* [PATCH bpf-next v3 13/13] tools: bpftool: allow reuse of maps with bpftool prog load
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Add map parameter to prog load which will allow reuse of existing
maps instead of creating new ones.
We need feature detection and compat code for reallocarray, since
it's not available in many libc versions.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
.../bpftool/Documentation/bpftool-prog.rst | 20 ++-
tools/bpf/bpftool/bash-completion/bpftool | 67 +++++++-
tools/bpf/bpftool/main.h | 3 +
tools/bpf/bpftool/map.c | 4 +-
tools/bpf/bpftool/prog.c | 148 ++++++++++++++++--
5 files changed, 219 insertions(+), 23 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index e53e1ad2caf0..64156a16d530 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,9 +24,10 @@ MAP COMMANDS
| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}]
| **bpftool** **prog pin** *PROG* *FILE*
-| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
+| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
| **bpftool** **prog help**
|
+| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
| *TYPE* := {
| **socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
@@ -73,10 +74,17 @@ DESCRIPTION
Note: *FILE* must be located in *bpffs* mount.
- **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
+ **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
Load bpf program from binary *OBJ* and pin as *FILE*.
**type** is optional, if not specified program type will be
inferred from section names.
+ By default bpftool will create new maps as declared in the ELF
+ object being loaded. **map** parameter allows for the reuse
+ of existing maps. It can be specified multiple times, each
+ time for a different map. *IDX* refers to index of the map
+ to be replaced in the ELF file counting from 0, while *NAME*
+ allows to replace a map by name. *MAP* specifies the map to
+ use, referring to it by **id** or through a **pinned** file.
If **dev** *NAME* is specified program will be loaded onto
given networking device (offload).
@@ -172,6 +180,14 @@ EXAMPLES
mov %rbx,0x0(%rbp)
48 89 5d 00
+|
+| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
+| **# bpftool prog show pinned /sys/fs/bpf/xdp1**
+| 9: xdp name xdp_prog1 tag 539ec6ce11b52f98 gpl
+| loaded_at 2018-06-25T16:17:31-0700 uid 0
+| xlated 488B jited 336B memlock 4096B map_ids 7
+| **# rm /sys/fs/bpf/xdp1**
+|
SEE ALSO
========
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index caf8711993be..598066c40191 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,29 @@ _bpftool_get_prog_tags()
command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
}
+_bpftool_get_obj_map_names()
+{
+ local obj
+
+ obj=$1
+
+ maps=$(objdump -j maps -t $obj 2>/dev/null | \
+ command awk '/g . maps/ {print $NF}')
+
+ COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) )
+}
+
+_bpftool_get_obj_map_idxs()
+{
+ local obj
+
+ obj=$1
+
+ nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g . maps')
+
+ COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) )
+}
+
_sysfs_get_netdevs()
{
COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
@@ -220,12 +243,14 @@ _bpftool()
# Completion depends on object and command in use
case $object in
prog)
- case $prev in
- id)
- _bpftool_get_prog_ids
- return 0
- ;;
- esac
+ if [[ $command != "load" ]]; then
+ case $prev in
+ id)
+ _bpftool_get_prog_ids
+ return 0
+ ;;
+ esac
+ fi
local PROG_TYPE='id pinned tag'
case $command in
@@ -268,22 +293,52 @@ _bpftool()
return 0
;;
load)
+ local obj
+
if [[ ${#words[@]} -lt 6 ]]; then
_filedir
return 0
fi
+ obj=${words[3]}
+
+ if [[ ${words[-4]} == "map" ]]; then
+ COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+ return 0
+ fi
+ if [[ ${words[-3]} == "map" ]]; then
+ if [[ ${words[-2]} == "idx" ]]; then
+ _bpftool_get_obj_map_idxs $obj
+ elif [[ ${words[-2]} == "name" ]]; then
+ _bpftool_get_obj_map_names $obj
+ fi
+ return 0
+ fi
+ if [[ ${words[-2]} == "map" ]]; then
+ COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) )
+ return 0
+ fi
+
case $prev in
type)
COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
"$cur" ) )
return 0
;;
+ id)
+ _bpftool_get_map_ids
+ return 0
+ ;;
+ pinned)
+ _filedir
+ return 0
+ ;;
dev)
_sysfs_get_netdevs
return 0
;;
*)
+ COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
_bpftool_once_attr 'type'
_bpftool_once_attr 'dev'
return 0
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 1e02e4031693..41004bb2644a 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -75,6 +75,8 @@
"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
#define HELP_SPEC_OPTIONS \
"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+#define HELP_SPEC_MAP \
+ "MAP := { id MAP_ID | pinned FILE }"
enum bpf_obj_type {
BPF_OBJ_UNKNOWN,
@@ -136,6 +138,7 @@ int do_cgroup(int argc, char **arg);
int do_perf(int argc, char **arg);
int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd(int *argc, char ***argv);
int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 5989e1575ae4..e2baec1122fb 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -93,7 +93,7 @@ static void *alloc_value(struct bpf_map_info *info)
return malloc(info->value_size);
}
-static int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv)
{
int fd;
@@ -824,7 +824,7 @@ static int do_help(int argc, char **argv)
" %s %s event_pipe MAP [cpu N index M]\n"
" %s %s help\n"
"\n"
- " MAP := { id MAP_ID | pinned FILE }\n"
+ " " HELP_SPEC_MAP "\n"
" DATA := { [hex] BYTES }\n"
" " HELP_SPEC_PROGRAM "\n"
" VALUE := { DATA | MAP | PROG }\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 2bdd5ecd1aad..dce960d22106 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -31,6 +31,7 @@
* SOFTWARE.
*/
+#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <stdarg.h>
@@ -682,18 +683,34 @@ static int do_pin(int argc, char **argv)
return err;
}
+struct map_replace {
+ int idx;
+ int fd;
+ char *name;
+};
+
+int map_replace_compar(const void *p1, const void *p2)
+{
+ const struct map_replace *a = p1, *b = p2;
+
+ return a->idx - b->idx;
+}
+
static int do_load(int argc, char **argv)
{
enum bpf_attach_type expected_attach_type;
struct bpf_object_open_attr attr = {
.prog_type = BPF_PROG_TYPE_UNSPEC,
};
+ struct map_replace *map_replace = NULL;
+ unsigned int old_map_fds = 0;
struct bpf_program *prog;
struct bpf_object *obj;
struct bpf_map *map;
const char *pinfile;
+ unsigned int i, j;
__u32 ifindex = 0;
- int err;
+ int idx, err;
if (!REQ_ARGS(2))
return -1;
@@ -708,16 +725,16 @@ static int do_load(int argc, char **argv)
if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
p_err("program type already specified");
- return -1;
+ goto err_free_reuse_maps;
}
if (!REQ_ARGS(1))
- return -1;
+ goto err_free_reuse_maps;
/* Put a '/' at the end of type to appease libbpf */
type = malloc(strlen(*argv) + 2);
if (!type) {
p_err("mem alloc failed");
- return -1;
+ goto err_free_reuse_maps;
}
*type = 0;
strcat(type, *argv);
@@ -728,37 +745,81 @@ static int do_load(int argc, char **argv)
free(type);
if (err < 0) {
p_err("unknown program type '%s'", *argv);
- return err;
+ goto err_free_reuse_maps;
}
NEXT_ARG();
+ } else if (is_prefix(*argv, "map")) {
+ char *endptr, *name;
+ int fd;
+
+ NEXT_ARG();
+
+ if (!REQ_ARGS(4))
+ goto err_free_reuse_maps;
+
+ if (is_prefix(*argv, "idx")) {
+ NEXT_ARG();
+
+ idx = strtoul(*argv, &endptr, 0);
+ if (*endptr) {
+ p_err("can't parse %s as IDX", *argv);
+ goto err_free_reuse_maps;
+ }
+ name = NULL;
+ } else if (is_prefix(*argv, "name")) {
+ NEXT_ARG();
+
+ name = *argv;
+ idx = -1;
+ } else {
+ p_err("expected 'idx' or 'name', got: '%s'?",
+ *argv);
+ goto err_free_reuse_maps;
+ }
+ NEXT_ARG();
+
+ fd = map_parse_fd(&argc, &argv);
+ if (fd < 0)
+ goto err_free_reuse_maps;
+
+ map_replace = reallocarray(map_replace, old_map_fds + 1,
+ sizeof(*map_replace));
+ if (!map_replace) {
+ p_err("mem alloc failed");
+ goto err_free_reuse_maps;
+ }
+ map_replace[old_map_fds].idx = idx;
+ map_replace[old_map_fds].name = name;
+ map_replace[old_map_fds].fd = fd;
+ old_map_fds++;
} else if (is_prefix(*argv, "dev")) {
NEXT_ARG();
if (ifindex) {
p_err("offload device already specified");
- return -1;
+ goto err_free_reuse_maps;
}
if (!REQ_ARGS(1))
- return -1;
+ goto err_free_reuse_maps;
ifindex = if_nametoindex(*argv);
if (!ifindex) {
p_err("unrecognized netdevice '%s': %s",
*argv, strerror(errno));
- return -1;
+ goto err_free_reuse_maps;
}
NEXT_ARG();
} else {
- p_err("expected no more arguments, 'type' or 'dev', got: '%s'?",
+ p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
*argv);
- return -1;
+ goto err_free_reuse_maps;
}
}
obj = bpf_object__open_xattr(&attr);
if (IS_ERR_OR_NULL(obj)) {
p_err("failed to open object file");
- return -1;
+ goto err_free_reuse_maps;
}
prog = bpf_program__next(NULL, obj);
@@ -782,10 +843,62 @@ static int do_load(int argc, char **argv)
bpf_program__set_type(prog, attr.prog_type);
bpf_program__set_expected_attach_type(prog, expected_attach_type);
- bpf_map__for_each(map, obj)
+ qsort(map_replace, old_map_fds, sizeof(*map_replace),
+ map_replace_compar);
+
+ /* After the sort maps by name will be first on the list, because they
+ * have idx == -1. Resolve them.
