { +pr_err ("bpf: failed to get private field\n" ); +return -EINVAL ; + } + err =bpf_program__get_fd (prog, &fd); +if (err || fd <0 ) { +pr_err ("bpf: failed to get file descriptor\n" ); +return -EINVAL ; + } + + err =func (priv->pev, fd, arg); +if (err) { +pr_err ("bpf: call back failed, stop iterate\n" ); +return err; + } + } + } + +return 0 ; +}
tools/perf/util/bpf-loader.h +13 -0
@@ -6,10 +6,14 @@#define __BPF_LOADER_H#include <linux/compiler.h> +#include "probe-event.h" #include "debug.h" #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" +typedef int (*bpf_prog_iter_callback_t )(struct perf_probe_event *pev, +int fd,void *arg); +#ifdef HAVE_LIBBPF_SUPPORT int bpf__prepare_load (const char *filename,bool source);int bpf__probe (void );
@@ -17,6 +21,8 @@ int bpf__unprobe(void);int bpf__load (void );void bpf__clear (void ); + +int bpf__for_each_program (bpf_prog_iter_callback_t func,void *arg);#else static inline int bpf__prepare_load (const char *filename__maybe_unused ,bool source__maybe_unused )
@@ -29,5 +35,12 @@ static inline int bpf__probe(void) { return 0; }static inline int bpf__unprobe (void ) {return 0 ; }static inline int bpf__load (void ) {return 0 ; }static inline void bpf__clear (void ) { } + +static inline int +bpf__for_each_program (bpf_prog_iter_callback_t func__maybe_unused , +void *arg__maybe_unused ) +{ +return 0 ; +}#endif #endif
tools/perf/util/evlist.c +51 -0
63 lines not on this page · raw message
tools/perf/util/evlist.h +1 -0
@@ -72,6 +72,7 @@ void perf_evlist__delete(struct perf_evlist *evlist);void perf_evlist__add (struct perf_evlist *evlist,struct perf_evsel *entry);int perf_evlist__add_default (struct perf_evlist *evlist); +int perf_evlist__add_bpf (struct perf_evlist *evlist);int __perf_evlist__add_default_attrs (struct perf_evlist *evlist,struct perf_event_attr *attrs,size_t nr_attrs);
tools/perf/util/evsel.c +1 -0
@@ -206,6 +206,7 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->leader = evsel; evsel->unit ="" ; evsel->scale =1.0 ; + evsel->bpf_fd =-1 ;INIT_LIST_HEAD (&evsel->node); perf_evsel__object.init (evsel); evsel->sample_size =__perf_evsel__sample_size (attr->sample_type);
tools/perf/util/evsel.h +1 -0
@@ -100,6 +100,7 @@ struct perf_evsel {unsigned long *per_pkg_mask;struct perf_evsel *leader;char *group_name; +int bpf_fd; };union u64_swap {
Signature · 1 line
1.8.3.4
RFC PATCH v8 35/49 perf tools: Attach eBPF program to perf event
In reply to Wang NanIn this patch PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd.
It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error.
--- tools/perf/util/evsel.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
tools/perf/util/evsel.c +16 -0
@@ -1185,6 +1185,22 @@ retry_open: err); goto try_fallback; } + +if (evsel->bpf_fd >=0 ) { +int evt_fd =FD (evsel, cpu, thread); +int bpf_fd = evsel->bpf_fd; + + err =ioctl (evt_fd, +PERF_EVENT_IOC_SET_BPF , + bpf_fd); +if (err && errno !=EEXIST ) { +pr_err ("failed to attach bpf fd %d: %s\n" , + bpf_fd,strerror (errno)); + err = -EINVAL ; + goto out_close; + } + } + set_rlimit =NO_CHANGE ;/*
Signature · 1 line
1.8.3.4
RFC PATCH v8 36/49 perf tools: Suppress probing messages when probing by BPF loading
In reply to Wang NanThis patch suppress message output by add_perf_probe_events() and del_perf_probe_events() if they are triggered by BPF loading. Before this patch, when using 'perf record' with BPF object/source as event selector, following message will be output:
Added new event:
perf_bpf_probe:lock_page_ret (on __lock_page%return)
You can now use it in all perf tools, such as:
perf record -e perf_bpf_probe:lock_page_ret -aR sleep 1
...
Removed event: perf_bpf_probe:lock_page_ret
Which is misleading, especially 'use it in all perf tools' because they will be removed after 'pref record' exit.
In this patch, a 'silent' field is appended into probe_conf to control output. bpf__{,un}probe() set it to true when calling {add,del}_perf_probe_events().
--- tools/perf/util/bpf-loader.c | 6 ++++++ tools/perf/util/probe-event.c | 22 ++++++++++++++++------ tools/perf/util/probe-event.h | 1 + 3 files changed, 23 insertions(+), 6 deletions(-)
tools/perf/util/bpf-loader.c +6 -0
@@ -197,6 +197,7 @@ static bool is_probing = false;int bpf__unprobe (void ) {struct strfilter *delfilter; +bool old_silent = probe_conf.silent;int ret;if (!is_probing)
@@ -208,7 +209,9 @@ int bpf__unprobe(void)return -ENOMEM ; } + probe_conf.silent = true; ret =del_perf_probe_events (delfilter); + probe_conf.silent = old_silent;strfilter__delete (delfilter);if (ret <0 && is_probing) pr_err("Error: failed to delete events: %s\n",
@@ -221,15 +224,18 @@ int bpf__unprobe(void)int bpf__probe (void ) {int err; +bool old_silent = probe_conf.silent;if (nr_probe_events <=0 )return 0 ; + probe_conf.silent = true; probe_conf.max_probes =MAX_PROBES ;/* Let add_perf_probe_events keeps probe_trace_event */ err =add_perf_probe_events (probe_event_array, nr_probe_events, false); + probe_conf.silent = old_silent;/* add_perf_probe_events return negative when fail */ if (err <0 )
tools/perf/util/probe-event.c +16 -6
@@ -51,7 +51,9 @@#define PERFPROBE_GROUP "probe"bool probe_event_dry_run;/* Dry run flag */ -struct probe_conf probe_conf; +struct probe_conf probe_conf = { + .silent = false, +}; #define semantic_error(msg ...) pr_err("Semantic error :" msg)
@@ -2246,10 +2248,12 @@ static int show_perf_probe_event(const char *group, const char *event, ret =perf_probe_event__sprintf (group, event, pev, module, &buf);if (ret >=0 ) { -if (use_stdout) +if (use_stdout && !probe_conf.silent)printf ("%s\n" , buf.buf); -else +else if (!probe_conf.silent)pr_info ("%s\n" , buf.buf); +else +pr_debug ("%s\n" , buf.buf); }strbuf_release (&buf);
@@ -2508,7 +2512,10 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, safename = (pev->point.function && !strisglob (pev->point.function)); ret =0 ; -pr_info ("Added new event%s\n" , (ntevs >1 ) ?"s:" :":" ); +if (!probe_conf.silent) +pr_info ("Added new event%s\n" , (ntevs >1 ) ?"s:" :":" ); +else +pr_debug ("Added new event%s\n" , (ntevs >1 ) ?"s:" :":" );for (i =0 ; i < ntevs; i++) { tev = &tevs[i];/* Skip if the symbol is out of .text or blacklisted */
@@ -2565,7 +2572,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,warn_uprobe_event_compat (tev);/* Note that it is possible to skip all events because of blacklist */ -if (ret >=0 && event) { +if (ret >=0 && event && !probe_conf.silent) {/* Show how to use the event. */ pr_info ("\nYou can now use it in all perf tools, such as:\n\n" );pr_info ("\tperf record -e %s:%s -aR sleep 1\n\n" , group, event);
@@ -2860,7 +2867,10 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) goto error; } -pr_info ("Removed event: %s\n" , ent->s); +if (!probe_conf.silent) +pr_info ("Removed event: %s\n" , ent->s); +else +pr_debug ("Removed event: %s\n" , ent->s);return 0 ; error: pr_warning("Failed to delete event: %s\n",
tools/perf/util/probe-event.h +1 -0
@@ -13,6 +13,7 @@ struct probe_conf {bool force_add;bool no_inlines;int max_probes; +bool silent; };extern struct probe_conf probe_conf;extern bool probe_event_dry_run;
Signature · 1 line
1.8.3.4
RFC PATCH v8 37/49 perf record: Add clang options for compiling BPF scripts
In reply to Wang NanAlthough previous patch allows setting BPF compiler related options in perfconfig, on some ad-hoc situation it still requires passing options through cmdline. This patch introduces 2 options to 'perf record' for this propose: --clang-path and --clang-opt.
