From 2058b38371d0dbd84831a085db64b996d623f81a Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 6 Jul 2018 14:28:14 -0700 Subject: bpftool: introduce cgroup tree command This commit introduces a new bpftool command: cgroup tree. The idea is to iterate over the whole cgroup tree and print all attached programs. I was debugging a bpf/systemd issue, and found, that there is no simple way to listen all bpf programs attached to cgroups. I did master something in bash, but after some time got tired of it, and decided, that adding a dedicated bpftool command could be a better idea. So, here it is: $ sudo ./bpftool cgroup tree CgroupPath ID AttachType AttachFlags Name /sys/fs/cgroup/system.slice/systemd-machined.service 18 ingress 17 egress /sys/fs/cgroup/system.slice/systemd-logind.service 20 ingress 19 egress /sys/fs/cgroup/system.slice/systemd-udevd.service 16 ingress 15 egress /sys/fs/cgroup/system.slice/systemd-journald.service 14 ingress 13 egress Signed-off-by: Roman Gushchin Acked-by: Jakub Kicinski Cc: Quentin Monnet Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/cgroup.c | 170 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 165 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 16bee011e16c..ee7a9765c6b3 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -2,7 +2,12 @@ // Copyright (C) 2017 Facebook // Author: Roman Gushchin +#define _XOPEN_SOURCE 500 +#include #include +#include +#include +#include #include #include #include @@ -53,7 +58,8 @@ static enum bpf_attach_type parse_attach_type(const char *str) } static int show_bpf_prog(int id, const char *attach_type_str, - const char *attach_flags_str) + const char *attach_flags_str, + int level) { struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); @@ -78,7 +84,8 @@ static int show_bpf_prog(int id, const char *attach_type_str, jsonw_string_field(json_wtr, "name", info.name); jsonw_end_object(json_wtr); } else { - printf("%-8u %-15s %-15s %-15s\n", info.id, + printf("%s%-8u %-15s %-15s %-15s\n", level ? " " : "", + info.id, attach_type_str, attach_flags_str, info.name); @@ -88,7 +95,20 @@ static int show_bpf_prog(int id, const char *attach_type_str, return 0; } -static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) +static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) +{ + __u32 prog_cnt = 0; + int ret; + + ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + if (ret) + return -1; + + return prog_cnt; +} + +static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) { __u32 prog_ids[1024] = {0}; char *attach_flags_str; @@ -123,7 +143,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) for (iter = 0; iter < prog_cnt; iter++) show_bpf_prog(prog_ids[iter], attach_type_strings[type], - attach_flags_str); + attach_flags_str, level); return 0; } @@ -161,7 +181,7 @@ static int do_show(int argc, char **argv) * If we were able to get the show for at least one * attach type, let's return 0. */ - if (show_attached_bpf_progs(cgroup_fd, type) == 0) + if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0) ret = 0; } @@ -173,6 +193,143 @@ exit: return ret; } +/* + * To distinguish nftw() errors and do_show_tree_fn() errors + * and avoid duplicating error messages, let's return -2 + * from do_show_tree_fn() in case of error. + */ +#define NFTW_ERR -1 +#define SHOW_TREE_FN_ERR -2 +static int do_show_tree_fn(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftw) +{ + enum bpf_attach_type type; + bool skip = true; + int cgroup_fd; + + if (typeflag != FTW_D) + return 0; + + cgroup_fd = open(fpath, O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s: %s", fpath, strerror(errno)); + return SHOW_TREE_FN_ERR; + } + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + int count = count_attached_bpf_progs(cgroup_fd, type); + + if (count < 0 && errno != EINVAL) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } + if (count > 0) { + skip = false; + break; + } + } + + if (skip) { + close(cgroup_fd); + return 0; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "cgroup", fpath); + jsonw_name(json_wtr, "programs"); + jsonw_start_array(json_wtr); + } else { + printf("%s\n", fpath); + } + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) + show_attached_bpf_progs(cgroup_fd, type, ftw->level); + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + + close(cgroup_fd); + + return 0; +} + +static char *find_cgroup_root(void) +{ + struct mntent *mnt; + FILE *f; + + f = fopen("/proc/mounts", "r"); + if (f == NULL) + return NULL; + + while ((mnt = getmntent(f))) { + if (strcmp(mnt->mnt_type, "cgroup2") == 0) { + fclose(f); + return strdup(mnt->mnt_dir); + } + } + + fclose(f); + return NULL; +} + +static int do_show_tree(int argc, char **argv) +{ + char *cgroup_root; + int ret; + + switch (argc) { + case 0: + cgroup_root = find_cgroup_root(); + if (!cgroup_root) { + p_err("cgroup v2 isn't mounted"); + return -1; + } + break; + case 1: + cgroup_root = argv[0]; + break; + default: + p_err("too many parameters for cgroup tree"); + return -1; + } + + + if (json_output) + jsonw_start_array(json_wtr); + else + printf("%s\n" + "%-8s %-15s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "AttachFlags", "Name"); + + switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) { + case NFTW_ERR: + p_err("can't iterate over %s: %s", cgroup_root, + strerror(errno)); + ret = -1; + break; + case SHOW_TREE_FN_ERR: + ret = -1; + break; + default: + ret = 0; + } + + if (json_output) + jsonw_end_array(json_wtr); + + if (argc == 0) + free(cgroup_root); + + return ret; +} + static int do_attach(int argc, char **argv) { enum bpf_attach_type attach_type; @@ -289,6 +446,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } CGROUP\n" + " %s %s tree [CGROUP_ROOT]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" @@ -298,6 +456,7 @@ static int do_help(int argc, char **argv) " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); @@ -307,6 +466,7 @@ static int do_help(int argc, char **argv) static const struct cmd cmds[] = { { "show", do_show }, { "list", do_show }, + { "tree", do_show_tree }, { "attach", do_attach }, { "detach", do_detach }, { "help", do_help }, -- cgit v1.2.3 From 7d31a0a168979e671e25073c492c29c42610e7e2 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 6 Jul 2018 14:28:15 -0700 Subject: bpftool: document cgroup tree command Describe cgroup tree command in the corresponding bpftool man page. Signed-off-by: Roman Gushchin Acked-by: Jakub Kicinski Cc: Quentin Monnet Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 7b0e6d453e92..edbe81534c6d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -15,12 +15,13 @@ SYNOPSIS *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } *COMMANDS* := - { **show** | **list** | **attach** | **detach** | **help** } + { **show** | **list** | **tree** | **attach** | **detach** | **help** } MAP COMMANDS ============= | **bpftool** **cgroup { show | list }** *CGROUP* +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* | **bpftool** **cgroup help** @@ -39,6 +40,15 @@ DESCRIPTION Output will start with program ID followed by attach type, attach flags and program name. + **bpftool cgroup tree** [*CGROUP_ROOT*] + Iterate over all cgroups in *CGROUP_ROOT* and list all + attached programs. If *CGROUP_ROOT* is not specified, + bpftool uses cgroup v2 mountpoint. + + The output is similar to the output of cgroup show/list + commands: it starts with absolute cgroup path, followed by + program ID, attach type, attach flags and program name. + **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* and optional *ATTACH_FLAGS*. -- cgit v1.2.3 From 02000b55850deeadffe433e4b4930a8831f477de Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 6 Jul 2018 14:28:16 -0700 Subject: bpftool: add bash completion for cgroup tree command This commit adds a bash completion to the bpftool cgroup tree command. Signed-off-by: Roman Gushchin Cc: Jakub Kicinski Cc: Quentin Monnet Cc: Daniel Borkmann Cc: Alexei Starovoitov Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/bash-completion/bpftool | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index fffd76f4998b..ce0bc0cda361 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -414,6 +414,10 @@ _bpftool() _filedir return 0 ;; + tree) + _filedir + return 0 + ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ @@ -455,7 +459,7 @@ _bpftool() *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'help attach detach \ - show list' -- "$cur" ) ) + show list tree' -- "$cur" ) ) ;; esac ;; -- cgit v1.2.3 From 7479efc71f6da5fde6c67d91380ebc0fb455c53d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:42:55 -0700 Subject: selftests/bpf: remove duplicated word from test offloads Trivial removal of duplicated "mode" in error message. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_offload.