+ */
+ j = 0;
+ while (j < old_map_fds && map_replace[j].name) {
+ i = 0;
+ bpf_map__for_each(map, obj) {
+ if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
+ map_replace[j].idx = i;
+ break;
+ }
+ i++;
+ }
+ if (map_replace[j].idx == -1) {
+ p_err("unable to find map '%s'", map_replace[j].name);
+ goto err_close_obj;
+ }
+ j++;
+ }
+ /* Resort if any names were resolved */
+ if (j)
+ qsort(map_replace, old_map_fds, sizeof(*map_replace),
+ map_replace_compar);
+
+ /* Set ifindex and name reuse */
+ j = 0;
+ idx = 0;
+ bpf_map__for_each(map, obj) {
if (!bpf_map__is_offload_neutral(map))
bpf_map__set_ifindex(map, ifindex);
+ if (j < old_map_fds && idx == map_replace[j].idx) {
+ err = bpf_map__reuse_fd(map, map_replace[j++].fd);
+ if (err) {
+ p_err("unable to set up map reuse: %d", err);
+ goto err_close_obj;
+ }
+
+ /* Next reuse wants to apply to the same map */
+ if (j < old_map_fds && map_replace[j].idx == idx) {
+ p_err("replacement for map idx %d specified more than once",
+ idx);
+ goto err_close_obj;
+ }
+ }
+
+ idx++;
+ }
+ if (j < old_map_fds) {
+ p_err("map idx '%d' not used", map_replace[j].idx);
+ goto err_close_obj;
+ }
+
err = bpf_object__load(obj);
if (err) {
p_err("failed to load object file");
@@ -799,11 +912,18 @@ static int do_load(int argc, char **argv)
jsonw_null(json_wtr);
bpf_object__close(obj);
+ for (i = 0; i < old_map_fds; i++)
+ close(map_replace[i].fd);
+ free(map_replace);
return 0;
err_close_obj:
bpf_object__close(obj);
+err_free_reuse_maps:
+ for (i = 0; i < old_map_fds; i++)
+ close(map_replace[i].fd);
+ free(map_replace);
return -1;
}
@@ -819,9 +939,11 @@ static int do_help(int argc, char **argv)
" %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
" %s %s dump jited PROG [{ file FILE | opcodes }]\n"
" %s %s pin PROG FILE\n"
- " %s %s load OBJ FILE [type TYPE] [dev NAME]\n"
+ " %s %s load OBJ FILE [type TYPE] [dev NAME] \\\n"
+ " [map { idx IDX | name NAME } MAP]\n"
" %s %s help\n"
"\n"
+ " " HELP_SPEC_MAP "\n"
" " HELP_SPEC_PROGRAM "\n"
" TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
" tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 12/13] tools: libbpf: allow map reuse
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
More advanced applications may want to only replace programs without
destroying associated maps. Allow libbpf users to achieve that.
Instead of always creating all of the maps at load time, expose to
users an API to reconstruct the map object from already existing
map.
The map parameters are read from the kernel and replace the parameters
of the ELF map. libbpf does not restrict the map replacement, i.e.
the reused map does not have to be compatible with the ELF map
definition. We relay on the verifier for checking the compatibility
between maps and programs. The ELF map definition is completely
overwritten by the information read from the kernel, to make sure
libbpf's view of map object corresponds to the actual map.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
v3 (Andrey):
- use dup3();
- close existing fd;
- handle errors better;
- depend on fd value to determine pre-set.
---
tools/lib/bpf/libbpf.c | 53 ++++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf.h | 1 +
2 files changed, 54 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fd2c4433863d..955f8eafbf41 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1035,6 +1035,53 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
return 0;
}
+int bpf_map__reuse_fd(struct bpf_map *map, int fd)
+{
+ struct bpf_map_info info = {};
+ __u32 len = sizeof(info);
+ int new_fd, err;
+ char *new_name;
+
+ err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err)
+ return err;
+
+ new_name = strdup(info.name);
+ if (!new_name)
+ return -errno;
+
+ new_fd = open("/", O_RDONLY | O_CLOEXEC);
+ if (new_fd < 0)
+ goto err_free_new_name;
+
+ new_fd = dup3(fd, new_fd, O_CLOEXEC);
+ if (new_fd < 0)
+ goto err_close_new_fd;
+
+ err = zclose(map->fd);
+ if (err)
+ goto err_close_new_fd;
+ free(map->name);
+
+ map->fd = new_fd;
+ map->name = new_name;
+ map->def.type = info.type;
+ map->def.key_size = info.key_size;
+ map->def.value_size = info.value_size;
+ map->def.max_entries = info.max_entries;
+ map->def.map_flags = info.map_flags;
+ map->btf_key_type_id = info.btf_key_type_id;
+ map->btf_value_type_id = info.btf_value_type_id;
+
+ return 0;
+
+err_close_new_fd:
+ close(new_fd);
+err_free_new_name:
+ free(new_name);
+ return -errno;
+}
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
@@ -1047,6 +1094,12 @@ bpf_object__create_maps(struct bpf_object *obj)
struct bpf_map_def *def = &map->def;
int *pfd = &map->fd;
+ if (map->fd >= 0) {
+ pr_debug("skip map create (preset) %s: fd=%d\n",
+ map->name, map->fd);
+ continue;
+ }
+
create_attr.name = map->name;
create_attr.map_ifindex = map->map_ifindex;
create_attr.map_type = def->type;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e911ad32d02e..1f8fc2060460 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -261,6 +261,7 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__reuse_fd(struct bpf_map *map, int fd);
bool bpf_map__is_offload_neutral(struct bpf_map *map);
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
int bpf_map__pin(struct bpf_map *map, const char *path);
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 11/13] tools: bpf: make use of reallocarray
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
reallocarray() is a safer variant of realloc which checks for
multiplication overflow in case of array allocation. Since it's
not available in Glibc < 2.26 import kernel's overflow.h and
add a static inline implementation when needed. Use feature
detection to probe for existence of reallocarray.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
---
tools/bpf/bpftool/Makefile | 6 +-
tools/bpf/bpftool/main.h | 1 +
tools/bpf/bpftool/xlated_dumper.c | 6 +-
tools/build/feature/Makefile | 4 +
tools/build/feature/test-reallocarray.c | 8 +
tools/include/linux/compiler-gcc.h | 4 +
tools/include/linux/overflow.h | 278 ++++++++++++++++++++++++
tools/include/tools/libc_compat.h | 20 ++
tools/lib/bpf/Makefile | 6 +-
tools/lib/bpf/libbpf.c | 10 +-
10 files changed, 334 insertions(+), 9 deletions(-)
create mode 100644 tools/build/feature/test-reallocarray.c
create mode 100644 tools/include/linux/overflow.h
create mode 100644 tools/include/tools/libc_compat.h
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 0911b00b25cc..6c4830e18879 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -52,7 +52,7 @@ INSTALL ?= install
RM ?= rm -f
FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray
FEATURE_DISPLAY = libbfd disassembler-four-args
check_feat := 1
@@ -75,6 +75,10 @@ ifeq ($(feature-disassembler-four-args), 1)
CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
endif
+ifeq ($(feature-reallocarray), 0)
+CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
include $(wildcard $(OUTPUT)*.d)
all: $(OUTPUT)bpftool
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 15b6c49ae533..1e02e4031693 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -42,6 +42,7 @@
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/hashtable.h>
+#include <tools/libc_compat.h>
#include "json_writer.h"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index b97f1da60dd1..3284759df98a 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -35,6 +35,7 @@
* POSSIBILITY OF SUCH DAMAGE.