--- tools/perf/builtin-record.c | 7 +++++++ 1 file changed, 7 insertions(+)
tools/perf/builtin-record.c +7 -0
@@ -30,6 +30,7 @@#include "util/auxtrace.h" #include "util/parse-branch-options.h" #include "util/bpf-loader.h" +#include "util/llvm-utils.h" #include <unistd.h> #include <sched.h>
@@ -1071,6 +1072,12 @@ struct option __record_options[] = { "opts", "AUX area tracing Snapshot Mode", ""), OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), +#ifdef HAVE_LIBBPF_SUPPORT +OPT_STRING (0 ,"clang-path" , &llvm_param.clang_path,"clang path" , +"clang binary to use for compiling BPF scriptlets" ), +OPT_STRING (0 ,"clang-opt" , &llvm_param.clang_opt,"clang options" , +"options passed to clang when compiling BPF scriptlets" ), +#endifOPT_END () };
Signature · 1 line
1.8.3.4
RFC PATCH v8 38/49 bpf tools: Load instructions buffer using load_program()
In reply to Wang NanExtract code for loading a 'struct bpf_insn' array into kernel to load_program() and makes bpf_program__load() to call it. Now we have function loads instructions into kernel. It will be used by further patches, which creates different instances from a program and load them into kernel.
--- tools/lib/bpf/libbpf.c | 51 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 20 deletions(-)
tools/lib/bpf/libbpf.c +31 -20
@@ -745,48 +745,59 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) }static int -bpf_program__load (struct bpf_program *prog, -char *license,u32 kern_version) +load_program (struct bpf_insn *insns,int insns_cnt, +char *license,u32 kern_version,int *pfd) { -int fd, err; +int ret;char *log_buf; -if (!prog->insns || !prog->insns_cnt) +if (!insns || !insns_cnt)return -EINVAL ; log_buf =malloc (BPF_LOG_BUF_SIZE );if (!log_buf)pr_warning ("Alloc log buffer for bpf loader error, continue without log\n" ); - fd =bpf_load_program (BPF_PROG_TYPE_KPROBE , prog->insns, - prog->insns_cnt, license, - kern_version, log_buf, -BPF_LOG_BUF_SIZE ); + ret =bpf_load_program (BPF_PROG_TYPE_KPROBE , insns, + insns_cnt, license, kern_version, + log_buf,BPF_LOG_BUF_SIZE ); -if (fd >=0 ) { - prog->fd = fd; -pr_debug ("load bpf program '%s': fd = %d\n" , - prog->section_name, prog->fd); - err =0 ; +if (ret >=0 ) { + *pfd = ret; + ret =0 ; goto out; } - err = -EINVAL ; -pr_warning ("load bpf program '%s' failed: %s\n" , - prog->section_name,strerror (errno)); + ret = -EINVAL ; +pr_warning ("load bpf program failed: %s\n" ,strerror (errno));if (log_buf) { -pr_warning ("bpf: load: failed to load program '%s':\n" , - prog->section_name);pr_warning ("-- BEGIN DUMP LOG ---\n" ); -pr_warning ("%s\n" , log_buf); +pr_warning ("\n%s\n" , log_buf);pr_warning ("-- END LOG --\n" ); } out: +free (log_buf); +return ret; +} + +static int +bpf_program__load (struct bpf_program *prog, +char *license,u32 kern_version) +{ +int err, fd; + + err =load_program (prog->insns, prog->insns_cnt, + license, kern_version, &fd); +if (!err) + prog->fd = fd; + +if (err) +pr_warning ("failed to load program '%s'\n" , + prog->section_name);zfree (&prog->insns); prog->insns_cnt =0 ; -free (log_buf);return err; }
Signature · 1 line
1.8.3.4
Re: [RFC PATCH v8 38/49] bpf tools: Load instructions buffer using load_program()
Quoted 7 lines · Wang Nan
Extract code for loading a 'struct
bpf_insn' array into kernel toload_program()and makesbpf_program__load()to call it. Now we have function loads instructions into kernel. It will be used by further patches, which creates different instances from a program and load them into kernel.Signed-off-by Wang Nan<[email protected]>
I think it's cleaner to squash this patch with earlier libbpf patches. Looks good otherwise.
Re: [RFC PATCH v8 38/49] bpf tools: Load instructions buffer using load_program()
Quoted 11 lines · Alexei Starovoitov
Quoted 7 lines · Wang Nan
Extract code for loading a 'struct
bpf_insn' array into kernel toload_program()and makesbpf_program__load()to call it. Now we have function loads instructions into kernel. It will be used by further patches, which creates different instances from a program and load them into kernel.Signed-off-by Wang Nan<[email protected]>I think it's cleaner to squash this patch with earlier libbpf patches. Looks good otherwise.
I thought you may don't want to enlarge this patchset, so I separated the newly introduced patches from the original ones, then you can skip reading the first 37 patches. But if you wish, I'll squash them together.
Thank you.