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') 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 @@ try: 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...") -- cgit v1.2.3 From 219f860d2a11b285ac2e880ca4a73e0d36811c0c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:42:56 -0700 Subject: selftests/bpf: add Error: prefix in check_extack helper 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 Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_offload.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'tools') 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 @@ def check_extack(output, reference, args): 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 @@ try: 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 @@ try: 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...") -- cgit v1.2.3 From 8d1fc3de3d9f9bda0d8ec719d8686e9c5b432573 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:42:57 -0700 Subject: tools: bpftool: refactor argument parsing for prog load 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 Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.h | 15 +++++++++++++++ tools/bpf/bpftool/prog.c | 11 +++++++---- 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'tools') 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) -- cgit v1.2.3 From ba6dd679a3e81af023ec091c2fb7c82003a27316 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:42:58 -0700 Subject: tools: bpftool: add support for loading programs for offload 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 Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/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(-) (limited to 'tools') 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 #include #include +#include #include #include @@ -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" -- cgit v1.2.3 From b60df2a0e11fcd24186c312b0307ab8494031e27 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:42:59 -0700 Subject: tools: libbpf: expose the prog type guessing from section name logic 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 Reviewed-by: Quentin Monnet Acked-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 43 +++++++++++++++++++++++++------------------ tools/lib/bpf/libbpf.h | 3 +++ 2 files changed, 28 insertions(+), 18 deletions(-) (limited to 'tools') 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, -- cgit v1.2.3 From 49f2cba3e57a4d71e3e7001cc2934b563ee495f4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:00 -0700 Subject: tools: bpftool: allow users to specify program type for prog load 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 Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/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(-) (limited to 'tools') 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], -- cgit v1.2.3 From f83fb22c6c68fdbc98c76291c9e12a40d1eb7ca5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:01 -0700 Subject: tools: libbpf: recognize offload neutral maps 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 Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 8 +++++++- tools/lib/bpf/libbpf.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'tools') 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); -- cgit v1.2.3 From 07f2d4eac2a850fc9649b27aa935cdcd263fb1ff Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:02 -0700 Subject: tools: libbpf: add extended attributes version of bpf_object__open() 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 Reviewed-by: Quentin Monnet Acked-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 26 ++++++++++++++++++++------ tools/lib/bpf/libbpf.h | 6 ++++++ 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'tools') 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 @@ out: 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); -- cgit v1.2.3 From c8406848badd0a0b040b0d286e612678662a2ab3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:03 -0700 Subject: tools: bpftool: reimplement bpf_prog_load() for prog load 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 Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/prog.c | 61 +++++++++++++++++++++++++++++++++++++----------- 1 file changed, 48 insertions(+), 13 deletions(-) (limited to 'tools') 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 #include +#include + #include #include @@ -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) -- cgit v1.2.3 From 8d13406c02f9c38f106416e1dbe0e68059b9f59a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:04 -0700 Subject: tools: libbpf: move library error code into a separate file 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 Signed-off-by: Daniel Borkmann --- 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 (limited to 'tools') 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 + * Copyright (C) 2015 Wang Nan + * 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 + */ + +#include +#include + +#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; +} -- cgit v1.2.3 From 531b014e7a2fedaeff0b19b2934d830cd4b35dc0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:05 -0700 Subject: tools: bpf: make use of reallocarray 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 Reviewed-by: Quentin Monnet Reviewed-by: Jiong Wang Signed-off-by: Daniel Borkmann --- 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 (limited to 'tools') 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 #include #include +#include #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 #include #include @@ -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 @@ $(OUTPUT)test-libbfd.bin: $(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 + +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 + +/* + * 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 +#include + +#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 */ +#define _GNU_SOURCE #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include @@ -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; -- cgit v1.2.3 From 26736eb9a483715c2e971a8866f55fbb156903e2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:06 -0700 Subject: tools: libbpf: allow map reuse 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 Reviewed-by: Quentin Monnet Acked-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 1 + 2 files changed, 54 insertions(+) (limited to 'tools') 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); -- cgit v1.2.3 From 3ff5a4dc5d890963e669fc99cc62ee07d1da24e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jul 2018 14:43:07 -0700 Subject: tools: bpftool: allow reuse of maps with bpftool prog load 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 Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/bpf/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(-) (limited to 'tools') 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 #include #include @@ -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" -- cgit v1.2.3 From 9b8ca3795199f333269859b0c8393f810b9616a3 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 12 Jul 2018 12:52:23 +0100 Subject: tools: bpf: synchronise BPF UAPI header with tools Update with latest changes from include/uapi/linux/bpf.h header. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 59b19b6a40d7..6bcb287a888d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1826,7 +1826,7 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * - * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) * Description * This helper is similar to **bpf_skb_load_bytes**\ () in that * it provides an easy way to load *len* bytes from *offset* @@ -1857,7 +1857,8 @@ union bpf_attr { * is resolved), the nexthop address is returned in ipv4_dst * or ipv6_dst based on family, smac is set to mac address of * egress device, dmac is set to nexthop mac address, rt_metric - * is set to metric from route (IPv4/IPv6 only). + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. * * *plen* argument is the size of the passed in struct. * *flags* argument can be a combination of one or more of the @@ -1873,9 +1874,10 @@ union bpf_attr { * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. * Return - * Egress device index on success, 0 if packet needs to continue - * up the stack for further processing or a negative error in case - * of failure. + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2031,7 +2033,6 @@ union bpf_attr { * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". - * * Return * 0 * @@ -2051,7 +2052,6 @@ union bpf_attr { * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". - * * Return * 0 * @@ -2612,6 +2612,18 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_DIRECT BIT(0) #define BPF_FIB_LOOKUP_OUTPUT BIT(1) +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + struct bpf_fib_lookup { /* input: network family for lookup (AF_INET, AF_INET6) * output: network family of egress nexthop @@ -2625,7 +2637,11 @@ struct bpf_fib_lookup { /* total length of packet from network header - used for MTU