*/
+#define _GNU_SOURCE
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
@@ -66,9 +67,8 @@ void kernel_syms_load(struct dump_data *dd)
while (!feof(fp)) {
if (!fgets(buff, sizeof(buff), fp))
break;
- tmp = realloc(dd->sym_mapping,
- (dd->sym_count + 1) *
- sizeof(*dd->sym_mapping));
+ tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
+ sizeof(*dd->sym_mapping));
if (!tmp) {
out:
free(dd->sym_mapping);
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dac9563b5470..0516259be70f 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -14,6 +14,7 @@ FILES= \
test-libaudit.bin \
test-libbfd.bin \
test-disassembler-four-args.bin \
+ test-reallocarray.bin \
test-liberty.bin \
test-liberty-z.bin \
test-cplus-demangle.bin \
@@ -204,6 +205,9 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
$(OUTPUT)test-disassembler-four-args.bin:
$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
+$(OUTPUT)test-reallocarray.bin:
+ $(BUILD)
+
$(OUTPUT)test-liberty.bin:
$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
diff --git a/tools/build/feature/test-reallocarray.c b/tools/build/feature/test-reallocarray.c
new file mode 100644
index 000000000000..8170de35150d
--- /dev/null
+++ b/tools/build/feature/test-reallocarray.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <stdlib.h>
+
+int main(void)
+{
+ return !!reallocarray(NULL, 1, 1);
+}
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 70fe61295733..0d35f18006a1 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -36,3 +36,7 @@
#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
#define __scanf(a, b) __attribute__((format(scanf, a, b)))
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
new file mode 100644
index 000000000000..8712ff70995f
--- /dev/null
+++ b/tools/include/linux/overflow.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type) (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_add_overflow(__a, __b, __d); \
+})
+
+#define check_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_sub_overflow(__a, __b, __d); \
+})
+
+#define check_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_mul_overflow(__a, __b, __d); \
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a + __b; \
+ *__d < __a; \
+})
+#define __unsigned_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a - __b; \
+ __a < __b; \
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a * __b; \
+ __builtin_constant_p(__b) ? \
+ __b > 0 && __a > type_max(typeof(__a)) / __b : \
+ __a > 0 && __b > type_max(typeof(__b)) / __a; \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a + (u64)__b; \
+ (((~(__a ^ __b)) & (*__d ^ __a)) \
+ & type_min(typeof(__a))) != 0; \
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a - (u64)__b; \
+ ((((__a ^ __b)) & (*__d ^ __a)) \
+ & type_min(typeof(__a))) != 0; \
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ typeof(a) __tmax = type_max(typeof(a)); \
+ typeof(a) __tmin = type_min(typeof(a)); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a * (u64)__b; \
+ (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \
+ (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \
+ (__b == (typeof(__b))-1 && __a == __tmin); \
+})
+
+
+#define check_add_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_add_overflow(a, b, d), \
+ __unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_sub_overflow(a, b, d), \
+ __unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_mul_overflow(a, b, d), \
+ __unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+ if (check_mul_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(n, size, &bytes))
+ return SIZE_MAX;
+ if (check_add_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n) \
+ __ab_c_size(n, \
+ sizeof(*(p)->member) + __must_be_array((p)->member),\
+ sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h
new file mode 100644
index 000000000000..664ced8cb1b0
--- /dev/null
+++ b/tools/include/tools/libc_compat.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+ size_t bytes;
+
+ if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+ return NULL;
+ return realloc(ptr, bytes);
+}
+#endif
+#endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5390e7725e43..7a8e4c98ef1a 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
endif
FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
+FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray
FEATURE_DISPLAY = libelf bpf
INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
@@ -120,6 +120,10 @@ ifeq ($(feature-libelf-getphdrnum), 1)
override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
endif
+ifeq ($(feature-reallocarray), 0)
+ override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
# Append required CFLAGS
override CFLAGS += $(EXTRA_WARNINGS)
override CFLAGS += -Werror -Wall
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f732237610e5..fd2c4433863d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -22,6 +22,7 @@
* License along with this program; if not, see <http://www.gnu.org/licenses>
*/
+#define _GNU_SOURCE
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
@@ -41,6 +42,7 @@
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
+#include <tools/libc_compat.h>
#include <libelf.h>
#include <gelf.h>
@@ -321,7 +323,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
progs = obj->programs;
nr_progs = obj->nr_programs;
- progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
+ progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
if (!progs) {
/*
* In this case the original obj->programs
@@ -822,8 +824,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
continue;
}
- reloc = realloc(reloc,
- sizeof(*obj->efile.reloc) * nr_reloc);
+ reloc = reallocarray(reloc, nr_reloc,
+ sizeof(*obj->efile.reloc));
if (!reloc) {
pr_warning("realloc failed\n");
err = -ENOMEM;
@@ -1115,7 +1117,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
return -LIBBPF_ERRNO__RELOC;
}
new_cnt = prog->insns_cnt + text->insns_cnt;
- new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
+ new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
if (!new_insn) {
pr_warning("oom in prog realloc\n");
return -ENOMEM;
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 10/13] tools: libbpf: move library error code into a separate file
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
libbpf_strerror() depends on XSI-compliant (POSIX) version of
strerror_r(), which prevents us from using GNU-extensions in
libbpf.c, like reallocarray() or dup3(). Move error printing
code into a separate file to allow it to continue using POSIX
strerror_r().