RFC PATCH v8 39/49 bpf tools: Load a program with different instance using preprocessor
In reply to Wang NanIn this patch, caller of libbpf is able to control the loaded programs by installing a preprocessor callback for a BPF program. With preprocessor, different instances can be created from one BPF program.
This patch will be used by perf to generate different prologue for different 'struct probe_trace_event' instances matched by one 'struct perf_probe_event'.
bpf_program__set_prep() is added to support this function. Caller should pass libbpf the number of instance should be created and a preprocessor function which will be called when doing real loading. The callback should return instructions arrays for each instances.
nr_instance and instance_fds are appended into bpf_programs to support multiple instances. bpf_program__get_nth_fd() is introduced for read fd of instances. Old interface bpf_program__get_fd() won't work for program which has preprocessor hooked.
--- tools/lib/bpf/libbpf.c | 135 +++++++++++++++++++++++++++++++++++++++++++++++-- tools/lib/bpf/libbpf.h | 22 ++++++++ 2 files changed, 152 insertions(+), 5 deletions(-)
tools/lib/bpf/libbpf.c +130 -5
@@ -100,6 +100,10 @@ struct bpf_program {int fd; +int nr_instance; +int *instance_fds; +bpf_program_prep_t preprocessor; +struct bpf_object *obj;void *priv;bpf_program_clear_priv_t clear_priv;
@@ -156,6 +160,19 @@ static void bpf_program__unload(struct bpf_program *prog)return ;zclose (prog->fd); + +if (prog->preprocessor) { +int i; + +if (prog->nr_instance <=0 ) +pr_warning ("Internal error when unloading: instance is %d\n" , + prog->nr_instance); +else +for (i =0 ; i < prog->nr_instance; i++) +zclose (prog->instance_fds[i]); + prog->nr_instance =-1 ; +zfree (&prog->instance_fds); + } }static void bpf_program__clear (struct bpf_program *prog)
@@ -231,6 +248,8 @@ bpf_program__new(struct bpf_object *obj, void *data, size_t size, prog->idx = idx; prog->fd =-1 ; prog->obj = obj; + prog->nr_instance =-1 ; + prog->instance_fds =NULL ;return prog; out:
@@ -786,13 +805,57 @@ static int bpf_program__load(struct bpf_program *prog, char *license, u32 kern_version) { - int err, fd; + int err = 0, fd, i; + +if (!prog->preprocessor) { + err =load_program (prog->insns, prog->insns_cnt, + license, kern_version, &fd); +if (!err) + prog->fd = fd; + goto out; + } + +if (prog->nr_instance <=0 || !prog->instance_fds) { +pr_warning ("Internal error when loading '%s'\n" , + prog->section_name); +return -EINVAL ; + } + +for (i =0 ; i < prog->nr_instance; i++) { +struct bpf_prog_prep_result result; +bpf_program_prep_t preprocessor = prog->preprocessor; + +bzero (&result,sizeof (result)); + err =preprocessor (prog, i, prog->insns, + prog->insns_cnt, &result); +if (err) { +pr_warning ("Preprocessing %dth instance of program '%s' failed\n" , + i, prog->section_name); + goto out; + } + +if (!result.new_insn_ptr || !result.new_insn_cnt) { +pr_debug ("Skip loading %dth instance of program '%s'\n" , + i, prog->section_name); + prog->instance_fds[i] =-1 ; +continue ; + } + + err =load_program (result.new_insn_ptr, + result.new_insn_cnt, + license, kern_version, &fd); - err =load_program (prog->insns, prog->insns_cnt, - license, kern_version, &fd); -if (!err) - prog->fd = fd; +if (err) { +pr_warning ("Loading %dth instance of program '%s' failed\n" , + i, prog->section_name); + goto out; + } +if (result.pfd) + *result.pfd = fd; + prog->instance_fds[i] = fd; + } +out:if (err)pr_warning ("failed to load program '%s'\n" , prog->section_name);
@@ -1043,6 +1106,68 @@ int bpf_program__get_fd(struct bpf_program *prog, int *pfd)if (!pfd)return -EINVAL ; +if (prog->preprocessor) { +pr_warning ("Invalid using bpf_program__get_fd() on program %s\n" , + prog->section_name); +return -EINVAL ; + } + *pfd = prog->fd;return 0 ; } + +int bpf_program__set_prep (struct bpf_program *prog,int nr_instance, +bpf_program_prep_t prep) +{ +int *instance_fds; + +if (nr_instance <=0 || !prep) +return -EINVAL ; + + instance_fds =malloc (sizeof (int ) * nr_instance); +if (!instance_fds) { +pr_warning ("alloc memory failed for instance of fds\n" ); +return -ENOMEM ; + } + +/* fill all fd with -1 */ +memset (instance_fds,0xff ,sizeof (int ) * nr_instance); + + prog->nr_instance = nr_instance; + prog->instance_fds = instance_fds; + prog->preprocessor = prep; +return 0 ; +} + +int bpf_program__get_nth_fd (struct bpf_program *prog,int n,int *pfd) +{ +int fd; + +if (!pfd) +return -EINVAL ; + +if (!prog->preprocessor || + prog->nr_instance <=0 || + !prog->instance_fds) { + +pr_warning ("Invalid using bpf_program__get_nth_fd() on program %s\n" , + prog->section_name); +return -EINVAL ; + } + +if (n >= prog->nr_instance || n <0 ) { +pr_warning ("Can't get the %dth fd from program %s: only %d instances\n" , + n, prog->section_name, prog->nr_instance); +return -EINVAL ; + } + + fd = prog->instance_fds[n]; +if (fd <0 ) { +pr_warning ("%dth instance of program '%s' is invalid\n" , + n, prog->section_name); +return -EEXIST ; + } + + *pfd = fd; +return 0 ; +}
tools/lib/bpf/libbpf.h +22 -0
@@ -69,6 +69,28 @@ int bpf_program__get_title(struct bpf_program *prog,int bpf_program__get_fd (struct bpf_program *prog,int *pfd); +struct bpf_insn ; +struct bpf_prog_prep_result { +/* +* If not NULL, load new instruction array. +* If set to NULL, don't load this instance. +*/ +struct bpf_insn *new_insn_ptr; +int new_insn_cnt; + +/* If not NULL, result fd is set to it */ +int *pfd; +}; + +typedef int (*bpf_program_prep_t )(struct bpf_program *,int n, +struct bpf_insn *,int insn_cnt, +struct bpf_prog_prep_result *res); + +int bpf_program__set_prep (struct bpf_program *prog,int nr_instance, +bpf_program_prep_t prep); + +int bpf_program__get_nth_fd (struct bpf_program *prog,int n,int *pfd); +/* * We don't need __attribute__((packed)) now since it is * unnecessary for 'bpf_map_def' because they are all aligned.
