diff options
| author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2020-08-06 13:15:47 +0200 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2020-08-06 13:15:47 +0200 |
| commit | 94fb1afb14c4f0ceb8c5508ddddac6819f662e95 (patch) | |
| tree | 4988e5769dc7482caa7f441475ae31f50bbd37ef /tools | |
| parent | perf evsel: Don't set sample_regs_intr/sample_regs_user for dummy event (diff) | |
| parent | Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next (diff) | |
| download | linux-94fb1afb14c4f0ceb8c5508ddddac6819f662e95.tar.xz linux-94fb1afb14c4f0ceb8c5508ddddac6819f662e95.zip | |
Mgerge remote-tracking branch 'torvalds/master' into perf/core
To sync headers, for instance, in this case tools/perf was ahead of
upstream till Linus merged tip/perf/core to get the
PERF_RECORD_TEXT_POKE changes:
Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h'
diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools')
291 files changed, 18034 insertions, 2677 deletions
diff --git a/tools/Makefile b/tools/Makefile index bd778812e915..85af6ebbce91 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -67,6 +67,9 @@ cpupower: FORCE cgroup firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging: FORCE $(call descend,$@) +bpf/%: FORCE + $(call descend,$@) + liblockdep: FORCE $(call descend,lib/lockdep) diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 6df1850f8353..0a6d09a3e91f 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -9,7 +9,8 @@ MAKE = make INSTALL ?= install CFLAGS += -Wall -O2 -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/include # This will work when bpf is built in tools env. where srctree # isn't set and when invoked from selftests build, where srctree @@ -123,5 +124,12 @@ runqslower_install: runqslower_clean: $(call descend,runqslower,clean) +resolve_btfids: + $(call descend,resolve_btfids) + +resolve_btfids_clean: + $(call descend,resolve_btfids,clean) + .PHONY: all install clean bpftool bpftool_install bpftool_clean \ - runqslower runqslower_install runqslower_clean + runqslower runqslower_install runqslower_clean \ + resolve_btfids resolve_btfids_clean diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 26cde83e1ca3..3e601bcfd461 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only *.d -/_bpftool +/bpftool-bootstrap /bpftool bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool feature libbpf -profiler.skel.h +/*.skel.h +/vmlinux.h diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index ce3a724f50c1..896f4c6c2870 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -36,6 +36,11 @@ DESCRIPTION otherwise list all BTF objects currently loaded on the system. + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BTF + objects. On such kernels bpftool will automatically emit this + information as well. + **bpftool btf dump** *BTF_SRC* Dump BTF entries from a given *BTF_SRC*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst index 8dce698eab79..070ffacb42b5 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-iter.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -17,14 +17,15 @@ SYNOPSIS ITER COMMANDS =================== -| **bpftool** **iter pin** *OBJ* *PATH* +| **bpftool** **iter pin** *OBJ* *PATH* [**map** *MAP*] | **bpftool** **iter help** | | *OBJ* := /a/file/of/bpf_iter_target.o +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } DESCRIPTION =========== - **bpftool iter pin** *OBJ* *PATH* + **bpftool iter pin** *OBJ* *PATH* [**map** *MAP*] A bpf iterator combines a kernel iterating of particular kernel data (e.g., tasks, bpf_maps, etc.) and a bpf program called for each kernel data object @@ -37,6 +38,12 @@ DESCRIPTION character ('.'), which is reserved for future extensions of *bpffs*. + Map element bpf iterator requires an additional parameter + *MAP* so bpf program can iterate over map elements for + that map. User can have a bpf program in kernel to run + with each map element, do checking, filtering, aggregation, + etc. without copying data to user space. + User can then *cat PATH* to see the bpf iterator output. **bpftool iter help** @@ -64,6 +71,13 @@ EXAMPLES Create a file-based bpf iterator from bpf_iter_netlink.o and pin it to /sys/fs/bpf/my_netlink +**# bpftool iter pin bpf_iter_hashmap.o /sys/fs/bpf/my_hashmap map id 20** + +:: + + Create a file-based bpf iterator from bpf_iter_hashmap.o and map with + id 20, and pin it to /sys/fs/bpf/my_hashmap + SEE ALSO ======== **bpf**\ (2), diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst index 0e43d7b06c11..4a52e7a93339 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-link.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -21,6 +21,7 @@ LINK COMMANDS | **bpftool** **link { show | list }** [*LINK*] | **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link detach *LINK* | **bpftool** **link help** | | *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } @@ -37,6 +38,11 @@ DESCRIPTION zero or more named attributes, some of which depend on type of link. + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + links. On such kernels bpftool will automatically emit this + information as well. + **bpftool link pin** *LINK* *FILE* Pin link *LINK* as *FILE*. @@ -44,6 +50,13 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. + **bpftool link detach** *LINK* + Force-detach link *LINK*. BPF link and its underlying BPF + program will stay valid, but they will be detached from the + respective BPF hook and BPF link will transition into + a defunct state until last open file descriptor for that + link is closed. + **bpftool link help** Print short help message. @@ -82,6 +95,7 @@ EXAMPLES 10: cgroup prog 25 cgroup_id 614 attach_type egress + pids test_progs(223) **# bpftool --json --pretty link show** @@ -91,7 +105,12 @@ EXAMPLES "type": "cgroup", "prog_id": 25, "cgroup_id": 614, - "attach_type": "egress" + "attach_type": "egress", + "pids": [{ + "pid": 223, + "comm": "test_progs" + } + ] } ] diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 70c78faa47ab..41e2a74252d0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -62,6 +62,11 @@ DESCRIPTION Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + maps. On such kernels bpftool will automatically emit this + information as well. + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -180,7 +185,8 @@ EXAMPLES :: 10: hash name some_map flags 0x0 - key 4B value 8B max_entries 2048 memlock 167936B + key 4B value 8B max_entries 2048 memlock 167936B + pids systemd(1) The following three commands are equivalent: diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 2b254959d488..82e356b664e8 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -45,7 +45,7 @@ PROG COMMANDS | **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | | **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | | **cgroup/getsockopt** | **cgroup/setsockopt** | -| **struct_ops** | **fentry** | **fexit** | **freplace** +| **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** @@ -75,6 +75,11 @@ DESCRIPTION program run. Activation or deactivation of the feature is performed via the **kernel.bpf_stats_enabled** sysctl knob. + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + programs. On such kernels bpftool will automatically emit this + information as well. + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] Dump eBPF instructions of the programs from the kernel. By default, eBPF will be disassembled and printed to standard @@ -243,6 +248,7 @@ EXAMPLES 10: xdp name some_prog tag 005a3d2123620c8b gpl run_time_ns 81632 run_cnt 10 loaded_at 2017-09-29T20:11:00+0000 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 + pids systemd(1) **# bpftool --json --pretty prog show** @@ -262,6 +268,11 @@ EXAMPLES "bytes_jited": 370, "bytes_memlock": 4096, "map_ids": [10 + ], + "pids": [{ + "pid": 1, + "comm": "systemd" + } ] } ] diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 9e85f101be85..8462690a039b 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -40,8 +40,9 @@ bash_compdir ?= /usr/share/bash-completion/completions CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers -CFLAGS += $(filter-out -Wswitch-enum,$(EXTRA_WARNINGS)) +CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(if $(OUTPUT),$(OUTPUT),.) \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ @@ -58,12 +59,13 @@ endif INSTALL ?= install RM ?= rm -f CLANG ?= clang +LLVM_STRIP ?= llvm-strip FEATURE_USER = .bpftool FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ - clang-bpf-global-var + clang-bpf-co-re FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ - clang-bpf-global-var + clang-bpf-co-re check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -116,40 +118,60 @@ CFLAGS += -DHAVE_LIBBFD_SUPPORT SRCS += $(BFD_SRCS) endif +BPFTOOL_BOOTSTRAP := $(if $(OUTPUT),$(OUTPUT)bpftool-bootstrap,./bpftool-bootstrap) + +BOOTSTRAP_OBJS = $(addprefix $(OUTPUT),main.o common.o json_writer.o gen.o btf.o) OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o -_OBJS = $(filter-out $(OUTPUT)prog.o,$(OBJS)) $(OUTPUT)_prog.o -ifeq ($(feature-clang-bpf-global-var),1) - __OBJS = $(OBJS) -else - __OBJS = $(_OBJS) -endif +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) -$(OUTPUT)_prog.o: prog.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -DBPFTOOL_WITHOUT_SKELETONS -o $@ $< +ifneq ($(VMLINUX_BTF)$(VMLINUX_H),) +ifeq ($(feature-clang-bpf-co-re),1) -$(OUTPUT)_bpftool: $(_OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(_OBJS) $(LIBS) +BUILD_BPF_SKELS := 1 -skeleton/profiler.bpf.o: skeleton/profiler.bpf.c $(LIBBPF) +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) +ifeq ($(VMLINUX_H),) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ +else + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF) $(QUIET_CLANG)$(CLANG) \ + -I$(if $(OUTPUT),$(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ - -I$(LIBBPF_PATH) -I$(srctree)/tools/lib \ - -g -O2 -target bpf -c $< -o $@ + -I$(LIBBPF_PATH) \ + -I$(srctree)/tools/lib \ + -g -O2 -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@ -profiler.skel.h: $(OUTPUT)_bpftool skeleton/profiler.bpf.o - $(QUIET_GEN)$(OUTPUT)./_bpftool gen skeleton skeleton/profiler.bpf.o > $@ +$(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@ -$(OUTPUT)prog.o: prog.c profiler.skel.h - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< +$(OUTPUT)prog.o: $(OUTPUT)profiler.skel.h + +$(OUTPUT)pids.o: $(OUTPUT)pid_iter.skel.h + +endif +endif + +CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< $(OUTPUT)feature.o: | zdep -$(OUTPUT)bpftool: $(__OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(__OBJS) $(LIBS) +$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) $(LIBS) + +$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) $(OUTPUT)%.o: %.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< @@ -157,7 +179,7 @@ $(OUTPUT)%.o: %.c clean: $(LIBBPF)-clean $(call QUIET_CLEAN, bpftool) $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d - $(Q)$(RM) -- $(OUTPUT)_bpftool profiler.skel.h skeleton/profiler.bpf.o + $(Q)$(RM) -- $(BPFTOOL_BOOTSTRAP) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h $(Q)$(RM) -r -- $(OUTPUT)libbpf/ $(call QUIET_CLEAN, core-gen) $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool @@ -192,6 +214,7 @@ FORCE: zdep: @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi +.SECONDARY: .PHONY: all FORCE clean install uninstall zdep .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 25b25aca1112..f53ed2f1a4aa 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -479,7 +479,7 @@ _bpftool() cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ cgroup/setsockopt struct_ops \ - fentry fexit freplace" -- \ + fentry fexit freplace sk_lookup" -- \ "$cur" ) ) return 0 ;; @@ -615,7 +615,23 @@ _bpftool() iter) case $command in pin) - _filedir + case $prev in + $command) + _filedir + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + *) + _bpftool_one_of_list $MAP_TYPE + ;; + esac return 0 ;; *) @@ -1106,7 +1122,7 @@ _bpftool() ;; link) case $command in - show|list|pin) + show|list|pin|detach) case $prev in id) _bpftool_get_link_ids @@ -1123,7 +1139,7 @@ _bpftool() COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) return 0 ;; - pin) + pin|detach) if [[ $prev == "$command" ]]; then COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) else diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index faac8189b285..8ab142ff5eac 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -422,54 +422,6 @@ done: return err; } -static struct btf *btf__parse_raw(const char *file) -{ - struct btf *btf; - struct stat st; - __u8 *buf; - FILE *f; - - if (stat(file, &st)) - return NULL; - - f = fopen(file, "rb"); - if (!f) - return NULL; - - buf = malloc(st.st_size); - if (!buf) { - btf = ERR_PTR(-ENOMEM); - goto exit_close; - } - - if ((size_t) st.st_size != fread(buf, 1, st.st_size, f)) { - btf = ERR_PTR(-EINVAL); - goto exit_free; - } - - btf = btf__new(buf, st.st_size); - -exit_free: - free(buf); -exit_close: - fclose(f); - return btf; -} - -static bool is_btf_raw(const char *file) -{ - __u16 magic = 0; - int fd, nb_read; - - fd = open(file, O_RDONLY); - if (fd < 0) - return false; - - nb_read = read(fd, &magic, sizeof(magic)); - close(fd); - return nb_read == sizeof(magic) && magic == BTF_MAGIC; -} - static int do_dump(int argc, char **argv) { struct btf *btf = NULL; @@ -547,11 +499,7 @@ static int do_dump(int argc, char **argv) } NEXT_ARG(); } else if (is_prefix(src, "file")) { - if (is_btf_raw(*argv)) - btf = btf__parse_raw(*argv); - else - btf = btf__parse_elf(*argv, NULL); - + btf = btf__parse(*argv, NULL); if (IS_ERR(btf)) { err = -PTR_ERR(btf); btf = NULL; @@ -596,7 +544,7 @@ static int do_dump(int argc, char **argv) goto done; } if (!btf) { - err = ENOENT; + err = -ENOENT; p_err("can't find btf with ID (%u)", btf_id); goto done; } @@ -809,6 +757,7 @@ show_btf_plain(struct bpf_btf_info *info, int fd, printf("%s%u", n++ == 0 ? " map_ids " : ",", obj->obj_id); } + emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); printf("\n"); } @@ -841,6 +790,9 @@ show_btf_json(struct bpf_btf_info *info, int fd, jsonw_uint(json_wtr, obj->obj_id); } jsonw_end_array(json_wtr); /* map_ids */ + + emit_obj_refs_json(&refs_table, info->id, json_wtr); /* pids */ + jsonw_end_object(json_wtr); /* btf object */ } @@ -893,6 +845,7 @@ static int do_show(int argc, char **argv) close(fd); return err; } + build_obj_refs_table(&refs_table, BPF_OBJ_BTF); if (fd >= 0) { err = show_btf(fd, &btf_prog_table, &btf_map_table); @@ -939,6 +892,7 @@ static int do_show(int argc, char **argv) exit_free: delete_btf_table(&btf_prog_table); delete_btf_table(&btf_map_table); + delete_obj_refs_table(&refs_table); return err; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index c47bdc65de8e..65303664417e 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,10 +1,11 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +#define _GNU_SOURCE #include <ctype.h> #include <errno.h> #include <fcntl.h> -#include <fts.h> +#include <ftw.h> #include <libgen.h> #include <mntent.h> #include <stdbool.h> @@ -29,6 +30,44 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { + [BPF_CGROUP_INET_INGRESS] = "ingress", + [BPF_CGROUP_INET_EGRESS] = "egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", + [BPF_CGROUP_INET_SOCK_RELEASE] = "sock_release", + [BPF_CGROUP_SOCK_OPS] = "sock_ops", + [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", + [BPF_CGROUP_INET4_GETPEERNAME] = "getpeername4", + [BPF_CGROUP_INET6_GETPEERNAME] = "getpeername6", + [BPF_CGROUP_INET4_GETSOCKNAME] = "getsockname4", + [BPF_CGROUP_INET6_GETSOCKNAME] = "getsockname6", + [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", + [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", + [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", + + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "raw_tp", + [BPF_TRACE_FENTRY] = "fentry", + [BPF_TRACE_FEXIT] = "fexit", + [BPF_MODIFY_RETURN] = "mod_ret", + [BPF_LSM_MAC] = "lsm_mac", + [BPF_SK_LOOKUP] = "sk_lookup", +}; + void p_err(const char *fmt, ...) { va_list ap; @@ -123,24 +162,35 @@ int mount_tracefs(const char *target) return err; } -int open_obj_pinned(char *path, bool quiet) +int open_obj_pinned(const char *path, bool quiet) { - int fd; + char *pname; + int fd = -1; + + pname = strdup(path); + if (!pname) { + if (!quiet) + p_err("mem alloc failed"); + goto out_ret; + } - fd = bpf_obj_get(path); + fd = bpf_obj_get(pname); if (fd < 0) { if (!quiet) - p_err("bpf obj get (%s): %s", path, - errno == EACCES && !is_bpffs(dirname(path)) ? + p_err("bpf obj get (%s): %s", pname, + errno == EACCES && !is_bpffs(dirname(pname)) ? "directory not in bpf file system (bpffs)" : strerror(errno)); - return -1; + goto out_free; } +out_free: + free(pname); +out_ret: return fd; } -int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) { enum bpf_obj_type type; int fd; @@ -330,71 +380,82 @@ void print_hex_data_json(uint8_t *data, size_t len) jsonw_end_array(json_wtr); } +/* extra params for nftw cb */ +static struct pinned_obj_table *build_fn_table; +static enum bpf_obj_type build_fn_type; + +static int do_build_table_cb(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftwbuf) +{ + struct bpf_prog_info pinned_info; + __u32 len = sizeof(pinned_info); + struct pinned_obj *obj_node; + enum bpf_obj_type objtype; + int fd, err = 0; + + if (typeflag != FTW_F) + goto out_ret; + + fd = open_obj_pinned(fpath, true); + if (fd < 0) + goto out_ret; + + objtype = get_fd_type(fd); + if (objtype != build_fn_type) + goto out_close; + + memset(&pinned_info, 0, sizeof(pinned_info)); + if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len)) + goto out_close; + + obj_node = calloc(1, sizeof(*obj_node)); + if (!obj_node) { + err = -1; + goto out_close; + } + + obj_node->id = pinned_info.id; + obj_node->path = strdup(fpath); + if (!obj_node->path) { + err = -1; + free(obj_node); + goto out_close; + } + + hash_add(build_fn_table->table, &obj_node->hash, obj_node->id); +out_close: + close(fd); +out_ret: + return err; +} + int build_pinned_obj_table(struct pinned_obj_table *tab, enum bpf_obj_type type) { - struct bpf_prog_info pinned_info = {}; - struct pinned_obj *obj_node = NULL; - __u32 len = sizeof(pinned_info); struct mntent *mntent = NULL; - enum bpf_obj_type objtype; FILE *mntfile = NULL; - FTSENT *ftse = NULL; - FTS *fts = NULL; - int fd, err; + int flags = FTW_PHYS; + int nopenfd = 16; + int err = 0; mntfile = setmntent("/proc/mounts", "r"); if (!mntfile) return -1; + build_fn_table = tab; + build_fn_type = type; + while ((mntent = getmntent(mntfile))) { - char *path[] = { mntent->mnt_dir, NULL }; + char *path = mntent->mnt_dir; if (strncmp(mntent->mnt_type, "bpf", 3) != 0) continue; - - fts = fts_open(path, 0, NULL); - if (!fts) - continue; - - while ((ftse = fts_read(fts))) { - if (!(ftse->fts_info & FTS_F)) - continue; - fd = open_obj_pinned(ftse->fts_path, true); - if (fd < 0) - continue; - - objtype = get_fd_type(fd); - if (objtype != type) { - close(fd); - continue; - } - memset(&pinned_info, 0, sizeof(pinned_info)); - err = bpf_obj_get_info_by_fd(fd, &pinned_info, &len); - if (err) { - close(fd); - continue; - } - - obj_node = malloc(sizeof(*obj_node)); - if (!obj_node) { - close(fd); - fts_close(fts); - fclose(mntfile); - return -1; - } - - memset(obj_node, 0, sizeof(*obj_node)); - obj_node->id = pinned_info.id; - obj_node->path = strdup(ftse->fts_path); - hash_add(tab->table, &obj_node->hash, obj_node->id); - - close(fd); - } - fts_close(fts); + err = nftw(path, do_build_table_cb, nopenfd, flags); + if (err) + break; } fclose(mntfile); - return 0; + return err; } void delete_pinned_obj_table(struct pinned_obj_table *tab) @@ -581,3 +642,311 @@ print_all_levels(__maybe_unused enum libbpf_print_level level, { return vfprintf(stderr, format, args); } + +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) +{ + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || + (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int prog_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "tag")) { + unsigned char tag[BPF_TAG_SIZE]; + + NEXT_ARGP(); + + if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, + tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) + != BPF_TAG_SIZE) { + p_err("can't parse tag"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(tag, fds, true); + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(name, fds, false); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int prog_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several programs match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +static int map_fd_by_name(char *name, int **fds) +{ + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int map_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_map_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get map by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return map_fd_by_name(name, fds); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int map_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several maps match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +{ + int err; + int fd; + + fd = map_parse_fd(argc, argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, info, info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return err; + } + + return fd; +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 768bf77df886..a43a6f10b564 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -504,6 +504,10 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, supported_types[prog_type] |= res; + if (!prog_type_name[prog_type]) { + p_info("program type name not found (type %d)", prog_type); + return; + } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; if (strlen(prog_type_name[prog_type]) > maxlen) { p_info("program type name too long"); @@ -533,6 +537,10 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, * check required for unprivileged users */ + if (!map_type_name[map_type]) { + p_info("map type name not found (type %d)", map_type); + return; + } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; if (strlen(map_type_name[map_type]) > maxlen) { p_info("map type name too long"); @@ -695,7 +703,7 @@ section_program_types(bool *supported_types, const char *define_prefix, "/*** eBPF program types ***/", define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) + for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) probe_prog_type(i, supported_types, define_prefix, ifindex); print_end_section(); @@ -741,7 +749,7 @@ section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", define_prefix, define_prefix, define_prefix, define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) + for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) probe_helpers_for_progtype(i, supported_types[i], define_prefix, ifindex); diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 10de76b296ba..8a4c2b3b0cd6 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -88,7 +88,7 @@ static const char *get_map_ident(const struct bpf_map *map) return NULL; } -static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args) { vprintf(fmt, args); } @@ -104,17 +104,20 @@ static int codegen_datasec_def(struct bpf_object *obj, int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); const char *sec_ident; char var_ident[256]; + bool strip_mods = false; - if (strcmp(sec_name, ".data") == 0) + if (strcmp(sec_name, ".data") == 0) { sec_ident = "data"; - else if (strcmp(sec_name, ".bss") == 0) + } else if (strcmp(sec_name, ".bss") == 0) { sec_ident = "bss"; - else if (strcmp(sec_name, ".rodata") == 0) + } else if (strcmp(sec_name, ".rodata") == 0) { sec_ident = "rodata"; - else if (strcmp(sec_name, ".kconfig") == 0) + strip_mods = true; + } else if (strcmp(sec_name, ".kconfig") == 0) { sec_ident = "kconfig"; - else + } else { return 0; + } printf(" struct %s__%s {\n", obj_name, sec_ident); for (i = 0; i < vlen; i++, sec_var++) { @@ -123,16 +126,10 @@ static int codegen_datasec_def(struct bpf_object *obj, DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, .field_name = var_ident, .indent_level = 2, + .strip_mods = strip_mods, ); int need_off = sec_var->offset, align_off, align; __u32 var_type_id = var->type; - const struct btf_type *t; - - t = btf__type_by_id(btf, var_type_id); - while (btf_is_mod(t)) { - var_type_id = t->type; - t = btf__type_by_id(btf, var_type_id); - } if (off > need_off) { p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", @@ -305,8 +302,11 @@ static int do_skeleton(int argc, char **argv) opts.object_name = obj_name; obj = bpf_object__open_mem(obj_data, file_sz, &opts); if (IS_ERR(obj)) { + char err_buf[256]; + + libbpf_strerror(PTR_ERR(obj), err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); obj = NULL; - p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); goto out; } diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 33240fcc6319..c9dba7543dba 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -2,6 +2,7 @@ // Copyright (C) 2020 Facebook #define _GNU_SOURCE +#include <unistd.h> #include <linux/err.h> #include <bpf/libbpf.h> @@ -9,11 +10,12 @@ static int do_pin(int argc, char **argv) { + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, iter_opts); const char *objfile, *path; struct bpf_program *prog; struct bpf_object *obj; struct bpf_link *link; - int err; + int err = -1, map_fd = -1; if (!REQ_ARGS(2)) usage(); @@ -21,10 +23,26 @@ static int do_pin(int argc, char **argv) objfile = GET_ARG(); path = GET_ARG(); + /* optional arguments */ + if (argc) { + if (is_prefix(*argv, "map")) { + NEXT_ARG(); + + if (!REQ_ARGS(2)) { + p_err("incorrect map spec"); + return -1; + } + + map_fd = map_parse_fd(&argc, &argv); + if (map_fd < 0) + return -1; + } + } + obj = bpf_object__open(objfile); if (IS_ERR(obj)) { p_err("can't open objfile %s", objfile); - return -1; + goto close_map_fd; } err = bpf_object__load(obj); @@ -39,7 +57,10 @@ static int do_pin(int argc, char **argv) goto close_obj; } - link = bpf_program__attach_iter(prog, NULL); + if (map_fd >= 0) + iter_opts.map_fd = map_fd; + + link = bpf_program__attach_iter(prog, &iter_opts); if (IS_ERR(link)) { err = PTR_ERR(link); p_err("attach_iter failed for program %s", @@ -62,14 +83,18 @@ close_link: bpf_link__destroy(link); close_obj: bpf_object__close(obj); +close_map_fd: + if (map_fd >= 0) + close(map_fd); return err; } static int do_help(int argc, char **argv) { fprintf(stderr, - "Usage: %1$s %2$s pin OBJ PATH\n" + "Usage: %1$s %2$s pin OBJ PATH [map MAP]\n" " %1$s %2$s help\n" + " " HELP_SPEC_MAP "\n" "", bin_name, "iter"); diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index fca57ee8fafe..1b793759170e 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -22,6 +22,8 @@ static const char * const link_type_name[] = { static int link_parse_fd(int *argc, char ***argv) { + int fd; + if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -35,7 +37,10 @@ static int link_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return bpf_link_get_fd_by_id(id); + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) + p_err("failed to get link with ID %d: %s", id, strerror(errno)); + return fd; } else if (is_prefix(**argv, "pinned")) { char *path; @@ -108,7 +113,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < ARRAY_SIZE(prog_type_name)) + if (prog_info.type < prog_type_name_size) jsonw_string_field(json_wtr, "prog_type", prog_type_name[prog_info.type]); else @@ -143,6 +148,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) } jsonw_end_array(json_wtr); } + + emit_obj_refs_json(&refs_table, info->id, json_wtr); + jsonw_end_object(json_wtr); return 0; @@ -184,7 +192,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < ARRAY_SIZE(prog_type_name)) + if (prog_info.type < prog_type_name_size) printf("\n\tprog_type %s ", prog_type_name[prog_info.type]); else @@ -212,6 +220,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tpinned %s", obj->path); } } + emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); printf("\n"); @@ -257,6 +266,7 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&link_table, BPF_OBJ_LINK); + build_obj_refs_table(&refs_table, BPF_OBJ_LINK); if (argc == 2) { fd = link_parse_fd(&argc, &argv); @@ -296,6 +306,8 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(&refs_table); + return errno == ENOENT ? 0 : -1; } @@ -309,6 +321,34 @@ static int do_pin(int argc, char **argv) return err; } +static int do_detach(int argc, char **argv) +{ + int err, fd; + + if (argc != 2) { + p_err("link specifier is invalid or missing\n"); + return 1; + } + + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return 1; + + err = bpf_link_detach(fd); + if (err) + err = -errno; + close(fd); + if (err) { + p_err("failed link detach: %s", strerror(-err)); + return 1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -319,6 +359,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [LINK]\n" " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s detach LINK\n" " %1$s %2$s help\n" "\n" " " HELP_SPEC_LINK "\n" @@ -334,6 +375,7 @@ static const struct cmd cmds[] = { { "list", do_show }, { "help", do_help }, { "pin", do_pin }, + { "detach", do_detach }, { 0 } }; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 46bd716a9d86..4a191fcbeb82 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -31,6 +31,7 @@ bool relaxed_maps; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; struct pinned_obj_table link_table; +struct obj_refs_table refs_table; static void __noreturn clean_and_exit(int i) { @@ -92,9 +93,16 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv, if (argc < 1 && cmds[0].func) return cmds[0].func(argc, argv); - for (i = 0; cmds[i].func; i++) - if (is_prefix(*argv, cmds[i].cmd)) + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not supported in bootstrap mode", + cmds[i].cmd); + return -1; + } return cmds[i].func(argc - 1, argv + 1); + } + } help(argc - 1, argv + 1); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 5cdf0bc049bd..e3a79b5a9960 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -56,82 +56,21 @@ #define HELP_SPEC_LINK \ "LINK := { id LINK_ID | pinned FILE }" -static const char * const prog_type_name[] = { - [BPF_PROG_TYPE_UNSPEC] = "unspec", - [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", - [BPF_PROG_TYPE_KPROBE] = "kprobe", - [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", - [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", - [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", - [BPF_PROG_TYPE_XDP] = "xdp", - [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", - [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", - [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", - [BPF_PROG_TYPE_LWT_IN] = "lwt_in", - [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", - [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", - [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", - [BPF_PROG_TYPE_SK_SKB] = "sk_skb", - [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", - [BPF_PROG_TYPE_SK_MSG] = "sk_msg", - [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", - [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", - [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", - [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", - [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", - [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", - [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", - [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", - [BPF_PROG_TYPE_TRACING] = "tracing", - [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_PROG_TYPE_EXT] = "ext", -}; +extern const char * const prog_type_name[]; +extern const size_t prog_type_name_size; -static const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", - [BPF_CGROUP_SOCK_OPS] = "sock_ops", - [BPF_CGROUP_DEVICE] = "device", - [BPF_CGROUP_INET4_BIND] = "bind4", - [BPF_CGROUP_INET6_BIND] = "bind6", - [BPF_CGROUP_INET4_CONNECT] = "connect4", - [BPF_CGROUP_INET6_CONNECT] = "connect6", - [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", - [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", - [BPF_CGROUP_INET4_GETPEERNAME] = "getpeername4", - [BPF_CGROUP_INET6_GETPEERNAME] = "getpeername6", - [BPF_CGROUP_INET4_GETSOCKNAME] = "getsockname4", - [BPF_CGROUP_INET6_GETSOCKNAME] = "getsockname6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", - [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", - [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", - [BPF_LIRC_MODE2] = "lirc_mode2", - [BPF_FLOW_DISSECTOR] = "flow_dissector", - [BPF_TRACE_RAW_TP] = "raw_tp", - [BPF_TRACE_FENTRY] = "fentry", - [BPF_TRACE_FEXIT] = "fexit", - [BPF_MODIFY_RETURN] = "mod_ret", - [BPF_LSM_MAC] = "lsm_mac", -}; +extern const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE]; extern const char * const map_type_name[]; extern const size_t map_type_name_size; +/* keep in sync with the definition in skeleton/pid_iter.bpf.c */ enum bpf_obj_type { BPF_OBJ_UNKNOWN, BPF_OBJ_PROG, BPF_OBJ_MAP, BPF_OBJ_LINK, + BPF_OBJ_BTF, }; extern const char *bin_name; @@ -139,12 +78,14 @@ extern const char *bin_name; extern json_writer_t *json_wtr; extern bool json_output; extern bool show_pinned; +extern bool show_pids; extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; extern struct pinned_obj_table link_table; +extern struct obj_refs_table refs_table; void __printf(1, 2) p_err(const char *fmt, ...); void __printf(1, 2) p_info(const char *fmt, ...); @@ -168,12 +109,35 @@ struct pinned_obj { struct hlist_node hash; }; +struct obj_refs_table { + DECLARE_HASHTABLE(table, 16); +}; + +struct obj_ref { + int pid; + char comm[16]; +}; + +struct obj_refs { + struct hlist_node node; + __u32 id; + int ref_cnt; + struct obj_ref *refs; +}; + struct btf; struct bpf_line_info; int build_pinned_obj_table(struct pinned_obj_table *table, enum bpf_obj_type type); void delete_pinned_obj_table(struct pinned_obj_table *tab); +__weak int build_obj_refs_table(struct obj_refs_table *table, + enum bpf_obj_type type); +__weak void delete_obj_refs_table(struct obj_refs_table *table); +__weak void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, + json_writer_t *json_wtr); +__weak void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, + const char *prefix); void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); @@ -188,29 +152,34 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv, int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); -int open_obj_pinned(char *path, bool quiet); -int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); +int open_obj_pinned(const char *path, bool quiet); +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); int mount_bpffs_for_pin(const char *name); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); -int do_prog(int argc, char **arg); -int do_map(int argc, char **arg); -int do_link(int argc, char **arg); -int do_event_pipe(int argc, char **argv); -int do_cgroup(int argc, char **arg); -int do_perf(int argc, char **arg); -int do_net(int argc, char **arg); -int do_tracelog(int argc, char **arg); -int do_feature(int argc, char **argv); -int do_btf(int argc, char **argv); +/* commands available in bootstrap mode */ int do_gen(int argc, char **argv); -int do_struct_ops(int argc, char **argv); -int do_iter(int argc, char **argv); +int do_btf(int argc, char **argv); + +/* non-bootstrap only commands */ +int do_prog(int argc, char **arg) __weak; +int do_map(int argc, char **arg) __weak; +int do_link(int argc, char **arg) __weak; +int do_event_pipe(int argc, char **argv) __weak; +int do_cgroup(int argc, char **arg) __weak; +int do_perf(int argc, char **arg) __weak; +int do_net(int argc, char **arg) __weak; +int do_tracelog(int argc, char **arg) __weak; +int do_feature(int argc, char **argv) __weak; +int do_struct_ops(int argc, char **argv) __weak; +int do_iter(int argc, char **argv) __weak; int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); +int prog_parse_fds(int *argc, char ***argv, int **fds); int map_parse_fd(int *argc, char ***argv); +int map_parse_fds(int *argc, char ***argv, int **fds); int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); struct bpf_prog_linfo; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 1d3b60651078..3a27d31a1856 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -93,162 +93,6 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -static int map_fd_by_name(char *name, int **fds) -{ - unsigned int id = 0; - int fd, nb_fds = 0; - void *tmp; - int err; - - while (true) { - struct bpf_map_info info = {}; - __u32 len = sizeof(info); - - err = bpf_map_get_next_id(id, &id); - if (err) { - if (errno != ENOENT) { - p_err("%s", strerror(errno)); - goto err_close_fds; - } - return nb_fds; - } - - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) { - p_err("can't get map by id (%u): %s", - id, strerror(errno)); - goto err_close_fds; - } - - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err) { - p_err("can't get map info (%u): %s", - id, strerror(errno)); - goto err_close_fd; - } - - if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { - close(fd); - continue; - } - - if (nb_fds > 0) { - tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); - if (!tmp) { - p_err("failed to realloc"); - goto err_close_fd; - } - *fds = tmp; - } - (*fds)[nb_fds++] = fd; - } - -err_close_fd: - close(fd); -err_close_fds: - while (--nb_fds >= 0) - close((*fds)[nb_fds]); - return -1; -} - -static int map_parse_fds(int *argc, char ***argv, int **fds) -{ - if (is_prefix(**argv, "id")) { - unsigned int id; - char *endptr; - - NEXT_ARGP(); - - id = strtoul(**argv, &endptr, 0); - if (*endptr) { - p_err("can't parse %s as ID", **argv); - return -1; - } - NEXT_ARGP(); - - (*fds)[0] = bpf_map_get_fd_by_id(id); - if ((*fds)[0] < 0) { - p_err("get map by id (%u): %s", id, strerror(errno)); - return -1; - } - return 1; - } else if (is_prefix(**argv, "name")) { - char *name; - - NEXT_ARGP(); - - name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { - p_err("can't parse name"); - return -1; - } - NEXT_ARGP(); - - return map_fd_by_name(name, fds); - } else if (is_prefix(**argv, "pinned")) { - char *path; - - NEXT_ARGP(); - - path = **argv; - NEXT_ARGP(); - - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); - if ((*fds)[0] < 0) - return -1; - return 1; - } - - p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); - return -1; -} - -int map_parse_fd(int *argc, char ***argv) -{ - int *fds = NULL; - int nb_fds, fd; - - fds = malloc(sizeof(int)); - if (!fds) { - p_err("mem alloc failed"); - return -1; - } - nb_fds = map_parse_fds(argc, argv, &fds); - if (nb_fds != 1) { - if (nb_fds > 1) { - p_err("several maps match this handle"); - while (nb_fds--) - close(fds[nb_fds]); - } - fd = -1; - goto exit_free; - } - - fd = fds[0]; -exit_free: - free(fds); - return fd; -} - -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) -{ - int err; - int fd; - - fd = map_parse_fd(argc, argv); - if (fd < 0) - return -1; - - err = bpf_obj_get_info_by_fd(fd, info, info_len); - if (err) { - p_err("can't get map info: %s", strerror(errno)); - close(fd); - return err; - } - - return fd; -} - static int do_dump_btf(const struct btf_dumper *d, struct bpf_map_info *map_info, void *key, void *value) @@ -629,7 +473,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); - if (prog_type < ARRAY_SIZE(prog_type_name)) + if (prog_type < prog_type_name_size) jsonw_string_field(json_wtr, "owner_prog_type", prog_type_name[prog_type]); else @@ -666,6 +510,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_end_array(json_wtr); } + emit_obj_refs_json(&refs_table, info->id, json_wtr); + jsonw_end_object(json_wtr); return 0; @@ -712,7 +558,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); - if (prog_type < ARRAY_SIZE(prog_type_name)) + if (prog_type < prog_type_name_size) printf("owner_prog_type %s ", prog_type_name[prog_type]); else @@ -753,6 +599,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (frozen) printf("%sfrozen", info->btf_id ? " " : ""); + emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + printf("\n"); return 0; } @@ -811,6 +659,7 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&map_table, BPF_OBJ_MAP); + build_obj_refs_table(&refs_table, BPF_OBJ_MAP); if (argc == 2) return do_show_subset(argc, argv); @@ -854,6 +703,8 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(&refs_table); + return errno == ENOENT ? 0 : -1; } diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c new file mode 100644 index 000000000000..e3b116325403 --- /dev/null +++ b/tools/bpf/bpftool/pids.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <bpf/bpf.h> + +#include "main.h" +#include "skeleton/pid_iter.h" + +#ifdef BPFTOOL_WITHOUT_SKELETONS + +int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) +{ + return -ENOTSUP; +} +void delete_obj_refs_table(struct obj_refs_table *table) {} +void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) {} +void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, json_writer_t *json_writer) {} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "pid_iter.skel.h" + +static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e) +{ + struct obj_refs *refs; + struct obj_ref *ref; + void *tmp; + int i; + + hash_for_each_possible(table->table, refs, node, e->id) { + if (refs->id != e->id) + continue; + + for (i = 0; i < refs->ref_cnt; i++) { + if (refs->refs[i].pid == e->pid) + return; + } + + tmp = realloc(refs->refs, (refs->ref_cnt + 1) * sizeof(*ref)); + if (!tmp) { + p_err("failed to re-alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + refs->refs = tmp; + ref = &refs->refs[refs->ref_cnt]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt++; + + return; + } + + /* new ref */ + refs = calloc(1, sizeof(*refs)); + if (!refs) { + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + + refs->id = e->id; + refs->refs = malloc(sizeof(*refs->refs)); + if (!refs->refs) { + free(refs); + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + ref = &refs->refs[0]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt = 1; + hash_add(table->table, &refs->node, e->id); +} + +static int __printf(2, 0) +libbpf_print_none(__maybe_unused enum libbpf_print_level level, + __maybe_unused const char *format, + __maybe_unused va_list args) +{ + return 0; +} + +int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) +{ + char buf[4096]; + struct pid_iter_bpf *skel; + struct pid_iter_entry *e; + int err, ret, fd = -1, i; + libbpf_print_fn_t default_print; + + hash_init(table->table); + set_max_rlimit(); + + skel = pid_iter_bpf__open(); + if (!skel) { + p_err("failed to open PID iterator skeleton"); + return -1; + } + + skel->rodata->obj_type = type; + + /* we don't want output polluted with libbpf errors if bpf_iter is not + * supported + */ + default_print = libbpf_set_print(libbpf_print_none); + err = pid_iter_bpf__load(skel); + libbpf_set_print(default_print); + if (err) { + /* too bad, kernel doesn't support BPF iterators yet */ + err = 0; + goto out; + } + err = pid_iter_bpf__attach(skel); + if (err) { + /* if we loaded above successfully, attach has to succeed */ + p_err("failed to attach PID iterator: %d", err); + goto out; + } + + fd = bpf_iter_create(bpf_link__fd(skel->links.iter)); + if (fd < 0) { + err = -errno; + p_err("failed to create PID iterator session: %d", err); + goto out; + } + + while (true) { + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) { + err = -errno; + p_err("failed to read PID iterator output: %d", err); + goto out; + } + if (ret == 0) + break; + if (ret % sizeof(*e)) { + err = -EINVAL; + p_err("invalid PID iterator output format"); + goto out; + } + ret /= sizeof(*e); + + e = (void *)buf; + for (i = 0; i < ret; i++, e++) { + add_ref(table, e); + } + } + err = 0; +out: + if (fd >= 0) + close(fd); + pid_iter_bpf__destroy(skel); + return err; +} + +void delete_obj_refs_table(struct obj_refs_table *table) +{ + struct obj_refs *refs; + struct hlist_node *tmp; + unsigned int bkt; + + hash_for_each_safe(table->table, bkt, tmp, refs, node) { + hash_del(&refs->node); + free(refs->refs); + free(refs); + } +} + +void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, + json_writer_t *json_writer) +{ + struct obj_refs *refs; + struct obj_ref *ref; + int i; + + if (hash_empty(table->table)) + return; + + hash_for_each_possible(table->table, refs, node, id) { + if (refs->id != id) + continue; + if (refs->ref_cnt == 0) + break; + + jsonw_name(json_writer, "pids"); + jsonw_start_array(json_writer); + for (i = 0; i < refs->ref_cnt; i++) { + ref = &refs->refs[i]; + jsonw_start_object(json_writer); + jsonw_int_field(json_writer, "pid", ref->pid); + jsonw_string_field(json_writer, "comm", ref->comm); + jsonw_end_object(json_writer); + } + jsonw_end_array(json_writer); + break; + } +} + +void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) +{ + struct obj_refs *refs; + struct obj_ref *ref; + int i; + + if (hash_empty(table->table)) + return; + + hash_for_each_possible(table->table, refs, node, id) { + if (refs->id != id) + continue; + if (refs->ref_cnt == 0) + break; + + printf("%s", prefix); + for (i = 0; i < refs->ref_cnt; i++) { + ref = &refs->refs[i]; + printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid); + } + break; + } +} + + +#endif diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index a5eff83496f2..158995d853b0 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -29,6 +29,42 @@ #include "main.h" #include "xlated_dumper.h" +const char * const prog_type_name[] = { + [BPF_PROG_TYPE_UNSPEC] = "unspec", + [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", + [BPF_PROG_TYPE_KPROBE] = "kprobe", + [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", + [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", + [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", + [BPF_PROG_TYPE_XDP] = "xdp", + [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", + [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", + [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", + [BPF_PROG_TYPE_LWT_IN] = "lwt_in", + [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", + [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", + [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", + [BPF_PROG_TYPE_SK_SKB] = "sk_skb", + [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", + [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", + [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", + [BPF_PROG_TYPE_TRACING] = "tracing", + [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_PROG_TYPE_EXT] = "ext", + [BPF_PROG_TYPE_LSM] = "lsm", + [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", +}; + +const size_t prog_type_name_size = ARRAY_SIZE(prog_type_name); + enum dump_mode { DUMP_JITED, DUMP_XLATED, @@ -86,158 +122,6 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) strftime(buf, size, "%FT%T%z", &load_tm); } -static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) -{ - unsigned int id = 0; - int fd, nb_fds = 0; - void *tmp; - int err; - - while (true) { - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); - - err = bpf_prog_get_next_id(id, &id); - if (err) { - if (errno != ENOENT) { - p_err("%s", strerror(errno)); - goto err_close_fds; - } - return nb_fds; - } - - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) { - p_err("can't get prog by id (%u): %s", - id, strerror(errno)); - goto err_close_fds; - } - - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err) { - p_err("can't get prog info (%u): %s", - id, strerror(errno)); - goto err_close_fd; - } - - if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || - (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { - close(fd); - continue; - } - - if (nb_fds > 0) { - tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); - if (!tmp) { - p_err("failed to realloc"); - goto err_close_fd; - } - *fds = tmp; - } - (*fds)[nb_fds++] = fd; - } - -err_close_fd: - close(fd); -err_close_fds: - while (--nb_fds >= 0) - close((*fds)[nb_fds]); - return -1; -} - -static int prog_parse_fds(int *argc, char ***argv, int **fds) -{ - if (is_prefix(**argv, "id")) { - unsigned int id; - char *endptr; - - NEXT_ARGP(); - - id = strtoul(**argv, &endptr, 0); - if (*endptr) { - p_err("can't parse %s as ID", **argv); - return -1; - } - NEXT_ARGP(); - - (*fds)[0] = bpf_prog_get_fd_by_id(id); - if ((*fds)[0] < 0) { - p_err("get by id (%u): %s", id, strerror(errno)); - return -1; - } - return 1; - } else if (is_prefix(**argv, "tag")) { - unsigned char tag[BPF_TAG_SIZE]; - - NEXT_ARGP(); - - if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, - tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) - != BPF_TAG_SIZE) { - p_err("can't parse tag"); - return -1; - } - NEXT_ARGP(); - - return prog_fd_by_nametag(tag, fds, true); - } else if (is_prefix(**argv, "name")) { - char *name; - - NEXT_ARGP(); - - name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { - p_err("can't parse name"); - return -1; - } - NEXT_ARGP(); - - return prog_fd_by_nametag(name, fds, false); - } else if (is_prefix(**argv, "pinned")) { - char *path; - - NEXT_ARGP(); - - path = **argv; - NEXT_ARGP(); - - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); - if ((*fds)[0] < 0) - return -1; - return 1; - } - - p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); - return -1; -} - -int prog_parse_fd(int *argc, char ***argv) -{ - int *fds = NULL; - int nb_fds, fd; - - fds = malloc(sizeof(int)); - if (!fds) { - p_err("mem alloc failed"); - return -1; - } - nb_fds = prog_parse_fds(argc, argv, &fds); - if (nb_fds != 1) { - if (nb_fds > 1) { - p_err("several programs match this handle"); - while (nb_fds--) - close(fds[nb_fds]); - } - fd = -1; - goto exit_free; - } - - fd = fds[0]; -exit_free: - free(fds); - return fd; -} - static void show_prog_maps(int fd, __u32 num_maps) { struct bpf_prog_info info = {}; @@ -342,6 +226,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_array(json_wtr); } + emit_obj_refs_json(&refs_table, info->id, json_wtr); + jsonw_end_object(json_wtr); } @@ -408,6 +294,8 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) if (info->btf_id) printf("\n\tbtf_id %d", info->btf_id); + emit_obj_refs_plain(&refs_table, info->id, "\n\tpids "); + printf("\n"); } @@ -473,6 +361,7 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); + build_obj_refs_table(&refs_table, BPF_OBJ_PROG); if (argc == 2) return do_show_subset(argc, argv); @@ -514,6 +403,8 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(&refs_table); + return err; } @@ -2016,7 +1907,7 @@ static int do_help(int argc, char **argv) " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" " cgroup/getsockopt | cgroup/setsockopt |\n" - " struct_ops | fentry | fexit | freplace }\n" + " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n" diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c new file mode 100644 index 000000000000..d9b420972934 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2020 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_tracing.h> +#include "pid_iter.h" + +/* keep in sync with the definition in main.h */ +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, + BPF_OBJ_LINK, + BPF_OBJ_BTF, +}; + +extern const void bpf_link_fops __ksym; +extern const void bpf_map_fops __ksym; +extern const void bpf_prog_fops __ksym; +extern const void btf_fops __ksym; + +const volatile enum bpf_obj_type obj_type = BPF_OBJ_UNKNOWN; + +static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) +{ + switch (type) { + case BPF_OBJ_PROG: + return BPF_CORE_READ((struct bpf_prog *)ent, aux, id); + case BPF_OBJ_MAP: + return BPF_CORE_READ((struct bpf_map *)ent, id); + case BPF_OBJ_BTF: + return BPF_CORE_READ((struct btf *)ent, id); + case BPF_OBJ_LINK: + return BPF_CORE_READ((struct bpf_link *)ent, id); + default: + return 0; + } +} + +SEC("iter/task_file") +int iter(struct bpf_iter__task_file *ctx) +{ + struct file *file = ctx->file; + struct task_struct *task = ctx->task; + struct pid_iter_entry e; + const void *fops; + + if (!file || !task) + return 0; + + switch (obj_type) { + case BPF_OBJ_PROG: + fops = &bpf_prog_fops; + break; + case BPF_OBJ_MAP: + fops = &bpf_map_fops; + break; + case BPF_OBJ_BTF: + fops = &btf_fops; + break; + case BPF_OBJ_LINK: + fops = &bpf_link_fops; + break; + default: + return 0; + } + + if (file->f_op != fops) + return 0; + + e.pid = task->tgid; + e.id = get_obj_id(file->private_data, obj_type); + bpf_probe_read_kernel(&e.comm, sizeof(e.comm), + task->group_leader->comm); + bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h new file mode 100644 index 000000000000..5692cf257adb --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (c) 2020 Facebook */ +#ifndef __PID_ITER_H +#define __PID_ITER_H + +struct pid_iter_entry { + __u32 id; + int pid; + char comm[16]; +}; + +#endif diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 20034c12f7c5..4e3512f700c0 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -1,7 +1,6 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include "profiler.h" -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> @@ -116,4 +115,4 @@ int BPF_PROG(fexit_XXX) return 0; } -char LICENSE[] SEC("license") = "GPL"; +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/profiler.h b/tools/bpf/bpftool/skeleton/profiler.h deleted file mode 100644 index 1f767e9510f7..000000000000 --- a/tools/bpf/bpftool/skeleton/profiler.h +++ /dev/null @@ -1,46 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __PROFILER_H -#define __PROFILER_H - -/* useful typedefs from vmlinux.h */ - -typedef signed char __s8; -typedef unsigned char __u8; -typedef short int __s16; -typedef short unsigned int __u16; -typedef int __s32; -typedef unsigned int __u32; -typedef long long int __s64; -typedef long long unsigned int __u64; - -typedef __s8 s8; -typedef __u8 u8; -typedef __s16 s16; -typedef __u16 u16; -typedef __s32 s32; -typedef __u32 u32; -typedef __s64 s64; -typedef __u64 u64; - -enum { - false = 0, - true = 1, -}; - -#ifdef __CHECKER__ -#define __bitwise__ __attribute__((bitwise)) -#else -#define __bitwise__ -#endif - -typedef __u16 __bitwise__ __le16; -typedef __u16 __bitwise__ __be16; -typedef __u32 __bitwise__ __le32; -typedef __u32 __bitwise__ __be32; -typedef __u64 __bitwise__ __le64; -typedef __u64 __bitwise__ __be64; - -typedef __u16 __bitwise__ __sum16; -typedef __u32 __bitwise__ __wsum; - -#endif /* __PROFILER_H */ diff --git a/tools/bpf/resolve_btfids/.gitignore b/tools/bpf/resolve_btfids/.gitignore new file mode 100644 index 000000000000..a026df7dc280 --- /dev/null +++ b/tools/bpf/resolve_btfids/.gitignore @@ -0,0 +1,4 @@ +/FEATURE-DUMP.libbpf +/bpf_helper_defs.h +/fixdep +/resolve_btfids diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build new file mode 100644 index 000000000000..ae82da03f9bf --- /dev/null +++ b/tools/bpf/resolve_btfids/Build @@ -0,0 +1,10 @@ +resolve_btfids-y += main.o +resolve_btfids-y += rbtree.o +resolve_btfids-y += zalloc.o +resolve_btfids-y += string.o +resolve_btfids-y += ctype.o +resolve_btfids-y += str_error_r.o + +$(OUTPUT)%.o: ../../lib/%.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile new file mode 100644 index 000000000000..a88cd4426398 --- /dev/null +++ b/tools/bpf/resolve_btfids/Makefile @@ -0,0 +1,91 @@ +# SPDX-License-Identifier: GPL-2.0-only +include ../../scripts/Makefile.include + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +ifeq ($(V),1) + Q = + msg = +else + Q = @ + msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + MAKEFLAGS=--no-print-directory +endif + +# always use the host compiler +ifneq ($(LLVM),) +HOSTAR ?= llvm-ar +HOSTCC ?= clang +HOSTLD ?= ld.lld +else +HOSTAR ?= ar +HOSTCC ?= gcc +HOSTLD ?= ld +endif +AR = $(HOSTAR) +CC = $(HOSTCC) +LD = $(HOSTLD) + +OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ + +LIBBPF_SRC := $(srctree)/tools/lib/bpf/ +SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ + +BPFOBJ := $(OUTPUT)/libbpf.a +SUBCMDOBJ := $(OUTPUT)/libsubcmd.a + +BINARY := $(OUTPUT)/resolve_btfids +BINARY_IN := $(BINARY)-in.o + +all: $(BINARY) + +$(OUTPUT): + $(call msg,MKDIR,,$@) + $(Q)mkdir -p $(OUTPUT) + +$(SUBCMDOBJ): fixdep FORCE + $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(OUTPUT) + +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + +CFLAGS := -g \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(LIBBPF_SRC) \ + -I$(SUBCMD_SRC) + +LIBS = -lelf -lz + +export srctree OUTPUT CFLAGS Q +include $(srctree)/tools/build/Makefile.include + +$(BINARY_IN): fixdep FORCE + $(Q)$(MAKE) $(build)=resolve_btfids + +$(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) + $(call msg,LINK,$@) + $(Q)$(CC) $(BINARY_IN) $(LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) + +libsubcmd-clean: + $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(OUTPUT) clean + +libbpf-clean: + $(Q)$(MAKE) -C $(LIBBPF_SRC) OUTPUT=$(OUTPUT) clean + +clean: libsubcmd-clean libbpf-clean fixdep-clean + $(call msg,CLEAN,$(BINARY)) + $(Q)$(RM) -f $(BINARY); \ + find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + +tags: + $(call msg,GEN,,tags) + $(Q)ctags -R . $(LIBBPF_SRC) $(SUBCMD_SRC) + +FORCE: + +.PHONY: all FORCE clean tags diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c new file mode 100644 index 000000000000..52d883325a23 --- /dev/null +++ b/tools/bpf/resolve_btfids/main.c @@ -0,0 +1,665 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * resolve_btfids scans Elf object for .BTF_ids section and resolves + * its symbols with BTF ID values. + * + * Each symbol points to 4 bytes data and is expected to have + * following name syntax: + * + * __BTF_ID__<type>__<symbol>[__<id>] + * + * type is: + * + * func - lookup BTF_KIND_FUNC symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__func__vfs_close__1: + * .zero 4 + * + * struct - lookup BTF_KIND_STRUCT symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__struct__sk_buff__1: + * .zero 4 + * + * union - lookup BTF_KIND_UNION symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__union__thread_union__1: + * .zero 4 + * + * typedef - lookup BTF_KIND_TYPEDEF symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__typedef__pid_t__1: + * .zero 4 + * + * set - store symbol size into first 4 bytes and sort following + * ID list + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__func__vfs_getattr__3: + * .zero 4 + * __BTF_ID__func__vfs_fallocate__4: + * .zero 4 + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <stdlib.h> +#include <libelf.h> +#include <gelf.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <linux/rbtree.h> +#include <linux/zalloc.h> +#include <linux/err.h> +#include <btf.h> +#include <libbpf.h> +#include <parse-options.h> + +#define BTF_IDS_SECTION ".BTF_ids" +#define BTF_ID "__BTF_ID__" + +#define BTF_STRUCT "struct" +#define BTF_UNION "union" +#define BTF_TYPEDEF "typedef" +#define BTF_FUNC "func" +#define BTF_SET "set" + +#define ADDR_CNT 100 + +struct btf_id { + struct rb_node rb_node; + char *name; + union { + int id; + int cnt; + }; + int addr_cnt; + Elf64_Addr addr[ADDR_CNT]; +}; + +struct object { + const char *path; + const char *btf; + + struct { + int fd; + Elf *elf; + Elf_Data *symbols; + Elf_Data *idlist; + int symbols_shndx; + int idlist_shndx; + size_t strtabidx; + unsigned long idlist_addr; + } efile; + + struct rb_root sets; + struct rb_root structs; + struct rb_root unions; + struct rb_root typedefs; + struct rb_root funcs; + + int nr_funcs; + int nr_structs; + int nr_unions; + int nr_typedefs; +}; + +static int verbose; + +int eprintf(int level, int var, const char *fmt, ...) +{ + va_list args; + int ret; + + if (var >= level) { + va_start(args, fmt); + ret = vfprintf(stderr, fmt, args); + va_end(args); + } + return ret; +} + +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_debug(fmt, ...) \ + eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) + +static bool is_btf_id(const char *name) +{ + return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1); +} + +static struct btf_id *btf_id__find(struct rb_root *root, const char *name) +{ + struct rb_node *p = root->rb_node; + struct btf_id *id; + int cmp; + + while (p) { + id = rb_entry(p, struct btf_id, rb_node); + cmp = strcmp(id->name, name); + if (cmp < 0) + p = p->rb_left; + else if (cmp > 0) + p = p->rb_right; + else + return id; + } + return NULL; +} + +static struct btf_id* +btf_id__add(struct rb_root *root, char *name, bool unique) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct btf_id *id; + int cmp; + + while (*p != NULL) { + parent = *p; + id = rb_entry(parent, struct btf_id, rb_node); + cmp = strcmp(id->name, name); + if (cmp < 0) + p = &(*p)->rb_left; + else if (cmp > 0) + p = &(*p)->rb_right; + else + return unique ? NULL : id; + } + + id = zalloc(sizeof(*id)); + if (id) { + pr_debug("adding symbol %s\n", name); + id->name = name; + rb_link_node(&id->rb_node, parent, p); + rb_insert_color(&id->rb_node, root); + } + return id; +} + +static char *get_id(const char *prefix_end) +{ + /* + * __BTF_ID__func__vfs_truncate__0 + * prefix_end = ^ + */ + char *p, *id = strdup(prefix_end + sizeof("__") - 1); + + if (id) { + /* + * __BTF_ID__func__vfs_truncate__0 + * id = ^ + * + * cut the unique id part + */ + p = strrchr(id, '_'); + p--; + if (*p != '_') { + free(id); + return NULL; + } + *p = '\0'; + } + return id; +} + +static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) +{ + char *id; + + id = get_id(name + size); + if (!id) { + pr_err("FAILED to parse symbol name: %s\n", name); + return NULL; + } + + return btf_id__add(root, id, false); +} + +static int elf_collect(struct object *obj) +{ + Elf_Scn *scn = NULL; + size_t shdrstrndx; + int idx = 0; + Elf *elf; + int fd; + + fd = open(obj->path, O_RDWR, 0666); + if (fd == -1) { + pr_err("FAILED cannot open %s: %s\n", + obj->path, strerror(errno)); + return -1; + } + + elf_version(EV_CURRENT); + + elf = elf_begin(fd, ELF_C_RDWR_MMAP, NULL); + if (!elf) { + pr_err("FAILED cannot create ELF descriptor: %s\n", + elf_errmsg(-1)); + return -1; + } + + obj->efile.fd = fd; + obj->efile.elf = elf; + + elf_flagelf(elf, ELF_C_SET, ELF_F_LAYOUT); + + if (elf_getshdrstrndx(elf, &shdrstrndx) != 0) { + pr_err("FAILED cannot get shdr str ndx\n"); + return -1; + } + + /* + * Scan all the elf sections and look for save data + * from .BTF_ids section and symbols. + */ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + Elf_Data *data; + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_err("FAILED get section(%d) header\n", idx); + return -1; + } + + name = elf_strptr(elf, shdrstrndx, sh.sh_name); + if (!name) { + pr_err("FAILED get section(%d) name\n", idx); + return -1; + } + + data = elf_getdata(scn, 0); + if (!data) { + pr_err("FAILED to get section(%d) data from %s\n", + idx, name); + return -1; + } + + pr_debug2("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + idx, name, (unsigned long) data->d_size, + (int) sh.sh_link, (unsigned long) sh.sh_flags, + (int) sh.sh_type); + + if (sh.sh_type == SHT_SYMTAB) { + obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; + obj->efile.strtabidx = sh.sh_link; + } else if (!strcmp(name, BTF_IDS_SECTION)) { + obj->efile.idlist = data; + obj->efile.idlist_shndx = idx; + obj->efile.idlist_addr = sh.sh_addr; + } + } + + return 0; +} + +static int symbols_collect(struct object *obj) +{ + Elf_Scn *scn = NULL; + int n, i, err = 0; + GElf_Shdr sh; + char *name; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -1; + + if (gelf_getshdr(scn, &sh) != &sh) + return -1; + + n = sh.sh_size / sh.sh_entsize; + + /* + * Scan symbols and look for the ones starting with + * __BTF_ID__* over .BTF_ids section. + */ + for (i = 0; !err && i < n; i++) { + char *tmp, *prefix; + struct btf_id *id; + GElf_Sym sym; + int err = -1; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -1; + + if (sym.st_shndx != obj->efile.idlist_shndx) + continue; + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + + if (!is_btf_id(name)) + continue; + + /* + * __BTF_ID__TYPE__vfs_truncate__0 + * prefix = ^ + */ + prefix = name + sizeof(BTF_ID) - 1; + + /* struct */ + if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) { + obj->nr_structs++; + id = add_symbol(&obj->structs, prefix, sizeof(BTF_STRUCT) - 1); + /* union */ + } else if (!strncmp(prefix, BTF_UNION, sizeof(BTF_UNION) - 1)) { + obj->nr_unions++; + id = add_symbol(&obj->unions, prefix, sizeof(BTF_UNION) - 1); + /* typedef */ + } else if (!strncmp(prefix, BTF_TYPEDEF, sizeof(BTF_TYPEDEF) - 1)) { + obj->nr_typedefs++; + id = add_symbol(&obj->typedefs, prefix, sizeof(BTF_TYPEDEF) - 1); + /* func */ + } else if (!strncmp(prefix, BTF_FUNC, sizeof(BTF_FUNC) - 1)) { + obj->nr_funcs++; + id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1); + /* set */ + } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { + id = add_symbol(&obj->sets, prefix, sizeof(BTF_SET) - 1); + /* + * SET objects store list's count, which is encoded + * in symbol's size, together with 'cnt' field hence + * that - 1. + */ + if (id) + id->cnt = sym.st_size / sizeof(int) - 1; + } else { + pr_err("FAILED unsupported prefix %s\n", prefix); + return -1; + } + + if (!id) + return -ENOMEM; + + if (id->addr_cnt >= ADDR_CNT) { + pr_err("FAILED symbol %s crossed the number of allowed lists", + id->name); + return -1; + } + id->addr[id->addr_cnt++] = sym.st_value; + } + + return 0; +} + +static int symbols_resolve(struct object *obj) +{ + int nr_typedefs = obj->nr_typedefs; + int nr_structs = obj->nr_structs; + int nr_unions = obj->nr_unions; + int nr_funcs = obj->nr_funcs; + int err, type_id; + struct btf *btf; + __u32 nr; + + btf = btf__parse(obj->btf ?: obj->path, NULL); + err = libbpf_get_error(btf); + if (err) { + pr_err("FAILED: load BTF from %s: %s", + obj->path, strerror(err)); + return -1; + } + + err = -1; + nr = btf__get_nr_types(btf); + + /* + * Iterate all the BTF types and search for collected symbol IDs. + */ + for (type_id = 1; type_id <= nr; type_id++) { + const struct btf_type *type; + struct rb_root *root; + struct btf_id *id; + const char *str; + int *nr; + + type = btf__type_by_id(btf, type_id); + if (!type) { + pr_err("FAILED: malformed BTF, can't resolve type for ID %d\n", + type_id); + goto out; + } + + if (btf_is_func(type) && nr_funcs) { + nr = &nr_funcs; + root = &obj->funcs; + } else if (btf_is_struct(type) && nr_structs) { + nr = &nr_structs; + root = &obj->structs; + } else if (btf_is_union(type) && nr_unions) { + nr = &nr_unions; + root = &obj->unions; + } else if (btf_is_typedef(type) && nr_typedefs) { + nr = &nr_typedefs; + root = &obj->typedefs; + } else + continue; + + str = btf__name_by_offset(btf, type->name_off); + if (!str) { + pr_err("FAILED: malformed BTF, can't resolve name for ID %d\n", + type_id); + goto out; + } + + id = btf_id__find(root, str); + if (id) { + id->id = type_id; + (*nr)--; + } + } + + err = 0; +out: + btf__free(btf); + return err; +} + +static int id_patch(struct object *obj, struct btf_id *id) +{ + Elf_Data *data = obj->efile.idlist; + int *ptr = data->d_buf; + int i; + + if (!id->id) { + pr_err("FAILED unresolved symbol %s\n", id->name); + return -EINVAL; + } + + for (i = 0; i < id->addr_cnt; i++) { + unsigned long addr = id->addr[i]; + unsigned long idx = addr - obj->efile.idlist_addr; + + pr_debug("patching addr %5lu: ID %7d [%s]\n", + idx, id->id, id->name); + + if (idx >= data->d_size) { + pr_err("FAILED patching index %lu out of bounds %lu\n", + idx, data->d_size); + return -1; + } + + idx = idx / sizeof(int); + ptr[idx] = id->id; + } + + return 0; +} + +static int __symbols_patch(struct object *obj, struct rb_root *root) +{ + struct rb_node *next; + struct btf_id *id; + + next = rb_first(root); + while (next) { + id = rb_entry(next, struct btf_id, rb_node); + + if (id_patch(obj, id)) + return -1; + + next = rb_next(next); + } + return 0; +} + +static int cmp_id(const void *pa, const void *pb) +{ + const int *a = pa, *b = pb; + + return *a - *b; +} + +static int sets_patch(struct object *obj) +{ + Elf_Data *data = obj->efile.idlist; + int *ptr = data->d_buf; + struct rb_node *next; + + next = rb_first(&obj->sets); + while (next) { + unsigned long addr, idx; + struct btf_id *id; + int *base; + int cnt; + + id = rb_entry(next, struct btf_id, rb_node); + addr = id->addr[0]; + idx = addr - obj->efile.idlist_addr; + + /* sets are unique */ + if (id->addr_cnt != 1) { + pr_err("FAILED malformed data for set '%s'\n", + id->name); + return -1; + } + + idx = idx / sizeof(int); + base = &ptr[idx] + 1; + cnt = ptr[idx]; + + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", + (idx + 1) * sizeof(int), cnt, id->name); + + qsort(base, cnt, sizeof(int), cmp_id); + + next = rb_next(next); + } +} + +static int symbols_patch(struct object *obj) +{ + int err; + + if (__symbols_patch(obj, &obj->structs) || + __symbols_patch(obj, &obj->unions) || + __symbols_patch(obj, &obj->typedefs) || + __symbols_patch(obj, &obj->funcs) || + __symbols_patch(obj, &obj->sets)) + return -1; + + if (sets_patch(obj)) + return -1; + + elf_flagdata(obj->efile.idlist, ELF_C_SET, ELF_F_DIRTY); + + err = elf_update(obj->efile.elf, ELF_C_WRITE); + if (err < 0) { + pr_err("FAILED elf_update(WRITE): %s\n", + elf_errmsg(-1)); + } + + pr_debug("update %s for %s\n", + err >= 0 ? "ok" : "failed", obj->path); + return err < 0 ? -1 : 0; +} + +static const char * const resolve_btfids_usage[] = { + "resolve_btfids [<options>] <ELF object>", + NULL +}; + +int main(int argc, const char **argv) +{ + bool no_fail = false; + struct object obj = { + .efile = { + .idlist_shndx = -1, + .symbols_shndx = -1, + }, + .structs = RB_ROOT, + .unions = RB_ROOT, + .typedefs = RB_ROOT, + .funcs = RB_ROOT, + .sets = RB_ROOT, + }; + struct option btfid_options[] = { + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show errors, etc)"), + OPT_STRING(0, "btf", &obj.btf, "BTF data", + "BTF data"), + OPT_BOOLEAN(0, "no-fail", &no_fail, + "do not fail if " BTF_IDS_SECTION " section is not found"), + OPT_END() + }; + int err = -1; + + argc = parse_options(argc, argv, btfid_options, resolve_btfids_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc != 1) + usage_with_options(resolve_btfids_usage, btfid_options); + + obj.path = argv[0]; + + if (elf_collect(&obj)) + goto out; + + /* + * We did not find .BTF_ids section or symbols section, + * nothing to do.. + */ + if (obj.efile.idlist_shndx == -1 || + obj.efile.symbols_shndx == -1) { + if (no_fail) + return 0; + pr_err("FAILED to find needed sections\n"); + return -1; + } + + if (symbols_collect(&obj)) + goto out; + + if (symbols_resolve(&obj)) + goto out; + + if (symbols_patch(&obj)) + goto out; + + err = 0; +out: + if (obj.efile.elf) + elf_end(obj.efile.elf); + close(obj.efile.fd); + return err; +} diff --git a/tools/build/Build.include b/tools/build/Build.include index 9ec01f4454f9..585486e40995 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -74,7 +74,8 @@ dep-cmd = $(if $(wildcard $(fixdep)), # dependencies in the cmd file if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)), \ @set -e; \ - $(echo-cmd) $(cmd_$(1)) && $(dep-cmd)) + $(echo-cmd) $(cmd_$(1)); \ + $(dep-cmd)) # if_changed - execute command if any prerequisite is newer than # target, or command line has changed diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 93b590d81209..846ee1341a5c 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -68,7 +68,7 @@ FILES= \ test-llvm-version.bin \ test-libaio.bin \ test-libzstd.bin \ - test-clang-bpf-global-var.bin \ + test-clang-bpf-co-re.bin \ test-file-handle.bin \ test-libpfm4.bin @@ -323,7 +323,7 @@ $(OUTPUT)test-libaio.bin: $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd -$(OUTPUT)test-clang-bpf-global-var.bin: +$(OUTPUT)test-clang-bpf-co-re.bin: $(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) | \ grep BTF_KIND_VAR diff --git a/tools/build/feature/test-clang-bpf-co-re.c b/tools/build/feature/test-clang-bpf-co-re.c new file mode 100644 index 000000000000..cb5265bfdd83 --- /dev/null +++ b/tools/build/feature/test-clang-bpf-co-re.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +struct test { + int a; + int b; +} __attribute__((preserve_access_index)); + +volatile struct test global_value_for_test = {}; diff --git a/tools/build/feature/test-clang-bpf-global-var.c b/tools/build/feature/test-clang-bpf-global-var.c deleted file mode 100644 index 221f1481d52e..000000000000 --- a/tools/build/feature/test-clang-bpf-global-var.c +++ /dev/null @@ -1,4 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2020 Facebook - -volatile int global_value_for_test = 1; diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 3c21de88af9e..f4699f9b46ba 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -173,7 +173,7 @@ class IocgStat: self.usages = [] self.usage = 0 for i in range(NR_USAGE_SLOTS): - usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_() + usage = iocg.usages[(usage_idx + 1 + i) % NR_USAGE_SLOTS].value_() upct = usage * 100 / HWEIGHT_WHOLE self.usages.append(upct) self.usage = max(self.usage, upct) diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 30ed0e06f52a..1a303a81aeef 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -45,7 +45,7 @@ int monitor_device(const char *device_name, if (fd == -1) { ret = -errno; fprintf(stderr, "Failed to open %s\n", chrdev_name); - goto exit_close_error; + goto exit_free_name; } req.lineoffset = line; @@ -117,6 +117,7 @@ int monitor_device(const char *device_name, exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret; } diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c index 06003789e7c7..16a5d9cb9da2 100644 --- a/tools/gpio/gpio-utils.c +++ b/tools/gpio/gpio-utils.c @@ -75,7 +75,7 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines, ret = -errno; fprintf(stderr, "Failed to open %s, %s\n", chrdev_name, strerror(errno)); - goto exit_close_error; + goto exit_free_name; } for (i = 0; i < nlines; i++) @@ -94,9 +94,9 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines, "GPIO_GET_LINEHANDLE_IOCTL", ret, strerror(errno)); } -exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret < 0 ? ret : req.fd; } diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index 8a71ad36f83b..b08d7a5e779b 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ int list_device(const char *device_name) if (fd == -1) { ret = -errno; fprintf(stderr, "Failed to open %s\n", chrdev_name); - goto exit_close_error; + goto exit_free_name; } /* Inspect this GPIO chip */ @@ -141,6 +141,7 @@ int list_device(const char *device_name) exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret; } diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h new file mode 100644 index 000000000000..4867d549e3c1 --- /dev/null +++ b/tools/include/linux/btf_ids.