No functional changes.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
tools/lib/bpf/Build | 2 +-
tools/lib/bpf/libbpf.c | 48 -----------------------
tools/lib/bpf/libbpf_errno.c | 74 ++++++++++++++++++++++++++++++++++++
3 files changed, 75 insertions(+), 49 deletions(-)
create mode 100644 tools/lib/bpf/libbpf_errno.c
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6070e655042d..13a861135127 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 06cd534d2fba..f732237610e5 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -95,54 +95,6 @@ void libbpf_set_print(libbpf_print_fn_t warn,
#define STRERR_BUFSIZE 128
-#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
- [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
- [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
- [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
- [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
- [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
- [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
- [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
- [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
- [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
- [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
- [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
- [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
- if (!buf || !size)
- return -1;
-
- err = err > 0 ? err : -err;
-
- if (err < __LIBBPF_ERRNO__START) {
- int ret;
-
- ret = strerror_r(err, buf, size);
- buf[size - 1] = '\0';
- return ret;
- }
-
- if (err < __LIBBPF_ERRNO__END) {
- const char *msg;
-
- msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
- snprintf(buf, size, "%s", msg);
- buf[size - 1] = '\0';
- return 0;
- }
-
- snprintf(buf, size, "Unknown libbpf error %d", err);
- buf[size - 1] = '\0';
- return -1;
-}
-
#define CHECK_ERR(action, err, out) do { \
err = action; \
if (err) \
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
new file mode 100644
index 000000000000..d9ba851bd7f9
--- /dev/null
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses>
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "libbpf.h"
+
+#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+ [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
+ [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
+ [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
+ [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
+ [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
+ [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
+ [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
+ [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
+ [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
+ [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
+ [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
+ [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+ if (!buf || !size)
+ return -1;
+
+ err = err > 0 ? err : -err;
+
+ if (err < __LIBBPF_ERRNO__START) {
+ int ret;
+
+ ret = strerror_r(err, buf, size);
+ buf[size - 1] = '\0';
+ return ret;
+ }
+
+ if (err < __LIBBPF_ERRNO__END) {
+ const char *msg;
+
+ msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+ snprintf(buf, size, "%s", msg);
+ buf[size - 1] = '\0';
+ return 0;
+ }
+
+ snprintf(buf, size, "Unknown libbpf error %d", err);
+ buf[size - 1] = '\0';
+ return -1;
+}
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 09/13] tools: bpftool: reimplement bpf_prog_load() for prog load
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
bpf_prog_load() is a very useful helper but it doesn't give us full
flexibility of modifying the BPF objects before loading. Open code
bpf_prog_load() in bpftool so we can add extra logic in following
commits.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
tools/bpf/bpftool/prog.c | 61 +++++++++++++++++++++++++++++++---------
1 file changed, 48 insertions(+), 13 deletions(-)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 98695585bbb6..2bdd5ecd1aad 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -43,6 +43,8 @@
#include <sys/types.h>
#include <sys/stat.h>
+#include <linux/err.h>
+
#include <bpf.h>
#include <libbpf.h>
@@ -682,17 +684,20 @@ static int do_pin(int argc, char **argv)
static int do_load(int argc, char **argv)
{
- struct bpf_prog_load_attr attr = {
+ enum bpf_attach_type expected_attach_type;
+ struct bpf_object_open_attr attr = {
.prog_type = BPF_PROG_TYPE_UNSPEC,
};
- const char *objfile, *pinfile;
+ struct bpf_program *prog;
struct bpf_object *obj;
- int prog_fd;
+ struct bpf_map *map;
+ const char *pinfile;
+ __u32 ifindex = 0;
int err;
if (!REQ_ARGS(2))
return -1;
- objfile = GET_ARG();
+ attr.file = GET_ARG();
pinfile = GET_ARG();
while (argc) {
@@ -719,7 +724,7 @@ static int do_load(int argc, char **argv)
strcat(type, "/");
err = libbpf_prog_type_by_name(type, &attr.prog_type,
- &attr.expected_attach_type);
+ &expected_attach_type);
free(type);
if (err < 0) {
p_err("unknown program type '%s'", *argv);
@@ -729,15 +734,15 @@ static int do_load(int argc, char **argv)
} else if (is_prefix(*argv, "dev")) {
NEXT_ARG();
- if (attr.ifindex) {
+ if (ifindex) {
p_err("offload device already specified");
return -1;
}
if (!REQ_ARGS(1))
return -1;
- attr.ifindex = if_nametoindex(*argv);
- if (!attr.ifindex) {
+ ifindex = if_nametoindex(*argv);
+ if (!ifindex) {
p_err("unrecognized netdevice '%s': %s",
*argv, strerror(errno));
return -1;
@@ -750,14 +755,44 @@ static int do_load(int argc, char **argv)
}
}
- attr.file = objfile;
-
- if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
- p_err("failed to load program");
+ obj = bpf_object__open_xattr(&attr);
+ if (IS_ERR_OR_NULL(obj)) {
+ p_err("failed to open object file");
return -1;
}
- if (do_pin_fd(prog_fd, pinfile))
+ prog = bpf_program__next(NULL, obj);
+ if (!prog) {
+ p_err("object file doesn't contain any bpf program");
+ goto err_close_obj;
+ }
+
+ bpf_program__set_ifindex(prog, ifindex);
+ if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+ const char *sec_name = bpf_program__title(prog, false);
+
+ err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
+ &expected_attach_type);
+ if (err < 0) {
+ p_err("failed to guess program type based on section name %s\n",
+ sec_name);
+ goto err_close_obj;
+ }
+ }
+ bpf_program__set_type(prog, attr.prog_type);
+ bpf_program__set_expected_attach_type(prog, expected_attach_type);
+
+ bpf_map__for_each(map, obj)
+ if (!bpf_map__is_offload_neutral(map))
+ bpf_map__set_ifindex(map, ifindex);
+
+ err = bpf_object__load(obj);
+ if (err) {
+ p_err("failed to load object file");
+ goto err_close_obj;
+ }
+
+ if (do_pin_fd(bpf_program__fd(prog), pinfile))
goto err_close_obj;
if (json_output)
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 08/13] tools: libbpf: add extended attributes version of bpf_object__open()
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Similarly to bpf_prog_load() users of bpf_object__open() may need
to specify the expected program type. Program type is needed at
open to avoid the kernel version check for program types which don't
require it.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
v3 (Andrey):
- put file path into the attr struct.
---
tools/lib/bpf/libbpf.c | 26 ++++++++++++++++++++------
tools/lib/bpf/libbpf.h | 6 ++++++
2 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 30992305f4c1..06cd534d2fba 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1520,15 +1520,26 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
return ERR_PTR(err);
}
-struct bpf_object *bpf_object__open(const char *path)
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
{
/* param validation */
- if (!path)
+ if (!attr->file)
return NULL;
- pr_debug("loading %s\n", path);
+ pr_debug("loading %s\n", attr->file);
+
+ return __bpf_object__open(attr->file, NULL, 0,
+ bpf_prog_type__needs_kver(attr->prog_type));
+}
+
+struct bpf_object *bpf_object__open(const char *path)
+{
+ struct bpf_object_open_attr attr = {
+ .file = path,
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
- return __bpf_object__open(path, NULL, 0, true);
+ return bpf_object__open_xattr(&attr);
}
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
@@ -2238,6 +2249,10 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd)
{
+ struct bpf_object_open_attr open_attr = {
+ .file = attr->file,
+ .prog_type = attr->prog_type,
+ };
struct bpf_program *prog, *first_prog = NULL;
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
@@ -2250,8 +2265,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
if (!attr->file)
return -EINVAL;
- obj = __bpf_object__open(attr->file, NULL, 0,
- bpf_prog_type__needs_kver(attr->prog_type));
+ obj = bpf_object__open_xattr(&open_attr);
if (IS_ERR_OR_NULL(obj))
return -ENOENT;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 749acf58a5da..e911ad32d02e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -66,7 +66,13 @@ void libbpf_set_print(libbpf_print_fn_t warn,
/* Hide internal to user */
struct bpf_object;
+struct bpf_object_open_attr {
+ const char *file;
+ enum bpf_prog_type prog_type;
+};
+
struct bpf_object *bpf_object__open(const char *path);
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 07/13] tools: libbpf: recognize offload neutral maps
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Add helper to libbpf for recognizing maps which should not have
ifindex set when program is loaded. These maps only contain
host metadata and therefore are not marked for offload, e.g.
the perf event map.
Use this helper in bpf_prog_load_xattr().
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
tools/lib/bpf/libbpf.c | 8 +++++++-
tools/lib/bpf/libbpf.h | 1 +
2 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 42f31eff5f3f..30992305f4c1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2154,6 +2154,11 @@ void *bpf_map__priv(struct bpf_map *map)
return map ? map->priv : ERR_PTR(-EINVAL);
}
+bool bpf_map__is_offload_neutral(struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
map->map_ifindex = ifindex;
@@ -2278,7 +2283,8 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
}
bpf_map__for_each(map, obj) {
- map->map_ifindex = attr->ifindex;
+ if (!bpf_map__is_offload_neutral(map))
+ map->map_ifindex = attr->ifindex;
}
if (!first_prog) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index d1ce5c828e2e..749acf58a5da 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -255,6 +255,7 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+bool bpf_map__is_offload_neutral(struct bpf_map *map);
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
int bpf_map__pin(struct bpf_map *map, const char *path);
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 06/13] tools: bpftool: allow users to specify program type for prog load
From: Jakub Kicinski @ 2018-07-10 21:43 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Sometimes program section names don't match with libbpf's expectation.
In particular XDP's default section names differ between libbpf and
iproute2. Allow users to pass program type on command line. Name
the types like the libbpf expected section names.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
.../bpftool/Documentation/bpftool-prog.rst | 15 ++++++-
tools/bpf/bpftool/bash-completion/bpftool | 6 +++
tools/bpf/bpftool/prog.c | 44 +++++++++++++++++--
3 files changed, 60 insertions(+), 5 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 41723c6acaa6..e53e1ad2caf0 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,10 +24,19 @@ MAP COMMANDS
| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}]
| **bpftool** **prog pin** *PROG* *FILE*
-| **bpftool** **prog load** *OBJ* *FILE* [**dev** *NAME*]
+| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
| **bpftool** **prog help**
|
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+| *TYPE* := {
+| **socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
+| **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** |
+| **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
+| **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
+| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
+| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+| }
+
DESCRIPTION
===========
@@ -64,8 +73,10 @@ DESCRIPTION
Note: *FILE* must be located in *bpffs* mount.