Signature · 1 line
1.8.3.4
RFC PATCH v8 40/49 perf tools: Fix probe-event.h include
In reply to Wang NanCommit 7b6ff0bdbf4f7f429c2116cca92a6d171217449e ("perf probe ppc64le:
Fixup function entry if using kallsyms lookup") adds 'struct map' into probe-event.h but not include "util/map.h" in it. This patch fixes it.
--- tools/perf/util/probe-event.h | 1 + 1 file changed, 1 insertion(+)
tools/perf/util/probe-event.h +1 -0
@@ -5,6 +5,7 @@#include "intlist.h" #include "strlist.h" #include "strfilter.h" +#include "map.h" /* Probe related configurations */ struct probe_conf {
Signature · 1 line
1.8.3.4
RFC PATCH v8 41/49 perf probe: Reset tev->args and tev->nargs when failure
In reply to Wang NanWhen failure occures in add_probe_trace_event(), tev->args is incomplete. Since information in tev may be used in further, this patch frees the allocated memory and set it to NULL to avoid dangling pointer.
--- tools/perf/util/probe-finder.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/util/probe-finder.c +4 -0
@@ -1243,6 +1243,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) end:free (args); +if (ret) { + tev->nargs =0 ; +zfree (&tev->args); + }return ret; }
Signature · 1 line
1.8.3.4
RFC PATCH v8 42/49 perf tools: Move linux/filter.h to tools/include
In reply to Wang NanFrom: He Kuang <[email protected]>
This patch moves filter.h from include/linux/kernel.h to tools/include/linux/filter.h to enable other libraries use macros in it, like libbpf which will be introduced by further patches. Currenty, the moved filter.h only contains the useful macros needed by libbpf for not introducing too much dependence.
MANIFEST is also updated for 'make perf-*-src-pkg'.
One change:
imm field of BPF_EMIT_CALL becomes ((FUNC) - BPF_FUNC_unspec) to suit user space code generator.
--- tools/include/linux/filter.h | 237 +++++++++++++++++++++++++++++++++++++++++++ tools/perf/MANIFEST | 1 + 2 files changed, 238 insertions(+) create mode 100644 tools/include/linux/filter.h
tools/include/linux/filter.h new file +237 -0
@@ -0,0 +1,237 @@ +/* +* Linux Socket Filter Data Structures +*/ +#ifndef __TOOLS_LINUX_FILTER_H +#define __TOOLS_LINUX_FILTER_H + +#include <linux/bpf.h> + +/* ArgX, context and stack frame pointer register positions. Note, +* Arg1, Arg2, Arg3, etc are used as argument mappings of function +* calls in BPF_CALL instruction. +*/ +#define BPF_REG_ARG1 BPF_REG_1 +#define BPF_REG_ARG2 BPF_REG_2 +#define BPF_REG_ARG3 BPF_REG_3 +#define BPF_REG_ARG4 BPF_REG_4 +#define BPF_REG_ARG5 BPF_REG_5 +#define BPF_REG_CTX BPF_REG_6 +#define BPF_REG_FP BPF_REG_10 + +/* Additional register mappings for converted user programs. */ +#define BPF_REG_A BPF_REG_0 +#define BPF_REG_X BPF_REG_7 +#define BPF_REG_TMP BPF_REG_8 + +/* BPF program can access up to 512 bytes of stack space. */ +#define MAX_BPF_STACK 512 + +/* Helper macros for filter block array initializers. */ + +/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ + +#define BPF_ALU64_REG (OP ,DST ,SRC ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_ALU32_REG (OP ,DST ,SRC ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ + +#define BPF_ALU64_IMM (OP ,DST ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_ALU32_IMM (OP ,DST ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Endianness conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ + +#define BPF_ENDIAN (TYPE ,DST ,LEN ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = LEN }) + +/* Short form of mov, dst_reg = src_reg */ + +#define BPF_MOV64_REG (DST ,SRC ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_MOV32_REG (DST ,SRC ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* Short form of mov, dst_reg = imm32 */ + +#define BPF_MOV64_IMM (DST ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_IMM (DST ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Short form of mov based on type, +* BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 +*/ + +#define BPF_MOV64_RAW (TYPE ,DST ,SRC ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_RAW (TYPE ,DST ,SRC ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = IMM }) + +/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ + +#define BPF_LD_ABS (SIZE ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ + +#define BPF_LD_IND (SIZE ,SRC ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ + .dst_reg = 0, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = IMM }) + +/* Memory load, dst_reg = *(uint *) (src_reg + off16) */ + +#define BPF_LDX_MEM (SIZE ,DST ,SRC ,OFF ) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Memory store, *(uint *) (dst_reg + off16) = src_reg */ + +#define BPF_STX_MEM (SIZE ,DST ,SRC ,OFF ) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Memory store, *(uint *) (dst_reg + off16) = imm32 */ + +#define BPF_ST_MEM (SIZE ,DST ,OFF ,IMM ) \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Conditional jumps against registers, +* if (dst_reg 'op' src_reg) goto pc + off16 +*/ + +#define BPF_JMP_REG (OP ,DST ,SRC ,OFF ) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Conditional jumps against immediates, +* if (dst_reg 'op' imm32) goto pc + off16 +*/ + +#define BPF_JMP_IMM (OP ,DST ,IMM ,OFF ) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Function call */ + +#define BPF_EMIT_CALL (FUNC ) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = ((FUNC) - BPF_FUNC_unspec) }) + +/* Raw code statement block */ + +#define BPF_RAW_INSN (CODE ,DST ,SRC ,OFF ,IMM ) \ + ((struct bpf_insn) { \ + .code = CODE, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = IMM }) + +/* Program exit */ + +#define BPF_EXIT_INSN () \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_EXIT, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + +#endif /* __TOOLS_LINUX_FILTER_H */
tools/perf/MANIFEST +1 -0
@@ -42,6 +42,7 @@ tools/include/linux/compiler.h tools/include/linux/export.h tools/include/linux/hash.h tools/include/linux/kernel.h +tools/include/linux/filter.h tools/include/linux/list.h tools/include/linux/log2.h tools/include/linux/poison.h
Signature · 1 line
1.8.3.4
RFC PATCH v8 43/49 perf tools: Iterater over tev instead of pev in bpf__for_each_program
In reply to Wang NanThis patch renames bpf__for_each_program() to bpf__for_each_tev() and makes it iterate over 'struct probe_trace_event' instead of 'struct probe_trace_event' during the loop. The callback (add_bpf_event()) now get rid of the iteration.
This is preparation for further patches, which will allow generating multiple instances form one BPF program and install then onto different 'struct probe_trace_event'.