check */ __u16 tot_len; - __u32 ifindex; /* L3 device index for lookup */ + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; union { /* inputs to lookup */ -- cgit v1.2.3 From 86f7d85cec9e1dba735ac5bd4b751b1908fedf80 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 12 Jul 2018 12:52:24 +0100 Subject: tools: bpf: build and install man page for eBPF helpers from bpftool/ Provide a new Makefile.helpers in tools/bpf, in order to build and install the man page for eBPF helpers. This Makefile is also included in the one used to build bpftool documentation, so that it can be called either on its own (cd tools/bpf && make -f Makefile.helpers) or from bpftool directory (cd tools/bpf/bpftool && make doc, or cd tools/bpf/bpftool/Documentation && make helpers). Makefile.helpers is not added directly to bpftool to avoid changing its Makefile too much (helpers are not 100% directly related with bpftool). But the possibility to build the page from bpftool directory makes us able to package the helpers man page with bpftool, and to install it along with bpftool documentation, so that the doc for helpers becomes easily available to developers through the "man" program. Cc: linux-man@vger.kernel.org Suggested-by: Daniel Borkmann Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/Makefile.helpers | 59 ++++++++++++++++++++++++++++++++ tools/bpf/bpftool/Documentation/Makefile | 13 ++++--- 2 files changed, 67 insertions(+), 5 deletions(-) create mode 100644 tools/bpf/Makefile.helpers (limited to 'tools') diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers new file mode 100644 index 000000000000..c34fea77f39f --- /dev/null +++ b/tools/bpf/Makefile.helpers @@ -0,0 +1,59 @@ +ifndef allow-override + include ../scripts/Makefile.include + include ../scripts/utilities.mak +else + # Assume Makefile.helpers is being run from bpftool/Documentation + # subdirectory. Go up two more directories to fetch bpf.h header and + # associated script. + UP2DIR := ../../ +endif + +INSTALL ?= install +RM ?= rm -f +RMDIR ?= rmdir --ignore-fail-on-non-empty + +ifeq ($(V),1) + Q = +else + Q = @ +endif + +prefix ?= /usr/local +mandir ?= $(prefix)/man +man7dir = $(mandir)/man7 + +HELPERS_RST = bpf-helpers.rst +MAN7_RST = $(HELPERS_RST) + +_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST)) +DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7)) + +helpers: man7 +man7: $(DOC_MAN7) + +RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) + +$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h + $(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@ + +$(OUTPUT)%.7: $(OUTPUT)%.rst +ifndef RST2MAN_DEP + $(error "rst2man not found, but required to generate man pages") +endif + $(QUIET_GEN)rst2man $< > $@ + +helpers-clean: + $(call QUIET_CLEAN, eBPF_helpers-manpage) + $(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST) + +helpers-install: helpers + $(call QUIET_INSTALL, eBPF_helpers-manpage) + $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir) + $(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) + +helpers-uninstall: + $(call QUIET_UNINST, eBPF_helpers-manpage) + $(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7)) + $(Q)$(RMDIR) $(DESTDIR)$(man7dir) + +.PHONY: helpers helpers-clean helpers-install helpers-uninstall diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index a9d47c1558bb..f7663a3e60c9 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -15,12 +15,15 @@ prefix ?= /usr/local mandir ?= $(prefix)/man man8dir = $(mandir)/man8 -MAN8_RST = $(wildcard *.rst) +# Load targets for building eBPF helpers man page. +include ../../Makefile.helpers + +MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst)) _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) -man: man8 +man: man8 helpers man8: $(DOC_MAN8) RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) @@ -31,16 +34,16 @@ ifndef RST2MAN_DEP endif $(QUIET_GEN)rst2man $< > $@ -clean: +clean: helpers-clean $(call QUIET_CLEAN, Documentation) $(Q)$(RM) $(DOC_MAN8) -install: man +install: man helpers-install $(call QUIET_INSTALL, Documentation-man) $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir) $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir) -uninstall: +uninstall: helpers-uninstall $(call QUIET_UNINST, Documentation-man) $(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8)) $(Q)$(RMDIR) $(DESTDIR)$(man8dir) -- cgit v1.2.3 From 05296620f6d14dce0030b87e1e57891a770fb65c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:40 -0700 Subject: xdp: factor out common program/flags handling from drivers Basic operations drivers perform during xdp setup and query can be moved to helpers in the core. Encapsulate program and flags into a structure and add helpers. Note that the structure is intended as the "main" program information source in the driver. Most drivers will additionally place the program pointer in their fast path or ring structures. The helpers don't have a huge impact now, but they will decrease the code duplication when programs can be installed in HW and driver at the same time. Encapsulating the basic operations in helpers will hopefully also reduce the number of changes to drivers which adopt them. Helpers could really be static inline, but they depend on definition of struct netdev_bpf which means they'd have to be placed in netdevice.h, an already 4500 line header. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 6 ++-- .../net/ethernet/netronome/nfp/nfp_net_common.c | 28 +++++++----------- drivers/net/netdevsim/bpf.c | 16 +++------- drivers/net/netdevsim/netdevsim.h | 4 +-- include/net/xdp.h | 13 +++++++++ net/core/xdp.c | 34 ++++++++++++++++++++++ tools/testing/selftests/bpf/test_offload.py | 4 +-- 7 files changed, 67 insertions(+), 38 deletions(-) (limited to 'tools') diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 2a71a9ffd095..2021dda595b7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -553,8 +553,7 @@ struct nfp_net_dp { * @rss_cfg: RSS configuration * @rss_key: RSS secret key * @rss_itbl: RSS indirection table - * @xdp_flags: Flags with which XDP prog was loaded - * @xdp_prog: XDP prog (for ctrl path, both DRV and HW modes) + * @xdp: Information about the attached XDP program * @max_r_vecs: Number of allocated interrupt vectors for RX/TX * @max_tx_rings: Maximum number of TX rings supported by the Firmware * @max_rx_rings: Maximum number of RX rings supported by the Firmware @@ -610,8 +609,7 @@ struct nfp_net { u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ]; u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ]; - u32 xdp_flags; - struct bpf_prog *xdp_prog; + struct xdp_attachment_info xdp; unsigned int max_tx_rings; unsigned int max_rx_rings; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index d20714598613..4bb589dbffbc 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3417,34 +3417,29 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog, return nfp_net_ring_reconfig(nn, dp, extack); } -static int -nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags, - struct netlink_ext_ack *extack) +static int nfp_net_xdp_setup(struct nfp_net *nn, struct netdev_bpf *bpf) { struct bpf_prog *drv_prog, *offload_prog; int err; - if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES) + if (!xdp_attachment_flags_ok(&nn->xdp, bpf)) return -EBUSY; /* Load both when no flags set to allow easy activation of driver path * when program is replaced by one which can't be offloaded. */ - drv_prog = flags & XDP_FLAGS_HW_MODE ? NULL : prog; - offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog; + drv_prog = bpf->flags & XDP_FLAGS_HW_MODE ? NULL : bpf->prog; + offload_prog = bpf->flags & XDP_FLAGS_DRV_MODE ? NULL : bpf->prog; - err = nfp_net_xdp_setup_drv(nn, drv_prog, extack); + err = nfp_net_xdp_setup_drv(nn, drv_prog, bpf->extack); if (err) return err; - err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack); - if (err && flags & XDP_FLAGS_HW_MODE) + err = nfp_app_xdp_offload(nn->app, nn, offload_prog, bpf->extack); + if (err && bpf->flags & XDP_FLAGS_HW_MODE) return err; - if (nn->xdp_prog) - bpf_prog_put(nn->xdp_prog); - nn->xdp_prog = prog; - nn->xdp_flags = flags; + xdp_attachment_setup(&nn->xdp, bpf); return 0; } @@ -3456,12 +3451,9 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: case XDP_SETUP_PROG_HW: - return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags, - xdp->extack); + return nfp_net_xdp_setup(nn, xdp); case XDP_QUERY_PROG: - xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0; - xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0; - return 0; + return xdp_attachment_query(&nn->xdp, xdp); default: return nfp_app_bpf(nn->app, nn, xdp); } diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 712e6f918065..c485d97b5df4 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -199,10 +199,8 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) { int