- **bpftool prog load** *OBJ* *FILE* [**dev** *NAME*]
+ **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
Load bpf program from binary *OBJ* and pin as *FILE*.
+ **type** is optional, if not specified program type will be
+ inferred from section names.
If **dev** *NAME* is specified program will be loaded onto
given networking device (offload).
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 238c2f80092a..caf8711993be 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -274,11 +274,17 @@ _bpftool()
fi
case $prev in
+ type)
+ COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+ "$cur" ) )
+ return 0
+ ;;
dev)
_sysfs_get_netdevs
return 0
;;
*)
+ _bpftool_once_attr 'type'
_bpftool_once_attr 'dev'
return 0
;;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 21c74de7156f..98695585bbb6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -688,6 +688,7 @@ static int do_load(int argc, char **argv)
const char *objfile, *pinfile;
struct bpf_object *obj;
int prog_fd;
+ int err;
if (!REQ_ARGS(2))
return -1;
@@ -695,7 +696,37 @@ static int do_load(int argc, char **argv)
pinfile = GET_ARG();
while (argc) {
- if (is_prefix(*argv, "dev")) {
+ if (is_prefix(*argv, "type")) {
+ char *type;
+
+ NEXT_ARG();
+
+ if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+ p_err("program type already specified");
+ return -1;
+ }
+ if (!REQ_ARGS(1))
+ return -1;
+
+ /* Put a '/' at the end of type to appease libbpf */
+ type = malloc(strlen(*argv) + 2);
+ if (!type) {
+ p_err("mem alloc failed");
+ return -1;
+ }
+ *type = 0;
+ strcat(type, *argv);
+ strcat(type, "/");
+
+ err = libbpf_prog_type_by_name(type, &attr.prog_type,
+ &attr.expected_attach_type);
+ free(type);
+ if (err < 0) {
+ p_err("unknown program type '%s'", *argv);
+ return err;
+ }
+ NEXT_ARG();
+ } else if (is_prefix(*argv, "dev")) {
NEXT_ARG();
if (attr.ifindex) {
@@ -713,7 +744,7 @@ static int do_load(int argc, char **argv)
}
NEXT_ARG();
} else {
- p_err("expected no more arguments or 'dev', got: '%s'?",
+ p_err("expected no more arguments, 'type' or 'dev', got: '%s'?",
*argv);
return -1;
}
@@ -753,10 +784,17 @@ static int do_help(int argc, char **argv)
" %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
" %s %s dump jited PROG [{ file FILE | opcodes }]\n"
" %s %s pin PROG FILE\n"
- " %s %s load OBJ FILE [dev NAME]\n"
+ " %s %s load OBJ FILE [type TYPE] [dev NAME]\n"
" %s %s help\n"
"\n"
" " HELP_SPEC_PROGRAM "\n"
+ " TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
+ " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
+ " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
+ " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+ " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
+ " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
+ " cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 05/13] tools: libbpf: expose the prog type guessing from section name logic
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
libbpf can guess program type based on ELF section names. As libbpf
becomes more popular its association between section name strings and
types becomes more of a standard. Allow libbpf users to use the same
logic for matching strings to types, e.g. when the string originates
from command line.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
v3 (Andrey):
- use -EINVAL error code;
- rename helper to libbpf_prog_type_by_name().
---
tools/lib/bpf/libbpf.c | 43 ++++++++++++++++++++++++------------------
tools/lib/bpf/libbpf.h | 3 +++
2 files changed, 28 insertions(+), 18 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 38ed3e92e393..42f31eff5f3f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2081,23 +2081,31 @@ static const struct {
#undef BPF_S_PROG_SEC
#undef BPF_SA_PROG_SEC
-static int bpf_program__identify_section(struct bpf_program *prog)
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type)
{
int i;
- if (!prog->section_name)
- goto err;
-
- for (i = 0; i < ARRAY_SIZE(section_names); i++)
- if (strncmp(prog->section_name, section_names[i].sec,
- section_names[i].len) == 0)
- return i;
+ if (!name)
+ return -EINVAL;
-err:
- pr_warning("failed to guess program type based on section name %s\n",
- prog->section_name);
+ for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+ if (strncmp(name, section_names[i].sec, section_names[i].len))
+ continue;
+ *prog_type = section_names[i].prog_type;
+ *expected_attach_type = section_names[i].expected_attach_type;
+ return 0;
+ }
+ return -EINVAL;
+}
- return -1;
+static int
+bpf_program__identify_section(struct bpf_program *prog,
+ enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type)
+{
+ return libbpf_prog_type_by_name(prog->section_name, prog_type,
+ expected_attach_type);
}
int bpf_map__fd(struct bpf_map *map)
@@ -2230,7 +2238,6 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
enum bpf_prog_type prog_type;
struct bpf_object *obj;
struct bpf_map *map;
- int section_idx;
int err;
if (!attr)
@@ -2252,14 +2259,14 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
prog->prog_ifindex = attr->ifindex;
expected_attach_type = attr->expected_attach_type;
if (prog_type == BPF_PROG_TYPE_UNSPEC) {
- section_idx = bpf_program__identify_section(prog);
- if (section_idx < 0) {
+ err = bpf_program__identify_section(prog, &prog_type,
+ &expected_attach_type);
+ if (err < 0) {
+ pr_warning("failed to guess program type based on section name %s\n",
+ prog->section_name);
bpf_object__close(obj);
return -EINVAL;
}
- prog_type = section_names[section_idx].prog_type;
- expected_attach_type =
- section_names[section_idx].expected_attach_type;
}
bpf_program__set_type(prog, prog_type);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 564f4be9bae0..d1ce5c828e2e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -92,6 +92,9 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
bpf_object_clear_priv_t clear_priv);
void *bpf_object__priv(struct bpf_object *prog);
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type);
+
/* Accessors of bpf_program */
struct bpf_program;
struct bpf_program *bpf_program__next(struct bpf_program *prog,
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 04/13] tools: bpftool: add support for loading programs for offload
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Extend the bpftool prog load command to also accept "dev"
parameter, which will allow us to load programs onto devices.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
.../bpftool/Documentation/bpftool-prog.rst | 6 ++--
tools/bpf/bpftool/bash-completion/bpftool | 23 ++++++++++--
tools/bpf/bpftool/prog.c | 35 +++++++++++++++++--
3 files changed, 58 insertions(+), 6 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 43d34a5c3ec5..41723c6acaa6 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,7 +24,7 @@ MAP COMMANDS
| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}]
| **bpftool** **prog pin** *PROG* *FILE*
-| **bpftool** **prog load** *OBJ* *FILE*
+| **bpftool** **prog load** *OBJ* *FILE* [**dev** *NAME*]
| **bpftool** **prog help**
|
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
@@ -64,8 +64,10 @@ DESCRIPTION
Note: *FILE* must be located in *bpffs* mount.
- **bpftool prog load** *OBJ* *FILE*
+ **bpftool prog load** *OBJ* *FILE* [**dev** *NAME*]
Load bpf program from binary *OBJ* and pin as *FILE*.
+ If **dev** *NAME* is specified program will be loaded onto
+ given networking device (offload).
Note: *FILE* must be located in *bpffs* mount.