--- tools/perf/util/bpf-loader.c | 31 +++++++++++++++++++------------ tools/perf/util/bpf-loader.h | 8 ++++---- tools/perf/util/evlist.c | 42 ++++++++++++++++-------------------------- 3 files changed, 39 insertions(+), 42 deletions(-)
tools/perf/util/bpf-loader.c +19 -12
@@ -266,8 +266,7 @@ errout: }int -bpf__for_each_program (bpf_prog_iter_callback_t func, -void *arg) +bpf__for_each_tev (bpf_prog_iter_callback_t func,void *arg) {struct bpf_object *obj, *tmp;struct bpf_program *prog;
@@ -275,8 +274,10 @@ bpf__for_each_program(bpf_prog_iter_callback_t func,bpf_object__for_each (obj, tmp) {bpf_object__for_each_program (prog, obj) { +struct probe_trace_event *tev; +struct perf_probe_event *pev;struct bpf_prog_priv *priv; -int fd; +int i, fd; err =bpf_program__get_private (prog, (void **)&priv);
@@ -284,16 +285,22 @@ bpf__for_each_program(bpf_prog_iter_callback_t func,pr_err ("bpf: failed to get private field\n" );return -EINVAL ; } - err =bpf_program__get_fd (prog, &fd); -if (err || fd <0 ) { -pr_err ("bpf: failed to get file descriptor\n" ); -return -EINVAL ; - } - err =func (priv->pev, fd, arg); -if (err) { -pr_err ("bpf: call back failed, stop iterate\n" ); -return err; + pev = priv->pev; +for (i =0 ; i < pev->ntevs; i++) { + tev = &pev->tevs[i]; + + err =bpf_program__get_fd (prog, &fd); + +if (err || fd <0 ) { +pr_err ("bpf: failed to get file descriptor\n" ); +return -EINVAL ; + } + err =func (tev, fd, arg); +if (err) { +pr_err ("bpf: call back failed, stop iterate\n" ); +return err; + } } } }
tools/perf/util/bpf-loader.h +4 -4
@@ -11,7 +11,7 @@#define PERF_BPF_PROBE_GROUP "perf_bpf_probe" -typedef int (*bpf_prog_iter_callback_t )(struct perf_probe_event *pev, +typedef int (*bpf_prog_iter_callback_t )(struct probe_trace_event *tev,int fd,void *arg);#ifdef HAVE_LIBBPF_SUPPORT
@@ -22,7 +22,7 @@ int bpf__load(void);void bpf__clear (void ); -int bpf__for_each_program (bpf_prog_iter_callback_t func,void *arg); +int bpf__for_each_tev (bpf_prog_iter_callback_t func,void *arg);#else static inline int bpf__prepare_load (const char *filename__maybe_unused ,bool source__maybe_unused )
@@ -37,8 +37,8 @@ static inline int bpf__load(void) { return 0; }static inline void bpf__clear (void ) { }static inline int -bpf__for_each_program (bpf_prog_iter_callback_t func__maybe_unused , -void *arg__maybe_unused ) +bpf__for_each_tev (bpf_prog_iter_callback_t func__maybe_unused , +void *arg__maybe_unused ) {return 0 ; }
tools/perf/util/evlist.c +16 -26
65 lines not on this page · raw message
Signature · 1 line
1.8.3.4
Re: [RFC PATCH v8 43/49] perf tools: Iterater over tev instead of pev in bpf__for_each_program
Quoted 10 lines · Wang Nan
This patch renames
bpf__for_each_program()tobpf__for_each_tev()and makes it iterate over 'structprobe_trace_event' instead of 'structprobe_trace_event' during the loop. The callback (add_bpf_event()) now get rid of the iteration.This is preparation for further patches, which will allow generating multiple instances form one BPF program and install then onto different 'struct
probe_trace_event'.Signed-off-by Wang Nan<[email protected]>
please squash this patch with earlier one that introduces this function.
RFC PATCH v8 44/49 perf tools: Add BPF_PROLOGUE config options for further patches
In reply to Wang NanIf both LIBBPF and DWARF is detected, it is possible to create prologue for eBPF programs to help them accessing kernel data. HAVE_BPF_PROLOGUE and CONFIG_BPF_PROLOGUE is added as flags for this feature.
PERF_HAVE_ARCH_GET_REG_OFFSET indicates an architecture supports converting name of a register to its offset in 'struct pt_regs'. Without this support, BPF_PROLOGUE should be turned off.
--- tools/perf/config/Makefile | 12 ++++++++++++ tools/perf/util/include/dwarf-regs.h | 7 +++++++ 2 files changed, 19 insertions(+)
tools/perf/config/Makefile +12 -0
@@ -310,6 +310,18 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_LIBBPF_SUPPORT $(call detected,CONFIG_LIBBPF) endif + + ifndef NO_DWARF + ifneq ($(origin PERF_HAVE_ARCH_GET_REG_INFO), undefined) + CFLAGS += -DHAVE_BPF_PROLOGUE + $(call detected,CONFIG_BPF_PROLOGUE) + else + msg := $(warning BPF prologue is not supported by architecture $(ARCH)); + endif + else + msg := $(warning DWARF support is off, BPF prologue is disabled); + endif + endif # NO_LIBBPF endif # NO_LIBELF
tools/perf/util/include/dwarf-regs.h +7 -0
@@ -5,4 +5,11 @@const char *get_arch_regstr (unsigned int n);#endif +#ifdef HAVE_BPF_PROLOGUE +/* +* Arch should support fetching the offset of a register in pt_regs +* by its name. +*/ +int arch_get_reg_info (const char *name,int *offset); +#endif #endif
Signature · 1 line
1.8.3.4
RFC PATCH v8 45/49 perf tools: Introduce arch_get_reg_info() for x86
In reply to Wang NanFrom: He Kuang <[email protected]>
arch_get_reg_info() is a helper function which converts register name like "%rax" to offset of a register in 'struct pt_regs', which is required by BPF prologue generator.
This patch replaces original string table by a 'struct reg_info' table, which records offset of registers according to its name.
For x86, since there are two sub-archs (x86_32 and x86_64) but we can only get pt_regs for the arch we are currently on, this patch fills offset with '-1' for another sub-arch. This introduces a limitation to perf prologue that, we are unable to generate prologue on a x86_32 compiled perf for BPF programs targeted on x86_64 kernel. This limitation is acceptable, because this is a very rare usecase.