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_BTF_IDS_H +#define _LINUX_BTF_IDS_H + +#ifdef CONFIG_DEBUG_INFO_BTF + +#include <linux/compiler.h> /* for __PASTE */ + +/* + * Following macros help to define lists of BTF IDs placed + * in .BTF_ids section. They are initially filled with zeros + * (during compilation) and resolved later during the + * linking phase by resolve_btfids tool. + * + * Any change in list layout must be reflected in resolve_btfids + * tool logic. + */ + +#define BTF_IDS_SECTION ".BTF_ids" + +#define ____BTF_ID(symbol) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".local " #symbol " ; \n" \ +".type " #symbol ", STT_OBJECT; \n" \ +".size " #symbol ", 4; \n" \ +#symbol ": \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define __BTF_ID(symbol) \ + ____BTF_ID(symbol) + +#define __ID(prefix) \ + __PASTE(prefix, __COUNTER__) + +/* + * The BTF_ID defines unique symbol for each ID pointing + * to 4 zero bytes. + */ +#define BTF_ID(prefix, name) \ + __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__)) + +/* + * The BTF_ID_LIST macro defines pure (unsorted) list + * of BTF IDs, with following layout: + * + * BTF_ID_LIST(list1) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * + * list1: + * __BTF_ID__type1__name1__1: + * .zero 4 + * __BTF_ID__type2__name2__2: + * .zero 4 + * + */ +#define __BTF_ID_LIST(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " " #name "; \n" \ +#name ":; \n" \ +".popsection; \n"); \ + +#define BTF_ID_LIST(name) \ +__BTF_ID_LIST(name, local) \ +extern u32 name[]; + +#define BTF_ID_LIST_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) + +/* + * The BTF_ID_UNUSED macro defines 4 zero bytes. + * It's used when we want to define 'unused' entry + * in BTF_ID_LIST, like: + * + * BTF_ID_LIST(bpf_skb_output_btf_ids) + * BTF_ID(struct, sk_buff) + * BTF_ID_UNUSED + * BTF_ID(struct, task_struct) + */ + +#define BTF_ID_UNUSED \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#else + +#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID(prefix, name) +#define BTF_ID_UNUSED +#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; + +#endif /* CONFIG_DEBUG_INFO_BTF */ + +#ifdef CONFIG_NET +/* Define a list of socket types which can be the argument for + * skc_to_*_sock() helpers. All these sockets should have + * sock_common as the first argument in its memory layout. + */ +#define BTF_SOCK_TYPE_xxx \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + +enum { +#define BTF_SOCK_TYPE(name, str) name, +BTF_SOCK_TYPE_xxx +#undef BTF_SOCK_TYPE +MAX_BTF_SOCK_TYPE, +}; + +extern u32 btf_sock_ids[]; +#endif + +#endif diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 9f9002734e19..2b3f7353e891 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -111,8 +111,6 @@ # define noinline #endif -#define uninitialized_var(x) x = *(&(x)) - #include <linux/types.h> /* @@ -201,4 +199,8 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __fallthrough #endif +/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ +#define ___PASTE(a, b) a##b +#define __PASTE(a, b) ___PASTE(a, b) + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h index 67e01bbadbfe..501262aee8ff 100644 --- a/tools/include/linux/irqflags.h +++ b/tools/include/linux/irqflags.h @@ -2,9 +2,9 @@ #ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ #define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -# define lockdep_hardirq_context(p) 0 +# define lockdep_hardirq_context() 0 # define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled(p) 0 +# define lockdep_hardirqs_enabled() 0 # define lockdep_softirqs_enabled(p) 0 # define lockdep_hardirq_enter() do { } while (0) # define lockdep_hardirq_exit() do { } while (0) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index f4a01305d9a6..c8c189a5f0a6 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -606,9 +606,9 @@ __SYSCALL(__NR_sendto, sys_sendto) #define __NR_recvfrom 207 __SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom) #define __NR_setsockopt 208 -__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt) +__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt) #define __NR_getsockopt 209 -__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt) +__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt) #define __NR_shutdown 210 __SYSCALL(__NR_shutdown, sys_shutdown) #define __NR_sendmsg 211 diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8bd33050b7bb..b134e679e9db 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -117,6 +117,7 @@ enum bpf_cmd { BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, BPF_ITER_CREATE, + BPF_LINK_DETACH, }; enum bpf_map_type { @@ -189,6 +190,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, + BPF_PROG_TYPE_SK_LOOKUP, }; enum bpf_attach_type { @@ -226,6 +228,10 @@ enum bpf_attach_type { BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, + BPF_CGROUP_INET_SOCK_RELEASE, + BPF_XDP_CPUMAP, + BPF_SK_LOOKUP, + BPF_XDP, __MAX_BPF_ATTACH_TYPE }; @@ -238,10 +244,18 @@ enum bpf_link_type { BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, + BPF_LINK_TYPE_XDP = 6, MAX_BPF_LINK_TYPE, }; +enum bpf_iter_link_info { + BPF_ITER_LINK_UNSPEC = 0, + BPF_ITER_LINK_MAP_FD = 1, + + MAX_BPF_ITER_LINK_INFO, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -603,7 +617,10 @@ union bpf_attr { struct { /* struct used by BPF_LINK_CREATE command */ __u32 prog_fd; /* eBPF program to attach */ - __u32 target_fd; /* object to attach to */ + union { + __u32 target_fd; /* object to attach to */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ } link_create; @@ -618,6 +635,10 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { + __u32 link_fd; + } link_detach; + struct { /* struct used by BPF_ENABLE_STATS command */ __u32 type; } enable_stats; @@ -653,7 +674,7 @@ union bpf_attr { * Map value associated to *key*, or **NULL** if no entry was * found. * - * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) * Description * Add or update the value of the entry associated to *key* in * *map* with *value*. *flags* is one of: @@ -671,13 +692,13 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * long bpf_map_delete_elem(struct bpf_map *map, const void *key) * Description * Delete entry with *key* from *map*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) * Description * For tracing programs, safely attempt to read *size* bytes from * kernel space address *unsafe_ptr* and store the data in *dst*. @@ -695,7 +716,7 @@ union bpf_attr { * Return * Current *ktime*. * - * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * long bpf_trace_printk(const char *fmt, u32 fmt_size, ...) * Description * This helper is a "printk()-like" facility for debugging. It * prints a message defined by format *fmt* (of size *fmt_size*) @@ -775,7 +796,7 @@ union bpf_attr { * Return * The SMP id of the processor running the program. * - * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description * Store *len* bytes from address *from* into the packet * associated to *skb*, at *offset*. *flags* are a combination of @@ -792,7 +813,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * long bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) * Description * Recompute the layer 3 (e.g. IP) checksum for the packet * associated to *skb*. Computation is incremental, so the helper @@ -817,7 +838,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * long bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) * Description * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the * packet associated to *skb*. Computation is incremental, so the @@ -849,7 +870,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * long bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) * Description * This special helper is used to trigger a "tail call", or in * other words, to jump into another eBPF program. The same stack @@ -880,7 +901,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * long bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) * Description * Clone and redirect the packet associated to *skb* to another * net device of index *ifindex*. Both ingress and egress @@ -916,7 +937,7 @@ union bpf_attr { * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. * - * int bpf_get_current_comm(void *buf, u32 size_of_buf) + * long bpf_get_current_comm(void *buf, u32 size_of_buf) * Description * Copy the **comm** attribute of the current task into *buf* of * *size_of_buf*. The **comm** attribute contains the name of @@ -953,7 +974,7 @@ union bpf_attr { * Return * The classid, or 0 for the default unconfigured classid. * - * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * long bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) * Description * Push a *vlan_tci* (VLAN tag control information) of protocol * *vlan_proto* to the packet associated to *skb*, then update @@ -969,7 +990,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_vlan_pop(struct sk_buff *skb) + * long bpf_skb_vlan_pop(struct sk_buff *skb) * Description * Pop a VLAN header from the packet associated to *skb*. * @@ -981,7 +1002,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * long bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) * Description * Get tunnel metadata. This helper takes a pointer *key* to an * empty **struct bpf_tunnel_key** of **size**, that will be @@ -1032,7 +1053,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * long bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) * Description * Populate tunnel metadata for packet associated to *skb.* The * tunnel metadata is set to the contents of *key*, of *size*. The @@ -1098,7 +1119,7 @@ union bpf_attr { * The value of the perf event counter read from the map, or a * negative error code in case of failure. * - * int bpf_redirect(u32 ifindex, u64 flags) + * long bpf_redirect(u32 ifindex, u64 flags) * Description * Redirect the packet to another net device of index *ifindex*. * This helper is somewhat similar to **bpf_clone_redirect**\ @@ -1145,7 +1166,7 @@ union bpf_attr { * The realm of the route for the packet associated to *skb*, or 0 * if none was found. * - * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -1190,7 +1211,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) + * long bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) * Description * This helper was provided as an easy way to load data from a * packet. It can be used to load *len* bytes from *offset* from @@ -1207,7 +1228,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) + * long bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) * Description * Walk a user or a kernel stack and return its id. To achieve * this, the helper needs *ctx*, which is a pointer to the context @@ -1276,7 +1297,7 @@ union bpf_attr { * The checksum result, or a negative error code in case of * failure. * - * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Retrieve tunnel options metadata for the packet associated to * *skb*, and store the raw tunnel option data to the buffer *opt* @@ -1294,7 +1315,7 @@ union bpf_attr { * Return * The size of the option data retrieved. * - * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Set tunnel options metadata for the packet associated to *skb* * to the option data contained in the raw buffer *opt* of *size*. @@ -1304,7 +1325,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * long bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) * Description * Change the protocol of the *skb* to *proto*. Currently * supported are transition from IPv4 to IPv6, and from IPv6 to @@ -1331,7 +1352,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * long bpf_skb_change_type(struct sk_buff *skb, u32 type) * Description * Change the packet type for the packet associated to *skb*. This * comes down to setting *skb*\ **->pkt_type** to *type*, except @@ -1358,7 +1379,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * long bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) * Description * Check whether *skb* is a descendant of the cgroup2 held by * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. @@ -1389,7 +1410,7 @@ union bpf_attr { * Return * A pointer to the current task struct. * - * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * long bpf_probe_write_user(void *dst, const void *src, u32 len) * Description * Attempt in a safe way to write *len* bytes from the buffer * *src* to *dst* in memory. It only works for threads that are in @@ -1408,7 +1429,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * long bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) * Description * Check whether the probe is being run is the context of a given * subset of the cgroup2 hierarchy. The cgroup2 to test is held by @@ -1420,7 +1441,7 @@ union bpf_attr { * * 1, if the *skb* task does not belong to the cgroup2. * * A negative error code, if an error occurred. * - * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) * Description * Resize (trim or grow) the packet associated to *skb* to the * new *len*. The *flags* are reserved for future usage, and must @@ -1444,7 +1465,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * long bpf_skb_pull_data(struct sk_buff *skb, u32 len) * Description * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes @@ -1500,7 +1521,7 @@ union bpf_attr { * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. * - * int bpf_get_numa_node_id(void) + * long bpf_get_numa_node_id(void) * Description * Return the id of the current NUMA node. The primary use case * for this helper is the selection of sockets for the local NUMA @@ -1511,7 +1532,7 @@ union bpf_attr { * Return * The id of current NUMA node. * - * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * long bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) * Description * Grows headroom of packet associated to *skb* and adjusts the * offset of the MAC header accordingly, adding *len* bytes of @@ -1532,7 +1553,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) * Description * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that * it is possible to use a negative value for *delta*. This helper @@ -1547,7 +1568,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for @@ -1595,14 +1616,14 @@ union bpf_attr { * is returned (note that **overflowuid** might also be the actual * UID value for the socket). * - * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * long bpf_set_hash(struct sk_buff *skb, u32 hash) * Description * Set the full hash for *skb* (set the field *skb*\ **->hash**) * to value *hash*. * Return * 0 * - * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1621,16 +1642,19 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) + * long bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -1676,7 +1700,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -1697,7 +1721,7 @@ union bpf_attr { * **XDP_REDIRECT** on success, or the value of the two lower bits * of the *flags* argument on error. * - * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) + * long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description * Redirect the packet to the socket referenced by *map* (of type * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and @@ -1708,7 +1732,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a *map* referencing sockets. The * *skops* is used as a new value for the entry associated to @@ -1727,7 +1751,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) * Description * Adjust the address pointed by *xdp_md*\ **->data_meta** by * *delta* (which can be positive or negative). Note that this @@ -1756,7 +1780,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * long bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) * Description * Read the value of a perf event counter, and store it into *buf* * of size *buf_size*. This helper relies on a *map* of type @@ -1806,7 +1830,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description * For en eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in @@ -1817,7 +1841,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1842,7 +1866,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_override_return(struct pt_regs *regs, u64 rc) + * long bpf_override_return(struct pt_regs *regs, u64 rc) * Description * Used for error injection, this helper uses kprobes to override * the return value of the probed function, and to set it to *rc*. @@ -1867,7 +1891,7 @@ union bpf_attr { * Return * 0 * - * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * long bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) * Description * Attempt to set the value of the **bpf_sock_ops_cb_flags** field * for the full TCP socket associated to *bpf_sock_ops* to @@ -1911,7 +1935,7 @@ union bpf_attr { * be set is returned (which comes down to 0 if all bits were set * as required). * - * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) * Description * This helper is used in programs implementing policies at the * socket level. If the message *msg* is allowed to pass (i.e. if @@ -1925,7 +1949,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) * Description * For socket policies, apply the verdict of the eBPF program to * the next *bytes* (number of bytes) of message *msg*. @@ -1959,7 +1983,7 @@ union bpf_attr { * Return * 0 * - * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) * Description * For socket policies, prevent the execution of the verdict eBPF * program for message *msg* until *bytes* (byte number) have been @@ -1977,7 +2001,7 @@ union bpf_attr { * Return * 0 * - * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) * Description * For socket policies, pull in non-linear data from user space * for *msg* and set pointers *msg*\ **->data** and *msg*\ @@ -2008,7 +2032,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * long bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) * Description * Bind the socket associated to *ctx* to the address pointed by * *addr*, of length *addr_len*. This allows for making outgoing @@ -2026,7 +2050,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) * Description * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is * possible to both shrink and grow the packet tail. @@ -2040,7 +2064,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * long bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) * Description * Retrieve the XFRM state (IP transform framework, see also * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. @@ -2056,7 +2080,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) + * long bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. * To achieve this, the helper needs *ctx*, which is a pointer @@ -2089,7 +2113,7 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * - * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) + * long bpf_skb_load_bytes_relative(const void *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* @@ -2111,7 +2135,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * long bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) * Description * Do FIB lookup in kernel tables using parameters in *params*. * If lookup is successful and result shows packet is to be @@ -2142,7 +2166,7 @@ union bpf_attr { * * > 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 *skops, struct bpf_map *map, void *key, u64 flags) + * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. * The *skops* is used as a new value for the entry associated to @@ -2161,7 +2185,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) * Description * This helper is used in programs implementing policies at the * socket level. If the message *msg* is allowed to pass (i.e. if @@ -2175,7 +2199,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) * Description * This helper is used in programs implementing policies at the * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. @@ -2189,7 +2213,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * long bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) * Description * Encapsulate the packet associated to *skb* within a Layer 3 * protocol header. This header is provided in the buffer at @@ -2226,7 +2250,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * long bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) * Description * Store *len* bytes from address *from* into the packet * associated to *skb*, at *offset*. Only the flags, tag and TLVs @@ -2241,7 +2265,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * long bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) * Description * Adjust the size allocated to TLVs in the outermost IPv6 * Segment Routing Header contained in the packet associated to @@ -2257,7 +2281,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * long bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) * Description * Apply an IPv6 Segment Routing action of type *action* to the * packet associated to *skb*. Each action takes a parameter @@ -2286,7 +2310,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_repeat(void *ctx) + * long bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded repeat key message. This delays @@ -2305,7 +2329,7 @@ union bpf_attr { * Return * 0 * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * long bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded key press with *scancode*, @@ -2370,7 +2394,7 @@ union bpf_attr { * Return * A pointer to the local storage area. * - * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) * Description * Select a **SO_REUSEPORT** socket from a * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. @@ -2415,7 +2439,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -2452,7 +2476,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -2471,7 +2495,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * int bpf_sk_release(struct bpf_sock *sock) + * long bpf_sk_release(struct bpf_sock *sock) * Description * Release the reference held by *sock*. *sock* must be a * non-**NULL** pointer that was returned from @@ -2479,7 +2503,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) * Description * Push an element *value* in *map*. *flags* is one of: * @@ -2489,19 +2513,19 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * long bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * long bpf_map_peek_elem(struct bpf_map *map, void *value) * Description * Get an element from *map* without removing it. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description * For socket policies, insert *len* bytes into *msg* at offset * *start*. @@ -2517,7 +2541,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description * Will remove *len* bytes from a *msg* starting at byte *start*. * This may result in **ENOMEM** errors under certain situations if @@ -2529,7 +2553,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded pointer movement. @@ -2543,7 +2567,7 @@ union bpf_attr { * Return * 0 * - * int bpf_spin_lock(struct bpf_spin_lock *lock) + * long bpf_spin_lock(struct bpf_spin_lock *lock) * Description * Acquire a spinlock represented by the pointer *lock*, which is * stored as part of a value of a map. Taking the lock allows to @@ -2591,7 +2615,7 @@ union bpf_attr { * Return * 0 * - * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * long bpf_spin_unlock(struct bpf_spin_lock *lock) * Description * Release the *lock* previously locked by a call to * **bpf_spin_lock**\ (\ *lock*\ ). @@ -2614,7 +2638,7 @@ union bpf_attr { * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * - * int bpf_skb_ecn_set_ce(struct sk_buff *skb) + * long bpf_skb_ecn_set_ce(struct sk_buff *skb) * Description * Set ECN (Explicit Congestion Notification) field of IP header * to **CE** (Congestion Encountered) if current value is **ECT** @@ -2651,7 +2675,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Check whether *iph* and *th* contain a valid SYN cookie ACK for * the listening socket in *sk*. @@ -2666,7 +2690,7 @@ union bpf_attr { * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. * - * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) * Description * Get name of sysctl in /proc/sys/ and copy it into provided by * program buffer *buf* of size *buf_len*. @@ -2682,7 +2706,7 @@ union bpf_attr { * **-E2BIG** if the buffer wasn't big enough (*buf* will contain * truncated name in this case). * - * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) * Description * Get current value of sysctl as it is presented in /proc/sys * (incl. newline, etc), and copy it as a string into provided @@ -2701,7 +2725,7 @@ union bpf_attr { * **-EINVAL** if current value was unavailable, e.g. because * sysctl is uninitialized and read returns -EIO for it. * - * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) * Description * Get new value being written by user space to sysctl (before * the actual write happens) and copy it as a string into @@ -2718,7 +2742,7 @@ union bpf_attr { * * **-EINVAL** if sysctl is being read. * - * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) * Description * Override new value being written by user space to sysctl with * value provided by program in buffer *buf* of size *buf_len*. @@ -2735,7 +2759,7 @@ union bpf_attr { * * **-EINVAL** if sysctl is being read. * - * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) * Description * Convert the initial part of the string from buffer *buf* of * size *buf_len* to a long integer according to the given base @@ -2759,7 +2783,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) * Description * Convert the initial part of the string from buffer *buf* of * size *buf_len* to an unsigned long integer according to the @@ -2810,7 +2834,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return @@ -2818,7 +2842,7 @@ union bpf_attr { * * **-ENOENT** if the bpf-local-storage cannot be found. * - * int bpf_send_signal(u32 sig) + * long bpf_send_signal(u32 sig) * Description * Send signal *sig* to the process of the current task. * The signal may be delivered to any of this process's threads. @@ -2859,7 +2883,7 @@ union bpf_attr { * * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 * - * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -2883,21 +2907,21 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) * Description * Safely attempt to read *size* bytes from user space address * *unsafe_ptr* and store the data in *dst*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * Description * Safely attempt to read *size* bytes from kernel space address * *unsafe_ptr* and store the data in *dst*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe user address * *unsafe_ptr* to *dst*. The *size* should include the @@ -2941,7 +2965,7 @@ union bpf_attr { * including the trailing NUL character. On error, a negative * value. * - * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. @@ -2949,14 +2973,14 @@ union bpf_attr { * On success, the strictly positive length of the string, including * the trailing NUL character. On error, a negative value. * - * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt) * Description * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. * *rcv_nxt* is the ack_seq to be sent out. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_send_signal_thread(u32 sig) + * long bpf_send_signal_thread(u32 sig) * Description * Send signal *sig* to the thread corresponding to the current task. * Return @@ -2976,7 +3000,7 @@ union bpf_attr { * Return * The 64 bit jiffies * - * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) * Description * For an eBPF program attached to a perf event, retrieve the * branch records (**struct perf_branch_entry**) associated to *ctx* @@ -2995,7 +3019,7 @@ union bpf_attr { * * **-ENOENT** if architecture does not support branch records. * - * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) * Description * Returns 0 on success, values for *pid* and *tgid* as seen from the current * *namespace* will be returned in *nsdata*. @@ -3007,7 +3031,7 @@ union bpf_attr { * * **-ENOENT** if pidns does not exists for the current task. * - * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -3062,8 +3086,12 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and + * **BPF_PROG_TYPE_SCHED_ACT** programs. + * * Assign the *sk* to the *skb*. When combined with appropriate * routing configuration to receive the packet towards the socket, * will cause *skb* to be delivered to the specified socket. @@ -3089,6 +3117,56 @@ union bpf_attr { * **-ESOCKTNOSUPPORT** if the socket type is not supported * (reuseport). * + * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) + * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs. + * + * Select the *sk* as a result of a socket lookup. + * + * For the operation to succeed passed socket must be compatible + * with the packet description provided by the *ctx* object. + * + * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must + * be an exact match. While IP family (**AF_INET** or + * **AF_INET6**) must be compatible, that is IPv6 sockets + * that are not v6-only can be selected for IPv4 packets. + * + * Only TCP listeners and UDP unconnected sockets can be + * selected. *sk* can also be NULL to reset any previous + * selection. + * + * *flags* argument can combination of following values: + * + * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous + * socket selection, potentially done by a BPF program + * that ran before us. + * + * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip + * load-balancing within reuseport group for the socket + * being selected. + * + * On success *ctx->sk* will point to the selected socket. + * + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EAFNOSUPPORT** if socket family (*sk->family*) is + * not compatible with packet family (*ctx->family*). + * + * * **-EEXIST** if socket has been already selected, + * potentially by another program, and + * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified. + * + * * **-EINVAL** if unsupported flags were specified. + * + * * **-EPROTOTYPE** if socket L4 protocol + * (*sk->protocol*) doesn't match packet protocol + * (*ctx->protocol*). + * + * * **-ESOCKTNOSUPPORT** if socket is not in allowed + * state (TCP listening or UDP unconnected). + * * u64 bpf_ktime_get_boot_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. @@ -3097,7 +3175,7 @@ union bpf_attr { * Return * Current *ktime*. * - * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) * Description * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print * out the format string. @@ -3126,7 +3204,7 @@ union bpf_attr { * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. * - * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * long bpf_seq_write(struct seq_file *m, const void *data, u32 len) * Description * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. * The *m* represents the seq_file. The *data* and *len* represent the @@ -3168,7 +3246,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification @@ -3222,7 +3300,7 @@ union bpf_attr { * Return * Requested value, or 0, if *flags* are not recognized. * - * int bpf_csum_level(struct sk_buff *skb, u64 level) + * long bpf_csum_level(struct sk_buff *skb, u64 level) * Description * Change the skbs checksum level by one layer up or down, or * reset it entirely to none in order to have the stack perform @@ -3253,6 +3331,69 @@ union bpf_attr { * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level * is returned or the error code -EACCES in case the skb is not * subject to CHECKSUM_UNNECESSARY. + * + * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *task*, which is a valid + * pointer to struct task_struct. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_task_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3390,7 +3531,14 @@ union bpf_attr { FN(ringbuf_submit), \ FN(ringbuf_discard), \ FN(ringbuf_query), \ - FN(csum_level), + FN(csum_level), \ + FN(skc_to_tcp6_sock), \ + FN(skc_to_tcp_sock), \ + FN(skc_to_tcp_timewait_sock), \ + FN(skc_to_tcp_request_sock), \ + FN(skc_to_udp6_sock), \ + FN(get_task_stack), \ + /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3532,6 +3680,12 @@ enum { BPF_RINGBUF_HDR_SZ = 8, }; +/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */ +enum { + BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0), + BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1), +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, @@ -3775,6 +3929,19 @@ struct bpf_devmap_val { } bpf_prog; }; +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; +}; + enum sk_action { SK_DROP = 0, SK_PASS, @@ -3907,12 +4074,15 @@ struct bpf_link_info { __u32 netns_ino; __u32 attach_type; } netns; + struct { + __u32 ifindex; + } xdp; }; } __attribute__((aligned(8))); /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on - * attach attach type). + * attach type). */ struct bpf_sock_addr { __u32 user_family; /* Allows 4-byte read, but no write. */ @@ -4261,4 +4431,19 @@ struct bpf_pidns_info { __u32 pid; __u32 tgid; }; + +/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ +struct bpf_sk_lookup { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + + __u32 family; /* Protocol family (AF_INET, AF_INET6) */ + __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ + __u32 remote_ip4; /* Network byte order */ + __u32 remote_ip6[4]; /* Network byte order */ + __u32 remote_port; /* Network byte order */ + __u32 local_ip4; /* Network byte order */ + __u32 local_ip6[4]; /* Network byte order */ + __u32 local_port; /* Host byte order */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h new file mode 100644 index 000000000000..eaef459e7bd4 --- /dev/null +++ b/tools/include/uapi/linux/filter.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Linux Socket Filter Data Structures + */ + +#ifndef __LINUX_FILTER_H__ +#define __LINUX_FILTER_H__ + + +#include <linux/types.h> +#include <linux/bpf_common.h> + +/* + * Current version of the filter code architecture. + */ +#define BPF_MAJOR_VERSION 1 +#define BPF_MINOR_VERSION 1 + +/* + * Try and keep these values and structures similar to BSD, especially + * the BPF code definitions which need to match so you can share filters + */ + +struct sock_filter { /* Filter block */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ +}; + +struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ + unsigned short len; /* Number of filter blocks */ + struct sock_filter *filter; +}; + +/* ret - BPF_K and BPF_X also apply */ +#define BPF_RVAL(code) ((code) & 0x18) +#define BPF_A 0x10 + +/* misc */ +#define BPF_MISCOP(code) ((code) & 0xf8) +#define BPF_TAX 0x00 +#define BPF_TXA 0x80 + +/* + * Macros for filter block array initializers. + */ +#ifndef BPF_STMT +#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } +#endif +#ifndef BPF_JUMP +#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k } +#endif + +/* + * Number of scratch memory words for: BPF_ST and BPF_STX + */ +#define BPF_MEMWORDS 16 + +/* RATIONALE. Negative offsets are invalid in BPF. + We use them to reference ancillary data. + Unlike introduction new instructions, it does not break + existing compilers/optimizers. + */ +#define SKF_AD_OFF (-0x1000) +#define SKF_AD_PROTOCOL 0 +#define SKF_AD_PKTTYPE 4 +#define SKF_AD_IFINDEX 8 +#define SKF_AD_NLATTR 12 +#define SKF_AD_NLATTR_NEST 16 +#define SKF_AD_MARK 20 +#define SKF_AD_QUEUE 24 +#define SKF_AD_HATYPE 28 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_ALU_XOR_X 40 +#define SKF_AD_VLAN_TAG 44 +#define SKF_AD_VLAN_TAG_PRESENT 48 +#define SKF_AD_PAY_OFFSET 52 +#define SKF_AD_RANDOM 56 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 + +#define SKF_NET_OFF (-0x100000) +#define SKF_LL_OFF (-0x200000) + +#define BPF_NET_OFF SKF_NET_OFF +#define BPF_LL_OFF SKF_LL_OFF + +#endif /* __LINUX_FILTER_H__ */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index cafedbbfefbe..781e482dc499 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -344,6 +344,7 @@ enum { IFLA_BRPORT_ISOLATED, IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, + IFLA_BRPORT_MRP_IN_OPEN, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index be328c59389d..a78a8096f4ce 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -73,9 +73,12 @@ struct xdp_umem_reg { }; struct xdp_statistics { - __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_dropped; /* Dropped for other reasons */ __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 rx_ring_full; /* Dropped due to rx ring being full */ + __u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */ + __u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */ }; struct xdp_options { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 52ca2093831c..077e7ee69e3d 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -533,9 +533,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -594,13 +595,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h index 5f305c86b892..28a837b6069d 100644 --- a/tools/io_uring/liburing.h +++ b/tools/io_uring/liburing.h @@ -10,6 +10,7 @@ extern "C" { #include <string.h> #include "../../include/uapi/linux/io_uring.h" #include <inttypes.h> +#include <linux/swab.h> #include "barrier.h" /* @@ -145,11 +146,14 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd, } static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd, - short poll_mask) + unsigned poll_mask) { memset(sqe, 0, sizeof(*sqe)); sqe->opcode = IORING_OP_POLL_ADD; sqe->fd = fd; +#if __BYTE_ORDER == __BIG_ENDIAN + poll_mask = __swahw32(poll_mask); +#endif sqe->poll_events = poll_mask; } diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a7329b671c41..eab14c97c15d 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -598,10 +598,21 @@ int bpf_link_create(int prog_fd, int target_fd, attr.link_create.prog_fd = prog_fd; attr.link_create.target_fd = target_fd; attr.link_create.attach_type = attach_type; + attr.link_create.flags = OPTS_GET(opts, flags, 0); return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); } +int bpf_link_detach(int link_fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.link_detach.link_fd = link_fd; + + return sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr)); +} + int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts) { diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index dbef24ebcfcb..28855fd5b5f4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -170,13 +170,16 @@ LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, struct bpf_link_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; }; -#define bpf_link_create_opts__last_field sz +#define bpf_link_create_opts__last_field flags LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, const struct bpf_link_create_opts *opts); +LIBBPF_API int bpf_link_detach(int link_fd); + struct bpf_link_update_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 flags; /* extra flags */ diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 7009dc90e012..eae5cccff761 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -217,7 +217,7 @@ enum bpf_field_info_kind { */ #define BPF_CORE_READ_INTO(dst, src, a, ...) \ ({ \ - ___core_read(bpf_core_read, dst, src, a, ##__VA_ARGS__) \ + ___core_read(bpf_core_read, dst, (src), a, ##__VA_ARGS__) \ }) /* @@ -227,7 +227,7 @@ enum bpf_field_info_kind { */ #define BPF_CORE_READ_STR_INTO(dst, src, a, ...) \ ({ \ - ___core_read(bpf_core_read_str, dst, src, a, ##__VA_ARGS__) \ + ___core_read(bpf_core_read_str, dst, (src), a, ##__VA_ARGS__)\ }) /* @@ -254,8 +254,8 @@ enum bpf_field_info_kind { */ #define BPF_CORE_READ(src, a, ...) \ ({ \ - ___type(src, a, ##__VA_ARGS__) __r; \ - BPF_CORE_READ_INTO(&__r, src, a, ##__VA_ARGS__); \ + ___type((src), a, ##__VA_ARGS__) __r; \ + BPF_CORE_READ_INTO(&__r, (src), a, ##__VA_ARGS__); \ __r; \ }) diff --git a/tools/lib/bpf/bpf_endian.h b/tools/lib/bpf/bpf_endian.h index fbe28008450f..ec9db4feca9f 100644 --- a/tools/lib/bpf/bpf_endian.h +++ b/tools/lib/bpf/bpf_endian.h @@ -2,8 +2,35 @@ #ifndef __BPF_ENDIAN__ #define __BPF_ENDIAN__ -#include <linux/stddef.h> -#include <linux/swab.h> +/* + * Isolate byte #n and put it into byte #m, for __u##b type. + * E.g., moving byte #6 (nnnnnnnn) into byte #1 (mmmmmmmm) for __u64: + * 1) xxxxxxxx nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx + * 2) nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx 00000000 + * 3) 00000000 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn + * 4) 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn 00000000 + */ +#define ___bpf_mvb(x, b, n, m) ((__u##b)(x) << (b-(n+1)*8) >> (b-8) << (m*8)) + +#define ___bpf_swab16(x) ((__u16)( \ + ___bpf_mvb(x, 16, 0, 1) | \ + ___bpf_mvb(x, 16, 1, 0))) + +#define ___bpf_swab32(x) ((__u32)( \ + ___bpf_mvb(x, 32, 0, 3) | \ + ___bpf_mvb(x, 32, 1, 2) | \ + ___bpf_mvb(x, 32, 2, 1) | \ + ___bpf_mvb(x, 32, 3, 0))) + +#define ___bpf_swab64(x) ((__u64)( \ + ___bpf_mvb(x, 64, 0, 7) | \ + ___bpf_mvb(x, 64, 1, 6) | \ + ___bpf_mvb(x, 64, 2, 5) | \ + ___bpf_mvb(x, 64, 3, 4) | \ + ___bpf_mvb(x, 64, 4, 3) | \ + ___bpf_mvb(x, 64, 5, 2) | \ + ___bpf_mvb(x, 64, 6, 1) | \ + ___bpf_mvb(x, 64, 7, 0))) /* LLVM's BPF target selects the endianness of the CPU * it compiles on, or the user specifies (bpfel/bpfeb), @@ -23,16 +50,16 @@ #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ # define __bpf_ntohs(x) __builtin_bswap16(x) # define __bpf_htons(x) __builtin_bswap16(x) -# define __bpf_constant_ntohs(x) ___constant_swab16(x) -# define __bpf_constant_htons(x) ___constant_swab16(x) +# define __bpf_constant_ntohs(x) ___bpf_swab16(x) +# define __bpf_constant_htons(x) ___bpf_swab16(x) # define __bpf_ntohl(x) __builtin_bswap32(x) # define __bpf_htonl(x) __builtin_bswap32(x) -# define __bpf_constant_ntohl(x) ___constant_swab32(x) -# define __bpf_constant_htonl(x) ___constant_swab32(x) +# define __bpf_constant_ntohl(x) ___bpf_swab32(x) +# define __bpf_constant_htonl(x) ___bpf_swab32(x) # define __bpf_be64_to_cpu(x) __builtin_bswap64(x) # define __bpf_cpu_to_be64(x) __builtin_bswap64(x) -# define __bpf_constant_be64_to_cpu(x) ___constant_swab64(x) -# define __bpf_constant_cpu_to_be64(x) ___constant_swab64(x) +# define __bpf_constant_be64_to_cpu(x) ___bpf_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___bpf_swab64(x) #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ # define __bpf_ntohs(x) (x) # define __bpf_htons(x) (x) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index f67dce2af802..bc14db706b88 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -40,7 +40,7 @@ * Helper macro to manipulate data structures */ #ifndef offsetof -#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) +#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) #endif #ifndef container_of #define container_of(ptr, type, member) \ @@ -75,5 +75,6 @@ enum libbpf_tristate { }; #define __kconfig __attribute__((section(".kconfig"))) +#define __ksym __attribute__((section(".ksyms"))) #endif diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 58eceb884df3..eebf020cbe3e 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -215,7 +215,7 @@ struct pt_regs; #define PT_REGS_PARM5(x) ((x)->regs[8]) #define PT_REGS_RET(x) ((x)->regs[31]) #define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->regs[1]) +#define PT_REGS_RC(x) ((x)->regs[2]) #define PT_REGS_SP(x) ((x)->regs[29]) #define PT_REGS_IP(x) ((x)->cp0_epc) @@ -226,7 +226,7 @@ struct pt_regs; #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8]) #define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31]) #define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[1]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2]) #define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29]) #define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index bfef3d606b54..856b09a04563 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -386,10 +386,10 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, void btf__free(struct btf *btf) { - if (!btf) + if (IS_ERR_OR_NULL(btf)) return; - if (btf->fd != -1) + if (btf->fd >= 0) close(btf->fd); free(btf->data); @@ -397,7 +397,7 @@ void btf__free(struct btf *btf) free(btf); } -struct btf *btf__new(__u8 *data, __u32 size) +struct btf *btf__new(const void *data, __u32 size) { struct btf *btf; int err; @@ -562,6 +562,83 @@ done: return btf; } +struct btf *btf__parse_raw(const char *path) +{ + void *data = NULL; + struct btf *btf; + FILE *f = NULL; + __u16 magic; + int err = 0; + long sz; + + f = fopen(path, "rb"); + if (!f) { + err = -errno; + goto err_out; + } + + /* check BTF magic */ + if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) { + err = -EIO; + goto err_out; + } + if (magic != BTF_MAGIC) { + /* definitely not a raw BTF */ + err = -EPROTO; + goto err_out; + } + + /* get file size */ + if (fseek(f, 0, SEEK_END)) { + err = -errno; + goto err_out; + } + sz = ftell(f); + if (sz < 0) { + err = -errno; + goto err_out; + } + /* rewind to the start */ + if (fseek(f, 0, SEEK_SET)) { + err = -errno; + goto err_out; + } + + /* pre-alloc memory and read all of BTF data */ + data = malloc(sz); + if (!data) { + err = -ENOMEM; + goto err_out; + } + if (fread(data, 1, sz, f) < sz) { + err = -EIO; + goto err_out; + } + + /* finally parse BTF data */ + btf = btf__new(data, sz); + +err_out: + free(data); + if (f) + fclose(f); + return err ? ERR_PTR(err) : btf; +} + +struct btf *btf__parse(const char *path, struct btf_ext **btf_ext) +{ + struct btf *btf; + + if (btf_ext) + *btf_ext = NULL; + + btf = btf__parse_raw(path); + if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO) + return btf; + + return btf__parse_elf(path, btf_ext); +} + static int compare_vsi_off(const void *_a, const void *_b) { const struct btf_var_secinfo *a = _a; @@ -700,6 +777,11 @@ int btf__fd(const struct btf *btf) return btf->fd; } +void btf__set_fd(struct btf *btf, int fd) +{ + btf->fd = fd; +} + const void *btf__get_raw_data(const struct btf *btf, __u32 *size) { *size = btf->data_size; @@ -1020,7 +1102,7 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) void btf_ext__free(struct btf_ext *btf_ext) { - if (!btf_ext) + if (IS_ERR_OR_NULL(btf_ext)) return; free(btf_ext->data); free(btf_ext); @@ -2946,41 +3028,6 @@ static int btf_dedup_remap_types(struct btf_dedup *d) return 0; } -static struct btf *btf_load_raw(const char *path) -{ - struct btf *btf; - size_t read_cnt; - struct stat st; - void *data; - FILE *f; - - if (stat(path, &st)) - return ERR_PTR(-errno); - - data = malloc(st.st_size); - if (!data) - return ERR_PTR(-ENOMEM); - - f = fopen(path, "rb"); - if (!f) { - btf = ERR_PTR(-errno); - goto cleanup; - } - - read_cnt = fread(data, 1, st.st_size, f); - fclose(f); - if (read_cnt < st.st_size) { - btf = ERR_PTR(-EBADF); - goto cleanup; - } - - btf = btf__new(data, read_cnt); - -cleanup: - free(data); - return btf; -} - /* * Probe few well-known locations for vmlinux kernel image and try to load BTF * data out of it to use for target BTF. @@ -3016,7 +3063,7 @@ struct btf *libbpf_find_kernel_btf(void) continue; if (locations[i].raw_btf) - btf = btf_load_raw(path); + btf = btf__parse_raw(path); else btf = btf__parse_elf(path, NULL); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 70c1b7ec2bd0..f4a1a1d2b9a3 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -63,9 +63,10 @@ struct btf_ext_header { }; LIBBPF_API void btf__free(struct btf *btf); -LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); -LIBBPF_API struct btf *btf__parse_elf(const char *path, - struct btf_ext **btf_ext); +LIBBPF_API struct btf *btf__new(const void *data, __u32 size); +LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); +LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext); +LIBBPF_API struct btf *btf__parse_raw(const char *path); LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, @@ -79,6 +80,7 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); +LIBBPF_API void btf__set_fd(struct btf *btf, int fd); LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); @@ -143,8 +145,10 @@ struct btf_dump_emit_type_decl_opts { * necessary indentation already */ int indent_level; + /* strip all the const/volatile/restrict mods */ + bool strip_mods; }; -#define btf_dump_emit_type_decl_opts__last_field indent_level +#define btf_dump_emit_type_decl_opts__last_field strip_mods LIBBPF_API int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, @@ -168,6 +172,11 @@ static inline bool btf_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } +static inline bool btf_is_void(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNKN; +} + static inline bool btf_is_int(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_INT; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index bbb430317260..cf711168d34a 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -60,6 +60,7 @@ struct btf_dump { const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; struct btf_dump_opts opts; + bool strip_mods; /* per-type auxiliary state */ struct btf_dump_type_aux_state *type_states; @@ -182,7 +183,7 @@ void btf_dump__free(struct btf_dump *d) { int i, cnt; - if (!d) + if (IS_ERR_OR_NULL(d)) return; free(d->type_states); @@ -1032,7 +1033,9 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, fname = OPTS_GET(opts, field_name, ""); lvl = OPTS_GET(opts, indent_level, 0); + d->strip_mods = OPTS_GET(opts, strip_mods, false); btf_dump_emit_type_decl(d, id, fname, lvl); + d->strip_mods = false; return 0; } @@ -1045,6 +1048,10 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, stack_start = d->decl_stack_cnt; for (;;) { + t = btf__type_by_id(d->btf, id); + if (d->strip_mods && btf_is_mod(t)) + goto skip_mod; + err = btf_dump_push_decl_stack_id(d, id); if (err < 0) { /* @@ -1056,12 +1063,11 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, d->decl_stack_cnt = stack_start; return; } - +skip_mod: /* VOID */ if (id == 0) break; - t = btf__type_by_id(d->btf, id); switch (btf_kind(t)) { case BTF_KIND_PTR: case BTF_KIND_VOLATILE: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 11e4725b8b1c..7be04e45d29c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -230,6 +230,7 @@ struct bpf_program { struct bpf_insn *insns; size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; + bool load; struct reloc_desc *reloc_desc; int nr_reloc; @@ -285,6 +286,7 @@ struct bpf_struct_ops { #define BSS_SEC ".bss" #define RODATA_SEC ".rodata" #define KCONFIG_SEC ".kconfig" +#define KSYMS_SEC ".ksyms" #define STRUCT_OPS_SEC ".struct_ops" enum libbpf_map_type { @@ -310,6 +312,7 @@ struct bpf_map { int map_ifindex; int inner_map_fd; struct bpf_map_def def; + __u32 numa_node; __u32 btf_var_idx; __u32 btf_key_type_id; __u32 btf_value_type_id; @@ -329,24 +332,39 @@ struct bpf_map { enum extern_type { EXT_UNKNOWN, - EXT_CHAR, - EXT_BOOL, - EXT_INT, - EXT_TRISTATE, - EXT_CHAR_ARR, + EXT_KCFG, + EXT_KSYM, +}; + +enum kcfg_type { + KCFG_UNKNOWN, + KCFG_CHAR, + KCFG_BOOL, + KCFG_INT, + KCFG_TRISTATE, + KCFG_CHAR_ARR, }; struct extern_desc { - const char *name; + enum extern_type type; int sym_idx; int btf_id; - enum extern_type type; - int sz; - int align; - int data_off; - bool is_signed; - bool is_weak; + int sec_btf_id; + const char *name; bool is_set; + bool is_weak; + union { + struct { + enum kcfg_type type; + int sz; + int align; + int data_off; + bool is_signed; + } kcfg; + struct { + unsigned long long addr; + } ksym; + }; }; static LIST_HEAD(bpf_objects_list); @@ -524,6 +542,7 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->instances.fds = NULL; prog->instances.nr = -1; prog->type = BPF_PROG_TYPE_UNSPEC; + prog->load = true; return 0; errout: @@ -1423,19 +1442,19 @@ static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, return NULL; } -static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, - char value) +static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val, + char value) { - switch (ext->type) { - case EXT_BOOL: + switch (ext->kcfg.type) { + case KCFG_BOOL: if (value == 'm') { - pr_warn("extern %s=%c should be tristate or char\n", + pr_warn("extern (kcfg) %s=%c should be tristate or char\n", ext->name, value); return -EINVAL; } *(bool *)ext_val = value == 'y' ? true : false; break; - case EXT_TRISTATE: + case KCFG_TRISTATE: if (value == 'y') *(enum libbpf_tristate *)ext_val = TRI_YES; else if (value == 'm') @@ -1443,14 +1462,14 @@ static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, else /* value == 'n' */ *(enum libbpf_tristate *)ext_val = TRI_NO; break; - case EXT_CHAR: + case KCFG_CHAR: *(char *)ext_val = value; break; - case EXT_UNKNOWN: - case EXT_INT: - case EXT_CHAR_ARR: + case KCFG_UNKNOWN: + case KCFG_INT: + case KCFG_CHAR_ARR: default: - pr_warn("extern %s=%c should be bool, tristate, or char\n", + pr_warn("extern (kcfg) %s=%c should be bool, tristate, or char\n", ext->name, value); return -EINVAL; } @@ -1458,29 +1477,29 @@ static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, return 0; } -static int set_ext_value_str(struct extern_desc *ext, char *ext_val, - const char *value) +static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, + const char *value) { size_t len; - if (ext->type != EXT_CHAR_ARR) { - pr_warn("extern %s=%s should char array\n", ext->name, value); + if (ext->kcfg.type != KCFG_CHAR_ARR) { + pr_warn("extern (kcfg) %s=%s should be char array\n", ext->name, value); return -EINVAL; } len = strlen(value); if (value[len - 1] != '"') { - pr_warn("extern '%s': invalid string config '%s'\n", + pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", ext->name, value); return -EINVAL; } /* strip quotes */ len -= 2; - if (len >= ext->sz) { - pr_warn("extern '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", - ext->name, value, len, ext->sz - 1); - len = ext->sz - 1; + if (len >= ext->kcfg.sz) { + pr_warn("extern (kcfg) '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", + ext->name, value, len, ext->kcfg.sz - 1); + len = ext->kcfg.sz - 1; } memcpy(ext_val, value + 1, len); ext_val[len] = '\0'; @@ -1507,11 +1526,11 @@ static int parse_u64(const char *value, __u64 *res) return 0; } -static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) +static bool is_kcfg_value_in_range(const struct extern_desc *ext, __u64 v) { - int bit_sz = ext->sz * 8; + int bit_sz = ext->kcfg.sz * 8; - if (ext->sz == 8) + if (ext->kcfg.sz == 8) return true; /* Validate that value stored in u64 fits in integer of `ext->sz` @@ -1526,26 +1545,26 @@ static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) * For unsigned target integer, check that all the (64 - Y) bits are * zero. */ - if (ext->is_signed) + if (ext->kcfg.is_signed) return v + (1ULL << (bit_sz - 1)) < (1ULL << bit_sz); else return (v >> bit_sz) == 0; } -static int set_ext_value_num(struct extern_desc *ext, void *ext_val, - __u64 value) +static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val, + __u64 value) { - if (ext->type != EXT_INT && ext->type != EXT_CHAR) { - pr_warn("extern %s=%llu should be integer\n", + if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR) { + pr_warn("extern (kcfg) %s=%llu should be integer\n", ext->name, (unsigned long long)value); return -EINVAL; } - if (!is_ext_value_in_range(ext, value)) { - pr_warn("extern %s=%llu value doesn't fit in %d bytes\n", - ext->name, (unsigned long long)value, ext->sz); + if (!is_kcfg_value_in_range(ext, value)) { + pr_warn("extern (kcfg) %s=%llu value doesn't fit in %d bytes\n", + ext->name, (unsigned long long)value, ext->kcfg.sz); return -ERANGE; } - switch (ext->sz) { + switch (ext->kcfg.sz) { case 1: *(__u8 *)ext_val = value; break; case 2: *(__u16 *)ext_val = value; break; case 4: *(__u32 *)ext_val = value; break; @@ -1591,30 +1610,30 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, if (!ext || ext->is_set) return 0; - ext_val = data + ext->data_off; + ext_val = data + ext->kcfg.data_off; value = sep + 1; switch (*value) { case 'y': case 'n': case 'm': - err = set_ext_value_tri(ext, ext_val, *value); + err = set_kcfg_value_tri(ext, ext_val, *value); break; case '"': - err = set_ext_value_str(ext, ext_val, value); + err = set_kcfg_value_str(ext, ext_val, value); break; default: /* assume integer */ err = parse_u64(value, &num); if (err) { - pr_warn("extern %s=%s should be integer\n", + pr_warn("extern (kcfg) %s=%s should be integer\n", ext->name, value); return err; } - err = set_ext_value_num(ext, ext_val, num); + err = set_kcfg_value_num(ext, ext_val, num); break; } if (err) return err; - pr_debug("extern %s=%s\n", ext->name, value); + pr_debug("extern (kcfg) %s=%s\n", ext->name, value); return 0; } @@ -1685,16 +1704,20 @@ static int bpf_object__read_kconfig_mem(struct bpf_object *obj, static int bpf_object__init_kconfig_map(struct bpf_object *obj) { - struct extern_desc *last_ext; + struct extern_desc *last_ext = NULL, *ext; size_t map_sz; - int err; + int i, err; - if (obj->nr_extern == 0) - return 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type == EXT_KCFG) + last_ext = ext; + } - last_ext = &obj->externs[obj->nr_extern - 1]; - map_sz = last_ext->data_off + last_ext->sz; + if (!last_ext) + return 0; + map_sz = last_ext->kcfg.data_off + last_ext->kcfg.sz; err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, obj->efile.symbols_shndx, NULL, map_sz); @@ -1957,6 +1980,10 @@ static int parse_btf_map_def(struct bpf_object *obj, return -EINVAL; pr_debug("map '%s': found map_flags = %u.\n", map->name, map->def.map_flags); + } else if (strcmp(name, "numa_node") == 0) { + if (!get_map_field_int(map->name, obj->btf, m, &map->numa_node)) + return -EINVAL; + pr_debug("map '%s': found numa_node = %u.\n", map->name, map->numa_node); } else if (strcmp(name, "key_size") == 0) { __u32 sz; @@ -2311,18 +2338,23 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return false; } -static void bpf_object__sanitize_btf(struct bpf_object *obj) +static bool btf_needs_sanitization(struct bpf_object *obj) +{ + bool has_func_global = obj->caps.btf_func_global; + bool has_datasec = obj->caps.btf_datasec; + bool has_func = obj->caps.btf_func; + + return !has_func || !has_datasec || !has_func_global; +} + +static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { bool has_func_global = obj->caps.btf_func_global; bool has_datasec = obj->caps.btf_datasec; bool has_func = obj->caps.btf_func; - struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - if (!obj->btf || (has_func && has_datasec && has_func_global)) - return; - for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); @@ -2375,17 +2407,6 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) } } -static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) -{ - if (!obj->btf_ext) - return; - - if (!obj->caps.btf_func) { - btf_ext__free(obj->btf_ext); - obj->btf_ext = NULL; - } -} - static bool libbpf_needs_btf(const struct bpf_object *obj) { return obj->efile.btf_maps_shndx >= 0 || @@ -2446,19 +2467,11 @@ static int bpf_object__finalize_btf(struct bpf_object *obj) return 0; err = btf__finalize_data(obj, obj->btf); - if (!err) - return 0; - - pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - btf_ext__free(obj->btf_ext); - obj->btf_ext = NULL; - - if (libbpf_needs_btf(obj)) { - pr_warn("BTF is required, but is missing or corrupted.\n"); - return -ENOENT; + if (err) { + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + return err; } + return 0; } @@ -2479,51 +2492,77 @@ static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog) static int bpf_object__load_vmlinux_btf(struct bpf_object *obj) { + bool need_vmlinux_btf = false; struct bpf_program *prog; int err; + /* CO-RE relocations need kernel BTF */ + if (obj->btf_ext && obj->btf_ext->field_reloc_info.len) + need_vmlinux_btf = true; + bpf_object__for_each_program(prog, obj) { + if (!prog->load) + continue; if (libbpf_prog_needs_vmlinux_btf(prog)) { - obj->btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(obj->btf_vmlinux)) { - err = PTR_ERR(obj->btf_vmlinux); - pr_warn("Error loading vmlinux BTF: %d\n", err); - obj->btf_vmlinux = NULL; - return err; - } - return 0; + need_vmlinux_btf = true; + break; } } + if (!need_vmlinux_btf) + return 0; + + obj->btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(obj->btf_vmlinux)) { + err = PTR_ERR(obj->btf_vmlinux); + pr_warn("Error loading vmlinux BTF: %d\n", err); + obj->btf_vmlinux = NULL; + return err; + } return 0; } static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { + struct btf *kern_btf = obj->btf; + bool btf_mandatory, sanitize; int err = 0; if (!obj->btf) return 0; - bpf_object__sanitize_btf(obj); - bpf_object__sanitize_btf_ext(obj); + sanitize = btf_needs_sanitization(obj); + if (sanitize) { + const void *raw_data; + __u32 sz; - err = btf__load(obj->btf); - if (err) { - pr_warn("Error loading %s into kernel: %d.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - /* btf_ext can't exist without btf, so free it as well */ - if (obj->btf_ext) { - btf_ext__free(obj->btf_ext); - obj->btf_ext = NULL; - } + /* clone BTF to sanitize a copy and leave the original intact */ + raw_data = btf__get_raw_data(obj->btf, &sz); + kern_btf = btf__new(raw_data, sz); + if (IS_ERR(kern_btf)) + return PTR_ERR(kern_btf); - if (kernel_needs_btf(obj)) - return err; + bpf_object__sanitize_btf(obj, kern_btf); } - return 0; + + err = btf__load(kern_btf); + if (sanitize) { + if (!err) { + /* move fd to libbpf's BTF */ + btf__set_fd(obj->btf, btf__fd(kern_btf)); + btf__set_fd(kern_btf, -1); + } + btf__free(kern_btf); + } + if (err) { + btf_mandatory = kernel_needs_btf(obj); + pr_warn("Error loading .BTF into kernel: %d. %s\n", err, + btf_mandatory ? "BTF is mandatory, can't proceed." + : "BTF is optional, ignoring."); + if (!btf_mandatory) + err = 0; + } + return err; } static int bpf_object__elf_collect(struct bpf_object *obj) @@ -2709,8 +2748,33 @@ static int find_extern_btf_id(const struct btf *btf, const char *ext_name) return -ENOENT; } -static enum extern_type find_extern_type(const struct btf *btf, int id, - bool *is_signed) +static int find_extern_sec_btf_id(struct btf *btf, int ext_btf_id) { + const struct btf_var_secinfo *vs; + const struct btf_type *t; + int i, j, n; + + if (!btf) + return -ESRCH; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + vs = btf_var_secinfos(t); + for (j = 0; j < btf_vlen(t); j++, vs++) { + if (vs->type == ext_btf_id) + return i; + } + } + + return -ENOENT; +} + +static enum kcfg_type find_kcfg_type(const struct btf *btf, int id, + bool *is_signed) { const struct btf_type *t; const char *name; @@ -2725,29 +2789,29 @@ static enum extern_type find_extern_type(const struct btf *btf, int id, int enc = btf_int_encoding(t); if (enc & BTF_INT_BOOL) - return t->size == 1 ? EXT_BOOL : EXT_UNKNOWN; + return t->size == 1 ? KCFG_BOOL : KCFG_UNKNOWN; if (is_signed) *is_signed = enc & BTF_INT_SIGNED; if (t->size == 1) - return EXT_CHAR; + return KCFG_CHAR; if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) - return EXT_UNKNOWN; - return EXT_INT; + return KCFG_UNKNOWN; + return KCFG_INT; } case BTF_KIND_ENUM: if (t->size != 4) - return EXT_UNKNOWN; + return KCFG_UNKNOWN; if (strcmp(name, "libbpf_tristate")) - return EXT_UNKNOWN; - return EXT_TRISTATE; + return KCFG_UNKNOWN; + return KCFG_TRISTATE; case BTF_KIND_ARRAY: if (btf_array(t)->nelems == 0) - return EXT_UNKNOWN; - if (find_extern_type(btf, btf_array(t)->type, NULL) != EXT_CHAR) - return EXT_UNKNOWN; - return EXT_CHAR_ARR; + return KCFG_UNKNOWN; + if (find_kcfg_type(btf, btf_array(t)->type, NULL) != KCFG_CHAR) + return KCFG_UNKNOWN; + return KCFG_CHAR_ARR; default: - return EXT_UNKNOWN; + return KCFG_UNKNOWN; } } @@ -2756,23 +2820,45 @@ static int cmp_externs(const void *_a, const void *_b) const struct extern_desc *a = _a; const struct extern_desc *b = _b; - /* descending order by alignment requirements */ - if (a->align != b->align) - return a->align > b->align ? -1 : 1; - /* ascending order by size, within same alignment class */ - if (a->sz != b->sz) - return a->sz < b->sz ? -1 : 1; + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + if (a->type == EXT_KCFG) { + /* descending order by alignment requirements */ + if (a->kcfg.align != b->kcfg.align) + return a->kcfg.align > b->kcfg.align ? -1 : 1; + /* ascending order by size, within same alignment class */ + if (a->kcfg.sz != b->kcfg.sz) + return a->kcfg.sz < b->kcfg.sz ? -1 : 1; + } + /* resolve ties by name */ return strcmp(a->name, b->name); } +static int find_int_btf_id(const struct btf *btf) +{ + const struct btf_type *t; + int i, n; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(btf, i); + + if (btf_is_int(t) && btf_int_bits(t) == 32) + return i; + } + + return 0; +} + static int bpf_object__collect_externs(struct bpf_object *obj) { + struct btf_type *sec, *kcfg_sec = NULL, *ksym_sec = NULL; const struct btf_type *t; struct extern_desc *ext; - int i, n, off, btf_id; - struct btf_type *sec; - const char *ext_name; + int i, n, off; + const char *ext_name, *sec_name; Elf_Scn *scn; GElf_Shdr sh; @@ -2818,22 +2904,50 @@ static int bpf_object__collect_externs(struct bpf_object *obj) ext->name = btf__name_by_offset(obj->btf, t->name_off); ext->sym_idx = i; ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK; - ext->sz = btf__resolve_size(obj->btf, t->type); - if (ext->sz <= 0) { - pr_warn("failed to resolve size of extern '%s': %d\n", - ext_name, ext->sz); - return ext->sz; - } - ext->align = btf__align_of(obj->btf, t->type); - if (ext->align <= 0) { - pr_warn("failed to determine alignment of extern '%s': %d\n", - ext_name, ext->align); - return -EINVAL; - } - ext->type = find_extern_type(obj->btf, t->type, - &ext->is_signed); - if (ext->type == EXT_UNKNOWN) { - pr_warn("extern '%s' type is unsupported\n", ext_name); + + ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); + if (ext->sec_btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n", + ext_name, ext->btf_id, ext->sec_btf_id); + return ext->sec_btf_id; + } + sec = (void *)btf__type_by_id(obj->btf, ext->sec_btf_id); + sec_name = btf__name_by_offset(obj->btf, sec->name_off); + + if (strcmp(sec_name, KCONFIG_SEC) == 0) { + kcfg_sec = sec; + ext->type = EXT_KCFG; + ext->kcfg.sz = btf__resolve_size(obj->btf, t->type); + if (ext->kcfg.sz <= 0) { + pr_warn("failed to resolve size of extern (kcfg) '%s': %d\n", + ext_name, ext->kcfg.sz); + return ext->kcfg.sz; + } + ext->kcfg.align = btf__align_of(obj->btf, t->type); + if (ext->kcfg.align <= 0) { + pr_warn("failed to determine alignment of extern (kcfg) '%s': %d\n", + ext_name, ext->kcfg.align); + return -EINVAL; + } + ext->kcfg.type = find_kcfg_type(obj->btf, t->type, + &ext->kcfg.is_signed); + if (ext->kcfg.type == KCFG_UNKNOWN) { + pr_warn("extern (kcfg) '%s' type is unsupported\n", ext_name); + return -ENOTSUP; + } + } else if (strcmp(sec_name, KSYMS_SEC) == 0) { + const struct btf_type *vt; + + ksym_sec = sec; + ext->type = EXT_KSYM; + + vt = skip_mods_and_typedefs(obj->btf, t->type, NULL); + if (!btf_is_void(vt)) { + pr_warn("extern (ksym) '%s' is not typeless (void)\n", ext_name); + return -ENOTSUP; + } + } else { + pr_warn("unrecognized extern section '%s'\n", sec_name); return -ENOTSUP; } } @@ -2842,42 +2956,80 @@ static int bpf_object__collect_externs(struct bpf_object *obj) if (!obj->nr_extern) return 0; - /* sort externs by (alignment, size, name) and calculate their offsets - * within a map */ + /* sort externs by type, for kcfg ones also by (align, size, name) */ qsort(obj->externs, obj->nr_extern, sizeof(*ext), cmp_externs); - off = 0; - for (i = 0; i < obj->nr_extern; i++) { - ext = &obj->externs[i]; - ext->data_off = roundup(off, ext->align); - off = ext->data_off + ext->sz; - pr_debug("extern #%d: symbol %d, off %u, name %s\n", - i, ext->sym_idx, ext->data_off, ext->name); - } - btf_id = btf__find_by_name(obj->btf, KCONFIG_SEC); - if (btf_id <= 0) { - pr_warn("no BTF info found for '%s' datasec\n", KCONFIG_SEC); - return -ESRCH; - } + /* for .ksyms section, we need to turn all externs into allocated + * variables in BTF to pass kernel verification; we do this by + * pretending that each extern is a 8-byte variable + */ + if (ksym_sec) { + /* find existing 4-byte integer type in BTF to use for fake + * extern variables in DATASEC + */ + int int_btf_id = find_int_btf_id(obj->btf); - sec = (struct btf_type *)btf__type_by_id(obj->btf, btf_id); - sec->size = off; - n = btf_vlen(sec); - for (i = 0; i < n; i++) { - struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; - - t = btf__type_by_id(obj->btf, vs->type); - ext_name = btf__name_by_offset(obj->btf, t->name_off); - ext = find_extern_by_name(obj, ext_name); - if (!ext) { - pr_warn("failed to find extern definition for BTF var '%s'\n", - ext_name); - return -ESRCH; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type != EXT_KSYM) + continue; + pr_debug("extern (ksym) #%d: symbol %d, name %s\n", + i, ext->sym_idx, ext->name); } - vs->offset = ext->data_off; - btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + + sec = ksym_sec; + n = btf_vlen(sec); + for (i = 0, off = 0; i < n; i++, off += sizeof(int)) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + struct btf_type *vt; + + vt = (void *)btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, vt->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF var '%s'\n", + ext_name); + return -ESRCH; + } + btf_var(vt)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + vt->type = int_btf_id; + vs->offset = off; + vs->size = sizeof(int); + } + sec->size = off; } + if (kcfg_sec) { + sec = kcfg_sec; + /* for kcfg externs calculate their offsets within a .kconfig map */ + off = 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (ext->type != EXT_KCFG) + continue; + + ext->kcfg.data_off = roundup(off, ext->kcfg.align); + off = ext->kcfg.data_off + ext->kcfg.sz; + pr_debug("extern (kcfg) #%d: symbol %d, off %u, name %s\n", + i, ext->sym_idx, ext->kcfg.data_off, ext->name); + } + sec->size = off; + n = btf_vlen(sec); + for (i = 0; i < n; i++) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + + t = btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, t->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF var '%s'\n", + ext_name); + return -ESRCH; + } + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + vs->offset = ext->kcfg.data_off; + } + } return 0; } @@ -3007,11 +3159,11 @@ static int bpf_program__record_reloc(struct bpf_program *prog, sym_idx); return -LIBBPF_ERRNO__RELOC; } - pr_debug("found extern #%d '%s' (sym %d, off %u) for insn %u\n", - i, ext->name, ext->sym_idx, ext->data_off, insn_idx); + pr_debug("found extern #%d '%s' (sym %d) for insn %u\n", + i, ext->name, ext->sym_idx, insn_idx); reloc_desc->type = RELO_EXTERN; reloc_desc->insn_idx = insn_idx; - reloc_desc->sym_off = ext->data_off; + reloc_desc->sym_off = i; /* sym_off stores extern index */ return 0; } @@ -3222,20 +3374,27 @@ err_free_new_name: return err; } -int bpf_map__resize(struct bpf_map *map, __u32 max_entries) +__u32 bpf_map__max_entries(const struct bpf_map *map) { - if (!map || !max_entries) - return -EINVAL; + return map->def.max_entries; +} - /* If map already created, its attributes can't be changed. */ +int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) +{ if (map->fd >= 0) return -EBUSY; - map->def.max_entries = max_entries; - return 0; } +int bpf_map__resize(struct bpf_map *map, __u32 max_entries) +{ + if (!map || !max_entries) + return -EINVAL; + + return bpf_map__set_max_entries(map, max_entries); +} + static int bpf_object__probe_loading(struct bpf_object *obj) { @@ -3603,6 +3762,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) create_attr.map_flags = def->map_flags; create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; + create_attr.numa_node = map->numa_node; if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { int nr_cpus; @@ -3626,7 +3786,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; - if (obj->btf && !bpf_map_find_btf_info(obj, map)) { + if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; @@ -4799,8 +4959,8 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) if (targ_btf_path) targ_btf = btf__parse_elf(targ_btf_path, NULL); else - targ_btf = libbpf_find_kernel_btf(); - if (IS_ERR(targ_btf)) { + targ_btf = obj->btf_vmlinux; + if (IS_ERR_OR_NULL(targ_btf)) { pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); return PTR_ERR(targ_btf); } @@ -4847,7 +5007,9 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) } out: - btf__free(targ_btf); + /* obj->btf_vmlinux is freed at the end of object load phase */ + if (targ_btf != obj->btf_vmlinux) + btf__free(targ_btf); if (!IS_ERR_OR_NULL(cand_cache)) { hashmap__for_each_entry(cand_cache, entry, i) { bpf_core_free_cands(entry->value); @@ -4934,6 +5096,7 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + struct extern_desc *ext; if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { pr_warn("relocation out of range: '%s'\n", @@ -4952,9 +5115,15 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) insn[0].imm = obj->maps[relo->map_idx].fd; break; case RELO_EXTERN: - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; - insn[1].imm = relo->sym_off; + ext = &obj->externs[relo->sym_off]; + if (ext->type == EXT_KCFG) { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + insn[1].imm = ext->kcfg.data_off; + } else /* EXT_KSYM */ { + insn[0].imm = (__u32)ext->ksym.addr; + insn[1].imm = ext->ksym.addr >> 32; + } break; case RELO_CALL: err = bpf_program__reloc_text(prog, obj, relo); @@ -5207,18 +5376,17 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; } - /* if .BTF.ext was loaded, kernel supports associated BTF for prog */ - if (prog->obj->btf_ext) - btf_fd = bpf_object__btf_fd(prog->obj); - else - btf_fd = -1; - load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0; - load_attr.func_info = prog->func_info; - load_attr.func_info_rec_size = prog->func_info_rec_size; - load_attr.func_info_cnt = prog->func_info_cnt; - load_attr.line_info = prog->line_info; - load_attr.line_info_rec_size = prog->line_info_rec_size; - load_attr.line_info_cnt = prog->line_info_cnt; + /* specify func_info/line_info only if kernel supports them */ + btf_fd = bpf_object__btf_fd(prog->obj); + if (btf_fd >= 0 && prog->obj->caps.btf_func) { + load_attr.prog_btf_fd = btf_fd; + load_attr.func_info = prog->func_info; + load_attr.func_info_rec_size = prog->func_info_rec_size; + load_attr.func_info_cnt = prog->func_info_cnt; + load_attr.line_info = prog->line_info; + load_attr.line_info_rec_size = prog->line_info_rec_size; + load_attr.line_info_cnt = prog->line_info_cnt; + } load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; @@ -5287,6 +5455,12 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { int err = 0, fd, i, btf_id; + if (prog->obj->loaded) { + pr_warn("prog '%s'('%s'): can't load after object was loaded\n", + prog->name, prog->section_name); + return -EINVAL; + } + if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { @@ -5375,16 +5549,21 @@ static bool bpf_program__is_function_storage(const struct bpf_program *prog, static int bpf_object__load_progs(struct bpf_object *obj, int log_level) { + struct bpf_program *prog; size_t i; int err; for (i = 0; i < obj->nr_programs; i++) { - if (bpf_program__is_function_storage(&obj->programs[i], obj)) + prog = &obj->programs[i]; + if (bpf_program__is_function_storage(prog, obj)) + continue; + if (!prog->load) { + pr_debug("prog '%s'('%s'): skipped loading\n", + prog->name, prog->section_name); continue; - obj->programs[i].log_level |= log_level; - err = bpf_program__load(&obj->programs[i], - obj->license, - obj->kern_version); + } + prog->log_level |= log_level; + err = bpf_program__load(prog, obj->license, obj->kern_version); if (err) return err; } @@ -5573,56 +5752,114 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) return 0; } +static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +{ + char sym_type, sym_name[500]; + unsigned long long sym_addr; + struct extern_desc *ext; + int ret, err = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (!f) { + err = -errno; + pr_warn("failed to open /proc/kallsyms: %d\n", err); + return err; + } + + while (true) { + ret = fscanf(f, "%llx %c %499s%*[^\n]\n", + &sym_addr, &sym_type, sym_name); + if (ret == EOF && feof(f)) + break; + if (ret != 3) { + pr_warn("failed to read kallsyms entry: %d\n", ret); + err = -EINVAL; + goto out; + } + + ext = find_extern_by_name(obj, sym_name); + if (!ext || ext->type != EXT_KSYM) + continue; + + if (ext->is_set && ext->ksym.addr != sym_addr) { + pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", + sym_name, ext->ksym.addr, sym_addr); + err = -EINVAL; + goto out; + } + if (!ext->is_set) { + ext->is_set = true; + ext->ksym.addr = sym_addr; + pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); + } + } + +out: + fclose(f); + return err; +} + static int bpf_object__resolve_externs(struct bpf_object *obj, const char *extra_kconfig) { - bool need_config = false; + bool need_config = false, need_kallsyms = false; struct extern_desc *ext; + void *kcfg_data = NULL; int err, i; - void *data; if (obj->nr_extern == 0) return 0; - data = obj->maps[obj->kconfig_map_idx].mmaped; + if (obj->kconfig_map_idx >= 0) + kcfg_data = obj->maps[obj->kconfig_map_idx].mmaped; for (i = 0; i < obj->nr_extern; i++) { ext = &obj->externs[i]; - if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { - void *ext_val = data + ext->data_off; + if (ext->type == EXT_KCFG && + strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + void *ext_val = kcfg_data + ext->kcfg.data_off; __u32 kver = get_kernel_version(); if (!kver) { pr_warn("failed to get kernel version\n"); return -EINVAL; } - err = set_ext_value_num(ext, ext_val, kver); + err = set_kcfg_value_num(ext, ext_val, kver); if (err) return err; - pr_debug("extern %s=0x%x\n", ext->name, kver); - } else if (strncmp(ext->name, "CONFIG_", 7) == 0) { + pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); + } else if (ext->type == EXT_KCFG && + strncmp(ext->name, "CONFIG_", 7) == 0) { need_config = true; + } else if (ext->type == EXT_KSYM) { + need_kallsyms = true; } else { pr_warn("unrecognized extern '%s'\n", ext->name); return -EINVAL; } } if (need_config && extra_kconfig) { - err = bpf_object__read_kconfig_mem(obj, extra_kconfig, data); + err = bpf_object__read_kconfig_mem(obj, extra_kconfig, kcfg_data); if (err) return -EINVAL; need_config = false; for (i = 0; i < obj->nr_extern; i++) { ext = &obj->externs[i]; - if (!ext->is_set) { + if (ext->type == EXT_KCFG && !ext->is_set) { need_config = true; break; } } } if (need_config) { - err = bpf_object__read_kconfig_file(obj, data); + err = bpf_object__read_kconfig_file(obj, kcfg_data); + if (err) + return -EINVAL; + } + if (need_kallsyms) { + err = bpf_object__read_kallsyms_file(obj); if (err) return -EINVAL; } @@ -5653,12 +5890,10 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) return -EINVAL; if (obj->loaded) { - pr_warn("object should not be loaded twice\n"); + pr_warn("object '%s': load can't be attempted twice\n", obj->name); return -EINVAL; } - obj->loaded = true; - err = bpf_object__probe_loading(obj); err = err ? : bpf_object__probe_caps(obj); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); @@ -5673,6 +5908,8 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) btf__free(obj->btf_vmlinux); obj->btf_vmlinux = NULL; + obj->loaded = true; /* doesn't matter if successfully or not */ + if (err) goto out; @@ -6267,7 +6504,7 @@ void bpf_object__close(struct bpf_object *obj) { size_t i; - if (!obj) + if (IS_ERR_OR_NULL(obj)) return; if (obj->clear_priv) @@ -6445,6 +6682,20 @@ const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) return title; } +bool bpf_program__autoload(const struct bpf_program *prog) +{ + return prog->load; +} + +int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) +{ + if (prog->obj->loaded) + return -EINVAL; + + prog->load = autoload; + return 0; +} + int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); @@ -6548,6 +6799,7 @@ BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); +BPF_PROG_TYPE_FNS(sk_lookup, BPF_PROG_TYPE_SK_LOOKUP); enum bpf_attach_type bpf_program__get_expected_attach_type(struct bpf_program *prog) @@ -6661,7 +6913,10 @@ static const struct bpf_sec_def section_defs[] = { .attach_fn = attach_iter), BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), - BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), + BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, + BPF_XDP_CPUMAP), + BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP, + BPF_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), @@ -6672,6 +6927,10 @@ static const struct bpf_sec_def section_defs[] = { BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS), BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), + BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET_SOCK_CREATE), + BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET_SOCK_RELEASE), BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE), BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, @@ -6724,6 +6983,8 @@ static const struct bpf_sec_def section_defs[] = { BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT), BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), + BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, + BPF_SK_LOOKUP), }; #undef BPF_PROG_SEC_IMPL @@ -7094,6 +7355,71 @@ const char *bpf_map__name(const struct bpf_map *map) return map ? map->name : NULL; } +enum bpf_map_type bpf_map__type(const struct bpf_map *map) +{ + return map->def.type; +} + +int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type) +{ + if (map->fd >= 0) + return -EBUSY; + map->def.type = type; + return 0; +} + +__u32 bpf_map__map_flags(const struct bpf_map *map) +{ + return map->def.map_flags; +} + +int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) +{ + if (map->fd >= 0) + return -EBUSY; + map->def.map_flags = flags; + return 0; +} + +__u32 bpf_map__numa_node(const struct bpf_map *map) +{ + return map->numa_node; +} + +int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node) +{ + if (map->fd >= 0) + return -EBUSY; + map->numa_node = numa_node; + return 0; +} + +__u32 bpf_map__key_size(const struct bpf_map *map) +{ + return map->def.key_size; +} + +int bpf_map__set_key_size(struct bpf_map *map, __u32 size) +{ + if (map->fd >= 0) + return -EBUSY; + map->def.key_size = size; + return 0; +} + +__u32 bpf_map__value_size(const struct bpf_map *map) +{ + return map->def.value_size; +} + +int bpf_map__set_value_size(struct bpf_map *map, __u32 size) +{ + if (map->fd >= 0) + return -EBUSY; + map->def.value_size = size; + return 0; +} + __u32 bpf_map__btf_key_type_id(const struct bpf_map *map) { return map ? map->btf_key_type_id : 0; @@ -7146,9 +7472,17 @@ bool bpf_map__is_internal(const struct bpf_map *map) return map->libbpf_type != LIBBPF_MAP_UNSPEC; } -void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) +__u32 bpf_map__ifindex(const struct bpf_map *map) +{ + return map->map_ifindex; +} + +int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { + if (map->fd >= 0) + return -EBUSY; map->map_ifindex = ifindex; + return 0; } int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) @@ -7356,7 +7690,7 @@ int bpf_link__destroy(struct bpf_link *link) { int err = 0; - if (!link) + if (IS_ERR_OR_NULL(link)) return 0; if (!link->disconnected && link->detach) @@ -7414,6 +7748,11 @@ struct bpf_link *bpf_link__open(const char *path) return link; } +int bpf_link__detach(struct bpf_link *link) +{ + return bpf_link_detach(link->fd) ? -errno : 0; +} + int bpf_link__pin(struct bpf_link *link, const char *path) { int err; @@ -7500,6 +7839,9 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, pr_warn("program '%s': failed to attach to pfd %d: %s\n", bpf_program__title(prog, false), pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + if (err == -EPROTO) + pr_warn("program '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n", + bpf_program__title(prog, false), pfd); return ERR_PTR(err); } if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { @@ -7945,17 +8287,30 @@ bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) return bpf_program__attach_fd(prog, netns_fd, "netns"); } +struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex) +{ + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program__attach_fd(prog, ifindex, "xdp"); +} + struct bpf_link * bpf_program__attach_iter(struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, link_fd; + __u32 target_fd = 0; if (!OPTS_VALID(opts, bpf_iter_attach_opts)) return ERR_PTR(-EINVAL); + if (OPTS_HAS(opts, map_fd)) { + target_fd = opts->map_fd; + link_create_opts.flags = BPF_ITER_LINK_MAP_FD; + } + prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("program '%s': can't attach before loaded\n", @@ -7968,7 +8323,8 @@ bpf_program__attach_iter(struct bpf_program *prog, return ERR_PTR(-ENOMEM); link->detach = &bpf_link__detach_fd; - link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_ITER, NULL); + link_fd = bpf_link_create(prog_fd, target_fd, BPF_TRACE_ITER, + &link_create_opts); if (link_fd < 0) { link_fd = -errno; free(link); @@ -8151,7 +8507,7 @@ void perf_buffer__free(struct perf_buffer *pb) { int i; - if (!pb) + if (IS_ERR_OR_NULL(pb)) return; if (pb->cpu_bufs) { for (i = 0; i < pb->cpu_cnt; i++) { @@ -8264,7 +8620,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { const char *online_cpus_file = "/sys/devices/system/cpu/online"; - struct bpf_map_info map = {}; + struct bpf_map_info map; char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; bool *online = NULL; @@ -8277,19 +8633,28 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, return ERR_PTR(-EINVAL); } + /* best-effort sanity checks */ + memset(&map, 0, sizeof(map)); map_info_len = sizeof(map); err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); if (err) { err = -errno; - pr_warn("failed to get map info for map FD %d: %s\n", - map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); - return ERR_PTR(err); - } - - if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { - pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", - map.name); - return ERR_PTR(-EINVAL); + /* if BPF_OBJ_GET_INFO_BY_FD is supported, will return + * -EBADFD, -EFAULT, or -E2BIG on real error + */ + if (err != -EINVAL) { + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + pr_debug("failed to get map info for FD %d; API not supported? Ignoring...