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index ce0bc0cda361..238c2f80092a 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,12 @@ _bpftool_get_prog_tags()
command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
}
+_sysfs_get_netdevs()
+{
+ COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
+ "$cur" ) )
+}
+
# For bpftool map update: retrieve type of the map to update.
_bpftool_map_update_map_type()
{
@@ -262,8 +268,21 @@ _bpftool()
return 0
;;
load)
- _filedir
- return 0
+ if [[ ${#words[@]} -lt 6 ]]; then
+ _filedir
+ return 0
+ fi
+
+ case $prev in
+ dev)
+ _sysfs_get_netdevs
+ return 0
+ ;;
+ *)
+ _bpftool_once_attr 'dev'
+ return 0
+ ;;
+ esac
;;
*)
[[ $prev == $object ]] && \
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a5ef46c59029..21c74de7156f 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -39,6 +39,7 @@
#include <string.h>
#include <time.h>
#include <unistd.h>
+#include <net/if.h>
#include <sys/types.h>
#include <sys/stat.h>
@@ -681,6 +682,9 @@ static int do_pin(int argc, char **argv)
static int do_load(int argc, char **argv)
{
+ struct bpf_prog_load_attr attr = {
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
const char *objfile, *pinfile;
struct bpf_object *obj;
int prog_fd;
@@ -690,7 +694,34 @@ static int do_load(int argc, char **argv)
objfile = GET_ARG();
pinfile = GET_ARG();
- if (bpf_prog_load(objfile, BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
+ while (argc) {
+ if (is_prefix(*argv, "dev")) {
+ NEXT_ARG();
+
+ if (attr.ifindex) {
+ p_err("offload device already specified");
+ return -1;
+ }
+ if (!REQ_ARGS(1))
+ return -1;
+
+ attr.ifindex = if_nametoindex(*argv);
+ if (!attr.ifindex) {
+ p_err("unrecognized netdevice '%s': %s",
+ *argv, strerror(errno));
+ return -1;
+ }
+ NEXT_ARG();
+ } else {
+ p_err("expected no more arguments or 'dev', got: '%s'?",
+ *argv);
+ return -1;
+ }
+ }
+
+ attr.file = objfile;
+
+ if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
p_err("failed to load program");
return -1;
}
@@ -722,7 +753,7 @@ static int do_help(int argc, char **argv)
" %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
" %s %s dump jited PROG [{ file FILE | opcodes }]\n"
" %s %s pin PROG FILE\n"
- " %s %s load OBJ FILE\n"
+ " %s %s load OBJ FILE [dev NAME]\n"
" %s %s help\n"
"\n"
" " HELP_SPEC_PROGRAM "\n"
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 03/13] tools: bpftool: refactor argument parsing for prog load
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Add a new macro for printing more informative message than straight
usage() when parameters are missing, and use it for prog do_load().
Save the object and pin path argument to variables for clarity.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
tools/bpf/bpftool/main.h | 15 +++++++++++++++
tools/bpf/bpftool/prog.c | 11 +++++++----
2 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d39f7ef01d23..15b6c49ae533 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -50,6 +50,21 @@
#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); })
#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; })
+#define GET_ARG() ({ argc--; *argv++; })
+#define REQ_ARGS(cnt) \
+ ({ \
+ int _cnt = (cnt); \
+ bool _res; \
+ \
+ if (argc < _cnt) { \
+ p_err("'%s' needs at least %d arguments, %d found", \
+ argv[-1], _cnt, argc); \
+ _res = false; \
+ } else { \
+ _res = true; \
+ } \
+ _res; \
+ })
#define ERR_MAX_LEN 1024
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a740da99d477..a5ef46c59029 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -681,18 +681,21 @@ static int do_pin(int argc, char **argv)
static int do_load(int argc, char **argv)
{
+ const char *objfile, *pinfile;
struct bpf_object *obj;
int prog_fd;
- if (argc != 2)
- usage();
+ if (!REQ_ARGS(2))
+ return -1;
+ objfile = GET_ARG();
+ pinfile = GET_ARG();
- if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
+ if (bpf_prog_load(objfile, BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
p_err("failed to load program");
return -1;
}
- if (do_pin_fd(prog_fd, argv[1]))
+ if (do_pin_fd(prog_fd, pinfile))
goto err_close_obj;
if (json_output)
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 02/13] selftests/bpf: add Error: prefix in check_extack helper
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Currently the test only checks errors, not warnings, so save typing
and prefix the extack messages with "Error:" inside the check helper.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
tools/testing/selftests/bpf/test_offload.py | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index a257e4b08392..f8d9bd81d9a4 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -547,11 +547,11 @@ netns = [] # net namespaces to be removed
if skip_extack:
return
lines = output.split("\n")
- comp = len(lines) >= 2 and lines[1] == reference
+ comp = len(lines) >= 2 and lines[1] == 'Error: ' + reference
fail(not comp, "Missing or incorrect netlink extack message")
def check_extack_nsim(output, reference, args):
- check_extack(output, "Error: netdevsim: " + reference, args)
+ check_extack(output, "netdevsim: " + reference, args)
def check_no_extack(res, needle):
fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
@@ -654,7 +654,7 @@ netns = []
ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
fail=False, include_stderr=True)
fail(ret == 0, "TC filter loaded without enabling TC offloads")
- check_extack(err, "Error: TC offload is disabled on net device.", args)
+ check_extack(err, "TC offload is disabled on net device.", args)
sim.wait_for_flush()
sim.set_ethtool_tc_offloads(True)
@@ -694,7 +694,7 @@ netns = []
skip_sw=True,
fail=False, include_stderr=True)
fail(ret == 0, "Offloaded a filter to chain other than 0")
- check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+ check_extack(err, "Driver supports only offload of chain 0.", args)
sim.tc_flush_filters()
start_test("Test TC replace...")
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 01/13] selftests/bpf: remove duplicated word from test offloads
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20180710214307.4834-1-jakub.kicinski@netronome.com>
Trivial removal of duplicated "mode" in error message.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
tools/testing/selftests/bpf/test_offload.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index be800d0e7a84..a257e4b08392 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -830,7 +830,7 @@ netns = []
check_extack_nsim(err, "program loaded with different flags.", args)
ret, _, err = sim.unset_xdp("", force=True,
fail=False, include_stderr=True)
- fail(ret == 0, "Removed program with a bad mode mode")
+ fail(ret == 0, "Removed program with a bad mode")
check_extack_nsim(err, "program loaded with different flags.", args)
start_test("Test MTU restrictions...")
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next v3 00/13] tools: bpf: extend bpftool prog load
From: Jakub Kicinski @ 2018-07-10 21:42 UTC (permalink / raw)
To: alexei.starovoitov, daniel, Andrey Ignatov
Cc: oss-drivers, netdev, Jakub Kicinski
Hi!
This series starts with two minor clean ups to test_offload.py
selftest script.
The next 11 patches extend the abilities of bpftool prog load
beyond the simple cgroup use cases. Three new parameters are
added:
- type - allows specifying program type, independent of how
code sections are named;
- map - allows reusing existing maps, instead of creating a new
map on every program load;
- dev - offload/binding to a device.
A number of changes to libbpf is required to accomplish the task.
The section - program type logic mapping is exposed. We should
probably aim to use the libbpf program section naming everywhere.
For reuse of maps we need to allow users to set FD for bpf map
object in libbpf.
Examples
Load program my_xdp.o and pin it as /sys/fs/bpf/my_xdp, for xdp
program type:
$ bpftool prog load my_xdp.o /sys/fs/bpf/my_xdp \
type xdp
As above but for offload:
$ bpftool prog load my_xdp.o /sys/fs/bpf/my_xdp \
type xdp \
dev netdevsim0
Load program my_maps.o, but for the first map reuse map id 17,
and for the map called "other_map" reuse pinned map /sys/fs/bpf/map0:
$ bpftool prog load my_maps.o /sys/fs/bpf/prog \
map idx 0 id 17 \
map name other_map pinned /sys/fs/bpf/map0
---
v3:
- fix return codes in patch 5;
- rename libbpf_prog_type_by_string() -> libbpf_prog_type_by_name();
- fold file path into xattr in patch 8;
- add patch 10;
- use dup3() in patch 12;
- depend on fd value in patch 12;
- close old fd in patch 12.
v2:
- add compat for reallocarray().