--- tools/perf/arch/x86/Makefile | 1 + tools/perf/arch/x86/util/Build | 2 + tools/perf/arch/x86/util/dwarf-regs.c | 104 ++++++++++++++++++++++++---------- 3 files changed, 78 insertions(+), 29 deletions(-)
tools/perf/arch/x86/Makefile +1 -0
@@ -2,3 +2,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif HAVE_KVM_STAT_SUPPORT := 1 +PERF_HAVE_ARCH_GET_REG_INFO := 1
tools/perf/arch/x86/util/Build +2 -0
@@ -2,6 +2,8 @@ libperf-y += header.o libperf-y += tsc.o libperf-y += kvm-stat.o +# BPF_PROLOGUE also need dwarf-regs.o. However, if CONFIG_BPF_PROLOGUE +# is true, CONFIG_DWARF must true. libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
tools/perf/arch/x86/util/dwarf-regs.c +75 -29
124 lines not on this page · raw message
Signature · 1 line
1.8.3.4
RFC PATCH v8 46/49 perf tools: Add prologue for BPF programs for fetching arguments
In reply to Wang NanFrom: He Kuang <[email protected]>
This patch generates prologue for a BPF program which fetch arguments for it. With this patch, the program can have arguments as follow:
SEC("lock_page=__lock_page page->flags")
int lock_page(struct pt_regs *ctx, int err, unsigned long flags)
{
return 1;}
This patch passes at most 3 arguments from r3, r4 and r5. r1 is still the ctx pointer. r2 is used to indicate the successfulness of dereferencing.
This patch uses r6 to hold ctx (struct pt_regs) and r7 to hold stack pointer for result. Result of each arguments first store on stack:
low address
BPF_REG_FP - 24 ARG3 BPF_REG_FP - 16 ARG2 BPF_REG_FP - 8 ARG1
BPF_REG_FP
high address
Then loaded into r3, r4 and r5.
The output prologue for offn(...off2(off1(reg)))) should be:
r6 <- r1 // save ctx into a callee saved register
r7 <- fp
r7 <- r7 - stack_offset // pointer to result slot
/* load r3 with the offset in pt_regs of 'reg' */
(r7) <- r3 // make slot valid
r3 <- r3 + off1 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7 // result put onto stack
call probe_read // read unsafe pointer
jnei r0, 0, err // error checking
r3 <- (r7) // read result
r3 <- r3 + off2 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7
call probe_read
jnei r0, 0, err
...
/* load r2, r3, r4 from stack */
goto success
err:
r2 <- 1
/* load r3, r4, r5 with 0 */
goto usercode
success:
r2 <- 0
usercode:
r1 <- r6 // restore ctx
// original user codeIf all of arguments reside in register (dereferencing is not required), gen_prologue_fastpath() will be used to create fast prologue:
r3 <- (r1 + offset of reg1)
r4 <- (r1 + offset of reg2)
r5 <- (r1 + offset of reg3)
r2 <- 0P.S.
eBPF calling convention is defined as:
* r0 - return value from in-kernel function, and exit value
for eBPF program
* r1 - r5 - arguments from eBPF program to in-kernel function
* r6 - r9 - callee saved registers that in-kernel function will
preserve
* r10 - read-only frame pointer to access stack
--- tools/perf/util/Build | 1 + tools/perf/util/bpf-prologue.c | 425 +++++++++++++++++++++++++++++++++++++++++ tools/perf/util/bpf-prologue.h | 19 ++ 3 files changed, 445 insertions(+) create mode 100644 tools/perf/util/bpf-prologue.c create mode 100644 tools/perf/util/bpf-prologue.h
tools/perf/util/Build +1 -0
@@ -80,6 +80,7 @@ libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-y += parse-branch-options.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o +libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o libperf-$(CONFIG_LIBELF) += symbol-elf.o libperf-$(CONFIG_LIBELF) += probe-event.o
tools/perf/util/bpf-prologue.c new file +425 -0
425 lines not on this page · raw message
tools/perf/util/bpf-prologue.h new file +19 -0
@@ -0,0 +1,19 @@ +/* +* Copyright (C) 2015, He Kuang <[email protected]> +* Copyright (C) 2015, Huawei Inc. +*/ +#ifndef __BPF_PROLOGUE_H +#define __BPF_PROLOGUE_H + +#include <linux/filter.h> +#include "probe-event.h" + +#define BPF_PROLOGUE_MAX_ARGS 3 +#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3 +#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2 + +int bpf__gen_prologue (struct probe_trace_arg *args,int nargs, +struct bpf_insn *new_prog,size_t *new_cnt, +size_t cnt_space); + +#endif /* __BPF_PROLOGUE_H */
Signature · 1 line
1.8.3.4
Re: [RFC PATCH v8 46/49] perf tools: Add prologue for BPF programs for fetching arguments
On 2015/6/24 20:31, Wang Nan wrote:
[SNIP]
Quoted 14 lines
tools/perf/util/bpf-prologue.h new file +8
-0@@ -0,0 +1,19 @@ +/* +* Copyright (C) 2015, He Kuang <[email protected]> +* Copyright (C) 2015, Huawei Inc. +*/ +#ifndef __BPF_PROLOGUE_H +#define __BPF_PROLOGUE_H + +#include <linux/filter.h>
tools/perf/util/bpf-prologue.h line 18
Quoted 10 lines
tools/perf/util/bpf-prologue.h new file +10
-0+#include "probe-event.h" + +#define BPF_PROLOGUE_MAX_ARGS 3 +#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3 +#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2 + +int bpf__gen_prologue (struct probe_trace_arg *args,int nargs, +struct bpf_insn *new_prog,size_t *new_cnt, +size_t cnt_space); +
Here is a problem: if CONFIG_BPF_PROLOGUE is not set, a missing symbol problem will be triggered.
I have updated this part in my patchset:
+/*
+ * Copyright (C) 2015, He Kuang <[email protected]>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_PROLOGUE_H
+#define __BPF_PROLOGUE_H
+
+#include <linux/compiler.h>
+#include <linux/filter.h>
+#include "probe-event.h"
+
+#define BPF_PROLOGUE_MAX_ARGS 3
+#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3 +#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
+
+#ifdef HAVE_BPF_PROLOGUE
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+ struct bpf_insn *new_prog, size_t *new_cnt,
+ size_t cnt_space);
+#else
+static inline int
+bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
+ int nargs __maybe_unused, + struct bpf_insn *new_prog __maybe_unused, + size_t *new_cnt, + size_t cnt_space __maybe_unused)
+{
+ if (!new_cnt)
+ return -EINVAL;
+ *new_cnt = 0;
+ return 0;
+}
+#endif
+#endif /* __BPF_PROLOGUE_H */
Quoted 1 line
tools/perf/util/bpf-prologue.h new file +1
-0+#endif /* __BPF_PROLOGUE_H */
Re: [RFC PATCH v8 46/49] perf tools: Add prologue for BPF programs for fetching arguments
In reply to Wang NanQuoted 8 lines · Wang Nan
This patch generates prologue for a BPF program which fetch arguments for it. With this patch, the program can have arguments as follow:
SEC("lock_page=__lock_page page->flags")
intlock_page(struct pt_regs *ctx, int err, unsigned long flags){ return 1;}
looks great. Please address issues found by buildbot.
RFC PATCH v8 47/49 perf tools: Generate prologue for BPF programs
In reply to Wang NanThis patch generates prologue for each 'struct probe_trace_event' for fetching arguments for BPF programs.