err; - if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) { - NSIM_EA(bpf->extack, "program loaded with different flags"); + if (!xdp_attachment_flags_ok(&ns->xdp, bpf)) return -EBUSY; - } if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); @@ -219,11 +217,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) return err; } - if (ns->xdp_prog) - bpf_prog_put(ns->xdp_prog); - - ns->xdp_prog = bpf->prog; - ns->xdp_flags = bpf->flags; + xdp_attachment_setup(&ns->xdp, bpf); if (!bpf->prog) ns->xdp_prog_mode = XDP_ATTACHED_NONE; @@ -567,9 +561,7 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) nsim_bpf_destroy_prog(bpf->offload.prog); return 0; case XDP_QUERY_PROG: - bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0; - bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0; - return 0; + return xdp_attachment_query(&ns->xdp, bpf); case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); if (err) @@ -636,6 +628,6 @@ void nsim_bpf_uninit(struct netdevsim *ns) { WARN_ON(!list_empty(&ns->bpf_bound_progs)); WARN_ON(!list_empty(&ns->bpf_bound_maps)); - WARN_ON(ns->xdp_prog); + WARN_ON(ns->xdp.prog); WARN_ON(ns->bpf_offloaded); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index d8a7cc995e88..69ffb4a2d14b 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -18,6 +18,7 @@ #include #include #include +#include #define DRV_NAME "netdevsim" @@ -67,9 +68,8 @@ struct netdevsim { struct bpf_prog *bpf_offloaded; u32 bpf_offloaded_id; - u32 xdp_flags; + struct xdp_attachment_info xdp; int xdp_prog_mode; - struct bpf_prog *xdp_prog; u32 prog_id_gen; diff --git a/include/net/xdp.h b/include/net/xdp.h index 2deea7166a34..fcb033f51d8c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -144,4 +144,17 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) return unlikely(xdp->data_meta > xdp->data); } +struct xdp_attachment_info { + struct bpf_prog *prog; + u32 flags; +}; + +struct netdev_bpf; +int xdp_attachment_query(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); +bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); +void xdp_attachment_setup(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); + #endif /* __LINUX_NET_XDP_H__ */ diff --git a/net/core/xdp.c b/net/core/xdp.c index 31c58719b5a9..57285383ed00 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -3,8 +3,11 @@ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. * Released under terms in GPL version 2. See COPYING. */ +#include +#include #include #include +#include #include #include #include @@ -370,3 +373,34 @@ void xdp_return_buff(struct xdp_buff *xdp) __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle); } EXPORT_SYMBOL_GPL(xdp_return_buff); + +int xdp_attachment_query(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + bpf->prog_id = info->prog ? info->prog->aux->id : 0; + bpf->prog_flags = info->prog ? info->flags : 0; + return 0; +} +EXPORT_SYMBOL_GPL(xdp_attachment_query); + +bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { + NL_SET_ERR_MSG(bpf->extack, + "program loaded with different flags"); + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); + +void xdp_attachment_setup(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + if (info->prog) + bpf_prog_put(info->prog); + info->prog = bpf->prog; + info->flags = bpf->flags; +} +EXPORT_SYMBOL_GPL(xdp_attachment_setup); diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index f8d9bd81d9a4..40401e9e9351 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -821,7 +821,7 @@ try: ret, _, err = sim.set_xdp(obj, "", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack_nsim(err, "program loaded with different flags.", args) + check_extack(err, "program loaded with different flags.", args) start_test("Test XDP prog remove with bad flags...") ret, _, err = sim.unset_xdp("offload", force=True, @@ -831,7 +831,7 @@ try: ret, _, err = sim.unset_xdp("", force=True, fail=False, include_stderr=True) fail(ret == 0, "Removed program with a bad mode") - check_extack_nsim(err, "program loaded with different flags.", args) + check_extack(err, "program loaded with different flags.", args) start_test("Test MTU restrictions...") ret, _ = sim.set_mtu(9000, fail=False) -- cgit v1.2.3 From 799e173d7125155c00e9492c8212c5e41333049f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:42 -0700 Subject: netdevsim: add support for simultaneous driver and hw XDP Allow netdevsim to accept driver and offload attachment of XDP BPF programs at the same time. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- drivers/net/netdevsim/bpf.c | 32 +++++++++-------------------- drivers/net/netdevsim/netdev.c | 3 +-- drivers/net/netdevsim/netdevsim.h | 2 +- tools/testing/selftests/bpf/test_offload.py | 8 -------- 4 files changed, 12 insertions(+), 33 deletions(-) (limited to 'tools') diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 5544c9b51173..c36d2a768202 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -92,7 +92,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = { static bool nsim_xdp_offload_active(struct netdevsim *ns) { - return ns->xdp_prog_mode == XDP_ATTACHED_HW; + return ns->xdp_hw.prog; } static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded) @@ -195,11 +195,13 @@ static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf) return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns)); } -static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) +static int +nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, + struct xdp_attachment_info *xdp) { int err; - if (!xdp_attachment_flags_ok(&ns->xdp, bpf)) + if (!xdp_attachment_flags_ok(xdp, bpf)) return -EBUSY; if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { @@ -217,14 +219,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) return err; } - xdp_attachment_setup(&ns->xdp, bpf); - - if (!bpf->prog) - ns->xdp_prog_mode = XDP_ATTACHED_NONE; - else if (bpf->command == XDP_SETUP_PROG) - ns->xdp_prog_mode = XDP_ATTACHED_DRV; - else - ns->xdp_prog_mode = XDP_ATTACHED_HW; + xdp_attachment_setup(xdp, bpf); return 0; } @@ -284,10 +279,6 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf) NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled"); return -EINVAL; } - if (nsim_xdp_offload_active(ns)) { - NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog"); - return -EBUSY; - } return 0; } @@ -561,25 +552,21 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) nsim_bpf_destroy_prog(bpf->offload.prog); return 0; case XDP_QUERY_PROG: - if (ns->xdp_prog_mode != XDP_ATTACHED_DRV) - return 0; return xdp_attachment_query(&ns->xdp, bpf); case XDP_QUERY_PROG_HW: - if (ns->xdp_prog_mode != XDP_ATTACHED_HW) - return 0; - return xdp_attachment_query(&ns->xdp, bpf); + return xdp_attachment_query(&ns->xdp_hw, bpf); case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); if (err) return err; - return nsim_xdp_set_prog(ns, bpf); + return nsim_xdp_set_prog(ns, bpf, &ns->xdp); case XDP_SETUP_PROG_HW: err = nsim_setup_prog_hw_checks(ns, bpf); if (err) return err; - return nsim_xdp_set_prog(ns, bpf); + return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw); case BPF_OFFLOAD_MAP_ALLOC: if (!ns->bpf_map_accept) return -EOPNOTSUPP; @@ -635,5 +622,6 @@ void nsim_bpf_uninit(struct netdevsim *ns) WARN_ON(!list_empty(&ns->bpf_bound_progs)); WARN_ON(!list_empty(&ns->bpf_bound_maps)); WARN_ON(ns->xdp.prog); + WARN_ON(ns->xdp_hw.prog); WARN_ON(ns->bpf_offloaded); } diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index b2f9d0df93b0..a7b179f0d954 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -228,8 +228,7 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu) { struct netdevsim *ns = netdev_priv(dev); - if (ns->xdp_prog_mode == XDP_ATTACHED_DRV && - new_mtu > NSIM_XDP_MAX_MTU) + if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU) return -EBUSY; dev->mtu = new_mtu; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 69ffb4a2d14b..0aeabbe81cc6 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -69,7 +69,7 @@ struct netdevsim { u32 bpf_offloaded_id; struct xdp_attachment_info xdp; - int xdp_prog_mode; + struct xdp_attachment_info xdp_hw; u32 prog_id_gen; diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 40401e9e9351..4f982a0255c2 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -814,20 +814,12 @@ try: "Device parameters reported for non-offloaded program") start_test("Test XDP prog replace with bad flags...") - ret, _, err = sim.set_xdp(obj, "offload", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack_nsim(err, "program loaded with different flags.", args) ret, _, err = sim.set_xdp(obj, "", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") check_extack(err, "program loaded with different flags.", args) start_test("Test XDP prog remove with bad flags...") - ret, _, err = sim.unset_xdp("offload", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode mode") - 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") -- cgit v1.2.3 From 99dadb6e3ec130800d199ec42fff03242b1be1eb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:43 -0700 Subject: selftests/bpf: add test for multiple programs Add tests for having an XDP program attached in the driver and another one attached in HW simultaneously. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_offload.py | 63 +++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 4f982a0255c2..b746227eaff2 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -339,6 +339,11 @@ class NetdevSim: self.dfs = DebugfsDir(self.dfs_dir) return self.dfs + def dfs_read(self, f): + path = os.path.join(self.dfs_dir, f) + _, data = cmd('cat %s' % (path)) + return data.strip() + def dfs_num_bound_progs(self): path = os.path.join(self.dfs_dir, "bpf_bound_progs") _, progs = cmd('ls %s' % (path)) @@ -814,6 +819,10 @@ try: "Device parameters reported for non-offloaded program") start_test("Test XDP prog replace with bad flags...") + ret, _, err = sim.set_xdp(obj, "generic", force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Replaced XDP program with a program in different mode") + fail(err.count("File exists") != 1, "Replaced driver XDP with generic") ret, _, err = sim.set_xdp(obj, "", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") @@ -883,6 +892,60 @@ try: rm(pin_file) bpftool_prog_list_wait(expected=0) + start_test("Test multi-attachment XDP - attach...") + sim.set_xdp(obj, "offload") + xdp = sim.ip_link_show(xdp=True)["xdp"] + offloaded = sim.dfs_read("bpf_offloaded_id") + fail("prog" not in xdp, "Base program not reported in single program mode") + fail(len(ipl["xdp"]["attached"]) != 1, + "Wrong attached program count with one program") + + sim.set_xdp(obj, "") + two_xdps = sim.ip_link_show(xdp=True)["xdp"] + offloaded2 = sim.dfs_read("bpf_offloaded_id") + + fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs") + fail("prog" in two_xdps, "Base program reported in multi program mode") + fail(xdp["attached"][0] not in two_xdps["attached"], + "Offload program not reported after driver activated") + fail(len(two_xdps["attached"]) != 2, + "Wrong attached program count with two programs") + fail(two_xdps["attached"][0]["prog"]["id"] == + two_xdps["attached"][1]["prog"]["id"], + "offloaded and drv programs have the same id") + fail(offloaded != offloaded2, + "offload ID changed after loading driver program") + + start_test("Test multi-attachment XDP - replace...") + ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True) + fail(err.count("busy") != 1, "Replaced one of programs without -force") + + start_test("Test multi-attachment XDP - detach...") + ret, _, err = sim.unset_xdp("drv", force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Removed program with a bad mode") + check_extack(err, "program loaded with different flags.", args) + + sim.unset_xdp("offload") + xdp = sim.ip_link_show(xdp=True)["xdp"] + offloaded = sim.dfs_read("bpf_offloaded_id") + + fail(xdp["mode"] != 1, "Bad mode reported after multiple programs") + fail("prog" not in xdp, + "Base program not reported after multi program mode") + fail(xdp["attached"][0] not in two_xdps["attached"], + "Offload program not reported after driver activated") + fail(len(ipl["xdp"]["attached"]) != 1, + "Wrong attached program count with remaining programs") + fail(offloaded != "0", "offload ID reported with only driver program left") + + start_test("Test multi-attachment XDP - device remove...") + sim.set_xdp(obj, "offload") + sim.remove() + + sim = NetdevSim() + sim.set_ethtool_tc_offloads(True) + start_test("Test mixing of TC and XDP...") sim.tc_add_ingress() sim.set_xdp(obj, "offload") -- cgit v1.2.3 From db42a21a1e8d11a30a06050281c2723ec78b63a7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 13 Jul 2018 19:08:59 -0700 Subject: tools: include reallocarray feature test in FEATURE_TESTS_BASIC perf propagates its feature check results to libbpf. This means features for which perf probes must be a superset of libbpf's required features. perf depends on FEATURE_TESTS_BASIC for its list of features. commit 531b014e7a2f ("tools: bpf: make use of reallocarray") added reallocarray use to libbpf, make perf also perform the reallocarray feature check. Fixes: 531b014e7a2f ("tools: bpf: make use of reallocarray") Reported-by: Guenter Roeck Signed-off-by: Jakub Kicinski Tested-by: Guenter Roeck Signed-off-by: Daniel Borkmann --- tools/build/Makefile.feature | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 5b6dda3b1ca8..f216b2f5c3d7 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -57,6 +57,7 @@ FEATURE_TESTS_BASIC := \ libunwind-aarch64 \ pthread-attr-setaffinity-np \ pthread-barrier \ + reallocarray \ stackprotector-all \ timerfd \ libdw-dwarf-unwind \ -- cgit v1.2.3 From 92b57121ca79b286bef4f304e887272f3f2d86bb Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Fri, 13 Jul 2018 21:57:02 -0700 Subject: bpf: btf: export btf types and name by offset from lib This patch introduces btf__resolve_type() function and exports two existing functions from libbpf. btf__resolve_type follows modifier types like const and typedef until it hits a type which actually takes up memory, and then returns it. This function follows similar pattern to btf__resolve_size but instead of computing size, it just returns the type. These functions will be used in the followig patch which parses information inside array of `struct btf_type *`. btf_name_by_offset is used for printing variable names. Signed-off-by: Okash Khawaja Acked-by: Martin KaFai Lau Acked-by: Song Liu Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/lib/bpf/btf.c | 65 ++++++++++++++++++++++++++++++++++++----------------- tools/lib/bpf/btf.h | 3 +++ 2 files changed, 48 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 8c54a4b6f187..03161be094b4 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -17,6 +17,11 @@ #define BTF_MAX_NR_TYPES 65535 +#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ + ((k) == BTF_KIND_VOLATILE) || \ + ((k) == BTF_KIND_CONST) || \ + ((k) == BTF_KIND_RESTRICT)) + static struct btf_type btf_void; struct btf { @@ -33,14 +38,6 @@ struct btf { int fd; }; -static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) -{ - if (offset < btf->hdr->str_len) - return &btf->strings[offset]; - else - return NULL; -} - static int btf_add_type(struct btf *btf, struct btf_type *t) { if (btf->types_size - btf->nr_types < 2) { @@ -190,15 +187,6 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } -static const struct btf_type *btf_type_by_id(const struct btf *btf, - uint32_t type_id) -{ - if (type_id > btf->nr_types) - return NULL; - - return btf->types[type_id]; -} - static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; @@ -234,7 +222,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) int64_t size = -1; int i; - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { size = btf_type_size(t); @@ -259,7 +247,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return -EINVAL; } - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); } if (size < 0) @@ -271,6 +259,26 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return nelems * size; } +int btf__resolve_type(const struct btf *btf, __u32 type_id) +{ + const struct btf_type *t; + int depth = 0; + + t = btf__type_by_id(btf, type_id); + while (depth < MAX_RESOLVE_DEPTH && + !btf_type_is_void_or_null(t) && + IS_MODIFIER(BTF_INFO_KIND(t->info))) { + type_id = t->type; + t = btf__type_by_id(btf, type_id); + depth++; + } + + if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t)) + return -EINVAL; + + return type_id; +} + int32_t btf__find_by_name(const struct btf *btf, const char *type_name) { uint32_t i; @@ -280,7 +288,7 @@ int32_t btf__find_by_name(const struct btf *btf, const char *type_name) for (i = 1; i <= btf->nr_types; i++) { const struct btf_type *t = btf->types[i]; - const char *name = btf_name_by_offset(btf, t->name_off); + const char *name = btf__name_by_offset(btf, t->name_off); if (name && !strcmp(type_name, name)) return i; @@ -371,3 +379,20 @@ int btf__fd(const struct btf *btf) { return btf->fd; } + +const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +{ + if (offset < btf->hdr->str_len) + return &btf->strings[offset]; + else + return NULL; +} + +const struct btf_type *btf__type_by_id(const struct btf *btf, + __u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 74bb344035bb..24f361d99a5e 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -17,6 +17,9 @@ void btf__free(struct btf *btf); struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); int32_t btf__find_by_name(const struct btf *btf, const char *type_name); int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +int btf__resolve_type(const struct btf *btf, __u32 type_id); int btf__fd(const struct btf *btf); +const char *btf__name_by_offset(const struct btf *btf, __u32 offset); +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id); #endif -- cgit v1.2.3 From b12d6ec09730b2646e85c348e599b592348dd0e3 Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Fri, 13 Jul 2018 21:57:03 -0700 Subject: bpf: btf: add btf print functionality This consumes functionality exported in the previous patch. It does the main job of printing with BTF data. This is used in the following patch to provide a more readable output of a map's dump. It relies on json_writer to do json printing. Below is sample output where map keys are ints and values are of type struct A: typedef int int_type; enum E { E0, E1, }; struct B { int x; int y; }; struct A { int m; unsigned long long n; char o; int p[8]; int q[4][8]; enum E r; void *s; struct B t; const int u; int_type v; unsigned int w1: 3; unsigned int w2: 3; }; $ sudo bpftool map dump id 14 [{ "key": 0, "value": { "m": 1, "n": 2, "o": "c", "p": [15,16,17,18,15,16,17,18 ], "q": [[25,26,27,28,25,26,27,28 ],[35,36,37,38,35,36,37,38 ],[45,46,47,48,45,46,47,48 ],[55,56,57,58,55,56,57,58 ] ], "r": 1, "s": 0x7ffd80531cf8, "t": { "x": 5, "y": 10 }, "u": 100, "v": 20, "w1": 0x7, "w2": 0x3 } } ] This patch uses json's {} and [] to imply struct/union and array. More explicit information can be added later. For example, a command line option can be introduced to print whether a key or value is struct or union, name of a struct etc. This will however come at the expense of duplicating info when, for example, printing an array of structs. enums are printed as ints without their names. Signed-off-by: Okash Khawaja Acked-by: Martin KaFai Lau Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/btf_dumper.c | 251 +++++++++++++++++++++++++++++++++++++++++ tools/bpf/bpftool/main.h | 15 +++ 2 files changed, 266 insertions(+) create mode 100644 tools/bpf/bpftool/btf_dumper.c (limited to 'tools') diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c new file mode 100644 index 000000000000..55bc512a1831 --- /dev/null +++ b/tools/bpf/bpftool/btf_dumper.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ + +#include +#include /* for (FILE *) used by json_writer */ +#include +#include +#include +#include +#include + +#include "btf.h" +#include "json_writer.h" +#include "main.h" + +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data); + +static void btf_dumper_ptr(const void *data, json_writer_t *jw, + bool is_plain_text) +{ + if (is_plain_text) + jsonw_printf(jw, "%p", *(unsigned long *)data); + else + jsonw_printf(jw, "%u", *(unsigned long *)data); +} + +static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + int actual_type_id; + + actual_type_id = btf__resolve_type(d->btf, type_id); + if (actual_type_id < 0) + return actual_type_id; + + return btf_dumper_do_type(d, actual_type_id, 0, data); +} + +static void btf_dumper_enum(const void *data, json_writer_t *jw) +{ + jsonw_printf(jw, "%d", *(int *)data); +} + +static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + struct btf_array *arr = (struct btf_array *)(t + 1); + long long elem_size; + int ret = 0; + __u32 i; + + elem_size = btf__resolve_size(d->btf, arr->type); + if (elem_size < 0) + return elem_size; + + jsonw_start_array(d->jw); + for (i = 0; i < arr->nelems; i++) { + ret = btf_dumper_do_type(d, arr->type, 0, + data + i * elem_size); + if (ret) + break; + } + + jsonw_end_array(d->jw); + return ret; +} + +static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int left_shift_bits, right_shift_bits; + int nr_bits = BTF_INT_BITS(int_type); + int total_bits_offset; + int bytes_to_copy; + int bits_to_copy; + __u64 print_num; + + total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + bits_to_copy = bit_offset + nr_bits; + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy); + + print_num = 0; + memcpy(&print_num, data, bytes_to_copy); +#if defined(__BIG_ENDIAN_BITFIELD) + left_shift_bits = bit_offset; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + left_shift_bits = 64 - bits_to_copy; +#else +#error neither big nor little endian +#endif + right_shift_bits = 64 - nr_bits; + + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; + if (is_plain_text) + jsonw_printf(jw, "0x%llx", print_num); + else + jsonw_printf(jw, "%llu", print_num); +} + +static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + __u32 *int_type; + __u32 nr_bits; + + int_type = (__u32 *)(t + 1); + nr_bits = BTF_INT_BITS(*int_type); + /* if this is bit field */ + if (bit_offset || BTF_INT_OFFSET(*int_type) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + return 0; + } + + switch (BTF_INT_ENCODING(*int_type)) { + case 0: + if (BTF_INT_BITS(*int_type) == 64) + jsonw_printf(jw, "%lu", *(__u64 *)data); + else if (BTF_INT_BITS(*int_type) == 32) + jsonw_printf(jw, "%u", *(__u32 *)data); + else if (BTF_INT_BITS(*int_type) == 16) + jsonw_printf(jw, "%hu", *(__u16 *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhu", *(__u8 *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_SIGNED: + if (BTF_INT_BITS(*int_type) == 64) + jsonw_printf(jw, "%ld", *(long long *)data); + else if (BTF_INT_BITS(*int_type) == 32) + jsonw_printf(jw, "%d", *(int *)data); + else if (BTF_INT_BITS(*int_type) == 16) + jsonw_printf(jw, "%hd", *(short *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhd", *(char *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_CHAR: + if (isprint(*(char *)data)) + jsonw_printf(jw, "\"%c\"", *(char *)data); + else + if (is_plain_text) + jsonw_printf(jw, "0x%hhx", *(char *)data); + else + jsonw_printf(jw, "\"\\u00%02hhx\"", + *(char *)data); + break; + case BTF_INT_BOOL: + jsonw_bool(jw, *(int *)data); + break; + default: + /* shouldn't happen */ + return -EINVAL; + } + + return 0; +} + +static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t; + struct btf_member *m; + const void *data_off; + int ret = 0; + int i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + jsonw_start_object(d->jw); + m = (struct btf_member *)(t + 1); + + for (i = 0; i < vlen; i++) { + data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset); + jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off)); + ret = btf_dumper_do_type(d, m[i].type, + BITS_PER_BYTE_MASKED(m[i].offset), + data_off); + if (ret) + break; + } + + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + return btf_dumper_int(t, bit_offset, data, d->jw, + d->is_plain_text); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return btf_dumper_struct(d, type_id, data); + case BTF_KIND_ARRAY: + return btf_dumper_array(d, type_id, data); + case BTF_KIND_ENUM: + btf_dumper_enum(data, d->jw); + return 0; + case BTF_KIND_PTR: + btf_dumper_ptr(data, d->jw, d->is_plain_text); + return 0; + case BTF_KIND_UNKN: + jsonw_printf(d->jw, "(unknown)"); + return 0; + case BTF_KIND_FWD: + /* map key or value can't be forward */ + jsonw_printf(d->jw, "(fwd-kind-invalid)"); + return -EINVAL; + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_dumper_modifier(d, type_id, data); + default: + jsonw_printf(d->jw, "(unsupported-kind"); + return -EINVAL; + } +} + +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + return btf_dumper_do_type(d, type_id, 0, data); +} diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 41004bb2644a..238e734d75b3 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -150,4 +150,19 @@ unsigned int get_page_size(void); unsigned int get_possible_cpus(void); const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); +struct btf_dumper { + const struct btf *btf; + json_writer_t *jw; + bool is_plain_text; +}; + +/* btf_dumper_type - print data along with type information + * @d: an instance containing context for dumping types + * @type_id: index in btf->types array. this points to the type to be dumped + * @data: pointer the actual data, i.e. the values to be printed + * + * Returns zero on success and negative error code otherwise + */ +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data); #endif -- cgit v1.2.3 From 2d3feca8c44f315624b7c0f5b8361e2f54405c12 Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Fri, 13 Jul 2018 21:57:04 -0700 Subject: bpf: btf: print map dump and lookup with btf info This patch augments the output of bpftool's map dump and map lookup commands to print data along side btf info, if the correspondin btf info is available. The outputs for each of map dump and map lookup commands are augmented in two ways: 1. when neither of -j and -p are supplied, btf-ful map data is printed whose aim is human readability. This means no commitments for json- or backward- compatibility. 