Jakub Kicinski (13):
selftests/bpf: remove duplicated word from test offloads
selftests/bpf: add Error: prefix in check_extack helper
tools: bpftool: refactor argument parsing for prog load
tools: bpftool: add support for loading programs for offload
tools: libbpf: expose the prog type guessing from section name logic
tools: bpftool: allow users to specify program type for prog load
tools: libbpf: recognize offload neutral maps
tools: libbpf: add extended attributes version of bpf_object__open()
tools: bpftool: reimplement bpf_prog_load() for prog load
tools: libbpf: move library error code into a separate file
tools: bpf: make use of reallocarray
tools: libbpf: allow map reuse
tools: bpftool: allow reuse of maps with bpftool prog load
.../bpftool/Documentation/bpftool-prog.rst | 33 ++-
tools/bpf/bpftool/Makefile | 6 +-
tools/bpf/bpftool/bash-completion/bpftool | 96 +++++-
tools/bpf/bpftool/main.h | 19 ++
tools/bpf/bpftool/map.c | 4 +-
tools/bpf/bpftool/prog.c | 245 ++++++++++++++-
tools/bpf/bpftool/xlated_dumper.c | 6 +-
tools/build/feature/Makefile | 4 +
tools/build/feature/test-reallocarray.c | 8 +
tools/include/linux/compiler-gcc.h | 4 +
tools/include/linux/overflow.h | 278 ++++++++++++++++++
tools/include/tools/libc_compat.h | 20 ++
tools/lib/bpf/Build | 2 +-
tools/lib/bpf/Makefile | 6 +-
tools/lib/bpf/libbpf.c | 188 +++++++-----
tools/lib/bpf/libbpf.h | 11 +
tools/lib/bpf/libbpf_errno.c | 74 +++++
tools/testing/selftests/bpf/test_offload.py | 10 +-
18 files changed, 906 insertions(+), 108 deletions(-)
create mode 100644 tools/build/feature/test-reallocarray.c
create mode 100644 tools/include/linux/overflow.h
create mode 100644 tools/include/tools/libc_compat.h
create mode 100644 tools/lib/bpf/libbpf_errno.c
--
2.17.1
^ permalink raw reply
* Re: [PATCH net-next v2 02/10] r8169: use phy_resume/phy_suspend
From: Heiner Kallweit @ 2018-07-10 21:42 UTC (permalink / raw)
To: Andrew Lunn
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <20180710205247.GI892@lunn.ch>
On 10.07.2018 22:52, Andrew Lunn wrote:
>>> Why is it powered up, but not connected? Is it powered down before it
>>> is disconnected? Is it the bootloader which is powering it up?
>>>
>> Exactly, if the device is active when driver is loaded and the
>> interface isn't used and therefore not brought up, then, when runtime-
>> suspending, we face this situation.
>
> Well, it is more complex than that. If the interface is not used, why
> bother even loading the MAC driver?
>
It would be nice to be able to detect at driver load time whether
interface is used. But driver loading is based on existence of the
PCI device and we don't know about any netctl- or whatever-based
network configuration.
> If you are trying to make a really low power system, the bootloader
> also needs to be involved. It needs to shut down anything it starts
> before handing over control the linux.
>
I agree but in most cases wed don't have any influence on the
bootloader / BIOS.
> Another approach is to handle this in phylib. When the mdio bus is
> suspended, look for any PHYs which are not connected and power them
> down. The assumption being, any MAC driver using WoL via a PHY does
> not disconnect the PHY before suspending.
>
> Andrew
>
^ permalink raw reply
* Re: [PATCH net-next v2 07/10] r8169: migrate speed_down function to phylib
From: Andrew Lunn @ 2018-07-10 21:40 UTC (permalink / raw)
To: Heiner Kallweit
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <33b9c24f-99af-2029-8cd6-3811611af330@gmail.com>
On Tue, Jul 10, 2018 at 11:26:13PM +0200, Heiner Kallweit wrote:
> On 10.07.2018 22:44, Andrew Lunn wrote:
> >> static void rtl_speed_down(struct rtl8169_private *tp)
> >> {
> >> - u32 adv;
> >> - int lpa;
> >> + struct phy_device *phydev = tp->dev->phydev;
> >> + u32 adv = phydev->lp_advertising & phydev->supported;
> >>
> >> - rtl_writephy(tp, 0x1f, 0x0000);
> >> - lpa = rtl_readphy(tp, MII_LPA);
> >> + if (adv & BASET10)
> >> + phydev->advertising &= ~(BASET100 | BASET1000);
> >> + else if (adv & BASET100)
> >> + phydev->advertising &= ~BASET1000;
> >
> > Please use phy_set_max_speed(). We need MAC drivers to stop directly
> > accessing phydev members. Otherwise we are going to have problems
> > supporting 2.5G PHYs.
> >
> The issue I see with phy_set_max_speed() is that it also adjusts
> phydev->supported and I don't think that's what we want.
> What the chip supports doesn't change, just what we want to
> advertise.
True.
Which is one more reason to do it inside phylib.
Andrew
^ permalink raw reply
* Re: [PATCH net-next v2 09/10] r8169: remove mii_if_info member from struct rtl8169_private
From: Andrew Lunn @ 2018-07-10 21:37 UTC (permalink / raw)
To: Heiner Kallweit
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <8b78b589-3d6c-65f4-d39a-2ce708af8220@gmail.com>
On Tue, Jul 10, 2018 at 11:32:36PM +0200, Heiner Kallweit wrote:
> On 10.07.2018 23:00, Andrew Lunn wrote:
> >> @@ -6719,7 +6703,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
> >> if (ret)
> >> return ret;
> >>
> >> - if (!tp->mii.supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
> >> + if (!tp->supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
> >
> > It is better to use phy_set_max_speed() with SPEED_100 if
> > tp->supports_gmii is not set.
> >
> Then the info message wouldn't fit any longer, it's meaningful in case
> 1GBit PHY + 100MBit MAC only.
What you should avoid is this part:
phydev->supported & PHY_1000BT_FEATURES
Because phydev->supported is going to go away sometime soon.
Does anybody care about knowing they have a 1Gbit PHY connected to the
100Mbit MAC? So long as it works, i think not.
Andrew
^ permalink raw reply
* Re: [PATCH net-next v2 09/10] r8169: remove mii_if_info member from struct rtl8169_private
From: Andrew Lunn @ 2018-07-10 21:00 UTC (permalink / raw)
To: Heiner Kallweit
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <aaa67fd8-9039-0786-96fa-0803db280c97@gmail.com>
> @@ -6719,7 +6703,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
> if (ret)
> return ret;
>
> - if (!tp->mii.supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
> + if (!tp->supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
It is better to use phy_set_max_speed() with SPEED_100 if
tp->supports_gmii is not set.
Andrew
^ permalink raw reply
* Re: [PATCH net-next v2 09/10] r8169: remove mii_if_info member from struct rtl8169_private
From: Heiner Kallweit @ 2018-07-10 21:32 UTC (permalink / raw)
To: Andrew Lunn
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <20180710210036.GK892@lunn.ch>
On 10.07.2018 23:00, Andrew Lunn wrote:
>> @@ -6719,7 +6703,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
>> if (ret)
>> return ret;
>>
>> - if (!tp->mii.supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
>> + if (!tp->supports_gmii && phydev->supported & PHY_1000BT_FEATURES) {
>
> It is better to use phy_set_max_speed() with SPEED_100 if
> tp->supports_gmii is not set.
>
Then the info message wouldn't fit any longer, it's meaningful in case
1GBit PHY + 100MBit MAC only.
> Andrew
>
^ permalink raw reply
* [PATCH bpf v2 1/1] bpf: btf: Fix bitfield extraction for big endian
From: Okash Khawaja @ 2018-07-10 21:33 UTC (permalink / raw)
To: Daniel Borkmann, Martin KaFai Lau, Alexei Starovoitov,
Yonghong Song, Jakub Kicinski, David S. Miller
Cc: netdev, kernel-team, linux-kernel
In-Reply-To: <20180710213306.646146378@fb.com>
[-- Attachment #1: fix-btf-bitfields.patch --]
[-- Type: text/plain, Size: 2221 bytes --]
When extracting bitfield from a number, btf_int_bits_seq_show() builds
a mask and accesses least significant byte of the number in a way
specific to little-endian. This patch fixes that by checking endianness
of the machine and then shifting left and right the unneeded bits.
Thanks to Martin Lau for the help in navigating potential pitfalls when
dealing with endianess and for the final solution.
Fixes: b00b8daec828 ("bpf: btf: Add pretty print capability for data with BTF type info")
Signed-off-by: Okash Khawaja <osk@fb.com>
---
kernel/bpf/btf.c | 30 +++++++++++++-----------------
1 file changed, 13 insertions(+), 17 deletions(-)
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -991,16 +991,13 @@ static void btf_int_bits_seq_show(const
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
u16 nr_bits = BTF_INT_BITS(int_data);
u16 total_bits_offset;
u16 nr_copy_bytes;
u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u64 print_num;
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
@@ -1008,21 +1005,20 @@ static void btf_int_bits_seq_show(const
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- print_num.u64_num >>= bits_offset;
-
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
^ permalink raw reply
* [PATCH bpf v2 0/1] bpf: btf: Fix endianness of bitfields
From: Okash Khawaja @ 2018-07-10 21:33 UTC (permalink / raw)
To: Daniel Borkmann, Martin KaFai Lau, Alexei Starovoitov,
Yonghong Song, Jakub Kicinski, David S. Miller
Cc: netdev, kernel-team, linux-kernel
Hi,
Following are the changes from v1:
- use compile time check for endianness
- factor out right_shift_bits from the check as it is same in both
- change size of bit shift variables to match length of bit offset in
BTF specification
Please note that I have considered non-big endians to be little endians
for our purposes. Let me know if you think that's a problem. We need to
then decide what to do in case neither of macros are defined.