\n", + map_fd); + } else { + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } } pb = calloc(1, sizeof(*pb)); @@ -8321,7 +8686,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = pb->cpu_cnt; goto error; } - if (map.max_entries < pb->cpu_cnt) + if (map.max_entries && map.max_entries < pb->cpu_cnt) pb->cpu_cnt = map.max_entries; } @@ -8994,6 +9359,9 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) const struct bpf_sec_def *sec_def; const char *sec_name = bpf_program__title(prog, false); + if (!prog->load) + continue; + sec_def = find_sec_def(sec_name); if (!sec_def || !sec_def->attach_fn) continue; @@ -9016,8 +9384,7 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->prog_cnt; i++) { struct bpf_link **link = s->progs[i].link; - if (!IS_ERR_OR_NULL(*link)) - bpf_link__destroy(*link); + bpf_link__destroy(*link); *link = NULL; } } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 334437af3014..3ed1399bfbbc 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -200,6 +200,8 @@ LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); +LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); /* returns program size in bytes */ LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); @@ -227,6 +229,7 @@ LIBBPF_API int bpf_link__unpin(struct bpf_link *link); LIBBPF_API int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog); LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); +LIBBPF_API int bpf_link__detach(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * @@ -255,6 +258,8 @@ LIBBPF_API struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); +LIBBPF_API struct bpf_link * +bpf_program__attach_xdp(struct bpf_program *prog, int ifindex); struct bpf_map; @@ -262,8 +267,9 @@ LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 map_fd; }; -#define bpf_iter_attach_opts__last_field sz +#define bpf_iter_attach_opts__last_field map_fd LIBBPF_API struct bpf_link * bpf_program__attach_iter(struct bpf_program *prog, @@ -348,6 +354,7 @@ LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog); LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, @@ -375,6 +382,7 @@ LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -418,11 +426,38 @@ bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); +/* get/set map FD */ LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); +/* get map definition */ LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +/* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); +/* get/set map type */ +LIBBPF_API enum bpf_map_type bpf_map__type(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); +/* get/set map size (max_entries) */ +LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); +LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); +/* get/set map flags */ +LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags); +/* get/set map NUMA node */ +LIBBPF_API __u32 bpf_map__numa_node(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); +/* get/set map key size */ +LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); +/* get/set map value size */ +LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); +/* get map key/value BTF type IDs */ LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); +/* get/set map if_index */ +LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, @@ -430,11 +465,8 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); -LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); -LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); -LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f732c77b7ed0..0c4722bfdd0a 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -270,3 +270,30 @@ LIBBPF_0.0.9 { ring_buffer__new; ring_buffer__poll; } LIBBPF_0.0.8; + +LIBBPF_0.1.0 { + global: + bpf_link__detach; + bpf_link_detach; + bpf_map__ifindex; + bpf_map__key_size; + bpf_map__map_flags; + bpf_map__max_entries; + bpf_map__numa_node; + bpf_map__set_key_size; + bpf_map__set_map_flags; + bpf_map__set_max_entries; + bpf_map__set_numa_node; + bpf_map__set_type; + bpf_map__set_value_size; + bpf_map__type; + bpf_map__value_size; + bpf_program__attach_xdp; + bpf_program__autoload; + bpf_program__is_sk_lookup; + bpf_program__set_autoload; + bpf_program__set_sk_lookup; + btf__parse; + btf__parse_raw; + btf__set_fd; +} LIBBPF_0.0.9; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 10cd8d1891f5..5a3d3f078408 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -78,6 +78,9 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; + case BPF_PROG_TYPE_SK_LOOKUP: + xattr.expected_attach_type = BPF_SK_LOOKUP; + break; case BPF_PROG_TYPE_KPROBE: xattr.kern_version = get_kernel_version(); break; diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index e91a2eb19592..f9d610d5a1a4 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -1122,12 +1122,10 @@ maintain at least the appearance of FIFO order. In practice, this difficulty is solved by inserting a special fence between P1's two loads when the kernel is compiled for the Alpha architecture. In fact, as of version 4.15, the kernel automatically -adds this fence (called smp_read_barrier_depends() and defined as -nothing at all on non-Alpha builds) after every READ_ONCE() and atomic -load. The effect of the fence is to cause the CPU not to execute any -po-later instructions until after the local cache has finished -processing all the stores it has already received. Thus, if the code -was changed to: +adds this fence after every READ_ONCE() and atomic load on Alpha. The +effect of the fence is to cause the CPU not to execute any po-later +instructions until after the local cache has finished processing all +the stores it has already received. Thus, if the code was changed to: P1() { @@ -1146,14 +1144,14 @@ READ_ONCE() or another synchronization primitive rather than accessed directly. The LKMM requires that smp_rmb(), acquire fences, and strong fences -share this property with smp_read_barrier_depends(): They do not allow -the CPU to execute any po-later instructions (or po-later loads in the -case of smp_rmb()) until all outstanding stores have been processed by -the local cache. In the case of a strong fence, the CPU first has to -wait for all of its po-earlier stores to propagate to every other CPU -in the system; then it has to wait for the local cache to process all -the stores received as of that time -- not just the stores received -when the strong fence began. +share this property: They do not allow the CPU to execute any po-later +instructions (or po-later loads in the case of smp_rmb()) until all +outstanding stores have been processed by the local cache. In the +case of a strong fence, the CPU first has to wait for all of its +po-earlier stores to propagate to every other CPU in the system; then +it has to wait for the local cache to process all the stores received +as of that time -- not just the stores received when the strong fence +began. And of course, none of this matters for any architecture other than Alpha. @@ -1987,28 +1985,36 @@ outcome undefined. In technical terms, the compiler is allowed to assume that when the program executes, there will not be any data races. A "data race" -occurs when two conflicting memory accesses execute concurrently; -two memory accesses "conflict" if: +occurs when there are two memory accesses such that: - they access the same location, +1. they access the same location, - they occur on different CPUs (or in different threads on the - same CPU), +2. at least one of them is a store, - at least one of them is a plain access, +3. at least one of them is plain, - and at least one of them is a store. +4. they occur on different CPUs (or in different threads on the + same CPU), and -The LKMM tries to determine whether a program contains two conflicting -accesses which may execute concurrently; if it does then the LKMM says -there is a potential data race and makes no predictions about the -program's outcome. +5. they execute concurrently. -Determining whether two accesses conflict is easy; you can see that -all the concepts involved in the definition above are already part of -the memory model. The hard part is telling whether they may execute -concurrently. The LKMM takes a conservative attitude, assuming that -accesses may be concurrent unless it can prove they cannot. +In the literature, two accesses are said to "conflict" if they satisfy +1 and 2 above. We'll go a little farther and say that two accesses +are "race candidates" if they satisfy 1 - 4. Thus, whether or not two +race candidates actually do race in a given execution depends on +whether they are concurrent. + +The LKMM tries to determine whether a program contains race candidates +which may execute concurrently; if it does then the LKMM says there is +a potential data race and makes no predictions about the program's +outcome. + +Determining whether two accesses are race candidates is easy; you can +see that all the concepts involved in the definition above are already +part of the memory model. The hard part is telling whether they may +execute concurrently. The LKMM takes a conservative attitude, +assuming that accesses may be concurrent unless it can prove they +are not. If two memory accesses aren't concurrent then one must execute before the other. Therefore the LKMM decides two accesses aren't concurrent @@ -2171,8 +2177,8 @@ again, now using plain accesses for buf: } This program does not contain a data race. Although the U and V -accesses conflict, the LKMM can prove they are not concurrent as -follows: +accesses are race candidates, the LKMM can prove they are not +concurrent as follows: The smp_wmb() fence in P0 is both a compiler barrier and a cumul-fence. It guarantees that no matter what hash of @@ -2326,12 +2332,11 @@ could now perform the load of x before the load of ptr (there might be a control dependency but no address dependency at the machine level). Finally, it turns out there is a situation in which a plain write does -not need to be w-post-bounded: when it is separated from the -conflicting access by a fence. At first glance this may seem -impossible. After all, to be conflicting the second access has to be -on a different CPU from the first, and fences don't link events on -different CPUs. Well, normal fences don't -- but rcu-fence can! -Here's an example: +not need to be w-post-bounded: when it is separated from the other +race-candidate access by a fence. At first glance this may seem +impossible. After all, to be race candidates the two accesses must +be on different CPUs, and fences don't link events on different CPUs. +Well, normal fences don't -- but rcu-fence can! Here's an example: int x, y; @@ -2367,7 +2372,7 @@ concurrent and there is no race, even though P1's plain store to y isn't w-post-bounded by any marked accesses. Putting all this material together yields the following picture. For -two conflicting stores W and W', where W ->co W', the LKMM says the +race-candidate stores W and W', where W ->co W', the LKMM says the stores don't race if W can be linked to W' by a w-post-bounded ; vis ; w-pre-bounded @@ -2380,8 +2385,8 @@ sequence, and if W' is plain then they also have to be linked by a w-post-bounded ; vis ; r-pre-bounded -sequence. For a conflicting load R and store W, the LKMM says the two -accesses don't race if R can be linked to W by an +sequence. For race-candidate load R and store W, the LKMM says the +two accesses don't race if R can be linked to W by an r-post-bounded ; xb* ; w-pre-bounded @@ -2413,20 +2418,20 @@ is, the rules governing the memory subsystem's choice of a store to satisfy a load request and its determination of where a store will fall in the coherence order): - If R and W conflict and it is possible to link R to W by one - of the xb* sequences listed above, then W ->rfe R is not - allowed (i.e., a load cannot read from a store that it + If R and W are race candidates and it is possible to link R to + W by one of the xb* sequences listed above, then W ->rfe R is + not allowed (i.e., a load cannot read from a store that it executes before, even if one or both is plain). - If W and R conflict and it is possible to link W to R by one - of the vis sequences listed above, then R ->fre W is not - allowed (i.e., if a store is visible to a load then the load - must read from that store or one coherence-after it). + If W and R are race candidates and it is possible to link W to + R by one of the vis sequences listed above, then R ->fre W is + not allowed (i.e., if a store is visible to a load then the + load must read from that store or one coherence-after it). - If W and W' conflict and it is possible to link W to W' by one - of the vis sequences listed above, then W' ->co W is not - allowed (i.e., if one store is visible to a second then the - second must come after the first in the coherence order). + If W and W' are race candidates and it is possible to link W + to W' by one of the vis sequences listed above, then W' ->co W + is not allowed (i.e., if one store is visible to a second then + the second must come after the first in the coherence order). This is the extent to which the LKMM deals with plain accesses. Perhaps it could say more (for example, plain accesses might diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt index 7fe8d7aa3029..63c4adfed884 100644 --- a/tools/memory-model/Documentation/recipes.txt +++ b/tools/memory-model/Documentation/recipes.txt @@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by locking will be seen as ordered by CPUs not holding that lock. Consider this example: - /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */ + /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ void CPU0(void) { spin_lock(&mylock); diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt index b177f3e4a614..ecbbaa5396d4 100644 --- a/tools/memory-model/Documentation/references.txt +++ b/tools/memory-model/Documentation/references.txt @@ -73,6 +73,18 @@ o Christopher Pulte, Shaked Flur, Will Deacon, Jon French, Linux-kernel memory model ========================= +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Calibrating your fear of big bad optimizing compilers" + Linux Weekly News. https://lwn.net/Articles/799218/ + +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Who's afraid of a big bad optimizing compiler?" + Linux Weekly News. https://lwn.net/Articles/793253/ + o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2018. "Frightening small children and disconcerting grown-ups: Concurrency in the Linux kernel". In Proceedings of @@ -88,6 +100,11 @@ o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2017. "A formal kernel memory-ordering model (part 2)" Linux Weekly News. https://lwn.net/Articles/720550/ +o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and + Alan Stern. 2017-2019. "A Formal Model of Linux-Kernel Memory + Ordering" (backup material for the LWN articles) + https://mirrors.edge.kernel.org/pub/linux/kernel/people/paulmck/LWNLinuxMM/ + Memory-model tooling ==================== @@ -110,5 +127,5 @@ Memory-model comparisons ======================== o Paul E. McKenney, Ulrich Weigand, Andrea Parri, and Boqun - Feng. 2016. "Linux-Kernel Memory Model". (6 June 2016). - http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/p0124r2.html. + Feng. 2018. "Linux-Kernel Memory Model". (27 September 2018). + http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p0124r6.html. diff --git a/tools/memory-model/README b/tools/memory-model/README index fc07b52f2028..ecb7385376bf 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -28,8 +28,34 @@ downloaded separately: See "herdtools7/INSTALL.md" for installation instructions. Note that although these tools usually provide backwards compatibility, -this is not absolutely guaranteed. Therefore, if a later version does -not work, please try using the exact version called out above. +this is not absolutely guaranteed. + +For example, a future version of herd7 might not work with the model +in this release. A compatible model will likely be made available in +a later release of Linux kernel. + +If you absolutely need to run the model in this particular release, +please try using the exact version called out above. + +klitmus7 is independent of the model provided here. It has its own +dependency on a target kernel release where converted code is built +and executed. Any change in kernel APIs essential to klitmus7 will +necessitate an upgrade of klitmus7. + +If you find any compatibility issues in klitmus7, please inform the +memory model maintainers. + +klitmus7 Compatibility Table +---------------------------- + + ============ ========== + target Linux herdtools7 + ------------ ---------- + -- 4.18 7.48 -- + 4.15 -- 4.19 7.49 -- + 4.20 -- 5.5 7.54 -- + 5.6 -- 7.56 -- + ============ ========== ================== @@ -207,11 +233,15 @@ The Linux-kernel memory model (LKMM) has the following limitations: case as a store release. b. The "unless" RMW operations are not currently modeled: - atomic_long_add_unless(), atomic_add_unless(), - atomic_inc_unless_negative(), and - atomic_dec_unless_positive(). These can be emulated + atomic_long_add_unless(), atomic_inc_unless_negative(), + and atomic_dec_unless_positive(). These can be emulated in litmus tests, for example, by using atomic_cmpxchg(). + One exception of this limitation is atomic_add_unless(), + which is provided directly by herd7 (so no corresponding + definition in linux-kernel.def). atomic_add_unless() is + modeled by herd7 therefore it can be used in litmus tests. + c. The call_rcu() function is not modeled. It can be emulated in litmus tests by adding another process that invokes synchronize_rcu() and the body of the callback diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 3c5967748abb..2e2ce089b0e9 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -82,7 +82,7 @@ bool arch_callee_saved_reg(unsigned char reg); unsigned long arch_jump_destination(struct instruction *insn); -unsigned long arch_dest_rela_offset(int addend); +unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 9872195f998b..1967370440b3 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -67,7 +67,7 @@ bool arch_callee_saved_reg(unsigned char reg) } } -unsigned long arch_dest_rela_offset(int addend) +unsigned long arch_dest_reloc_offset(int addend) { return addend + 4; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5e0d70a89fb8..e034a8f24f46 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -353,7 +353,7 @@ static struct instruction *find_last_insn(struct objtool_file *file, static int add_dead_ends(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; /* @@ -371,24 +371,24 @@ static int add_dead_ends(struct objtool_file *file) if (!sec) goto reachable; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -406,24 +406,24 @@ reachable: if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -441,26 +441,26 @@ static void add_ignores(struct objtool_file *file) struct instruction *insn; struct section *sec; struct symbol *func; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); if (!sec) return; - list_for_each_entry(rela, &sec->rela_list, list) { - switch (rela->sym->type) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + switch (reloc->sym->type) { case STT_FUNC: - func = rela->sym; + func = reloc->sym; break; case STT_SECTION: - func = find_func_by_offset(rela->sym->sec, rela->addend); + func = find_func_by_offset(reloc->sym->sec, reloc->addend); if (!func) continue; break; default: - WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type); + WARN("unexpected relocation symbol type in %s: %d", sec->name, reloc->sym->type); continue; } @@ -580,20 +580,20 @@ static void add_uaccess_safe(struct objtool_file *file) static int add_ignore_alternatives(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.ignore_alts entry"); return -1; @@ -611,7 +611,7 @@ static int add_ignore_alternatives(struct objtool_file *file) static int add_jump_destinations(struct objtool_file *file) { struct instruction *insn; - struct rela *rela; + struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; @@ -622,19 +622,19 @@ static int add_jump_destinations(struct objtool_file *file) if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_sec = insn->sec; dest_off = arch_jump_destination(insn); - } else if (rela->sym->type == STT_SECTION) { - dest_sec = rela->sym->sec; - dest_off = arch_dest_rela_offset(rela->addend); - } else if (rela->sym->sec->idx) { - dest_sec = rela->sym->sec; - dest_off = rela->sym->sym.st_value + - arch_dest_rela_offset(rela->addend); - } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + } else if (reloc->sym->type == STT_SECTION) { + dest_sec = reloc->sym->sec; + dest_off = arch_dest_reloc_offset(reloc->addend); + } else if (reloc->sym->sec->idx) { + dest_sec = reloc->sym->sec; + dest_off = reloc->sym->sym.st_value + + arch_dest_reloc_offset(reloc->addend); + } else if (strstr(reloc->sym->name, "_indirect_thunk_")) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. @@ -648,7 +648,7 @@ static int add_jump_destinations(struct objtool_file *file) continue; } else { /* external sibling call */ - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; continue; } @@ -724,15 +724,15 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; - struct rela *rela; + struct reloc *reloc; for_each_insn(file, insn) { if (insn->type != INSN_CALL) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_off = arch_jump_destination(insn); insn->call_dest = find_func_by_offset(insn->sec, dest_off); if (!insn->call_dest) @@ -752,19 +752,19 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (rela->sym->type == STT_SECTION) { - dest_off = arch_dest_rela_offset(rela->addend); - insn->call_dest = find_func_by_offset(rela->sym->sec, + } else if (reloc->sym->type == STT_SECTION) { + dest_off = arch_dest_reloc_offset(reloc->addend); + insn->call_dest = find_func_by_offset(reloc->sym->sec, dest_off); if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, - rela->sym->sec->name, + reloc->sym->sec->name, dest_off); return -1; } } else - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; /* * Many compilers cannot disable KCOV with a function attribute @@ -773,9 +773,9 @@ static int add_call_destinations(struct objtool_file *file) */ if (insn->sec->noinstr && !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (rela) { - rela->type = R_NONE; - elf_write_rela(file->elf, rela); + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); } elf_write_insn(file->elf, insn->sec, @@ -890,7 +890,7 @@ static int handle_group_alt(struct objtool_file *file, */ if ((insn->offset != special_alt->new_off || (insn->type != INSN_CALL && !is_static_jump(insn))) && - find_rela_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { + find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { WARN_FUNC("unsupported relocation in alternatives section", insn->sec, insn->offset); @@ -1036,34 +1036,34 @@ out: } static int add_jump_table(struct objtool_file *file, struct instruction *insn, - struct rela *table) + struct reloc *table) { - struct rela *rela = table; + struct reloc *reloc = table; struct instruction *dest_insn; struct alternative *alt; struct symbol *pfunc = insn->func->pfunc; unsigned int prev_offset = 0; /* - * Each @rela is a switch table relocation which points to the target + * Each @reloc is a switch table relocation which points to the target * instruction. */ - list_for_each_entry_from(rela, &table->sec->rela_list, list) { + list_for_each_entry_from(reloc, &table->sec->reloc_list, list) { /* Check for the end of the table: */ - if (rela != table && rela->jump_table_start) + if (reloc != table && reloc->jump_table_start) break; /* Make sure the table entries are consecutive: */ - if (prev_offset && rela->offset != prev_offset + 8) + if (prev_offset && reloc->offset != prev_offset + 8) break; /* Detect function pointers from contiguous objects: */ - if (rela->sym->sec == pfunc->sec && - rela->addend == pfunc->offset) + if (reloc->sym->sec == pfunc->sec && + reloc->addend == pfunc->offset) break; - dest_insn = find_insn(file, rela->sym->sec, rela->addend); + dest_insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!dest_insn) break; @@ -1079,7 +1079,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; list_add_tail(&alt->list, &insn->alts); - prev_offset = rela->offset; + prev_offset = reloc->offset; } if (!prev_offset) { @@ -1134,11 +1134,11 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, * * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ -static struct rela *find_jump_table(struct objtool_file *file, +static struct reloc *find_jump_table(struct objtool_file *file, struct symbol *func, struct instruction *insn) { - struct rela *text_rela, *table_rela; + struct reloc *text_reloc, *table_reloc; struct instruction *dest_insn, *orig_insn = insn; struct section *table_sec; unsigned long table_offset; @@ -1163,16 +1163,16 @@ static struct rela *find_jump_table(struct objtool_file *file, break; /* look for a relocation which references .rodata */ - text_rela = find_rela_by_dest_range(file->elf, insn->sec, + text_reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!text_rela || text_rela->sym->type != STT_SECTION || - !text_rela->sym->sec->rodata) + if (!text_reloc || text_reloc->sym->type != STT_SECTION || + !text_reloc->sym->sec->rodata) continue; - table_offset = text_rela->addend; - table_sec = text_rela->sym->sec; + table_offset = text_reloc->addend; + table_sec = text_reloc->sym->sec; - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) table_offset += 4; /* @@ -1189,14 +1189,14 @@ static struct rela *find_jump_table(struct objtool_file *file, continue; /* - * Each table entry has a rela associated with it. The rela + * Each table entry has a reloc associated with it. The reloc * should reference text in the same function as the original * instruction. */ - table_rela = find_rela_by_dest(file->elf, table_sec, table_offset); - if (!table_rela) + table_reloc = find_reloc_by_dest(file->elf, table_sec, table_offset); + if (!table_reloc) continue; - dest_insn = find_insn(file, table_rela->sym->sec, table_rela->addend); + dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend); if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func) continue; @@ -1205,10 +1205,10 @@ static struct rela *find_jump_table(struct objtool_file *file, * indicates a rare GCC quirk/bug which can leave dead code * behind. */ - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) file->ignore_unreachables = true; - return table_rela; + return table_reloc; } return NULL; @@ -1222,7 +1222,7 @@ static void mark_func_jump_tables(struct objtool_file *file, struct symbol *func) { struct instruction *insn, *last = NULL; - struct rela *rela; + struct reloc *reloc; func_for_each_insn(file, func, insn) { if (!last) @@ -1245,10 +1245,10 @@ static void mark_func_jump_tables(struct objtool_file *file, if (insn->type != INSN_JUMP_DYNAMIC) continue; - rela = find_jump_table(file, func, insn); - if (rela) { - rela->jump_table_start = true; - insn->jump_table = rela; + reloc = find_jump_table(file, func, insn); + if (reloc) { + reloc->jump_table_start = true; + insn->jump_table = reloc; } } } @@ -1302,8 +1302,8 @@ static int add_jump_table_alts(struct objtool_file *file) static int read_unwind_hints(struct objtool_file *file) { - struct section *sec, *relasec; - struct rela *rela; + struct section *sec, *relocsec; + struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; struct cfi_reg *cfa; @@ -1313,8 +1313,8 @@ static int read_unwind_hints(struct objtool_file *file) if (!sec) return 0; - relasec = sec->rela; - if (!relasec) { + relocsec = sec->reloc; + if (!relocsec) { WARN("missing .rela.discard.unwind_hints section"); return -1; } @@ -1329,13 +1329,13 @@ static int read_unwind_hints(struct objtool_file *file) for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; - rela = find_rela_by_dest(file->elf, sec, i * sizeof(*hint)); - if (!rela) { - WARN("can't find rela for unwind_hints[%d]", i); + reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); + if (!reloc) { + WARN("can't find reloc for unwind_hints[%d]", i); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("can't find insn for unwind_hints[%d]", i); return -1; @@ -1393,19 +1393,19 @@ static int read_retpoline_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.retpoline_safe entry"); return -1; @@ -1428,19 +1428,19 @@ static int read_instr_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.instr_end"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -1453,13 +1453,13 @@ static int read_instr_hints(struct objtool_file *file) if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_begin entry"); return -1; @@ -1475,22 +1475,22 @@ static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; struct section *sec; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { + list_for_each_entry(reloc, &sec->reloc_list, list) { unsigned long dest_off; - if (rela->sym->type != STT_SECTION) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.intra_function_call entry"); return -1; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 906b5210f7ca..061aa96e15d3 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -37,7 +37,7 @@ struct instruction { struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; - struct rela *jump_table; + struct reloc *jump_table; struct list_head alts; struct symbol *func; struct list_head stack_ops; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 26d11d821941..3ddbd66f1a37 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -228,26 +228,26 @@ struct symbol *find_symbol_by_name(const struct elf *elf, const char *name) return NULL; } -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len) { - struct rela *rela, *r = NULL; + struct reloc *reloc, *r = NULL; unsigned long o; - if (!sec->rela) + if (!sec->reloc) return NULL; - sec = sec->rela; + sec = sec->reloc; for_offset_range(o, offset, offset + len) { - elf_hash_for_each_possible(elf->rela_hash, rela, hash, + elf_hash_for_each_possible(elf->reloc_hash, reloc, hash, sec_offset_hash(sec, o)) { - if (rela->sec != sec) + if (reloc->sec != sec) continue; - if (rela->offset >= offset && rela->offset < offset + len) { - if (!r || rela->offset < r->offset) - r = rela; + if (reloc->offset >= offset && reloc->offset < offset + len) { + if (!r || reloc->offset < r->offset) + r = reloc; } } if (r) @@ -257,9 +257,9 @@ struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, return NULL; } -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) { - return find_rela_by_dest_range(elf, sec, offset, 1); + return find_reloc_by_dest_range(elf, sec, offset, 1); } static int read_sections(struct elf *elf) @@ -288,7 +288,7 @@ static int read_sections(struct elf *elf) memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_getscn(elf->elf, i); if (!s) { @@ -434,7 +434,13 @@ static int read_symbols(struct elf *elf) size_t pnamelen; if (sym->type != STT_FUNC) continue; - sym->pfunc = sym->cfunc = sym; + + if (sym->pfunc == NULL) + sym->pfunc = sym; + + if (sym->cfunc == NULL) + sym->cfunc = sym; + coldstr = strstr(sym->name, ".cold"); if (!coldstr) continue; @@ -482,72 +488,101 @@ err: return -1; } -void elf_add_rela(struct elf *elf, struct rela *rela) +void elf_add_reloc(struct elf *elf, struct reloc *reloc) +{ + struct section *sec = reloc->sec; + + list_add_tail(&reloc->list, &sec->reloc_list); + elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc)); +} + +static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) { - struct section *sec = rela->sec; + if (!gelf_getrel(sec->data, i, &reloc->rel)) { + WARN_ELF("gelf_getrel"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rel.r_info); + reloc->addend = 0; + reloc->offset = reloc->rel.r_offset; + *symndx = GELF_R_SYM(reloc->rel.r_info); + return 0; +} - list_add_tail(&rela->list, &sec->rela_list); - elf_hash_add(elf->rela_hash, &rela->hash, rela_hash(rela)); +static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) +{ + if (!gelf_getrela(sec->data, i, &reloc->rela)) { + WARN_ELF("gelf_getrela"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rela.r_info); + reloc->addend = reloc->rela.r_addend; + reloc->offset = reloc->rela.r_offset; + *symndx = GELF_R_SYM(reloc->rela.r_info); + return 0; } -static int read_relas(struct elf *elf) +static int read_relocs(struct elf *elf) { struct section *sec; - struct rela *rela; + struct reloc *reloc; int i; unsigned int symndx; - unsigned long nr_rela, max_rela = 0, tot_rela = 0; + unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0; list_for_each_entry(sec, &elf->sections, list) { - if (sec->sh.sh_type != SHT_RELA) + if ((sec->sh.sh_type != SHT_RELA) && + (sec->sh.sh_type != SHT_REL)) continue; - sec->base = find_section_by_name(elf, sec->name + 5); + sec->base = find_section_by_index(elf, sec->sh.sh_info); if (!sec->base) { - WARN("can't find base section for rela section %s", + WARN("can't find base section for reloc section %s", sec->name); return -1; } - sec->base->rela = sec; + sec->base->reloc = sec; - nr_rela = 0; + nr_reloc = 0; for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - rela = malloc(sizeof(*rela)); - if (!rela) { + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); - - if (!gelf_getrela(sec->data, i, &rela->rela)) { - WARN_ELF("gelf_getrela"); - return -1; + memset(reloc, 0, sizeof(*reloc)); + switch (sec->sh.sh_type) { + case SHT_REL: + if (read_rel_reloc(sec, i, reloc, &symndx)) + return -1; + break; + case SHT_RELA: + if (read_rela_reloc(sec, i, reloc, &symndx)) + return -1; + break; + default: return -1; } - rela->type = GELF_R_TYPE(rela->rela.r_info); - rela->addend = rela->rela.r_addend; - rela->offset = rela->rela.r_offset; - symndx = GELF_R_SYM(rela->rela.r_info); - rela->sec = sec; - rela->idx = i; - rela->sym = find_symbol_by_index(elf, symndx); - if (!rela->sym) { - WARN("can't find rela entry symbol %d for %s", + reloc->sec = sec; + reloc->idx = i; + reloc->sym = find_symbol_by_index(elf, symndx); + if (!reloc->sym) { + WARN("can't find reloc entry symbol %d for %s", symndx, sec->name); return -1; } - elf_add_rela(elf, rela); - nr_rela++; + elf_add_reloc(elf, reloc); + nr_reloc++; } - max_rela = max(max_rela, nr_rela); - tot_rela += nr_rela; + max_reloc = max(max_reloc, nr_reloc); + tot_reloc += nr_reloc; } if (stats) { - printf("max_rela: %lu\n", max_rela); - printf("tot_rela: %lu\n", tot_rela); + printf("max_reloc: %lu\n", max_reloc); + printf("tot_reloc: %lu\n", tot_reloc); } return 0; @@ -573,7 +608,7 @@ struct elf *elf_open_read(const char *name, int flags) elf_hash_init(elf->symbol_name_hash); elf_hash_init(elf->section_hash); elf_hash_init(elf->section_name_hash); - elf_hash_init(elf->rela_hash); + elf_hash_init(elf->reloc_hash); elf->fd = open(name, flags); if (elf->fd == -1) { @@ -606,7 +641,7 @@ struct elf *elf_open_read(const char *name, int flags) if (read_symbols(elf)) goto err; - if (read_relas(elf)) + if (read_relocs(elf)) goto err; return elf; @@ -632,7 +667,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_newscn(elf->elf); if (!s) { @@ -719,28 +754,28 @@ struct section *elf_create_section(struct elf *elf, const char *name, return sec; } -struct section *elf_create_rela_section(struct elf *elf, struct section *base) +static struct section *elf_create_rel_reloc_section(struct elf *elf, struct section *base) { - char *relaname; + char *relocname; struct section *sec; - relaname = malloc(strlen(base->name) + strlen(".rela") + 1); - if (!relaname) { + relocname = malloc(strlen(base->name) + strlen(".rel") + 1); + if (!relocname) { perror("malloc"); return NULL; } - strcpy(relaname, ".rela"); - strcat(relaname, base->name); + strcpy(relocname, ".rel"); + strcat(relocname, base->name); - sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0); - free(relaname); + sec = elf_create_section(elf, relocname, sizeof(GElf_Rel), 0); + free(relocname); if (!sec) return NULL; - base->rela = sec; + base->reloc = sec; sec->base = base; - sec->sh.sh_type = SHT_RELA; + sec->sh.sh_type = SHT_REL; sec->sh.sh_addralign = 8; sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; sec->sh.sh_info = base->idx; @@ -749,42 +784,125 @@ struct section *elf_create_rela_section(struct elf *elf, struct section *base) return sec; } -int elf_rebuild_rela_section(struct elf *elf, struct section *sec) +static struct section *elf_create_rela_reloc_section(struct elf *elf, struct section *base) { - struct rela *rela; - int nr, idx = 0, size; - GElf_Rela *relas; + char *relocname; + struct section *sec; - nr = 0; - list_for_each_entry(rela, &sec->rela_list, list) - nr++; + relocname = malloc(strlen(base->name) + strlen(".rela") + 1); + if (!relocname) { + perror("malloc"); + return NULL; + } + strcpy(relocname, ".rela"); + strcat(relocname, base->name); + + sec = elf_create_section(elf, relocname, sizeof(GElf_Rela), 0); + free(relocname); + if (!sec) + return NULL; - size = nr * sizeof(*relas); - relas = malloc(size); - if (!relas) { + base->reloc = sec; + sec->base = base; + + sec->sh.sh_type = SHT_RELA; + sec->sh.sh_addralign = 8; + sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + sec->sh.sh_info = base->idx; + sec->sh.sh_flags = SHF_INFO_LINK; + + return sec; +} + +struct section *elf_create_reloc_section(struct elf *elf, + struct section *base, + int reltype) +{ + switch (reltype) { + case SHT_REL: return elf_create_rel_reloc_section(elf, base); + case SHT_RELA: return elf_create_rela_reloc_section(elf, base); + default: return NULL; + } +} + +static int elf_rebuild_rel_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rel *relocs; + + /* Allocate a buffer for relocations */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { perror("malloc"); return -1; } - sec->changed = true; - elf->changed = true; + sec->data->d_buf = relocs; + sec->data->d_size = size; + + sec->sh.sh_size = size; + + idx = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + idx++; + } + + return 0; +} + +static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rela *relocs; + + /* Allocate a buffer for relocations with addends */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { + perror("malloc"); + return -1; + } - sec->data->d_buf = relas; + sec->data->d_buf = relocs; sec->data->d_size = size; sec->sh.sh_size = size; idx = 0; - list_for_each_entry(rela, &sec->rela_list, list) { - relas[idx].r_offset = rela->offset; - relas[idx].r_addend = rela->addend; - relas[idx].r_info = GELF_R_INFO(rela->sym->idx, rela->type); + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_addend = reloc->addend; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); idx++; } return 0; } +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) +{ + struct reloc *reloc; + int nr; + + sec->changed = true; + elf->changed = true; + + nr = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) + nr++; + + switch (sec->sh.sh_type) { + case SHT_REL: return elf_rebuild_rel_reloc_section(sec, nr); + case SHT_RELA: return elf_rebuild_rela_reloc_section(sec, nr); + default: return -1; + } +} + int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn) @@ -804,17 +922,27 @@ int elf_write_insn(struct elf *elf, struct section *sec, return 0; } -int elf_write_rela(struct elf *elf, struct rela *rela) +int elf_write_reloc(struct elf *elf, struct reloc *reloc) { - struct section *sec = rela->sec; + struct section *sec = reloc->sec; - rela->rela.r_info = GELF_R_INFO(rela->sym->idx, rela->type); - rela->rela.r_addend = rela->addend; - rela->rela.r_offset = rela->offset; + if (sec->sh.sh_type == SHT_REL) { + reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rel.r_offset = reloc->offset; - if (!gelf_update_rela(sec->data, rela->idx, &rela->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; + if (!gelf_update_rel(sec->data, reloc->idx, &reloc->rel)) { + WARN_ELF("gelf_update_rel"); + return -1; + } + } else { + reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rela.r_addend = reloc->addend; + reloc->rela.r_offset = reloc->offset; + + if (!gelf_update_rela(sec->data, reloc->idx, &reloc->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } } elf->changed = true; @@ -862,7 +990,7 @@ void elf_close(struct elf *elf) { struct section *sec, *tmpsec; struct symbol *sym, *tmpsym; - struct rela *rela, *tmprela; + struct reloc *reloc, *tmpreloc; if (elf->elf) elf_end(elf->elf); @@ -876,10 +1004,10 @@ void elf_close(struct elf *elf) hash_del(&sym->hash); free(sym); } - list_for_each_entry_safe(rela, tmprela, &sec->rela_list, list) { - list_del(&rela->list); - hash_del(&rela->hash); - free(rela); + list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { + list_del(&reloc->list); + hash_del(&reloc->hash); + free(reloc); } list_del(&sec->list); free(sec); diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 7324e772583e..6cc80a075166 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -32,8 +32,8 @@ struct section { GElf_Shdr sh; struct rb_root symbol_tree; struct list_head symbol_list; - struct list_head rela_list; - struct section *base, *rela; + struct list_head reloc_list; + struct section *base, *reloc; struct symbol *sym; Elf_Data *data; char *name; @@ -58,10 +58,13 @@ struct symbol { bool uaccess_safe; }; -struct rela { +struct reloc { struct list_head list; struct hlist_node hash; - GElf_Rela rela; + union { + GElf_Rela rela; + GElf_Rel rel; + }; struct section *sec; struct symbol *sym; unsigned long offset; @@ -84,7 +87,7 @@ struct elf { DECLARE_HASHTABLE(symbol_name_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_name_hash, ELF_HASH_BITS); - DECLARE_HASHTABLE(rela_hash, ELF_HASH_BITS); + DECLARE_HASHTABLE(reloc_hash, ELF_HASH_BITS); }; #define OFFSET_STRIDE_BITS 4 @@ -111,19 +114,19 @@ static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) return ol; } -static inline u32 rela_hash(struct rela *rela) +static inline u32 reloc_hash(struct reloc *reloc) { - return sec_offset_hash(rela->sec, rela->offset); + return sec_offset_hash(reloc->sec, reloc->offset); } struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr); -struct section *elf_create_rela_section(struct elf *elf, struct section *base); -void elf_add_rela(struct elf *elf, struct rela *rela); +struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype); +void elf_add_reloc(struct elf *elf, struct reloc *reloc); int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); -int elf_write_rela(struct elf *elf, struct rela *rela); +int elf_write_reloc(struct elf *elf, struct reloc *reloc); int elf_write(struct elf *elf); void elf_close(struct elf *elf); @@ -132,11 +135,11 @@ struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); -int elf_rebuild_rela_section(struct elf *elf, struct section *sec); +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 4c37f80eb987..968f55e6dd94 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -80,56 +80,56 @@ int create_orc(struct objtool_file *file) return 0; } -static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relasec, +static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relocsec, unsigned int idx, struct section *insn_sec, unsigned long insn_off, struct orc_entry *o) { struct orc_entry *orc; - struct rela *rela; + struct reloc *reloc; /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); - /* populate rela for ip */ - rela = malloc(sizeof(*rela)); - if (!rela) { + /* populate reloc for ip */ + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); + memset(reloc, 0, sizeof(*reloc)); if (insn_sec->sym) { - rela->sym = insn_sec->sym; - rela->addend = insn_off; + reloc->sym = insn_sec->sym; + reloc->addend = insn_off; } else { /* * The Clang assembler doesn't produce section symbols, so we * have to reference the function symbol instead: */ - rela->sym = find_symbol_containing(insn_sec, insn_off); - if (!rela->sym) { + reloc->sym = find_symbol_containing(insn_sec, insn_off); + if (!reloc->sym) { /* * Hack alert. This happens when we need to reference * the NOP pad insn immediately after the function. */ - rela->sym = find_symbol_containing(insn_sec, + reloc->sym = find_symbol_containing(insn_sec, insn_off - 1); } - if (!rela->sym) { + if (!reloc->sym) { WARN("missing symbol for insn at offset 0x%lx\n", insn_off); return -1; } - rela->addend = insn_off - rela->sym->offset; + reloc->addend = insn_off - reloc->sym->offset; } - rela->type = R_X86_64_PC32; - rela->offset = idx * sizeof(int); - rela->sec = ip_relasec; + reloc->type = R_X86_64_PC32; + reloc->offset = idx * sizeof(int); + reloc->sec = ip_relocsec; - elf_add_rela(elf, rela); + elf_add_reloc(elf, reloc); return 0; } @@ -137,7 +137,7 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti int create_orc_sections(struct objtool_file *file) { struct instruction *insn, *prev_insn; - struct section *sec, *u_sec, *ip_relasec; + struct section *sec, *u_sec, *ip_relocsec; unsigned int idx; struct orc_entry empty = { @@ -181,8 +181,8 @@ int create_orc_sections(struct objtool_file *file) if (!sec) return -1; - ip_relasec = elf_create_rela_section(file->elf, sec); - if (!ip_relasec) + ip_relocsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); + if (!ip_relocsec) return -1; /* create .orc_unwind section */ @@ -200,7 +200,7 @@ int create_orc_sections(struct objtool_file *file) if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc, sizeof(struct orc_entry))) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, insn->sec, insn->offset, &insn->orc)) return -1; @@ -212,7 +212,7 @@ int create_orc_sections(struct objtool_file *file) /* section terminator */ if (prev_insn) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, prev_insn->sec, prev_insn->offset + prev_insn->len, &empty)) @@ -222,7 +222,7 @@ int create_orc_sections(struct objtool_file *file) } } - if (elf_rebuild_rela_section(file->elf, ip_relasec)) + if (elf_rebuild_reloc_section(file->elf, ip_relocsec)) return -1; return 0; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index e74e0189de22..e893f1e48e44 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -72,7 +72,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) { - struct rela *orig_rela, *new_rela; + struct reloc *orig_reloc, *new_reloc; unsigned long offset; offset = idx * entry->size; @@ -118,30 +118,30 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, } } - orig_rela = find_rela_by_dest(elf, sec, offset + entry->orig); - if (!orig_rela) { - WARN_FUNC("can't find orig rela", sec, offset + entry->orig); + orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); + if (!orig_reloc) { + WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_rela->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section rela symbol %s", - sec, offset + entry->orig, orig_rela->sym->name); + if (orig_reloc->sym->type != STT_SECTION) { + WARN_FUNC("don't know how to handle non-section reloc symbol %s", + sec, offset + entry->orig, orig_reloc->sym->name); return -1; } - alt->orig_sec = orig_rela->sym->sec; - alt->orig_off = orig_rela->addend; + alt->orig_sec = orig_reloc->sym->sec; + alt->orig_off = orig_reloc->addend; if (!entry->group || alt->new_len) { - new_rela = find_rela_by_dest(elf, sec, offset + entry->new); - if (!new_rela) { - WARN_FUNC("can't find new rela", + new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); + if (!new_reloc) { + WARN_FUNC("can't find new reloc", sec, offset + entry->new); return -1; } - alt->new_sec = new_rela->sym->sec; - alt->new_off = (unsigned int)new_rela->addend; + alt->new_sec = new_reloc->sym->sec; + alt->new_off = (unsigned int)new_reloc->addend; /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 35b61bfc1b1a..b190f2eb2611 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -427,8 +427,8 @@ 336 common recv sys_recv compat_sys_recv 337 common recvfrom sys_recvfrom compat_sys_recvfrom 338 common shutdown sys_shutdown -339 common setsockopt sys_setsockopt compat_sys_setsockopt -340 common getsockopt sys_getsockopt compat_sys_getsockopt +339 common setsockopt sys_setsockopt sys_setsockopt +340 common getsockopt sys_getsockopt sys_getsockopt 341 common sendmsg sys_sendmsg compat_sys_sendmsg 342 common recvmsg sys_recvmsg compat_sys_recvmsg 343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index b38d48464368..56ae24b6e4be 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -372,8 +372,8 @@ 362 common connect sys_connect compat_sys_connect 363 common listen sys_listen sys_listen 364 common accept4 sys_accept4 compat_sys_accept4 -365 common getsockopt sys_getsockopt compat_sys_getsockopt -366 common setsockopt sys_setsockopt compat_sys_setsockopt +365 common getsockopt sys_getsockopt sys_getsockopt +366 common setsockopt sys_setsockopt sys_setsockopt 367 common getsockname sys_getsockname compat_sys_getsockname 368 common getpeername sys_getpeername compat_sys_getpeername 369 common sendto sys_sendto compat_sys_sendto diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 78847b32e137..e008d638e641 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -396,8 +396,8 @@ 538 x32 sendmmsg compat_sys_sendmmsg 539 x32 process_vm_readv compat_sys_process_vm_readv 540 x32 process_vm_writev compat_sys_process_vm_writev -541 x32 setsockopt compat_sys_setsockopt -542 x32 getsockopt compat_sys_getsockopt +541 x32 setsockopt sys_setsockopt +542 x32 getsockopt sys_getsockopt 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit 545 x32 execveat compat_sys_execveat diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 6e04304560ca..c3b56db8b921 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -285,7 +285,7 @@ struct cpufreq_available_governors *cpufreq_get_available_governors(unsigned } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -362,7 +362,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -418,7 +418,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -493,7 +493,7 @@ static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -726,7 +726,7 @@ struct cpufreq_stats *cpufreq_get_stats(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1 index 80a1311fa747..20b6345c53ad 100644 --- a/tools/power/cpupower/man/cpupower-idle-info.1 +++ b/tools/power/cpupower/man/cpupower-idle-info.1 @@ -75,7 +75,7 @@ By default only values of core zero are displayed. How to display settings of other cores is described in the cpupower(1) manpage in the \-\-cpu option section. .SH REFERENCES -http://www.acpi.info/spec.htm +https://uefi.org/specifications .SH "FILES" .nf \fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1 index 70a56476f4b0..8ee737eefa5c 100644 --- a/tools/power/cpupower/man/cpupower-monitor.1 +++ b/tools/power/cpupower/man/cpupower-monitor.1 @@ -170,7 +170,7 @@ displayed. .SH REFERENCES "BIOS and Kernel Developer’s Guide (BKDG) for AMD Family 14h Processors" -http://support.amd.com/us/Processor_TechDocs/43170.pdf +https://support.amd.com/us/Processor_TechDocs/43170.pdf "Intel® Turbo Boost Technology in Intel® Coreâ„¢ Microarchitecture (Nehalem) Based Processors" @@ -178,7 +178,7 @@ http://download.intel.com/design/processor/applnots/320354.pdf "Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals +https://www.intel.com/products/processor/manuals .SH FILES .ta diff --git a/tools/power/cpupower/utils/helpers/bitmask.c b/tools/power/cpupower/utils/helpers/bitmask.c index 6c7932f5bd66..649d87cb8b0f 100644 --- a/tools/power/cpupower/utils/helpers/bitmask.c +++ b/tools/power/cpupower/utils/helpers/bitmask.c @@ -26,11 +26,11 @@ struct bitmask *bitmask_alloc(unsigned int n) struct bitmask *bmp; bmp = malloc(sizeof(*bmp)); - if (bmp == 0) + if (!bmp) return 0; bmp->size = n; bmp->maskp = calloc(longsperbits(n), sizeof(unsigned long)); - if (bmp->maskp == 0) { + if (!bmp->maskp) { free(bmp); return 0; } @@ -40,7 +40,7 @@ struct bitmask *bitmask_alloc(unsigned int n) /* Free `struct bitmask` */ void bitmask_free(struct bitmask *bmp) { - if (bmp == 0) + if (!bmp) return; free(bmp->maskp); bmp->maskp = (unsigned long *)0xdeadcdef; /* double free tripwire */ diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index afe6beb40ad9..89d0a7dab4bc 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -6,7 +6,7 @@ |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.6 + Version: 5.7 Author: Todd Brandt <todd.e.brandt@intel.com> Home Page: https://01.org/pm-graph diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 602e64b68ba7..46ff97e909c6 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -81,7 +81,7 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.6' + version = '5.7' ansi = False rs = 0 display = '' @@ -198,7 +198,7 @@ class SystemValues: 'suspend_console': {}, 'acpi_pm_prepare': {}, 'syscore_suspend': {}, - 'arch_thaw_secondary_cpus_end': {}, + 'arch_enable_nonboot_cpus_end': {}, 'syscore_resume': {}, 'acpi_pm_finish': {}, 'resume_console': {}, @@ -924,10 +924,7 @@ class SystemValues: tp = TestProps() tf = self.openlog(self.ftracefile, 'r') for line in tf: - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) + if tp.stampInfo(line, self): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -1244,8 +1241,8 @@ class DevProps: if self.xtraclass: return ' '+self.xtraclass if self.isasync: - return ' async_device' - return ' sync_device' + return ' (async)' + return ' (sync)' # Class: DeviceNode # Description: @@ -1301,6 +1298,7 @@ class Data: 'FAIL' : r'(?i).*\bFAILED\b.*', 'INVALID' : r'(?i).*\bINVALID\b.*', 'CRASH' : r'(?i).*\bCRASHED\b.*', + 'TIMEOUT' : r'(?i).*\bTIMEOUT\b.*', 'IRQ' : r'.*\bgenirq: .*', 'TASKFAIL': r'.*Freezing of tasks *.*', 'ACPI' : r'.*\bACPI *(?P<b>[A-Za-z]*) *Error[: ].*', @@ -1358,11 +1356,11 @@ class Data: if self.dmesg[p]['order'] == order: return p return '' - def lastPhase(self): + def lastPhase(self, depth=1): plist = self.sortedPhases() - if len(plist) < 1: + if len(plist) < depth: return '' - return plist[-1] + return plist[-1*depth] def turbostatInfo(self): tp = TestProps() out = {'syslpi':'N/A','pkgpc10':'N/A'} @@ -1382,9 +1380,12 @@ class Data: if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf = sysvals.openlog(sysvals.dmesgfile, 'r') i = 0 + tp = TestProps() list = [] for line in lf: i += 1 + if tp.stampInfo(line, sysvals): + continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if not m: continue @@ -1400,15 +1401,15 @@ class Data: list.append((msg, err, dir, t, i, i)) self.kerror = True break - msglist = [] + tp.msglist = [] for msg, type, dir, t, idx1, idx2 in list: - msglist.append(msg) + tp.msglist.append(msg) self.errorinfo[dir].append((type, t, idx1, idx2)) if self.kerror: sysvals.dmesglog = True if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf.close() - return msglist + return tp def setStart(self, time, msg=''): self.start = time if msg: @@ -1623,6 +1624,8 @@ class Data: if('src' in d): for e in d['src']: e.time = self.trimTimeVal(e.time, t0, dT, left) + e.end = self.trimTimeVal(e.end, t0, dT, left) + e.length = e.end - e.time for dir in ['suspend', 'resume']: list = [] for e in self.errorinfo[dir]: @@ -1640,7 +1643,12 @@ class Data: if tL > 0: left = True if tR > tZero else False self.trimTime(tS, tL, left) - self.tLow.append('%.0f'%(tL*1000)) + if 'trying' in self.dmesg[lp] and self.dmesg[lp]['trying'] >= 0.001: + tTry = round(self.dmesg[lp]['trying'] * 1000) + text = '%.0f (-%.0f waking)' % (tL * 1000, tTry) + else: + text = '%.0f' % (tL * 1000) + self.tLow.append(text) lp = phase def getMemTime(self): if not self.hwstart or not self.hwend: @@ -1776,7 +1784,7 @@ class Data: length = -1.0 if(start >= 0 and end >= 0): length = end - start - if pid == -2: + if pid == -2 or name not in sysvals.tracefuncs.keys(): i = 2 origname = name while(name in list): @@ -1789,6 +1797,15 @@ class Data: if color: list[name]['color'] = color return name + def findDevice(self, phase, name): + list = self.dmesg[phase]['list'] + mydev = '' + for devname in sorted(list): + if name == devname or re.match('^%s\[(?P<num>[0-9]*)\]$' % name, devname): + mydev = devname + if mydev: + return list[mydev] + return False def deviceChildren(self, devname, phase): devlist = [] list = self.dmesg[phase]['list'] @@ -2779,6 +2796,7 @@ class TestProps: testerrfmt = '^# enter_sleep_error (?P<e>.*)' sysinfofmt = '^# sysinfo .*' cmdlinefmt = '^# command \| (?P<cmd>.*)' + kparamsfmt = '^# kparams \| (?P<kp>.*)' devpropfmt = '# Device Properties: .*' pinfofmt = '# platform-(?P<val>[a-z,A-Z,0-9]*): (?P<info>.*)' tracertypefmt = '# tracer: (?P<t>.*)' @@ -2790,8 +2808,9 @@ class TestProps: '[ +!#\*@$]*(?P<dur>[0-9\.]*) .*\| (?P<msg>.*)' ftrace_line_fmt_nop = \ ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\ - '(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\ + '(?P<flags>\S*) *(?P<time>[0-9\.]*): *'+\ '(?P<msg>.*)' + machinesuspend = 'machine_suspend\[.*' def __init__(self): self.stamp = '' self.sysinfo = '' @@ -2812,16 +2831,13 @@ class TestProps: self.ftrace_line_fmt = self.ftrace_line_fmt_nop else: doError('Invalid tracer format: [%s]' % tracer) - def stampInfo(self, line): + def stampInfo(self, line, sv): if re.match(self.stampfmt, line): self.stamp = line return True elif re.match(self.sysinfofmt, line): self.sysinfo = line return True - elif re.match(self.cmdlinefmt, line): - self.cmdline = line - return True elif re.match(self.tstatfmt, line): self.turbostat.append(line) return True @@ -2834,6 +2850,20 @@ class TestProps: elif re.match(self.firmwarefmt, line): self.fwdata.append(line) return True + elif(re.match(self.devpropfmt, line)): + self.parseDevprops(line, sv) + return True + elif(re.match(self.pinfofmt, line)): + self.parsePlatformInfo(line, sv) + return True + m = re.match(self.cmdlinefmt, line) + if m: + self.cmdline = m.group('cmd') + return True + m = re.match(self.tracertypefmt, line) + if(m): + self.setTracerType(m.group('t')) + return True return False def parseStamp(self, data, sv): # global test data @@ -2858,9 +2888,13 @@ class TestProps: data.stamp[key] = val sv.hostname = data.stamp['host'] sv.suspendmode = data.stamp['mode'] + if sv.suspendmode == 'freeze': + self.machinesuspend = 'timekeeping_freeze\[.*' + else: + self.machinesuspend = 'machine_suspend\[.*' if sv.suspendmode == 'command' and sv.ftracefile != '': modes = ['on', 'freeze', 'standby', 'mem', 'disk'] - fp = sysvals.openlog(sv.ftracefile, 'r') + fp = sv.openlog(sv.ftracefile, 'r') for line in fp: m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line) if m and m.group('mode') in ['1', '2', '3', '4']: @@ -2868,9 +2902,7 @@ class TestProps: data.stamp['mode'] = sv.suspendmode break fp.close() - m = re.match(self.cmdlinefmt, self.cmdline) - if m: - sv.cmdline = m.group('cmd') + sv.cmdline = self.cmdline if not sv.stamp: sv.stamp = data.stamp # firmware data @@ -3052,20 +3084,7 @@ def appendIncompleteTraceLog(testruns): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -3166,33 +3185,19 @@ def parseTraceLog(live=False): if sysvals.usekprobes: tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend', 'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', - 'CPU_OFF', 'timekeeping_freeze', 'acpi_suspend'] + 'CPU_OFF', 'acpi_suspend'] # extract the callgraph and traceevent data + s2idle_enter = hwsus = False tp = TestProps() - testruns = [] - testdata = [] - testrun = 0 - data, limbo = 0, True + testruns, testdata = [], [] + testrun, data, limbo = 0, 0, True tf = sysvals.openlog(sysvals.ftracefile, 'r') phase = 'suspend_prepare' for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # tracer type line: determine the trace data type - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # ignore all other commented lines if line[0] == '#': @@ -3303,16 +3308,29 @@ def parseTraceLog(live=False): phase = data.setPhase('suspend_noirq', t.time, isbegin) continue # suspend_machine/resume_machine - elif(re.match('machine_suspend\[.*', t.name)): + elif(re.match(tp.machinesuspend, t.name)): + lp = data.lastPhase() if(isbegin): - lp = data.lastPhase() + hwsus = True if lp.startswith('resume_machine'): - data.dmesg[lp]['end'] = t.time + # trim out s2idle loops, track time trying to freeze + llp = data.lastPhase(2) + if llp.startswith('suspend_machine'): + if 'trying' not in data.dmesg[llp]: + data.dmesg[llp]['trying'] = 0 + data.dmesg[llp]['trying'] += \ + t.time - data.dmesg[lp]['start'] + data.currphase = '' + del data.dmesg[lp] + continue phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True) data.setPhase(phase, t.time, False) if data.tSuspended == 0: data.tSuspended = t.time else: + if lp.startswith('resume_machine'): + data.dmesg[lp]['end'] = t.time + continue phase = data.setPhase('resume_machine', t.time, True) if(sysvals.suspendmode in ['mem', 'disk']): susp = phase.replace('resume', 'suspend') @@ -3343,6 +3361,19 @@ def parseTraceLog(live=False): # global events (outside device calls) are graphed if(name not in testrun.ttemp): testrun.ttemp[name] = [] + # special handling for s2idle_enter + if name == 'machine_suspend': + if hwsus: + s2idle_enter = hwsus = False + elif s2idle_enter and not isbegin: + if(len(testrun.ttemp[name]) > 0): + testrun.ttemp[name][-1]['end'] = t.time + testrun.ttemp[name][-1]['loop'] += 1 + elif not s2idle_enter and isbegin: + s2idle_enter = True + testrun.ttemp[name].append({'begin': t.time, + 'end': t.time, 'pid': pid, 'loop': 0}) + continue if(isbegin): # create a new list entry testrun.ttemp[name].append(\ @@ -3374,9 +3405,8 @@ def parseTraceLog(live=False): if(not m): continue n = m.group('d') - list = data.dmesg[phase]['list'] - if(n in list): - dev = list[n] + dev = data.findDevice(phase, n) + if dev: dev['length'] = t.time - dev['start'] dev['end'] = t.time # kprobe event processing @@ -3479,7 +3509,12 @@ def parseTraceLog(live=False): # add actual trace funcs for name in sorted(test.ttemp): for event in test.ttemp[name]: - data.newActionGlobal(name, event['begin'], event['end'], event['pid']) + if event['end'] - event['begin'] <= 0: + continue + title = name + if name == 'machine_suspend' and 'loop' in event: + title = 's2idle_enter_%dx' % event['loop'] + data.newActionGlobal(title, event['begin'], event['end'], event['pid']) # add the kprobe based virtual tracefuncs as actual devices for key in sorted(tp.ktemp): name, pid = key @@ -3548,8 +3583,9 @@ def parseTraceLog(live=False): for p in sorted(phasedef, key=lambda k:phasedef[k]['order']): if p not in data.dmesg: if not terr: - pprint('TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)) - terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp) + ph = p if 'machine' in p else lp + terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, ph) + pprint('TEST%s FAILED: %s' % (tn, terr)) error.append(terr) if data.tSuspended == 0: data.tSuspended = data.dmesg[lp]['end'] @@ -3611,7 +3647,7 @@ def loadKernelLog(): idx = line.find('[') if idx > 1: line = line[idx:] - if tp.stampInfo(line): + if tp.stampInfo(line, sysvals): continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if(not m): @@ -3959,18 +3995,20 @@ def addCallgraphs(sv, hf, data): if sv.cgphase and p != sv.cgphase: continue list = data.dmesg[p]['list'] - for devname in data.sortedDevices(p): - if len(sv.cgfilter) > 0 and devname not in sv.cgfilter: + for d in data.sortedDevices(p): + if len(sv.cgfilter) > 0 and d not in sv.cgfilter: continue - dev = list[devname] + dev = list[d] color = 'white' if 'color' in data.dmesg[p]: color = data.dmesg[p]['color'] if 'color' in dev: color = dev['color'] - name = devname - if(devname in sv.devprops): - name = sv.devprops[devname].altName(devname) + name = d if '[' not in d else d.split('[')[0] + if(d in sv.devprops): + name = sv.devprops[d].altName(d) + if 'drv' in dev and dev['drv']: + name += ' {%s}' % dev['drv'] if sv.suspendmode in suspendmodename: name += ' '+p if('ftrace' in dev): @@ -4517,12 +4555,9 @@ def createHTML(testruns, testfail): # draw the devices for this phase phaselist = data.dmesg[b]['list'] for d in sorted(data.tdevlist[b]): - name = d - drv = '' - dev = phaselist[d] - xtraclass = '' - xtrainfo = '' - xtrastyle = '' + dname = d if '[' not in d else d.split('[')[0] + name, dev = dname, phaselist[d] + drv = xtraclass = xtrainfo = xtrastyle = '' if 'htmlclass' in dev: xtraclass = dev['htmlclass'] if 'color' in dev: @@ -4553,7 +4588,7 @@ def createHTML(testruns, testfail): title += b devtl.html += devtl.html_device.format(dev['id'], \ title, left, top, '%.3f'%rowheight, width, \ - d+drv, xtraclass, xtrastyle) + dname+drv, xtraclass, xtrastyle) if('cpuexec' in dev): for t in sorted(dev['cpuexec']): start, end = t @@ -4571,6 +4606,8 @@ def createHTML(testruns, testfail): continue # draw any trace events for this device for e in dev['src']: + if e.length == 0: + continue height = '%.3f' % devtl.rowH top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH)) left = '%f' % (((e.time-m0)*100)/mTotal) @@ -5876,7 +5913,7 @@ def getArgFloat(name, args, min, max, main=True): def processData(live=False, quiet=False): if not quiet: - pprint('PROCESSING DATA') + pprint('PROCESSING: %s' % sysvals.htmlfile) sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \ (sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes)) error = '' @@ -5928,7 +5965,7 @@ def processData(live=False, quiet=False): sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) createHTML(testruns, error) if not quiet: - pprint('DONE') + pprint('DONE: %s' % sysvals.htmlfile) data = testruns[0] stamp = data.stamp stamp['suspend'], stamp['resume'] = data.getTimeValues() @@ -5984,25 +6021,27 @@ def runTest(n=0, quiet=False): return 0 def find_in_html(html, start, end, firstonly=True): - n, cnt, out = 0, len(html), [] - while n < cnt: - e = cnt if (n + 10000 > cnt or n == 0) else n + 10000 - m = re.search(start, html[n:e]) - if not m: - break - i = m.end() - m = re.search(end, html[n+i:e]) + cnt, out, list = len(html), [], [] + if firstonly: + m = re.search(start, html) + if m: + list.append(m) + else: + list = re.finditer(start, html) + for match in list: + s = match.end() + e = cnt if (len(out) < 1 or s + 10000 > cnt) else s + 10000 + m = re.search(end, html[s:e]) if not m: break - j = m.start() - str = html[n+i:n+i+j] + e = s + m.start() + str = html[s:e] if end == 'ms': num = re.search(r'[-+]?\d*\.\d+|\d+', str) str = num.group() if num else 'NaN' if firstonly: return str out.append(str) - n += i+j if firstonly: return '' return out @@ -6034,7 +6073,7 @@ def data_from_html(file, outpath, issues, fulldetail=False): else: result = 'pass' # extract error info - ilist = [] + tp, ilist = False, [] extra = dict() log = find_in_html(html, '<div id="dmesglog" style="display:none;">', '</div>').strip() @@ -6042,8 +6081,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): d = Data(0) d.end = 999999999 d.dmesgtext = log.split('\n') - msglist = d.extractErrorInfo() - for msg in msglist: + tp = d.extractErrorInfo() + for msg in tp.msglist: sysvals.errorSummary(issues, msg) if stmp[2] == 'freeze': extra = d.turbostatInfo() @@ -6059,8 +6098,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): if wifi: extra['wifi'] = wifi low = find_in_html(html, 'freeze time: <b>', ' ms</b>') - if low and '|' in low: - issue = 'FREEZEx%d' % len(low.split('|')) + if low and 'waking' in low: + issue = 'FREEZEWAKE' match = [i for i in issues if i['match'] == issue] if len(match) > 0: match[0]['count'] += 1 @@ -6126,6 +6165,11 @@ def data_from_html(file, outpath, issues, fulldetail=False): data[key] = extra[key] if fulldetail: data['funclist'] = find_in_html(html, '<div title="', '" class="traceevent"', False) + if tp: + for arg in ['-multi ', '-info ']: + if arg in tp.cmdline: + data['target'] = tp.cmdline[tp.cmdline.find(arg):].split()[1] + break return data def genHtml(subdir, force=False): @@ -6155,8 +6199,7 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Generating a summary of folder:\n %s' % inpath) if genhtml: genHtml(subdir) - issues = [] - testruns = [] + target, issues, testruns = '', [], [] desc = {'host':[],'mode':[],'kernel':[]} for dirname, dirnames, filenames in os.walk(subdir): for filename in filenames: @@ -6165,6 +6208,8 @@ def runSummary(subdir, local=True, genhtml=False): data = data_from_html(os.path.join(dirname, filename), outpath, issues) if(not data): continue + if 'target' in data: + target = data['target'] testruns.append(data) for key in desc: if data[key] not in desc[key]: @@ -6172,6 +6217,8 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Summary files:') if len(desc['host']) == len(desc['mode']) == len(desc['kernel']) == 1: title = '%s %s %s' % (desc['host'][0], desc['kernel'][0], desc['mode'][0]) + if target: + title += ' %s' % target else: title = inpath createHTMLSummarySimple(testruns, os.path.join(outpath, 'summary.html'), title) diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 9f68f51ca652..9f4b190f1d74 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.4"; +static const char *version_str = "v1.5"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -44,6 +44,9 @@ static int force_online_offline; static int auto_mode; static int fact_enable_fail; +static int mbox_delay; +static int mbox_retries = 3; + /* clos related */ static int current_clos = -1; static int clos_epp = -1; @@ -198,7 +201,7 @@ int out_format_is_json(void) static int get_stored_topology_info(int cpu, int *core_id, int *pkg_id, int *die_id) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; struct cpu_topology cpu_top; FILE *fp; int ret; @@ -230,7 +233,7 @@ err_ret: static void store_cpu_topology(void) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; FILE *fp; int i; @@ -247,6 +250,8 @@ static void store_cpu_topology(void) return; } + fprintf(stderr, "Caching topology information\n"); + for (i = 0; i < topo_max_cpus; ++i) { struct cpu_topology cpu_top; @@ -734,7 +739,7 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, unsigned int req_data, unsigned int *resp) { const char *pathname = "/dev/isst_interface"; - int fd; + int fd, retry; struct isst_if_mbox_cmds mbox_cmds = { 0 }; debug_printf( @@ -786,29 +791,42 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, mbox_cmds.mbox_cmd[0].parameter = parameter; mbox_cmds.mbox_cmd[0].req_data = req_data; + if (mbox_delay) + usleep(mbox_delay * 1000); + fd = open(pathname, O_RDWR); if (fd < 0) err(-1, "%s open failed", pathname); - if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { - if (errno == ENOTTY) { - perror("ISST_IF_MBOX_COMMAND\n"); - fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); - exit(0); + retry = mbox_retries; + + do { + if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { + if (errno == ENOTTY) { + perror("ISST_IF_MBOX_COMMAND\n"); + fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); + exit(0); + } + debug_printf( + "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", + cpu, command, sub_command, parameter, req_data, errno); + --retry; + } else { + *resp = mbox_cmds.mbox_cmd[0].resp_data; + debug_printf( + "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", + cpu, command, sub_command, parameter, req_data, *resp); + break; } - debug_printf( - "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", - cpu, command, sub_command, parameter, req_data, errno); - return -1; - } else { - *resp = mbox_cmds.mbox_cmd[0].resp_data; - debug_printf( - "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", - cpu, command, sub_command, parameter, req_data, *resp); - } + } while (retry); close(fd); + if (!retry) { + debug_printf("Failed mbox command even after retries\n"); + return -1; + + } return 0; } @@ -1245,7 +1263,11 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, fprintf(stderr, "Option is set to online/offline\n"); ctdp_level.core_cpumask_size = alloc_cpu_set(&ctdp_level.core_cpumask); - isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + ret = isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + if (ret) { + isst_display_error_info_message(1, "Can't get coremask, online/offline option is ignored", 0, 0); + return; + } if (ctdp_level.cpu_count) { int i, max_cpus = get_topo_max_cpus(); for (i = 0; i < max_cpus; ++i) { @@ -2593,6 +2615,8 @@ static void usage(void) printf("\t[-i|--info] : Print platform information\n"); printf("\t[-o|--out] : Output file\n"); printf("\t\t\tDefault : stderr\n"); + printf("\t[-p|--pause] : Delay between two mail box commands in milliseconds\n"); + printf("\t[-r|--retry] : Retry count for mail box commands on failure, default 3\n"); printf("\t[-v|--version] : Print version\n"); printf("\nResult format\n"); @@ -2624,6 +2648,7 @@ static void print_version(void) static void cmdline(int argc, char **argv) { const char *pathname = "/dev/isst_interface"; + char *ptr; FILE *fp; int opt; int option_index = 0; @@ -2635,7 +2660,9 @@ static void cmdline(int argc, char **argv) { "format", required_argument, 0, 'f' }, { "help", no_argument, 0, 'h' }, { "info", no_argument, 0, 'i' }, + { "pause", required_argument, 0, 'p' }, { "out", required_argument, 0, 'o' }, + { "retry", required_argument, 0, 'r' }, { "version", no_argument, 0, 'v' }, { 0, 0, 0, 0 } }; @@ -2688,6 +2715,20 @@ static void cmdline(int argc, char **argv) fclose(outf); outf = fopen_or_exit(optarg, "w"); break; + case 'p': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid pause interval, ignore\n"); + else + mbox_delay = ret; + break; + case 'r': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid retry count, ignore\n"); + else + mbox_retries = ret; + break; case 'v': print_version(); break; diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index f9b769f3437d..425ef40067e7 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -240,12 +240,6 @@ def main(argv, linux=None): if cli_args.subcommand == 'run': if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -263,12 +257,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -285,12 +273,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -309,12 +291,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 63dbda2d029f..e20e2056cb38 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -34,7 +34,7 @@ class LinuxSourceTreeOperations(object): def make_mrproper(self): try: - subprocess.check_output(['make', 'mrproper']) + subprocess.check_output(['make', 'mrproper'], stderr=subprocess.STDOUT) except OSError as e: raise ConfigError('Could not call make command: ' + e) except subprocess.CalledProcessError as e: @@ -47,7 +47,7 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.PIPE) + subprocess.check_output(command, stderr=subprocess.STDOUT) except OSError as e: raise ConfigError('Could not call make command: ' + e) except subprocess.CalledProcessError as e: @@ -77,7 +77,7 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command) + subprocess.check_output(command, stderr=subprocess.STDOUT) except OSError as e: raise BuildError('Could not call execute make: ' + e) except subprocess.CalledProcessError as e: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index f9eeaea94cad..287c74d821c3 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -251,21 +251,21 @@ class KUnitMainTest(unittest.TestCase): pass def test_config_passes_args_pass(self): - kunit.main(['config'], self.linux_source_mock) + kunit.main(['config', '--build_dir=.kunit'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 0 def test_build_passes_args_pass(self): kunit.main(['build'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 0 - self.linux_source_mock.build_um_kernel.assert_called_once_with(False, 8, '', None) + self.linux_source_mock.build_um_kernel.assert_called_once_with(False, 8, '.kunit', None) assert self.linux_source_mock.run_kernel.call_count == 0 def test_exec_passes_args_pass(self): kunit.main(['exec'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 0 assert self.linux_source_mock.run_kernel.call_count == 1 - self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=300) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='.kunit', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_passes_args_pass(self): @@ -273,7 +273,7 @@ class KUnitMainTest(unittest.TestCase): assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( - build_dir='', timeout=300) + build_dir='.kunit', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_exec_passes_args_fail(self): @@ -313,7 +313,7 @@ class KUnitMainTest(unittest.TestCase): def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) - self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=timeout) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='.kunit', timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_timeout(self): @@ -321,12 +321,12 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( - build_dir='', timeout=timeout) + build_dir='.kunit', timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_builddir(self): build_dir = '.kunit' - kunit.main(['run', '--build_dir', build_dir], self.linux_source_mock) + kunit.main(['run', '--build_dir=.kunit'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( build_dir=build_dir, timeout=300) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1195bd85af38..e03bc15ce731 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -6,6 +6,7 @@ TARGETS += breakpoints TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 +TARGETS += core TARGETS += cpufreq TARGETS += cpu-hotplug TARGETS += drivers/dma-buf @@ -15,6 +16,7 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += firmware +TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio @@ -54,6 +56,7 @@ TARGETS += splice TARGETS += static_keys TARGETS += sync TARGETS += sysctl +TARGETS += tc-testing TARGETS += timens ifneq (1, $(quicktest)) TARGETS += timers diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 22aaec74ea0a..e7a8cf83ba48 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -111,6 +111,7 @@ SCRATCH_DIR := $(OUTPUT)/tools BUILD_DIR := $(SCRATCH_DIR)/build INCLUDE_DIR := $(SCRATCH_DIR)/include BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a +RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids # Define simple and short `make test_progs`, `make test_sysctl`, etc targets # to build individual tests. @@ -134,12 +135,12 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) $(call msg,CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< -VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux) \ +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ ../../../../vmlinux \ /sys/kernel/btf/vmlinux \ /boot/vmlinux-$(shell uname -r) -VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(OUTPUT)/runqslower: $(BPFOBJ) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ @@ -177,13 +178,28 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers -$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): +$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(BUILD_DIR)/resolve_btfids $(INCLUDE_DIR): $(call msg,MKDIR,,$@) mkdir -p $@ $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR) +ifeq ($(VMLINUX_H),) $(call msg,GEN,,$@) $(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ +else + $(call msg,CP,,$@) + cp "$(VMLINUX_H)" $@ +endif + +$(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids \ + $(TOOLSDIR)/bpf/resolve_btfids/main.c \ + $(TOOLSDIR)/lib/rbtree.c \ + $(TOOLSDIR)/lib/zalloc.c \ + $(TOOLSDIR)/lib/string.c \ + $(TOOLSDIR)/lib/ctype.c \ + $(TOOLSDIR)/lib/str_error_r.c + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ + OUTPUT=$(BUILD_DIR)/resolve_btfids/ BPFOBJ=$(BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, @@ -347,9 +363,11 @@ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ + $(RESOLVE_BTFIDS) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ + $(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@ endef diff --git a/tools/testing/selftests/bpf/bpf_legacy.h b/tools/testing/selftests/bpf/bpf_legacy.h index 6f8988738bc1..719ab56cdb5d 100644 --- a/tools/testing/selftests/bpf/bpf_legacy.h +++ b/tools/testing/selftests/bpf/bpf_legacy.h @@ -2,20 +2,6 @@ #ifndef __BPF_LEGACY__ #define __BPF_LEGACY__ -/* - * legacy bpf_map_def with extra fields supported only by bpf_load(), do not - * use outside of samples/bpf - */ -struct bpf_map_def_legacy { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; - unsigned int inner_map_idx; - unsigned int numa_node; -}; - #define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ struct ____btf_map_##name { \ type_key key; \ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 0fb910df5387..033051717ba5 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -290,3 +290,26 @@ free_mem: free(fhp); return ret; } + +int cgroup_setup_and_join(const char *path) { + int cg_fd; + + if (setup_cgroup_environment()) { + fprintf(stderr, "Failed to setup cgroup environment\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(path); + if (cg_fd < 0) { + fprintf(stderr, "Failed to create test cgroup\n"); + cleanup_cgroup_environment(); + return cg_fd; + } + + if (join_cgroup(path)) { + fprintf(stderr, "Failed to join cgroup\n"); + cleanup_cgroup_environment(); + return -EINVAL; + } + return cg_fd; +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index d64bb8957090..5fe3d88e4f0d 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -9,6 +9,7 @@ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) +int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); int join_cgroup(const char *path); int setup_cgroup_environment(void); diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c index e8da7b39158d..b8d6aef99db4 100644 --- a/tools/testing/selftests/bpf/get_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c @@ -58,20 +58,10 @@ int main(int argc, char **argv) int exit_code = 1; char buf[256]; - err = setup_cgroup_environment(); - if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err, - errno)) + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno)) return 1; - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n", - cgroup_fd, errno)) - goto cleanup_cgroup_env; - - err = join_cgroup(TEST_CGROUP); - if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno)) - goto cleanup_cgroup_env; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) goto cleanup_cgroup_env; diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index e36dd1a1780d..f56655690f9b 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -7,8 +7,6 @@ #include <arpa/inet.h> -#include <sys/epoll.h> - #include <linux/err.h> #include <linux/in.h> #include <linux/in6.h> @@ -17,8 +15,13 @@ #include "network_helpers.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) -#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ - __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) +#define log_err(MSG, ...) ({ \ + int __save = errno; \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, clean_errno(), \ + ##__VA_ARGS__); \ + errno = __save; \ +}) struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -37,131 +40,169 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -int start_server_with_port(int family, int type, __u16 port) +static int settimeo(int fd, int timeout_ms) { - struct sockaddr_storage addr = {}; - socklen_t len; - int fd; + struct timeval timeout = { .tv_sec = 3 }; - if (family == AF_INET) { - struct sockaddr_in *sin = (void *)&addr; + if (timeout_ms > 0) { + timeout.tv_sec = timeout_ms / 1000; + timeout.tv_usec = (timeout_ms % 1000) * 1000; + } - sin->sin_family = AF_INET; - sin->sin_port = htons(port); - len = sizeof(*sin); - } else { - struct sockaddr_in6 *sin6 = (void *)&addr; + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeout, + sizeof(timeout))) { + log_err("Failed to set SO_RCVTIMEO"); + return -1; + } - sin6->sin6_family = AF_INET6; - sin6->sin6_port = htons(port); - len = sizeof(*sin6); + if (setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeout, + sizeof(timeout))) { + log_err("Failed to set SO_SNDTIMEO"); + return -1; } - fd = socket(family, type | SOCK_NONBLOCK, 0); + return 0; +} + +#define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; }) + +int start_server(int family, int type, const char *addr_str, __u16 port, + int timeout_ms) +{ + struct sockaddr_storage addr = {}; + socklen_t len; + int fd; + + if (make_sockaddr(family, addr_str, port, &addr, &len)) + return -1; + + fd = socket(family, type, 0); if (fd < 0) { log_err("Failed to create server socket"); return -1; } + if (settimeo(fd, timeout_ms)) + goto error_close; + if (bind(fd, (const struct sockaddr *)&addr, len) < 0) { log_err("Failed to bind socket"); - close(fd); - return -1; + goto error_close; } if (type == SOCK_STREAM) { if (listen(fd, 1) < 0) { log_err("Failed to listed on socket"); - close(fd); - return -1; + goto error_close; } } return fd; + +error_close: + save_errno_close(fd); + return -1; } -int start_server(int family, int type) +static int connect_fd_to_addr(int fd, + const struct sockaddr_storage *addr, + socklen_t addrlen) { - return start_server_with_port(family, type, 0); -} + if (connect(fd, (const struct sockaddr *)addr, addrlen)) { + log_err("Failed to connect to server"); + return -1; + } -static const struct timeval timeo_sec = { .tv_sec = 3 }; -static const size_t timeo_optlen = sizeof(timeo_sec); + return 0; +} -int connect_to_fd(int family, int type, int server_fd) +int connect_to_fd(int server_fd, int timeout_ms) { - int fd, save_errno; + struct sockaddr_storage addr; + struct sockaddr_in *addr_in; + socklen_t addrlen, optlen; + int fd, type; - fd = socket(family, type, 0); - if (fd < 0) { - log_err("Failed to create client socket"); + optlen = sizeof(type); + if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) { + log_err("getsockopt(SOL_TYPE)"); return -1; } - if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) { - save_errno = errno; - close(fd); - errno = save_errno; + addrlen = sizeof(addr); + if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) { + log_err("Failed to get server addr"); return -1; } + addr_in = (struct sockaddr_in *)&addr; + fd = socket(addr_in->sin_family, type, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (settimeo(fd, timeout_ms)) + goto error_close; + + if (connect_fd_to_addr(fd, &addr, addrlen)) + goto error_close; + return fd; + +error_close: + save_errno_close(fd); + return -1; } -int connect_fd_to_fd(int client_fd, int server_fd) +int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) { struct sockaddr_storage addr; socklen_t len = sizeof(addr); - int save_errno; - if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, - timeo_optlen)) { - log_err("Failed to set SO_RCVTIMEO"); + if (settimeo(client_fd, timeout_ms)) return -1; - } if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { log_err("Failed to get server addr"); return -1; } - if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) { - if (errno != EINPROGRESS) { - save_errno = errno; - log_err("Failed to connect to server"); - errno = save_errno; - } + if (connect_fd_to_addr(client_fd, &addr, len)) return -1; - } return 0; } -int connect_wait(int fd) +int make_sockaddr(int family, const char *addr_str, __u16 port, + struct sockaddr_storage *addr, socklen_t *len) { - struct epoll_event ev = {}, events[2]; - int timeout_ms = 1000; - int efd, nfd; - - efd = epoll_create1(EPOLL_CLOEXEC); - if (efd < 0) { - log_err("Failed to open epoll fd"); - return -1; - } + if (family == AF_INET) { + struct sockaddr_in *sin = (void *)addr; - ev.events = EPOLLRDHUP | EPOLLOUT; - ev.data.fd = fd; + sin->sin_family = AF_INET; + sin->sin_port = htons(port); + if (addr_str && + inet_pton(AF_INET, addr_str, &sin->sin_addr) != 1) { + log_err("inet_pton(AF_INET, %s)", addr_str); + return -1; + } + if (len) + *len = sizeof(*sin); + return 0; + } else if (family == AF_INET6) { + struct sockaddr_in6 *sin6 = (void *)addr; - if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) { - log_err("Failed to register fd=%d on epoll fd=%d", fd, efd); - close(efd); - return -1; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = htons(port); + if (addr_str && + inet_pton(AF_INET6, addr_str, &sin6->sin6_addr) != 1) { + log_err("inet_pton(AF_INET6, %s)", addr_str); + return -1; + } + if (len) + *len = sizeof(*sin6); + return 0; } - - nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms); - if (nfd < 0) - log_err("Failed to wait for I/O event on epoll fd=%d", efd); - - close(efd); - return nfd; + return -1; } diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 6a8009605670..c3728f6667e4 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,10 +33,11 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; -int start_server(int family, int type); -int start_server_with_port(int family, int type, __u16 port); -int connect_to_fd(int family, int type, int server_fd); -int connect_fd_to_fd(int client_fd, int server_fd); -int connect_wait(int client_fd); +int start_server(int family, int type, const char *addr, __u16 port, + int timeout_ms); +int connect_to_fd(int server_fd, int timeout_ms); +int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms); +int make_sockaddr(int family, const char *addr_str, __u16 port, + struct sockaddr_storage *addr, socklen_t *len); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/autoload.c b/tools/testing/selftests/bpf/prog_tests/autoload.c new file mode 100644 index 000000000000..3693f7d133eb --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/autoload.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include <time.h> +#include "test_autoload.skel.h" + +void test_autoload(void) +{ + int duration = 0, err; + struct test_autoload* skel; + + skel = test_autoload__open_and_load(); + /* prog3 should be broken */ + if (CHECK(skel, "skel_open_and_load", "unexpected success\n")) + goto cleanup; + + skel = test_autoload__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + goto cleanup; + + /* don't load prog3 */ + bpf_program__set_autoload(skel->progs.prog3, false); + + err = test_autoload__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + err = test_autoload__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + usleep(1); + + CHECK(!skel->bss->prog1_called, "prog1", "not called\n"); + CHECK(!skel->bss->prog2_called, "prog2", "not called\n"); + CHECK(skel->bss->prog3_called, "prog3", "called?!\n"); + +cleanup: + test_autoload__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 87c29dde1cf9..4ffefdc1130f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -5,11 +5,23 @@ #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" #include "bpf_iter_task.skel.h" +#include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" +#include "bpf_iter_tcp4.skel.h" +#include "bpf_iter_tcp6.skel.h" +#include "bpf_iter_udp4.skel.h" +#include "bpf_iter_udp6.skel.h" #include "bpf_iter_test_kern1.skel.h" #include "bpf_iter_test_kern2.skel.h" #include "bpf_iter_test_kern3.skel.h" #include "bpf_iter_test_kern4.skel.h" +#include "bpf_iter_bpf_hash_map.skel.h" +#include "bpf_iter_bpf_percpu_hash_map.skel.h" +#include "bpf_iter_bpf_array_map.skel.h" +#include "bpf_iter_bpf_percpu_array_map.skel.h" +#include "bpf_iter_bpf_sk_storage_map.skel.h" +#include "bpf_iter_test_kern5.skel.h" +#include "bpf_iter_test_kern6.skel.h" static int duration; @@ -106,6 +118,20 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_stack(void) +{ + struct bpf_iter_task_stack *skel; + + skel = bpf_iter_task_stack__open_and_load(); + if (CHECK(!skel, "bpf_iter_task_stack__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_task_stack); + + bpf_iter_task_stack__destroy(skel); +} + static void test_task_file(void) { struct bpf_iter_task_file *skel; @@ -120,6 +146,62 @@ static void test_task_file(void) bpf_iter_task_file__destroy(skel); } +static void test_tcp4(void) +{ + struct bpf_iter_tcp4 *skel; + + skel = bpf_iter_tcp4__open_and_load(); + if (CHECK(!skel, "bpf_iter_tcp4__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_tcp4); + + bpf_iter_tcp4__destroy(skel); +} + +static void test_tcp6(void) +{ + struct bpf_iter_tcp6 *skel; + + skel = bpf_iter_tcp6__open_and_load(); + if (CHECK(!skel, "bpf_iter_tcp6__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_tcp6); + + bpf_iter_tcp6__destroy(skel); +} + +static void test_udp4(void) +{ + struct bpf_iter_udp4 *skel; + + skel = bpf_iter_udp4__open_and_load(); + if (CHECK(!skel, "bpf_iter_udp4__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_udp4); + + bpf_iter_udp4__destroy(skel); +} + +static void test_udp6(void) +{ + struct bpf_iter_udp6 *skel; + + skel = bpf_iter_udp6__open_and_load(); + if (CHECK(!skel, "bpf_iter_udp6__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_udp6); + + bpf_iter_udp6__destroy(skel); +} + /* The expected string is less than 16 bytes */ static int do_read_with_fd(int iter_fd, const char *expected, bool read_one_char) @@ -380,6 +462,440 @@ out: bpf_iter_test_kern4__destroy(skel); } +static void test_bpf_hash_map(void) +{ + __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_hash_map *skel; + int err, i, len, map_fd, iter_fd; + __u64 val, expected_val = 0; + struct bpf_link *link; + struct key_t { + int a; + int b; + int c; + } key; + char buf[64]; + + skel = bpf_iter_bpf_hash_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_hash_map__open", + "skeleton open failed\n")) + return; + + skel->bss->in_test_mode = true; + + err = bpf_iter_bpf_hash_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_hash_map__load", + "skeleton load failed\n")) + goto out; + + /* iterator with hashmap2 and hashmap3 should fail */ + opts.map_fd = bpf_map__fd(skel->maps.hashmap2); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", + "attach_iter for hashmap2 unexpected succeeded\n")) + goto out; + + opts.map_fd = bpf_map__fd(skel->maps.hashmap3); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", + "attach_iter for hashmap3 unexpected succeeded\n")) + goto out; + + /* hashmap1 should be good, update map values here */ + map_fd = bpf_map__fd(skel->maps.hashmap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) { + key.a = i + 1; + key.b = i + 2; + key.c = i + 3; + val = i + 4; + expected_key_a += key.a; + expected_key_b += key.b; + expected_key_c += key.c; + expected_val += val; + + err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum_a != expected_key_a, + "key_sum_a", "got %u expected %u\n", + skel->bss->key_sum_a, expected_key_a)) + goto close_iter; + if (CHECK(skel->bss->key_sum_b != expected_key_b, + "key_sum_b", "got %u expected %u\n", + skel->bss->key_sum_b, expected_key_b)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %llu expected %llu\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_hash_map__destroy(skel); +} + +static void test_bpf_percpu_hash_map(void) +{ + __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_percpu_hash_map *skel; + int err, i, j, len, map_fd, iter_fd; + __u32 expected_val = 0; + struct bpf_link *link; + struct key_t { + int a; + int b; + int c; + } key; + char buf[64]; + void *val; + + val = malloc(8 * bpf_num_possible_cpus()); + + skel = bpf_iter_bpf_percpu_hash_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__open", + "skeleton open failed\n")) + return; + + skel->rodata->num_cpus = bpf_num_possible_cpus(); + + err = bpf_iter_bpf_percpu_hash_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__load", + "skeleton load failed\n")) + goto out; + + /* update map values here */ + map_fd = bpf_map__fd(skel->maps.hashmap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) { + key.a = i + 1; + key.b = i + 2; + key.c = i + 3; + expected_key_a += key.a; + expected_key_b += key.b; + expected_key_c += key.c; + + for (j = 0; j < bpf_num_possible_cpus(); j++) { + *(__u32 *)(val + j * 8) = i + j; + expected_val += i + j; + } + + err = bpf_map_update_elem(map_fd, &key, val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum_a != expected_key_a, + "key_sum_a", "got %u expected %u\n", + skel->bss->key_sum_a, expected_key_a)) + goto close_iter; + if (CHECK(skel->bss->key_sum_b != expected_key_b, + "key_sum_b", "got %u expected %u\n", + skel->bss->key_sum_b, expected_key_b)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_percpu_hash_map__destroy(skel); +} + +static void test_bpf_array_map(void) +{ + __u64 val, expected_val = 0, res_first_val, first_val = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + __u32 expected_key = 0, res_first_key; + struct bpf_iter_bpf_array_map *skel; + int err, i, map_fd, iter_fd; + struct bpf_link *link; + char buf[64] = {}; + int len, start; + + skel = bpf_iter_bpf_array_map__open_and_load(); + if (CHECK(!skel, "bpf_iter_bpf_array_map__open_and_load", + "skeleton open_and_load failed\n")) + return; + + map_fd = bpf_map__fd(skel->maps.arraymap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + val = i + 4; + expected_key += i; + expected_val += val; + + if (i == 0) + first_val = val; + + err = bpf_map_update_elem(map_fd, &i, &val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + start = 0; + while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0) + start += len; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + res_first_key = *(__u32 *)buf; + res_first_val = *(__u64 *)(buf + sizeof(__u32)); + if (CHECK(res_first_key != 0 || res_first_val != first_val, + "bpf_seq_write", + "seq_write failure: first key %u vs expected 0, " + " first value %llu vs expected %llu\n", + res_first_key, res_first_val, first_val)) + goto close_iter; + + if (CHECK(skel->bss->key_sum != expected_key, + "key_sum", "got %u expected %u\n", + skel->bss->key_sum, expected_key)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %llu expected %llu\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + err = bpf_map_lookup_elem(map_fd, &i, &val); + if (CHECK(err, "map_lookup", "map_lookup failed\n")) + goto out; + if (CHECK(i != val, "invalid_val", + "got value %llu expected %u\n", val, i)) + goto out; + } + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_array_map__destroy(skel); +} + +static void test_bpf_percpu_array_map(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_percpu_array_map *skel; + __u32 expected_key = 0, expected_val = 0; + int err, i, j, map_fd, iter_fd; + struct bpf_link *link; + char buf[64]; + void *val; + int len; + + val = malloc(8 * bpf_num_possible_cpus()); + + skel = bpf_iter_bpf_percpu_array_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__open", + "skeleton open failed\n")) + return; + + skel->rodata->num_cpus = bpf_num_possible_cpus(); + + err = bpf_iter_bpf_percpu_array_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__load", + "skeleton load failed\n")) + goto out; + + /* update map values here */ + map_fd = bpf_map__fd(skel->maps.arraymap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + expected_key += i; + + for (j = 0; j < bpf_num_possible_cpus(); j++) { + *(__u32 *)(val + j * 8) = i + j; + expected_val += i + j; + } + + err = bpf_map_update_elem(map_fd, &i, val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum != expected_key, + "key_sum", "got %u expected %u\n", + skel->bss->key_sum, expected_key)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_percpu_array_map__destroy(skel); +} + +static void test_bpf_sk_storage_map(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + int err, i, len, map_fd, iter_fd, num_sockets; + struct bpf_iter_bpf_sk_storage_map *skel; + int sock_fd[3] = {-1, -1, -1}; + __u32 val, expected_val = 0; + struct bpf_link *link; + char buf[64]; + + skel = bpf_iter_bpf_sk_storage_map__open_and_load(); + if (CHECK(!skel, "bpf_iter_bpf_sk_storage_map__open_and_load", + "skeleton open_and_load failed\n")) + return; + + map_fd = bpf_map__fd(skel->maps.sk_stg_map); + num_sockets = ARRAY_SIZE(sock_fd); + for (i = 0; i < num_sockets; i++) { + sock_fd[i] = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(sock_fd[i] < 0, "socket", "errno: %d\n", errno)) + goto out; + + val = i + 1; + expected_val += val; + + err = bpf_map_update_elem(map_fd, &sock_fd[i], &val, + BPF_NOEXIST); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->ipv6_sk_count != num_sockets, + "ipv6_sk_count", "got %u expected %u\n", + skel->bss->ipv6_sk_count, num_sockets)) + goto close_iter; + + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + for (i = 0; i < num_sockets; i++) { + if (sock_fd[i] >= 0) + close(sock_fd[i]); + } + bpf_iter_bpf_sk_storage_map__destroy(skel); +} + +static void test_rdonly_buf_out_of_bound(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_test_kern5 *skel; + struct bpf_link *link; + + skel = bpf_iter_test_kern5__open_and_load(); + if (CHECK(!skel, "bpf_iter_test_kern5__open_and_load", + "skeleton open_and_load failed\n")) + return; + + opts.map_fd = bpf_map__fd(skel->maps.hashmap1); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n")) + bpf_link__destroy(link); + + bpf_iter_test_kern5__destroy(skel); +} + +static void test_buf_neg_offset(void) +{ + struct bpf_iter_test_kern6 *skel; + + skel = bpf_iter_test_kern6__open_and_load(); + if (CHECK(skel, "bpf_iter_test_kern6__open_and_load", + "skeleton open_and_load unexpected success\n")) + bpf_iter_test_kern6__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -392,8 +908,18 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_stack")) + test_task_stack(); if (test__start_subtest("task_file")) test_task_file(); + if (test__start_subtest("tcp4")) + test_tcp4(); + if (test__start_subtest("tcp6")) + test_tcp6(); + if (test__start_subtest("udp4")) + test_udp4(); + if (test__start_subtest("udp6")) + test_udp6(); if (test__start_subtest("anon")) test_anon_iter(false); if (test__start_subtest("anon-read-one-char")) @@ -406,4 +932,18 @@ void test_bpf_iter(void) test_overflow(true, false); if (test__start_subtest("prog-ret-1")) test_overflow(false, true); + if (test__start_subtest("bpf_hash_map")) + test_bpf_hash_map(); + if (test__start_subtest("bpf_percpu_hash_map")) + test_bpf_percpu_hash_map(); + if (test__start_subtest("bpf_array_map")) + test_bpf_array_map(); + if (test__start_subtest("bpf_percpu_array_map")) + test_bpf_percpu_array_map(); + if (test__start_subtest("bpf_sk_storage_map")) + test_bpf_sk_storage_map(); + if (test__start_subtest("rdonly-buf-out-of-bound")) + test_rdonly_buf_out_of_bound(); + if (test__start_subtest("buf-neg-offset")) + test_buf_neg_offset(); } diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c new file mode 100644 index 000000000000..643dfa35419c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <network_helpers.h> + +#include "progs/cg_storage_multi.h" + +#include "cg_storage_multi_egress_only.skel.h" +#include "cg_storage_multi_isolated.skel.h" +#include "cg_storage_multi_shared.skel.h" + +#define PARENT_CGROUP "/cgroup_storage" +#define CHILD_CGROUP "/cgroup_storage/child" + +static int duration; + +static bool assert_storage(struct bpf_map *map, const void *key, + struct cgroup_value *expected) +{ + struct cgroup_value value; + int map_fd; + + map_fd = bpf_map__fd(map); + + if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) < 0, + "map-lookup", "errno %d", errno)) + return true; + if (CHECK(memcmp(&value, expected, sizeof(struct cgroup_value)), + "assert-storage", "storages differ")) + return true; + + return false; +} + +static bool assert_storage_noexist(struct bpf_map *map, const void *key) +{ + struct cgroup_value value; + int map_fd; + + map_fd = bpf_map__fd(map); + + if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) == 0, + "map-lookup", "succeeded, expected ENOENT")) + return true; + if (CHECK(errno != ENOENT, + "map-lookup", "errno %d, expected ENOENT", errno)) + return true; + + return false; +} + +static bool connect_send(const char *cgroup_path) +{ + bool res = true; + int server_fd = -1, client_fd = -1; + + if (join_cgroup(cgroup_path)) + goto out_clean; + + server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (server_fd < 0) + goto out_clean; + + client_fd = connect_to_fd(server_fd, 0); + if (client_fd < 0) + goto out_clean; + + if (send(client_fd, "message", strlen("message"), 0) < 0) + goto out_clean; + + res = false; + +out_clean: + close(client_fd); + close(server_fd); + return res; +} + +static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_egress_only *obj; + struct cgroup_value expected_cgroup_value; + struct bpf_cgroup_storage_key key; + struct bpf_link *parent_link = NULL, *child_link = NULL; + bool err; + + key.attach_type = BPF_CGROUP_INET_EGRESS; + + obj = cg_storage_multi_egress_only__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is only one run and in that run the storage is + * parent cgroup's storage. + * Also assert that child cgroup's storage does not exist + */ + parent_link = bpf_program__attach_cgroup(obj->progs.egress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_link), "parent-cg-attach", + "err %ld", PTR_ERR(parent_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 1, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there are two additional runs, one that run with parent + * cgroup's storage and one with child cgroup's storage. + */ + child_link = bpf_program__attach_cgroup(obj->progs.egress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_link), "child-cg-attach", + "err %ld", PTR_ERR(child_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + +close_bpf_object: + if (!IS_ERR(parent_link)) + bpf_link__destroy(parent_link); + if (!IS_ERR(child_link)) + bpf_link__destroy(child_link); + + cg_storage_multi_egress_only__destroy(obj); +} + +static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_isolated *obj; + struct cgroup_value expected_cgroup_value; + struct bpf_cgroup_storage_key key; + struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL; + struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL; + struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL; + bool err; + + obj = cg_storage_multi_isolated__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is three runs, two with parent cgroup egress and + * one with parent cgroup ingress, stored in separate parent storages. + * Also assert that child cgroup's storages does not exist + */ + parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", + "err %ld", PTR_ERR(parent_egress1_link))) + goto close_bpf_object; + parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", + "err %ld", PTR_ERR(parent_egress2_link))) + goto close_bpf_object; + parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", + "err %ld", PTR_ERR(parent_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there is six additional runs, parent cgroup egresses and + * ingress, child cgroup egresses and ingress. + * Assert that egree and ingress storages are separate. + */ + child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", + "err %ld", PTR_ERR(child_egress1_link))) + goto close_bpf_object; + child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", + "err %ld", PTR_ERR(child_egress2_link))) + goto close_bpf_object; + child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", + "err %ld", PTR_ERR(child_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 9, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 4 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + +close_bpf_object: + if (!IS_ERR(parent_egress1_link)) + bpf_link__destroy(parent_egress1_link); + if (!IS_ERR(parent_egress2_link)) + bpf_link__destroy(parent_egress2_link); + if (!IS_ERR(parent_ingress_link)) + bpf_link__destroy(parent_ingress_link); + if (!IS_ERR(child_egress1_link)) + bpf_link__destroy(child_egress1_link); + if (!IS_ERR(child_egress2_link)) + bpf_link__destroy(child_egress2_link); + if (!IS_ERR(child_ingress_link)) + bpf_link__destroy(child_ingress_link); + + cg_storage_multi_isolated__destroy(obj); +} + +static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_shared *obj; + struct cgroup_value expected_cgroup_value; + __u64 key; + struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL; + struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL; + struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL; + bool err; + + obj = cg_storage_multi_shared__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is three runs, two with parent cgroup egress and + * one with parent cgroup ingress. + * Also assert that child cgroup's storage does not exist + */ + parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", + "err %ld", PTR_ERR(parent_egress1_link))) + goto close_bpf_object; + parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", + "err %ld", PTR_ERR(parent_egress2_link))) + goto close_bpf_object; + parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", + "err %ld", PTR_ERR(parent_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 2, + .ingress_pkts = 1, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key = get_cgroup_id(CHILD_CGROUP); + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there is six additional runs, parent cgroup egresses and + * ingress, child cgroup egresses and ingress. + */ + child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", + "err %ld", PTR_ERR(child_egress1_link))) + goto close_bpf_object; + child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", + "err %ld", PTR_ERR(child_egress2_link))) + goto close_bpf_object; + child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", + "err %ld", PTR_ERR(child_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 9, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 4, + .ingress_pkts = 2, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key = get_cgroup_id(CHILD_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 2, + .ingress_pkts = 1, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + +close_bpf_object: + if (!IS_ERR(parent_egress1_link)) + bpf_link__destroy(parent_egress1_link); + if (!IS_ERR(parent_egress2_link)) + bpf_link__destroy(parent_egress2_link); + if (!IS_ERR(parent_ingress_link)) + bpf_link__destroy(parent_ingress_link); + if (!IS_ERR(child_egress1_link)) + bpf_link__destroy(child_egress1_link); + if (!IS_ERR(child_egress2_link)) + bpf_link__destroy(child_egress2_link); + if (!IS_ERR(child_ingress_link)) + bpf_link__destroy(child_ingress_link); + + cg_storage_multi_shared__destroy(obj); +} + +void test_cg_storage_multi(void) +{ + int parent_cgroup_fd = -1, child_cgroup_fd = -1; + + parent_cgroup_fd = test__join_cgroup(PARENT_CGROUP); + if (CHECK(parent_cgroup_fd < 0, "cg-create-parent", "errno %d", errno)) + goto close_cgroup_fd; + child_cgroup_fd = create_and_get_cgroup(CHILD_CGROUP); + if (CHECK(child_cgroup_fd < 0, "cg-create-child", "errno %d", errno)) + goto close_cgroup_fd; + + if (test__start_subtest("egress_only")) + test_egress_only(parent_cgroup_fd, child_cgroup_fd); + + if (test__start_subtest("isolated")) + test_isolated(parent_cgroup_fd, child_cgroup_fd); + + if (test__start_subtest("shared")) + test_shared(parent_cgroup_fd, child_cgroup_fd); + +close_cgroup_fd: + close(child_cgroup_fd); + close(parent_cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c index 6e04f8d1d15b..4d9b514b3fd9 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" +#include "testing_helpers.h" #include "test_cgroup_link.skel.h" static __u32 duration = 0; @@ -37,7 +38,8 @@ void test_cgroup_link(void) int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs); DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts); struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link; - __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags; + __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags, prog_id; + struct bpf_link_info info; int i = 0, err, prog_fd; bool detach_legacy = false; @@ -219,6 +221,22 @@ void test_cgroup_link(void) /* BPF programs should still get called */ ping_and_check(0, cg_nr); + prog_id = link_info_prog_id(links[0], &info); + CHECK(prog_id == 0, "link_info", "failed\n"); + CHECK(info.cgroup.cgroup_id == 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id); + + err = bpf_link__detach(links[0]); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto cleanup; + + /* cgroup_id should be zero in link_info */ + prog_id = link_info_prog_id(links[0], &info); + CHECK(prog_id == 0, "link_info", "failed\n"); + CHECK(info.cgroup.cgroup_id != 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id); + + /* First BPF program shouldn't be called anymore */ + ping_and_check(0, cg_nr - 1); + /* leave cgroup and remove them, don't detach programs */ cleanup_cgroup_environment(); diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c index 059047af7df3..464edc1c1708 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c @@ -13,7 +13,7 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk) socklen_t addr_len = sizeof(addr); __u32 duration = 0; - serv_sk = start_server(AF_INET6, SOCK_STREAM); + serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); if (CHECK(serv_sk < 0, "start_server", "failed to start server\n")) return; @@ -24,17 +24,13 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk) *g_serv_port = addr.sin6_port; /* Client outside of test cgroup should fail to connect by timeout. */ - err = connect_fd_to_fd(out_sk, serv_sk); + err = connect_fd_to_fd(out_sk, serv_sk, 1000); if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd", "unexpected result err %d errno %d\n", err, errno)) goto cleanup; - err = connect_wait(out_sk); - if (CHECK(err, "connect_wait", "unexpected result %d\n", err)) - goto cleanup; - /* Client inside test cgroup should connect just fine. */ - in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk); + in_sk = connect_to_fd(serv_sk, 0); if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno)) goto cleanup; @@ -85,7 +81,7 @@ void test_cgroup_skb_sk_lookup(void) * differs from that of testing cgroup. Moving selftests process to * testing cgroup won't change cgroup id of an already created socket. */ - out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0); + out_sk = socket(AF_INET6, SOCK_STREAM, 0); if (CHECK_FAIL(out_sk < 0)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c index 17bbf76812ca..9229db2f5ca5 100644 --- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -114,7 +114,7 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) goto close_bpf_object; } - fd = connect_to_fd(family, type, server_fd); + fd = connect_to_fd(server_fd, 0); if (fd < 0) { err = -1; goto close_bpf_object; @@ -137,25 +137,25 @@ void test_connect_force_port(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server_with_port(AF_INET, SOCK_STREAM, 60123); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 60123, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET6, SOCK_STREAM, 60124); + server_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 60124, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET, SOCK_DGRAM, 60123); + server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 60123, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET6, SOCK_DGRAM, 60124); + server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 60124, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM)); diff --git a/tools/testing/selftests/bpf/prog_tests/core_retro.c b/tools/testing/selftests/bpf/prog_tests/core_retro.c new file mode 100644 index 000000000000..6acb0e94d4d7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_retro.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#define _GNU_SOURCE +#include <test_progs.h> +#include "test_core_retro.skel.h" + +void test_core_retro(void) +{ + int err, zero = 0, res, duration = 0, my_pid = getpid(); + struct test_core_retro *skel; + + /* load program */ + skel = test_core_retro__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) + goto out_close; + + err = bpf_map_update_elem(bpf_map__fd(skel->maps.exp_tgid_map), &zero, &my_pid, 0); + if (CHECK(err, "map_update", "failed to set expected PID: %d\n", errno)) + goto out_close; + + /* attach probe */ + err = test_core_retro__attach(skel); + if (CHECK(err, "attach_kprobe", "err %d\n", err)) + goto out_close; + + /* trigger */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.results), &zero, &res); + if (CHECK(err, "map_lookup", "failed to lookup result: %d\n", errno)) + goto out_close; + + CHECK(res != my_pid, "pid_check", "got %d != exp %d\n", res, my_pid); + +out_close: + test_core_retro__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/endian.c b/tools/testing/selftests/bpf/prog_tests/endian.c new file mode 100644 index 000000000000..1a11612ace6c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/endian.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include "test_endian.skel.h" + +static int duration; + +#define IN16 0x1234 +#define IN32 0x12345678U +#define IN64 0x123456789abcdef0ULL + +#define OUT16 0x3412 +#define OUT32 0x78563412U +#define OUT64 0xf0debc9a78563412ULL + +void test_endian(void) +{ + struct test_endian* skel; + struct test_endian__bss *bss; + int err; + + skel = test_endian__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + bss = skel->bss; + + bss->in16 = IN16; + bss->in32 = IN32; + bss->in64 = IN64; + + err = test_endian__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + usleep(1); + + CHECK(bss->out16 != OUT16, "out16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out16, (__u64)OUT16); + CHECK(bss->out32 != OUT32, "out32", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out32, (__u64)OUT32); + CHECK(bss->out64 != OUT64, "out16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out64, (__u64)OUT64); + + CHECK(bss->const16 != OUT16, "const16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const16, (__u64)OUT16); + CHECK(bss->const32 != OUT32, "const32", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const32, (__u64)OUT32); + CHECK(bss->const64 != OUT64, "const64", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const64, (__u64)OUT64); +cleanup: + test_endian__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c new file mode 100644 index 000000000000..d884b2ed5bc5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" + +void test_get_stackid_cannot_attach(void) +{ + struct perf_event_attr attr = { + /* .type = PERF_TYPE_SOFTWARE, */ + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .precise_ip = 1, + .sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK, + .branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_CALL_STACK, + .sample_period = 5000, + .size = sizeof(struct perf_event_attr), + }; + struct test_stacktrace_build_id *skel; + __u32 duration = 0; + int pmu_fd, err; + + skel = test_stacktrace_build_id__open(); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + return; + + /* override program type */ + bpf_program__set_perf_event(skel->progs.oncpu); + + err = test_stacktrace_build_id__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) { + printf("%s:SKIP:cannot open PERF_COUNT_HW_CPU_CYCLES with precise_ip > 0\n", + __func__); + test__skip(); + goto cleanup; + } + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain", + "should have failed\n"); + close(pmu_fd); + + /* add PERF_SAMPLE_CALLCHAIN, attach should succeed */ + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain", + "err: %ld\n", PTR_ERR(skel->links.oncpu)); + close(pmu_fd); + + /* add exclude_callchain_kernel, attach should fail */ + attr.exclude_callchain_kernel = 1; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel", + "should have failed\n"); + close(pmu_fd); + +cleanup: + test_stacktrace_build_id__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c new file mode 100644 index 000000000000..e3d6777226a8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> +#include "test_ksyms.skel.h" +#include <sys/stat.h> + +static int duration; + +static __u64 kallsyms_find(const char *sym) +{ + char type, name[500]; + __u64 addr, res = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (CHECK(!f, "kallsyms_fopen", "failed to open: %d\n", errno)) + return 0; + + while (fscanf(f, "%llx %c %499s%*[^\n]\n", &addr, &type, name) > 0) { + if (strcmp(name, sym) == 0) { + res = addr; + goto out; + } + } + + CHECK(false, "not_found", "symbol %s not found\n", sym); +out: + fclose(f); + return res; +} + +void test_ksyms(void) +{ + __u64 link_fops_addr = kallsyms_find("bpf_link_fops"); + const char *btf_path = "/sys/kernel/btf/vmlinux"; + struct test_ksyms *skel; + struct test_ksyms__data *data; + struct stat st; + __u64 btf_size; + int err; + + if (CHECK(stat(btf_path, &st), "stat_btf", "err %d\n", errno)) + return; + btf_size = st.st_size; + + skel = test_ksyms__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open and load skeleton\n")) + return; + + err = test_ksyms__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + data = skel->data; + CHECK(data->out__bpf_link_fops != link_fops_addr, "bpf_link_fops", + "got 0x%llx, exp 0x%llx\n", + data->out__bpf_link_fops, link_fops_addr); + CHECK(data->out__bpf_link_fops1 != 0, "bpf_link_fops1", + "got %llu, exp %llu\n", data->out__bpf_link_fops1, (__u64)0); + CHECK(data->out__btf_size != btf_size, "btf_size", + "got %llu, exp %llu\n", data->out__btf_size, btf_size); + CHECK(data->out__per_cpu_start != 0, "__per_cpu_start", + "got %llu, exp %llu\n", data->out__per_cpu_start, (__u64)0); + +cleanup: + test_ksyms__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c index c1168e4a9036..5a2a689dbb68 100644 --- a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c +++ b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c @@ -23,7 +23,7 @@ void test_load_bytes_relative(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server(AF_INET, SOCK_STREAM); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; @@ -49,7 +49,7 @@ void test_load_bytes_relative(void) if (CHECK_FAIL(err)) goto close_bpf_object; - client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd); + client_fd = connect_to_fd(server_fd, 0); if (CHECK_FAIL(client_fd < 0)) goto close_bpf_object; close(client_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c new file mode 100644 index 000000000000..c230a573c373 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <test_progs.h> +#include <network_helpers.h> + +#include "map_ptr_kern.skel.h" + +void test_map_ptr(void) +{ + struct map_ptr_kern *skel; + __u32 duration = 0, retval; + char buf[128]; + int err; + + skel = map_ptr_kern__open_and_load(); + if (CHECK(!skel, "skel_open_load", "open_load failed\n")) + return; + + err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4, + sizeof(pkt_v4), buf, NULL, &retval, NULL); + + if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) + goto cleanup; + + if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval, + skel->bss->g_map_type, skel->bss->g_line)) + goto cleanup; + +cleanup: + map_ptr_kern__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index a122ce3b360e..c33ec180b3f2 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -4,6 +4,7 @@ #include <sched.h> #include <sys/socket.h> #include <test_progs.h> +#include "test_perf_buffer.skel.h" #include "bpf/libbpf_internal.h" /* AddressSanitizer sometimes crashes due to data dereference below, due to @@ -25,16 +26,11 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void test_perf_buffer(void) { - int err, prog_fd, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; - const char *prog_name = "kprobe/sys_nanosleep"; - const char *file = "./test_perf_buffer.o"; + int err, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; struct perf_buffer_opts pb_opts = {}; - struct bpf_map *perf_buf_map; + struct test_perf_buffer *skel; cpu_set_t cpu_set, cpu_seen; - struct bpf_program *prog; - struct bpf_object *obj; struct perf_buffer *pb; - struct bpf_link *link; bool *online; nr_cpus = libbpf_num_possible_cpus(); @@ -51,33 +47,21 @@ void test_perf_buffer(void) nr_on_cpus++; /* load program */ - err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd); - if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) { - obj = NULL; - goto out_close; - } - - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) + skel = test_perf_buffer__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) goto out_close; - /* load map */ - perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map"); - if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n")) - goto out_close; - - /* attach kprobe */ - link = bpf_program__attach_kprobe(prog, false /* retprobe */, - SYS_NANOSLEEP_KPROBE_NAME); - if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) + /* attach probe */ + err = test_perf_buffer__attach(skel); + if (CHECK(err, "attach_kprobe", "err %d\n", err)) goto out_close; /* set up perf buffer */ pb_opts.sample_cb = on_sample; pb_opts.ctx = &cpu_seen; - pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts); if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) - goto out_detach; + goto out_close; /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); @@ -94,7 +78,7 @@ void test_perf_buffer(void) &cpu_set); if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n", i, err)) - goto out_detach; + goto out_close; usleep(1); } @@ -110,9 +94,7 @@ void test_perf_buffer(void) out_free_pb: perf_buffer__free(pb); -out_detach: - bpf_link__destroy(link); out_close: - bpf_object__close(obj); + test_perf_buffer__destroy(skel); free(online); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c new file mode 100644 index 000000000000..72c3690844fb --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#define _GNU_SOURCE +#include <pthread.h> +#include <sched.h> +#include <test_progs.h> +#include "perf_event_stackmap.skel.h" + +#ifndef noinline +#define noinline __attribute__((noinline)) +#endif + +noinline int func_1(void) +{ + static int val = 1; + + val += 1; + + usleep(100); + return val; +} + +noinline int func_2(void) +{ + return func_1(); +} + +noinline int func_3(void) +{ + return func_2(); +} + +noinline int func_4(void) +{ + return func_3(); +} + +noinline int func_5(void) +{ + return func_4(); +} + +noinline int func_6(void) +{ + int i, val = 1; + + for (i = 0; i < 100; i++) + val += func_5(); + + return val; +} + +void test_perf_event_stackmap(void) +{ + struct perf_event_attr attr = { + /* .type = PERF_TYPE_SOFTWARE, */ + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .precise_ip = 2, + .sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK | + PERF_SAMPLE_CALLCHAIN, + .branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_CALL_STACK, + .sample_period = 5000, + .size = sizeof(struct perf_event_attr), + }; + struct perf_event_stackmap *skel; + __u32 duration = 0; + cpu_set_t cpu_set; + int pmu_fd, err; + + skel = perf_event_stackmap__open(); + + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + return; + + err = perf_event_stackmap__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; + + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno)) + goto cleanup; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (pmu_fd < 0) { + printf("%s:SKIP:cpu doesn't support the event\n", __func__); + test__skip(); + goto cleanup; + } + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.oncpu))) { + close(pmu_fd); + goto cleanup; + } + + /* create kernel and user stack traces for testing */ + func_6(); + + CHECK(skel->data->stackid_kernel != 2, "get_stackid_kernel", "failed\n"); + CHECK(skel->data->stackid_user != 2, "get_stackid_user", "failed\n"); + CHECK(skel->data->stack_kernel != 2, "get_stack_kernel", "failed\n"); + CHECK(skel->data->stack_user != 2, "get_stack_user", "failed\n"); + +cleanup: + perf_event_stackmap__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c new file mode 100644 index 000000000000..3b127cab4864 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/err.h> +#include <string.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <linux/btf.h> +#include <linux/kernel.h> +#define CONFIG_DEBUG_INFO_BTF +#include <linux/btf_ids.h> +#include "test_progs.h" + +static int duration; + +struct symbol { + const char *name; + int type; + int id; +}; + +struct symbol test_symbols[] = { + { "unused", BTF_KIND_UNKN, 0 }, + { "S", BTF_KIND_TYPEDEF, -1 }, + { "T", BTF_KIND_TYPEDEF, -1 }, + { "U", BTF_KIND_TYPEDEF, -1 }, + { "S", BTF_KIND_STRUCT, -1 }, + { "U", BTF_KIND_UNION, -1 }, + { "func", BTF_KIND_FUNC, -1 }, +}; + +BTF_ID_LIST(test_list_local) +BTF_ID_UNUSED +BTF_ID(typedef, S) +BTF_ID(typedef, T) +BTF_ID(typedef, U) +BTF_ID(struct, S) +BTF_ID(union, U) +BTF_ID(func, func) + +extern __u32 test_list_global[]; +BTF_ID_LIST_GLOBAL(test_list_global) +BTF_ID_UNUSED +BTF_ID(typedef, S) +BTF_ID(typedef, T) +BTF_ID(typedef, U) +BTF_ID(struct, S) +BTF_ID(union, U) +BTF_ID(func, func) + +static int +__resolve_symbol(struct btf *btf, int type_id) +{ + const struct btf_type *type; + const char *str; + unsigned int i; + + type = btf__type_by_id(btf, type_id); + if (!type) { + PRINT_FAIL("Failed to get type for ID %d\n", type_id); + return -1; + } + + for (i = 0; i < ARRAY_SIZE(test_symbols); i++) { + if (test_symbols[i].id != -1) + continue; + + if (BTF_INFO_KIND(type->info) != test_symbols[i].type) + continue; + + str = btf__name_by_offset(btf, type->name_off); + if (!str) { + PRINT_FAIL("Failed to get name for BTF ID %d\n", type_id); + return -1; + } + + if (!strcmp(str, test_symbols[i].name)) + test_symbols[i].id = type_id; + } + + return 0; +} + +static int resolve_symbols(void) +{ + struct btf *btf; + int type_id; + __u32 nr; + + btf = btf__parse_elf("btf_data.o", NULL); + if (CHECK(libbpf_get_error(btf), "resolve", + "Failed to load BTF from btf_data.o\n")) + return -1; + + nr = btf__get_nr_types(btf); + + for (type_id = 1; type_id <= nr; type_id++) { + if (__resolve_symbol(btf, type_id)) + break; + } + + btf__free(btf); + return 0; +} + +int test_resolve_btfids(void) +{ + __u32 *test_list, *test_lists[] = { test_list_local, test_list_global }; + unsigned int i, j; + int ret = 0; + + if (resolve_symbols()) + return -1; + + /* Check BTF_ID_LIST(test_list_local) and + * BTF_ID_LIST_GLOBAL(test_list_global) IDs + */ + for (j = 0; j < ARRAY_SIZE(test_lists); j++) { + test_list = test_lists[j]; + for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) { + ret = CHECK(test_list[i] != test_symbols[i].id, + "id_check", + "wrong ID for %s (%d != %d)\n", + test_symbols[i].name, + test_list[i], test_symbols[i].id); + } + } + + return ret; +} diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c index 713167449c98..8b571890c57e 100644 --- a/tools/testing/selftests/bpf/prog_tests/section_names.c +++ b/tools/testing/selftests/bpf/prog_tests/section_names.c @@ -35,7 +35,7 @@ static struct sec_name_test tests[] = { {-EINVAL, 0}, }, {"raw_tp/", {0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0}, {-EINVAL, 0} }, - {"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} }, + {"xdp", {0, BPF_PROG_TYPE_XDP, BPF_XDP}, {0, BPF_XDP} }, {"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} }, {"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} }, {"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} }, diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c new file mode 100644 index 000000000000..c571584c00f5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -0,0 +1,1329 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare +/* + * Test BPF attach point for INET socket lookup (BPF_SK_LOOKUP). + * + * Tests exercise: + * - attaching/detaching/querying programs to BPF_SK_LOOKUP hook, + * - redirecting socket lookup to a socket selected by BPF program, + * - failing a socket lookup on BPF program's request, + * - error scenarios for selecting a socket from BPF program, + * - accessing BPF program context, + * - attaching and running multiple BPF programs. + * + * Tests run in a dedicated network namespace. + */ + +#define _GNU_SOURCE +#include <arpa/inet.h> +#include <assert.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include <bpf/libbpf.h> +#include <bpf/bpf.h> + +#include "test_progs.h" +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" +#include "network_helpers.h" +#include "testing_helpers.h" +#include "test_sk_lookup.skel.h" + +/* External (address, port) pairs the client sends packets to. */ +#define EXT_IP4 "127.0.0.1" +#define EXT_IP6 "fd00::1" +#define EXT_PORT 7007 + +/* Internal (address, port) pairs the server listens/receives at. */ +#define INT_IP4 "127.0.0.2" +#define INT_IP4_V6 "::ffff:127.0.0.2" +#define INT_IP6 "fd00::2" +#define INT_PORT 8008 + +#define IO_TIMEOUT_SEC 3 + +enum server { + SERVER_A = 0, + SERVER_B = 1, + MAX_SERVERS, +}; + +enum { + PROG1 = 0, + PROG2, +}; + +struct inet_addr { + const char *ip; + unsigned short port; +}; + +struct test { + const char *desc; + struct bpf_program *lookup_prog; + struct bpf_program *reuseport_prog; + struct bpf_map *sock_map; + int sotype; + struct inet_addr connect_to; + struct inet_addr listen_at; + enum server accept_on; + bool reuseport_has_conns; /* Add a connected socket to reuseport group */ +}; + +static __u32 duration; /* for CHECK macro */ + +static bool is_ipv6(const char *ip) +{ + return !!strchr(ip, ':'); +} + +static int attach_reuseport(int sock_fd, struct bpf_program *reuseport_prog) +{ + int err, prog_fd; + + prog_fd = bpf_program__fd(reuseport_prog); + if (prog_fd < 0) { + errno = -prog_fd; + return -1; + } + + err = setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, + &prog_fd, sizeof(prog_fd)); + if (err) + return -1; + + return 0; +} + +static socklen_t inetaddr_len(const struct sockaddr_storage *addr) +{ + return (addr->ss_family == AF_INET ? sizeof(struct sockaddr_in) : + addr->ss_family == AF_INET6 ? sizeof(struct sockaddr_in6) : 0); +} + +static int make_socket(int sotype, const char *ip, int port, + struct sockaddr_storage *addr) +{ + struct timeval timeo = { .tv_sec = IO_TIMEOUT_SEC }; + int err, family, fd; + + family = is_ipv6(ip) ? AF_INET6 : AF_INET; + err = make_sockaddr(family, ip, port, addr, NULL); + if (CHECK(err, "make_address", "failed\n")) + return -1; + + fd = socket(addr->ss_family, sotype, 0); + if (CHECK(fd < 0, "socket", "failed\n")) { + log_err("failed to make socket"); + return -1; + } + + err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo, sizeof(timeo)); + if (CHECK(err, "setsockopt(SO_SNDTIMEO)", "failed\n")) { + log_err("failed to set SNDTIMEO"); + close(fd); + return -1; + } + + err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo, sizeof(timeo)); + if (CHECK(err, "setsockopt(SO_RCVTIMEO)", "failed\n")) { + log_err("failed to set RCVTIMEO"); + close(fd); + return -1; + } + + return fd; +} + +static int make_server(int sotype, const char *ip, int port, + struct bpf_program *reuseport_prog) +{ + struct sockaddr_storage addr = {0}; + const int one = 1; + int err, fd = -1; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + /* Enabled for UDPv6 sockets for IPv4-mapped IPv6 to work. */ + if (sotype == SOCK_DGRAM) { + err = setsockopt(fd, SOL_IP, IP_RECVORIGDSTADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(IP_RECVORIGDSTADDR)", "failed\n")) { + log_err("failed to enable IP_RECVORIGDSTADDR"); + goto fail; + } + } + + if (sotype == SOCK_DGRAM && addr.ss_family == AF_INET6) { + err = setsockopt(fd, SOL_IPV6, IPV6_RECVORIGDSTADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(IPV6_RECVORIGDSTADDR)", "failed\n")) { + log_err("failed to enable IPV6_RECVORIGDSTADDR"); + goto fail; + } + } + + if (sotype == SOCK_STREAM) { + err = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(SO_REUSEADDR)", "failed\n")) { + log_err("failed to enable SO_REUSEADDR"); + goto fail; + } + } + + if (reuseport_prog) { + err = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(SO_REUSEPORT)", "failed\n")) { + log_err("failed to enable SO_REUSEPORT"); + goto fail; + } + } + + err = bind(fd, (void *)&addr, inetaddr_len(&addr)); + if (CHECK(err, "bind", "failed\n")) { + log_err("failed to bind listen socket"); + goto fail; + } + + if (sotype == SOCK_STREAM) { + err = listen(fd, SOMAXCONN); + if (CHECK(err, "make_server", "listen")) { + log_err("failed to listen on port %d", port); + goto fail; + } + } + + /* Late attach reuseport prog so we can have one init path */ + if (reuseport_prog) { + err = attach_reuseport(fd, reuseport_prog); + if (CHECK(err, "attach_reuseport", "failed\n")) { + log_err("failed to attach reuseport prog"); + goto fail; + } + } + + return fd; +fail: + close(fd); + return -1; +} + +static int make_client(int sotype, const char *ip, int port) +{ + struct sockaddr_storage addr = {0}; + int err, fd; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + err = connect(fd, (void *)&addr, inetaddr_len(&addr)); + if (CHECK(err, "make_client", "connect")) { + log_err("failed to connect client socket"); + goto fail; + } + + return fd; +fail: + close(fd); + return -1; +} + +static int send_byte(int fd) +{ + ssize_t n; + + errno = 0; + n = send(fd, "a", 1, 0); + if (CHECK(n <= 0, "send_byte", "send")) { + log_err("failed/partial send"); + return -1; + } + return 0; +} + +static int recv_byte(int fd) +{ + char buf[1]; + ssize_t n; + + n = recv(fd, buf, sizeof(buf), 0); + if (CHECK(n <= 0, "recv_byte", "recv")) { + log_err("failed/partial recv"); + return -1; + } + return 0; +} + +static int tcp_recv_send(int server_fd) +{ + char buf[1]; + int ret, fd; + ssize_t n; + + fd = accept(server_fd, NULL, NULL); + if (CHECK(fd < 0, "accept", "failed\n")) { + log_err("failed to accept"); + return -1; + } + + n = recv(fd, buf, sizeof(buf), 0); + if (CHECK(n <= 0, "recv", "failed\n")) { + log_err("failed/partial recv"); + ret = -1; + goto close; + } + + n = send(fd, buf, n, 0); + if (CHECK(n <= 0, "send", "failed\n")) { + log_err("failed/partial send"); + ret = -1; + goto close; + } + + ret = 0; +close: + close(fd); + return ret; +} + +static void v4_to_v6(struct sockaddr_storage *ss) +{ + struct sockaddr_in6 *v6 = (struct sockaddr_in6 *)ss; + struct sockaddr_in v4 = *(struct sockaddr_in *)ss; + + v6->sin6_family = AF_INET6; + v6->sin6_port = v4.sin_port; + v6->sin6_addr.s6_addr[10] = 0xff; + v6->sin6_addr.s6_addr[11] = 0xff; + memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4); +} + +static int udp_recv_send(int server_fd) +{ + char cmsg_buf[CMSG_SPACE(sizeof(struct sockaddr_storage))]; + struct sockaddr_storage _src_addr = { 0 }; + struct sockaddr_storage *src_addr = &_src_addr; + struct sockaddr_storage *dst_addr = NULL; + struct msghdr msg = { 0 }; + struct iovec iov = { 0 }; + struct cmsghdr *cm; + char buf[1]; + int ret, fd; + ssize_t n; + + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + + msg.msg_name = src_addr; + msg.msg_namelen = sizeof(*src_addr); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + errno = 0; + n = recvmsg(server_fd, &msg, 0); + if (CHECK(n <= 0, "recvmsg", "failed\n")) { + log_err("failed to receive"); + return -1; + } + if (CHECK(msg.msg_flags & MSG_CTRUNC, "recvmsg", "truncated cmsg\n")) + return -1; + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if ((cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_ORIGDSTADDR) || + (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_ORIGDSTADDR)) { + dst_addr = (struct sockaddr_storage *)CMSG_DATA(cm); + break; + } + log_err("warning: ignored cmsg at level %d type %d", + cm->cmsg_level, cm->cmsg_type); + } + if (CHECK(!dst_addr, "recvmsg", "missing ORIGDSTADDR\n")) + return -1; + + /* Server socket bound to IPv4-mapped IPv6 address */ + if (src_addr->ss_family == AF_INET6 && + dst_addr->ss_family == AF_INET) { + v4_to_v6(dst_addr); + } + + /* Reply from original destination address. */ + fd = socket(dst_addr->ss_family, SOCK_DGRAM, 0); + if (CHECK(fd < 0, "socket", "failed\n")) { + log_err("failed to create tx socket"); + return -1; + } + + ret = bind(fd, (struct sockaddr *)dst_addr, sizeof(*dst_addr)); + if (CHECK(ret, "bind", "failed\n")) { + log_err("failed to bind tx socket"); + goto out; + } + + msg.msg_control = NULL; + msg.msg_controllen = 0; + n = sendmsg(fd, &msg, 0); + if (CHECK(n <= 0, "sendmsg", "failed\n")) { + log_err("failed to send echo reply"); + ret = -1; + goto out; + } + + ret = 0; +out: + close(fd); + return ret; +} + +static int tcp_echo_test(int client_fd, int server_fd) +{ + int err; + + err = send_byte(client_fd); + if (err) + return -1; + err = tcp_recv_send(server_fd); + if (err) + return -1; + err = recv_byte(client_fd); + if (err) + return -1; + + return 0; +} + +static int udp_echo_test(int client_fd, int server_fd) +{ + int err; + + err = send_byte(client_fd); + if (err) + return -1; + err = udp_recv_send(server_fd); + if (err) + return -1; + err = recv_byte(client_fd); + if (err) + return -1; + + return 0; +} + +static struct bpf_link *attach_lookup_prog(struct bpf_program *prog) +{ + struct bpf_link *link; + int net_fd; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (CHECK(net_fd < 0, "open", "failed\n")) { + log_err("failed to open /proc/self/ns/net"); + return NULL; + } + + link = bpf_program__attach_netns(prog, net_fd); + if (CHECK(IS_ERR(link), "bpf_program__attach_netns", "failed\n")) { + errno = -PTR_ERR(link); + log_err("failed to attach program '%s' to netns", + bpf_program__name(prog)); + link = NULL; + } + + close(net_fd); + return link; +} + +static int update_lookup_map(struct bpf_map *map, int index, int sock_fd) +{ + int err, map_fd; + uint64_t value; + + map_fd = bpf_map__fd(map); + if (CHECK(map_fd < 0, "bpf_map__fd", "failed\n")) { + errno = -map_fd; + log_err("failed to get map FD"); + return -1; + } + + value = (uint64_t)sock_fd; + err = bpf_map_update_elem(map_fd, &index, &value, BPF_NOEXIST); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) { + log_err("failed to update redir_map @ %d", index); + return -1; + } + + return 0; +} + +static void query_lookup_prog(struct test_sk_lookup *skel) +{ + struct bpf_link *link[3] = {}; + struct bpf_link_info info; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + __u32 prog_id; + int net_fd; + int err; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (CHECK(net_fd < 0, "open", "failed\n")) { + log_err("failed to open /proc/self/ns/net"); + return; + } + + link[0] = attach_lookup_prog(skel->progs.lookup_pass); + if (!link[0]) + goto close; + link[1] = attach_lookup_prog(skel->progs.lookup_pass); + if (!link[1]) + goto detach; + link[2] = attach_lookup_prog(skel->progs.lookup_drop); + if (!link[2]) + goto detach; + + err = bpf_prog_query(net_fd, BPF_SK_LOOKUP, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + if (CHECK(err, "bpf_prog_query", "failed\n")) { + log_err("failed to query lookup prog"); + goto detach; + } + + errno = 0; + if (CHECK(attach_flags != 0, "bpf_prog_query", + "wrong attach_flags on query: %u", attach_flags)) + goto detach; + if (CHECK(prog_cnt != 3, "bpf_prog_query", + "wrong program count on query: %u", prog_cnt)) + goto detach; + prog_id = link_info_prog_id(link[0], &info); + CHECK(prog_ids[0] != prog_id, "bpf_prog_query", + "invalid program #0 id on query: %u != %u\n", + prog_ids[0], prog_id); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + prog_id = link_info_prog_id(link[1], &info); + CHECK(prog_ids[1] != prog_id, "bpf_prog_query", + "invalid program #1 id on query: %u != %u\n", + prog_ids[1], prog_id); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + prog_id = link_info_prog_id(link[2], &info); + CHECK(prog_ids[2] != prog_id, "bpf_prog_query", + "invalid program #2 id on query: %u != %u\n", + prog_ids[2], prog_id); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + + err = bpf_link__detach(link[0]); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto detach; + + /* prog id is still there, but netns_ino is zeroed out */ + prog_id = link_info_prog_id(link[0], &info); + CHECK(prog_ids[0] != prog_id, "bpf_prog_query", + "invalid program #0 id on query: %u != %u\n", + prog_ids[0], prog_id); + CHECK(info.netns.netns_ino != 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + +detach: + if (link[2]) + bpf_link__destroy(link[2]); + if (link[1]) + bpf_link__destroy(link[1]); + if (link[0]) + bpf_link__destroy(link[0]); +close: + close(net_fd); +} + +static void run_lookup_prog(const struct test *t) +{ + int server_fds[MAX_SERVERS] = { -1 }; + int client_fd, reuse_conn_fd = -1; + struct bpf_link *lookup_link; + int i, err; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + server_fds[i] = make_server(t->sotype, t->listen_at.ip, + t->listen_at.port, + t->reuseport_prog); + if (server_fds[i] < 0) + goto close; + + err = update_lookup_map(t->sock_map, i, server_fds[i]); + if (err) + goto close; + + /* want just one server for non-reuseport test */ + if (!t->reuseport_prog) + break; + } + + /* Regular UDP socket lookup with reuseport behaves + * differently when reuseport group contains connected + * sockets. Check that adding a connected UDP socket to the + * reuseport group does not affect how reuseport works with + * BPF socket lookup. + */ + if (t->reuseport_has_conns) { + struct sockaddr_storage addr = {}; + socklen_t len = sizeof(addr); + + /* Add an extra socket to reuseport group */ + reuse_conn_fd = make_server(t->sotype, t->listen_at.ip, + t->listen_at.port, + t->reuseport_prog); + if (reuse_conn_fd < 0) + goto close; + + /* Connect the extra socket to itself */ + err = getsockname(reuse_conn_fd, (void *)&addr, &len); + if (CHECK(err, "getsockname", "errno %d\n", errno)) + goto close; + err = connect(reuse_conn_fd, (void *)&addr, len); + if (CHECK(err, "connect", "errno %d\n", errno)) + goto close; + } + + client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port); + if (client_fd < 0) + goto close; + + if (t->sotype == SOCK_STREAM) + tcp_echo_test(client_fd, server_fds[t->accept_on]); + else + udp_echo_test(client_fd, server_fds[t->accept_on]); + + close(client_fd); +close: + if (reuse_conn_fd != -1) + close(reuse_conn_fd); + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + if (server_fds[i] != -1) + close(server_fds[i]); + } + bpf_link__destroy(lookup_link); +} + +static void test_redirect_lookup(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv4 redir addr", + .lookup_prog = skel->progs.redir_ip4, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, EXT_PORT }, + }, + { + .desc = "TCP IPv4 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "TCP IPv4 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "TCP IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + { + .desc = "TCP IPv6 redir addr", + .lookup_prog = skel->progs.redir_ip6, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, EXT_PORT }, + }, + { + .desc = "TCP IPv4->IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4_V6, INT_PORT }, + }, + { + .desc = "TCP IPv6 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "TCP IPv6 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "UDP IPv4 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, INT_PORT }, + }, + { + .desc = "UDP IPv4 redir addr", + .lookup_prog = skel->progs.redir_ip4, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv4 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "UDP IPv4 redir and reuseport with conns", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + .reuseport_has_conns = true, + }, + { + .desc = "UDP IPv4 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "UDP IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + { + .desc = "UDP IPv6 redir addr", + .lookup_prog = skel->progs.redir_ip6, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, EXT_PORT }, + }, + { + .desc = "UDP IPv4->IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .listen_at = { INT_IP4_V6, INT_PORT }, + .connect_to = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv6 redir and reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "UDP IPv6 redir and reuseport with conns", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + .reuseport_has_conns = true, + }, + { + .desc = "UDP IPv6 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_A, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + run_lookup_prog(t); + } +} + +static void drop_on_lookup(const struct test *t) +{ + struct sockaddr_storage dst = {}; + int client_fd, server_fd, err; + struct bpf_link *lookup_link; + ssize_t n; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + server_fd = make_server(t->sotype, t->listen_at.ip, t->listen_at.port, + t->reuseport_prog); + if (server_fd < 0) + goto detach; + + client_fd = make_socket(t->sotype, t->connect_to.ip, + t->connect_to.port, &dst); + if (client_fd < 0) + goto close_srv; + + err = connect(client_fd, (void *)&dst, inetaddr_len(&dst)); + if (t->sotype == SOCK_DGRAM) { + err = send_byte(client_fd); + if (err) + goto close_all; + + /* Read out asynchronous error */ + n = recv(client_fd, NULL, 0, 0); + err = n == -1; + } + if (CHECK(!err || errno != ECONNREFUSED, "connect", + "unexpected success or error\n")) + log_err("expected ECONNREFUSED on connect"); + +close_all: + close(client_fd); +close_srv: + close(server_fd); +detach: + bpf_link__destroy(lookup_link); +} + +static void test_drop_on_lookup(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "TCP IPv6 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, EXT_PORT }, + }, + { + .desc = "UDP IPv4 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv6 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + drop_on_lookup(t); + } +} + +static void drop_on_reuseport(const struct test *t) +{ + struct sockaddr_storage dst = { 0 }; + int client, server1, server2, err; + struct bpf_link *lookup_link; + ssize_t n; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + server1 = make_server(t->sotype, t->listen_at.ip, t->listen_at.port, + t->reuseport_prog); + if (server1 < 0) + goto detach; + + err = update_lookup_map(t->sock_map, SERVER_A, server1); + if (err) + goto detach; + + /* second server on destination address we should never reach */ + server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port, + NULL /* reuseport prog */); + if (server2 < 0) + goto close_srv1; + + client = make_socket(t->sotype, t->connect_to.ip, + t->connect_to.port, &dst); + if (client < 0) + goto close_srv2; + + err = connect(client, (void *)&dst, inetaddr_len(&dst)); + if (t->sotype == SOCK_DGRAM) { + err = send_byte(client); + if (err) + goto close_all; + + /* Read out asynchronous error */ + n = recv(client, NULL, 0, 0); + err = n == -1; + } + if (CHECK(!err || errno != ECONNREFUSED, "connect", + "unexpected success or error\n")) + log_err("expected ECONNREFUSED on connect"); + +close_all: + close(client); +close_srv2: + close(server2); +close_srv1: + close(server1); +detach: + bpf_link__destroy(lookup_link); +} + +static void test_drop_on_reuseport(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv6 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + }, + { + .desc = "UDP IPv4 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv6 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + drop_on_reuseport(t); + } +} + +static void run_sk_assign(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog, + const char *listen_ip, const char *connect_ip) +{ + int client_fd, peer_fd, server_fds[MAX_SERVERS] = { -1 }; + struct bpf_link *lookup_link; + int i, err; + + lookup_link = attach_lookup_prog(lookup_prog); + if (!lookup_link) + return; + + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + server_fds[i] = make_server(SOCK_STREAM, listen_ip, 0, NULL); + if (server_fds[i] < 0) + goto close_servers; + + err = update_lookup_map(skel->maps.redir_map, i, + server_fds[i]); + if (err) + goto close_servers; + } + + client_fd = make_client(SOCK_STREAM, connect_ip, EXT_PORT); + if (client_fd < 0) + goto close_servers; + + peer_fd = accept(server_fds[SERVER_B], NULL, NULL); + if (CHECK(peer_fd < 0, "accept", "failed\n")) + goto close_client; + + close(peer_fd); +close_client: + close(client_fd); +close_servers: + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + if (server_fds[i] != -1) + close(server_fds[i]); + } + bpf_link__destroy(lookup_link); +} + +static void run_sk_assign_v4(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog) +{ + run_sk_assign(skel, lookup_prog, INT_IP4, EXT_IP4); +} + +static void run_sk_assign_v6(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog) +{ + run_sk_assign(skel, lookup_prog, INT_IP6, EXT_IP6); +} + +static void run_sk_assign_connected(struct test_sk_lookup *skel, + int sotype) +{ + int err, client_fd, connected_fd, server_fd; + struct bpf_link *lookup_link; + + server_fd = make_server(sotype, EXT_IP4, EXT_PORT, NULL); + if (server_fd < 0) + return; + + connected_fd = make_client(sotype, EXT_IP4, EXT_PORT); + if (connected_fd < 0) + goto out_close_server; + + /* Put a connected socket in redirect map */ + err = update_lookup_map(skel->maps.redir_map, SERVER_A, connected_fd); + if (err) + goto out_close_connected; + + lookup_link = attach_lookup_prog(skel->progs.sk_assign_esocknosupport); + if (!lookup_link) + goto out_close_connected; + + /* Try to redirect TCP SYN / UDP packet to a connected socket */ + client_fd = make_client(sotype, EXT_IP4, EXT_PORT); + if (client_fd < 0) + goto out_unlink_prog; + if (sotype == SOCK_DGRAM) { + send_byte(client_fd); + recv_byte(server_fd); + } + + close(client_fd); +out_unlink_prog: + bpf_link__destroy(lookup_link); +out_close_connected: + close(connected_fd); +out_close_server: + close(server_fd); +} + +static void test_sk_assign_helper(struct test_sk_lookup *skel) +{ + if (test__start_subtest("sk_assign returns EEXIST")) + run_sk_assign_v4(skel, skel->progs.sk_assign_eexist); + if (test__start_subtest("sk_assign honors F_REPLACE")) + run_sk_assign_v4(skel, skel->progs.sk_assign_replace_flag); + if (test__start_subtest("sk_assign accepts NULL socket")) + run_sk_assign_v4(skel, skel->progs.sk_assign_null); + if (test__start_subtest("access ctx->sk")) + run_sk_assign_v4(skel, skel->progs.access_ctx_sk); + if (test__start_subtest("narrow access to ctx v4")) + run_sk_assign_v4(skel, skel->progs.ctx_narrow_access); + if (test__start_subtest("narrow access to ctx v6")) + run_sk_assign_v6(skel, skel->progs.ctx_narrow_access); + if (test__start_subtest("sk_assign rejects TCP established")) + run_sk_assign_connected(skel, SOCK_STREAM); + if (test__start_subtest("sk_assign rejects UDP connected")) + run_sk_assign_connected(skel, SOCK_DGRAM); +} + +struct test_multi_prog { + const char *desc; + struct bpf_program *prog1; + struct bpf_program *prog2; + struct bpf_map *redir_map; + struct bpf_map *run_map; + int expect_errno; + struct inet_addr listen_at; +}; + +static void run_multi_prog_lookup(const struct test_multi_prog *t) +{ + struct sockaddr_storage dst = {}; + int map_fd, server_fd, client_fd; + struct bpf_link *link1, *link2; + int prog_idx, done, err; + + map_fd = bpf_map__fd(t->run_map); + + done = 0; + prog_idx = PROG1; + err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) + return; + prog_idx = PROG2; + err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) + return; + + link1 = attach_lookup_prog(t->prog1); + if (!link1) + return; + link2 = attach_lookup_prog(t->prog2); + if (!link2) + goto out_unlink1; + + server_fd = make_server(SOCK_STREAM, t->listen_at.ip, + t->listen_at.port, NULL); + if (server_fd < 0) + goto out_unlink2; + + err = update_lookup_map(t->redir_map, SERVER_A, server_fd); + if (err) + goto out_close_server; + + client_fd = make_socket(SOCK_STREAM, EXT_IP4, EXT_PORT, &dst); + if (client_fd < 0) + goto out_close_server; + + err = connect(client_fd, (void *)&dst, inetaddr_len(&dst)); + if (CHECK(err && !t->expect_errno, "connect", + "unexpected error %d\n", errno)) + goto out_close_client; + if (CHECK(err && t->expect_errno && errno != t->expect_errno, + "connect", "unexpected error %d\n", errno)) + goto out_close_client; + + done = 0; + prog_idx = PROG1; + err = bpf_map_lookup_elem(map_fd, &prog_idx, &done); + CHECK(err, "bpf_map_lookup_elem", "failed\n"); + CHECK(!done, "bpf_map_lookup_elem", "PROG1 !done\n"); + + done = 0; + prog_idx = PROG2; + err = bpf_map_lookup_elem(map_fd, &prog_idx, &done); + CHECK(err, "bpf_map_lookup_elem", "failed\n"); + CHECK(!done, "bpf_map_lookup_elem", "PROG2 !done\n"); + +out_close_client: + close(client_fd); +out_close_server: + close(server_fd); +out_unlink2: + bpf_link__destroy(link2); +out_unlink1: + bpf_link__destroy(link1); +} + +static void test_multi_prog_lookup(struct test_sk_lookup *skel) +{ + struct test_multi_prog tests[] = { + { + .desc = "multi prog - pass, pass", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "multi prog - drop, drop", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - pass, drop", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - drop, pass", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - pass, redir", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, pass", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - drop, redir", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, drop", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, redir", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + }; + struct test_multi_prog *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + t->redir_map = skel->maps.redir_map; + t->run_map = skel->maps.run_map; + if (test__start_subtest(t->desc)) + run_multi_prog_lookup(t); + } +} + +static void run_tests(struct test_sk_lookup *skel) +{ + if (test__start_subtest("query lookup prog")) + query_lookup_prog(skel); + test_redirect_lookup(skel); + test_drop_on_lookup(skel); + test_drop_on_reuseport(skel); + test_sk_assign_helper(skel); + test_multi_prog_lookup(skel); +} + +static int switch_netns(void) +{ + static const char * const setup_script[] = { + "ip -6 addr add dev lo " EXT_IP6 "/128", + "ip -6 addr add dev lo " INT_IP6 "/128", + "ip link set dev lo up", + NULL, + }; + const char * const *cmd; + int err; + + err = unshare(CLONE_NEWNET); + if (CHECK(err, "unshare", "failed\n")) { + log_err("unshare(CLONE_NEWNET)"); + return -1; + } + + for (cmd = setup_script; *cmd; cmd++) { + err = system(*cmd); + if (CHECK(err, "system", "failed\n")) { + log_err("system(%s)", *cmd); + return -1; + } + } + + return 0; +} + +void test_sk_lookup(void) +{ + struct test_sk_lookup *skel; + int err; + + err = switch_netns(); + if (err) + return; + + skel = test_sk_lookup__open_and_load(); + if (CHECK(!skel, "skel open_and_load", "failed\n")) + return; + + run_tests(skel); + + test_sk_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 7021b92af313..25de86af2d03 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,6 +11,7 @@ void test_skb_ctx(void) .cb[3] = 4, .cb[4] = 5, .priority = 6, + .ifindex = 1, .tstamp = 7, .wire_len = 100, .gso_segs = 8, @@ -92,6 +93,10 @@ void test_skb_ctx(void) "ctx_out_priority", "skb->priority == %d, expected %d\n", skb.priority, 7); + CHECK_ATTR(skb.ifindex != 1, + "ctx_out_ifindex", + "skb->ifindex == %d, expected %d\n", + skb.ifindex, 1); CHECK_ATTR(skb.tstamp != 8, "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index fa153cf67b1b..fe87b77af459 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -41,7 +41,7 @@ void test_skeleton(void) CHECK(bss->in4 != 0, "in4", "got %lld != exp %lld\n", bss->in4, 0LL); CHECK(bss->out4 != 0, "out4", "got %lld != exp %lld\n", bss->out4, 0LL); - CHECK(rodata->in6 != 0, "in6", "got %d != exp %d\n", rodata->in6, 0); + CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0); CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0); /* validate we can pre-setup global variables, even in .bss */ @@ -49,7 +49,7 @@ void test_skeleton(void) data->in2 = 11; bss->in3 = 12; bss->in4 = 13; - rodata->in6 = 14; + rodata->in.in6 = 14; err = test_skeleton__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) @@ -60,7 +60,7 @@ void test_skeleton(void) CHECK(data->in2 != 11, "in2", "got %lld != exp %lld\n", data->in2, 11LL); CHECK(bss->in3 != 12, "in3", "got %d != exp %d\n", bss->in3, 12); CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL); - CHECK(rodata->in6 != 14, "in6", "got %d != exp %d\n", rodata->in6, 14); + CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14); /* now set new values and attach to get them into outX variables */ data->in1 = 1; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 8547ecbdc61f..ec281b0363b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -193,11 +193,10 @@ static void run_test(int cgroup_fd) if (CHECK_FAIL(server_fd < 0)) goto close_bpf_object; + pthread_mutex_lock(&server_started_mtx); if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) goto close_server_fd; - - pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); pthread_mutex_unlock(&server_started_mtx); diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index 9013a0c01eed..d207e968e6b1 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -118,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd) goto close_bpf_object; } - client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd); + client_fd = connect_to_fd(server_fd, 0); if (client_fd < 0) { err = -1; goto close_bpf_object; @@ -161,7 +161,7 @@ void test_tcp_rtt(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server(AF_INET, SOCK_STREAM); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c new file mode 100644 index 000000000000..39b0decb1bb2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Oracle and/or its affiliates. */ + +#include <test_progs.h> + +#include "trace_printk.skel.h" + +#define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" +#define SEARCHMSG "testing,testing" + +void test_trace_printk(void) +{ + int err, iter = 0, duration = 0, found = 0; + struct trace_printk__bss *bss; + struct trace_printk *skel; + char *buf = NULL; + FILE *fp = NULL; + size_t buflen; + + skel = trace_printk__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + err = trace_printk__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + bss = skel->bss; + + err = trace_printk__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + fp = fopen(TRACEBUF, "r"); + if (CHECK(fp == NULL, "could not open trace buffer", + "error %d opening %s", errno, TRACEBUF)) + goto cleanup; + + /* We do not want to wait forever if this test fails... */ + fcntl(fileno(fp), F_SETFL, O_NONBLOCK); + + /* wait for tracepoint to trigger */ + usleep(1); + trace_printk__detach(skel); + + if (CHECK(bss->trace_printk_ran == 0, + "bpf_trace_printk never ran", + "ran == %d", bss->trace_printk_ran)) + goto cleanup; + + if (CHECK(bss->trace_printk_ret <= 0, + "bpf_trace_printk returned <= 0 value", + "got %d", bss->trace_printk_ret)) + goto cleanup; + + /* verify our search string is in the trace buffer */ + while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) { + if (strstr(buf, SEARCHMSG) != NULL) + found++; + if (found == bss->trace_printk_ran) + break; + if (++iter > 1000) + break; + } + + if (CHECK(!found, "message from bpf_trace_printk not found", + "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + goto cleanup; + +cleanup: + trace_printk__destroy(skel); + free(buf); + if (fp) + fclose(fp); +} diff --git a/tools/testing/selftests/bpf/prog_tests/udp_limit.c b/tools/testing/selftests/bpf/prog_tests/udp_limit.c new file mode 100644 index 000000000000..2aba09d4d01b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/udp_limit.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "udp_limit.skel.h" + +#include <sys/types.h> +#include <sys/socket.h> + +static int duration; + +void test_udp_limit(void) +{ + struct udp_limit *skel; + int fd1 = -1, fd2 = -1; + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/udp_limit"); + if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) + return; + + skel = udp_limit__open_and_load(); + if (CHECK(!skel, "skel-load", "errno %d", errno)) + goto close_cgroup_fd; + + skel->links.sock = bpf_program__attach_cgroup(skel->progs.sock, cgroup_fd); + skel->links.sock_release = bpf_program__attach_cgroup(skel->progs.sock_release, cgroup_fd); + if (CHECK(IS_ERR(skel->links.sock) || IS_ERR(skel->links.sock_release), + "cg-attach", "sock %ld sock_release %ld", + PTR_ERR(skel->links.sock), + PTR_ERR(skel->links.sock_release))) + goto close_skeleton; + + /* BPF program enforces a single UDP socket per cgroup, + * verify that. + */ + fd1 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd1 < 0, "fd1", "errno %d", errno)) + goto close_skeleton; + + fd2 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd2 >= 0, "fd2", "errno %d", errno)) + goto close_skeleton; + + /* We can reopen again after close. */ + close(fd1); + fd1 = -1; + + fd1 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd1 < 0, "fd1-again", "errno %d", errno)) + goto close_skeleton; + + /* Make sure the program was invoked the expected + * number of times: + * - open fd1 - BPF_CGROUP_INET_SOCK_CREATE + * - attempt to openfd2 - BPF_CGROUP_INET_SOCK_CREATE + * - close fd1 - BPF_CGROUP_INET_SOCK_RELEASE + * - open fd1 again - BPF_CGROUP_INET_SOCK_CREATE + */ + if (CHECK(skel->bss->invocations != 4, "bss-invocations", + "invocations=%d", skel->bss->invocations)) + goto close_skeleton; + + /* We should still have a single socket in use */ + if (CHECK(skel->bss->in_use != 1, "bss-in_use", + "in_use=%d", skel->bss->in_use)) + goto close_skeleton; + +close_skeleton: + if (fd1 >= 0) + close(fd1); + if (fd2 >= 0) + close(fd2); + udp_limit__destroy(skel); +close_cgroup_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c new file mode 100644 index 000000000000..c75525eab02c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include <time.h> +#include "test_varlen.skel.h" + +#define CHECK_VAL(got, exp) \ + CHECK((got) != (exp), "check", "got %ld != exp %ld\n", \ + (long)(got), (long)(exp)) + +void test_varlen(void) +{ + int duration = 0, err; + struct test_varlen* skel; + struct test_varlen__bss *bss; + struct test_varlen__data *data; + const char str1[] = "Hello, "; + const char str2[] = "World!"; + const char exp_str[] = "Hello, \0World!\0"; + const int size1 = sizeof(str1); + const int size2 = sizeof(str2); + + skel = test_varlen__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + bss = skel->bss; + data = skel->data; + + err = test_varlen__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + bss->test_pid = getpid(); + + /* trigger everything */ + memcpy(bss->buf_in1, str1, size1); + memcpy(bss->buf_in2, str2, size2); + bss->capture = true; + usleep(1); + bss->capture = false; + + CHECK_VAL(bss->payload1_len1, size1); + CHECK_VAL(bss->payload1_len2, size2); + CHECK_VAL(bss->total1, size1 + size2); + CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check", + "doesn't match!"); + + CHECK_VAL(data->payload2_len1, size1); + CHECK_VAL(data->payload2_len2, size2); + CHECK_VAL(data->total2, size1 + size2); + CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", + "doesn't match!"); + + CHECK_VAL(data->payload3_len1, size1); + CHECK_VAL(data->payload3_len2, size2); + CHECK_VAL(data->total3, size1 + size2); + CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check", + "doesn't match!"); + + CHECK_VAL(data->payload4_len1, size1); + CHECK_VAL(data->payload4_len2, size2); + CHECK_VAL(data->total4, size1 + size2); + CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check", + "doesn't match!"); +cleanup: + test_varlen__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c new file mode 100644 index 000000000000..0176573fe4e7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/bpf.h> +#include <linux/if_link.h> +#include <test_progs.h> + +#include "test_xdp_with_cpumap_helpers.skel.h" + +#define IFINDEX_LO 1 + +void test_xdp_with_cpumap_helpers(void) +{ + struct test_xdp_with_cpumap_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_cpumap_val val = { + .qsize = 192, + }; + __u32 duration = 0, idx = 0; + __u32 len = sizeof(info); + int err, prog_fd, map_fd; + + skel = test_xdp_with_cpumap_helpers__open_and_load(); + if (CHECK_FAIL(!skel)) { + perror("test_xdp_with_cpumap_helpers__open_and_load"); + return; + } + + /* can not attach program with cpumaps that allow programs + * as xdp generic + */ + prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Generic attach of program with 8-byte CPUMAP", + "should have failed\n"); + + prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); + if (CHECK_FAIL(err)) + goto out_close; + + val.bpf_prog.fd = prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err, "Add program to cpumap entry", "err %d errno %d\n", + err, errno); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + CHECK(err, "Read cpumap entry", "err %d errno %d\n", err, errno); + CHECK(info.id != val.bpf_prog.id, "Expected program id in cpumap entry", + "expected %u read %u\n", info.id, val.bpf_prog.id); + + /* can not attach BPF_XDP_CPUMAP program to a device */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Attach of BPF_XDP_CPUMAP program", + "should have failed\n"); + + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err == 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry", + "should have failed\n"); + +out_close: + test_xdp_with_cpumap_helpers__destroy(skel); +} + +void test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("cpumap_with_progs")) + test_xdp_with_cpumap_helpers(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c new file mode 100644 index 000000000000..6f814999b395 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <uapi/linux/if_link.h> +#include <test_progs.h> +#include "test_xdp_link.skel.h" + +#define IFINDEX_LO 1 + +void test_xdp_link(void) +{ + __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err; + DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); + struct test_xdp_link *skel1 = NULL, *skel2 = NULL; + struct bpf_link_info link_info; + struct bpf_prog_info prog_info; + struct bpf_link *link; + __u32 link_info_len = sizeof(link_info); + __u32 prog_info_len = sizeof(prog_info); + + skel1 = test_xdp_link__open_and_load(); + if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n")) + goto cleanup; + prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler); + + skel2 = test_xdp_link__open_and_load(); + if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n")) + goto cleanup; + prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler); + + memset(&prog_info, 0, sizeof(prog_info)); + err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len); + if (CHECK(err, "fd_info1", "failed %d\n", -errno)) + goto cleanup; + id1 = prog_info.id; + + memset(&prog_info, 0, sizeof(prog_info)); + err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len); + if (CHECK(err, "fd_info2", "failed %d\n", -errno)) + goto cleanup; + id2 = prog_info.id; + + /* set initial prog attachment */ + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); + if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err)) + goto cleanup; + + /* validate prog ID */ + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err); + + /* BPF link is not allowed to replace prog attachment */ + link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); + if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + bpf_link__destroy(link); + /* best-effort detach prog */ + opts.old_fd = prog_fd1; + bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + goto cleanup; + } + + /* detach BPF program */ + opts.old_fd = prog_fd1; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + if (CHECK(err, "prog_detach", "failed %d\n", err)) + goto cleanup; + + /* now BPF link should attach successfully */ + link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); + if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + goto cleanup; + skel1->links.xdp_handler = link; + + /* validate prog ID */ + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err)) + goto cleanup; + + /* BPF prog attach is not allowed to replace BPF link */ + opts.old_fd = prog_fd1; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); + if (CHECK(!err, "prog_attach_fail", "unexpected success\n")) + goto cleanup; + + /* Can't force-update when BPF link is active */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0); + if (CHECK(!err, "prog_update_fail", "unexpected success\n")) + goto cleanup; + + /* Can't force-detach when BPF link is active */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + if (CHECK(!err, "prog_detach_fail", "unexpected success\n")) + goto cleanup; + + /* BPF link is not allowed to replace another BPF link */ + link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); + if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + bpf_link__destroy(link); + goto cleanup; + } + + bpf_link__destroy(skel1->links.xdp_handler); + skel1->links.xdp_handler = NULL; + + /* new link attach should succeed */ + link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); + if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + goto cleanup; + skel2->links.xdp_handler = link; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id2, "id2_check", + "loaded prog id %u != id2 %u, err %d", id0, id1, err)) + goto cleanup; + + /* updating program under active BPF link works as expected */ + err = bpf_link__update_program(link, skel1->progs.xdp_handler); + if (CHECK(err, "link_upd", "failed: %d\n", err)) + goto cleanup; + + memset(&link_info, 0, sizeof(link_info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + if (CHECK(err, "link_info", "failed: %d\n", err)) + goto cleanup; + + CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type", + "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP); + CHECK(link_info.prog_id != id1, "link_prog_id", + "got %u != exp %u\n", link_info.prog_id, id1); + CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex", + "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO); + + err = bpf_link__detach(link); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto cleanup; + + memset(&link_info, 0, sizeof(link_info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + if (CHECK(err, "link_info", "failed: %d\n", err)) + goto cleanup; + CHECK(link_info.prog_id != id1, "link_prog_id", + "got %u != exp %u\n", link_info.prog_id, id1); + /* ifindex should be zeroed out */ + CHECK(link_info.xdp.ifindex != 0, "link_ifindex", + "got %u != exp %u\n", link_info.xdp.ifindex, 0); + +cleanup: + test_xdp_link__destroy(skel1); + test_xdp_link__destroy(skel2); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h new file mode 100644 index 000000000000..c196280df90d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +/* "undefine" structs in vmlinux.h, because we "override" them below */ +#define bpf_iter_meta bpf_iter_meta___not_used +#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used +#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used +#define bpf_iter__netlink bpf_iter__netlink___not_used +#define bpf_iter__task bpf_iter__task___not_used +#define bpf_iter__task_file bpf_iter__task_file___not_used +#define bpf_iter__tcp bpf_iter__tcp___not_used +#define tcp6_sock tcp6_sock___not_used +#define bpf_iter__udp bpf_iter__udp___not_used +#define udp6_sock udp6_sock___not_used +#define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used +#define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used +#include "vmlinux.h" +#undef bpf_iter_meta +#undef bpf_iter__bpf_map +#undef bpf_iter__ipv6_route +#undef bpf_iter__netlink +#undef bpf_iter__task +#undef bpf_iter__task_file +#undef bpf_iter__tcp +#undef tcp6_sock +#undef bpf_iter__udp +#undef udp6_sock +#undef bpf_iter__bpf_map_elem +#undef bpf_iter__bpf_sk_storage_map + +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +} __attribute__((preserve_access_index)); + +struct bpf_iter__ipv6_route { + struct bpf_iter_meta *meta; + struct fib6_info *rt; +} __attribute__((preserve_access_index)); + +struct bpf_iter__netlink { + struct bpf_iter_meta *meta; + struct netlink_sock *sk; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task { + struct bpf_iter_meta *meta; + struct task_struct *task; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task_file { + struct bpf_iter_meta *meta; + struct task_struct *task; + __u32 fd; + struct file *file; +} __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; +} __attribute__((preserve_access_index)); + +struct bpf_iter__tcp { + struct bpf_iter_meta *meta; + struct sock_common *sk_common; + uid_t uid; +} __attribute__((preserve_access_index)); + +struct tcp6_sock { + struct tcp_sock tcp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); + +struct bpf_iter__udp { + struct bpf_iter_meta *meta; + struct udp_sock *udp_sk; + uid_t uid __attribute__((aligned(8))); + int bucket __attribute__((aligned(8))); +} __attribute__((preserve_access_index)); + +struct udp6_sock { + struct udp_sock udp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map_elem { + struct bpf_iter_meta *meta; + struct bpf_map *map; + void *key; + void *value; +}; + +struct bpf_iter__bpf_sk_storage_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; + struct sock *sk; + void *value; +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c new file mode 100644 index 000000000000..6286023fd62b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} arraymap1 SEC(".maps"); + +__u32 key_sum = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *key = ctx->key; + __u64 *val = ctx->value; + + if (key == (void *)0 || val == (void *)0) + return 0; + + bpf_seq_write(ctx->meta->seq, key, sizeof(__u32)); + bpf_seq_write(ctx->meta->seq, val, sizeof(__u64)); + key_sum += *key; + val_sum += *val; + *val = *key; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c new file mode 100644 index 000000000000..07ddbfdbcab7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, __u64); + __type(value, __u64); +} hashmap2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap3 SEC(".maps"); + +/* will set before prog run */ +bool in_test_mode = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u32 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + struct key_t *key = ctx->key; + __u64 *val = ctx->value; + + if (in_test_mode) { + /* test mode is used by selftests to + * test functionality of bpf_hash_map iter. + * + * the above hashmap1 will have correct size + * and will be accepted, hashmap2 and hashmap3 + * should be rejected due to smaller key/value + * size. + */ + if (key == (void *)0 || val == (void *)0) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + val_sum += *val; + return 0; + } + + /* non-test mode, the map is prepared with the + * below bpftool command sequence: + * bpftool map create /sys/fs/bpf/m1 type hash \ + * key 12 value 8 entries 3 name map1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 1 \ + * value 0 0 0 1 0 0 0 1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 2 \ + * value 0 0 0 1 0 0 0 2 + * The bpftool iter command line: + * bpftool iter pin ./bpf_iter_bpf_hash_map.o /sys/fs/bpf/p1 \ + * map id 77 + * The below output will be: + * map dump starts + * 77: (1000000 0 2000000) (200000001000000) + * 77: (1000000 0 1000000) (100000001000000) + * map dump ends + */ + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, "map dump starts\n"); + + if (key == (void *)0 || val == (void *)0) { + BPF_SEQ_PRINTF(seq, "map dump ends\n"); + return 0; + } + + BPF_SEQ_PRINTF(seq, "%d: (%x %d %x) (%llx)\n", map->id, + key->a, key->b, key->c, *val); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c index b57bd6fef208..08651b23edba 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -1,27 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__bpf_map +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__bpf_map { - struct bpf_iter_meta *meta; - struct bpf_map *map; -} __attribute__((preserve_access_index)); - SEC("iter/bpf_map") int dump_bpf_map(struct bpf_iter__bpf_map *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c new file mode 100644 index 000000000000..85fa710fad90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u32); +} arraymap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +__u32 key_sum = 0, val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum += *key; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c new file mode 100644 index 000000000000..feaaa2b89c57 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u32 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct key_t *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c new file mode 100644 index 000000000000..6b70ccaba301 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +__u32 val_sum = 0; +__u32 ipv6_sk_count = 0; + +SEC("iter/bpf_sk_storage_map") +int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + struct sock *sk = ctx->sk; + __u32 *val = ctx->value; + + if (sk == (void *)0 || val == (void *)0) + return 0; + + if (sk->sk_family == AF_INET6) + ipv6_sk_count++; + + val_sum += *val; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c index c8e9ca74c87b..d58d9f1642b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -1,35 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__ipv6_route +#include "bpf_iter.h" +#include "bpf_tracing_net.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__ipv6_route { - struct bpf_iter_meta *meta; - struct fib6_info *rt; -} __attribute__((preserve_access_index)); - char _license[] SEC("license") = "GPL"; extern bool CONFIG_IPV6_SUBTREES __kconfig __weak; -#define RTF_GATEWAY 0x0002 -#define IFNAMSIZ 16 -#define fib_nh_gw_family nh_common.nhc_gw_family -#define fib_nh_gw6 nh_common.nhc_gw.ipv6 -#define fib_nh_dev nh_common.nhc_dev - SEC("iter/ipv6_route") int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index 75ecf956a2df..95989f4c99b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -1,30 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__netlink bpf_iter__netlink___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__netlink +#include "bpf_iter.h" +#include "bpf_tracing_net.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; -#define sk_rmem_alloc sk_backlog.rmem_alloc -#define sk_refcnt __sk_common.skc_refcnt - -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__netlink { - struct bpf_iter_meta *meta; - struct netlink_sock *sk; -} __attribute__((preserve_access_index)); - static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; @@ -54,10 +36,10 @@ int dump_netlink(struct bpf_iter__netlink *ctx) if (!nlk->groups) { group = 0; } else { - /* FIXME: temporary use bpf_probe_read here, needs + /* FIXME: temporary use bpf_probe_read_kernel here, needs * verifier support to do direct access. */ - bpf_probe_read(&group, sizeof(group), &nlk->groups[0]); + bpf_probe_read_kernel(&group, sizeof(group), &nlk->groups[0]); } BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ", nlk->portid, (u32)group, @@ -74,7 +56,7 @@ int dump_netlink(struct bpf_iter__netlink *ctx) * with current verifier. */ inode = SOCK_INODE(sk); - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); } BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index ee754021f98e..4983087852a0 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -1,27 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c index 0f0ec3db20ba..8b787baa2654 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c @@ -1,29 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task_file bpf_iter__task_file___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task_file +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task_file { - struct bpf_iter_meta *meta; - struct task_struct *task; - __u32 fd; - struct file *file; -} __attribute__((preserve_access_index)); - SEC("iter/task_file") int dump_task_file(struct bpf_iter__task_file *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c new file mode 100644 index 000000000000..50e59a2e142e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define MAX_STACK_TRACE_DEPTH 64 +unsigned long entries[MAX_STACK_TRACE_DEPTH] = {}; +#define SIZE_OF_ULONG (sizeof(unsigned long)) + +SEC("iter/task") +int dump_task_stack(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + long i, retlen; + + if (task == (void *)0) + return 0; + + retlen = bpf_get_task_stack(task, entries, + MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, 0); + if (retlen < 0) + return 0; + + BPF_SEQ_PRINTF(seq, "pid: %8u num_entries: %8u\n", task->pid, + retlen / SIZE_OF_ULONG); + for (i = 0; i < MAX_STACK_TRACE_DEPTH; i++) { + if (retlen > i * SIZE_OF_ULONG) + BPF_SEQ_PRINTF(seq, "[<0>] %pB\n", (void *)entries[i]); + } + BPF_SEQ_PRINTF(seq, "\n"); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c new file mode 100644 index 000000000000..54380c5e1069 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + __be32 dest, src; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->rcv_nxt - tp->copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, destp, destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->write_seq - tp->snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + __u16 destp, srcp; + __be32 dest, src; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = tw->tw_daddr; + src = tw->tw_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, irsk->ir_loc_addr, + irsk->ir_num, irsk->ir_rmt_addr, + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp4(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "rem_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET) + return 0; + + tp = bpf_skc_to_tcp_sock(sk_common); + if (tp) + return dump_tcp_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c new file mode 100644 index 000000000000..b4fbddfa4e10 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct in6_addr *dest, *src; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->tcp.inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->tcp.rcv_nxt - tp->tcp.copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->tcp.write_seq - tp->tcp.snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->tcp.snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(&tp->tcp) ? -1 + : tp->tcp.snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + const struct in6_addr *dest, *src; + __u16 destp, srcp; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + struct in6_addr *src, *dest; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + src = &irsk->ir_v6_loc_addr; + dest = &irsk->ir_v6_rmt_addr; + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], + irsk->ir_num, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp6(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp6_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "remote_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET6) + return 0; + + tp = bpf_skc_to_tcp6_sock(sk_common); + if (tp) + return dump_tcp6_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c index 13c2c90c835f..2a4647f20c46 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c @@ -1,25 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c index 0aa71b333cf3..ee49493dc125 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -1,25 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__bpf_map +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__bpf_map { - struct bpf_iter_meta *meta; - struct bpf_map *map; -} __attribute__((preserve_access_index)); - __u32 map1_id = 0, map2_id = 0; __u32 map1_accessed = 0, map2_accessed = 0; __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c new file mode 100644 index 000000000000..e3a7575e81d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +__u32 key_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *key = ctx->key; + + if (key == (void *)0) + return 0; + + /* out of bound access w.r.t. hashmap1 */ + key_sum += *(__u32 *)(key + sizeof(struct key_t)); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c new file mode 100644 index 000000000000..1c7304f56b1e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 value_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *value = ctx->value; + + if (value == (void *)0) + return 0; + + /* negative offset, verifier failure. */ + value_sum += *(__u32 *)(value - 4); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h index dee1339e6905..d5e3df66ad9a 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h @@ -1,27 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; int count = 0; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c new file mode 100644 index 000000000000..f258583afbbd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp4(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __be32 dest, src; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, + " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode ref pointer drops\n"); + + /* filter out udp6 sockets */ + inet = &udp_sk->inet; + if (inet->sk.sk_family == AF_INET6) + return 0; + + inet = &udp_sk->inet; + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + + BPF_SEQ_PRINTF(seq, "%5d: %08X:%04X %08X:%04X ", + ctx->bucket, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c new file mode 100644 index 000000000000..65f93bb03f0f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; + +#define IPV6_SEQ_DGRAM_HEADER \ + " sl " \ + "local_address " \ + "remote_address " \ + "st tx_queue rx_queue tr tm->when retrnsmt" \ + " uid timeout inode ref pointer drops\n" + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp6(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + const struct in6_addr *dest, *src; + struct udp6_sock *udp6_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, IPV6_SEQ_DGRAM_HEADER); + + udp6_sk = bpf_skc_to_udp6_sock(udp_sk); + if (udp6_sk == (void *)0) + return 0; + + inet = &udp_sk->inet; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + dest = &inet->sk.sk_v6_daddr; + src = &inet->sk.sk_v6_rcv_saddr; + + BPF_SEQ_PRINTF(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + ctx->bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h new file mode 100644 index 000000000000..01378911252b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_NET_H__ +#define __BPF_TRACING_NET_H__ + +#define AF_INET 2 +#define AF_INET6 10 + +#define ICSK_TIME_RETRANS 1 +#define ICSK_TIME_PROBE0 3 +#define ICSK_TIME_LOSS_PROBE 5 +#define ICSK_TIME_REO_TIMEOUT 6 + +#define IFNAMSIZ 16 + +#define RTF_GATEWAY 0x0002 + +#define TCP_INFINITE_SSTHRESH 0x7fffffff +#define TCP_PINGPONG_THRESH 3 + +#define fib_nh_dev nh_common.nhc_dev +#define fib_nh_gw_family nh_common.nhc_gw_family +#define fib_nh_gw6 nh_common.nhc_gw.ipv6 + +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr +#define inet_dport sk.__sk_common.skc_dport + +#define ir_loc_addr req.__req_common.skc_rcv_saddr +#define ir_num req.__req_common.skc_num +#define ir_rmt_addr req.__req_common.skc_daddr +#define ir_rmt_port req.__req_common.skc_dport +#define ir_v6_rmt_addr req.__req_common.skc_v6_daddr +#define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr + +#define sk_family __sk_common.skc_family +#define sk_rmem_alloc sk_backlog.rmem_alloc +#define sk_refcnt __sk_common.skc_refcnt +#define sk_state __sk_common.skc_state +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr + +#define s6_addr32 in6_u.u6_addr32 + +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr +#define tw_dport __tw_common.skc_dport +#define tw_refcnt __tw_common.skc_refcnt +#define tw_v6_daddr __tw_common.skc_v6_daddr +#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr + +#endif diff --git a/tools/testing/selftests/bpf/progs/btf_data.c b/tools/testing/selftests/bpf/progs/btf_data.c new file mode 100644 index 000000000000..baa525275bde --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_data.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +struct S { + int a; + int b; + int c; +}; + +union U { + int a; + int b; + int c; +}; + +struct S1 { + int a; + int b; + int c; +}; + +union U1 { + int a; + int b; + int c; +}; + +typedef int T; +typedef int S; +typedef int U; +typedef int T1; +typedef int S1; +typedef int U1; + +struct root_struct { + S m_1; + T m_2; + U m_3; + S1 m_4; + T1 m_5; + U1 m_6; + struct S m_7; + struct S1 m_8; + union U m_9; + union U1 m_10; +}; + +int func(struct root_struct *root) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h new file mode 100644 index 000000000000..a0778fe7857a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PROGS_CG_STORAGE_MULTI_H +#define __PROGS_CG_STORAGE_MULTI_H + +#include <asm/types.h> + +struct cgroup_value { + __u32 egress_pkts; + __u32 ingress_pkts; +}; + +#endif diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c new file mode 100644 index 000000000000..44ad46b33539 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c new file mode 100644 index 000000000000..a25373002055 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress/1") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress/2") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c new file mode 100644 index 000000000000..a149f33bc533 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, __u64); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress/1") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress/2") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 1ab2c5eba86c..b1b2773c0b9d 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -104,6 +104,30 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx) return 0; } +static __inline int set_keepalive(struct bpf_sock_addr *ctx) +{ + int zero = 0, one = 1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one))) + return 1; + if (ctx->type == SOCK_STREAM) { + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one))) + return 1; + } + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero))) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -121,6 +145,9 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) if (bind_to_device(ctx)) return 0; + if (set_keepalive(ctx)) + return 0; + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) return 0; else if (ctx->type == SOCK_STREAM) diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c new file mode 100644 index 000000000000..473665cac67e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define LOOP_BOUND 0xf +#define MAX_ENTRIES 8 +#define HALF_ENTRIES (MAX_ENTRIES >> 1) + +_Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND"); + +enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC; +__u32 g_line = 0; + +#define VERIFY_TYPE(type, func) ({ \ + g_map_type = type; \ + if (!func()) \ + return 0; \ +}) + + +#define VERIFY(expr) ({ \ + g_line = __LINE__; \ + if (!(expr)) \ + return 0; \ +}) + +struct bpf_map_memory { + __u32 pages; +} __attribute__((preserve_access_index)); + +struct bpf_map { + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 id; + struct bpf_map_memory memory; +} __attribute__((preserve_access_index)); + +static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, + __u32 value_size, __u32 max_entries) +{ + VERIFY(map->map_type == g_map_type); + VERIFY(map->key_size == key_size); + VERIFY(map->value_size == value_size); + VERIFY(map->max_entries == max_entries); + VERIFY(map->id > 0); + VERIFY(map->memory.pages > 0); + + return 1; +} + +static inline int check_bpf_map_ptr(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(indirect->map_type == direct->map_type); + VERIFY(indirect->key_size == direct->key_size); + VERIFY(indirect->value_size == direct->value_size); + VERIFY(indirect->max_entries == direct->max_entries); + VERIFY(indirect->id == direct->id); + VERIFY(indirect->memory.pages == direct->memory.pages); + + return 1; +} + +static inline int check(struct bpf_map *indirect, struct bpf_map *direct, + __u32 key_size, __u32 value_size, __u32 max_entries) +{ + VERIFY(check_bpf_map_ptr(indirect, direct)); + VERIFY(check_bpf_map_fields(indirect, key_size, value_size, + max_entries)); + return 1; +} + +static inline int check_default(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32), + MAX_ENTRIES)); + return 1; +} + +typedef struct { + int counter; +} atomic_t; + +struct bpf_htab { + struct bpf_map map; + atomic_t count; + __u32 n_buckets; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); /* to test bpf_htab.count */ + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_hash SEC(".maps"); + +static inline int check_hash(void) +{ + struct bpf_htab *hash = (struct bpf_htab *)&m_hash; + struct bpf_map *map = (struct bpf_map *)&m_hash; + int i; + + VERIFY(check_default(&hash->map, map)); + + VERIFY(hash->n_buckets == MAX_ENTRIES); + VERIFY(hash->elem_size == 64); + + VERIFY(hash->count.counter == 0); + for (i = 0; i < HALF_ENTRIES; ++i) { + const __u32 key = i; + const __u32 val = 1; + + if (bpf_map_update_elem(hash, &key, &val, 0)) + return 0; + } + VERIFY(hash->count.counter == HALF_ENTRIES); + + return 1; +} + +struct bpf_array { + struct bpf_map map; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_array SEC(".maps"); + +static inline int check_array(void) +{ + struct bpf_array *array = (struct bpf_array *)&m_array; + struct bpf_map *map = (struct bpf_map *)&m_array; + int i, n_lookups = 0, n_keys = 0; + + VERIFY(check_default(&array->map, map)); + + VERIFY(array->elem_size == 8); + + for (i = 0; i < array->map.max_entries && i < LOOP_BOUND; ++i) { + const __u32 key = i; + __u32 *val = bpf_map_lookup_elem(array, &key); + + ++n_lookups; + if (val) + ++n_keys; + } + + VERIFY(n_lookups == MAX_ENTRIES); + VERIFY(n_keys == MAX_ENTRIES); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_prog_array SEC(".maps"); + +static inline int check_prog_array(void) +{ + struct bpf_array *prog_array = (struct bpf_array *)&m_prog_array; + struct bpf_map *map = (struct bpf_map *)&m_prog_array; + + VERIFY(check_default(&prog_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_perf_event_array SEC(".maps"); + +static inline int check_perf_event_array(void) +{ + struct bpf_array *perf_event_array = (struct bpf_array *)&m_perf_event_array; + struct bpf_map *map = (struct bpf_map *)&m_perf_event_array; + + VERIFY(check_default(&perf_event_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_hash SEC(".maps"); + +static inline int check_percpu_hash(void) +{ + struct bpf_htab *percpu_hash = (struct bpf_htab *)&m_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_percpu_hash; + + VERIFY(check_default(&percpu_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_array SEC(".maps"); + +static inline int check_percpu_array(void) +{ + struct bpf_array *percpu_array = (struct bpf_array *)&m_percpu_array; + struct bpf_map *map = (struct bpf_map *)&m_percpu_array; + + VERIFY(check_default(&percpu_array->map, map)); + + return 1; +} + +struct bpf_stack_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u64); +} m_stack_trace SEC(".maps"); + +static inline int check_stack_trace(void) +{ + struct bpf_stack_map *stack_trace = + (struct bpf_stack_map *)&m_stack_trace; + struct bpf_map *map = (struct bpf_map *)&m_stack_trace; + + VERIFY(check(&stack_trace->map, map, sizeof(__u32), sizeof(__u64), + MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cgroup_array SEC(".maps"); + +static inline int check_cgroup_array(void) +{ + struct bpf_array *cgroup_array = (struct bpf_array *)&m_cgroup_array; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_array; + + VERIFY(check_default(&cgroup_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_hash SEC(".maps"); + +static inline int check_lru_hash(void) +{ + struct bpf_htab *lru_hash = (struct bpf_htab *)&m_lru_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_hash; + + VERIFY(check_default(&lru_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_percpu_hash SEC(".maps"); + +static inline int check_lru_percpu_hash(void) +{ + struct bpf_htab *lru_percpu_hash = (struct bpf_htab *)&m_lru_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_percpu_hash; + + VERIFY(check_default(&lru_percpu_hash->map, map)); + + return 1; +} + +struct lpm_trie { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct lpm_key { + struct bpf_lpm_trie_key trie_key; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); + __type(key, struct lpm_key); + __type(value, __u32); +} m_lpm_trie SEC(".maps"); + +static inline int check_lpm_trie(void) +{ + struct lpm_trie *lpm_trie = (struct lpm_trie *)&m_lpm_trie; + struct bpf_map *map = (struct bpf_map *)&m_lpm_trie; + + VERIFY(check(&lpm_trie->map, map, sizeof(struct lpm_key), sizeof(__u32), + MAX_ENTRIES)); + + return 1; +} + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); + }); +} m_array_of_maps SEC(".maps") = { + .values = { (void *)&inner_map, 0, 0, 0, 0, 0, 0, 0, 0 }, +}; + +static inline int check_array_of_maps(void) +{ + struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_array_of_maps; + + VERIFY(check_default(&array_of_maps->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct inner_map); +} m_hash_of_maps SEC(".maps") = { + .values = { + [2] = &inner_map, + }, +}; + +static inline int check_hash_of_maps(void) +{ + struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps; + + VERIFY(check_default(&hash_of_maps->map, map)); + + return 1; +} + +struct bpf_dtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap SEC(".maps"); + +static inline int check_devmap(void) +{ + struct bpf_dtab *devmap = (struct bpf_dtab *)&m_devmap; + struct bpf_map *map = (struct bpf_map *)&m_devmap; + + VERIFY(check_default(&devmap->map, map)); + + return 1; +} + +struct bpf_stab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockmap SEC(".maps"); + +static inline int check_sockmap(void) +{ + struct bpf_stab *sockmap = (struct bpf_stab *)&m_sockmap; + struct bpf_map *map = (struct bpf_map *)&m_sockmap; + + VERIFY(check_default(&sockmap->map, map)); + + return 1; +} + +struct bpf_cpu_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cpumap SEC(".maps"); + +static inline int check_cpumap(void) +{ + struct bpf_cpu_map *cpumap = (struct bpf_cpu_map *)&m_cpumap; + struct bpf_map *map = (struct bpf_map *)&m_cpumap; + + VERIFY(check_default(&cpumap->map, map)); + + return 1; +} + +struct xsk_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_xskmap SEC(".maps"); + +static inline int check_xskmap(void) +{ + struct xsk_map *xskmap = (struct xsk_map *)&m_xskmap; + struct bpf_map *map = (struct bpf_map *)&m_xskmap; + + VERIFY(check_default(&xskmap->map, map)); + + return 1; +} + +struct bpf_shtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockhash SEC(".maps"); + +static inline int check_sockhash(void) +{ + struct bpf_shtab *sockhash = (struct bpf_shtab *)&m_sockhash; + struct bpf_map *map = (struct bpf_map *)&m_sockhash; + + VERIFY(check_default(&sockhash->map, map)); + + return 1; +} + +struct bpf_cgroup_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_cgroup_storage SEC(".maps"); + +static inline int check_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_storage; + + VERIFY(check(&cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct reuseport_array { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_reuseport_sockarray SEC(".maps"); + +static inline int check_reuseport_sockarray(void) +{ + struct reuseport_array *reuseport_sockarray = + (struct reuseport_array *)&m_reuseport_sockarray; + struct bpf_map *map = (struct bpf_map *)&m_reuseport_sockarray; + + VERIFY(check_default(&reuseport_sockarray->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_percpu_cgroup_storage SEC(".maps"); + +static inline int check_percpu_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *percpu_cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_percpu_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_percpu_cgroup_storage; + + VERIFY(check(&percpu_cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct bpf_queue_stack { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_queue SEC(".maps"); + +static inline int check_queue(void) +{ + struct bpf_queue_stack *queue = (struct bpf_queue_stack *)&m_queue; + struct bpf_map *map = (struct bpf_map *)&m_queue; + + VERIFY(check(&queue->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_STACK); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_stack SEC(".maps"); + +static inline int check_stack(void) +{ + struct bpf_queue_stack *stack = (struct bpf_queue_stack *)&m_stack; + struct bpf_map *map = (struct bpf_map *)&m_stack; + + VERIFY(check(&stack->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct bpf_sk_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, __u32); + __type(value, __u32); +} m_sk_storage SEC(".maps"); + +static inline int check_sk_storage(void) +{ + struct bpf_sk_storage_map *sk_storage = + (struct bpf_sk_storage_map *)&m_sk_storage; + struct bpf_map *map = (struct bpf_map *)&m_sk_storage; + + VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap_hash SEC(".maps"); + +static inline int check_devmap_hash(void) +{ + struct bpf_dtab *devmap_hash = (struct bpf_dtab *)&m_devmap_hash; + struct bpf_map *map = (struct bpf_map *)&m_devmap_hash; + + VERIFY(check_default(&devmap_hash->map, map)); + + return 1; +} + +struct bpf_ringbuf_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} m_ringbuf SEC(".maps"); + +static inline int check_ringbuf(void) +{ + struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf; + struct bpf_map *map = (struct bpf_map *)&m_ringbuf; + + VERIFY(check(&ringbuf->map, map, 0, 0, 1 << 12)); + + return 1; +} + +SEC("cgroup_skb/egress") +int cg_skb(void *ctx) +{ + VERIFY_TYPE(BPF_MAP_TYPE_HASH, check_hash); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY, check_array); + VERIFY_TYPE(BPF_MAP_TYPE_PROG_ARRAY, check_prog_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, check_perf_event_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_HASH, check_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, check_percpu_array); + VERIFY_TYPE(BPF_MAP_TYPE_STACK_TRACE, check_stack_trace); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, check_cgroup_array); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_HASH, check_lru_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, check_lru_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LPM_TRIE, check_lpm_trie); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, check_array_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, check_hash_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP, check_devmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKMAP, check_sockmap); + VERIFY_TYPE(BPF_MAP_TYPE_CPUMAP, check_cpumap); + VERIFY_TYPE(BPF_MAP_TYPE_XSKMAP, check_xskmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKHASH, check_sockhash); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, check_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + check_reuseport_sockarray); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + check_percpu_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_QUEUE, check_queue); + VERIFY_TYPE(BPF_MAP_TYPE_STACK, check_stack); + VERIFY_TYPE(BPF_MAP_TYPE_SK_STORAGE, check_sk_storage); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, check_devmap_hash); + VERIFY_TYPE(BPF_MAP_TYPE_RINGBUF, check_ringbuf); + + return 1; +} + +__u32 _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c new file mode 100644 index 000000000000..25467d13c356 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16384); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(stack_trace_t)); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, stack_trace_t); +} stackdata_map SEC(".maps"); + +long stackid_kernel = 1; +long stackid_user = 1; +long stack_kernel = 1; +long stack_user = 1; + +SEC("perf_event") +int oncpu(void *ctx) +{ + stack_trace_t *trace; + __u32 key = 0; + long val; + + val = bpf_get_stackid(ctx, &stackmap, 0); + if (val > 0) + stackid_kernel = 2; + val = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK); + if (val > 0) + stackid_user = 2; + + trace = bpf_map_lookup_elem(&stackdata_map, &key); + if (!trace) + return 0; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), 0); + if (val > 0) + stack_kernel = 2; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), BPF_F_USER_STACK); + if (val > 0) + stack_user = 2; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_autoload.c b/tools/testing/selftests/bpf/progs/test_autoload.c new file mode 100644 index 000000000000..62c8cdec6d5d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_autoload.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +bool prog1_called = false; +bool prog2_called = false; +bool prog3_called = false; + +SEC("raw_tp/sys_enter") +int prog1(const void *ctx) +{ + prog1_called = true; + return 0; +} + +SEC("raw_tp/sys_exit") +int prog2(const void *ctx) +{ + prog2_called = true; + return 0; +} + +struct fake_kernel_struct { + int whatever; +} __attribute__((preserve_access_index)); + +SEC("fentry/unexisting-kprobe-will-fail-if-loaded") +int prog3(const void *ctx) +{ + struct fake_kernel_struct *fake = (void *)ctx; + fake->whatever = 123; + prog3_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_retro.c b/tools/testing/selftests/bpf/progs/test_core_retro.c new file mode 100644 index 000000000000..20861ec2f674 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_retro.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +struct task_struct { + int tgid; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} exp_tgid_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} results SEC(".maps"); + +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + int tgid = BPF_CORE_READ(task, tgid); + int zero = 0; + int real_tgid = bpf_get_current_pid_tgid() >> 32; + int *exp_tgid = bpf_map_lookup_elem(&exp_tgid_map, &zero); + + /* only pass through sys_enters from test process */ + if (!exp_tgid || *exp_tgid != real_tgid) + return 0; + + bpf_map_update_elem(&results, &zero, &tgid, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_endian.c b/tools/testing/selftests/bpf/progs/test_endian.c new file mode 100644 index 000000000000..ddb687c5d125 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_endian.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IN16 0x1234 +#define IN32 0x12345678U +#define IN64 0x123456789abcdef0ULL + +__u16 in16 = 0; +__u32 in32 = 0; +__u64 in64 = 0; + +__u16 out16 = 0; +__u32 out32 = 0; +__u64 out64 = 0; + +__u16 const16 = 0; +__u32 const32 = 0; +__u64 const64 = 0; + +SEC("raw_tp/sys_enter") +int sys_enter(const void *ctx) +{ + out16 = __builtin_bswap16(in16); + out32 = __builtin_bswap32(in32); + out64 = __builtin_bswap64(in64); + const16 = ___bpf_swab16(IN16); + const32 = ___bpf_swab32(IN32); + const64 = ___bpf_swab64(IN64); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 29817a703984..b6a6eb279e54 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -57,8 +57,9 @@ struct { SEC("raw_tracepoint/sys_enter") int bpf_prog1(void *ctx) { - int max_len, max_buildid_len, usize, ksize, total_size; + int max_len, max_buildid_len, total_size; struct stack_trace_t *data; + long usize, ksize; void *raw_data; __u32 key = 0; diff --git a/tools/testing/selftests/bpf/progs/test_ksyms.c b/tools/testing/selftests/bpf/progs/test_ksyms.c new file mode 100644 index 000000000000..6c9cbb5a3bdf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u64 out__bpf_link_fops = -1; +__u64 out__bpf_link_fops1 = -1; +__u64 out__btf_size = -1; +__u64 out__per_cpu_start = -1; + +extern const void bpf_link_fops __ksym; +extern const void __start_BTF __ksym; +extern const void __stop_BTF __ksym; +extern const void __per_cpu_start __ksym; +/* non-existing symbol, weak, default to zero */ +extern const void bpf_link_fops1 __ksym __weak; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + out__bpf_link_fops = (__u64)&bpf_link_fops; + out__btf_size = (__u64)(&__stop_BTF - &__start_BTF); + out__per_cpu_start = (__u64)&__per_cpu_start; + + out__bpf_link_fops1 = (__u64)&bpf_link_fops1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index ad59c4c9aba8..8207a2dc2f9d 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -12,8 +12,8 @@ struct { __uint(value_size, sizeof(int)); } perf_buf_map SEC(".maps"); -SEC("kprobe/sys_nanosleep") -int BPF_KPROBE(handle_sys_nanosleep_entry) +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) { int cpu = bpf_get_smp_processor_id(); diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c new file mode 100644 index 000000000000..bbf8296f4d66 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -0,0 +1,641 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> + +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define IP4(a, b, c, d) \ + bpf_htonl((((__u32)(a) & 0xffU) << 24) | \ + (((__u32)(b) & 0xffU) << 16) | \ + (((__u32)(c) & 0xffU) << 8) | \ + (((__u32)(d) & 0xffU) << 0)) +#define IP6(aaaa, bbbb, cccc, dddd) \ + { bpf_htonl(aaaa), bpf_htonl(bbbb), bpf_htonl(cccc), bpf_htonl(dddd) } + +#define MAX_SOCKS 32 + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_SOCKS); + __type(key, __u32); + __type(value, __u64); +} redir_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} run_map SEC(".maps"); + +enum { + PROG1 = 0, + PROG2, +}; + +enum { + SERVER_A = 0, + SERVER_B, +}; + +/* Addressable key/value constants for convenience */ +static const int KEY_PROG1 = PROG1; +static const int KEY_PROG2 = PROG2; +static const int PROG_DONE = 1; + +static const __u32 KEY_SERVER_A = SERVER_A; +static const __u32 KEY_SERVER_B = SERVER_B; + +static const __u16 DST_PORT = 7007; /* Host byte order */ +static const __u32 DST_IP4 = IP4(127, 0, 0, 1); +static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); + +SEC("sk_lookup/lookup_pass") +int lookup_pass(struct bpf_sk_lookup *ctx) +{ + return SK_PASS; +} + +SEC("sk_lookup/lookup_drop") +int lookup_drop(struct bpf_sk_lookup *ctx) +{ + return SK_DROP; +} + +SEC("sk_reuseport/reuse_pass") +int reuseport_pass(struct sk_reuseport_md *ctx) +{ + return SK_PASS; +} + +SEC("sk_reuseport/reuse_drop") +int reuseport_drop(struct sk_reuseport_md *ctx) +{ + return SK_DROP; +} + +/* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ +SEC("sk_lookup/redir_port") +int redir_port(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->local_port != DST_PORT) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ +SEC("sk_lookup/redir_ip4") +int redir_ip4(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip4 != DST_IP4) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ +SEC("sk_lookup/redir_ip6") +int redir_ip6(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET6) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip6[0] != DST_IP6[0] || + ctx->local_ip6[1] != DST_IP6[1] || + ctx->local_ip6[2] != DST_IP6[2] || + ctx->local_ip6[3] != DST_IP6[3]) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup/select_sock_a") +int select_sock_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup/select_sock_a_no_reuseport") +int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_NO_REUSEPORT); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_reuseport/select_sock_b") +int select_sock_b(struct sk_reuseport_md *ctx) +{ + __u32 key = KEY_SERVER_B; + int err; + + err = bpf_sk_select_reuseport(ctx, &redir_map, &key, 0); + return err ? SK_DROP : SK_PASS; +} + +/* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ +SEC("sk_lookup/sk_assign_eexist") +int sk_assign_eexist(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err != -EEXIST) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -EEXIST); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ +SEC("sk_lookup/sk_assign_replace_flag") +int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(sk=NULL) is accepted. */ +SEC("sk_lookup/sk_assign_null") +int sk_assign_null(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk = NULL; + int err, ret; + + ret = SK_DROP; + + err = bpf_sk_assign(ctx, NULL, 0); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + if (ctx->sk != sk) + goto out; + err = bpf_sk_assign(ctx, NULL, 0); + if (err != -EEXIST) + goto out; + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that selected sk is accessible through context. */ +SEC("sk_lookup/access_ctx_sk") +int access_ctx_sk(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk1 = NULL, *sk2 = NULL; + int err, ret; + + ret = SK_DROP; + + /* Try accessing unassigned (NULL) ctx->sk field */ + if (ctx->sk && ctx->sk->family != AF_INET) + goto out; + + /* Assign a value to ctx->sk */ + sk1 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk1) + goto out; + err = bpf_sk_assign(ctx, sk1, 0); + if (err) + goto out; + if (ctx->sk != sk1) + goto out; + + /* Access ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + /* Reset selection */ + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk) + goto out; + + /* Assign another socket */ + sk2 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk2) + goto out; + err = bpf_sk_assign(ctx, sk2, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk != sk2) + goto out; + + /* Access reassigned ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk1) + bpf_sk_release(sk1); + if (sk2) + bpf_sk_release(sk2); + return ret; +} + +/* Check narrow loads from ctx fields that support them. + * + * Narrow loads of size >= target field size from a non-zero offset + * are not covered because they give bogus results, that is the + * verifier ignores the offset. + */ +SEC("sk_lookup/ctx_narrow_access") +int ctx_narrow_access(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, family; + __u16 *half; + __u8 *byte; + bool v4; + + v4 = (ctx->family == AF_INET); + + /* Narrow loads from family field */ + byte = (__u8 *)&ctx->family; + half = (__u16 *)&ctx->family; + if (byte[0] != (v4 ? AF_INET : AF_INET6) || + byte[1] != 0 || byte[2] != 0 || byte[3] != 0) + return SK_DROP; + if (half[0] != (v4 ? AF_INET : AF_INET6)) + return SK_DROP; + + byte = (__u8 *)&ctx->protocol; + if (byte[0] != IPPROTO_TCP || + byte[1] != 0 || byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->protocol; + if (half[0] != IPPROTO_TCP) + return SK_DROP; + + /* Narrow loads from remote_port field. Expect non-0 value. */ + byte = (__u8 *)&ctx->remote_port; + if (byte[0] == 0 && byte[1] == 0 && byte[2] == 0 && byte[3] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_port; + if (half[0] == 0) + return SK_DROP; + + /* Narrow loads from local_port field. Expect DST_PORT. */ + byte = (__u8 *)&ctx->local_port; + if (byte[0] != ((DST_PORT >> 0) & 0xff) || + byte[1] != ((DST_PORT >> 8) & 0xff) || + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_port; + if (half[0] != DST_PORT) + return SK_DROP; + + /* Narrow loads from IPv4 fields */ + if (v4) { + /* Expect non-0.0.0.0 in remote_ip4 */ + byte = (__u8 *)&ctx->remote_ip4; + if (byte[0] == 0 && byte[1] == 0 && + byte[2] == 0 && byte[3] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip4; + if (half[0] == 0 && half[1] == 0) + return SK_DROP; + + /* Expect DST_IP4 in local_ip4 */ + byte = (__u8 *)&ctx->local_ip4; + if (byte[0] != ((DST_IP4 >> 0) & 0xff) || + byte[1] != ((DST_IP4 >> 8) & 0xff) || + byte[2] != ((DST_IP4 >> 16) & 0xff) || + byte[3] != ((DST_IP4 >> 24) & 0xff)) + return SK_DROP; + half = (__u16 *)&ctx->local_ip4; + if (half[0] != ((DST_IP4 >> 0) & 0xffff) || + half[1] != ((DST_IP4 >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect 0.0.0.0 IPs when family != AF_INET */ + byte = (__u8 *)&ctx->remote_ip4; + if (byte[0] != 0 || byte[1] != 0 && + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip4; + if (half[0] != 0 || half[1] != 0) + return SK_DROP; + + byte = (__u8 *)&ctx->local_ip4; + if (byte[0] != 0 || byte[1] != 0 && + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_ip4; + if (half[0] != 0 || half[1] != 0) + return SK_DROP; + } + + /* Narrow loads from IPv6 fields */ + if (!v4) { + /* Expenct non-:: IP in remote_ip6 */ + byte = (__u8 *)&ctx->remote_ip6; + if (byte[0] == 0 && byte[1] == 0 && + byte[2] == 0 && byte[3] == 0 && + byte[4] == 0 && byte[5] == 0 && + byte[6] == 0 && byte[7] == 0 && + byte[8] == 0 && byte[9] == 0 && + byte[10] == 0 && byte[11] == 0 && + byte[12] == 0 && byte[13] == 0 && + byte[14] == 0 && byte[15] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip6; + if (half[0] == 0 && half[1] == 0 && + half[2] == 0 && half[3] == 0 && + half[4] == 0 && half[5] == 0 && + half[6] == 0 && half[7] == 0) + return SK_DROP; + + /* Expect DST_IP6 in local_ip6 */ + byte = (__u8 *)&ctx->local_ip6; + if (byte[0] != ((DST_IP6[0] >> 0) & 0xff) || + byte[1] != ((DST_IP6[0] >> 8) & 0xff) || + byte[2] != ((DST_IP6[0] >> 16) & 0xff) || + byte[3] != ((DST_IP6[0] >> 24) & 0xff) || + byte[4] != ((DST_IP6[1] >> 0) & 0xff) || + byte[5] != ((DST_IP6[1] >> 8) & 0xff) || + byte[6] != ((DST_IP6[1] >> 16) & 0xff) || + byte[7] != ((DST_IP6[1] >> 24) & 0xff) || + byte[8] != ((DST_IP6[2] >> 0) & 0xff) || + byte[9] != ((DST_IP6[2] >> 8) & 0xff) || + byte[10] != ((DST_IP6[2] >> 16) & 0xff) || + byte[11] != ((DST_IP6[2] >> 24) & 0xff) || + byte[12] != ((DST_IP6[3] >> 0) & 0xff) || + byte[13] != ((DST_IP6[3] >> 8) & 0xff) || + byte[14] != ((DST_IP6[3] >> 16) & 0xff) || + byte[15] != ((DST_IP6[3] >> 24) & 0xff)) + return SK_DROP; + half = (__u16 *)&ctx->local_ip6; + if (half[0] != ((DST_IP6[0] >> 0) & 0xffff) || + half[1] != ((DST_IP6[0] >> 16) & 0xffff) || + half[2] != ((DST_IP6[1] >> 0) & 0xffff) || + half[3] != ((DST_IP6[1] >> 16) & 0xffff) || + half[4] != ((DST_IP6[2] >> 0) & 0xffff) || + half[5] != ((DST_IP6[2] >> 16) & 0xffff) || + half[6] != ((DST_IP6[3] >> 0) & 0xffff) || + half[7] != ((DST_IP6[3] >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect :: IPs when family != AF_INET6 */ + byte = (__u8 *)&ctx->remote_ip6; + if (byte[0] != 0 || byte[1] != 0 || + byte[2] != 0 || byte[3] != 0 || + byte[4] != 0 || byte[5] != 0 || + byte[6] != 0 || byte[7] != 0 || + byte[8] != 0 || byte[9] != 0 || + byte[10] != 0 || byte[11] != 0 || + byte[12] != 0 || byte[13] != 0 || + byte[14] != 0 || byte[15] != 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip6; + if (half[0] != 0 || half[1] != 0 || + half[2] != 0 || half[3] != 0 || + half[4] != 0 || half[5] != 0 || + half[6] != 0 || half[7] != 0) + return SK_DROP; + + byte = (__u8 *)&ctx->local_ip6; + if (byte[0] != 0 || byte[1] != 0 || + byte[2] != 0 || byte[3] != 0 || + byte[4] != 0 || byte[5] != 0 || + byte[6] != 0 || byte[7] != 0 || + byte[8] != 0 || byte[9] != 0 || + byte[10] != 0 || byte[11] != 0 || + byte[12] != 0 || byte[13] != 0 || + byte[14] != 0 || byte[15] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_ip6; + if (half[0] != 0 || half[1] != 0 || + half[2] != 0 || half[3] != 0 || + half[4] != 0 || half[5] != 0 || + half[6] != 0 || half[7] != 0) + return SK_DROP; + } + + /* Success, redirect to KEY_SERVER_B */ + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (sk) { + bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + } + return SK_PASS; +} + +/* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ +SEC("sk_lookup/sk_assign_esocknosupport") +int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + + err = bpf_sk_assign(ctx, sk, 0); + if (err != -ESOCKTNOSUPPORT) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -ESOCKTNOSUPPORT); + goto out; + } + + ret = SK_PASS; /* Success, pass to regular lookup */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +SEC("sk_lookup/multi_prog_pass1") +int multi_prog_pass1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_pass2") +int multi_prog_pass2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_drop1") +int multi_prog_drop1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +SEC("sk_lookup/multi_prog_drop2") +int multi_prog_drop2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + if (err) + return SK_DROP; + + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_redir1") +int multi_prog_redir1(struct bpf_sk_lookup *ctx) +{ + int ret; + + ret = select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_redir2") +int multi_prog_redir2(struct bpf_sk_lookup *ctx) +{ + int ret; + + ret = select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +char _license[] SEC("license") = "Dual BSD/GPL"; +__u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c index 77ae86f44db5..374ccef704e1 100644 --- a/tools/testing/selftests/bpf/progs/test_skeleton.c +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -20,7 +20,9 @@ long long in4 __attribute__((aligned(64))) = 0; struct s in5 = {}; /* .rodata section */ -const volatile int in6 = 0; +const volatile struct { + const int in6; +} in = {}; /* .data section */ int out1 = -1; @@ -46,7 +48,7 @@ int handler(const void *ctx) out3 = in3; out4 = in4; out5 = in5; - out6 = in6; + out6 = in.in6; bpf_syscall = CONFIG_BPF_SYSCALL; kern_ver = LINUX_KERNEL_VERSION; diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c new file mode 100644 index 000000000000..cd4b72c55dfe --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define MAX_LEN 256 + +char buf_in1[MAX_LEN] = {}; +char buf_in2[MAX_LEN] = {}; + +int test_pid = 0; +bool capture = false; + +/* .bss */ +long payload1_len1 = 0; +long payload1_len2 = 0; +long total1 = 0; +char payload1[MAX_LEN + MAX_LEN] = {}; + +/* .data */ +int payload2_len1 = -1; +int payload2_len2 = -1; +int total2 = -1; +char payload2[MAX_LEN + MAX_LEN] = { 1 }; + +int payload3_len1 = -1; +int payload3_len2 = -1; +int total3= -1; +char payload3[MAX_LEN + MAX_LEN] = { 1 }; + +int payload4_len1 = -1; +int payload4_len2 = -1; +int total4= -1; +char payload4[MAX_LEN + MAX_LEN] = { 1 }; + +SEC("raw_tp/sys_enter") +int handler64_unsigned(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload1; + u64 len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len <= MAX_LEN) { + payload += len; + payload1_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len <= MAX_LEN) { + payload += len; + payload1_len2 = len; + } + + total1 = payload - (void *)payload1; + + return 0; +} + +SEC("raw_tp/sys_exit") +int handler64_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload3; + long len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload3_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload3_len2 = len; + } + total3 = payload - (void *)payload3; + + return 0; +} + +SEC("tp/raw_syscalls/sys_enter") +int handler32_unsigned(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload2; + u32 len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len2 = len; + } + + total2 = payload - (void *)payload2; + + return 0; +} + +SEC("tp/raw_syscalls/sys_exit") +int handler32_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload4; + int len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload4_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload4_len2 = len; + } + total4 = payload - (void *)payload4; + + return 0; +} + +SEC("tp/syscalls/sys_exit_getpid") +int handler_exit(void *regs) +{ + long bla; + + if (bpf_probe_read_kernel(&bla, sizeof(bla), 0)) + return 1; + else + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index 5611b564d3b1..29fa09d6a6c6 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -63,20 +63,20 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) return 0; } -SEC("kprobe/hrtimer_nanosleep") -int BPF_KPROBE(handle__kprobe, - ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +SEC("kprobe/hrtimer_start_range_ns") +int BPF_KPROBE(handle__kprobe, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) { - if (rqtp == MY_TV_NSEC) + if (tim == MY_TV_NSEC) kprobe_called = true; return 0; } -SEC("fentry/hrtimer_nanosleep") -int BPF_PROG(handle__fentry, - ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +SEC("fentry/hrtimer_start_range_ns") +int BPF_PROG(handle__fentry, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) { - if (rqtp == MY_TV_NSEC) + if (tim == MY_TV_NSEC) fentry_called = true; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c new file mode 100644 index 000000000000..eb93ea95d1d8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +SEC("xdp/handler") +int xdp_handler(struct xdp_md *xdp) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c new file mode 100644 index 000000000000..59ee4f182ff8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp_redir") +int xdp_redir_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&cpu_map, 1, 0); +} + +SEC("xdp_dummy") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp_cpumap/dummy_cm") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + if (ctx->ingress_ifindex == IFINDEX_LO) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c new file mode 100644 index 000000000000..8ca7f399b670 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020, Oracle and/or its affiliates. + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int trace_printk_ret = 0; +int trace_printk_ran = 0; + +SEC("tp/raw_syscalls/sys_enter") +int sys_enter(void *ctx) +{ + static const char fmt[] = "testing,testing %d\n"; + + trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), + ++trace_printk_ran); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c new file mode 100644 index 000000000000..165e3c2dd9a3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/udp_limit.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <sys/socket.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int invocations = 0, in_use = 0; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_map SEC(".maps"); + +SEC("cgroup/sock_create") +int sock(struct bpf_sock *ctx) +{ + int *sk_storage; + __u32 key; + + if (ctx->type != SOCK_DGRAM) + return 1; + + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!sk_storage) + return 0; + *sk_storage = 0xdeadbeef; + + __sync_fetch_and_add(&invocations, 1); + + if (in_use > 0) { + /* BPF_CGROUP_INET_SOCK_RELEASE is _not_ called + * when we return an error from the BPF + * program! + */ + return 0; + } + + __sync_fetch_and_add(&in_use, 1); + return 1; +} + +SEC("cgroup/sock_release") +int sock_release(struct bpf_sock *ctx) +{ + int *sk_storage; + __u32 key; + + if (ctx->type != SOCK_DGRAM) + return 1; + + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, 0); + if (!sk_storage || *sk_storage != 0xdeadbeef) + return 0; + + __sync_fetch_and_add(&invocations, 1); + __sync_fetch_and_add(&in_use, -1); + return 1; +} diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py index a53ed58528d6..bfff82be3fc1 100755 --- a/tools/testing/selftests/bpf/tcp_client.py +++ b/tools/testing/selftests/bpf/tcp_client.py @@ -34,7 +34,7 @@ serverPort = int(sys.argv[1]) # create active socket sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) try: - sock.connect(('localhost', serverPort)) + sock.connect(('::1', serverPort)) except socket.error as e: sys.exit(1) diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py index 0ca60d193bed..42ab8882f00f 100755 --- a/tools/testing/selftests/bpf/tcp_server.py +++ b/tools/testing/selftests/bpf/tcp_server.py @@ -38,7 +38,7 @@ serverSocket = None # create passive socket serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) -try: serverSocket.bind(('localhost', 0)) +try: serverSocket.bind(('::1', 0)) except socket.error as msg: print('bind fails: ' + str(msg)) diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 655729004391..d946252a25bb 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -74,22 +74,7 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to setup cgroup environment\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (cgroup_fd < 0) { - printf("Failed to create test cgroup\n"); - goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; - } + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); /* Attach the bpf program */ if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) { diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index d850fb9076b5..804dddd97d4c 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -33,21 +33,10 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to load DEV_CGROUP program\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); if (cgroup_fd < 0) { printf("Failed to create test cgroup\n"); - goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; + goto out; } /* Attach bpf program */ diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 9df0d2ac45f8..4f6444bcd53f 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -10,7 +10,13 @@ if [ "$(id -u)" != "0" ]; then exit $ksft_skip fi -SRC_TREE=../../../../ +if [ "$building_out_of_srctree" ]; then + # We are in linux-build/kselftest/bpf + OUTPUT=../../ +else + # We are in linux/tools/testing/selftests/bpf + OUTPUT=../../../../ +fi test_run() { @@ -19,8 +25,8 @@ test_run() echo "[ JIT enabled:$1 hardened:$2 ]" dmesg -C - if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then - insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null + if [ -f ${OUTPUT}/lib/test_bpf.ko ]; then + insmod ${OUTPUT}/lib/test_bpf.ko 2> /dev/null if [ $? -ne 0 ]; then rc=1 fi diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 785eabf2a593..5620919fde9e 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -140,7 +140,7 @@ ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment -kill -INT $! +kill -TERM $! if [[ $(< $TMP_FILE) != "foobar" ]]; then exit 1 diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c index c1da5404454a..a7b9a69f4fd5 100644 --- a/tools/testing/selftests/bpf/test_netcnt.c +++ b/tools/testing/selftests/bpf/test_netcnt.c @@ -58,22 +58,9 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to load bpf program\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (cgroup_fd < 0) { - printf("Failed to create test cgroup\n"); + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + if (cgroup_fd < 0) goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; - } /* Attach bpf program */ if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) { @@ -82,9 +69,9 @@ int main(int argc, char **argv) } if (system("which ping6 &>/dev/null") == 0) - assert(!system("ping6 localhost -c 10000 -f -q > /dev/null")); + assert(!system("ping6 ::1 -c 10000 -f -q > /dev/null")); else - assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null")); + assert(!system("ping -6 ::1 -c 10000 -f -q > /dev/null")); if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL, &prog_cnt)) { diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 54fa5fa688ce..b1e4dadacd9b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -12,6 +12,9 @@ #include <string.h> #include <execinfo.h> /* backtrace */ +#define EXIT_NO_TEST 2 +#define EXIT_ERR_SETUP_INFRA 3 + /* defined in test_progs.h */ struct test_env env = {}; @@ -111,13 +114,31 @@ static void reset_affinity() { if (err < 0) { stdio_restore(); fprintf(stderr, "Failed to reset process affinity: %d!\n", err); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); } err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); if (err < 0) { stdio_restore(); fprintf(stderr, "Failed to reset thread affinity: %d!\n", err); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); + } +} + +static void save_netns(void) +{ + env.saved_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (env.saved_netns_fd == -1) { + perror("open(/proc/self/ns/net)"); + exit(EXIT_ERR_SETUP_INFRA); + } +} + +static void restore_netns(void) +{ + if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) { + stdio_restore(); + perror("setns(CLONE_NEWNS)"); + exit(EXIT_ERR_SETUP_INFRA); } } @@ -138,8 +159,6 @@ void test__end_subtest() test->test_num, test->subtest_num, test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); - reset_affinity(); - free(test->subtest_name); test->subtest_name = NULL; } @@ -366,6 +385,8 @@ enum ARG_KEYS { ARG_TEST_NAME_BLACKLIST = 'b', ARG_VERIFIER_STATS = 's', ARG_VERBOSE = 'v', + ARG_GET_TEST_CNT = 'c', + ARG_LIST_TEST_NAMES = 'l', }; static const struct argp_option opts[] = { @@ -379,6 +400,10 @@ static const struct argp_option opts[] = { "Output verifier statistics", }, { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, "Verbose output (use -vv or -vvv for progressively verbose output)" }, + { "count", ARG_GET_TEST_CNT, NULL, 0, + "Get number of selected top-level tests " }, + { "list", ARG_LIST_TEST_NAMES, NULL, 0, + "List test names that would run (without running them) " }, {}, }; @@ -511,6 +536,12 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } } break; + case ARG_GET_TEST_CNT: + env->get_test_cnt = true; + break; + case ARG_LIST_TEST_NAMES: + env->list_test_names = true; + break; case ARGP_KEY_ARG: argp_usage(state); break; @@ -643,6 +674,7 @@ int main(int argc, char **argv) return -1; } + save_netns(); stdio_hijack(); for (i = 0; i < prog_test_cnt; i++) { struct prog_test_def *test = &prog_test_defs[i]; @@ -654,6 +686,17 @@ int main(int argc, char **argv) test->test_num, test->test_name)) continue; + if (env.get_test_cnt) { + env.succ_cnt++; + continue; + } + + if (env.list_test_names) { + fprintf(env.stdout, "%s\n", test->test_name); + env.succ_cnt++; + continue; + } + test->run_test(); /* ensure last sub-test is finalized properly */ if (test->subtest_name) @@ -673,19 +716,34 @@ int main(int argc, char **argv) test->error_cnt ? "FAIL" : "OK"); reset_affinity(); + restore_netns(); if (test->need_cgroup_cleanup) cleanup_cgroup_environment(); } stdio_restore(); + + if (env.get_test_cnt) { + printf("%d\n", env.succ_cnt); + goto out; + } + + if (env.list_test_names) + goto out; + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); +out: free_str_set(&env.test_selector.blacklist); free_str_set(&env.test_selector.whitelist); free(env.test_selector.num_set); free_str_set(&env.subtest_selector.blacklist); free_str_set(&env.subtest_selector.whitelist); free(env.subtest_selector.num_set); + close(env.saved_netns_fd); + + if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0) + return EXIT_NO_TEST; return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f4503c926aca..6e09bf738473 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -66,6 +66,8 @@ struct test_env { enum verbosity verbosity; bool jit_enabled; + bool get_test_cnt; + bool list_test_names; struct prog_test_def *test; FILE *stdout; @@ -78,6 +80,8 @@ struct test_env { int sub_succ_cnt; /* successful sub-tests */ int fail_cnt; /* total failed tests + sub-tests */ int skip_cnt; /* skipped tests */ + + int saved_netns_fd; }; extern struct test_env env; diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c index 356351c0ac28..4a64306728ab 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c @@ -160,16 +160,10 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CGROUP_PATH); + cgfd = cgroup_setup_and_join(CGROUP_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CGROUP_PATH)) - goto err; - if (send_packet(argv[1])) goto err; diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 52bf14955797..9613f7538840 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -464,16 +464,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 0358814c67dc..b8c72c1d9cf7 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1638,16 +1638,10 @@ int main(int argc, char **argv) exit(err); } - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index f0fc103261a4..6c9f269c396d 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -421,19 +421,11 @@ int main(int argc, char **argv) struct bpf_object *obj; struct bpf_map *map; - err = setup_cgroup_environment(); - CHECK(err, "setup_cgroup_environment()", "err:%d errno:%d", - err, errno); - - atexit(cleanup_cgroup_environment); - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - CHECK(cgroup_fd == -1, "create_and_get_cgroup()", + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + CHECK(cgroup_fd < 0, "cgroup_setup_and_join()", "cgroup_fd:%d errno:%d", cgroup_fd, errno); - - err = join_cgroup(TEST_CGROUP); - CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno); + atexit(cleanup_cgroup_environment); err = bpf_prog_load_xattr(&attr, &obj, &egress_fd); CHECK(err, "bpf_prog_load_xattr()", "err:%d", err); diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c index 15653b0e26eb..154a8fd2a48d 100644 --- a/tools/testing/selftests/bpf/test_socket_cookie.c +++ b/tools/testing/selftests/bpf/test_socket_cookie.c @@ -191,16 +191,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_test(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 78789b27e573..9b6fb00dc7a0 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1963,23 +1963,9 @@ int main(int argc, char **argv) } if (!cg_fd) { - if (setup_cgroup_environment()) { - fprintf(stderr, "ERROR: cgroup env failed\n"); - return -EINVAL; - } - - cg_fd = create_and_get_cgroup(CG_PATH); - if (cg_fd < 0) { - fprintf(stderr, - "ERROR: (%i) open cg path failed: %s\n", - cg_fd, strerror(errno)); + cg_fd = cgroup_setup_and_join(CG_PATH); + if (cg_fd < 0) return cg_fd; - } - - if (join_cgroup(CG_PATH)) { - fprintf(stderr, "ERROR: failed to join cgroup\n"); - return -EINVAL; - } cg_created = 1; } diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index d196e2a4a6e0..a20a919244c0 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -1619,16 +1619,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 3ae127620463..74a9e49988b6 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -102,16 +102,10 @@ int main(int argc, char **argv) __u32 key = 0; int rv; - if (setup_cgroup_environment()) - goto err; - - cg_fd = create_and_get_cgroup(cg_path); + cg_fd = cgroup_setup_and_join(cg_path); if (cg_fd < 0) goto err; - if (join_cgroup(cg_path)) - goto err; - 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; diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index f9765ddf0761..8549b31716ab 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -86,16 +86,10 @@ int main(int argc, char **argv) CPU_SET(0, &cpuset); pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); - if (setup_cgroup_environment()) - goto err; - - cg_fd = create_and_get_cgroup(cg_path); + cg_fd = cgroup_setup_and_join(cg_path); if (cg_fd < 0) goto err; - if (join_cgroup(cg_path)) - goto err; - 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; diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c4b17e08d431..dd80f0c84afb 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -10,52 +10,72 @@ # | xdp forwarding | # ------------------ -cleanup() +ret=0 + +setup() { - if [ "$?" = "0" ]; then - echo "selftests: test_xdp_redirect [PASS]"; - else - echo "selftests: test_xdp_redirect [FAILED]"; - fi - set +e + local xdpmode=$1 + + ip netns add ns1 + ip netns add ns2 + + ip link add veth1 index 111 type veth peer name veth11 netns ns1 + ip link add veth2 index 222 type veth peer name veth22 netns ns2 + + ip link set veth1 up + ip link set veth2 up + ip -n ns1 link set dev veth11 up + ip -n ns2 link set dev veth22 up + + ip -n ns1 addr add 10.1.1.11/24 dev veth11 + ip -n ns2 addr add 10.1.1.22/24 dev veth22 +} + +cleanup() +{ ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null ip netns del ns1 2> /dev/null ip netns del ns2 2> /dev/null } -ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" - exit 0 -fi -set -e - -ip netns add ns1 -ip netns add ns2 +test_xdp_redirect() +{ + local xdpmode=$1 -trap cleanup 0 2 3 6 9 + setup -ip link add veth1 index 111 type veth peer name veth11 -ip link add veth2 index 222 type veth peer name veth22 + ip link set dev veth1 $xdpmode off &> /dev/null + if [ $? -ne 0 ];then + echo "selftests: test_xdp_redirect $xdpmode [SKIP]" + return 0 + fi -ip link set veth11 netns ns1 -ip link set veth22 netns ns2 + ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null + ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null -ip link set veth1 up -ip link set veth2 up + ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null + local ret1=$? + ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null + local ret2=$? -ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11 -ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22 + if [ $ret1 -eq 0 -a $ret2 -eq 0 ]; then + echo "selftests: test_xdp_redirect $xdpmode [PASS]"; + else + ret=1 + echo "selftests: test_xdp_redirect $xdpmode [FAILED]"; + fi -ip netns exec ns1 ip link set dev veth11 up -ip netns exec ns2 ip link set dev veth22 up + cleanup +} -ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222 -ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111 +set -e +trap cleanup 2 3 6 9 -ip netns exec ns1 ping -c 1 10.1.1.22 -ip netns exec ns2 ping -c 1 10.1.1.11 +test_xdp_redirect xdpgeneric +test_xdp_redirect xdpdrv -exit 0 +exit $ret diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0af6337a8962..800d503e5cb4 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -64,3 +64,17 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } + +__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) +{ + __u32 info_len = sizeof(*info); + int err; + + memset(info, 0, sizeof(*info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), info, &info_len); + if (err) { + printf("failed to get link info: %d\n", -errno); + return 0; + } + return info->prog_id; +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 923b51762759..d4f8e749611b 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ #include <stdbool.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> int parse_num_list(const char *s, bool **set, int *set_len); +__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c new file mode 100644 index 000000000000..2ad5f974451c --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c @@ -0,0 +1,492 @@ +{ + "valid 1,2,4,8-byte reads from bpf_sk_lookup", + .insns = { + /* 1-byte read from family field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 3), + /* 2-byte read from family field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 2), + /* 4-byte read from family field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + + /* 1-byte read from protocol field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 3), + /* 2-byte read from protocol field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 2), + /* 4-byte read from protocol field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + + /* 1-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 3), + /* 2-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 2), + /* 4-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + + /* 1-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 6), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 7), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 9), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 10), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 11), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 13), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 14), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 15), + /* 2-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 6), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 10), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 14), + /* 4-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + + /* 1-byte read from remote_port field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 3), + /* 2-byte read from remote_port field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 2), + /* 4-byte read from remote_port field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + + /* 1-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 3), + /* 2-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 2), + /* 4-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + + /* 1-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 6), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 7), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 9), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 10), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 11), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 13), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 14), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 15), + /* 2-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 6), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 10), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 14), + /* 4-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + + /* 1-byte read from local_port field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 3), + /* 2-byte read from local_port field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 2), + /* 4-byte read from local_port field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + + /* 8-byte read from sk field */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* invalid 8-byte reads from a 4-byte fields in bpf_sk_lookup */ +{ + "invalid 8-byte read from bpf_sk_lookup family field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup protocol field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_ip4 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_ip6 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_port field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_ip4 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_ip6 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_port field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */ +{ + "invalid 4-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 2-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 1-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* out of bounds and unaligned reads from bpf_sk_lookup */ +{ + "invalid 4-byte read past end of bpf_sk_lookup", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + sizeof(struct bpf_sk_lookup)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte unaligned read from bpf_sk_lookup at odd offset", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte unaligned read from bpf_sk_lookup at even offset", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 2), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* in-bound and out-of-bound writes to bpf_sk_lookup */ +{ + "invalid 8-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 2-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 1-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte write past end of bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + sizeof(struct bpf_sk_lookup)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c new file mode 100644 index 000000000000..b52209db8250 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/map_ptr.c @@ -0,0 +1,62 @@ +{ + "bpf_map_ptr: read with negative offset rejected", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "R1 is bpf_array invalid negative access: off=-8", +}, +{ + "bpf_map_ptr: write rejected", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "only read from bpf_array is supported", +}, +{ + "bpf_map_ptr: read non-existent field rejected", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4", +}, +{ + "bpf_map_ptr: read ops field accepted", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c index cd26ee6b7b1d..1f2b8c4cb26d 100644 --- a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c +++ b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c @@ -56,7 +56,7 @@ .fixup_map_in_map = { 16 }, .fixup_map_array_48b = { 13 }, .result = REJECT, - .errstr = "R0 invalid mem access 'map_ptr'", + .errstr = "only read from bpf_array is supported", }, { "cond: two branches returning different map pointers for lookup (tail, tail)", diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 97ee658e1242..ed4e76b24649 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -836,3 +836,41 @@ .errstr = "R0 invalid mem access 'inv'", .errstr_unpriv = "R0 pointer -= pointer prohibited", }, +{ + "32bit pkt_ptr -= scalar", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2), + BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_7), + BPF_ALU32_REG(BPF_SUB, BPF_REG_6, BPF_REG_4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "32bit scalar -= pkt_ptr", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2), + BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_6), + BPF_ALU32_REG(BPF_SUB, BPF_REG_4, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index b3ead29c6089..2cf6f10ab7c4 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -47,7 +47,7 @@ void child(int cpu) _exit(0); } -bool run_test(int cpu) +int run_test(int cpu) { int status; pid_t pid = fork(); @@ -55,7 +55,7 @@ bool run_test(int cpu) if (pid < 0) { ksft_print_msg("fork() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (pid == 0) child(cpu); @@ -63,67 +63,68 @@ bool run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGSTOP) { ksft_print_msg("child did not stop with SIGSTOP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) { if (errno == EIO) { - ksft_exit_skip( + ksft_print_msg( "ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n", strerror(errno)); + return KSFT_SKIP; } ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WIFEXITED(status)) { ksft_print_msg("child did not single-step: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGTRAP) { ksft_print_msg("child did not stop with SIGTRAP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFEXITED(status)) { ksft_print_msg("child did not exit after PTRACE_CONT: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } - return true; + return KSFT_PASS; } void suspend(void) @@ -183,32 +184,38 @@ int main(int argc, char **argv) } } + err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); + if (err < 0) + ksft_exit_fail_msg("sched_getaffinity() failed\n"); + for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { if (!CPU_ISSET(cpu, &available_cpus)) continue; tests++; } - ksft_set_plan(tests); if (do_suspend) suspend(); - err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); - if (err < 0) - ksft_exit_fail_msg("sched_getaffinity() failed\n"); - + ksft_set_plan(tests); for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { - bool test_success; + int test_success; if (!CPU_ISSET(cpu, &available_cpus)) continue; test_success = run_test(cpu); - if (test_success) { + switch (test_success) { + case KSFT_PASS: ksft_test_result_pass("CPU %d\n", cpu); - } else { + break; + case KSFT_SKIP: + ksft_test_result_skip("CPU %d\n", cpu); + break; + case KSFT_FAIL: ksft_test_result_fail("CPU %d\n", cpu); succeeded = false; + break; } } diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore index a81085742d40..83c0f6246055 100644 --- a/tools/testing/selftests/clone3/.gitignore +++ b/tools/testing/selftests/clone3/.gitignore @@ -2,3 +2,4 @@ clone3 clone3_clear_sighand clone3_set_tid +clone3_cap_checkpoint_restore diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile index cf976c732906..ef7564cb7abe 100644 --- a/tools/testing/selftests/clone3/Makefile +++ b/tools/testing/selftests/clone3/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ +LDLIBS += -lcap -TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid +TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \ + clone3_cap_checkpoint_restore include ../lib.mk diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index f14c269a5a18..b7e6dec36173 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -131,9 +131,9 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); - test_clone3_supported(); ksft_print_header(); ksft_set_plan(17); + test_clone3_supported(); /* Just a simple clone3() should return 0.*/ test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST); diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c new file mode 100644 index 000000000000..9562425aa0a9 --- /dev/null +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Based on Christian Brauner's clone3() example. + * These tests are assuming to be running in the host's + * PID namespace. + */ + +/* capabilities related code based on selftests/bpf/test_verifier.c */ + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <sys/capability.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/un.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sched.h> + +#include "../kselftest_harness.h" +#include "clone3_selftests.h" + +#ifndef MAX_PID_NS_LEVEL +#define MAX_PID_NS_LEVEL 32 +#endif + +static void child_exit(int ret) +{ + fflush(stdout); + fflush(stderr); + _exit(ret); +} + +static int call_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int status; + pid_t pid = -1; + + struct clone_args args = { + .exit_signal = SIGCHLD, + .set_tid = ptr_to_u64(set_tid), + .set_tid_size = set_tid_size, + }; + + pid = sys_clone3(&args, sizeof(struct clone_args)); + if (pid < 0) { + TH_LOG("%s - Failed to create new process", strerror(errno)); + return -errno; + } + + if (pid == 0) { + int ret; + char tmp = 0; + + TH_LOG("I am the child, my PID is %d (expected %d)", getpid(), set_tid[0]); + + if (set_tid[0] != getpid()) + child_exit(EXIT_FAILURE); + child_exit(EXIT_SUCCESS); + } + + TH_LOG("I am the parent (%d). My child's pid is %d", getpid(), pid); + + if (waitpid(pid, &status, 0) < 0) { + TH_LOG("Child returned %s", strerror(errno)); + return -errno; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static int test_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int ret; + + TH_LOG("[%d] Trying clone3() with CLONE_SET_TID to %d", getpid(), set_tid[0]); + ret = call_clone3_set_tid(_metadata, set_tid, set_tid_size); + TH_LOG("[%d] clone3() with CLONE_SET_TID %d says:%d", getpid(), set_tid[0], ret); + return ret; +} + +struct libcap { + struct __user_cap_header_struct hdr; + struct __user_cap_data_struct data[2]; +}; + +static int set_capability(void) +{ + cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID }; + struct libcap *cap; + int ret = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return -1; + } + + /* Drop all capabilities */ + if (cap_clear(caps)) { + perror("cap_clear"); + goto out; + } + + cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET); + cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET); + + cap = (struct libcap *) caps; + + /* 40 -> CAP_CHECKPOINT_RESTORE */ + cap->data[1].effective |= 1 << (40 - 32); + cap->data[1].permitted |= 1 << (40 - 32); + + if (cap_set_proc(caps)) { + perror("cap_set_proc"); + goto out; + } + ret = 0; +out: + if (cap_free(caps)) + perror("cap_free"); + return ret; +} + +TEST(clone3_cap_checkpoint_restore) +{ + pid_t pid; + int status; + int ret = 0; + pid_t set_tid[1]; + + test_clone3_supported(); + + EXPECT_EQ(getuid(), 0) + XFAIL(return, "Skipping all tests as non-root\n"); + + memset(&set_tid, 0, sizeof(set_tid)); + + /* Find the current active PID */ + pid = fork(); + if (pid == 0) { + TH_LOG("Child has PID %d", getpid()); + child_exit(EXIT_SUCCESS); + } + ASSERT_GT(waitpid(pid, &status, 0), 0) + TH_LOG("Waiting for child %d failed", pid); + + /* After the child has finished, its PID should be free. */ + set_tid[0] = pid; + + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + + ASSERT_EQ(prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0), 0); + + EXPECT_EQ(setgid(65534), 0) + TH_LOG("Failed to setgid(65534)"); + ASSERT_EQ(setuid(65534), 0); + + set_tid[0] = pid; + /* This would fail without CAP_CHECKPOINT_RESTORE */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), -EPERM); + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + /* This should work as we have CAP_CHECKPOINT_RESTORE as non-root */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c index 9e1af8aa7698..db5fc9c5edcf 100644 --- a/tools/testing/selftests/clone3/clone3_clear_sighand.c +++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c @@ -119,9 +119,8 @@ static void test_clone3_clear_sighand(void) int main(int argc, char **argv) { ksft_print_header(); - test_clone3_supported(); - ksft_set_plan(1); + test_clone3_supported(); test_clone3_clear_sighand(); diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 25beb22f35b5..5831c1082d6d 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -157,8 +157,8 @@ int main(int argc, char *argv[]) pid_t set_tid[MAX_PID_NS_LEVEL * 2]; ksft_print_header(); - test_clone3_supported(); ksft_set_plan(29); + test_clone3_supported(); if (pipe(pipe_1) < 0 || pipe(pipe_2) < 0) ksft_exit_fail_msg("pipe() failed\n"); diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore new file mode 100644 index 000000000000..6e6712ce5817 --- /dev/null +++ b/tools/testing/selftests/core/.gitignore @@ -0,0 +1 @@ +close_range_test diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile new file mode 100644 index 000000000000..f6f2d6f473c6 --- /dev/null +++ b/tools/testing/selftests/core/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS += -g -I../../../../usr/include/ + +TEST_GEN_PROGS := close_range_test + +include ../lib.mk + diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c new file mode 100644 index 000000000000..c99b98b0d461 --- /dev/null +++ b/tools/testing/selftests/core/close_range_test.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/kernel.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> + +#include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +#ifndef __NR_close_range +#define __NR_close_range -1 +#endif + +#ifndef CLOSE_RANGE_UNSHARE +#define CLOSE_RANGE_UNSHARE (1U << 1) +#endif + +static inline int sys_close_range(unsigned int fd, unsigned int max_fd, + unsigned int flags) +{ + return syscall(__NR_close_range, fd, max_fd, flags); +} + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +TEST(close_range) +{ + int i, ret; + int open_fds[101]; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) { + if (errno == ENOSYS) + XFAIL(return, "close_range() syscall not supported"); + } + + EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0)); + + for (i = 0; i <= 50; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 51; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + EXPECT_EQ(0, sys_close_range(open_fds[51], open_fds[92], 0)); + + for (i = 51; i <= 92; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 93; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* test that the kernel caps and still closes all fds */ + EXPECT_EQ(0, sys_close_range(open_fds[93], open_fds[99], 0)); + + for (i = 93; i <= 99; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + EXPECT_EQ(0, sys_close_range(open_fds[100], open_fds[100], 0)); + + EXPECT_EQ(-1, fcntl(open_fds[100], F_GETFL)); +} + +TEST(close_range_unshare) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], open_fds[50], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 50; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 51; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + ret = sys_close_range(open_fds[51], open_fds[92], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 51; i <= 92; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 93; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* test that the kernel caps and still closes all fds */ + ret = sys_close_range(open_fds[93], open_fds[99], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 93; i <= 99; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) == -1) + exit(EXIT_FAILURE); + + ret = sys_close_range(open_fds[100], open_fds[100], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(close_range_unshare_capped) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], UINT_MAX, + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 0d347d48c112..517297a14ecf 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -121,6 +121,7 @@ h1_destroy() h2_create() { host_create $h2 2 + tc qdisc add dev $h2 clsact # Some of the tests in this suite use multicast traffic. As this traffic # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus @@ -141,6 +142,7 @@ h2_create() h2_destroy() { ethtool -s $h2 autoneg on + tc qdisc del dev $h2 clsact host_destroy $h2 } @@ -336,6 +338,17 @@ get_qdisc_npackets() qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets } +send_packets() +{ + local vlan=$1; shift + local proto=$1; shift + local pkts=$1; shift + + $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ + -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ + -t $proto -q -c $pkts "$@" +} + # This sends traffic in an attempt to build a backlog of $size. Returns 0 on # success. After 10 failed attempts it bails out and returns 1. It dumps the # backlog size to stdout. @@ -364,9 +377,7 @@ build_backlog() return 1 fi - $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ - -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ - -t $proto -q -c $pkts "$@" + send_packets $vlan $proto $pkts "$@" done } @@ -531,3 +542,115 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } + +do_drop_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trigger=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local backlog + local base + local now + local pct + + RET=0 + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac + + # Create a bit of a backlog and observe no mirroring due to drops. + qevent_rule_install_$subtest + base=$($fetch_counter) + + build_backlog $vlan $((2 * limit / 3)) udp >/dev/null + + busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed without buffer pressure" + + # Push to the queue until it's at the limit. The configured limit is + # rounded by the qdisc and then by the driver, so this is the best we + # can do to get to the real limit of the system. + build_backlog $vlan $((3 * limit / 2)) udp >/dev/null + + base=$($fetch_counter) + send_packets $vlan udp 11 + + now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) + check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen" + + # When no extra traffic is injected, there should be no mirroring. + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + send_packets $vlan udp 11 + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed after uninstall" + + log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd" + + stop_traffic + sleep 1 +} + +qevent_rule_install_mirror() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action mirred egress mirror dev $swp2 hw_stats disabled +} + +qevent_rule_uninstall_mirror() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_mirror() +{ + tc_rule_handle_stats_get "dev $h2 ingress" 101 +} + +do_drop_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + local qevent_name=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto udp \ + action drop + + do_drop_test "$vlan" "$limit" "$qevent_name" mirror \ + qevent_counter_fetch_mirror + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + +qevent_rule_install_trap() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap hw_stats disabled +} + +qevent_rule_uninstall_trap() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_trap() +{ + local trap_name=$1; shift + + devlink_trap_rx_packets_get "$trap_name" +} + +do_drop_trap_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trap_name=$1; shift + + do_drop_test "$vlan" "$limit" "$trap_name" trap \ + "qevent_counter_fetch_trap $trap_name" +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index 1c36c576613b..3f007c5f8361 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -7,6 +7,8 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test + red_trap_test " : ${QDISC:=ets} source sch_red_core.sh @@ -83,6 +85,26 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_mirror_test 10 $BACKLOG1 early_drop + do_drop_mirror_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + +red_trap_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_trap_test 10 $BACKLOG1 early_drop + do_drop_trap_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index 558667ea11ec..ede9c38d3eff 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -7,6 +7,7 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test " source sch_red_core.sh @@ -57,6 +58,13 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + do_drop_mirror_test 10 $BACKLOG + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index fd583a171db7..d7cf33a3f18d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -28,7 +28,7 @@ cleanup() trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre" +ALL_TESTS="router tc_flower mirror_gre tc_police" for current_test in ${TESTS:-$ALL_TESTS}; do source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh new file mode 100644 index 000000000000..e79ac0dad1f4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../tc_police_scale.sh + +tc_police_get_target() +{ + local should_fail=$1; shift + local target + + target=$(devlink_resource_size_get global_policers single_rate_policers) + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 43ba1b438f6d..43f662401bc3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -22,7 +22,7 @@ cleanup() devlink_sp_read_kvd_defaults trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre" +ALL_TESTS="router tc_flower mirror_gre tc_police" for current_test in ${TESTS:-$ALL_TESTS}; do source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh new file mode 100644 index 000000000000..e79ac0dad1f4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../tc_police_scale.sh + +tc_police_get_target() +{ + local should_fail=$1; shift + local target + + target=$(devlink_resource_size_get global_policers single_rate_policers) + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh new file mode 100755 index 000000000000..448b75c1545a --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that policers shared by different tc filters are correctly reference +# counted by observing policers' occupancy via devlink-resource. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + tc_police_occ_test +" +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +tc_police_occ_get() +{ + devlink_resource_occ_get global_policers single_rate_policers +} + +tc_police_occ_test() +{ + RET=0 + + local occ=$(tc_police_occ_get) + + tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 1 handle 101 flower + (( occ == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $occ" + + tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok \ + index 10 + tc filter add dev $swp1 ingress pref 2 handle 102 proto ip \ + flower skip_sw action police index 10 + + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 2 handle 102 flower + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 1 handle 101 flower + (( occ == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $occ" + + log_test "tc police occupancy" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh new file mode 100644 index 000000000000..4b96561c462f --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -0,0 +1,92 @@ +# SPDX-License-Identifier: GPL-2.0 + +TC_POLICE_NUM_NETIFS=2 + +tc_police_h1_create() +{ + simple_if_init $h1 +} + +tc_police_h1_destroy() +{ + simple_if_fini $h1 +} + +tc_police_switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +tc_police_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +tc_police_rules_create() +{ + local count=$1; shift + local should_fail=$1; shift + + TC_POLICE_BATCH_FILE="$(mktemp)" + + for ((i = 0; i < count; ++i)); do + cat >> $TC_POLICE_BATCH_FILE <<-EOF + filter add dev $swp1 ingress \ + prot ip \ + flower skip_sw \ + action police rate 10mbit burst 100k \ + conform-exceed drop/ok + EOF + done + + tc -b $TC_POLICE_BATCH_FILE + check_err_fail $should_fail $? "Rule insertion" +} + +__tc_police_test() +{ + local count=$1; shift + local should_fail=$1; shift + + tc_police_rules_create $count $should_fail + + offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l) + ((offload_count == count)) + check_err_fail $should_fail $? "tc police offload count" +} + +tc_police_test() +{ + local count=$1; shift + local should_fail=$1; shift + + if ! tc_offload_check $TC_POLICE_NUM_NETIFS; then + check_err 1 "Could not test offloaded functionality" + return + fi + + __tc_police_test $count $should_fail +} + +tc_police_setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + tc_police_h1_create + tc_police_switch_create +} + +tc_police_cleanup() +{ + pre_cleanup + + tc_police_switch_destroy + tc_police_h1_destroy + + vrf_cleanup +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 9241250c5921..553cb9fad508 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -11,6 +11,8 @@ ALL_TESTS=" matchall_mirror_behind_flower_ingress_test matchall_sample_behind_flower_ingress_test matchall_mirror_behind_flower_egress_test + police_limits_test + multi_police_test " NUM_NETIFS=2 @@ -287,6 +289,80 @@ matchall_mirror_behind_flower_egress_test() matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2" } +police_limits_test() +{ + RET=0 + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 0.5kbit burst 1m conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too low rate" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 2.5tbit burst 1g conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too high rate" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 1m conform-exceed drop/ok + check_err $? "Failed to add police action with low rate" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.9tbit burst 1g conform-exceed drop/ok + check_err $? "Failed to add police action with high rate" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 512b conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too low burst size" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 2k conform-exceed drop/ok + check_err $? "Failed to add police action with low burst size" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc qdisc del dev $swp1 clsact + + log_test "police rate and burst limits" +} + +multi_police_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have multiple police + # actions in a single rule. + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok + check_err $? "Failed to add rule with single police action" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/pipe \ + action police rate 200mbit burst 200k conform-exceed drop/ok + check_fail $? "Incorrect success to add rule with two police actions" + + tc qdisc del dev $swp1 clsact + + log_test "multi police" +} + setup_prepare() { swp1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh new file mode 100644 index 000000000000..ba1d53b9f815 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -0,0 +1,786 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +VNI_GEN=$RANDOM +NSIM_ID=$((RANDOM % 1024)) +NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID +NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID +NSIM_NETDEV= +HAS_ETHTOOL= +EXIT_STATUS=0 +num_cases=0 +num_errors=0 + +clean_up_devs=( ) + +function err_cnt { + echo "ERROR:" $@ + EXIT_STATUS=1 + ((num_errors++)) + ((num_cases++)) +} + +function pass_cnt { + ((num_cases++)) +} + +function cleanup_tuns { + for dev in "${clean_up_devs[@]}"; do + [ -e /sys/class/net/$dev ] && ip link del dev $dev + done + clean_up_devs=( ) +} + +function cleanup_nsim { + if [ -e $NSIM_DEV_SYS ]; then + echo $NSIM_ID > /sys/bus/netdevsim/del_device + fi +} + +function cleanup { + cleanup_tuns + cleanup_nsim +} + +trap cleanup EXIT + +function new_vxlan { + local dev=$1 + local dstport=$2 + local lower=$3 + local ipver=$4 + local flags=$5 + + local group ipfl + + [ "$ipver" != '6' ] && group=239.1.1.1 || group=fff1::1 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags id $((VNI_GEN++))" + + ip $ipfl link add $dev type vxlan \ + group $group \ + dev $lower \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function new_geneve { + local dev=$1 + local dstport=$2 + local ipver=$3 + local flags=$4 + + local group ipfl + + [ "$ipver" != '6' ] && remote=1.1.1.2 || group=::2 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags vni $((VNI_GEN++))" + + ip $ipfl link add $dev type geneve \ + remote $remote \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function del_dev { + local dev=$1 + + ip link del dev $dev + check_tables +} + +# Helpers for netdevsim port/type encoding +function mke { + local port=$1 + local type=$2 + + echo $((port << 16 | type)) +} + +function pre { + local val=$1 + + echo -e "port: $((val >> 16))\ttype: $((val & 0xffff))" +} + +function pre_ethtool { + local val=$1 + local port=$((val >> 16)) + local type=$((val & 0xffff)) + + case $type in + 1) + type_name="vxlan" + ;; + 2) + type_name="geneve" + ;; + 4) + type_name="vxlan-gpe" + ;; + *) + type_name="bit X" + ;; + esac + + echo "port $port, $type_name" +} + +function check_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local -n expected=$2 + local last=$3 + + read -a have < $path + + if [ ${#expected[@]} -ne ${#have[@]} ]; then + echo "check_table: BAD NUMBER OF ITEMS" + return 0 + fi + + for i in "${!expected[@]}"; do + if [ -n "$HAS_ETHTOOL" -a ${expected[i]} -ne 0 ]; then + pp_expected=`pre_ethtool ${expected[i]}` + ethtool --show-tunnels $NSIM_NETDEV | grep "$pp_expected" >/dev/null + if [ $? -ne 0 -a $last -ne 0 ]; then + err_cnt "ethtool table $1 on port $port: $pfx - $msg" + echo " check_table: ethtool does not contain '$pp_expected'" + ethtool --show-tunnels $NSIM_NETDEV + return 0 + + fi + fi + + if [ ${expected[i]} != ${have[i]} ]; then + if [ $last -ne 0 ]; then + err_cnt "table $1 on port $port: $pfx - $msg" + echo " check_table: wrong entry $i" + echo " expected: `pre ${expected[i]}`" + echo " have: `pre ${have[i]}`" + return 0 + fi + return 1 + fi + done + + pass_cnt + return 0 +} + +function check_tables { + # Need retries in case we have workqueue making the changes + local retries=10 + + while ! check_table 0 exp0 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done + while ! check_table 1 exp1 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done +} + +function print_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + read -a have < $path + + tree $NSIM_DEV_DFS/ + + echo "Port $port table $1:" + + for i in "${!have[@]}"; do + echo " `pre ${have[i]}`" + done + +} + +function print_tables { + print_table 0 + print_table 1 +} + +function get_netdev_name { + local -n old=$1 + + new=$(ls /sys/class/net) + + for netdev in $new; do + for check in $old; do + [ $netdev == $check ] && break + done + + if [ $netdev != $check ]; then + echo $netdev + break + fi + done +} + +### +### Code start +### + +# Probe ethtool support +ethtool -h | grep show-tunnels 2>&1 >/dev/null && HAS_ETHTOOL=y + +modprobe netdevsim + +# Basic test +pfx="basic" + +for port in 0 1; do + old_netdevs=$(ls /sys/class/net) + if [ $port -eq 0 ]; then + echo $NSIM_ID > /sys/bus/netdevsim/new_device + else + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + echo 1 > $NSIM_DEV_SYS/new_port + fi + NSIM_NETDEV=`get_netdev_name old_netdevs` + + msg="new NIC device created" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + msg="VxLAN v4 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlan0 4789 $NSIM_NETDEV + new_vxlan vxlan1 4789 $NSIM_NETDEV + + msg="VxLAN v4 devices go down" + exp0=( 0 0 0 0 ) + ifconfig vxlan1 down + ifconfig vxlan0 down + check_tables + + msg="VxLAN v6 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlanA 4789 $NSIM_NETDEV 6 + + for ifc in vxlan0 vxlan1; do + ifconfig $ifc up + done + + new_vxlan vxlanB 4789 $NSIM_NETDEV 6 + + msg="another VxLAN v6 devices" + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + new_vxlan vxlanC 4790 $NSIM_NETDEV 6 + + msg="Geneve device" + exp1=( `mke 6081 2` 0 0 0 ) + new_geneve gnv0 6081 + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + exp1=( `mke 6081 2` 0 0 0 ) + check_tables + + cleanup_tuns + + msg="tunnels destroyed" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + modprobe -r geneve + modprobe -r vxlan + modprobe -r udp_tunnel + + check_tables +done + +modprobe -r netdevsim + +# Module tests +pfx="module tests" + +if modinfo netdevsim | grep udp_tunnel >/dev/null; then + err_cnt "netdevsim depends on udp_tunnel" +else + pass_cnt +fi + +modprobe netdevsim + +old_netdevs=$(ls /sys/class/net) +port=0 +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep +echo 0 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +modprobe -r vxlan +modprobe -r udp_tunnel + +msg="remove tunnels" +exp0=( 0 0 0 0 ) +check_tables + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +exp0=( 0 0 0 0 ) + +modprobe -r netdevsim +modprobe netdevsim + +# Overflow the table + +function overflow_table0 { + local pfx=$1 + + msg="create VxLANs 1/5" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="create VxLANs 2/5" + exp0=( `mke 10000 1` `mke 10001 1` 0 0 ) + new_vxlan vxlan1 10001 $NSIM_NETDEV + + msg="create VxLANs 3/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` 0 ) + new_vxlan vxlan2 10002 $NSIM_NETDEV + + msg="create VxLANs 4/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` `mke 10003 1` ) + new_vxlan vxlan3 10003 $NSIM_NETDEV + + msg="create VxLANs 5/5" + new_vxlan vxlan4 10004 $NSIM_NETDEV +} + +function overflow_table1 { + local pfx=$1 + + msg="create GENEVE 1/5" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="create GENEVE 2/5" + exp1=( `mke 20000 2` `mke 20001 2` 0 0 ) + new_geneve gnv1 20001 + + msg="create GENEVE 3/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` 0 ) + new_geneve gnv2 20002 + + msg="create GENEVE 4/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` `mke 20003 2` ) + new_geneve gnv3 20003 + + msg="create GENEVE 5/5" + new_geneve gnv4 20004 +} + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Sync all +pfx="sync all" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Destroy full NIC +pfx="destroy full" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "destroy NIC" + overflow_table1 "destroy NIC" + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# IPv4 only +pfx="IPv4 only" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v6" + new_vxlan vxlanA1 10000 $NSIM_NETDEV 6 + + ip link set dev vxlanA0 down + ip link set dev vxlanA0 up + check_tables + + msg="create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="down VxLANs v4" + exp0=( 0 0 0 0 ) + ip link set dev vxlan0 down + check_tables + + msg="up VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + ip link set dev vxlan0 up + check_tables + + msg="destroy VxLANs v4" + exp0=( 0 0 0 0 ) + del_dev vxlan0 + + msg="recreate VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + del_dev vxlanA0 + del_dev vxlanA1 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Failures +pfx="error injection" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + + msg="1 - create VxLANs v6" + exp0=( 0 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="1 - create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="1 - remove VxLANs v4" + del_dev vxlan0 + + msg="1 - remove VxLANs v6" + exp0=( 0 0 0 0 ) + del_dev vxlanA0 + + msg="2 - create GENEVE" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="2 - destroy GENEVE" + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + exp1=( `mke 20000 2` 0 0 0 ) + del_dev gnv0 + + msg="2 - create second GENEVE" + exp1=( 0 `mke 20001 2` 0 0 ) + new_geneve gnv0 20001 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# netdev flags +pfx="netdev flags" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="turn off" + exp0=( 0 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + check_tables + + msg="turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + + msg="create VxLANs v4 - off" + exp0=( 0 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="created off - turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# device initiated reset +pfx="reset notification" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 10000 1` 0 0 0 ) + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +modprobe -r netdevsim + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $num_cases checks" +else + echo "FAILED $num_errors/$num_cases checks" +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 8a6b507e34a8..1d27f52c61e6 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -21,7 +21,6 @@ #include <linux/android/binder.h> #include <linux/android/binderfs.h> -#include "../../kselftest.h" #include "../../kselftest_harness.h" #define DEFAULT_THREADS 4 @@ -37,37 +36,26 @@ fd = -EBADF; \ } -#define log_exit(format, ...) \ - ({ \ - fprintf(stderr, format "\n", ##__VA_ARGS__); \ - exit(EXIT_FAILURE); \ - }) - -static void change_mountns(void) +static void change_mountns(struct __test_metadata *_metadata) { int ret; ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare mount namespace", + strerror(errno)); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to mount / as private\n", - strerror(errno)); -} - -static void rmdir_protect_errno(const char *dir) -{ - int saved_errno = errno; - (void)rmdir(dir); - errno = saved_errno; + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount / as private", + strerror(errno)); + } } -static int __do_binderfs_test(void) +static int __do_binderfs_test(struct __test_metadata *_metadata) { - int fd, ret, saved_errno; + int fd, ret, saved_errno, result = 1; size_t len; ssize_t wret; struct binderfs_device device = { 0 }; @@ -75,113 +63,107 @@ static int __do_binderfs_test(void) char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; - change_mountns(); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - ksft_exit_fail_msg( - "%s - Failed to create binderfs mountpoint\n", + EXPECT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", strerror(errno)); + goto out; + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) { - if (errno != ENODEV) - ksft_exit_fail_msg("%s - Failed to mount binderfs\n", - strerror(errno)); - - rmdir_protect_errno(binderfs_mntpt); - return 1; + EXPECT_EQ(ret, 0) { + if (errno == ENODEV) + XFAIL(goto out, "binderfs missing"); + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + goto rmdir; } - /* binderfs mount test passed */ - ksft_inc_pass_cnt(); + /* success: binderfs mounted */ memcpy(device.name, "my-binder", strlen("my-binder")); snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - ksft_exit_fail_msg( - "%s - Failed to open binder-control device\n", + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", strerror(errno)); + goto umount; + } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to allocate new binder device\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", strerror(errno)); + goto umount; } - ksft_print_msg( - "Allocated new binder device with major %d, minor %d, and name %s\n", + TH_LOG("Allocated new binder device with major %d, minor %d, and name %s", device.major, device.minor, device.name); - /* binder device allocation test passed */ - ksft_inc_pass_cnt(); + /* success: binder device allocation */ snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt); fd = open(device_path, O_CLOEXEC | O_RDONLY); - if (fd < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to open my-binder device\n", - strerror(errno)); + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open my-binder device", + strerror(errno)); + goto umount; } ret = ioctl(fd, BINDER_VERSION, &version); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to open perform BINDER_VERSION request\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to open perform BINDER_VERSION request", strerror(errno)); + goto umount; } - ksft_print_msg("Detected binder version: %d\n", - version.protocol_version); + TH_LOG("Detected binder version: %d", version.protocol_version); - /* binder transaction with binderfs binder device passed */ - ksft_inc_pass_cnt(); + /* success: binder transaction with binderfs binder device */ ret = unlink(device_path); - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to delete binder device\n", - strerror(errno)); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to delete binder device", + strerror(errno)); + goto umount; } - /* binder device removal passed */ - ksft_inc_pass_cnt(); + /* success: binder device removal */ snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); ret = unlink(device_path); - if (!ret) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("Managed to delete binder-control device\n"); - } else if (errno != EPERM) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to delete binder-control device but exited with unexpected error code\n", + EXPECT_NE(ret, 0) { + TH_LOG("Managed to delete binder-control device"); + goto umount; + } + EXPECT_EQ(errno, EPERM) { + TH_LOG("%s - Failed to delete binder-control device but exited with unexpected error code", strerror(errno)); + goto umount; } - /* binder-control device removal failed as expected */ - ksft_inc_xfail_cnt(); + /* success: binder-control device removal failed as expected */ + result = 0; -on_error: +umount: ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", - strerror(errno)); - - /* binderfs unmount test passed */ - ksft_inc_pass_cnt(); - return 0; + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + } +rmdir: + ret = rmdir(binderfs_mntpt); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to rmdir binderfs mount", strerror(errno)); + } +out: + return result; } static int wait_for_pid(pid_t pid) @@ -291,7 +273,7 @@ static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf, return 0; } -static void change_userns(int syncfds[2]) +static void change_userns(struct __test_metadata *_metadata, int syncfds[2]) { int ret; char buf; @@ -299,25 +281,29 @@ static void change_userns(int syncfds[2]) close_prot_errno_disarm(syncfds[1]); ret = unshare(CLONE_NEWUSER); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare user namespace", + strerror(errno)); + } ret = write_nointr(syncfds[0], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } ret = read_nointr(syncfds[0], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } close_prot_errno_disarm(syncfds[0]); - if (setid_userns_root()) - ksft_exit_fail_msg("setid_userns_root() failed"); + ASSERT_EQ(setid_userns_root(), 0) { + TH_LOG("setid_userns_root() failed"); + } } -static void change_idmaps(int syncfds[2], pid_t pid) +static void change_idmaps(struct __test_metadata *_metadata, int syncfds[2], pid_t pid) { int ret; char buf; @@ -326,35 +312,42 @@ static void change_idmaps(int syncfds[2], pid_t pid) close_prot_errno_disarm(syncfds[0]); ret = read_nointr(syncfds[1], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid()); ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(UID_MAP) failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid()); ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(GID_MAP) failed"); + } ret = write_nointr(syncfds[1], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } close_prot_errno_disarm(syncfds[1]); } +struct __test_metadata *_thread_metadata; static void *binder_version_thread(void *data) { + struct __test_metadata *_metadata = _thread_metadata; int fd = PTR_TO_INT(data); struct binder_version version = { 0 }; int ret; ret = ioctl(fd, BINDER_VERSION, &version); if (ret < 0) - ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno)); + TH_LOG("%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); pthread_exit(data); } @@ -377,68 +370,79 @@ TEST(binderfs_stress) device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { + TH_LOG("%s - Failed to fork", strerror(errno)); close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); } if (pid == 0) { int i, j, k, nthreads; pthread_attr_t attr; pthread_t threads[DEFAULT_THREADS]; - change_userns(syncfds); - change_mountns(); + change_userns(_metadata, syncfds); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - log_exit("%s - Failed to create binderfs mountpoint\n", - strerror(errno)); + ASSERT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", + strerror(errno)); + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) - log_exit("%s - Failed to mount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + } for (int i = 0; i < ARRAY_SIZE(fds); i++) { snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - log_exit("%s - Failed to open binder-control device\n", strerror(errno)); + ASSERT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", + strerror(errno)); + } memset(&device, 0, sizeof(device)); snprintf(device.name, sizeof(device.name), "%d", i); ret = ioctl(fd, BINDER_CTL_ADD, &device); close_prot_errno_disarm(fd); - if (ret < 0) - log_exit("%s - Failed to allocate new binder device\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", + strerror(errno)); + } snprintf(device_path, sizeof(device_path), "%s/%d", binderfs_mntpt, i); fds[i] = open(device_path, O_RDONLY | O_CLOEXEC); - if (fds[i] < 0) - log_exit("%s - Failed to open binder device\n", strerror(errno)); + ASSERT_GE(fds[i], 0) { + TH_LOG("%s - Failed to open binder device", strerror(errno)); + } } ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - log_exit("%s - Failed to unmount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + rmdir(binderfs_mntpt); + } nthreads = get_nprocs_conf(); if (nthreads > DEFAULT_THREADS) nthreads = DEFAULT_THREADS; + _thread_metadata = _metadata; pthread_attr_init(&attr); for (k = 0; k < ARRAY_SIZE(fds); k++) { for (i = 0; i < nthreads; i++) { ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k])); if (ret) { - ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i); + TH_LOG("%s - Failed to create thread %d", + strerror(errno), i); break; } } @@ -448,7 +452,8 @@ TEST(binderfs_stress) ret = pthread_join(threads[j], &fdptr); if (ret) - ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr)); + TH_LOG("%s - Failed to join thread %d for fd %d", + strerror(errno), j, PTR_TO_INT(fdptr)); } } pthread_attr_destroy(&attr); @@ -459,11 +464,12 @@ TEST(binderfs_stress) exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); - if (ret) - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } TEST(binderfs_test_privileged) @@ -471,7 +477,7 @@ TEST(binderfs_test_privileged) if (geteuid() != 0) XFAIL(return, "Tests are not run as root. Skipping privileged tests"); - if (__do_binderfs_test() == 1) + if (__do_binderfs_test(_metadata)) XFAIL(return, "The Android binderfs filesystem is not available"); } @@ -482,31 +488,33 @@ TEST(binderfs_test_unprivileged) pid_t pid; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); + TH_LOG("%s - Failed to fork", strerror(errno)); } if (pid == 0) { - change_userns(syncfds); - if (__do_binderfs_test() == 1) + change_userns(_metadata, syncfds); + if (__do_binderfs_test(_metadata)) exit(2); exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); if (ret) { if (ret == 2) XFAIL(return, "The Android binderfs filesystem is not available"); - else - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } } diff --git a/tools/testing/selftests/firmware/settings b/tools/testing/selftests/firmware/settings new file mode 100644 index 000000000000..085e664ee093 --- /dev/null +++ b/tools/testing/selftests/firmware/settings @@ -0,0 +1,8 @@ +# The async firmware timeout is set to 1 second (but ends up being effectively +# 2 seconds). There are 3 test configs, each done with and without firmware +# present, each with 2 "nowait" functions tested 5 times. Expected time for a +# normal execution should be 2 * 3 * 2 * 2 * 5 = 120 seconds for those alone. +# Additionally, fw_fallback may take 5 seconds for internal timeouts in each +# of the 3 configs, so at least another 15 seconds are needed. Add another +# 10 seconds for each testing config: 120 + 15 + 30 +timeout=165 diff --git a/tools/testing/selftests/fpu/.gitignore b/tools/testing/selftests/fpu/.gitignore new file mode 100644 index 000000000000..d6d12ac1d9c3 --- /dev/null +++ b/tools/testing/selftests/fpu/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0+ +test_fpu diff --git a/tools/testing/selftests/fpu/Makefile b/tools/testing/selftests/fpu/Makefile new file mode 100644 index 000000000000..ea62c176ede7 --- /dev/null +++ b/tools/testing/selftests/fpu/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0+ + +LDLIBS := -lm + +TEST_GEN_PROGS := test_fpu + +TEST_PROGS := run_test_fpu.sh + +include ../lib.mk diff --git a/tools/testing/selftests/fpu/run_test_fpu.sh b/tools/testing/selftests/fpu/run_test_fpu.sh new file mode 100755 index 000000000000..d77be93ec139 --- /dev/null +++ b/tools/testing/selftests/fpu/run_test_fpu.sh @@ -0,0 +1,46 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Load kernel module for FPU tests + +uid=$(id -u) +if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit 1 +fi + +if ! which modprobe > /dev/null 2>&1; then + echo "$0: You need modprobe installed" + exit 4 +fi + +if ! modinfo test_fpu > /dev/null 2>&1; then + echo "$0: You must have the following enabled in your kernel:" + echo "CONFIG_TEST_FPU=m" + exit 4 +fi + +NR_CPUS=$(getconf _NPROCESSORS_ONLN) +if [ ! $NR_CPUS ]; then + NR_CPUS=1 +fi + +modprobe test_fpu + +if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + mount -t debugfs none /sys/kernel/debug + + if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + echo "$0: Error mounting debugfs" + exit 4 + fi +fi + +echo "Running 1000 iterations on all CPUs... " +for i in $(seq 1 1000); do + for c in $(seq 1 $NR_CPUS); do + ./test_fpu & + done +done + +rmmod test_fpu diff --git a/tools/testing/selftests/fpu/test_fpu.c b/tools/testing/selftests/fpu/test_fpu.c new file mode 100644 index 000000000000..200238522a9d --- /dev/null +++ b/tools/testing/selftests/fpu/test_fpu.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* This testcase operates with the test_fpu kernel driver. + * It modifies the FPU control register in user mode and calls the kernel + * module to perform floating point operations in the kernel. The control + * register value should be independent between kernel and user mode. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <fenv.h> +#include <unistd.h> +#include <fcntl.h> + +const char *test_fpu_path = "/sys/kernel/debug/selftest_helpers/test_fpu"; + +int main(void) +{ + char dummy[1]; + int fd = open(test_fpu_path, O_RDONLY); + + if (fd < 0) { + printf("[SKIP]\tcan't access %s: %s\n", + test_fpu_path, strerror(errno)); + return 0; + } + + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with default rounding mode failed\n"); + return 1; + } + + fesetround(FE_DOWNWARD); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with downward rounding mode failed\n"); + return 2; + } + if (fegetround() != FE_DOWNWARD) { + printf("[FAIL]\tusermode rounding mode clobbered\n"); + return 3; + } + + /* Note: the tests up to this point are quite safe and will only return + * an error. But the exception mask setting can cause misbehaving kernel + * to crash. + */ + feclearexcept(FE_ALL_EXCEPT); + feenableexcept(FE_ALL_EXCEPT); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with fpu exceptions unmasked failed\n"); + return 4; + } + if (fegetexcept() != FE_ALL_EXCEPT) { + printf("[FAIL]\tusermode fpu exception mask clobbered\n"); + return 5; + } + + printf("[OK]\ttest_fpu\n"); + return 0; +} diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index c82aa77958e5..ea2147248ebe 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -130,7 +130,7 @@ test_reqs() if [[ $KMOD_VERSION -le 19 ]]; then echo "$0: You need at least kmod 20" >&2 echo "kmod <= 19 is buggy, for details see:" >&2 - echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 + echo "https://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 exit $ksft_skip fi diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 862eee734553..8d50483fe204 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -1,11 +1,43 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * kselftest.h: kselftest framework return codes to include from - * selftests. + * kselftest.h: low-level kselftest framework to include from + * selftest programs. When possible, please use + * kselftest_harness.h instead. * * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com> * Copyright (c) 2014 Samsung Electronics Co., Ltd. * + * Using this API consists of first counting how many tests your code + * has to run, and then starting up the reporting: + * + * ksft_print_header(); + * ksft_set_plan(total_number_of_tests); + * + * For each test, report any progress, debugging, etc with: + * + * ksft_print_msg(fmt, ...); + * + * and finally report the pass/fail/skip/xfail state of the test with one of: + * + * ksft_test_result(condition, fmt, ...); + * ksft_test_result_pass(fmt, ...); + * ksft_test_result_fail(fmt, ...); + * ksft_test_result_skip(fmt, ...); + * ksft_test_result_xfail(fmt, ...); + * ksft_test_result_error(fmt, ...); + * + * When all tests are finished, clean up and exit the program with one of: + * + * ksft_exit(condition); + * ksft_exit_pass(); + * ksft_exit_fail(); + * + * If the program wants to report details on why the entire program has + * failed, it can instead exit with a message (this is usually done when + * the program is aborting before finishing all tests): + * + * ksft_exit_fail_msg(fmt, ...); + * */ #ifndef __KSELFTEST_H #define __KSELFTEST_H @@ -74,7 +106,7 @@ static inline void ksft_print_cnts(void) if (ksft_plan != ksft_test_num()) printf("# Planned tests != run tests (%u != %u)\n", ksft_plan, ksft_test_num()); - printf("# Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n", + printf("# Totals: pass:%d fail:%d xfail:%d xpass:%d skip:%d error:%d\n", ksft_cnt.ksft_pass, ksft_cnt.ksft_fail, ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass, ksft_cnt.ksft_xskip, ksft_cnt.ksft_error); @@ -120,6 +152,32 @@ static inline void ksft_test_result_fail(const char *msg, ...) va_end(args); } +/** + * ksft_test_result() - Report test success based on truth of condition + * + * @condition: if true, report test success, otherwise failure. + */ +#define ksft_test_result(condition, fmt, ...) do { \ + if (!!(condition)) \ + ksft_test_result_pass(fmt, ##__VA_ARGS__);\ + else \ + ksft_test_result_fail(fmt, ##__VA_ARGS__);\ + } while (0) + +static inline void ksft_test_result_xfail(const char *msg, ...) +{ + int saved_errno = errno; + va_list args; + + ksft_cnt.ksft_xfail++; + + va_start(args, msg); + printf("ok %d # XFAIL ", ksft_test_num()); + errno = saved_errno; + vprintf(msg, args); + va_end(args); +} + static inline void ksft_test_result_skip(const char *msg, ...) { int saved_errno = errno; @@ -128,12 +186,13 @@ static inline void ksft_test_result_skip(const char *msg, ...) ksft_cnt.ksft_xskip++; va_start(args, msg); - printf("not ok %d # SKIP ", ksft_test_num()); + printf("ok %d # SKIP ", ksft_test_num()); errno = saved_errno; vprintf(msg, args); va_end(args); } +/* TODO: how does "error" differ from "fail" or "skip"? */ static inline void ksft_test_result_error(const char *msg, ...) { int saved_errno = errno; @@ -156,11 +215,22 @@ static inline int ksft_exit_pass(void) static inline int ksft_exit_fail(void) { - printf("Bail out!\n"); ksft_print_cnts(); exit(KSFT_FAIL); } +/** + * ksft_exit() - Exit selftest based on truth of condition + * + * @condition: if true, exit self test with success, otherwise fail. + */ +#define ksft_exit(condition) do { \ + if (!!(condition)) \ + ksft_exit_pass(); \ + else \ + ksft_exit_fail(); \ + } while (0) + static inline int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; @@ -190,18 +260,30 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { - if (msg) { - int saved_errno = errno; - va_list args; + int saved_errno = errno; + va_list args; + + va_start(args, msg); - va_start(args, msg); - printf("not ok %d # SKIP ", 1 + ksft_test_num()); + /* + * FIXME: several tests misuse ksft_exit_skip so produce + * something sensible if some tests have already been run + * or a plan has been printed. Those tests should use + * ksft_test_result_skip or ksft_exit_fail_msg instead. + */ + if (ksft_plan || ksft_test_num()) { + ksft_cnt.ksft_xskip++; + printf("ok %d # SKIP ", 1 + ksft_test_num()); + } else { + printf("1..0 # SKIP "); + } + if (msg) { errno = saved_errno; vprintf(msg, args); va_end(args); - } else { - ksft_print_cnts(); } + if (ksft_test_num()) + ksft_print_cnts(); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 676b3a8b114d..cc9c846585f0 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -53,6 +53,10 @@ run_one() settings="$BASE_DIR/$DIR/settings" if [ -r "$settings" ] ; then while read line ; do + # Skip comments. + if echo "$line" | grep -q '^#'; then + continue + fi field=$(echo "$line" | cut -d= -f1) value=$(echo "$line" | cut -d= -f2-) eval "kselftest_$field"="$value" @@ -77,10 +81,10 @@ run_one() echo "ok $test_num $TEST_HDR_MSG") || (rc=$?; \ if [ $rc -eq $skip_rc ]; then \ - echo "not ok $test_num $TEST_HDR_MSG # SKIP" + echo "ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ echo "#" - echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" + echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" fi) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index c9f03ef93338..4f78e4805633 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -50,7 +50,9 @@ #ifndef __KSELFTEST_HARNESS_H #define __KSELFTEST_HARNESS_H +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <asm/types.h> #include <errno.h> #include <stdbool.h> @@ -58,10 +60,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/mman.h> #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include "kselftest.h" + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -104,26 +109,28 @@ /* Unconditional logger for internal use. */ #define __TH_LOG(fmt, ...) \ - fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \ + fprintf(TH_LOG_STREAM, "# %s:%d:%s:" fmt "\n", \ __FILE__, __LINE__, _metadata->name, ##__VA_ARGS__) /** - * XFAIL(statement, fmt, ...) + * SKIP(statement, fmt, ...) * - * @statement: statement to run after reporting XFAIL + * @statement: statement to run after reporting SKIP * @fmt: format string * @...: optional arguments * - * This forces a "pass" after reporting a failure with an XFAIL prefix, + * This forces a "pass" after reporting why something is being skipped * and runs "statement", which is usually "return" or "goto skip". */ -#define XFAIL(statement, fmt, ...) do { \ +#define SKIP(statement, fmt, ...) do { \ + snprintf(_metadata->results->reason, \ + sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \ if (TH_LOG_ENABLED) { \ - fprintf(TH_LOG_STREAM, "[ XFAIL! ] " fmt "\n", \ - ##__VA_ARGS__); \ + fprintf(TH_LOG_STREAM, "# SKIP %s\n", \ + _metadata->results->reason); \ } \ - /* TODO: find a way to pass xfail to test runner process. */ \ _metadata->passed = 1; \ + _metadata->skip = 1; \ _metadata->trigger = 0; \ statement; \ } while (0) @@ -195,8 +202,9 @@ * * .. code-block:: c * - * FIXTURE_DATA(datatype name) + * FIXTURE_DATA(datatype_name) * + * Almost always, you want just FIXTURE() instead (see below). * This call may be used when the type of the fixture data * is needed. In general, this should not be needed unless * the *self* is being passed to a helper directly. @@ -211,7 +219,7 @@ * * .. code-block:: c * - * FIXTURE(datatype name) { + * FIXTURE(fixture_name) { * type property1; * ... * }; @@ -238,7 +246,7 @@ * * .. code-block:: c * - * FIXTURE_SETUP(fixture name) { implementation } + * FIXTURE_SETUP(fixture_name) { implementation } * * Populates the required "setup" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -264,7 +272,7 @@ * * .. code-block:: c * - * FIXTURE_TEARDOWN(fixture name) { implementation } + * FIXTURE_TEARDOWN(fixture_name) { implementation } * * Populates the required "teardown" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -285,7 +293,7 @@ * * .. code-block:: c * - * FIXTURE_VARIANT(datatype name) { + * FIXTURE_VARIANT(fixture_name) { * type property1; * ... * }; @@ -305,8 +313,8 @@ * * .. code-block:: c * - * FIXTURE_ADD(datatype name) { - * .property1 = val1; + * FIXTURE_VARIANT_ADD(fixture_name, variant_name) { + * .property1 = val1, * ... * }; * @@ -672,20 +680,53 @@ __bail(_assert, _metadata->no_print, _metadata->step)) #define __INC_STEP(_metadata) \ - if (_metadata->passed && _metadata->step < 255) \ + /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ + if (_metadata->passed && _metadata->step < 253) \ _metadata->step++; +#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) + #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ __typeof__(_expected) __exp = (_expected); \ __typeof__(_seen) __seen = (_seen); \ if (_assert) __INC_STEP(_metadata); \ if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ - _expected_str, __exp_print, #_t, \ - _seen_str, __seen_print); \ + /* Report with actual signedness to avoid weird output. */ \ + switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ + case 0: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 1: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 2: { \ + long long __exp_print = (intptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 3: { \ + long long __exp_print = (intptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + } \ _metadata->passed = 0; \ /* Ensure the optional handler is triggered */ \ _metadata->trigger = 1; \ @@ -726,6 +767,10 @@ } \ } +struct __test_results { + char reason[1024]; /* Reason for test result */ +}; + struct __test_metadata; struct __fixture_variant_metadata; @@ -773,11 +818,13 @@ struct __test_metadata { struct __fixture_metadata *fixture; int termsig; int passed; + int skip; /* did SKIP get used? */ int trigger; /* extra handler after the evaluation */ int timeout; /* seconds to wait for test timeout */ bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -813,12 +860,12 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) /* Sanity check handler execution environment. */ if (!t) { fprintf(TH_LOG_STREAM, - "no active test in SIGALRM handler!?\n"); + "# no active test in SIGALRM handler!?\n"); abort(); } if (sig != SIGALRM || sig != info->si_signo) { fprintf(TH_LOG_STREAM, - "%s: SIGALRM handler caught signal %d!?\n", + "# %s: SIGALRM handler caught signal %d!?\n", t->name, sig != SIGALRM ? sig : info->si_signo); abort(); } @@ -839,7 +886,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &action, &saved_action)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to install SIGALRM handler\n", + "# %s: unable to install SIGALRM handler\n", t->name); return; } @@ -851,7 +898,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &saved_action, NULL)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to uninstall SIGALRM handler\n", + "# %s: unable to uninstall SIGALRM handler\n", t->name); return; } @@ -860,39 +907,51 @@ void __wait_for_test(struct __test_metadata *t) if (t->timed_out) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test terminated by timeout\n", t->name); + "# %s: Test terminated by timeout\n", t->name); } else if (WIFEXITED(status)) { - t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0; if (t->termsig != -1) { + t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test exited normally " - "instead of by signal (code: %d)\n", - t->name, - WEXITSTATUS(status)); - } else if (!t->passed) { - fprintf(TH_LOG_STREAM, - "%s: Test failed at step #%d\n", + "# %s: Test exited normally instead of by signal (code: %d)\n", t->name, WEXITSTATUS(status)); + } else { + switch (WEXITSTATUS(status)) { + /* Success */ + case 0: + t->passed = 1; + break; + /* SKIP */ + case 255: + t->passed = 1; + t->skip = 1; + break; + /* Other failure, assume step report. */ + default: + t->passed = 0; + fprintf(TH_LOG_STREAM, + "# %s: Test failed at step #%d\n", + t->name, + WEXITSTATUS(status)); + } } } else if (WIFSIGNALED(status)) { t->passed = 0; if (WTERMSIG(status) == SIGABRT) { fprintf(TH_LOG_STREAM, - "%s: Test terminated by assertion\n", + "# %s: Test terminated by assertion\n", t->name); } else if (WTERMSIG(status) == t->termsig) { t->passed = 1; } else { fprintf(TH_LOG_STREAM, - "%s: Test terminated unexpectedly " - "by signal %d\n", + "# %s: Test terminated unexpectedly by signal %d\n", t->name, WTERMSIG(status)); } } else { fprintf(TH_LOG_STREAM, - "%s: Test ended in some other way [%u]\n", + "# %s: Test ended in some other way [%u]\n", t->name, status); } @@ -904,25 +963,39 @@ void __run_test(struct __fixture_metadata *f, { /* reset test struct */ t->passed = 1; + t->skip = 0; t->trigger = 0; t->step = 0; t->no_print = 0; + memset(t->results->reason, 0, sizeof(t->results->reason)); - printf("[ RUN ] %s%s%s.%s\n", + ksft_print_msg(" RUN %s%s%s.%s ...\n", f->name, variant->name[0] ? "." : "", variant->name, t->name); t->pid = fork(); if (t->pid < 0) { - printf("ERROR SPAWNING TEST CHILD\n"); + ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { t->fn(t, variant); - /* return the step that failed or 0 */ - _exit(t->passed ? 0 : t->step); + if (t->skip) + _exit(255); + /* Pass is exit 0 */ + if (t->passed) + _exit(0); + /* Something else happened, report the step. */ + _exit(t->step); } else { __wait_for_test(t); } - printf("[ %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"), + ksft_print_msg(" %4s %s%s%s.%s\n", t->passed ? "OK" : "FAIL", f->name, variant->name[0] ? "." : "", variant->name, t->name); + + if (t->skip) + ksft_test_result_skip("%s\n", t->results->reason[0] ? + t->results->reason : "unknown"); + else + ksft_test_result(t->passed, "%s%s%s.%s\n", + f->name, variant->name[0] ? "." : "", variant->name, t->name); } static int test_harness_run(int __attribute__((unused)) argc, @@ -931,6 +1004,7 @@ static int test_harness_run(int __attribute__((unused)) argc, struct __fixture_variant_metadata no_variant = { .name = "", }; struct __fixture_variant_metadata *v; struct __fixture_metadata *f; + struct __test_results *results; struct __test_metadata *t; int ret = 0; unsigned int case_count = 0, test_count = 0; @@ -945,14 +1019,20 @@ static int test_harness_run(int __attribute__((unused)) argc, } } - /* TODO(wad) add optional arguments similar to gtest. */ - printf("[==========] Running %u tests from %u test cases.\n", + results = mmap(NULL, sizeof(*results), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + + ksft_print_header(); + ksft_set_plan(test_count); + ksft_print_msg("Starting %u tests from %u test cases.\n", test_count, case_count); for (f = __fixture_list; f; f = f->next) { for (v = f->variant ?: &no_variant; v; v = v->next) { for (t = f->tests; t; t = t->next) { count++; + t->results = results; __run_test(f, v, t); + t->results = NULL; if (t->passed) pass_count++; else @@ -960,9 +1040,14 @@ static int test_harness_run(int __attribute__((unused)) argc, } } } - printf("[==========] %u / %u tests passed.\n", pass_count, count); - printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); - return ret; + munmap(results, sizeof(*results)); + + ksft_print_msg("%s: %u / %u tests passed.\n", ret ? "FAILED" : "PASSED", + pass_count, count); + ksft_exit(ret == 0); + + /* unreachable */ + return KSFT_FAIL; } static void __attribute__((constructor)) __constructor_order_first(void) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index b0556c752443..7a17ea815736 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -59,9 +59,8 @@ else all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) endif -.ONESHELL: define RUN_TESTS - @BASE_DIR="$(selfdir)"; \ + BASE_DIR="$(selfdir)"; \ . $(selfdir)/kselftest/runner.sh; \ if [ "X$(summary)" != "X" ]; then \ per_test_logging=1; \ @@ -71,22 +70,21 @@ endef run_tests: all ifdef building_out_of_srctree - @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then - @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ + rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi - @if [ "X$(TEST_PROGS)" != "X" ]; then - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) - else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + @if [ "X$(TEST_PROGS)" != "X" ]; then \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) ; \ + else \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)); \ fi else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) + @$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) - $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index ee64ff8df8f4..8383eb89d88a 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -8,6 +8,7 @@ # set -e TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT +CLEAR_ONCE=/sys/kernel/debug/clear_warn_once KSELFTEST_SKIP_TEST=4 # Verify we have LKDTM available in the kernel. @@ -67,6 +68,11 @@ cleanup() { } trap cleanup EXIT +# Reset WARN_ONCE counters so we trip it each time this runs. +if [ -w $CLEAR_ONCE ] ; then + echo 1 > $CLEAR_ONCE +fi + # Save existing dmesg so we can detect new content below dmesg > "$DMESG" diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 92ca32143ae5..9d266e79c6a2 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -14,6 +14,7 @@ STACK_GUARD_PAGE_LEADING STACK_GUARD_PAGE_TRAILING UNSET_SMEP CR4 bits went missing DOUBLE_FAULT +CORRUPT_PAC UNALIGNED_LOAD_STORE_WRITE #OVERWRITE_ALLOCATION Corrupts memory on failure #WRITE_AFTER_FREE Corrupts memory on failure diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 895ec992b2f1..9491bbaa0831 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -17,6 +17,8 @@ TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh TEST_PROGS += vrf-xfrm-tests.sh +TEST_PROGS += rxtimestamp.sh +TEST_PROGS += devlink_port_split.py TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py new file mode 100755 index 000000000000..58bb7e9b88ce --- /dev/null +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -0,0 +1,277 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 + +from subprocess import PIPE, Popen +import json +import time +import argparse +import collections +import sys + +# +# Test port split configuration using devlink-port lanes attribute. +# The test is skipped in case the attribute is not available. +# +# First, check that all the ports with 1 lane fail to split. +# Second, check that all the ports with more than 1 lane can be split +# to all valid configurations (e.g., split to 2, split to 4 etc.) +# + + +Port = collections.namedtuple('Port', 'bus_info name') + + +def run_command(cmd, should_fail=False): + """ + Run a command in subprocess. + Return: Tuple of (stdout, stderr). + """ + + p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True) + stdout, stderr = p.communicate() + stdout, stderr = stdout.decode(), stderr.decode() + + if stderr != "" and not should_fail: + print("Error sending command: %s" % cmd) + print(stdout) + print(stderr) + return stdout, stderr + + +class devlink_ports(object): + """ + Class that holds information on the devlink ports, required to the tests; + if_names: A list of interfaces in the devlink ports. + """ + + def get_if_names(dev): + """ + Get a list of physical devlink ports. + Return: Array of tuples (bus_info/port, if_name). + """ + + arr = [] + + cmd = "devlink -j port show" + stdout, stderr = run_command(cmd) + assert stderr == "" + ports = json.loads(stdout)['port'] + + for port in ports: + if dev in port: + if ports[port]['flavour'] == 'physical': + arr.append(Port(bus_info=port, name=ports[port]['netdev'])) + + return arr + + def __init__(self, dev): + self.if_names = devlink_ports.get_if_names(dev) + + +def get_max_lanes(port): + """ + Get the $port's maximum number of lanes. + Return: number of lanes, e.g. 1, 2, 4 and 8. + """ + + cmd = "devlink -j port show %s" % port + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + if 'lanes' in values: + lanes = values['lanes'] + else: + lanes = 0 + return lanes + + +def get_split_ability(port): + """ + Get the $port split ability. + Return: split ability, true or false. + """ + + cmd = "devlink -j port show %s" % port.name + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + return values['splittable'] + + +def split(k, port, should_fail=False): + """ + Split $port into $k ports. + If should_fail == True, the split should fail. Otherwise, should pass. + Return: Array of sub ports after splitting. + If the $port wasn't split, the array will be empty. + """ + + cmd = "devlink port split %s count %s" % (port.bus_info, k) + stdout, stderr = run_command(cmd, should_fail=should_fail) + + if should_fail: + if not test(stderr != "", "%s is unsplittable" % port.name): + print("split an unsplittable port %s" % port.name) + return create_split_group(port, k) + else: + if stderr == "": + return create_split_group(port, k) + print("didn't split a splittable port %s" % port.name) + + return [] + + +def unsplit(port): + """ + Unsplit $port. + """ + + cmd = "devlink port unsplit %s" % port + stdout, stderr = run_command(cmd) + test(stderr == "", "Unsplit port %s" % port) + + +def exists(port, dev): + """ + Check if $port exists in the devlink ports. + Return: True is so, False otherwise. + """ + + return any(dev_port.name == port + for dev_port in devlink_ports.get_if_names(dev)) + + +def exists_and_lanes(ports, lanes, dev): + """ + Check if every port in the list $ports exists in the devlink ports and has + $lanes number of lanes after splitting. + Return: True if both are True, False otherwise. + """ + + for port in ports: + max_lanes = get_max_lanes(port) + if not exists(port, dev): + print("port %s doesn't exist in devlink ports" % port) + return False + if max_lanes != lanes: + print("port %s has %d lanes, but %s were expected" + % (port, lanes, max_lanes)) + return False + return True + + +def test(cond, msg): + """ + Check $cond and print a message accordingly. + Return: True is pass, False otherwise. + """ + + if cond: + print("TEST: %-60s [ OK ]" % msg) + else: + print("TEST: %-60s [FAIL]" % msg) + + return cond + + +def create_split_group(port, k): + """ + Create the split group for $port. + Return: Array with $k elements, which are the split port group. + """ + + return list(port.name + "s" + str(i) for i in range(k)) + + +def split_unsplittable_port(port, k): + """ + Test that splitting of unsplittable port fails. + """ + + # split to max + new_split_group = split(k, port, should_fail=True) + + if new_split_group != []: + unsplit(port.bus_info) + + +def split_splittable_port(port, k, lanes, dev): + """ + Test that splitting of splittable port passes correctly. + """ + + new_split_group = split(k, port) + + # Once the split command ends, it takes some time to the sub ifaces' + # to get their names. Use udevadm to continue only when all current udev + # events are handled. + cmd = "udevadm settle" + stdout, stderr = run_command(cmd) + assert stderr == "" + + if new_split_group != []: + test(exists_and_lanes(new_split_group, lanes/k, dev), + "split port %s into %s" % (port.name, k)) + + unsplit(port.bus_info) + + +def make_parser(): + parser = argparse.ArgumentParser(description='A test for port splitting.') + parser.add_argument('--dev', + help='The devlink handle of the device under test. ' + + 'The default is the first registered devlink ' + + 'handle.') + + return parser + + +def main(cmdline=None): + parser = make_parser() + args = parser.parse_args(cmdline) + + dev = args.dev + if not dev: + cmd = "devlink -j dev show" + stdout, stderr = run_command(cmd) + assert stderr == "" + + devs = json.loads(stdout)['dev'] + dev = list(devs.keys())[0] + + cmd = "devlink dev show %s" % dev + stdout, stderr = run_command(cmd) + if stderr != "": + print("devlink device %s can not be found" % dev) + sys.exit(1) + + ports = devlink_ports(dev) + + for port in ports.if_names: + max_lanes = get_max_lanes(port.name) + + # If max lanes is 0, do not test port splitting at all + if max_lanes == 0: + continue + + # If 1 lane, shouldn't be able to split + elif max_lanes == 1: + test(not get_split_ability(port), + "%s should not be able to split" % port.name) + split_unsplittable_port(port, max_lanes) + + # Else, splitting should pass and all the split ports should exist. + else: + lane = max_lanes + test(get_split_ability(port), + "%s should be able to split" % port.name) + while lane > 1: + split_splittable_port(port, lane, max_lanes, dev) + + lane //= 2 + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index f0e6be4c09e9..75fe24bcb9cd 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -98,6 +98,11 @@ devlink_resource_size_set() check_err $? "Failed setting path $path to size $size" } +devlink_resource_occ_get() +{ + devlink_resource_get "$@" | jq '.["occ"]' +} + devlink_reload() { local still_pending diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index 43a948feed26..dbb9fcf759e0 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -50,23 +50,6 @@ cleanup() h1_destroy } -different_speeds_get() -{ - local dev1=$1; shift - local dev2=$1; shift - local with_mode=$1; shift - local adver=$1; shift - - local -a speeds_arr - - speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver)) - if [[ ${#speeds_arr[@]} < 2 ]]; then - check_err 1 "cannot check different speeds. There are not enough speeds" - fi - - echo ${speeds_arr[0]} ${speeds_arr[1]} -} - same_speeds_autoneg_off() { # Check that when each of the reported speeds is forced, the links come diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh new file mode 100755 index 000000000000..4b42dfd4efd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -0,0 +1,102 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + autoneg + autoneg_force_mode + no_cable +" + +NUM_NETIFS=2 +source lib.sh +source ethtool_lib.sh + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + swp3=$NETIF_NO_CABLE +} + +ethtool_extended_state_check() +{ + local dev=$1; shift + local expected_ext_state=$1; shift + local expected_ext_substate=${1:-""}; shift + + local ext_state=$(ethtool $dev | grep "Link detected" \ + | cut -d "(" -f2 | cut -d ")" -f1) + local ext_substate=$(echo $ext_state | cut -sd "," -f2 \ + | sed -e 's/^[[:space:]]*//') + ext_state=$(echo $ext_state | cut -d "," -f1) + + [[ $ext_state == $expected_ext_state ]] + check_err $? "Expected \"$expected_ext_state\", got \"$ext_state\"" + + [[ $ext_substate == $expected_ext_substate ]] + check_err $? "Expected \"$expected_ext_substate\", got \"$ext_substate\"" +} + +autoneg() +{ + RET=0 + + ip link set dev $swp1 up + + sleep 4 + ethtool_extended_state_check $swp1 "Autoneg" "No partner detected" + + log_test "Autoneg, No partner detected" + + ip link set dev $swp1 down +} + +autoneg_force_mode() +{ + RET=0 + + ip link set dev $swp1 up + ip link set dev $swp2 up + + local -a speeds_arr=($(different_speeds_get $swp1 $swp2 0 0)) + local speed1=${speeds_arr[0]} + local speed2=${speeds_arr[1]} + + ethtool_set $swp1 speed $speed1 autoneg off + ethtool_set $swp2 speed $speed2 autoneg off + + sleep 4 + ethtool_extended_state_check $swp1 "Autoneg" \ + "No partner detected during force mode" + + ethtool_extended_state_check $swp2 "Autoneg" \ + "No partner detected during force mode" + + log_test "Autoneg, No partner detected during force mode" + + ethtool -s $swp2 autoneg on + ethtool -s $swp1 autoneg on + + ip link set dev $swp2 down + ip link set dev $swp1 down +} + +no_cable() +{ + RET=0 + + ip link set dev $swp3 up + + sleep 1 + ethtool_extended_state_check $swp3 "No cable" + + log_test "No cable" + + ip link set dev $swp3 down +} + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ethtool_lib.sh b/tools/testing/selftests/net/forwarding/ethtool_lib.sh index 925d229a59d8..9188e624dec0 100644 --- a/tools/testing/selftests/net/forwarding/ethtool_lib.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_lib.sh @@ -67,3 +67,20 @@ common_speeds_get() <(printf '%s\n' "${dev1_speeds[@]}" | sort -u) \ <(printf '%s\n' "${dev2_speeds[@]}" | sort -u) } + +different_speeds_get() +{ + local dev1=$1; shift + local dev2=$1; shift + local with_mode=$1; shift + local adver=$1; shift + + local -a speeds_arr + + speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver)) + if [[ ${#speeds_arr[@]} < 2 ]]; then + check_err 1 "cannot check different speeds. There are not enough speeds" + fi + + echo ${speeds_arr[0]} ${speeds_arr[1]} +} diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e2adb533c8fc..b802c14d2950 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -14,6 +14,9 @@ NETIFS[p6]=veth5 NETIFS[p7]=veth6 NETIFS[p8]=veth7 +# Port that does not have a cable connected. +NETIF_NO_CABLE=eth8 + ############################################################################## # Defines diff --git a/tools/testing/selftests/net/forwarding/pedit_l4port.sh b/tools/testing/selftests/net/forwarding/pedit_l4port.sh new file mode 100755 index 000000000000..5f20d289ee43 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_l4port.sh @@ -0,0 +1,198 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on egress of $swp2, the +# traffic is acted upon by a pedit action. An ingress filter installed on $h2 verifies that the +# packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + test_udp_sport + test_udp_dport + test_tcp_sport + test_tcp_dport +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +: ${HIT_TIMEOUT:=2000} # ms + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 nomaster + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_l4port_one() +{ + local pedit_locus=$1; shift + local pedit_prot=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + local saddr=$1; shift + local daddr=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 \ + -a own -b $h2mac -q -t $pedit_prot sp=54321,dp=12345 + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_l4port() +{ + local locus=$1; shift + local prot=$1; shift + local pedit_port=$1; shift + local flower_port=$1; shift + local port + + for port in 1 11111 65535; do + do_test_pedit_l4port_one "$locus" "$prot" \ + "$prot $pedit_port set $port" \ + ip "ip_proto $prot $flower_port $port" \ + "-A 192.0.2.1 -B 192.0.2.2" + done +} + +test_udp_sport() +{ + do_test_pedit_l4port "dev $swp1 ingress" udp sport src_port + do_test_pedit_l4port "dev $swp2 egress" udp sport src_port +} + +test_udp_dport() +{ + do_test_pedit_l4port "dev $swp1 ingress" udp dport dst_port + do_test_pedit_l4port "dev $swp2 egress" udp dport dst_port +} + +test_tcp_sport() +{ + do_test_pedit_l4port "dev $swp1 ingress" tcp sport src_port + do_test_pedit_l4port "dev $swp2 egress" tcp sport src_port +} + +test_tcp_dport() +{ + do_test_pedit_l4port "dev $swp1 ingress" tcp dport dst_port + do_test_pedit_l4port "dev $swp2 egress" tcp dport dst_port +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh new file mode 100755 index 000000000000..e714bae473fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_red.sh @@ -0,0 +1,492 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends one stream of traffic from H1 through a TBF shaper, to a RED +# within TBF shaper on $swp3. The two shapers have the same configuration, and +# thus the resulting stream should fill all available bandwidth on the latter +# shaper. A second stream is sent from H2 also via $swp3, and used to inject +# additional traffic. Since all available bandwidth is taken, this traffic has +# to go to backlog. +# +# +--------------------------+ +--------------------------+ +# | H1 | | H2 | +# | + $h1 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | TBF 10Mbps | | | | +# +-----|--------------------+ +-----|--------------------+ +# | | +# +-----|------------------------------------------------|--------------------+ +# | SW | | | +# | +--|------------------------------------------------|----------------+ | +# | | + $swp1 + $swp2 | | +# | | BR | | +# | | | | +# | | + $swp3 | | +# | | | TBF 10Mbps / RED | | +# | +--------------------------------|-----------------------------------+ | +# | | | +# +-----------------------------------|---------------------------------------+ +# | +# +-----|--------------------+ +# | H3 | | +# | + $h1 | +# | 192.0.2.3/28 | +# | | +# +--------------------------+ + +ALL_TESTS=" + ping_ipv4 + ecn_test + ecn_nodrop_test + red_test + red_qevent_test + ecn_qevent_test +" + +NUM_NETIFS=6 +CHECK_TC="yes" +source lib.sh + +BACKLOG=30000 +PKTSZ=1400 + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + mtu_set $h1 10000 + tc qdisc replace dev $h1 root handle 1: tbf \ + rate 10Mbit burst 10K limit 1M +} + +h1_destroy() +{ + tc qdisc del dev $h1 root + mtu_restore $h1 + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 + mtu_set $h2 10000 +} + +h2_destroy() +{ + mtu_restore $h2 + simple_if_fini $h2 192.0.2.2/28 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.3/28 + mtu_set $h3 10000 +} + +h3_destroy() +{ + mtu_restore $h3 + simple_if_fini $h3 192.0.2.3/28 +} + +switch_create() +{ + ip link add dev br up type bridge + ip link set dev $swp1 up master br + ip link set dev $swp2 up master br + ip link set dev $swp3 up master br + + mtu_set $swp1 10000 + mtu_set $swp2 10000 + mtu_set $swp3 10000 + + tc qdisc replace dev $swp3 root handle 1: tbf \ + rate 10Mbit burst 10K limit 1M + ip link add name _drop_test up type dummy +} + +switch_destroy() +{ + ip link del dev _drop_test + tc qdisc del dev $swp3 root + + mtu_restore $h3 + mtu_restore $h2 + mtu_restore $h1 + + ip link set dev $swp3 down nomaster + ip link set dev $swp2 down nomaster + ip link set dev $swp1 down nomaster + ip link del dev br +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + h2=${NETIFS[p3]} + swp2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h3_mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.3 " from host 1" + ping_test $h2 192.0.2.3 " from host 2" +} + +get_qdisc_backlog() +{ + qdisc_stats_get $swp3 11: .backlog +} + +get_nmarked() +{ + qdisc_stats_get $swp3 11: .marked +} + +get_qdisc_npackets() +{ + qdisc_stats_get $swp3 11: .packets +} + +get_nmirrored() +{ + link_stats_get _drop_test tx packets +} + +send_packets() +{ + local proto=$1; shift + local pkts=$1; shift + + $MZ $h2 -p $PKTSZ -a own -b $h3_mac -A 192.0.2.2 -B 192.0.2.3 -t $proto -q -c $pkts "$@" +} + +# This sends traffic in an attempt to build a backlog of $size. Returns 0 on +# success. After 10 failed attempts it bails out and returns 1. It dumps the +# backlog size to stdout. +build_backlog() +{ + local size=$1; shift + local proto=$1; shift + + local i=0 + + while :; do + local cur=$(get_qdisc_backlog) + local diff=$((size - cur)) + local pkts=$(((diff + PKTSZ - 1) / PKTSZ)) + + if ((cur >= size)); then + echo $cur + return 0 + elif ((i++ > 10)); then + echo $cur + return 1 + fi + + send_packets $proto $pkts "$@" + sleep 1 + done +} + +check_marking() +{ + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets) + local nmarked_0=$(get_nmarked) + sleep 5 + local npackets_1=$(get_qdisc_npackets) + local nmarked_1=$(get_nmarked) + + local nmarked_d=$((nmarked_1 - nmarked_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmarked_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +check_mirroring() +{ + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets) + local nmirrored_0=$(get_nmirrored) + sleep 5 + local npackets_1=$(get_qdisc_npackets) + local nmirrored_1=$(get_nmirrored) + + local nmirrored_d=$((nmirrored_1 - nmirrored_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmirrored_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +ecn_test_common() +{ + local name=$1; shift + local limit=$1; shift + local backlog + local pct + + # Build the below-the-limit backlog using UDP. We could use TCP just + # fine, but this way we get a proof that UDP is accepted when queue + # length is below the limit. The main stream is using TCP, and if the + # limit is misconfigured, we would see this traffic being ECN marked. + RET=0 + backlog=$(build_backlog $((2 * limit / 3)) udp) + check_err $? "Could not build the requested backlog" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "$name backlog < limit" + + # Now push TCP, because non-TCP traffic would be early-dropped after the + # backlog crosses the limit, and we want to make sure that the backlog + # is above the limit. + RET=0 + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." + log_test "$name backlog > limit" +} + +do_ecn_test() +{ + local limit=$1; shift + local name=ECN + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + ecn_test_common "$name" $limit + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, it should all get dropped, and backlog + # building should fail. + RET=0 + build_backlog $((2 * limit)) udp >/dev/null + check_fail $? "UDP traffic went into backlog instead of being early-dropped" + log_test "$name backlog > limit: UDP early-dropped" + + stop_traffic + sleep 1 +} + +do_ecn_nodrop_test() +{ + local limit=$1; shift + local name="ECN nodrop" + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + ecn_test_common "$name" $limit + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, in nodrop mode, make sure it goes to + # backlog as well. + RET=0 + build_backlog $((2 * limit)) udp >/dev/null + check_err $? "UDP traffic was early-dropped instead of getting into backlog" + log_test "$name backlog > limit: UDP not dropped" + + stop_traffic + sleep 1 +} + +do_red_test() +{ + local limit=$1; shift + local backlog + local pct + + # Use ECN-capable TCP to verify there's no marking even though the queue + # is above limit. + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + + # Pushing below the queue limit should work. + RET=0 + backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "RED backlog < limit" + + # Pushing above should not. + RET=0 + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_fail $? "Traffic went into backlog instead of being early-dropped" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "RED backlog > limit" + + stop_traffic + sleep 1 +} + +do_red_qevent_test() +{ + local limit=$1; shift + local backlog + local base + local now + local pct + + RET=0 + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t udp -q & + sleep 1 + + tc filter add block 10 pref 1234 handle 102 matchall skip_hw \ + action mirred egress mirror dev _drop_test + + # Push to the queue until it's at the limit. The configured limit is + # rounded by the qdisc, so this is the best we can do to get to the real + # limit. + build_backlog $((3 * limit / 2)) udp >/dev/null + + base=$(get_nmirrored) + send_packets udp 100 + sleep 1 + now=$(get_nmirrored) + ((now >= base + 100)) + check_err $? "Dropped packets not observed: 100 expected, $((now - base)) seen" + + tc filter del block 10 pref 1234 handle 102 matchall + + base=$(get_nmirrored) + send_packets udp 100 + sleep 1 + now=$(get_nmirrored) + ((now == base)) + check_err $? "Dropped packets still observed: 0 expected, $((now - base)) seen" + + log_test "RED early_dropped packets mirrored" + + stop_traffic + sleep 1 +} + +do_ecn_qevent_test() +{ + local limit=$1; shift + local name=ECN + + RET=0 + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + tc filter add block 10 pref 1234 handle 102 matchall skip_hw \ + action mirred egress mirror dev _drop_test + + backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_mirroring "== 0") + check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected == 0." + + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_mirroring ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected >= 95." + + tc filter del block 10 pref 1234 handle 102 matchall + + log_test "ECN marked packets mirrored" + + stop_traffic + sleep 1 +} + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc replace dev $swp3 parent 1:1 handle 11: red \ + limit 1M avpkt $PKTSZ probability 1 \ + min $BACKLOG max $((BACKLOG + 1)) burst 38 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 parent 1:1 +} + +ecn_test() +{ + install_qdisc ecn + do_ecn_test $BACKLOG + uninstall_qdisc +} + +ecn_nodrop_test() +{ + install_qdisc ecn nodrop + do_ecn_nodrop_test $BACKLOG + uninstall_qdisc +} + +red_test() +{ + install_qdisc + do_red_test $BACKLOG + uninstall_qdisc +} + +red_qevent_test() +{ + install_qdisc qevent early_drop block 10 + do_red_qevent_test $BACKLOG + uninstall_qdisc +} + +ecn_qevent_test() +{ + install_qdisc ecn qevent mark block 10 + do_ecn_qevent_test $BACKLOG + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh new file mode 100755 index 000000000000..160f9cccdfb7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -0,0 +1,333 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test tc-police action. +# +# +---------------------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/24 | +# | | | +# | | default via 192.0.2.2 | +# +----|----------------------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | + $rp1 | +# | 192.0.2.2/24 | +# | | +# | 198.51.100.2/24 203.0.113.2/24 | +# | + $rp2 + $rp3 | +# | | | | +# +----|-----------------------------------------|----------------------------+ +# | | +# +----|----------------------------+ +----|----------------------------+ +# | | default via 198.51.100.2 | | | default via 203.0.113.2 | +# | | | | | | +# | | 198.51.100.1/24 | | | 203.0.113.1/24 | +# | + $h2 | | + $h3 | +# | H2 (vrf) | | H3 (vrf) | +# +---------------------------------+ +---------------------------------+ + +ALL_TESTS=" + police_rx_test + police_tx_test + police_shared_test + police_rx_mirror_test + police_tx_mirror_test +" +NUM_NETIFS=6 +source tc_common.sh +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 + + ip -4 route add default vrf v$h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del default vrf v$h1 nexthop via 192.0.2.2 + + simple_if_fini $h1 192.0.2.1/24 +} + +h2_create() +{ + simple_if_init $h2 198.51.100.1/24 + + ip -4 route add default vrf v$h2 nexthop via 198.51.100.2 + + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + + ip -4 route del default vrf v$h2 nexthop via 198.51.100.2 + + simple_if_fini $h2 198.51.100.1/24 +} + +h3_create() +{ + simple_if_init $h3 203.0.113.1/24 + + ip -4 route add default vrf v$h3 nexthop via 203.0.113.2 + + tc qdisc add dev $h3 clsact +} + +h3_destroy() +{ + tc qdisc del dev $h3 clsact + + ip -4 route del default vrf v$h3 nexthop via 203.0.113.2 + + simple_if_fini $h3 203.0.113.1/24 +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + ip link set dev $rp3 up + + __addr_add_del $rp1 add 192.0.2.2/24 + __addr_add_del $rp2 add 198.51.100.2/24 + __addr_add_del $rp3 add 203.0.113.2/24 + + tc qdisc add dev $rp1 clsact + tc qdisc add dev $rp2 clsact +} + +router_destroy() +{ + tc qdisc del dev $rp2 clsact + tc qdisc del dev $rp1 clsact + + __addr_add_del $rp3 del 203.0.113.2/24 + __addr_add_del $rp2 del 198.51.100.2/24 + __addr_add_del $rp1 del 192.0.2.2/24 + + ip link set dev $rp3 down + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +police_common_test() +{ + local test_name=$1; shift + + RET=0 + + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_rx_test() +{ + # Rule to police traffic destined to $h2 on ingress of $rp1 + tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok + + police_common_test "police on rx" + + tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower +} + +police_tx_test() +{ + # Rule to police traffic destined to $h2 on egress of $rp2 + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok + + police_common_test "police on tx" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower +} + +police_shared_common_test() +{ + local dport=$1; shift + local test_name=$1; shift + + RET=0 + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=$dport -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null +} + +police_shared_test() +{ + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp src_port 12345 \ + action drop + + # Rule to police traffic destined to $h2 on ingress of $rp1 + tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok \ + index 10 + + # Rule to police a different flow destined to $h2 on egress of $rp2 + # using same policer + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 22222 \ + action police index 10 + + police_shared_common_test 54321 "police with shared policer - rx" + + police_shared_common_test 22222 "police with shared policer - tx" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_mirror_common_test() +{ + local pol_if=$1; shift + local dir=$1; shift + local test_name=$1; shift + + RET=0 + + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + # Rule to measure bandwidth of mirrored traffic on ingress of $h3 + tc filter add dev $h3 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + # Rule to police traffic destined to $h2 and mirror to $h3 + tc filter add dev $pol_if $dir protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/pipe \ + action mirred egress mirror dev $rp3 + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + local t0=$(tc_rule_stats_get $h3 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h3 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null + tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower + tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_rx_mirror_test() +{ + police_mirror_common_test $rp1 ingress "police rx and mirror" +} + +police_tx_mirror_test() +{ + police_mirror_common_test $rp2 egress "police tx and mirror" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + h3_create + router_create +} + +cleanup() +{ + pre_cleanup + + router_destroy + h3_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f50976ee7d44..aa254aefc2c3 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -5,7 +5,7 @@ KSFT_KHDR_INSTALL := 1 CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh +TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh new file mode 100755 index 000000000000..39edce4f541c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns="ns1-$rndh" +ksft_skip=4 +test_cnt=1 +ret=0 +pids=() + +flush_pids() +{ + # mptcp_connect in join mode will sleep a bit before completing, + # give it some time + sleep 1.1 + + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1 + done + pids=() +} + +cleanup() +{ + ip netns del $ns + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1 + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi +ss -h | grep -q MPTCP +if [ $? -ne 0 ];then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip +fi + +__chk_nr() +{ + local condition="$1" + local expected=$2 + local msg nr + + shift 2 + msg=$* + nr=$(ss -inmHMN $ns | $condition) + + printf "%-50s" "$msg" + if [ $nr != $expected ]; then + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + +chk_msk_nr() +{ + __chk_nr "grep -c token:" $* +} + +chk_msk_fallback_nr() +{ + __chk_nr "grep -c fallback" $* +} + +chk_msk_remote_key_nr() +{ + __chk_nr "grep -c remote_key" $* +} + + +trap cleanup EXIT +ip netns add $ns +ip -n $ns link set dev lo up + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null & +sleep 0.1 +pids[0]=$! +chk_msk_nr 0 "no msk on netns creation" + +echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null & +sleep 0.1 +pids[1]=$! +chk_msk_nr 2 "after MPC handshake " +chk_msk_remote_key_nr 2 "....chk remote_key" +chk_msk_fallback_nr 0 "....chk no fallback" +flush_pids + + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null & +pids[0]=$! +sleep 0.1 +echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null & +pids[1]=$! +sleep 0.1 +chk_msk_fallback_nr 1 "check fallback" +flush_pids + +NR_CLIENTS=100 +for I in `seq 1 $NR_CLIENTS`; do + echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null & + pids[$((I*2))]=$! +done +sleep 0.1 + +for I in `seq 1 $NR_CLIENTS`; do + echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null & + pids[$((I*2 + 1))]=$! +done +sleep 1.5 + +chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +flush_pids + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index cedee5b952ba..cad6f73a5fd0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -11,6 +11,7 @@ #include <stdio.h> #include <stdlib.h> #include <strings.h> +#include <signal.h> #include <unistd.h> #include <sys/poll.h> @@ -36,6 +37,7 @@ extern int optind; static int poll_timeout = 10 * 1000; static bool listen_mode; +static bool quit; enum cfg_mode { CFG_MODE_POLL, @@ -52,11 +54,12 @@ static int pf = AF_INET; static int cfg_sndbuf; static int cfg_rcvbuf; static bool cfg_join; +static int cfg_wait; static void die_usage(void) { fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]" - "[-l] connect_address\n"); + "[-l] [-w sec] connect_address\n"); fprintf(stderr, "\t-6 use ipv6\n"); fprintf(stderr, "\t-t num -- set poll timeout to num\n"); fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); @@ -65,9 +68,15 @@ static void die_usage(void) fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n"); fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n"); fprintf(stderr, "\t-u -- check mptcp ulp\n"); + fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); exit(1); } +static void handle_signal(int nr) +{ + quit = true; +} + static const char *getxinfo_strerr(int err) { if (err == EAI_SYSTEM) @@ -418,8 +427,8 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd) } /* leave some time for late join/announce */ - if (cfg_join) - usleep(400000); + if (cfg_wait) + usleep(cfg_wait); close(peerfd); return 0; @@ -812,11 +821,12 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:")) != -1) { + while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:w:")) != -1) { switch (c) { case 'j': cfg_join = true; cfg_mode = CFG_MODE_POLL; + cfg_wait = 400000; break; case 'l': listen_mode = true; @@ -850,6 +860,9 @@ static void parse_opts(int argc, char **argv) case 'R': cfg_rcvbuf = parse_int(optarg); break; + case 'w': + cfg_wait = atoi(optarg)*1000000; + break; } } @@ -865,6 +878,7 @@ int main(int argc, char *argv[]) { init_rng(); + signal(SIGUSR1, handle_signal); parse_opts(argc, argv); if (tcpulp_audit) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index acf02e156d20..57d75b7f6220 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -3,7 +3,7 @@ time_start=$(date +%s) -optstring="S:R:d:e:l:r:h4cm:" +optstring="S:R:d:e:l:r:h4cm:f:t" ret=0 sin="" sout="" @@ -21,6 +21,8 @@ testmode="" sndbuf=0 rcvbuf=0 options_log=true +do_tcp=0 +filesize=0 if [ $tc_loss -eq 100 ];then tc_loss=1% @@ -40,9 +42,11 @@ usage() { echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-f: size of file to transfer in bytes (default random)" echo -e "\t-S: set sndbuf value (default: use kernel default)" echo -e "\t-R: set rcvbuf value (default: use kernel default)" echo -e "\t-m: test mode (poll, sendfile; default: poll)" + echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)" } while getopts "$optstring" option;do @@ -94,6 +98,12 @@ while getopts "$optstring" option;do "m") testmode="$OPTARG" ;; + "f") + filesize="$OPTARG" + ;; + "t") + do_tcp=$((do_tcp+1)) + ;; "?") usage $0 exit 1 @@ -186,6 +196,9 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 +# use TCP syn cookies, even if no flooding was detected. +ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -385,14 +398,23 @@ do_transfer() capuser="-Z $SUDO_USER" fi - local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap" + local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" + local capopt="-i any -s 65535 -B 32768 ${capuser}" + + ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + local cappid_listener=$! - ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & - local cappid=$! + ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! sleep 1 fi + local stat_synrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + local stat_cookietx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & local spid=$! @@ -413,7 +435,8 @@ do_transfer() if $capture; then sleep 1 - kill $cappid + kill ${cappid_listener} + kill ${cappid_connector} fi local duration @@ -435,6 +458,45 @@ do_transfer() check_transfer $cin $sout "file received by server" rets=$? + local stat_synrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + + local stat_cookietx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + + expect_synrx=$((stat_synrx_last_l)) + expect_ackrx=$((stat_ackrx_last_l)) + + cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) + cookies=${cookies##*=} + + if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then + expect_synrx=$((stat_synrx_last_l+1)) + expect_ackrx=$((stat_ackrx_last_l+1)) + fi + if [ $cookies -eq 2 ];then + if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: did not advance" + fi + if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: did not advance" + fi + else + if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: changed" + fi + if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: changed" + fi + fi + + if [ $expect_synrx -ne $stat_synrx_now_l ] ;then + echo "${listener_ns} SYNRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $expect_ackrx -ne $stat_ackrx_now_l ] ;then + echo "${listener_ns} ACKRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then echo "$duration [ OK ]" cat "$capout" @@ -449,20 +511,25 @@ make_file() { local name=$1 local who=$2 + local SIZE=$filesize + local ksize + local rem - local SIZE TSIZE - SIZE=$((RANDOM % (1024 * 8))) - TSIZE=$((SIZE * 1024)) + if [ $SIZE -eq 0 ]; then + local MAXSIZE=$((1024 * 1024 * 8)) + local MINSIZE=$((1024 * 256)) - dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE)) + fi - SIZE=$((RANDOM % 1024)) - SIZE=$((SIZE + 128)) - TSIZE=$((TSIZE + SIZE)) - dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + ksize=$((SIZE / 1024)) + rem=$((SIZE - (ksize * 1024))) + + dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" - echo "Created $name (size $TSIZE) containing data sent by $who" + echo "Created $name (size $(du -b "$name")) containing data sent by $who" } run_tests_lo() @@ -497,9 +564,11 @@ run_tests_lo() return 1 fi - # don't bother testing fallback tcp except for loopback case. - if [ ${listener_ns} != ${connector_ns} ]; then - return 0 + if [ $do_tcp -eq 0 ]; then + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi fi do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} @@ -516,6 +585,15 @@ run_tests_lo() return 1 fi + if [ $do_tcp -gt 1 ] ;then + do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + fi + return 0 } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dd42c2f692d0..f39c1129ce5f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -72,6 +72,15 @@ reset() init } +reset_with_cookies() +{ + reset + + for netns in "$ns1" "$ns2";do + ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 + done +} + for arg in "$@"; do if [ "$arg" = "-c" ]; then capture=1 @@ -138,7 +147,7 @@ do_transfer() capuser="-Z $SUDO_USER" fi - capfile="mp_join-${listener_ns}.pcap" + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") echo "Capturing traffic for test $TEST_COUNT into $capfile" ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & @@ -227,7 +236,7 @@ chk_join_nr() local count local dump_stats - printf "%-36s %s" "$msg" "syn" + printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then @@ -354,4 +363,57 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 +# single subflow, syncookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "single subflow with syn cookies" 1 1 1 + +# multiple subflows with syn cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "multiple subflows with syn cookies" 2 2 2 + +# multiple subflows limited by server +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows limited by server w cookies" 2 2 1 + +# test signal address with cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "signal address with syn cookies" 1 1 1 + +# test cookie with subflow and signal +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 1 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflow and signal w cookies" 2 2 2 + +# accept and use add_addr with additional subflows +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns2 ./pm_nl_ctl limits 1 3 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows and signal w. cookies" 3 3 3 + exit $ret diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 4b02933cab8a..bdc03a2097e8 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -125,9 +125,8 @@ static int do_setcpu(int cpu) CPU_ZERO(&mask); CPU_SET(cpu, &mask); if (sched_setaffinity(0, sizeof(mask), &mask)) - error(1, 0, "setaffinity %d", cpu); - - if (cfg_verbose) + fprintf(stderr, "cpu: unable to pin, may increase variance.\n"); + else if (cfg_verbose) fprintf(stderr, "cpu: %u\n", cpu); return 0; diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 77c09cd339c3..6bbf69a28e12 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -59,6 +59,45 @@ # Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of # VXLAN # +# - pmtu_ipv{4,6}_br_vxlan{4,6}_exception +# Set up three namespaces, A, B, and C, with routing between A and B over +# R1. R2 is unused in these tests. A has a veth connection to C, and is +# connected to B via a VXLAN endpoint, which is directly bridged to C. +# MTU on the B-R1 link is lower than other MTUs. +# +# Check that both C and A are able to communicate with B over the VXLAN +# tunnel, and that PMTU exceptions with the correct values are created. +# +# segment a_r1 segment b_r1 b_r1: 4000 +# .--------------R1--------------. everything +# C---veth A B else: 5000 +# ' bridge | +# '---- - - - - - VXLAN - - - - - - - ' +# +# - pmtu_ipv{4,6}_br_geneve{4,6}_exception +# Same as pmtu_ipv{4,6}_br_vxlan{4,6}_exception, with a GENEVE tunnel +# instead. +# +# - pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception +# Set up two namespaces, B, and C, with routing between the init namespace +# and B over R1. A and R2 are unused in these tests. The init namespace +# has a veth connection to C, and is connected to B via a VXLAN endpoint, +# which is handled by Open vSwitch and bridged to C. MTU on the B-R1 link +# is lower than other MTUs. +# +# Check that C is able to communicate with B over the VXLAN tunnel, and +# that PMTU exceptions with the correct values are created. +# +# segment a_r1 segment b_r1 b_r1: 4000 +# .--------------R1--------------. everything +# C---veth init B else: 5000 +# '- ovs | +# '---- - - - - - VXLAN - - - - - - - ' +# +# - pmtu_ipv{4,6}_ovs_geneve{4,6}_exception +# Same as pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception, with a GENEVE tunnel +# instead. +# # - pmtu_ipv{4,6}_fou{4,6}_exception # Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation # (FoU) over IPv4/IPv6, instead of VXLAN @@ -147,6 +186,22 @@ tests=" pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions 1 pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions 1 pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions 1 + pmtu_ipv4_br_vxlan4_exception IPv4, bridged vxlan4: PMTU exceptions 1 + pmtu_ipv6_br_vxlan4_exception IPv6, bridged vxlan4: PMTU exceptions 1 + pmtu_ipv4_br_vxlan6_exception IPv4, bridged vxlan6: PMTU exceptions 1 + pmtu_ipv6_br_vxlan6_exception IPv6, bridged vxlan6: PMTU exceptions 1 + pmtu_ipv4_br_geneve4_exception IPv4, bridged geneve4: PMTU exceptions 1 + pmtu_ipv6_br_geneve4_exception IPv6, bridged geneve4: PMTU exceptions 1 + pmtu_ipv4_br_geneve6_exception IPv4, bridged geneve6: PMTU exceptions 1 + pmtu_ipv6_br_geneve6_exception IPv6, bridged geneve6: PMTU exceptions 1 + pmtu_ipv4_ovs_vxlan4_exception IPv4, OVS vxlan4: PMTU exceptions 1 + pmtu_ipv6_ovs_vxlan4_exception IPv6, OVS vxlan4: PMTU exceptions 1 + pmtu_ipv4_ovs_vxlan6_exception IPv4, OVS vxlan6: PMTU exceptions 1 + pmtu_ipv6_ovs_vxlan6_exception IPv6, OVS vxlan6: PMTU exceptions 1 + pmtu_ipv4_ovs_geneve4_exception IPv4, OVS geneve4: PMTU exceptions 1 + pmtu_ipv6_ovs_geneve4_exception IPv6, OVS geneve4: PMTU exceptions 1 + pmtu_ipv4_ovs_geneve6_exception IPv4, OVS geneve6: PMTU exceptions 1 + pmtu_ipv6_ovs_geneve6_exception IPv6, OVS geneve6: PMTU exceptions 1 pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions 1 pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions 1 pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions 1 @@ -173,10 +228,12 @@ tests=" NS_A="ns-A" NS_B="ns-B" +NS_C="ns-C" NS_R1="ns-R1" NS_R2="ns-R2" ns_a="ip netns exec ${NS_A}" ns_b="ip netns exec ${NS_B}" +ns_c="ip netns exec ${NS_C}" ns_r1="ip netns exec ${NS_R1}" ns_r2="ip netns exec ${NS_R2}" @@ -239,9 +296,11 @@ routes_nh=" veth4_a_addr="192.168.1.1" veth4_b_addr="192.168.1.2" +veth4_c_addr="192.168.2.10" veth4_mask="24" veth6_a_addr="fd00:1::a" veth6_b_addr="fd00:1::b" +veth6_c_addr="fd00:2::c" veth6_mask="64" tunnel4_a_addr="192.168.2.1" @@ -428,7 +487,7 @@ setup_ip6ip6() { } setup_namespaces() { - for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 # Disable DAD, so that we don't have to wait to use the @@ -484,6 +543,7 @@ setup_vxlan_or_geneve() { a_addr="${2}" b_addr="${3}" opts="${4}" + br_if_a="${5}" if [ "${type}" = "vxlan" ]; then opts="${opts} ttl 64 dstport 4789" @@ -497,10 +557,16 @@ setup_vxlan_or_geneve() { run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1 run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} - run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a - run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + if [ -n "${br_if_a}" ]; then + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${br_if_a} + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${br_if_a} + run_cmd ${ns_a} ip link set ${type}_a master ${br_if_a} + else + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + fi - run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b run_cmd ${ns_a} ip link set ${type}_a up @@ -516,11 +582,27 @@ setup_vxlan4() { } setup_geneve6() { - setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 + setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" } setup_vxlan6() { - setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 + setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" +} + +setup_bridged_geneve4() { + setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" "br0" +} + +setup_bridged_vxlan4() { + setup_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" "br0" +} + +setup_bridged_geneve6() { + setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0" +} + +setup_bridged_vxlan6() { + setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0" } setup_xfrm() { @@ -630,6 +712,80 @@ setup_routing() { return 0 } +setup_bridge() { + run_cmd ${ns_a} ip link add br0 type bridge || return 2 + run_cmd ${ns_a} ip link set br0 up + + run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C + run_cmd ${ns_c} ip link set veth_A-C netns ns-A + + run_cmd ${ns_a} ip link set veth_A-C up + run_cmd ${ns_c} ip link set veth_C-A up + run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A + run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A + run_cmd ${ns_a} ip link set veth_A-C master br0 +} + +setup_ovs_vxlan_or_geneve() { + type="${1}" + a_addr="${2}" + b_addr="${3}" + + if [ "${type}" = "vxlan" ]; then + opts="${opts} ttl 64 dstport 4789" + opts_b="local ${b_addr}" + fi + + run_cmd ovs-vsctl add-port ovs_br0 ${type}_a -- \ + set interface ${type}_a type=${type} \ + options:remote_ip=${b_addr} options:key=1 options:csum=true || return 1 + + run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} || return 1 + + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b + + run_cmd ${ns_b} ip link set ${type}_b up +} + +setup_ovs_geneve4() { + setup_ovs_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 +} + +setup_ovs_vxlan4() { + setup_ovs_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 +} + +setup_ovs_geneve6() { + setup_ovs_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 +} + +setup_ovs_vxlan6() { + setup_ovs_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 +} + +setup_ovs_bridge() { + run_cmd ovs-vsctl add-br ovs_br0 || return 2 + run_cmd ip link set ovs_br0 up + + run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C + run_cmd ${ns_c} ip link set veth_A-C netns 1 + + run_cmd ip link set veth_A-C up + run_cmd ${ns_c} ip link set veth_C-A up + run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A + run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A + run_cmd ovs-vsctl add-port ovs_br0 veth_A-C + + # Move veth_A-R1 to init + run_cmd ${ns_a} ip link set veth_A-R1 netns 1 + run_cmd ip addr add ${prefix4}.${a_r1}.1/${veth4_mask} dev veth_A-R1 + run_cmd ip addr add ${prefix6}:${a_r1}::1/${veth6_mask} dev veth_A-R1 + run_cmd ip link set veth_A-R1 up + run_cmd ip route add ${prefix4}.${b_r1}.1 via ${prefix4}.${a_r1}.2 + run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -657,9 +813,14 @@ cleanup() { done tcpdump_pids= - for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done + + ip link del veth_A-C 2>/dev/null + ip link del veth_A-R1 2>/dev/null + ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null + ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null } mtu() { @@ -892,6 +1053,177 @@ test_pmtu_ipv6_geneve6_exception() { test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6 } +test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { + type=${1} + family=${2} + outer_family=${3} + ll_mtu=4000 + + if [ ${outer_family} -eq 4 ]; then + setup namespaces routing bridge bridged_${type}4 || return 2 + # IPv4 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14)) + else + setup namespaces routing bridge bridged_${type}6 || return 2 + # IPv6 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14)) + fi + + trace "${ns_a}" ${type}_a "${ns_b}" ${type}_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B \ + "${ns_a}" br0 "${ns_a}" veth-A-C \ + "${ns_c}" veth_C-A + + if [ ${family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_a}" br0 $((${ll_mtu} + 1000)) + mtu "${ns_a}" veth_A-C $((${ll_mtu} + 1000)) + mtu "${ns_c}" veth_C-A $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) + + run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} || return 1 + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" +} + +test_pmtu_ipv4_br_vxlan4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 4 4 +} + +test_pmtu_ipv6_br_vxlan4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 6 4 +} + +test_pmtu_ipv4_br_geneve4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 4 +} + +test_pmtu_ipv6_br_geneve4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 4 +} + +test_pmtu_ipv4_br_vxlan6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 4 6 +} + +test_pmtu_ipv6_br_vxlan6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 6 6 +} + +test_pmtu_ipv4_br_geneve6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 6 +} + +test_pmtu_ipv6_br_geneve6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 6 +} + +test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception() { + type=${1} + family=${2} + outer_family=${3} + ll_mtu=4000 + + if [ ${outer_family} -eq 4 ]; then + setup namespaces routing ovs_bridge ovs_${type}4 || return 2 + # IPv4 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14)) + else + setup namespaces routing ovs_bridge ovs_${type}6 || return 2 + # IPv6 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14)) + fi + + if [ "${type}" = "vxlan" ]; then + tun_a="vxlan_sys_4789" + elif [ "${type}" = "geneve" ]; then + tun_a="genev_sys_6081" + fi + + trace "" "${tun_a}" "${ns_b}" ${type}_b \ + "" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B \ + "" ovs_br0 "" veth-A-C \ + "${ns_c}" veth_C-A + + if [ ${family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + # Create route exception by exceeding link layer MTU + mtu "" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "" ovs_br0 $((${ll_mtu} + 1000)) + mtu "" veth_A-C $((${ll_mtu} + 1000)) + mtu "${ns_c}" veth_C-A $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "" ${tun_a} $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) + + run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 20 -s $((${ll_mtu} + 500)) ${dst} || return 1 + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on Open vSwitch ${type} interface" +} + +test_pmtu_ipv4_ovs_vxlan4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 4 4 +} + +test_pmtu_ipv6_ovs_vxlan4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 6 4 +} + +test_pmtu_ipv4_ovs_geneve4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 4 +} + +test_pmtu_ipv6_ovs_geneve4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 4 +} + +test_pmtu_ipv4_ovs_vxlan6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 4 6 +} + +test_pmtu_ipv6_ovs_vxlan6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 6 6 +} + +test_pmtu_ipv4_ovs_geneve6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 6 +} + +test_pmtu_ipv6_ovs_geneve6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 6 +} + test_pmtu_ipvX_over_fouY_or_gueY() { inner_family=${1} outer_family=${2} diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index bdbf4b3125b6..7c38a909f8b8 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -5,7 +5,6 @@ # set -e devdummy="test-dummy0" -ret=0 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -66,7 +65,7 @@ kci_test_bridge() devbr="test-br0" vlandev="testbr-vlan1" - ret=0 + local ret=0 ip link add name "$devbr" type bridge check_err $? @@ -113,7 +112,7 @@ kci_test_gre() rem=10.42.42.1 loc=10.0.0.1 - ret=0 + local ret=0 ip tunnel add $gredev mode gre remote $rem local $loc ttl 1 check_err $? ip link set $gredev up @@ -149,7 +148,7 @@ kci_test_gre() kci_test_tc() { dev=lo - ret=0 + local ret=0 tc qdisc add dev "$dev" root handle 1: htb check_err $? @@ -184,7 +183,7 @@ kci_test_tc() kci_test_polrouting() { - ret=0 + local ret=0 ip rule add fwmark 1 lookup 100 check_err $? ip route add local 0.0.0.0/0 dev lo table 100 @@ -207,7 +206,7 @@ kci_test_route_get() { local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) - ret=0 + local ret=0 ip route get 127.0.0.1 > /dev/null check_err $? @@ -290,7 +289,7 @@ kci_test_promote_secondaries() kci_test_addrlabel() { - ret=0 + local ret=0 ip addrlabel add prefix dead::/64 dev lo label 1 check_err $? @@ -330,7 +329,7 @@ kci_test_addrlabel() kci_test_ifalias() { - ret=0 + local ret=0 namewant=$(uuidgen) syspathname="/sys/class/net/$devdummy/ifalias" @@ -385,7 +384,7 @@ kci_test_ifalias() kci_test_vrf() { vrfname="test-vrf" - ret=0 + local ret=0 ip link show type vrf 2>/dev/null if [ $? -ne 0 ]; then @@ -425,7 +424,7 @@ kci_test_vrf() kci_test_encap_vxlan() { - ret=0 + local ret=0 vxlan="test-vxlan0" vlan="test-vlan0" testns="$1" @@ -511,7 +510,7 @@ kci_test_encap_vxlan() kci_test_encap_fou() { - ret=0 + local ret=0 name="test-fou" testns="$1" @@ -548,7 +547,7 @@ kci_test_encap_fou() kci_test_encap() { testns="testns" - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -565,15 +564,18 @@ kci_test_encap() check_err $? kci_test_encap_vxlan "$testns" + check_err $? kci_test_encap_fou "$testns" + check_err $? ip netns del "$testns" + return $ret } kci_test_macsec() { msname="test_macsec0" - ret=0 + local ret=0 ip macsec help 2>&1 | grep -q "^Usage: ip macsec" if [ $? -ne 0 ]; then @@ -631,7 +633,7 @@ kci_test_macsec() #------------------------------------------------------------------- kci_test_ipsec() { - ret=0 + local ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" srcip=192.168.123.1 dstip=192.168.123.2 @@ -731,7 +733,7 @@ kci_test_ipsec() #------------------------------------------------------------------- kci_test_ipsec_offload() { - ret=0 + local ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" srcip=192.168.123.3 dstip=192.168.123.4 @@ -841,7 +843,7 @@ kci_test_gretap() { testns="testns" DEV_NS=gretap00 - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -891,7 +893,7 @@ kci_test_ip6gretap() { testns="testns" DEV_NS=ip6gretap00 - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -941,7 +943,7 @@ kci_test_erspan() { testns="testns" DEV_NS=erspan00 - ret=0 + local ret=0 ip link help erspan 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then @@ -1006,7 +1008,7 @@ kci_test_ip6erspan() { testns="testns" DEV_NS=ip6erspan00 - ret=0 + local ret=0 ip link help ip6erspan 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then @@ -1077,7 +1079,7 @@ kci_test_fdb_get() test_mac=de:ad:be:ef:13:37 localip="10.0.2.2" dstip="10.0.2.3" - ret=0 + local ret=0 bridge fdb help 2>&1 |grep -q 'bridge fdb get' if [ $? -ne 0 ];then @@ -1125,7 +1127,7 @@ kci_test_neigh_get() dstmac=de:ad:be:ef:13:37 dstip=10.0.2.4 dstip6=dead::2 - ret=0 + local ret=0 ip neigh help 2>&1 |grep -q 'ip neigh get' if [ $? -ne 0 ];then @@ -1175,6 +1177,7 @@ kci_test_neigh_get() kci_test_rtnl() { + local ret=0 kci_add_dummy if [ $ret -ne 0 ];then echo "FAIL: cannot add dummy interface" @@ -1182,27 +1185,48 @@ kci_test_rtnl() fi kci_test_polrouting + check_err $? kci_test_route_get + check_err $? kci_test_addrlft + check_err $? kci_test_promote_secondaries + check_err $? kci_test_tc + check_err $? kci_test_gre + check_err $? kci_test_gretap + check_err $? kci_test_ip6gretap + check_err $? kci_test_erspan + check_err $? kci_test_ip6erspan + check_err $? kci_test_bridge + check_err $? kci_test_addrlabel + check_err $? kci_test_ifalias + check_err $? kci_test_vrf + check_err $? kci_test_encap + check_err $? kci_test_macsec + check_err $? kci_test_ipsec + check_err $? kci_test_ipsec_offload + check_err $? kci_test_fdb_get + check_err $? kci_test_neigh_get + check_err $? kci_del_dummy + return $ret } #check for needed privileges @@ -1221,4 +1245,4 @@ done kci_test_rtnl -exit $ret +exit $? diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index bcb79ba1f214..e4613ce4ed69 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -44,6 +44,7 @@ struct test_case { struct options sockopt; struct tstamps expected; bool enabled; + bool warn_on_fail; }; struct sof_flag { @@ -67,44 +68,44 @@ static struct socket_type socket_types[] = { static struct test_case test_cases[] = { { {}, {} }, { - { so_timestamp: 1 }, - { tstamp: true } + { .so_timestamp = 1 }, + { .tstamp = true } }, { - { so_timestampns: 1 }, - { tstampns: true } + { .so_timestampns = 1 }, + { .tstampns = true } }, { - { so_timestamp: 1, so_timestampns: 1 }, - { tstampns: true } + { .so_timestamp = 1, .so_timestampns = 1 }, + { .tstampns = true } }, { - { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE }, + { .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE }, {} }, { /* Loopback device does not support hw timestamps. */ - { so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE }, + { .so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE }, {} }, { - { so_timestamping: SOF_TIMESTAMPING_SOFTWARE }, - {} + { .so_timestamping = SOF_TIMESTAMPING_SOFTWARE }, + .warn_on_fail = true }, { - { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE + { .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_RX_HARDWARE }, {} }, { - { so_timestamping: SOF_TIMESTAMPING_SOFTWARE + { .so_timestamping = SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE }, - { swtstamp: true } + { .swtstamp = true } }, { - { so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE + { .so_timestamp = 1, .so_timestamping = SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE }, - { tstamp: true, swtstamp: true } + { .tstamp = true, .swtstamp = true } }, }; @@ -115,6 +116,9 @@ static struct option long_options[] = { { "tcp", no_argument, 0, 't' }, { "udp", no_argument, 0, 'u' }, { "ip", no_argument, 0, 'i' }, + { "strict", no_argument, 0, 'S' }, + { "ipv4", no_argument, 0, '4' }, + { "ipv6", no_argument, 0, '6' }, { NULL, 0, NULL, 0 }, }; @@ -270,37 +274,55 @@ void config_so_flags(int rcv, struct options o) error(1, errno, "Failed to set SO_TIMESTAMPING"); } -bool run_test_case(struct socket_type s, struct test_case t) +bool run_test_case(struct socket_type *s, int test_num, char ip_version, + bool strict) { - int port = (s.type == SOCK_RAW) ? 0 : next_port++; + union { + struct sockaddr_in6 addr6; + struct sockaddr_in addr4; + struct sockaddr addr_un; + } addr; int read_size = op_size; - struct sockaddr_in addr; + int src, dst, rcv, port; + socklen_t addr_size; bool failed = false; - int src, dst, rcv; - src = socket(AF_INET, s.type, s.protocol); + port = (s->type == SOCK_RAW) ? 0 : next_port++; + memset(&addr, 0, sizeof(addr)); + if (ip_version == '4') { + addr.addr4.sin_family = AF_INET; + addr.addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr.addr4.sin_port = htons(port); + addr_size = sizeof(addr.addr4); + if (s->type == SOCK_RAW) + read_size += 20; /* for IPv4 header */ + } else { + addr.addr6.sin6_family = AF_INET6; + addr.addr6.sin6_addr = in6addr_loopback; + addr.addr6.sin6_port = htons(port); + addr_size = sizeof(addr.addr6); + } + printf("Starting testcase %d over ipv%c...\n", test_num, ip_version); + src = socket(addr.addr_un.sa_family, s->type, + s->protocol); if (src < 0) error(1, errno, "Failed to open src socket"); - dst = socket(AF_INET, s.type, s.protocol); + dst = socket(addr.addr_un.sa_family, s->type, + s->protocol); if (dst < 0) error(1, errno, "Failed to open dst socket"); - memset(&addr, 0, sizeof(addr)); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); - addr.sin_port = htons(port); - - if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0) + if (bind(dst, &addr.addr_un, addr_size) < 0) error(1, errno, "Failed to bind to port %d", port); - if (s.type == SOCK_STREAM && (listen(dst, 1) < 0)) + if (s->type == SOCK_STREAM && (listen(dst, 1) < 0)) error(1, errno, "Failed to listen"); - if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0) + if (connect(src, &addr.addr_un, addr_size) < 0) error(1, errno, "Failed to connect"); - if (s.type == SOCK_STREAM) { + if (s->type == SOCK_STREAM) { rcv = accept(dst, NULL, NULL); if (rcv < 0) error(1, errno, "Failed to accept"); @@ -309,17 +331,22 @@ bool run_test_case(struct socket_type s, struct test_case t) rcv = dst; } - config_so_flags(rcv, t.sockopt); + config_so_flags(rcv, test_cases[test_num].sockopt); usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */ do_send(src); - if (s.type == SOCK_RAW) - read_size += 20; /* for IP header */ - failed = do_recv(rcv, read_size, t.expected); + failed = do_recv(rcv, read_size, test_cases[test_num].expected); close(rcv); close(src); + if (failed) { + printf("FAILURE in testcase %d over ipv%c ", test_num, + ip_version); + print_test_case(&test_cases[test_num]); + if (!strict && test_cases[test_num].warn_on_fail) + failed = false; + } return failed; } @@ -327,6 +354,9 @@ int main(int argc, char **argv) { bool all_protocols = true; bool all_tests = true; + bool cfg_ipv4 = false; + bool cfg_ipv6 = false; + bool strict = false; int arg_index = 0; int failures = 0; int s, t, opt; @@ -362,6 +392,15 @@ int main(int argc, char **argv) all_protocols = false; socket_types[0].enabled = true; break; + case 'S': + strict = true; + break; + case '4': + cfg_ipv4 = true; + break; + case '6': + cfg_ipv6 = true; + break; default: error(1, 0, "Failed to parse parameters."); } @@ -375,13 +414,14 @@ int main(int argc, char **argv) for (t = 0; t < ARRAY_SIZE(test_cases); t++) { if (!all_tests && !test_cases[t].enabled) continue; - - printf("Starting testcase %d...\n", t); - if (run_test_case(socket_types[s], test_cases[t])) { - failures++; - printf("FAILURE in test case "); - print_test_case(&test_cases[t]); - } + if (cfg_ipv4 || !cfg_ipv6) + if (run_test_case(&socket_types[s], t, '4', + strict)) + failures++; + if (cfg_ipv6 || !cfg_ipv4) + if (run_test_case(&socket_types[s], t, '6', + strict)) + failures++; } } if (!failures) diff --git a/tools/testing/selftests/net/rxtimestamp.sh b/tools/testing/selftests/net/rxtimestamp.sh new file mode 100755 index 000000000000..91631e88bf46 --- /dev/null +++ b/tools/testing/selftests/net/rxtimestamp.sh @@ -0,0 +1,4 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +./in_netns.sh ./rxtimestamp $@ diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index 011b0da6b033..490a8cca708a 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -64,6 +64,7 @@ static int cfg_payload_len = 10; static int cfg_poll_timeout = 100; static int cfg_delay_snd; static int cfg_delay_ack; +static int cfg_delay_tolerance_usec = 500; static bool cfg_show_payload; static bool cfg_do_pktinfo; static bool cfg_busy_poll; @@ -152,11 +153,12 @@ static void validate_key(int tskey, int tstype) static void validate_timestamp(struct timespec *cur, int min_delay) { - int max_delay = min_delay + 500 /* processing time upper bound */; int64_t cur64, start64; + int max_delay; cur64 = timespec_to_us64(cur); start64 = timespec_to_us64(&ts_usr); + max_delay = min_delay + cfg_delay_tolerance_usec; if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { fprintf(stderr, "ERROR: %lu us expected between %d and %d\n", @@ -683,6 +685,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -r: use raw\n" " -R: use raw (IP_HDRINCL)\n" " -S N: usec to sleep before reading error queue\n" + " -t N: tolerance (usec) for timestamp validation\n" " -u: use udp\n" " -v: validate SND delay (usec)\n" " -V: validate ACK delay (usec)\n" @@ -697,7 +700,7 @@ static void parse_opt(int argc, char **argv) int c; while ((c = getopt(argc, argv, - "46bc:CeEFhIl:LnNp:PrRS:uv:V:x")) != -1) { + "46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -760,6 +763,9 @@ static void parse_opt(int argc, char **argv) case 'S': cfg_sleep_usec = strtoul(optarg, NULL, 10); break; + case 't': + cfg_delay_tolerance_usec = strtoul(optarg, NULL, 10); + break; case 'u': proto_count++; cfg_proto = SOCK_DGRAM; diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh new file mode 100755 index 000000000000..18b982d611de --- /dev/null +++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh @@ -0,0 +1,396 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is designed for testing the new VRF strict_mode functionality. + +ret=0 + +# identifies the "init" network namespace which is often called root network +# namespace. +INIT_NETNS_NAME="init" + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +ip_expand_args() +{ + local nsname=$1 + local nsarg="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + nsarg="-netns ${nsname}" + fi + + echo "${nsarg}" +} + +vrf_count() +{ + local nsname=$1 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} -o link show type vrf | wc -l +} + +count_vrf_by_table_id() +{ + local nsname=$1 + local tableid=$2 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} -d -o link show type vrf | grep "table ${tableid}" | wc -l +} + +add_vrf() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link add ${vrfname} type vrf table ${vrftable} &>/dev/null +} + +add_vrf_and_check() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local cnt + local rc + + add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$? + + cnt=$(count_vrf_by_table_id ${nsname} ${vrftable}) + + log_test ${rc} 0 "${nsname}: add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}" +} + +add_vrf_and_check_fail() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local cnt + local rc + + add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$? + + cnt=$(count_vrf_by_table_id ${nsname} ${vrftable}) + + log_test ${rc} 2 "${nsname}: CANNOT add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}" +} + +del_vrf_and_check() +{ + local nsname=$1 + local vrfname=$2 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link del ${vrfname} + log_test $? 0 "${nsname}: remove vrf ${vrfname}" +} + +config_vrf_and_check() +{ + local nsname=$1 + local addr=$2 + local vrfname=$3 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link set dev ${vrfname} up && \ + ip ${nsarg} addr add ${addr} dev ${vrfname} + log_test $? 0 "${nsname}: vrf ${vrfname} up, addr ${addr}" +} + +read_strict_mode() +{ + local nsname=$1 + local rval + local rc=0 + local nsexec="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + # a custom network namespace is provided + nsexec="ip netns exec ${nsname}" + fi + + rval="$(${nsexec} bash -c "cat /proc/sys/net/vrf/strict_mode" | \ + grep -E "^[0-1]$")" &> /dev/null + if [ $? -ne 0 ]; then + # set errors + rval=255 + rc=1 + fi + + # on success, rval can be only 0 or 1; on error, rval is equal to 255 + echo ${rval} + return ${rc} +} + +read_strict_mode_compare_and_check() +{ + local nsname=$1 + local expected=$2 + local res + + res="$(read_strict_mode ${nsname})" + log_test ${res} ${expected} "${nsname}: check strict_mode=${res}" +} + +set_strict_mode() +{ + local nsname=$1 + local val=$2 + local nsexec="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + # a custom network namespace is provided + nsexec="ip netns exec ${nsname}" + fi + + ${nsexec} bash -c "echo ${val} >/proc/sys/net/vrf/strict_mode" &>/dev/null +} + +enable_strict_mode() +{ + local nsname=$1 + + set_strict_mode ${nsname} 1 +} + +disable_strict_mode() +{ + local nsname=$1 + + set_strict_mode ${nsname} 0 +} + +disable_strict_mode_and_check() +{ + local nsname=$1 + + disable_strict_mode ${nsname} + log_test $? 0 "${nsname}: disable strict_mode (=0)" +} + +enable_strict_mode_and_check() +{ + local nsname=$1 + + enable_strict_mode ${nsname} + log_test $? 0 "${nsname}: enable strict_mode (=1)" +} + +enable_strict_mode_and_check_fail() +{ + local nsname=$1 + + enable_strict_mode ${nsname} + log_test $? 1 "${nsname}: CANNOT enable strict_mode" +} + +strict_mode_check_default() +{ + local nsname=$1 + local strictmode + local vrfcnt + + vrfcnt=$(vrf_count ${nsname}) + strictmode=$(read_strict_mode ${nsname}) + log_test ${strictmode} 0 "${nsname}: strict_mode=0 by default, ${vrfcnt} vrfs" +} + +setup() +{ + modprobe vrf + + ip netns add testns + ip netns exec testns ip link set lo up +} + +cleanup() +{ + ip netns del testns 2>/dev/null + + ip link del vrf100 2>/dev/null + ip link del vrf101 2>/dev/null + ip link del vrf102 2>/dev/null + + echo 0 >/proc/sys/net/vrf/strict_mode 2>/dev/null +} + +vrf_strict_mode_tests_init() +{ + vrf_strict_mode_check_support init + + strict_mode_check_default init + + add_vrf_and_check init vrf100 100 + config_vrf_and_check init 172.16.100.1/24 vrf100 + + enable_strict_mode_and_check init + + add_vrf_and_check_fail init vrf101 100 + + disable_strict_mode_and_check init + + add_vrf_and_check init vrf101 100 + config_vrf_and_check init 172.16.101.1/24 vrf101 + + enable_strict_mode_and_check_fail init + + del_vrf_and_check init vrf101 + + enable_strict_mode_and_check init + + add_vrf_and_check init vrf102 102 + config_vrf_and_check init 172.16.102.1/24 vrf102 + + # the strict_modle is enabled in the init +} + +vrf_strict_mode_tests_testns() +{ + vrf_strict_mode_check_support testns + + strict_mode_check_default testns + + enable_strict_mode_and_check testns + + add_vrf_and_check testns vrf100 100 + config_vrf_and_check testns 10.0.100.1/24 vrf100 + + add_vrf_and_check_fail testns vrf101 100 + + add_vrf_and_check_fail testns vrf102 100 + + add_vrf_and_check testns vrf200 200 + + disable_strict_mode_and_check testns + + add_vrf_and_check testns vrf101 100 + + add_vrf_and_check testns vrf102 100 + + #the strict_mode is disabled in the testns +} + +vrf_strict_mode_tests_mix() +{ + read_strict_mode_compare_and_check init 1 + + read_strict_mode_compare_and_check testns 0 + + del_vrf_and_check testns vrf101 + + del_vrf_and_check testns vrf102 + + disable_strict_mode_and_check init + + enable_strict_mode_and_check testns + + enable_strict_mode_and_check init + enable_strict_mode_and_check init + + disable_strict_mode_and_check testns + disable_strict_mode_and_check testns + + read_strict_mode_compare_and_check init 1 + + read_strict_mode_compare_and_check testns 0 +} + +vrf_strict_mode_tests() +{ + log_section "VRF strict_mode test on init network namespace" + vrf_strict_mode_tests_init + + log_section "VRF strict_mode test on testns network namespace" + vrf_strict_mode_tests_testns + + log_section "VRF strict_mode test mixing init and testns network namespaces" + vrf_strict_mode_tests_mix +} + +vrf_strict_mode_check_support() +{ + local nsname=$1 + local output + local rc + + output="$(lsmod | grep '^vrf' | awk '{print $1}')" + if [ -z "${output}" ]; then + modinfo vrf || return $? + fi + + # we do not care about the value of the strict_mode; we only check if + # the strict_mode parameter is available or not. + read_strict_mode ${nsname} &>/dev/null; rc=$? + log_test ${rc} 0 "${nsname}: net.vrf.strict_mode is available" + + return ${rc} +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +modprobe vrf &>/dev/null +if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit 0 +fi + +cleanup &> /dev/null + +setup +vrf_strict_mode_tests +cleanup + +print_log_test_results + +exit $ret diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index a179f0dca8ce..a374e10ef506 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -4,7 +4,7 @@ TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ - nft_queue.sh + nft_queue.sh nft_meta.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/nft_meta.sh b/tools/testing/selftests/netfilter/nft_meta.sh new file mode 100755 index 000000000000..d250b84dd5bc --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_meta.sh @@ -0,0 +1,124 @@ +#!/bin/bash + +# check iif/iifname/oifgroup/iiftype match. + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +cleanup() +{ + ip netns del "$ns0" +} + +ip netns add "$ns0" +ip -net "$ns0" link set lo up +ip -net "$ns0" addr add 127.0.0.1 dev lo + +trap cleanup EXIT + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table inet filter { + counter iifcount {} + counter iifnamecount {} + counter iifgroupcount {} + counter iiftypecount {} + counter infproto4count {} + counter il4protocounter {} + counter imarkcounter {} + + counter oifcount {} + counter oifnamecount {} + counter oifgroupcount {} + counter oiftypecount {} + counter onfproto4count {} + counter ol4protocounter {} + counter oskuidcounter {} + counter oskgidcounter {} + counter omarkcounter {} + + chain input { + type filter hook input priority 0; policy accept; + + meta iif lo counter name "iifcount" + meta iifname "lo" counter name "iifnamecount" + meta iifgroup "default" counter name "iifgroupcount" + meta iiftype "loopback" counter name "iiftypecount" + meta nfproto ipv4 counter name "infproto4count" + meta l4proto icmp counter name "il4protocounter" + meta mark 42 counter name "imarkcounter" + } + + chain output { + type filter hook output priority 0; policy accept; + meta oif lo counter name "oifcount" counter + meta oifname "lo" counter name "oifnamecount" + meta oifgroup "default" counter name "oifgroupcount" + meta oiftype "loopback" counter name "oiftypecount" + meta nfproto ipv4 counter name "onfproto4count" + meta l4proto icmp counter name "ol4protocounter" + meta skuid 0 counter name "oskuidcounter" + meta skgid 0 counter name "oskgidcounter" + meta mark 42 counter name "omarkcounter" + } +} +EOF + +if [ $? -ne 0 ]; then + echo "SKIP: Could not add test ruleset" + exit $ksft_skip +fi + +ret=0 + +check_one_counter() +{ + local cname="$1" + local want="packets $2" + local verbose="$3" + + cnt=$(ip netns exec "$ns0" nft list counter inet filter $cname | grep -q "$want") + if [ $? -ne 0 ];then + echo "FAIL: $cname, want \"$want\", got" + ret=1 + ip netns exec "$ns0" nft list counter inet filter $counter + fi +} + +check_lo_counters() +{ + local want="$1" + local verbose="$2" + local counter + + for counter in iifcount iifnamecount iifgroupcount iiftypecount infproto4count \ + oifcount oifnamecount oifgroupcount oiftypecount onfproto4count \ + il4protocounter \ + ol4protocounter \ + ; do + check_one_counter "$counter" "$want" "$verbose" + done +} + +check_lo_counters "0" false +ip netns exec "$ns0" ping -q -c 1 127.0.0.1 -m 42 > /dev/null + +check_lo_counters "2" true + +check_one_counter oskuidcounter "1" true +check_one_counter oskgidcounter "1" true +check_one_counter imarkcounter "1" true +check_one_counter omarkcounter "1" true + +if [ $ret -eq 0 ];then + echo "OK: nftables meta iif/oif counters at expected values" +fi + +exit $ret diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c index 73d532556d17..7d84097ad45c 100644 --- a/tools/testing/selftests/pid_namespace/regression_enomem.c +++ b/tools/testing/selftests/pid_namespace/regression_enomem.c @@ -11,7 +11,6 @@ #include <syscall.h> #include <sys/wait.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #include "../pidfd/pidfd.h" diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 8d728eda783d..a2c80914e3dc 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -22,6 +22,10 @@ #define P_PIDFD 3 #endif +#ifndef CLONE_NEWTIME +#define CLONE_NEWTIME 0x00000080 +#endif + #ifndef CLONE_PIDFD #define CLONE_PIDFD 0x00001000 #endif diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 84b65ecccb04..7758c98be015 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -18,7 +18,6 @@ #include <linux/kcmp.h> #include "pidfd.h" -#include "../kselftest.h" #include "../kselftest_harness.h" /* diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 9418108eae13..7dca1aa4672d 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -20,7 +20,6 @@ #include "pidfd.h" #include "../clone3/clone3_selftests.h" -#include "../kselftest.h" #include "../kselftest_harness.h" enum { @@ -32,6 +31,7 @@ enum { PIDFD_NS_NET, PIDFD_NS_CGROUP, PIDFD_NS_PIDCLD, + PIDFD_NS_TIME, PIDFD_NS_MAX }; @@ -47,6 +47,7 @@ const struct ns_info { [PIDFD_NS_NET] = { "net", CLONE_NEWNET, }, [PIDFD_NS_CGROUP] = { "cgroup", CLONE_NEWCGROUP, }, [PIDFD_NS_PIDCLD] = { "pid_for_children", 0, }, + [PIDFD_NS_TIME] = { "time", CLONE_NEWTIME, }, }; FIXTURE(current_nsset) @@ -83,9 +84,49 @@ pid_t create_child(int *pidfd, unsigned flags) return sys_clone3(&args, sizeof(struct clone_args)); } +static bool switch_timens(void) +{ + int fd, ret; + + if (unshare(CLONE_NEWTIME)) + return false; + + fd = open("/proc/self/ns/time_for_children", O_RDONLY | O_CLOEXEC); + if (fd < 0) + return false; + + ret = setns(fd, CLONE_NEWTIME); + close(fd); + return ret == 0; +} + +static ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = read(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + FIXTURE_SETUP(current_nsset) { int i, proc_fd, ret; + int ipc_sockets[2]; + char c; for (i = 0; i < PIDFD_NS_MAX; i++) { self->nsfds[i] = -EBADF; @@ -130,6 +171,9 @@ FIXTURE_SETUP(current_nsset) TH_LOG("%m - Failed to open pidfd for process %d", self->pid); } + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + /* Create tasks that will be stopped. */ self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER | CLONE_NEWNS | @@ -139,10 +183,27 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid1, 0); if (self->child_pid1 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWNS | CLONE_NEWCGROUP | CLONE_NEWIPC | @@ -151,10 +212,24 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid2, 0); if (self->child_pid2 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + for (i = 0; i < PIDFD_NS_MAX; i++) { char p[100]; diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 7aff2d3b42c0..c585aaa2acd8 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -8,6 +8,7 @@ #include <sched.h> #include <signal.h> #include <stdio.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <syscall.h> @@ -27,6 +28,8 @@ #define MAX_EVENTS 5 +static bool have_pidfd_send_signal; + static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; @@ -56,6 +59,13 @@ static int test_pidfd_send_signal_simple_success(void) int pidfd, ret; const char *test_name = "pidfd_send_signal send SIGUSR1"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC); if (pidfd < 0) ksft_exit_fail_msg( @@ -86,6 +96,13 @@ static int test_pidfd_send_signal_exited_fail(void) pid_t pid; const char *test_name = "pidfd_send_signal signal exited process"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pid = fork(); if (pid < 0) ksft_exit_fail_msg("%s test: Failed to create new process\n", @@ -137,16 +154,34 @@ static int test_pidfd_send_signal_recycled_pid_fail(void) pid_t pid1; const char *test_name = "pidfd_send_signal signal recycled pid"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + ret = unshare(CLONE_NEWPID); - if (ret < 0) + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing pid namespace not permitted\n", + test_name); + return 0; + } ksft_exit_fail_msg("%s test: Failed to unshare pid namespace\n", test_name); + } ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg( - "%s test: Failed to unshare mount namespace\n", - test_name); + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing mount namespace not permitted\n", + test_name); + return 0; + } + ksft_exit_fail_msg("%s test: Failed to unshare mount namespace\n", + test_name); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); if (ret < 0) @@ -325,15 +360,17 @@ static int test_pidfd_send_signal_syscall_support(void) ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); if (ret < 0) { - if (errno == ENOSYS) - ksft_exit_skip( + if (errno == ENOSYS) { + ksft_test_result_skip( "%s test: pidfd_send_signal() syscall not supported\n", test_name); - + return 0; + } ksft_exit_fail_msg("%s test: Failed to send signal\n", test_name); } + have_pidfd_send_signal = true; close(pidfd); ksft_test_result_pass( "%s test: pidfd_send_signal() syscall is supported. Tests can be executed\n", @@ -521,7 +558,7 @@ static void test_pidfd_poll_leader_exit(int use_waitpid) int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(4); + ksft_set_plan(8); test_pidfd_poll_exec(0); test_pidfd_poll_exec(1); diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index da7a9dda9490..f7911aaeb007 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -35,6 +35,8 @@ #define CLOCK_INVALID -1 #endif +#define NSEC_PER_SEC 1000000000LL + /* clock_adjtime is not available in GLIBC < 2.14 */ #if !__GLIBC_PREREQ(2, 14) #include <sys/syscall.h> @@ -132,6 +134,8 @@ static void usage(char *progname) " 1 - external time stamp\n" " 2 - periodic output\n" " -p val enable output with a period of 'val' nanoseconds\n" + " -H val set output phase to 'val' nanoseconds (requires -p)\n" + " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" " -P val enable or disable (val=1|0) the system clock PPS\n" " -s set the ptp clock time from the system time\n" " -S set the system time from the ptp clock time\n" @@ -169,7 +173,6 @@ int main(int argc, char *argv[]) int list_pins = 0; int pct_offset = 0; int n_samples = 0; - int perout = -1; int pin_index = -1, pin_func; int pps = -1; int seconds = 0; @@ -177,10 +180,13 @@ int main(int argc, char *argv[]) int64_t t1, t2, tp; int64_t interval, offset; + int64_t perout_phase = -1; + int64_t pulsewidth = -1; + int64_t perout = -1; progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -197,6 +203,9 @@ int main(int argc, char *argv[]) case 'g': gettime = 1; break; + case 'H': + perout_phase = atoll(optarg); + break; case 'i': index = atoi(optarg); break; @@ -215,7 +224,7 @@ int main(int argc, char *argv[]) } break; case 'p': - perout = atoi(optarg); + perout = atoll(optarg); break; case 'P': pps = atoi(optarg); @@ -233,6 +242,9 @@ int main(int argc, char *argv[]) settime = 3; seconds = atoi(optarg); break; + case 'w': + pulsewidth = atoi(optarg); + break; case 'z': flagtest = 1; break; @@ -391,6 +403,16 @@ int main(int argc, char *argv[]) } } + if (pulsewidth >= 0 && perout < 0) { + puts("-w can only be specified together with -p"); + return -1; + } + + if (perout_phase >= 0 && perout < 0) { + puts("-H can only be specified together with -p"); + return -1; + } + if (perout >= 0) { if (clock_gettime(clkid, &ts)) { perror("clock_gettime"); @@ -398,11 +420,24 @@ int main(int argc, char *argv[]) } memset(&perout_request, 0, sizeof(perout_request)); perout_request.index = index; - perout_request.start.sec = ts.tv_sec + 2; - perout_request.start.nsec = 0; - perout_request.period.sec = 0; - perout_request.period.nsec = perout; - if (ioctl(fd, PTP_PEROUT_REQUEST, &perout_request)) { + perout_request.period.sec = perout / NSEC_PER_SEC; + perout_request.period.nsec = perout % NSEC_PER_SEC; + perout_request.flags = 0; + if (pulsewidth >= 0) { + perout_request.flags |= PTP_PEROUT_DUTY_CYCLE; + perout_request.on.sec = pulsewidth / NSEC_PER_SEC; + perout_request.on.nsec = pulsewidth % NSEC_PER_SEC; + } + if (perout_phase >= 0) { + perout_request.flags |= PTP_PEROUT_PHASE; + perout_request.phase.sec = perout_phase / NSEC_PER_SEC; + perout_request.phase.nsec = perout_phase % NSEC_PER_SEC; + } else { + perout_request.start.sec = ts.tv_sec + 2; + perout_request.start.nsec = 0; + } + + if (ioctl(fd, PTP_PEROUT_REQUEST2, &perout_request)) { perror("PTP_PEROUT_REQUEST"); } else { puts("periodic output request okay"); diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 93e80a42249a..d6e5ce084b1c 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE" then make clean > $resdir/Make.clean 2>&1 fi -make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 +make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv .config .config.sav sh $T/upd.sh < .config.sav > .config cp .config .config.new -yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err +yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh .config $c diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh new file mode 100755 index 000000000000..0e4c0b2eb7f0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Scan standard input for error messages, dumping any found to standard +# output. +# +# Usage: console-badness.sh +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +grep -v 'ODEBUG: ' | +grep -v 'This means that this is a DEBUG kernel and it is' | +grep -v 'Warning: unable to open an initial console' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 12810229fddc..51f3464b96d3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -215,9 +215,6 @@ identify_qemu_args () { then echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$TORTURE_QEMU_INTERACTIVE" - then - echo -net nic -net user fi ;; esac @@ -234,7 +231,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' + lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' } # print_bug @@ -275,3 +272,21 @@ specify_qemu_cpus () { esac fi } + +# specify_qemu_net qemu-args +# +# Appends a string containing "-net none" to qemu-args, unless the incoming +# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE +# environment variable is set, in which case the string that is be added is +# instead "-net nic -net user". +specify_qemu_net () { + if echo $1 | grep -q -e -net + then + echo $1 + elif test -n "$TORTURE_QEMU_INTERACTIVE" + then + echo $1 -net nic -net user + else + echo $1 -net none + fi +} diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index 30cb5b27d32e..188b864bc4bf 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -46,6 +46,12 @@ do exit 0; fi + # Check for stop request. + if test -f "$TORTURE_STOPFILE" + then + exit 1; + fi + # Set affinity to randomly selected online CPU if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 18d6518504ee..115e1822b26f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -9,6 +9,12 @@ # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> +if test -f "$TORTURE_STOPFILE" +then + echo "kvm-build.sh early exit due to run STOP request" + exit 1 +fi + config_template=${1} if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh new file mode 100755 index 000000000000..6e65c134e5f1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a group of kvm.sh tests on the specified commits. This currently +# unconditionally does three-minute runs on each scenario in CFLIST, +# taking advantage of all available CPUs and trusting the "make" utility. +# In the short term, adjustments can be made by editing this script and +# CFLIST. If some adjustments appear to have ongoing value, this script +# might grow some command-line arguments. +# +# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ... +# +# This script considers its arguments one at a time. If more elaborate +# specification of commits is needed, please use "git rev-list" to +# produce something that this simple script can understand. The reason +# for retaining the simplicity is that it allows the user to more easily +# see which commit came from which branch. +# +# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res" +# directory. The calls to kvm.sh create the usual entries, but this script +# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own +# directory numbered in run order, that is, "0001", "0002", and so on. +# For successful runs, the large build artifacts are removed. Doing this +# reduces the disk space required by about two orders of magnitude for +# successful runs. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +if ! git status > /dev/null 2>&1 +then + echo '!!!' This script needs to run in a git archive. 1>&2 + echo '!!!' Giving up. 1>&2 + exit 1 +fi + +# Remember where we started so that we can get back and the end. +curcommit="`git status | head -1 | awk '{ print $NF }'`" + +nfail=0 +ntry=0 +resdir="tools/testing/selftests/rcutorture/res" +ds="`date +%Y.%m.%d-%H.%M.%S`-group" +if ! test -e $resdir +then + mkdir $resdir || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh +cpus="`identify_qemu_vcpus`" +echo Using up to $cpus CPUs. + +# Each pass through this loop does one command-line argument. +for gitbr in $@ +do + echo ' --- git branch ' $gitbr + + # Each pass through this loop tests one commit. + for i in `git rev-list "$gitbr"` + do + ntry=`expr $ntry + 1` + idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null` + echo ' --- commit ' $i from branch $gitbr + date + mkdir $resdir/$ds/$idir + echo $gitbr > $resdir/$ds/$idir/gitbr + echo $i >> $resdir/$ds/$idir/gitbr + + # Test the specified commit. + git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1 + echo git checkout return code: $? "(Commit $ntry: $i)" + kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1 + ret=$? + echo kvm.sh return code $ret for commit $i from branch $gitbr + + # Move the build products to their resting place. + runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`" + mv $runresdir $resdir/$ds/$idir + rrd="`echo $runresdir | sed -e 's,^.*/,,'`" + echo Run results: $resdir/$ds/$idir/$rrd + if test "$ret" -ne 0 + then + # Failure, so leave all evidence intact. + nfail=`expr $nfail + 1` + else + # Success, so remove large files to save about 1GB. + ( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers ) + fi + done +done +date + +# Go back to the original commit. +git checkout "$curcommit" + +if test $nfail -ne 0 +then + echo '!!! ' $nfail failures in $ntry 'runs!!!' + exit 1 +else + echo No failures in $ntry runs. + exit 0 +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh new file mode 100755 index 000000000000..35a463dddffe --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh @@ -0,0 +1,71 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for refscale performance measurements. +# +# Usage: kvm-recheck-refscale.sh resdir +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' | +awk -v configfile="$configfile" ' +/^[ ]*Runs Time\(ns\) *$/ { + if (dataphase + 0 == 0) { + dataphase = 1; + # print configfile, $0; + } + next; +} + +/[^ ]*[0-9][0-9]* [0-9][0-9]*\.[0-9][0-9]*$/ { + if (dataphase == 1) { + # print $0; + readertimes[++n] = $2; + sum += $2; + } + next; +} + +{ + if (dataphase == 1) + dataphase == 2; + next; +} + +END { + print configfile " results:"; + newNR = asort(readertimes); + if (newNR <= 0) { + print "No refscale records found???" + exit; + } + medianidx = int(newNR / 2); + if (newNR == medianidx * 2) + medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2; + else + medianvalue = readertimes[medianidx]; + points = "Points:"; + for (i = 1; i <= newNR; i++) + points = points " " readertimes[i]; + print points; + print "Average reader duration: " sum / newNR " nanoseconds"; + print "Minimum reader duration: " readertimes[1]; + print "Median reader duration: " medianvalue; + print "Maximum reader duration: " readertimes[newNR]; + print "Computed from refscale printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 736f04749b90..840a4679a0d7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -31,6 +31,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 @@ -43,7 +44,8 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 + cat $T if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -55,15 +57,15 @@ do cat $i/Warnings fi else - if test -f "$i/qemu-cmd" - then - print_bug qemu failed - echo " $i" - elif test -f "$i/buildonly" + if test -f "$i/buildonly" then echo Build-only run, no boot/test configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile + elif test -f "$i/qemu-cmd" + then + print_bug qemu failed + echo " $i" else print_bug Build failed echo " $i" @@ -72,7 +74,11 @@ do done if test -f "$rd/kcsan.sum" then - if test -s "$rd/kcsan.sum" + if grep -q CONFIG_KCSAN=y $T + then + echo "Compiler or architecture does not support KCSAN!" + echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? + elif test -s "$rd/kcsan.sum" then echo KCSAN summary in $rd/kcsan.sum else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6ff611c630d1..e07779a62634 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -124,7 +124,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -cd $KVM kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then @@ -141,6 +140,7 @@ then cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" +qemu_args="`specify_qemu_net "$qemu_args"`" # Generate architecture-specific and interaction-specific qemu arguments qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" @@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" +echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -159,9 +160,16 @@ then touch $resdir/buildonly exit 0 fi + +# Decorate qemu-cmd with redirection, backgrounding, and PID capture +sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd +echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd + +# In case qemu refuses to run... echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & + +# Attempt to run qemu +( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 sleep 10 # Give qemu's pid a chance to reach the file if test -s "$resdir/qemu_pid" @@ -181,7 +189,7 @@ do kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then - if test $kruntime -ge $seconds + if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE" then break; fi @@ -210,10 +218,19 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - echo Grace period for qemu job at pid $qemu_pid + if ! test -f "$TORTURE_STOPFILE" + then + echo Grace period for qemu job at pid $qemu_pid + fi oldline="`tail $resdir/console.log`" while : do + if test -f "$TORTURE_STOPFILE" + then + echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + kill -KILL $qemu_pid + break + fi kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh new file mode 100755 index 000000000000..c45a953ef393 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Transform a qemu-cmd file to allow reuse. +# +# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out +# +# bzImage: Kernel and initrd from the same prior kvm.sh run. +# console.log: File into which to place console output. +# +# The original qemu-cmd file is provided on standard input. +# The transformed qemu-cmd file is on standard output. +# The transformation assumes that the qemu command is confined to a +# single line. It also assumes no whitespace in filenames. +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +image="$1" +if test -z "$image" +then + echo Need kernel image file. + exit 1 +fi +consolelog="$2" +if test -z "$consolelog" +then + echo "Need console log file name." + exit 1 +fi + +awk -v image="$image" -v consolelog="$consolelog" ' +{ + line = ""; + for (i = 1; i <= NF; i++) { + if (line == "") + line = $i; + else + line = line " " $i; + if ($i == "-serial") { + i++; + line = line " file:" consolelog; + } + if ($i == "-kernel") { + i++; + line = line " " image; + } + } + print line; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index c279cf9cb010..e655983b7429 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -73,6 +73,10 @@ usage () { while test $# -gt 0 do case "$1" in + --allcpus) + cpus=$TORTURE_ALLOTED_CPUS + max_cpus=$TORTURE_ALLOTED_CPUS + ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' TORTURE_BOOTARGS="$2" @@ -180,13 +184,14 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf + if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale then - # If you really want jitter for rcuperf, specify - # it after specifying rcuperf. (But why?) + # If you really want jitter for refscale or + # rcuperf, specify it after specifying the rcuperf + # or the refscale. (But why jitter in these cases?) jitter=0 fi ;; @@ -333,6 +338,8 @@ then mkdir -p "$resdir" || : fi mkdir $resdir/$ds +TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR +TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -497,3 +504,7 @@ fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y" +# Control buffer size: --bootargs trace_buf_size=3k +# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops +# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu +# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4bf62d7b1cbc..71a9f43a3918 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except that rcuperf runs don't indicate this. -if test "$TORTURE_SUITE" != rcuperf +# Check for proper termination, except for rcuperf and refscale. +if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale then # check for abject failure @@ -44,11 +44,23 @@ then tail -1 | awk ' { - for (i=NF-8;i<=NF;i++) + normalexit = 1; + for (i=NF-8;i<=NF;i++) { + if (i <= 0 || i !~ /^[0-9]*$/) { + bangstring = $0; + gsub(/^\[[^]]*] /, "", bangstring); + print bangstring; + normalexit = 0; + exit 0; + } sum+=$i; + } } - END { print sum }'` - print_bug $title FAILURE, $nerrs instances + END { + if (normalexit) + print sum " instances" + }'` + print_bug $title FAILURE, $nerrs exit fi @@ -104,10 +116,7 @@ then fi fi | tee -a $file.diags -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | -grep -v 'ODEBUG: ' | -grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' > $T.diags +console-badness.sh < $file > $T.diags if test -s $T.diags then print_warning "Assertion failure in $file $title" diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon new file mode 100644 index 000000000000..a98b58b54bb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_REF_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT new file mode 100644 index 000000000000..1cd25b7314e3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT new file mode 100644 index 000000000000..d10bc694f42c --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh new file mode 100644 index 000000000000..321e82641287 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 refscale.shutdown=1 \ + refscale.verbose=1 +} diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config index db1e11b08c8a..64c19d8eba79 100644 --- a/tools/testing/selftests/seccomp/config +++ b/tools/testing/selftests/seccomp/config @@ -1,2 +1,3 @@ CONFIG_SECCOMP=y CONFIG_SECCOMP_FILTER=y +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5838c8697ec3..91f5a89cadac 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -18,9 +18,9 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) { - pid_t pid, ret; - unsigned long long i; struct timespec start, finish; + unsigned long long i; + pid_t pid, ret; pid = getpid(); assert(clock_gettime(clk_id, &start) == 0); @@ -31,30 +31,43 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) assert(clock_gettime(clk_id, &finish) == 0); i = finish.tv_sec - start.tv_sec; - i *= 1000000000; + i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu\n", + printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", finish.tv_sec, finish.tv_nsec, start.tv_sec, start.tv_nsec, - i); + i, (double)i / 1000000000.0); return i; } unsigned long long calibrate(void) { - unsigned long long i; - - printf("Calibrating reasonable sample size...\n"); + struct timespec start, finish; + unsigned long long i, samples, step = 9973; + pid_t pid, ret; + int seconds = 15; - for (i = 5; ; i++) { - unsigned long long samples = 1 << i; + printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); - /* Find something that takes more than 5 seconds to run. */ - if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5) - return samples; - } + samples = 0; + pid = getpid(); + assert(clock_gettime(CLOCK_MONOTONIC, &start) == 0); + do { + for (i = 0; i < step; i++) { + ret = syscall(__NR_getpid); + assert(pid == ret); + } + assert(clock_gettime(CLOCK_MONOTONIC, &finish) == 0); + + samples += step; + i = finish.tv_sec - start.tv_sec; + i *= 1000000000ULL; + i += finish.tv_nsec - start.tv_nsec; + } while (i < 1000000000ULL); + + return samples * seconds; } int main(int argc, char *argv[]) @@ -68,32 +81,55 @@ int main(int argc, char *argv[]) }; long ret; unsigned long long samples; - unsigned long long native, filtered; + unsigned long long native, filter1, filter2; + + printf("Current BPF sysctl settings:\n"); + system("sysctl net.core.bpf_jit_enable"); + system("sysctl net.core.bpf_jit_harden"); if (argc > 1) samples = strtoull(argv[1], NULL, 0); else samples = calibrate(); - printf("Benchmarking %llu samples...\n", samples); + printf("Benchmarking %llu syscalls...\n", samples); + /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; printf("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); + /* One filter */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); - filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW: %llu ns\n", filtered); + filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1); + + if (filter1 == native) + printf("No overhead measured!? Try running again with more samples.\n"); + + /* Two filters */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + assert(ret == 0); + + filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2); + + /* Calculations */ + printf("Estimated total seccomp overhead for 1 filter: %llu ns\n", + filter1 - native); + + printf("Estimated total seccomp overhead for 2 filters: %llu ns\n", + filter2 - native); - printf("Estimated seccomp overhead per syscall: %llu ns\n", - filtered - native); + printf("Estimated seccomp per-filter overhead: %llu ns\n", + filter2 - filter1); - if (filtered == native) - printf("Trying running again with more samples.\n"); + printf("Estimated seccomp entry overhead: %llu ns\n", + filter1 - native - (filter2 - filter1)); return 0; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 252140a52553..5267b9fb7c0f 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -45,12 +45,19 @@ #include <sys/socket.h> #include <sys/ioctl.h> #include <linux/kcmp.h> +#include <sys/resource.h> #include <unistd.h> #include <sys/syscall.h> #include <poll.h> #include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +/* Attempt to de-conflict with the selftests tree. */ +#ifndef SKIP +#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 @@ -167,7 +174,9 @@ struct seccomp_metadata { #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#endif +#ifndef SECCOMP_RET_USER_NOTIF #define SECCOMP_RET_USER_NOTIF 0x7fc00000U #define SECCOMP_IOC_MAGIC '!' @@ -180,7 +189,7 @@ struct seccomp_metadata { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) struct seccomp_notif { __u64 id; @@ -203,6 +212,39 @@ struct seccomp_notif_sizes { }; #endif +#ifndef SECCOMP_IOCTL_NOTIF_ADDFD +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ + +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; +#endif + +struct seccomp_notif_addfd_small { + __u64 id; + char weird[4]; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL \ + SECCOMP_IOW(3, struct seccomp_notif_addfd_small) + +struct seccomp_notif_addfd_big { + union { + struct seccomp_notif_addfd addfd; + char buf[sizeof(struct seccomp_notif_addfd) + 8]; + }; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG \ + SECCOMP_IOWR(3, struct seccomp_notif_addfd_big) + #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 @@ -236,6 +278,40 @@ int seccomp(unsigned int op, unsigned int flags, void *args) #define SIBLING_EXIT_FAILURE 0xbadface #define SIBLING_EXIT_NEWPRIVS 0xbadfeed +static int __filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) +{ +#ifdef __NR_kcmp + errno = 0; + return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); +#else + errno = ENOSYS; + return -1; +#endif +} + +/* Have TH_LOG report actual location filecmp() is used. */ +#define filecmp(pid1, pid2, fd1, fd2) ({ \ + int _ret; \ + \ + _ret = __filecmp(pid1, pid2, fd1, fd2); \ + if (_ret != 0) { \ + if (_ret < 0 && errno == ENOSYS) { \ + TH_LOG("kcmp() syscall missing (test is less accurate)");\ + _ret = 0; \ + } \ + } \ + _ret; }) + +TEST(kcmp) +{ + int ret; + + ret = __filecmp(getpid(), getpid(), 1, 1); + EXPECT_EQ(ret, 0); + if (ret != 0 && errno == ENOSYS) + SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)"); +} + TEST(mode_strict_support) { long ret; @@ -1470,6 +1546,7 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, return tracer_pid; } + void teardown_trace_fixture(struct __test_metadata *_metadata, pid_t tracer) { @@ -1750,7 +1827,7 @@ void change_syscall(struct __test_metadata *_metadata, EXPECT_EQ(0, ret); } -void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, +void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, int status, void *args) { int ret; @@ -1827,6 +1904,24 @@ FIXTURE(TRACE_syscall) { pid_t tracer, mytid, mypid, parent; }; +FIXTURE_VARIANT(TRACE_syscall) { + /* + * All of the SECCOMP_RET_TRACE behaviors can be tested with either + * SECCOMP_RET_TRACE+PTRACE_CONT or plain ptrace()+PTRACE_SYSCALL. + * This indicates if we should use SECCOMP_RET_TRACE (false), or + * ptrace (true). + */ + bool use_ptrace; +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, ptrace) { + .use_ptrace = true, +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, seccomp) { + .use_ptrace = false, +}; + FIXTURE_SETUP(TRACE_syscall) { struct sock_filter filter[] = { @@ -1842,12 +1937,11 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; - - memset(&self->prog, 0, sizeof(self->prog)); - self->prog.filter = malloc(sizeof(filter)); - ASSERT_NE(NULL, self->prog.filter); - memcpy(self->prog.filter, filter, sizeof(filter)); - self->prog.len = (unsigned short)ARRAY_SIZE(filter); + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; /* Prepare some testable syscall results. */ self->mytid = syscall(__NR_gettid); @@ -1865,60 +1959,48 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, - false); -} + self->tracer = setup_trace_fixture(_metadata, + variant->use_ptrace ? tracer_ptrace + : tracer_seccomp, + NULL, variant->use_ptrace); -FIXTURE_TEARDOWN(TRACE_syscall) -{ - teardown_trace_fixture(_metadata, self->tracer); - if (self->prog.filter) - free(self->prog.filter); -} + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); -TEST_F(TRACE_syscall, ptrace_syscall_redirected) -{ - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + if (variant->use_ptrace) + return; - /* Tracer will redirect getpid to getppid. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); } -TEST_F(TRACE_syscall, ptrace_syscall_errno) +FIXTURE_TEARDOWN(TRACE_syscall) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - /* Tracer should skip the open syscall, resulting in ESRCH. */ - EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } -TEST_F(TRACE_syscall, ptrace_syscall_faked) +TEST(negative_ENOSYS) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + /* + * There should be no difference between an "internal" skip + * and userspace asking for syscall "-1". + */ + errno = 0; + EXPECT_EQ(-1, syscall(-1)); + EXPECT_EQ(errno, ENOSYS); + /* And no difference for "still not valid but not -1". */ + errno = 0; + EXPECT_EQ(-1, syscall(-101)); + EXPECT_EQ(errno, ENOSYS); +} - /* Tracer should skip the gettid syscall, resulting fake pid. */ - EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); +TEST_F(TRACE_syscall, negative_ENOSYS) +{ + negative_ENOSYS(_metadata); } TEST_F(TRACE_syscall, syscall_allowed) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getppid works as expected (no changes). */ EXPECT_EQ(self->parent, syscall(__NR_getppid)); EXPECT_NE(self->mypid, syscall(__NR_getppid)); @@ -1926,14 +2008,6 @@ TEST_F(TRACE_syscall, syscall_allowed) TEST_F(TRACE_syscall, syscall_redirected) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getpid has been redirected to getppid as expected. */ EXPECT_EQ(self->parent, syscall(__NR_getpid)); EXPECT_NE(self->mypid, syscall(__NR_getpid)); @@ -1941,33 +2015,17 @@ TEST_F(TRACE_syscall, syscall_redirected) TEST_F(TRACE_syscall, syscall_errno) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* openat has been skipped and an errno return. */ + /* Tracer should skip the open syscall, resulting in ESRCH. */ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } TEST_F(TRACE_syscall, syscall_faked) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* gettid has been skipped and an altered return value stored. */ + /* Tracer skips the gettid syscall and store altered return value. */ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } -TEST_F(TRACE_syscall, skip_after_RET_TRACE) +TEST_F(TRACE_syscall, skip_after) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -1982,14 +2040,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) }; long ret; - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ + /* Install additional "errno on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -1999,69 +2050,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) EXPECT_EQ(EPERM, errno); } -TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should die. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); -} - -TEST_F(TRACE_syscall, skip_after_ptrace) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should see EPERM. */ - EXPECT_EQ(-1, syscall(__NR_getpid)); - EXPECT_EQ(EPERM, errno); -} - -TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +TEST_F_SIGNAL(TRACE_syscall, kill_after, SIGSYS) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -2076,15 +2065,7 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) }; long ret; - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ + /* Install additional "death on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -3069,7 +3050,7 @@ TEST(get_metadata) /* Only real root can get metadata. */ if (geteuid()) { - XFAIL(return, "get_metadata requires real root"); + SKIP(return, "get_metadata requires real root"); return; } @@ -3112,7 +3093,7 @@ TEST(get_metadata) ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md); EXPECT_EQ(sizeof(md), ret) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); + SKIP(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); } EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG); @@ -3128,7 +3109,7 @@ skip: ASSERT_EQ(0, kill(pid, SIGKILL)); } -static int user_trap_syscall(int nr, unsigned int flags) +static int user_notif_syscall(int nr, unsigned int flags) { struct sock_filter filter[] = { BPF_STMT(BPF_LD+BPF_W+BPF_ABS, @@ -3174,7 +3155,7 @@ TEST(user_notification_basic) /* Check that we get -ENOSYS with no listener attached */ if (pid == 0) { - if (user_trap_syscall(__NR_getppid, 0) < 0) + if (user_notif_syscall(__NR_getppid, 0) < 0) exit(1); ret = syscall(__NR_getppid); exit(ret >= 0 || errno != ENOSYS); @@ -3191,13 +3172,13 @@ TEST(user_notification_basic) EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); /* Check that the basic notification machinery works */ - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* Installing a second listener in the chain should EBUSY */ - EXPECT_EQ(user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER), + EXPECT_EQ(user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER), -1); EXPECT_EQ(errno, EBUSY); @@ -3258,15 +3239,20 @@ TEST(user_notification_with_tsync) int ret; unsigned int flags; + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + /* these were exclusive */ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER | SECCOMP_FILTER_FLAG_TSYNC; - ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags)); + ASSERT_EQ(-1, user_notif_syscall(__NR_getppid, flags)); ASSERT_EQ(EINVAL, errno); /* but now they're not */ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH; - ret = user_trap_syscall(__NR_getppid, flags); + ret = user_notif_syscall(__NR_getppid, flags); close(ret); ASSERT_LE(0, ret); } @@ -3284,8 +3270,8 @@ TEST(user_notification_kill_in_middle) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3338,8 +3324,8 @@ TEST(user_notification_signal) ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); - listener = user_trap_syscall(__NR_gettid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3408,8 +3394,8 @@ TEST(user_notification_closed_listener) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3440,10 +3426,13 @@ TEST(user_notification_child_pid_ns) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + }; - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3482,8 +3471,8 @@ TEST(user_notification_sibling_pid_ns) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3505,7 +3494,10 @@ TEST(user_notification_sibling_pid_ns) } /* Create the sibling ns, and sibling in it. */ - ASSERT_EQ(unshare(CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWPID), 0) { + if (errno == EPERM) + SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + } ASSERT_EQ(errno, 0); pid2 = fork(); @@ -3547,8 +3539,8 @@ TEST(user_notification_fault_recv) ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3585,16 +3577,6 @@ TEST(seccomp_get_notif_sizes) EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp)); } -static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) -{ -#ifdef __NR_kcmp - return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); -#else - errno = ENOSYS; - return -1; -#endif -} - TEST(user_notification_continue) { pid_t pid; @@ -3609,7 +3591,7 @@ TEST(user_notification_continue) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3619,20 +3601,14 @@ TEST(user_notification_continue) int dup_fd, pipe_fds[2]; pid_t self; - ret = pipe(pipe_fds); - if (ret < 0) - exit(1); + ASSERT_GE(pipe(pipe_fds), 0); dup_fd = dup(pipe_fds[0]); - if (dup_fd < 0) - exit(1); + ASSERT_GE(dup_fd, 0); + EXPECT_NE(pipe_fds[0], dup_fd); self = getpid(); - - ret = filecmp(self, self, pipe_fds[0], dup_fd); - if (ret) - exit(2); - + ASSERT_EQ(filecmp(self, self, pipe_fds[0], dup_fd), 0); exit(0); } @@ -3673,7 +3649,7 @@ TEST(user_notification_continue) resp.val = 0; EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); + SKIP(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); } skip: @@ -3681,15 +3657,342 @@ skip: EXPECT_EQ(true, WIFEXITED(status)); EXPECT_EQ(0, WEXITSTATUS(status)) { if (WEXITSTATUS(status) == 2) { - XFAIL(return, "Kernel does not support kcmp() syscall"); + SKIP(return, "Kernel does not support kcmp() syscall"); return; } } } +TEST(user_notification_filter_empty) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int listener; + + listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + _exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +static void *do_thread(void *data) +{ + return NULL; +} + +TEST(user_notification_filter_empty_threaded) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t pid1, pid2; + int listener, status; + pthread_t thread; + + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + pid1 = fork(); + if (pid1 < 0) + _exit(EXIT_FAILURE); + + if (pid1 == 0) + _exit(EXIT_SUCCESS); + + pid2 = fork(); + if (pid2 < 0) + _exit(EXIT_FAILURE); + + if (pid2 == 0) + _exit(EXIT_SUCCESS); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (waitpid(pid1, &status, 0) != pid1 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + if (waitpid(pid2, &status, 0) != pid2 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +TEST(user_notification_addfd) +{ + pid_t pid; + long ret; + int status, listener, memfd, fd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif_addfd_small small = {}; + struct seccomp_notif_addfd_big big = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (syscall(__NR_getppid) != USER_NOTIF_MAGIC) + exit(1); + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + } + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + addfd.srcfd = memfd; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0x0; + + /* Verify bad newfd_flags cannot be set */ + addfd.newfd_flags = ~O_CLOEXEC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd_flags = O_CLOEXEC; + + /* Verify bad flags cannot be set */ + addfd.flags = 0xff; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.flags = 0; + + /* Verify that remote_fd cannot be set without setting flags */ + addfd.newfd = 1; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd = 0; + + /* Verify small size cannot be set */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1); + EXPECT_EQ(errno, EINVAL); + + /* Verify we can't send bits filled in unknown buffer area */ + memset(&big, 0xAA, sizeof(big)); + big.addfd = addfd; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1); + EXPECT_EQ(errno, E2BIG); + + + /* Verify we can set an arbitrary remote fd */ + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + /* + * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd), + * 4(listener), so the newly allocated fd should be 5. + */ + EXPECT_EQ(fd, 5); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Verify we can set an arbitrary remote fd with large size */ + memset(&big, 0x0, sizeof(big)); + big.addfd = addfd; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big); + EXPECT_EQ(fd, 6); + + /* Verify we can set a specific remote fd */ + addfd.newfd = 42; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + EXPECT_EQ(fd, 42); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Resume syscall */ + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* + * This sets the ID of the ADD FD to the last request plus 1. The + * notification ID increments 1 per notification. + */ + addfd.id = req.id + 1; + + /* This spins until the underlying notification is generated */ + while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 && + errno != -EINPROGRESS) + nanosleep(&delay, NULL); + + memset(&req, 0, sizeof(req)); + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + ASSERT_EQ(addfd.id, req.id); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + +TEST(user_notification_addfd_rlimit) +{ + pid_t pid; + long ret; + int status, listener, memfd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + const struct rlimit lim = { + .rlim_cur = 0, + .rlim_max = 0, + }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0); + + addfd.srcfd = memfd; + addfd.newfd_flags = O_CLOEXEC; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0; + + /* Should probably spot check /proc/sys/fs/file-nr */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EMFILE); + + addfd.newfd = 100; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EBADF); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + /* * TODO: - * - add microbenchmarks * - expand NNP testing * - better arch-specific TRACE and TRAP handlers. * - endianness checking when appropriate @@ -3697,7 +4000,6 @@ skip: * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages * - verify that RET_LOG generates log messages - * - ... */ TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/seccomp/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index ad0f8df2ca0a..8934a3766d20 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -71,7 +71,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) swapcontext(&sc, &uc); ksft_print_msg("%s\n", p->msg); if (!p->flag) { - ksft_exit_skip("[RUN]\tAborting\n"); + ksft_exit_fail_msg("[RUN]\tAborting\n"); exit(EXIT_FAILURE); } } @@ -144,7 +144,7 @@ int main(void) err = sigaltstack(&stk, NULL); if (err) { if (errno == EINVAL) { - ksft_exit_skip( + ksft_test_result_skip( "[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); /* * If test cases for the !SS_AUTODISARM variant were diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c index 3824b66f41a0..414a617db993 100644 --- a/tools/testing/selftests/sync/sync_test.c +++ b/tools/testing/selftests/sync/sync_test.c @@ -86,9 +86,9 @@ int main(void) int err; ksft_print_header(); - ksft_set_plan(3 + 7); sync_api_supported(); + ksft_set_plan(3 + 7); ksft_print_msg("[RUN]\tTesting sync framework\n"); diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/Makefile index be5a5e542804..91fee5c43274 100644 --- a/tools/testing/selftests/tc-testing/bpf/Makefile +++ b/tools/testing/selftests/tc-testing/Makefile @@ -1,11 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -APIDIR := ../../../../include/uapi +top_srcdir = $(abspath ../../../..) +APIDIR := $(top_scrdir)/include/uapi TEST_GEN_FILES = action.o -top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 -include ../../lib.mk +include ../lib.mk CLANG ?= clang LLC ?= llc @@ -28,3 +28,6 @@ $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ + +TEST_PROGS += ./tdc.sh +TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/action.c index c32b99b80e19..c32b99b80e19 100644 --- a/tools/testing/selftests/tc-testing/bpf/action.c +++ b/tools/testing/selftests/tc-testing/action.c diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh new file mode 100755 index 000000000000..7fe38c76db44 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +./tdc.py -c actions --nobuildebpf +./tdc.py -c qdisc diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index 080709cc4297..cd4a27ee1466 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -24,7 +24,7 @@ NAMES = { # Name of the namespace to use 'NS': 'tcut', # Directory containing eBPF test programs - 'EBPFDIR': './bpf' + 'EBPFDIR': './' } diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c index f83391aa42cf..5cebfb356345 100644 --- a/tools/testing/selftests/uevent/uevent_filtering.c +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -19,7 +19,6 @@ #include <sys/wait.h> #include <unistd.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 79db22604019..91d38a29956b 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -881,8 +881,9 @@ TEST_F(hmm, migrate) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory. + * Migrate anonymous memory to device private memory and fault some of it back + * to system memory, then try migrating the resulting mix of system and device + * private memory to the device. */ TEST_F(hmm, migrate_fault) { @@ -924,8 +925,17 @@ TEST_F(hmm, migrate_fault) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Fault pages back to system memory and check them. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + /* Fault half the pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + /* Migrate memory to the device again. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); @@ -1292,6 +1302,82 @@ TEST_F(hmm2, snapshot) } /* + * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that + * should be mapped by a large page table entry. + */ +TEST_F(hmm, compound) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + int *ptr; + unsigned char *m; + int ret; + long pagesizes[4]; + int n, idx; + unsigned long i; + + /* Skip test if we can't allocate a hugetlbfs page. */ + + n = gethugepagesizes(pagesizes, 4); + if (n <= 0) + return; + for (idx = 0; --n > 0; ) { + if (pagesizes[n] < pagesizes[idx]) + idx = n; + } + size = ALIGN(TWOMEG, pagesizes[idx]); + npages = size >> self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->ptr = get_hugepage_region(size, GHR_STRICT); + if (buffer->ptr == NULL) { + free(buffer); + return; + } + + buffer->size = size; + buffer->mirror = malloc(npages); + ASSERT_NE(buffer->mirror, NULL); + + /* Initialize the pages the device will snapshot in buffer->ptr. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_WRITE | + HMM_DMIRROR_PROT_PMD); + + /* Make the region read-only. */ + ret = mprotect(buffer->ptr, size, PROT_READ); + ASSERT_EQ(ret, 0); + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ | + HMM_DMIRROR_PROT_PMD); + + free_hugepage_region(buffer->ptr); + buffer->ptr = NULL; + hmm_buffer_free(buffer); +} + +/* * Test two devices reading the same memory (double mapped). */ TEST_F(hmm2, double_map) diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index fc19addcb5c8..fdbb602ecf32 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt) + * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst) * * There are examples in here of: * * how to set protection keys on memory diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index d2796ea98c5a..6703c7906b71 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vdso test_vsyscall mov_ss_trap \ - syscall_arg_fault + syscall_arg_fault fsgsbase_restore TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 15a329da59fa..998319553523 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -285,7 +285,8 @@ static unsigned short load_gs(void) /* 32-bit set_thread_area */ long ret; asm volatile ("int $0x80" - : "=a" (ret) : "a" (243), "b" (low_desc) + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) : "r8", "r9", "r10", "r11"); memcpy(&desc, low_desc, sizeof(desc)); munmap(low_desc, sizeof(desc)); @@ -489,11 +490,28 @@ static void test_ptrace_write_gsbase(void) * selector value is changed or not by the GSBASE write in * a ptracer. */ - if (gs == 0 && base == 0xFF) { - printf("[OK]\tGS was reset as expected\n"); - } else { + if (gs != *shared_scratch) { nerrs++; - printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base); + printf("[FAIL]\tGS changed to %lx\n", gs); + + /* + * On older kernels, poking a nonzero value into the + * base would zero the selector. On newer kernels, + * this behavior has changed -- poking the base + * changes only the base and, if FSGSBASE is not + * available, this may have no effect once the tracee + * is resumed. + */ + if (gs == 0) + printf("\tNote: this is expected behavior on older kernels.\n"); + } else if (have_fsgsbase && (base != 0xFF)) { + nerrs++; + printf("[FAIL]\tGSBASE changed to %lx\n", base); + } else { + printf("[OK]\tGS remained 0x%hx", *shared_scratch); + if (have_fsgsbase) + printf(" and GSBASE changed to 0xFF"); + printf("\n"); } } diff --git a/tools/testing/selftests/x86/fsgsbase_restore.c b/tools/testing/selftests/x86/fsgsbase_restore.c new file mode 100644 index 000000000000..6fffadc51579 --- /dev/null +++ b/tools/testing/selftests/x86/fsgsbase_restore.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fsgsbase_restore.c, test ptrace vs fsgsbase + * Copyright (c) 2020 Andy Lutomirski + * + * This test case simulates a tracer redirecting tracee execution to + * a function and then restoring tracee state using PTRACE_GETREGS and + * PTRACE_SETREGS. This is similar to what gdb does when doing + * 'p func()'. The catch is that this test has the called function + * modify a segment register. This makes sure that ptrace correctly + * restores segment state when using PTRACE_SETREGS. + * + * This is not part of fsgsbase.c, because that test is 64-bit only. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <err.h> +#include <sys/user.h> +#include <asm/prctl.h> +#include <sys/prctl.h> +#include <asm/ldt.h> +#include <sys/mman.h> +#include <stddef.h> +#include <sys/ptrace.h> +#include <sys/wait.h> +#include <stdint.h> + +#define EXPECTED_VALUE 0x1337f00d + +#ifdef __x86_64__ +# define SEG "%gs" +#else +# define SEG "%fs" +#endif + +static unsigned int dereference_seg_base(void) +{ + int ret; + asm volatile ("mov %" SEG ":(0), %0" : "=rm" (ret)); + return ret; +} + +static void init_seg(void) +{ + unsigned int *target = mmap( + NULL, sizeof(unsigned int), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + if (target == MAP_FAILED) + err(1, "mmap"); + + *target = EXPECTED_VALUE; + + printf("\tsegment base address = 0x%lx\n", (unsigned long)target); + + struct user_desc desc = { + .entry_number = 0, + .base_addr = (unsigned int)(uintptr_t)target, + .limit = sizeof(unsigned int) - 1, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) { + printf("\tusing LDT slot 0\n"); + asm volatile ("mov %0, %" SEG :: "rm" ((unsigned short)0x7)); + } else { + /* No modify_ldt for us (configured out, perhaps) */ + + struct user_desc *low_desc = mmap( + NULL, sizeof(desc), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + memcpy(low_desc, &desc, sizeof(desc)); + + low_desc->entry_number = -1; + + /* 32-bit set_thread_area */ + long ret; + asm volatile ("int $0x80" + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) +#ifdef __x86_64__ + : "r8", "r9", "r10", "r11" +#endif + ); + memcpy(&desc, low_desc, sizeof(desc)); + munmap(low_desc, sizeof(desc)); + + if (ret != 0) { + printf("[NOTE]\tcould not create a segment -- can't test anything\n"); + exit(0); + } + printf("\tusing GDT slot %d\n", desc.entry_number); + + unsigned short sel = (unsigned short)((desc.entry_number << 3) | 0x3); + asm volatile ("mov %0, %" SEG :: "rm" (sel)); + } +} + +static void tracee_zap_segment(void) +{ + /* + * The tracer will redirect execution here. This is meant to + * work like gdb's 'p func()' feature. The tricky bit is that + * we modify a segment register in order to make sure that ptrace + * can correctly restore segment registers. + */ + printf("\tTracee: in tracee_zap_segment()\n"); + + /* + * Write a nonzero selector with base zero to the segment register. + * Using a null selector would defeat the test on AMD pre-Zen2 + * CPUs, as such CPUs don't clear the base when loading a null + * selector. + */ + unsigned short sel; + asm volatile ("mov %%ss, %0\n\t" + "mov %0, %" SEG + : "=rm" (sel)); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee is going back to sleep\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + /* Should not get here. */ + while (true) { + printf("[FAIL]\tTracee hit unreachable code\n"); + pause(); + } +} + +int main() +{ + printf("\tSetting up a segment\n"); + init_seg(); + + unsigned int val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + return 1; + } + printf("[OK]\tThe segment points to the right place.\n"); + + pid_t chld = fork(); + if (chld < 0) + err(1, "fork"); + + if (chld == 0) { + prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0, 0); + + if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) + err(1, "PTRACE_TRACEME"); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee will take a nap until signaled\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + printf("\tTracee was resumed. Will re-check segment.\n"); + + val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + exit(1); + } + + printf("[OK]\tThe segment points to the right place.\n"); + exit(0); + } + + int status; + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + struct user_regs_struct regs; + + if (ptrace(PTRACE_GETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + +#ifdef __x86_64__ + printf("\tChild GS=0x%lx, GSBASE=0x%lx\n", (unsigned long)regs.gs, (unsigned long)regs.gs_base); +#else + printf("\tChild FS=0x%lx\n", (unsigned long)regs.xfs); +#endif + + struct user_regs_struct regs2 = regs; +#ifdef __x86_64__ + regs2.rip = (unsigned long)tracee_zap_segment; + regs2.rsp -= 128; /* Don't clobber the redzone. */ +#else + regs2.eip = (unsigned long)tracee_zap_segment; +#endif + + printf("\tTracer: redirecting tracee to tracee_zap_segment()\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s2) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_CONT, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + printf("\tTracer: restoring tracee state\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_DETACH, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld) + err(1, "waitpid"); + + if (WIFSIGNALED(status)) { + printf("[FAIL]\tTracee crashed\n"); + return 1; + } + + if (!WIFEXITED(status)) { + printf("[FAIL]\tTracee stopped for an unexpected reason: %d\n", status); + return 1; + } + + int exitcode = WEXITSTATUS(status); + if (exitcode != 0) { + printf("[FAIL]\tTracee reported failure\n"); + return 1; + } + + printf("[OK]\tAll is well.\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c index 5b7abebbcbb9..bff474b5efc6 100644 --- a/tools/testing/selftests/x86/syscall_arg_fault.c +++ b/tools/testing/selftests/x86/syscall_arg_fault.c @@ -53,6 +53,7 @@ static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void) if (ax != -EFAULT && ax != -ENOSYS) { printf("[FAIL]\tAX had the wrong value: 0x%lx\n", (unsigned long)ax); + printf("\tIP = 0x%lx\n", (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); n_errs++; } else { printf("[OK]\tSeems okay\n"); @@ -207,5 +208,30 @@ int main() } set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#ifdef __x86_64__ + printf("[RUN]\tSYSENTER with TF, invalid state, and GSBASE < 0\n"); + + if (sigsetjmp(jmpbuf, 1) == 0) { + sigtrap_consecutive_syscalls = 0; + + asm volatile ("wrgsbase %%rax\n\t" + :: "a" (0xffffffffffff0000UL)); + + set_eflags(get_eflags() | X86_EFLAGS_TF); + asm volatile ( + "movl $-1, %%eax\n\t" + "movl $-1, %%ebx\n\t" + "movl $-1, %%ecx\n\t" + "movl $-1, %%edx\n\t" + "movl $-1, %%esi\n\t" + "movl $-1, %%edi\n\t" + "movl $-1, %%ebp\n\t" + "movl $-1, %%esp\n\t" + "sysenter" + : : : "memory", "flags"); + } + set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#endif + return 0; } diff --git a/tools/usb/usbip/doc/usbip.8 b/tools/usb/usbip/doc/usbip.8 index a6097be25d28..a15d20063b98 100644 --- a/tools/usb/usbip/doc/usbip.8 +++ b/tools/usb/usbip/doc/usbip.8 @@ -83,7 +83,9 @@ List local USB devices. .SH EXAMPLES client:# usbip list --remote=server - - List exportable usb devices on the server. + - List devices exported by remote server. + + client:# modprobe vhci-hcd client:# usbip attach --remote=server --busid=1-2 - Connect the remote USB device. diff --git a/tools/usb/usbip/doc/usbipd.8 b/tools/usb/usbip/doc/usbipd.8 index ac4635db3f03..fb62a756893b 100644 --- a/tools/usb/usbip/doc/usbipd.8 +++ b/tools/usb/usbip/doc/usbipd.8 @@ -73,7 +73,7 @@ USB/IP client can connect and use exported devices. .SH EXAMPLES - server:# modprobe usbip + server:# modprobe usbip-host server:# usbipd -D - Start usbip daemon. diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index d1d8ba2a4a40..ca78aa368476 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -23,7 +23,7 @@ #include "list.h" #include "sysfs_utils.h" -struct udev *udev_context; +extern struct udev *udev_context; static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) { diff --git a/tools/usb/usbip/vudc/vudc_server_example.sh b/tools/usb/usbip/vudc/vudc_server_example.sh index 2736be64f203..fed53f51ee01 100755 --- a/tools/usb/usbip/vudc/vudc_server_example.sh +++ b/tools/usb/usbip/vudc/vudc_server_example.sh @@ -24,7 +24,7 @@ # ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR # OTHER DEALINGS IN THE SOFTWARE. # -# For more information, please refer to <http://unlicense.org/> +# For more information, please refer to <https://unlicense.org/> ################################################################################ ################################################################################ diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index caab980211a6..315e85cabeda 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -110,8 +110,6 @@ static inline void free_page(unsigned long addr) const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -#define uninitialized_var(x) x = x - # ifndef likely # define likely(x) (__builtin_expect(!!(x), 1)) # endif |