2. when either -j or -p are supplied, a new json object named "formatted" is added for each key-value pair. This object contains the same data as the key-value pair, but with btf info. "formatted" object promises json- and backward- compatibility. Below is a sample output. $ bpftool map dump -p id 8 [{ "key": ["0x0f","0x00","0x00","0x00" ], "value": ["0x03", "0x00", "0x00", "0x00", ... ], "formatted": { "key": 15, "value": { "int_field": 3, ... } } } ] This patch calls btf_dumper introduced in previous patch to accomplish the above. Indeed, btf-ful info is only displayed if btf data for the given map is available. Otherwise existing output is displayed as-is. Signed-off-by: Okash Khawaja Acked-by: Martin KaFai Lau Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/map.c | 217 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 201 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e2baec1122fb..9c8191845585 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -44,6 +45,8 @@ #include +#include "btf.h" +#include "json_writer.h" #include "main.h" static const char * const map_type_name[] = { @@ -148,8 +151,109 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) return fd; } +static int do_dump_btf(const struct btf_dumper *d, + struct bpf_map_info *map_info, void *key, + void *value) +{ + int ret; + + /* start of key-value pair */ + jsonw_start_object(d->jw); + + jsonw_name(d->jw, "key"); + + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + + jsonw_name(d->jw, "value"); + + ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + +err_end_obj: + /* end of key-value pair */ + jsonw_end_object(d->jw); + + return ret; +} + +static int get_btf(struct bpf_map_info *map_info, struct btf **btf) +{ + struct bpf_btf_info btf_info = { 0 }; + __u32 len = sizeof(btf_info); + __u32 last_size; + int btf_fd; + void *ptr; + int err; + + err = 0; + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id); + if (btf_fd < 0) + return 0; + + /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + * let's start with a sane default - 4KiB here - and resize it only if + * bpf_obj_get_info_by_fd() needs a bigger buffer. + */ + btf_info.btf_size = 4096; + last_size = btf_info.btf_size; + ptr = malloc(last_size); + if (!ptr) { + err = -ENOMEM; + goto exit_free; + } + + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + + if (!err && btf_info.btf_size > last_size) { + void *temp_ptr; + + last_size = btf_info.btf_size; + temp_ptr = realloc(ptr, last_size); + if (!temp_ptr) { + err = -ENOMEM; + goto exit_free; + } + ptr = temp_ptr; + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + } + + if (err || btf_info.btf_size > last_size) { + err = errno; + goto exit_free; + } + + *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL); + if (IS_ERR(*btf)) { + err = PTR_ERR(btf); + *btf = NULL; + } + +exit_free: + close(btf_fd); + free(ptr); + + return err; +} + +static json_writer_t *get_btf_writer(void) +{ + json_writer_t *jw = jsonw_new(stdout); + + if (!jw) + return NULL; + jsonw_pretty(jw, true); + + return jw; +} + static void print_entry_json(struct bpf_map_info *info, unsigned char *key, - unsigned char *value) + unsigned char *value, struct btf *btf) { jsonw_start_object(json_wtr); @@ -158,6 +262,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, print_hex_data_json(key, info->key_size); jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } } else { unsigned int i, n; @@ -508,10 +622,12 @@ static int do_show(int argc, char **argv) static int do_dump(int argc, char **argv) { + struct bpf_map_info info = {}; void *key, *value, *prev_key; unsigned int num_elems = 0; - struct bpf_map_info info = {}; __u32 len = sizeof(info); + json_writer_t *btf_wtr; + struct btf *btf = NULL; int err; int fd; @@ -537,8 +653,27 @@ static int do_dump(int argc, char **argv) } prev_key = NULL; + + err = get_btf(&info, &btf); + if (err) { + p_err("failed to get btf"); + goto exit_free; + } + if (json_output) jsonw_start_array(json_wtr); + else + if (btf) { + btf_wtr = get_btf_writer(); + if (!btf_wtr) { + p_info("failed to create json writer for btf. falling back to plain output"); + btf__free(btf); + btf = NULL; + } else { + jsonw_start_array(btf_wtr); + } + } + while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -549,9 +684,19 @@ static int do_dump(int argc, char **argv) if (!bpf_map_lookup_elem(fd, key, value)) { if (json_output) - print_entry_json(&info, key, value); + print_entry_json(&info, key, value, btf); else - print_entry_plain(&info, key, value); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, &info, key, value); + } else { + print_entry_plain(&info, key, value); + } } else { if (json_output) { jsonw_name(json_wtr, "key"); @@ -574,14 +719,19 @@ static int do_dump(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - else + else if (btf) { + jsonw_end_array(btf_wtr); + jsonw_destroy(&btf_wtr); + } else { printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); + } exit_free: free(key); free(value); close(fd); + btf__free(btf); return err; } @@ -637,6 +787,8 @@ static int do_lookup(int argc, char **argv) { struct bpf_map_info info = {}; __u32 len = sizeof(info); + json_writer_t *btf_wtr; + struct btf *btf = NULL; void *key, *value; int err; int fd; @@ -661,27 +813,60 @@ static int do_lookup(int argc, char **argv) goto exit_free; err = bpf_map_lookup_elem(fd, key, value); - if (!err) { - if (json_output) - print_entry_json(&info, key, value); - else + if (err) { + if (errno == ENOENT) { + if (json_output) { + jsonw_null(json_wtr); + } else { + printf("key:\n"); + fprint_hex(stdout, key, info.key_size, " "); + printf("\n\nNot found\n"); + } + } else { + p_err("lookup failed: %s", strerror(errno)); + } + + goto exit_free; + } + + /* here means bpf_map_lookup_elem() succeeded */ + err = get_btf(&info, &btf); + if (err) { + p_err("failed to get btf"); + goto exit_free; + } + + if (json_output) { + print_entry_json(&info, key, value, btf); + } else if (btf) { + /* if here json_wtr wouldn't have been initialised, + * so let's create separate writer for btf + */ + btf_wtr = get_btf_writer(); + if (!btf_wtr) { + p_info("failed to create json writer for btf. falling back to plain output"); + btf__free(btf); + btf = NULL; print_entry_plain(&info, key, value); - } else if (errno == ENOENT) { - if (json_output) { - jsonw_null(json_wtr); } else { - printf("key:\n"); - fprint_hex(stdout, key, info.key_size, " "); - printf("\n\nNot found\n"); + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, &info, key, value); + jsonw_destroy(&btf_wtr); } } else { - p_err("lookup failed: %s", strerror(errno)); + print_entry_plain(&info, key, value); } exit_free: free(key); free(value); close(fd); + btf__free(btf); return err; } -- cgit v1.2.3 From 060a7fccd394f1600be86536b1d3e8cdd66637c2 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:33 -0700 Subject: bpf: Sync bpf.h to tools/ Sync BPF_SOCK_OPS_TCP_LISTEN_CB related UAPI changes to tools/. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6bcb287a888d..870113916cac 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2555,6 +2555,9 @@ enum { * Arg1: old_state * Arg2: new_state */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From 04c13411151c220b41998020c32ac97f33b58683 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:34 -0700 Subject: selftests/bpf: Fix const'ness in cgroup_helpers Lack of const in cgroup helpers signatures forces to write ugly client code. Fix it. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/cgroup_helpers.c | 6 +++--- tools/testing/selftests/bpf/cgroup_helpers.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index c87b4e052ce9..cf16948aad4a 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -118,7 +118,7 @@ static int join_cgroup_from_top(char *cgroup_path) * * On success, it returns 0, otherwise on failure it returns 1. */ -int join_cgroup(char *path) +int join_cgroup(const char *path) { char cgroup_path[PATH_MAX + 1]; @@ -158,7 +158,7 @@ void cleanup_cgroup_environment(void) * On success, it returns the file descriptor. On failure it returns 0. * If there is a failure, it prints the error to stderr. */ -int create_and_get_cgroup(char *path) +int create_and_get_cgroup(const char *path) { char cgroup_path[PATH_MAX + 1]; int fd; @@ -186,7 +186,7 @@ int create_and_get_cgroup(char *path) * which is an invalid cgroup id. * If there is a failure, it prints the error to stderr. */ -unsigned long long get_cgroup_id(char *path) +unsigned long long get_cgroup_id(const char *path) { int dirfd, err, flags, mount_id, fhsize; union { diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 20a4a5dcd469..d64bb8957090 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -9,10 +9,10 @@ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) -int create_and_get_cgroup(char *path); -int join_cgroup(char *path); +int create_and_get_cgroup(const char *path); +int join_cgroup(const char *path); int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); -unsigned long long get_cgroup_id(char *path); +unsigned long long get_cgroup_id(const char *path); #endif -- cgit v1.2.3 From c65267e5ff418c81d7fea7025850ed4f190a1289 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:35 -0700 Subject: selftests/bpf: Switch test_tcpbpf_user to cgroup_helpers Switch to cgroup_helpers to simplify the code and fix cgroup cleanup: before cgroup was not cleaned up after the test. It also removes SYSTEM macro, that only printed error, but didn't terminate the test. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/Makefile | 1 + tools/testing/selftests/bpf/test_tcpbpf_user.c | 55 ++++++++++---------------- 2 files changed, 22 insertions(+), 34 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7a6214e9ae58..478bf1bcbbf5 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -61,6 +61,7 @@ $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c $(OUTPUT)/test_sockmap: cgroup_helpers.c +$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c $(OUTPUT)/test_progs: trace_helpers.c $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 84ab5163c828..fa97ec6428de 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -1,25 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 #include #include -#include #include #include -#include #include -#include -#include -#include #include -#include -#include #include -#include -#include #include #include -#include "bpf_util.h" + #include "bpf_rlimit.h" -#include +#include "bpf_util.h" +#include "cgroup_helpers.h" + #include "test_tcpbpf.h" static int bpf_find_map(const char *test, struct bpf_object *obj, @@ -35,42 +28,32 @@ static int bpf_find_map(const char *test, struct bpf_object *obj, return bpf_map__fd(map); } -#define SYSTEM(CMD) \ - do { \ - if (system(CMD)) { \ - printf("system(%s) FAILS!\n", CMD); \ - } \ - } while (0) - int main(int argc, char **argv) { const char *file = "test_tcpbpf_kern.o"; struct tcpbpf_globals g = {0}; - int cg_fd, prog_fd, map_fd; + const char *cg_path = "/foo"; bool debug_flag = false; int error = EXIT_FAILURE; struct bpf_object *obj; - char cmd[100], *dir; - struct stat buffer; + int prog_fd, map_fd; + int cg_fd = -1; __u32 key = 0; - int pid; int rv; if (argc > 1 && strcmp(argv[1], "-d") == 0) debug_flag = true; - dir = "/tmp/cgroupv2/foo"; + if (setup_cgroup_environment()) + goto err; + + cg_fd = create_and_get_cgroup(cg_path); + if (!cg_fd) + goto err; - if (stat(dir, &buffer) != 0) { - SYSTEM("mkdir -p /tmp/cgroupv2"); - SYSTEM("mount -t cgroup2 none /tmp/cgroupv2"); - SYSTEM("mkdir -p /tmp/cgroupv2/foo"); - } - pid = (int) getpid(); - sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid); - SYSTEM(cmd); + if (join_cgroup(cg_path)) + goto err; - cg_fd = open(dir, O_DIRECTORY, O_RDONLY); if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { printf("FAILED: load_bpf_file failed for: %s\n", file); goto err; @@ -83,7 +66,10 @@ int main(int argc, char **argv) goto err; } - SYSTEM("./tcp_server.py"); + if (system("./tcp_server.py")) { + printf("FAILED: TCP server\n"); + goto err; + } map_fd = bpf_find_map(__func__, obj, "global_map"); if (map_fd < 0) @@ -123,6 +109,7 @@ int main(int argc, char **argv) error = 0; err: bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); + close(cg_fd); + cleanup_cgroup_environment(); return error; - } -- cgit v1.2.3 From 2044e4ef0be29f0154b078a956a3d8331315298a Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:36 -0700 Subject: selftests/bpf: Better verification in test_tcpbpf Reduce amount of copy/paste for debug info when result is verified in the test and keep that info together with values being checked so that they won't get out of sync. It also improves debug experience: instead of checking manually what doesn't match in debug output for all fields, only unexpected field is printed. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_tcpbpf_user.c | 64 ++++++++++++++++---------- 1 file changed, 39 insertions(+), 25 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index fa97ec6428de..971f1644b9c7 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include @@ -15,6 +16,42 @@ #include "test_tcpbpf.h" +#define EXPECT_EQ(expected, actual, fmt) \ + do { \ + if ((expected) != (actual)) { \ + printf(" Value of: " #actual "\n" \ + " Actual: %" fmt "\n" \ + " Expected: %" fmt "\n", \ + (actual), (expected)); \ + goto err; \ + } \ + } while (0) + +int verify_result(const struct tcpbpf_globals *result) +{ + __u32 expected_events; + + expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) | + (1 << BPF_SOCK_OPS_RWND_INIT) | + (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) | + (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) | + (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) | + (1 << BPF_SOCK_OPS_NEEDS_ECN) | + (1 << BPF_SOCK_OPS_STATE_CB)); + + EXPECT_EQ(expected_events, result->event_map, "#" PRIx32); + EXPECT_EQ(501ULL, result->bytes_received, "llu"); + EXPECT_EQ(1002ULL, result->bytes_acked, "llu"); + EXPECT_EQ(1, result->data_segs_in, PRIu32); + EXPECT_EQ(1, result->data_segs_out, PRIu32); + EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32); + EXPECT_EQ(0, result->good_cb_test_rv, PRIu32); + + return 0; +err: + return -1; +} + static int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { @@ -33,7 +70,6 @@ int main(int argc, char **argv) const char *file = "test_tcpbpf_kern.o"; struct tcpbpf_globals g = {0}; const char *cg_path = "/foo"; - bool debug_flag = false; int error = EXIT_FAILURE; struct bpf_object *obj; int prog_fd, map_fd; @@ -41,9 +77,6 @@ int main(int argc, char **argv) __u32 key = 0; int rv; - if (argc > 1 && strcmp(argv[1], "-d") == 0) - debug_flag = true; - if (setup_cgroup_environment()) goto err; @@ -81,30 +114,11 @@ int main(int argc, char **argv) goto err; } - if (g.bytes_received != 501 || g.bytes_acked != 1002 || - g.data_segs_in != 1 || g.data_segs_out != 1 || - (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 || - g.good_cb_test_rv != 0) { + if (verify_result(&g)) { printf("FAILED: Wrong stats\n"); - if (debug_flag) { - printf("\n"); - printf("bytes_received: %d (expecting 501)\n", - (int)g.bytes_received); - printf("bytes_acked: %d (expecting 1002)\n", - (int)g.bytes_acked); - printf("data_segs_in: %d (expecting 1)\n", - g.data_segs_in); - printf("data_segs_out: %d (expecting 1)\n", - g.data_segs_out); - printf("event_map: 0x%x (at least 0x47e)\n", - g.event_map); - printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n", - g.bad_cb_test_rv); - printf("good_cb_test_rv:0x%x (expecting 0)\n", - g.good_cb_test_rv); - } goto err; } + printf("PASSED!\n"); error = 0; err: -- cgit v1.2.3 From 78d8e26d46bc2ed73ab6a0e369a342478fda4ce0 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:37 -0700 Subject: selftests/bpf: Test case for BPF_SOCK_OPS_TCP_LISTEN_CB Cover new TCP-BPF callback in test_tcpbpf: when listen() is called on socket, set BPF_SOCK_OPS_STATE_CB_FLAG so that BPF_SOCK_OPS_STATE_CB callback can be called on future state transition, and when such a transition happens (TCP_LISTEN -> TCP_CLOSE), track it in the map and verify it in user space later. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_tcpbpf.h | 1 + tools/testing/selftests/bpf/test_tcpbpf_kern.c | 17 ++++++++++++----- tools/testing/selftests/bpf/test_tcpbpf_user.c | 4 +++- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h index 2fe43289943c..7bcfa6207005 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf.h +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -12,5 +12,6 @@ struct tcpbpf_globals { __u32 good_cb_test_rv; __u64 bytes_received; __u64 bytes_acked; + __u32 num_listen; }; #endif diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c index 3e645ee41ed5..4b7fd540cea9 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -96,15 +96,22 @@ int bpf_testcb(struct bpf_sock_ops *skops) if (!gp) break; g = *gp; - g.total_retrans = skops->total_retrans; - g.data_segs_in = skops->data_segs_in; - g.data_segs_out = skops->data_segs_out; - g.bytes_received = skops->bytes_received; - g.bytes_acked = skops->bytes_acked; + if (skops->args[0] == BPF_TCP_LISTEN) { + g.num_listen++; + } else { + g.total_retrans = skops->total_retrans; + g.data_segs_in = skops->data_segs_in; + g.data_segs_out = skops->data_segs_out; + g.bytes_received = skops->bytes_received; + g.bytes_acked = skops->bytes_acked; + } bpf_map_update_elem(&global_map, &key, &g, BPF_ANY); } break; + case BPF_SOCK_OPS_TCP_LISTEN_CB: + bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG); + break; default: rv = -1; } diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 971f1644b9c7..a275c2971376 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -37,7 +37,8 @@ int verify_result(const struct tcpbpf_globals *result) (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) | (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) | (1 << BPF_SOCK_OPS_NEEDS_ECN) | - (1 << BPF_SOCK_OPS_STATE_CB)); + (1 << BPF_SOCK_OPS_STATE_CB) | + (1 << BPF_SOCK_OPS_TCP_LISTEN_CB)); EXPECT_EQ(expected_events, result->event_map, "#" PRIx32); EXPECT_EQ(501ULL, result->bytes_received, "llu"); @@ -46,6 +47,7 @@ int verify_result(const struct tcpbpf_globals *result) EXPECT_EQ(1, result->data_segs_out, PRIu32); EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32); EXPECT_EQ(0, result->good_cb_test_rv, PRIu32); + EXPECT_EQ(1, result->num_listen, PRIu32); return 0; err: -- cgit v1.2.3