After bpf__probe(), iterate over each programs to check whether prologue is required. If non of tev have argument, simply skip preprocessor hooking. For those who prologue is required, calls bpf__gen_prologue() and paste original instruction after prologue.
--- tools/perf/util/bpf-loader.c | 131 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 129 insertions(+), 2 deletions(-)
tools/perf/util/bpf-loader.c +129 -2
@@ -5,10 +5,12 @@* Copyright (C) 2015 Huawei Inc. */ +#include <linux/bpf.h> #include <bpf/libbpf.h> #include "perf.h" #include "debug.h" #include "bpf-loader.h" +#include "bpf-prologue.h" #include "llvm-utils.h" #include "probe-event.h" #include "probe-finder.h"
@@ -52,6 +54,8 @@ alloc_perf_probe_event(void)struct bpf_prog_priv {struct perf_probe_event *pev; +bool need_prologue; +struct bpf_insn *insns_buf; }; static void
@@ -61,6 +65,7 @@ bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,struct bpf_prog_priv *priv = _priv;if (priv->pev)clear_perf_probe_event (priv->pev); +zfree (&priv->insns_buf);free (priv); }
@@ -221,10 +226,109 @@ int bpf__unprobe(void)return ret <0 ? ret :0 ; } +static int +preproc_gen_prologue (struct bpf_program *prog,int n, +struct bpf_insn *orig_insns,int orig_insns_cnt, +struct bpf_prog_prep_result *res) +{ +struct probe_trace_event *tev; +struct perf_probe_event *pev; +struct bpf_prog_priv *priv; +struct bpf_insn *buf; +size_t prologue_cnt =0 ; +int err; + + err =bpf_program__get_private (prog, (void **)&priv); +if (err || !priv) + goto errout; + + pev = priv->pev; + +if (n <0 || n >= pev->ntevs) + goto errout; + + tev = &pev->tevs[n]; + + buf = priv->insns_buf; + err =bpf__gen_prologue (tev->args, tev->nargs, + buf, &prologue_cnt, +BPF_MAXINSNS - orig_insns_cnt); +if (err) { +const char *title; + + err =bpf_program__get_title (prog, &title, false); +if (err) + title ="??" ; + +pr_err ("Failed to generate prologue for program %s\n" , + title); +return err; + } + +memcpy (&buf[prologue_cnt], orig_insns, +sizeof (struct bpf_insn ) * orig_insns_cnt); + + res->new_insn_ptr = buf; + res->new_insn_cnt = prologue_cnt + orig_insns_cnt; + res->pfd =NULL ; +return 0 ; + +errout: +pr_err ("Internal error in preproc_gen_prologue\n" ); +return -EINVAL ; +} + +static int hook_load_preprocessor (struct bpf_program *prog) +{ +struct perf_probe_event *pev; +struct bpf_prog_priv *priv; +bool need_prologue = false; +int err, i; + + err =bpf_program__get_private (prog, (void **)&priv); +if (err || !priv) { +pr_err ("Internal error when hook preprocessor\n" ); +return -EINVAL ; + } + + pev = priv->pev; +for (i =0 ; i < pev->ntevs; i++) { +struct probe_trace_event *tev = &pev->tevs[i]; + +if (tev->nargs >0 ) { + need_prologue = true; +break ; + } + } + +/* +* Since all tev doesn't have argument, we don't need generate +* prologue. +*/ +if (!need_prologue) { + priv->need_prologue = false; +return 0 ; + } + + priv->need_prologue = true; + priv->insns_buf =malloc (sizeof (struct bpf_insn ) * +BPF_MAXINSNS ); +if (!priv->insns_buf) { +pr_err ("No enough memory: alloc insns_buf failed\n" ); +return -ENOMEM ; + } + + err =bpf_program__set_prep (prog, pev->ntevs, + preproc_gen_prologue); +return err; +} +int bpf__probe (void ) {int err;bool old_silent = probe_conf.silent; +struct bpf_object *obj, *tmp; +struct bpf_program *prog;if (nr_probe_events <=0 )return 0 ;
@@ -243,7 +347,27 @@ int bpf__probe(void)else is_probing = true; -return err <0 ? err :0 ; + err = err <0 ? err :0 ; +if (err) +return err; + +/* +* After probing, let's consider prologue, which +* add program fetcher to BPF programs. +* +* hook_load_preprocessorr() hooks pre-processor to bpf_program, +* let it generate prologue dynamically during loading. +*/ + +bpf_object__for_each (obj, tmp) { +bpf_object__for_each_program (prog, obj) { + err =hook_load_preprocessor (prog); +if (err) +return err; + } + } + +return err; }int bpf__load (void )
@@ -290,7 +414,10 @@ bpf__for_each_tev(bpf_prog_iter_callback_t func, void *arg)for (i =0 ; i < pev->ntevs; i++) { tev = &pev->tevs[i]; - err =bpf_program__get_fd (prog, &fd); +if (priv->need_prologue) + err =bpf_program__get_nth_fd (prog, i, &fd); +else + err =bpf_program__get_fd (prog, &fd);if (err || fd <0 ) {pr_err ("bpf: failed to get file descriptor\n" );
Signature · 1 line
1.8.3.4
Re: [RFC PATCH v8 47/49] perf tools: Generate prologue for BPF programs
Quoted 7 lines · Wang Nan
This patch generates prologue for each 'struct
probe_trace_event' for fetching arguments for BPF programs.After
bpf__probe(), iterate over each programs to check whether prologue is required. If non of tev have argument, simply skip preprocessor hooking. For those who prologue is required, callsbpf__gen_prologue()and paste original instruction after prologue.
please don't abbreviate tev, pev in commit logs. It's hard to read for anyone but core perf experts.
RFC PATCH v8 48/49 perf tools: Use same BPF program if arguments are identical
In reply to Wang NanThis patch allows creating only one BPF program for different tevs in one pev, if their prologue are identical.
This is done by comparing argument list of different tev, and maps type of prologue and tev using a mapping array. This patch use qsort to sort tevs prior type mapping for performance.
--- tools/perf/util/bpf-loader.c | 134 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 127 insertions(+), 7 deletions(-)
tools/perf/util/bpf-loader.c +127 -7
@@ -56,6 +56,8 @@ struct bpf_prog_priv {struct perf_probe_event *pev;bool need_prologue;struct bpf_insn *insns_buf; +int nr_types; +int *type_mapping; }; static void
@@ -66,6 +68,7 @@ bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,if (priv->pev)clear_perf_probe_event (priv->pev);zfree (&priv->insns_buf); +zfree (&priv->type_mapping);free (priv); }
@@ -236,7 +239,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,struct bpf_prog_priv *priv;struct bpf_insn *buf;size_t prologue_cnt =0 ; -int err; +int i, err; err =bpf_program__get_private (prog, (void **)&priv);if (err || !priv)
@@ -244,11 +247,20 @@ preproc_gen_prologue(struct bpf_program *prog, int n, pev = priv->pev; -if (n <0 || n >= pev->ntevs) +if (n <0 || n >= priv->nr_types) goto errout; - tev = &pev->tevs[n]; +/* Find a tev belong to that type */ +for (i =0 ; i < pev->ntevs; i++) +if (priv->type_mapping[i] == n) +break ; + +if (i >= pev->ntevs) { +pr_err ("Internal error: prologue type %d not found\n" , n); +return -EEXIST ; + } + tev = &pev->tevs[i]; buf = priv->insns_buf; err = bpf__gen_prologue(tev->args, tev->nargs, buf, &prologue_cnt,
@@ -278,6 +290,98 @@ errout:return -EINVAL ; } +/* +* compare_tev_args is reflexive, transitive and antisymmetric. +* I can show that but this margin is too narrow to contain. +*/ +static int compare_tev_args (const void *ptev1,const void *ptev2) +{ +int i, ret; +const struct probe_trace_event *tev1 = + *(const struct probe_trace_event **)ptev1; +const struct probe_trace_event *tev2 = + *(const struct probe_trace_event **)ptev2; + + ret = tev2->nargs - tev1->nargs; +if (ret) +return ret; + +for (i =0 ; i < tev1->nargs; i++) { +struct probe_trace_arg *arg1, *arg2; +struct probe_trace_arg_ref *ref1, *ref2; + + arg1 = &tev1->args[i]; + arg2 = &tev2->args[i]; + + ret =strcmp (arg1->value, arg2->value); +if (ret) +return ret; + + ref1 = arg1->ref; + ref2 = arg2->ref; + +while (ref1 && ref2) { + ret = ref2->offset - ref1->offset; +if (ret) +return ret; + + ref1 = ref1->next; + ref2 = ref2->next; + } + +if (ref1 || ref2) +return ref2 ?1 :-1 ; + } + +return 0 ; +} + +static int map_prologue (struct perf_probe_event *pev,int *mapping, +int *nr_types) +{ +int i, type =0 ; +struct { +struct probe_trace_event *tev; +int idx; + } *stevs; +size_t array_sz =sizeof (*stevs) * pev->ntevs; + + stevs =malloc (array_sz); +if (!stevs) { +pr_err ("No ehough memory: alloc stevs failed\n" ); +return -ENOMEM ; + } + +pr_debug ("In map_prologue, ntevs=%d\n" , pev->ntevs); +for (i =0 ; i < pev->ntevs; i++) { + stevs[i].tev = &pev->tevs[i]; + stevs[i].idx = i; + } +qsort (stevs, pev->ntevs,sizeof (*stevs), + compare_tev_args); + +for (i =0 ; i < pev->ntevs; i++) { +if (i ==0 ) { + mapping[stevs[i].idx] = type; +pr_debug ("mapping[%d]=%d\n" , stevs[i].idx, + type); +continue ; + } + +if (compare_tev_args (stevs + i, stevs + i -1 ) ==0 ) + mapping[stevs[i].idx] = type; +else + mapping[stevs[i].idx] = ++type; + +pr_debug ("mapping[%d]=%d\n" , stevs[i].idx, + mapping[stevs[i].idx]); + } +free (stevs); + *nr_types = type +1 ; + +return 0 ; +} +static int hook_load_preprocessor (struct bpf_program *prog) {struct perf_probe_event *pev;
@@ -318,7 +422,19 @@ static int hook_load_preprocessor(struct bpf_program *prog)return -ENOMEM ; } - err =bpf_program__set_prep (prog, pev->ntevs, + priv->type_mapping =malloc (sizeof (int ) * pev->ntevs); +if (!priv->type_mapping) { +pr_err ("No enough memory: alloc type_mapping failed\n" ); +return -ENOMEM ; + } +memset (priv->type_mapping,0xff , +sizeof (int ) * pev->ntevs); + + err =map_prologue (pev, priv->type_mapping, &priv->nr_types); +if (err) +return err; + + err =bpf_program__set_prep (prog, priv->nr_types, preproc_gen_prologue);return err; }
@@ -414,9 +530,13 @@ bpf__for_each_tev(bpf_prog_iter_callback_t func, void *arg)for (i =0 ; i < pev->ntevs; i++) { tev = &pev->tevs[i]; -if (priv->need_prologue) - err =bpf_program__get_nth_fd (prog, i, &fd); -else +if (priv->need_prologue) { +int type = priv->type_mapping[i]; + + err =bpf_program__get_nth_fd (prog, + type, + &fd); + }else err =bpf_program__get_fd (prog, &fd);if (err || fd <0 ) {
Signature · 1 line
1.8.3.4
RFC PATCH v8 49/49 perf record: Support custom vmlinux path
In reply to Wang NanFrom: He Kuang <[email protected]>
Make perf-record command support --vmlinux option if BPF_PROLOGUE is on.
'perf record' needs vmlinux as the source of DWARF info to generate prologue for BPF programs, so path of vmlinux should be specified.
Short name 'k' has been taken by 'clockid'. This patch skips the short option name and use '--vmlinux' for vmlinux path.
--- tools/perf/builtin-record.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/builtin-record.c +4 -0
@@ -1077,6 +1077,10 @@ struct option __record_options[] = { "clang binary to use for compiling BPF scriptlets"),OPT_STRING (0 ,"clang-opt" , &llvm_param.clang_opt,"clang options" ,"options passed to clang when compiling BPF scriptlets" ), +#ifdef HAVE_BPF_PROLOGUE +OPT_STRING (0 ,"vmlinux" , &symbol_conf.vmlinux_name, +"file" ,"vmlinux pathname" ), +#endif #endifOPT_END () };
Signature · 1 line
1.8.3.4
Quoted 12 lines · Wang Nan
The core stuffs in this series resides in 38/49 - 49/49, which allow users to access kernel data through parameters of eBPF programs. Now it is possible to write eBPF programs like this:
SEC("get_superblock=journal_get_superblock journal->j_errno")intget_superblock(struct pt_regs *ctx, int err, int j_errno){ char fmt[] = "j_errno=%lx\n"; bpf_trace_printk(fmt, sizeof(fmt), j_errno); if (j_errno) return 1; return 0;
Quoted 5 lines
}
Where, '
j_errno' in that function will be dereferenced according to dwarf information by prologue generated by perf. 'err' indicates the successfulness of the dereferencing.
Looks great. Very useful addition.
Quoted 5 lines
In addition, this series of patches supports setting BPF program to multiple probing points and generate different prologue for all of them if necessary. Using glob matching is also allowed. In the above example, there will be two
journal_get_superblock()functions in kernel if we compile both jbd and jbd2. That BPF function tracks both of them.
Sounds ok, but what is the real use case for it?