Thanks,
Okash
^ permalink raw reply
* [PATCH] tcp: allow user to create repair socket without window probes
From: Stefan Baranoff @ 2018-07-10 21:31 UTC (permalink / raw)
To: netdev
Cc: Andrey Vagin, Pavel Emelyanov, Stefan Baranoff, Eric Dumazet,
David S. Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI
Under rare conditions where repair code may be used it is possible that
window probes are either unnecessary or undesired. If the user knows that
window probes are not wanted or needed this change allows them to skip
sending them when a socket comes out of repair.
Signed-off-by: Stefan Baranoff <sbaranoff@gmail.com>
---
net/ipv4/tcp.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e7b53d2a..728ae7a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2821,14 +2821,16 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_REPAIR:
if (!tcp_can_repair_sock(sk))
err = -EPERM;
- else if (val == 1) {
- tp->repair = 1;
+ /* 1 for normal repair, 2 for no window probes */
+ else if (val == 1 || val == 2) {
+ tp->repair = val;
sk->sk_reuse = SK_FORCE_REUSE;
tp->repair_queue = TCP_NO_QUEUE;
} else if (val == 0) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
- tcp_send_window_probe(sk);
+ if (tp->repair == 1)
+ tcp_send_window_probe(sk);
} else
err = -EINVAL;
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH bpf-next v2 11/12] tools: libbpf: allow map reuse
From: Jakub Kicinski @ 2018-07-10 20:58 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: Andrey Ignatov, alexei.starovoitov, oss-drivers, netdev
In-Reply-To: <8389fcac-0e05-71c2-707f-447260b8bf91@iogearbox.net>
On Tue, 10 Jul 2018 20:16:46 +0200, Daniel Borkmann wrote:
> On 07/10/2018 08:09 PM, Jakub Kicinski wrote:
> > On Mon, 9 Jul 2018 21:23:20 -0700, Andrey Ignatov wrote:
> >> Jakub Kicinski <jakub.kicinski@netronome.com> [Mon, 2018-07-09 19:49 -0700]:
> >>> On Mon, 9 Jul 2018 13:22:54 -0700, Andrey Ignatov wrote:
> >>>> Jakub Kicinski <jakub.kicinski@netronome.com> [Mon, 2018-07-09 11:01 -0700]:
> >>>>> + map->fd = dup(fd);
> >>>>
> >>>> Unfortunately, new descriptor created by dup(2) will not have O_CLOEXEC set, in
> >>>> contrast to original fd returned by kernel on map creation.
> >>>>
> >>>> libbpf has other interface shortcomings where it comes up. E.g. struct
> >>>> bpf_object owns all descriptors it contains (progs, maps) and closes them in
> >>>> bpf_object__close(). if one wants to open/load ELF, then close it but
> >>>> keep, say, prog fd to attach it to cgroup some time later, then fd
> >>>> should be duplicated as well to get a new one not owned by bpf_object.
> >>>>
> >>>> Currently I use this workaround to avoid time when new fd doesn't have
> >>>> O_CLOEXEC:
> >>>>
> >>>> int new_prog_fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
> >>>> if (new_prog_fd < 0 ||
> >>>> dup3(bpf_program__fd(prog), new_prog_fd, O_CLOEXEC) == -1) {
> >>>> /* .. handle error .. */
> >>>> close(new_prog_fd);
> >>>> }
> >>>> /* .. use new_prog_fd with O_CLOEXEC set */
> >>>>
> >>>> Not sure how to simplify it. dup2() has same problem with regard to
> >>>> O_CLOEXEC.
> >>>>
> >>>> Use-case: standalone server application that uses libbpf and does
> >>>> fork()/execve() a lot.
> >>>
> >>> Good point! I have no better ideas. Although being slightly paranoid
> >>> I would perhaps use "/" instead of "/dev/null"? Shouldn't matter?
> >>
> >> No strong preferences, important thing is to create fd with O_CLOEXEC
> >> set somehow.
> >>
> >> Is it safer to use "/" than "/dev/null"? (trying to understand if I
> >> should change my code as well)
> >
> > IDK :) Could there be a crazy scenario when someone runs chroot or a
> > very broken system without /dev/null? / should always be there?
> >
> > Thanks for all the other reviews, I will update the code accordingly!
Oh no, dup3() is under _GNU_SOURCE as well. libbpf kind of depends
on XSI-compliant strerror_r() semantics, I think I'll have to move the
strerror_r()-dependent code out of the libbpf.c file :(
> Ok, I've tossed the v2 series from patchwork and waiting for your respin
> in that case.
Yes, thank you!
^ permalink raw reply
* Re: [PATCH net-next v2 07/10] r8169: migrate speed_down function to phylib
From: Heiner Kallweit @ 2018-07-10 21:26 UTC (permalink / raw)
To: Andrew Lunn
Cc: David Miller, Florian Fainelli, Realtek linux nic maintainers,
netdev@vger.kernel.org
In-Reply-To: <20180710204407.GH892@lunn.ch>
On 10.07.2018 22:44, Andrew Lunn wrote:
>> static void rtl_speed_down(struct rtl8169_private *tp)
>> {
>> - u32 adv;
>> - int lpa;
>> + struct phy_device *phydev = tp->dev->phydev;
>> + u32 adv = phydev->lp_advertising & phydev->supported;
>>
>> - rtl_writephy(tp, 0x1f, 0x0000);
>> - lpa = rtl_readphy(tp, MII_LPA);
>> + if (adv & BASET10)
>> + phydev->advertising &= ~(BASET100 | BASET1000);
>> + else if (adv & BASET100)
>> + phydev->advertising &= ~BASET1000;
>
> Please use phy_set_max_speed(). We need MAC drivers to stop directly
> accessing phydev members. Otherwise we are going to have problems
> supporting 2.5G PHYs.
>
The issue I see with phy_set_max_speed() is that it also adjusts
phydev->supported and I don't think that's what we want.
What the chip supports doesn't change, just what we want to
advertise.
> Andrew
>
^ permalink raw reply
* [PATCH] tcp: fix sequence numbers for repaired sockets re-using TIME-WAIT sockets
From: Stefan Baranoff @ 2018-07-10 21:25 UTC (permalink / raw)
To: netdev
Cc: Andrey Vagin, Pavel Emelyanov, Stefan Baranoff, Eric Dumazet,
David S. Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI
This patch fixes a bug where the sequence numbers of a socket created using
TCP repair functionality are lower than set after connect is called.
This occurs when the repair socket overlaps with a TIME-WAIT socket and
triggers the re-use code. The amount lower is equal to the number of times
that a particular IP/port set is re-used and then put back into TIME-WAIT.
Re-using the first time the sequence number is 1 lower, closing that socket
and then re-opening (with repair) a new socket with the same addresses/ports
puts the sequence number 2 lower than set via setsockopt. The third time is
3 lower, etc. I have not tested what the limit of this acrewal is, if any.
The fix is, if a socket is in repair mode, to respect the already set
sequence number and timestamp when it would have already re-used the
TIME-WAIT socket.
Signed-off-by: Stefan Baranoff <sbaranoff@gmail.com>
---
net/ipv4/tcp_ipv4.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bea17f1..3b2711e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
*/
if (tcptw->tw_ts_recent_stamp &&
(!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
- tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
- tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
- tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ /* In case of repair and re-using TIME-WAIT sockets we still
+ * want to be sure that it is safe as above but honor the
+ * sequence numbers and time stamps set as part of the repair
+ * process.
+ *
+ * Without this check re-using a TIME-WAIT socket with TCP
+ * repair would accumulate a -1 on the repair assigned
+ * sequence number. The first time it is reused the sequence
+ * is -1, the second time -2, etc. This fixes that issue
+ * without appearing to create any others.
+ */
+ if (likely(!tp->repair)) {
+ tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+ if (tp->write_seq == 0)
+ tp->write_seq = 1;
+ tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+ tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ }
sock_hold(sktw);
return 1;
}
--
1.8.3.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox