diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-01-28 16:02:33 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-01-28 16:02:33 -0800 |
| commit | bd2463ac7d7ec51d432f23bf0e893fb371a908cd (patch) | |
| tree | 3da32c23be83adb9d9bda7e51b51fa39f69f2447 /tools | |
| parent | a78208e2436963d0b2c7d186277d6e1a9755029a (diff) | |
| parent | f76e4c167ea2212e23c15ee7e601a865e822c291 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Add WireGuard
2) Add HE and TWT support to ath11k driver, from John Crispin.
3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.
4) Add variable window congestion control to TIPC, from Jon Maloy.
5) Add BCM84881 PHY driver, from Russell King.
6) Start adding netlink support for ethtool operations, from Michal
Kubecek.
7) Add XDP drop and TX action support to ena driver, from Sameeh
Jubran.
8) Add new ipv4 route notifications so that mlxsw driver does not have
to handle identical routes itself. From Ido Schimmel.
9) Add BPF dynamic program extensions, from Alexei Starovoitov.
10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.
11) Add support for macsec HW offloading, from Antoine Tenart.
12) Add initial support for MPTCP protocol, from Christoph Paasch,
Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.
13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
Cherian, and others.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
udp: segment looped gso packets correctly
netem: change mailing list
qed: FW 8.42.2.0 debug features
qed: rt init valid initialization changed
qed: Debug feature: ilt and mdump
qed: FW 8.42.2.0 Add fw overlay feature
qed: FW 8.42.2.0 HSI changes
qed: FW 8.42.2.0 iscsi/fcoe changes
qed: Add abstraction for different hsi values per chip
qed: FW 8.42.2.0 Additional ll2 type
qed: Use dmae to write to widebus registers in fw_funcs
qed: FW 8.42.2.0 Parser offsets modified
qed: FW 8.42.2.0 Queue Manager changes
qed: FW 8.42.2.0 Expose new registers and change windows
qed: FW 8.42.2.0 Internal ram offsets modifications
MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
Documentation: net: octeontx2: Add RVU HW and drivers overview
octeontx2-pf: ethtool RSS config support
octeontx2-pf: Add basic ethtool support
...
Diffstat (limited to 'tools')
296 files changed, 20141 insertions, 2786 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 5535650800ab..f897eeeb0b4f 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -73,7 +73,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm -all: $(PROGS) bpftool +all: $(PROGS) bpftool runqslower $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm' $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o @@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean +clean: bpftool_clean runqslower_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* @@ -97,7 +97,7 @@ clean: bpftool_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install +install: $(PROGS) bpftool_install runqslower_install $(call QUIET_INSTALL, bpf_jit_disasm) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin $(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm @@ -115,4 +115,14 @@ bpftool_install: bpftool_clean: $(call descend,bpftool,clean) -.PHONY: all install clean bpftool bpftool_install bpftool_clean +runqslower: + $(call descend,runqslower) + +runqslower_install: + $(call descend,runqslower,install) + +runqslower_clean: + $(call descend,runqslower,clean) + +.PHONY: all install clean bpftool bpftool_install bpftool_clean \ + runqslower runqslower_install runqslower_clean diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000000..94d91322895a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,305 @@ +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **gen** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMAND* := { **skeleton | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen skeleton** *FILE* +| **bpftool** **gen help** + +DESCRIPTION +=========== + **bpftool gen skeleton** *FILE* + Generate BPF skeleton C header file for a given *FILE*. + + BPF skeleton is an alternative interface to existing libbpf + APIs for working with BPF objects. Skeleton code is intended + to significantly shorten and simplify code to load and work + with BPF programs from userspace side. Generated code is + tailored to specific input BPF object *FILE*, reflecting its + structure by listing out available maps, program, variables, + etc. Skeleton eliminates the need to lookup mentioned + components by name. Instead, if skeleton instantiation + succeeds, they are populated in skeleton structure as valid + libbpf types (e.g., struct bpf_map pointer) and can be + passed to existing generic libbpf APIs. + + In addition to simple and reliable access to maps and + programs, skeleton provides a storage for BPF links (struct + bpf_link) for each BPF program within BPF object. When + requested, supported BPF programs will be automatically + attached and resulting BPF links stored for further use by + user in pre-allocated fields in skeleton struct. For BPF + programs that can't be automatically attached by libbpf, + user can attach them manually, but store resulting BPF link + in per-program link field. All such set up links will be + automatically destroyed on BPF skeleton destruction. This + eliminates the need for users to manage links manually and + rely on libbpf support to detach programs and free up + resources. + + Another facility provided by BPF skeleton is an interface to + global variables of all supported kinds: mutable, read-only, + as well as extern ones. This interface allows to pre-setup + initial values of variables before BPF object is loaded and + verified by kernel. For non-read-only variables, the same + interface can be used to fetch values of global variables on + userspace side, even if they are modified by BPF code. + + During skeleton generation, contents of source BPF object + *FILE* is embedded within generated code and is thus not + necessary to keep around. This ensures skeleton and BPF + object file are matching 1-to-1 and always stay in sync. + Generated code is dual-licensed under LGPL-2.1 and + BSD-2-Clause licenses. + + It is a design goal and guarantee that skeleton interfaces + are interoperable with generic libbpf APIs. User should + always be able to use skeleton API to create and load BPF + object, and later use libbpf APIs to keep working with + specific maps, programs, etc. + + As part of skeleton, few custom functions are generated. + Each of them is prefixed with object name, derived from + object file name. I.e., if BPF object file name is + **example.o**, BPF object name will be **example**. The + following custom functions are provided in such case: + + - **example__open** and **example__open_opts**. + These functions are used to instantiate skeleton. It + corresponds to libbpf's **bpf_object__open()** API. + **_opts** variants accepts extra **bpf_object_open_opts** + options. + + - **example__load**. + This function creates maps, loads and verifies BPF + programs, initializes global data maps. It corresponds to + libppf's **bpf_object__load** API. + + - **example__open_and_load** combines **example__open** and + **example__load** invocations in one commonly used + operation. + + - **example__attach** and **example__detach** + This pair of functions allow to attach and detach, + correspondingly, already loaded BPF object. Only BPF + programs of types supported by libbpf for auto-attachment + will be auto-attached and their corresponding BPF links + instantiated. For other BPF programs, user can manually + create a BPF link and assign it to corresponding fields in + skeleton struct. **example__detach** will detach both + links created automatically, as well as those populated by + user manually. + + - **example__destroy** + Detach and unload BPF programs, free up all the resources + used by skeleton and BPF object. + + If BPF object has global variables, corresponding structs + with memory layout corresponding to global data data section + layout will be created. Currently supported ones are: *.data*, + *.bss*, *.rodata*, and *.kconfig* structs/data sections. + These data sections/structs can be used to set up initial + values of variables, if set before **example__load**. + Afterwards, if target kernel supports memory-mapped BPF + arrays, same structs can be used to fetch and update + (non-read-only) data from userspace, with same simplicity + as for BPF side. + + **bpftool gen help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, + this option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available from libbpf, including debug-level + information. + +EXAMPLES +======== +**$ cat example.c** +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include "bpf_helpers.h" + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + + SEC("raw_tp/sys_enter") + int handle_sys_enter(struct pt_regs *ctx) + { + static long my_static_var; + if (global_flag) + my_static_var++; + else + data.x += param1; + return 0; + } + + SEC("raw_tp/sys_exit") + int handle_sys_exit(struct pt_regs *ctx) + { + int zero = 0; + bpf_map_lookup_elem(&my_map, &zero); + return 0; + } + +This is example BPF application with two BPF programs and a mix of BPF maps +and global variables. + +**$ bpftool gen skeleton example.o** +:: + + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + + /* THIS FILE IS AUTOGENERATED! */ + #ifndef __EXAMPLE_SKEL_H__ + #define __EXAMPLE_SKEL_H__ + + #include <stdlib.h> + #include <bpf/libbpf.h> + + struct example { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + struct bpf_map *data; + struct bpf_map *bss; + struct bpf_map *my_map; + } maps; + struct { + struct bpf_program *handle_sys_enter; + struct bpf_program *handle_sys_exit; + } progs; + struct { + struct bpf_link *handle_sys_enter; + struct bpf_link *handle_sys_exit; + } links; + struct example__bss { + struct { + int x; + } data; + } *bss; + struct example__data { + _Bool global_flag; + long int handle_sys_enter_my_static_var; + } *data; + struct example__rodata { + int param1; + } *rodata; + }; + + static void example__destroy(struct example *obj); + static inline struct example *example__open_opts( + const struct bpf_object_open_opts *opts); + static inline struct example *example__open(); + static inline int example__load(struct example *obj); + static inline struct example *example__open_and_load(); + static inline int example__attach(struct example *obj); + static inline void example__detach(struct example *obj); + + #endif /* __EXAMPLE_SKEL_H__ */ + +**$ cat example_user.c** +:: + + #include "example.skel.h" + + int main() + { + struct example *skel; + int err = 0; + + skel = example__open(); + if (!skel) + goto cleanup; + + skel->rodata->param1 = 128; + + err = example__load(skel); + if (err) + goto cleanup; + + err = example__attach(skel); + if (err) + goto cleanup; + + /* all libbpf APIs are usable */ + printf("my_map name: %s\n", bpf_map__name(skel->maps.my_map)); + printf("sys_enter prog FD: %d\n", + bpf_program__fd(skel->progs.handle_sys_enter)); + + /* detach and re-attach sys_exit program */ + bpf_link__destroy(skel->links.handle_sys_exit); + skel->links.handle_sys_exit = + bpf_program__attach(skel->progs.handle_sys_exit); + + printf("my_static_var: %ld\n", + skel->bss->handle_sys_enter_my_static_var); + + cleanup: + example__destroy(skel); + return err; + } + +**# ./example_user** +:: + + my_map name: my_map + sys_enter prog FD: 8 + my_static_var: 7 + +This is a stripped-out version of skeleton generated for above example code. + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 1c0f7146aab0..cdeae8ae90ba 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -39,9 +39,9 @@ MAP COMMANDS | **bpftool** **map freeze** *MAP* | **bpftool** **map help** | -| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } | *DATA* := { [**hex**] *BYTES* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** @@ -55,8 +55,9 @@ DESCRIPTION =========== **bpftool map { show | list }** [*MAP*] Show information about loaded maps. If *MAP* is specified - show information only about given map, otherwise list all - maps currently loaded on the system. + show information only about given maps, otherwise list all + maps currently loaded on the system. In case of **name**, + *MAP* may match several maps which will all be shown. Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). @@ -66,7 +67,8 @@ DESCRIPTION as *FILE*. **bpftool map dump** *MAP* - Dump all entries in a given *MAP*. + Dump all entries in a given *MAP*. In case of **name**, + *MAP* may match several maps which will all be dumped. **bpftool map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] Update map entry for a given *KEY*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 7a374b3c851d..64ddf8a4c518 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -33,7 +33,7 @@ PROG COMMANDS | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *TYPE* := { | **socket** | **kprobe** | **kretprobe** | **classifier** | **action** | | **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** | @@ -53,8 +53,10 @@ DESCRIPTION =========== **bpftool prog { show | list }** [*PROG*] Show information about loaded programs. If *PROG* is - specified show information only about given program, otherwise - list all programs currently loaded on the system. + specified show information only about given programs, + otherwise list all programs currently loaded on the system. + In case of **tag** or **name**, *PROG* may match several + programs which will all be shown. Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). @@ -68,11 +70,15 @@ DESCRIPTION performed via the **kernel.bpf_stats_enabled** sysctl knob. **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] - Dump eBPF instructions of the program from the kernel. By + Dump eBPF instructions of the programs from the kernel. By default, eBPF will be disassembled and printed to standard output in human-readable format. In this case, **opcodes** controls if raw opcodes should be printed as well. + In case of **tag** or **name**, *PROG* may match several + programs which will all be dumped. However, if **file** or + **visual** is specified, *PROG* must match a single program. + If **file** is specified, the binary image will instead be written to *FILE*. @@ -80,15 +86,17 @@ DESCRIPTION built instead, and eBPF instructions will be presented with CFG in DOT format, on standard output. - If the prog has line_info available, the source line will + If the programs have line_info available, the source line will be displayed by default. If **linum** is specified, the filename, line number and line column will also be displayed on top of the source line. **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] Dump jited image (host machine code) of the program. + If *FILE* is specified image will be written to a file, otherwise it will be disassembled and printed to stdout. + *PROG* must match a single program when **file** is specified. **opcodes** controls if raw opcodes will be printed. diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 6a9c52ef84a9..34239fda69ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -81,4 +81,5 @@ SEE ALSO **bpftool-feature**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-btf**\ (8), + **bpftool-gen**\ (8), diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 39bc6f0f4f0b..c4e810335810 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -45,7 +45,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ - -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/lib \ -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' ifneq ($(EXTRA_CFLAGS),) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 70493a6da206..754d8395e451 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -59,6 +59,21 @@ _bpftool_get_map_ids_for_type() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_map_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -71,6 +86,12 @@ _bpftool_get_prog_tags() command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_prog_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"name": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_btf_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ @@ -180,6 +201,52 @@ _bpftool_map_update_get_id() esac } +_bpftool_map_update_get_name() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_names_for_type stack + ;; + enqueue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + fi + + # Name to complete is for a value. It can be either prog name or map name. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_names + return 0 + ;; + prog_array) + _bpftool_get_prog_names + return 0 + ;; + *) + return 0 + ;; + esac +} + _bpftool() { local cur prev words objword @@ -251,7 +318,8 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - # Complete id, only for subcommands that use prog (but no map) ids + # Complete id and name, only for subcommands that use prog (but no + # map) ids/names. case $command in show|list|dump|pin) case $prev in @@ -259,12 +327,16 @@ _bpftool() _bpftool_get_prog_ids return 0 ;; + name) + _bpftool_get_prog_names + return 0 + ;; esac ;; esac - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -315,6 +387,9 @@ _bpftool() id) _bpftool_get_prog_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -335,6 +410,9 @@ _bpftool() id) _bpftool_get_map_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -399,6 +477,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; pinned|pinmaps) _filedir return 0 @@ -447,7 +529,7 @@ _bpftool() esac ;; map) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' case $command in show|list|dump|peek|pop|dequeue|freeze) case $prev in @@ -473,6 +555,24 @@ _bpftool() esac return 0 ;; + name) + case "$command" in + peek) + _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_type queue + ;; + pop) + _bpftool_get_map_names_for_type stack + ;; + dequeue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + ;; *) return 0 ;; @@ -520,6 +620,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -545,6 +649,10 @@ _bpftool() _bpftool_map_update_get_id $command return 0 ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -553,13 +661,13 @@ _bpftool() # map, depending on the type of the map to update. case "$(_bpftool_map_guess_map_type)" in array_of_maps|hash_of_maps) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ -- "$cur" ) ) return 0 ;; prog_array) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ -- "$cur" ) ) return 0 @@ -621,6 +729,10 @@ _bpftool() _bpftool_get_map_ids_for_type perf_event_array return 0 ;; + name) + _bpftool_get_map_names_for_type perf_event_array + return 0 + ;; cpu) return 0 ;; @@ -644,8 +756,8 @@ _bpftool() esac ;; btf) - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in dump) case $prev in @@ -676,6 +788,17 @@ _bpftool() esac return 0 ;; + name) + case $pprev in + prog) + _bpftool_get_prog_names + ;; + map) + _bpftool_get_map_names + ;; + esac + return 0 + ;; format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; @@ -716,6 +839,17 @@ _bpftool() ;; esac ;; + gen) + case $command in + skeleton) + _filedir + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list|tree) @@ -735,7 +869,7 @@ _bpftool() connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ getsockopt setsockopt' local ATTACH_FLAGS='multi override' - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' case $prev in $command) _filedir @@ -760,7 +894,7 @@ _bpftool() elif [[ "$command" == "attach" ]]; then # We have an attach type on the command line, # but it is not the previous word, or - # "id|pinned|tag" (we already checked for + # "id|pinned|tag|name" (we already checked for # that). This should only leave the case when # we need attach flags for "attach" commamnd. _bpftool_one_of_list "$ATTACH_FLAGS" @@ -786,7 +920,7 @@ _bpftool() esac ;; net) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in show|list) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index e5bc97b71ceb..b3745ed711ba 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -8,15 +8,15 @@ #include <stdio.h> #include <string.h> #include <unistd.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include <linux/btf.h> #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -77,6 +77,20 @@ static const char *btf_var_linkage_str(__u32 linkage) } } +static const char *btf_func_linkage_str(const struct btf_type *t) +{ + switch (btf_vlen(t)) { + case BTF_FUNC_STATIC: + return "static"; + case BTF_FUNC_GLOBAL: + return "global"; + case BTF_FUNC_EXTERN: + return "extern"; + default: + return "(unknown)"; + } +} + static const char *btf_str(const struct btf *btf, __u32 off) { if (!off) @@ -231,12 +245,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" fwd_kind=%s", fwd_kind); break; } - case BTF_KIND_FUNC: - if (json_output) + case BTF_KIND_FUNC: { + const char *linkage = btf_func_linkage_str(t); + + if (json_output) { jsonw_uint_field(w, "type_id", t->type); - else - printf(" type_id=%u", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u linkage=%s", t->type, linkage); + } break; + } case BTF_KIND_FUNC_PROTO: { const struct btf_param *p = (const void *)(t + 1); __u16 vlen = BTF_INFO_VLEN(t->info); @@ -370,6 +389,10 @@ static int dump_btf_c(const struct btf *btf, if (IS_ERR(d)) return PTR_ERR(d); + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n"); + printf("#endif\n\n"); + if (root_type_cnt) { for (i = 0; i < root_type_cnt; i++) { err = btf_dump__dump_type(d, root_type_ids[i]); @@ -386,6 +409,10 @@ static int dump_btf_c(const struct btf *btf, } } + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute pop\n"); + printf("#endif\n"); + done: btf_dump__free(d); return err; @@ -524,7 +551,7 @@ static int do_dump(int argc, char **argv) if (IS_ERR(btf)) { err = PTR_ERR(btf); btf = NULL; - p_err("failed to load BTF from %s: %s", + p_err("failed to load BTF from %s: %s", *argv, strerror(err)); goto done; } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 397e5716ab6d..01cc52b834fa 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -8,8 +8,8 @@ #include <linux/bitops.h> #include <linux/btf.h> #include <linux/err.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 1ef45e55039e..62c6a1d7cd18 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -14,7 +14,7 @@ #include <sys/types.h> #include <unistd.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" @@ -117,6 +117,25 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) return prog_cnt; } +static int cgroup_has_attached_progs(int cgroup_fd) +{ + enum bpf_attach_type type; + bool no_prog = true; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + int count = count_attached_bpf_progs(cgroup_fd, type); + + if (count < 0 && errno != EINVAL) + return -1; + + if (count > 0) { + no_prog = false; + break; + } + } + + return no_prog ? 0 : 1; +} static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { @@ -161,6 +180,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + int has_attached_progs; const char *path; int cgroup_fd; int ret = -1; @@ -192,6 +212,16 @@ static int do_show(int argc, char **argv) goto exit; } + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + path, strerror(errno)); + goto exit_cgroup; + } else if (!has_attached_progs) { + ret = 0; + goto exit_cgroup; + } + if (json_output) jsonw_start_array(json_wtr); else @@ -212,6 +242,7 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); +exit_cgroup: close(cgroup_fd); exit: return ret; @@ -228,7 +259,7 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftw) { enum bpf_attach_type type; - bool skip = true; + int has_attached_progs; int cgroup_fd; if (typeflag != FTW_D) @@ -240,22 +271,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, return SHOW_TREE_FN_ERR; } - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - int count = count_attached_bpf_progs(cgroup_fd, type); - - if (count < 0 && errno != EINVAL) { - p_err("can't query bpf programs attached to %s: %s", - fpath, strerror(errno)); - close(cgroup_fd); - return SHOW_TREE_FN_ERR; - } - if (count > 0) { - skip = false; - break; - } - } - - if (skip) { + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } else if (!has_attached_progs) { close(cgroup_fd); return 0; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 88264abaa738..b75b8ec5469c 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -20,8 +20,8 @@ #include <sys/stat.h> #include <sys/vfs.h> -#include <bpf.h> -#include <libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/bpf.h> +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ #include "main.h" diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 03bdc5b3ac49..446ba891f1e2 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -12,8 +12,8 @@ #include <linux/filter.h> #include <linux/limits.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <zlib.h> #include "main.h" @@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, printf("\n"); } +static void +probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + bool res; + + res = bpf_probe_large_insn_limit(ifindex); + print_bool_feature("have_large_insn_limit", + "Large program size limit", + "HAVE_LARGE_INSN_LIMIT", + res, define_prefix); +} + static int do_probe(int argc, char **argv) { enum probe_component target = COMPONENT_UNSPEC; @@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv) probe_helpers_for_progtype(i, supported_types[i], define_prefix, ifindex); + print_end_then_start_section("misc", + "Scanning miscellaneous eBPF features...", + "/*** eBPF misc features ***/", + define_prefix); + probe_large_insn_limit(define_prefix, ifindex); + exit_close_json: if (json_output) { /* End current "section" of probes */ diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000000..f8113b3646f5 --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,609 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <unistd.h> +#include <bpf/btf.h> + +#include "bpf/libbpf_internal.h" +#include "json_writer.h" +#include "main.h" + + +#define MAX_OBJ_NAME_LEN 64 + +static void sanitize_identifier(char *name) +{ + int i; + + for (i = 0; name[i]; i++) + if (!isalnum(name[i]) && name[i] != '_') + name[i] = '_'; +} + +static bool str_has_suffix(const char *str, const char *suffix) +{ + size_t i, n1 = strlen(str), n2 = strlen(suffix); + + if (n1 < n2) + return false; + + for (i = 0; i < n2; i++) { + if (str[n1 - i - 1] != suffix[n2 - i - 1]) + return false; + } + + return true; +} + +static void get_obj_name(char *name, const char *file) +{ + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(name, basename(file), MAX_OBJ_NAME_LEN - 1); + name[MAX_OBJ_NAME_LEN - 1] = '\0'; + if (str_has_suffix(name, ".o")) + name[strlen(name) - 2] = '\0'; + sanitize_identifier(name); +} + +static void get_header_guard(char *guard, const char *obj_name) +{ + int i; + + sprintf(guard, "__%s_SKEL_H__", obj_name); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static const char *get_map_ident(const struct bpf_map *map) +{ + const char *name = bpf_map__name(map); + + if (!bpf_map__is_internal(map)) + return name; + + if (str_has_suffix(name, ".data")) + return "data"; + else if (str_has_suffix(name, ".rodata")) + return "rodata"; + else if (str_has_suffix(name, ".bss")) + return "bss"; + else if (str_has_suffix(name, ".kconfig")) + return "kconfig"; + else + return NULL; +} + +static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +{ + vprintf(fmt, args); +} + +static int codegen_datasec_def(struct bpf_object *obj, + struct btf *btf, + struct btf_dump *d, + const struct btf_type *sec, + const char *obj_name) +{ + const char *sec_name = btf__name_by_offset(btf, sec->name_off); + const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); + int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); + const char *sec_ident; + char var_ident[256]; + + if (strcmp(sec_name, ".data") == 0) + sec_ident = "data"; + else if (strcmp(sec_name, ".bss") == 0) + sec_ident = "bss"; + else if (strcmp(sec_name, ".rodata") == 0) + sec_ident = "rodata"; + else if (strcmp(sec_name, ".kconfig") == 0) + sec_ident = "kconfig"; + else + return 0; + + printf(" struct %s__%s {\n", obj_name, sec_ident); + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .field_name = var_ident, + .indent_level = 2, + ); + 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", + sec_name, i, need_off, off); + return -EINVAL; + } + + align = btf__align_of(btf, var->type); + if (align <= 0) { + p_err("Failed to determine alignment of variable '%s': %d", + var_name, align); + return -EINVAL; + } + + align_off = (off + align - 1) / align * align; + if (align_off != need_off) { + printf("\t\tchar __pad%d[%d];\n", + pad_cnt, need_off - off); + pad_cnt++; + } + + /* sanitize variable name, e.g., for static vars inside + * a function, it's name is '<function name>.<variable name>', + * which we'll turn into a '<function name>_<variable name>' + */ + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t\t"); + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + return err; + printf(";\n"); + + off = sec_var->offset + sec_var->size; + } + printf(" } *%s;\n", sec_ident); + return 0; +} + +static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + int n = btf__get_nr_types(btf); + struct btf_dump *d; + int i, err = 0; + + d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); + if (IS_ERR(d)) + return PTR_ERR(d); + + for (i = 1; i <= n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + err = codegen_datasec_def(obj, btf, d, t, obj_name); + if (err) + goto out; + } +out: + btf_dump__free(d); + return err; +} + +static int codegen(const char *template, ...) +{ + const char *src, *end; + int skip_tabs = 0, n; + char *s, *dst; + va_list args; + char c; + + n = strlen(template); + s = malloc(n + 1); + if (!s) + return -ENOMEM; + src = template; + dst = s; + + /* find out "baseline" indentation to skip */ + while ((c = *src++)) { + if (c == '\t') { + skip_tabs++; + } else if (c == '\n') { + break; + } else { + p_err("unrecognized character at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + + while (*src) { + /* skip baseline indentation tabs */ + for (n = skip_tabs; n > 0; n--, src++) { + if (*src != '\t') { + p_err("not enough tabs at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + /* trim trailing whitespace */ + end = strchrnul(src, '\n'); + for (n = end - src; n > 0 && isspace(src[n - 1]); n--) + ; + memcpy(dst, src, n); + dst += n; + if (*end) + *dst++ = '\n'; + src = *end ? end + 1 : end; + } + *dst++ = '\0'; + + /* print out using adjusted template */ + va_start(args, template); + n = vprintf(s, args); + va_end(args); + + free(s); + return n; +} + +static int do_skeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; + size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN], *obj_data; + struct bpf_object *obj = NULL; + const char *file, *ident; + struct bpf_program *prog; + int fd, len, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + get_obj_name(obj_name, file); + opts.object_name = obj_name; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (IS_ERR(obj)) { + obj = NULL; + p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); + goto out; + } + + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) { + p_err("ignoring unrecognized internal map '%s'...", + bpf_map__name(map)); + continue; + } + map_cnt++; + } + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + get_header_guard(header_guard, obj_name); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object_skeleton *skeleton; \n\ + struct bpf_object *obj; \n\ + ", + obj_name, header_guard + ); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); + } + printf("\t} links;\n"); + } + + btf = bpf_object__btf(obj); + if (btf) { + err = codegen_datasecs(obj, obj_name); + if (err) + goto out; + } + + codegen("\ + \n\ + }; \n\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *obj) \n\ + { \n\ + if (!obj) \n\ + return; \n\ + if (obj->skeleton) \n\ + bpf_object__destroy_skeleton(obj->skeleton);\n\ + free(obj); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj); \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__create_skeleton(obj)) \n\ + goto err; \n\ + if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + return %1$s__open_opts(NULL); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *obj) \n\ + { \n\ + return bpf_object__load_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__load(obj)) { \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + return obj; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__attach_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + \n\ + s = (typeof(s))calloc(1, sizeof(*s)); \n\ + if (!s) \n\ + return -1; \n\ + obj->skeleton = s; \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + if (map_cnt) { + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + + if (!ident) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } + } + if (prog_cnt) { + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + i++; + } + } + codegen("\ + \n\ + \n\ + s->data_sz = %d; \n\ + s->data = (void *)\"\\ \n\ + ", + file_sz); + + /* embed contents of BPF object file */ + for (i = 0, len = 0; i < file_sz; i++) { + int w = obj_data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!obj_data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)obj_data[i]); + } + + codegen("\ + \n\ + \"; \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -1; \n\ + } \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s gen skeleton FILE\n" + " %1$s gen help\n" + "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "skeleton", do_skeleton }, + { "help", do_help }, + { 0 } +}; + +int do_gen(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index bfed711258ce..f7f5885aa3ba 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -24,7 +24,7 @@ #include <dis-asm.h> #include <sys/stat.h> #include <limits.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 4764581ff9ea..6d41bbfc6459 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -9,8 +9,8 @@ #include <stdlib.h> #include <string.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "main.h" @@ -58,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -227,6 +227,7 @@ static const struct cmd cmds[] = { { "net", do_net }, { "feature", do_feature }, { "btf", do_btf }, + { "gen", do_gen }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 2899095f8254..4e75b58d3989 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -42,12 +42,12 @@ #define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" #define HELP_SPEC_PROGRAM \ - "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ - "MAP := { id MAP_ID | pinned FILE }" + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -155,6 +155,7 @@ 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); +int do_gen(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index de61d73b9030..e6c85680b34d 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -15,9 +15,9 @@ #include <sys/types.h> #include <sys/stat.h> -#include <bpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -48,6 +48,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -91,10 +92,66 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -int map_parse_fd(int *argc, char ***argv) +static int map_fd_by_name(char *name, int **fds) { - int fd; + 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; @@ -108,10 +165,25 @@ int map_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) + (*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 fd; + 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; @@ -120,13 +192,43 @@ int map_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_MAP); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + 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; @@ -150,6 +252,7 @@ static int do_dump_btf(const struct btf_dumper *d, struct bpf_map_info *map_info, void *key, void *value) { + __u32 value_id; int ret; /* start of key-value pair */ @@ -163,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d, goto err_end_obj; } + value_id = map_info->btf_vmlinux_value_type_id ? + : map_info->btf_value_type_id; + if (!map_is_per_cpu(map_info->type)) { jsonw_name(d->jw, "value"); - ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + ret = btf_dumper_type(d, value_id, value); } else { unsigned int i, n, step; @@ -177,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d, jsonw_start_object(d->jw); jsonw_int_field(d->jw, "cpu", i); jsonw_name(d->jw, "value"); - ret = btf_dumper_type(d, map_info->btf_value_type_id, - value + i * step); + ret = btf_dumper_type(d, value_id, value + i * step); jsonw_end_object(d->jw); if (ret) break; @@ -479,6 +584,21 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; } +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(map_type_name)) + jsonw_string_field(wtr, "type", map_type_name[info->type]); + else + jsonw_uint_field(wtr, "type", info->type); + + if (*info->name) + jsonw_string_field(wtr, "name", info->name); + + jsonw_name(wtr, "flags"); + jsonw_printf(wtr, "%d", info->map_flags); +} + static int show_map_close_json(int fd, struct bpf_map_info *info) { char *memlock, *frozen_str; @@ -489,18 +609,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_start_object(json_wtr); - jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(json_wtr, "type", - map_type_name[info->type]); - else - jsonw_uint_field(json_wtr, "type", info->type); - - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); - - jsonw_name(json_wtr, "flags"); - jsonw_printf(json_wtr, "%d", info->map_flags); + show_map_header_json(info, json_wtr); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); @@ -561,14 +670,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) return 0; } -static int show_map_close_plain(int fd, struct bpf_map_info *info) +static void show_map_header_plain(struct bpf_map_info *info) { - char *memlock, *frozen_str; - int frozen = 0; - - memlock = get_fdinfo(fd, "memlock"); - frozen_str = get_fdinfo(fd, "frozen"); - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) printf("%s ", map_type_name[info->type]); @@ -581,6 +684,17 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("flags 0x%x", info->map_flags); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); printf("\n"); +} + +static int show_map_close_plain(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + show_map_header_plain(info); printf("\tkey %uB value %uB max_entries %u", info->key_size, info->value_size, info->max_entries); @@ -642,6 +756,50 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) return 0; } +static int do_show_subset(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int *fds = NULL; + int nb_fds, i; + int err = -1; + + 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) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", + strerror(errno)); + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + + if (json_output) + show_map_close_json(fds[i], &info); + else + show_map_close_plain(fds[i], &info); + + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { struct bpf_map_info info = {}; @@ -653,16 +811,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&map_table, BPF_OBJ_MAP); - if (argc == 2) { - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; - - if (json_output) - return show_map_close_json(fd, &info); - else - return show_map_close_plain(fd, &info); - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -765,26 +915,75 @@ static int dump_map_elem(int fd, void *key, void *value, return 0; } -static int do_dump(int argc, char **argv) +static int maps_have_btf(int *fds, int nb_fds) { struct bpf_map_info info = {}; - void *key, *value, *prev_key; - unsigned int num_elems = 0; __u32 len = sizeof(info); - json_writer_t *btf_wtr; + int err, i; + + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + return -1; + } + + if (!info.btf_id) + return 0; + } + + return 1; +} + +static struct btf *btf_vmlinux; + +static struct btf *get_map_kv_btf(const struct bpf_map_info *info) +{ struct btf *btf = NULL; - int err; - int fd; - if (argc != 2) - usage(); + if (info->btf_vmlinux_value_type_id) { + if (!btf_vmlinux) { + btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(btf_vmlinux)) + p_err("failed to get kernel btf"); + } + return btf_vmlinux; + } else if (info->btf_value_type_id) { + int err; + + err = btf__get_from_id(info->btf_id, &btf); + if (err || !btf) { + p_err("failed to get btf"); + btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH); + } + } - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; + return btf; +} - key = malloc(info.key_size); - value = alloc_value(&info); +static void free_map_kv_btf(struct btf *btf) +{ + if (!IS_ERR(btf) && btf != btf_vmlinux) + btf__free(btf); +} + +static void free_btf_vmlinux(void) +{ + if (!IS_ERR(btf_vmlinux)) + btf__free(btf_vmlinux); +} + +static int +map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, + bool show_header) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct btf *btf = NULL; + int err; + + key = malloc(info->key_size); + value = alloc_value(info); if (!key || !value) { p_err("mem alloc failed"); err = -1; @@ -793,30 +992,27 @@ static int do_dump(int argc, char **argv) prev_key = NULL; - err = btf__get_from_id(info.btf_id, &btf); - if (err) { - p_err("failed to get btf"); - goto exit_free; - } + if (wtr) { + btf = get_map_kv_btf(info); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto exit_free; + } - if (json_output) - jsonw_start_array(json_wtr); - else - if (btf) { - btf_wtr = get_btf_writer(); - if (!btf_wtr) { - p_info("failed to create json writer for btf. falling back to plain output"); - btf__free(btf); - btf = NULL; - } else { - jsonw_start_array(btf_wtr); - } + if (show_header) { + jsonw_start_object(wtr); /* map object */ + show_map_header_json(info, wtr); + jsonw_name(wtr, "elements"); } + jsonw_start_array(wtr); /* elements */ + } else if (show_header) { + show_map_header_plain(info); + } - if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info.value_size != 8) + if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info->value_size != 8) p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info.type]); + map_type_name[info->type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -824,15 +1020,14 @@ static int do_dump(int argc, char **argv) err = 0; break; } - num_elems += dump_map_elem(fd, key, value, &info, btf, btf_wtr); + num_elems += dump_map_elem(fd, key, value, info, btf, wtr); prev_key = key; } - if (json_output) - jsonw_end_array(json_wtr); - else if (btf) { - jsonw_end_array(btf_wtr); - jsonw_destroy(&btf_wtr); + if (wtr) { + jsonw_end_array(wtr); /* elements */ + if (show_header) + jsonw_end_object(wtr); /* map object */ } else { printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); @@ -842,11 +1037,78 @@ exit_free: free(key); free(value); close(fd); - btf__free(btf); + free_map_kv_btf(btf); return err; } +static int do_dump(int argc, char **argv) +{ + json_writer_t *wtr = NULL, *btf_wtr = NULL; + struct bpf_map_info info = {}; + int nb_fds, i = 0; + __u32 len = sizeof(info); + int *fds = NULL; + int err = -1; + + if (argc != 2) + usage(); + + 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) + goto exit_free; + + if (json_output) { + wtr = json_wtr; + } else { + int do_plain_btf; + + do_plain_btf = maps_have_btf(fds, nb_fds); + if (do_plain_btf < 0) + goto exit_close; + + if (do_plain_btf) { + btf_wtr = get_btf_writer(); + wtr = btf_wtr; + if (!btf_wtr) + p_info("failed to create json writer for btf. falling back to plain output"); + } + } + + if (wtr && nb_fds > 1) + jsonw_start_array(wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + p_err("can't get map info: %s", strerror(errno)); + break; + } + err = map_dump(fds[i], &info, wtr, nb_fds > 1); + if (!wtr && i != nb_fds - 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (wtr && nb_fds > 1) + jsonw_end_array(wtr); /* root array */ + + if (btf_wtr) + jsonw_destroy(&btf_wtr); +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + free_btf_vmlinux(); + return err; +} + static int alloc_key_value(struct bpf_map_info *info, void **key, void **value) { *key = NULL; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 4c5531d1a450..d9b29c17fbb8 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -6,7 +6,7 @@ */ #include <errno.h> #include <fcntl.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <poll.h> #include <signal.h> #include <stdbool.h> @@ -21,7 +21,7 @@ #include <sys/mman.h> #include <sys/syscall.h> -#include <bpf.h> +#include <bpf/bpf.h> #include <perf-sys.h> #include "main.h" diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 4f52d3151616..c5e3895b7c8b 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -7,7 +7,8 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <net/if.h> #include <linux/if.h> #include <linux/rtnetlink.h> @@ -16,8 +17,8 @@ #include <sys/stat.h> #include <sys/types.h> -#include <bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" +#include "bpf/libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c index 550a0f537eed..5f65140b003b 100644 --- a/tools/bpf/bpftool/netlink_dumper.c +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -3,11 +3,11 @@ #include <stdlib.h> #include <string.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index b2046f33e23f..3341aa14acda 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -13,7 +13,7 @@ #include <unistd.h> #include <ftw.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2ce9c5ba1934..a3521deca869 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -17,14 +17,19 @@ #include <linux/err.h> #include <linux/sizes.h> -#include <bpf.h> -#include <btf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include "cfg.h" #include "main.h" #include "xlated_dumper.h" +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", @@ -77,11 +82,12 @@ 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_tag(unsigned char *tag) +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; - int fd; while (true) { struct bpf_prog_info info = {}; @@ -89,36 +95,54 @@ static int prog_fd_by_tag(unsigned char *tag) err = bpf_prog_get_next_id(id, &id); if (err) { - p_err("%s", strerror(errno)); - return -1; + 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)); - return -1; + 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)); - close(fd); - return -1; + goto err_close_fd; } - if (!memcmp(tag, info.tag, BPF_TAG_SIZE)) - return fd; + if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || + (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + close(fd); + continue; + } - close(fd); + 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_fd(int *argc, char ***argv) +static int prog_parse_fds(int *argc, char ***argv, int **fds) { - int fd; - if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -132,10 +156,12 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; } else if (is_prefix(**argv, "tag")) { unsigned char tag[BPF_TAG_SIZE]; @@ -149,7 +175,20 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return prog_fd_by_tag(tag); + 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; @@ -158,13 +197,43 @@ int prog_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_PROG); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv); + 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 = {}; @@ -194,11 +263,8 @@ static void show_prog_maps(int fd, u32 num_maps) } } -static void print_prog_json(struct bpf_prog_info *info, int fd) +static void print_prog_header_json(struct bpf_prog_info *info) { - char *memlock; - - jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -219,7 +285,14 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } +} +static void print_prog_json(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -268,10 +341,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_plain(struct bpf_prog_info *info, int fd) +static void print_prog_header_plain(struct bpf_prog_info *info) { - char *memlock; - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); @@ -289,6 +360,13 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + print_prog_header_plain(info); if (info->load_time) { char buf[32]; @@ -349,6 +427,40 @@ static int show_prog(int fd) return 0; } +static int do_show_subset(int argc, char **argv) +{ + int *fds = NULL; + int nb_fds, i; + int err = -1; + + 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) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = show_prog(fds[i]); + if (err) { + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { __u32 id = 0; @@ -358,15 +470,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); - if (argc == 2) { - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - err = show_prog(fd); - close(fd); - return err; - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -408,101 +513,32 @@ static int do_show(int argc, char **argv) return err; } -static int do_dump(int argc, char **argv) +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; - enum {DUMP_JITED, DUMP_XLATED} mode; const char *disasm_opt = NULL; - struct bpf_prog_info *info; struct dump_data dd = {}; void *func_info = NULL; struct btf *btf = NULL; - char *filepath = NULL; - bool opcodes = false; - bool visual = false; char func_sig[1024]; unsigned char *buf; - bool linum = false; __u32 member_len; - __u64 arrays; ssize_t n; int fd; - if (is_prefix(*argv, "jited")) { - if (disasm_init()) - return -1; - mode = DUMP_JITED; - } else if (is_prefix(*argv, "xlated")) { - mode = DUMP_XLATED; - } else { - p_err("expected 'xlated' or 'jited', got: %s", *argv); - return -1; - } - NEXT_ARG(); - - if (argc < 2) - usage(); - - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - if (is_prefix(*argv, "file")) { - NEXT_ARG(); - if (!argc) { - p_err("expected file path"); - return -1; - } - - filepath = *argv; - NEXT_ARG(); - } else if (is_prefix(*argv, "opcodes")) { - opcodes = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "visual")) { - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); - } - - if (argc) { - usage(); - return -1; - } - - if (mode == DUMP_JITED) - arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; - else - arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - - arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - - info_linear = bpf_program__get_prog_info_linear(fd, arrays); - close(fd); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("can't get prog info: %s", strerror(errno)); - return -1; - } - - info = &info_linear->info; if (mode == DUMP_JITED) { if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); - goto err_free; + return -1; } buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); - goto err_free; + return -1; } buf = (unsigned char *)info->xlated_prog_insns; member_len = info->xlated_prog_len; @@ -510,7 +546,7 @@ static int do_dump(int argc, char **argv) if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { p_err("failed to get btf"); - goto err_free; + return -1; } func_info = (void *)info->func_info; @@ -526,7 +562,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) { p_err("can't open file %s: %s", filepath, strerror(errno)); - goto err_free; + return -1; } n = write(fd, buf, member_len); @@ -534,7 +570,7 @@ static int do_dump(int argc, char **argv) if (n != member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); - goto err_free; + return -1; } if (json_output) @@ -548,7 +584,7 @@ static int do_dump(int argc, char **argv) info->netns_ino, &disasm_opt); if (!name) - goto err_free; + return -1; } if (info->nr_jited_func_lens && info->jited_func_lens) { @@ -643,12 +679,130 @@ static int do_dump(int argc, char **argv) kernel_syms_destroy(&dd); } - free(info_linear); return 0; +} -err_free: - free(info_linear); - return -1; +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info_linear *info_linear; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int *fds = NULL; + int nb_fds, i = 0; + int err = -1; + __u64 arrays; + + if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + mode = DUMP_JITED; + } else if (is_prefix(*argv, "xlated")) { + mode = DUMP_XLATED; + } else { + p_err("expected 'xlated' or 'jited', got: %s", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + 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) + goto exit_free; + + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + p_err("expected file path"); + goto exit_close; + } + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } + + if (argc) { + usage(); + goto exit_close; + } + + if (mode == DUMP_JITED) + arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; + else + arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; + + arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + info_linear = bpf_program__get_prog_info_linear(fds[i], arrays); + if (IS_ERR_OR_NULL(info_linear)) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + if (json_output && nb_fds > 1) { + jsonw_start_object(json_wtr); /* prog object */ + print_prog_header_json(&info_linear->info); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info_linear->info); + } + + err = prog_dump(&info_linear->info, mode, filepath, opcodes, + visual, linum); + + if (json_output && nb_fds > 1) + jsonw_end_object(json_wtr); /* prog object */ + else if (i != nb_fds - 1 && nb_fds > 1) + printf("\n"); + + free(info_linear); + if (err) + break; + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + return err; } static int do_pin(int argc, char **argv) diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 5b91ee65a080..8608cd68cdd0 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -7,7 +7,7 @@ #include <stdlib.h> #include <string.h> #include <sys/types.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "disasm.h" #include "json_writer.h" diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore new file mode 100644 index 000000000000..90a456a2a72f --- /dev/null +++ b/tools/bpf/runqslower/.gitignore @@ -0,0 +1 @@ +/.output diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile new file mode 100644 index 000000000000..0c021352beed --- /dev/null +++ b/tools/bpf/runqslower/Makefile @@ -0,0 +1,84 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +OUTPUT := .output +CLANG ?= clang +LLC ?= llc +LLVM_STRIP ?= llvm-strip +DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +LIBBPF_SRC := $(abspath ../../lib/bpf) +BPFOBJ := $(OUTPUT)/libbpf.a +BPF_INCLUDE := $(OUTPUT) +INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib) +CFLAGS := -g -Wall + +# Try to detect best kernel BTF source +KERNEL_REL := $(shell uname -r) +VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL) +VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \ + $(wildcard $(VMLINUX_BTF_PATHS)))) + +abs_out := $(abspath $(OUTPUT)) +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +.DELETE_ON_ERROR: + +.PHONY: all clean runqslower +all: runqslower + +runqslower: $(OUTPUT)/runqslower + +clean: + $(call msg,CLEAN) + $(Q)rm -rf $(OUTPUT) runqslower + +$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) + $(call msg,BINARY,$@) + $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@ + +$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ + $(OUTPUT)/runqslower.bpf.o + +$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h + +$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) + $(call msg,GEN-SKEL,$@) + $(Q)$(BPFTOOL) gen skeleton $< > $@ + +$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) + $(call msg,BPF,$@) + $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + -c $(filter %.c,$^) -o $@ && \ + $(LLVM_STRIP) -g $@ + +$(OUTPUT)/%.o: %.c | $(OUTPUT) + $(call msg,CC,$@) + $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@ + +$(OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $(OUTPUT) + +$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) + $(call msg,GEN,$@) + $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \ + echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \ + "specify its location." >&2; \ + exit 1;\ + fi + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ + +$(BPFOBJ): | $(OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ + OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + +$(DEFAULT_BPFTOOL): + $(Q)$(MAKE) $(submake_extras) -C ../bpftool \ + prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c new file mode 100644 index 000000000000..48a39f72fadf --- /dev/null +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "runqslower.h" + +#define TASK_RUNNING 0 + +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK + +const volatile __u64 min_us = 0; +const volatile pid_t targ_pid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10240); + __type(key, u32); + __type(value, u64); +} start SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); +} events SEC(".maps"); + +/* record enqueue timestamp */ +__always_inline +static int trace_enqueue(u32 tgid, u32 pid) +{ + u64 ts; + + if (!pid || (targ_pid && targ_pid != pid)) + return 0; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, 0); + return 0; +} + +SEC("tp_btf/sched_wakeup") +int handle__sched_wakeup(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_wakeup_new") +int handle__sched_wakeup_new(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_switch") +int handle__sched_switch(u64 *ctx) +{ + /* TP_PROTO(bool preempt, struct task_struct *prev, + * struct task_struct *next) + */ + struct task_struct *prev = (struct task_struct *)ctx[1]; + struct task_struct *next = (struct task_struct *)ctx[2]; + struct event event = {}; + u64 *tsp, delta_us; + long state; + u32 pid; + + /* ivcsw: treat like an enqueue event and store timestamp */ + if (prev->state == TASK_RUNNING) + trace_enqueue(prev->tgid, prev->pid); + + pid = next->pid; + + /* fetch timestamp and calculate delta */ + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + return 0; /* missed enqueue */ + + delta_us = (bpf_ktime_get_ns() - *tsp) / 1000; + if (min_us && delta_us <= min_us) + return 0; + + event.pid = pid; + event.delta_us = delta_us; + bpf_get_current_comm(&event.task, sizeof(event.task)); + + /* output */ + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, + &event, sizeof(event)); + + bpf_map_delete_elem(&start, &pid); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c new file mode 100644 index 000000000000..d89715844952 --- /dev/null +++ b/tools/bpf/runqslower/runqslower.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook +#include <argp.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/resource.h> +#include <time.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "runqslower.h" +#include "runqslower.skel.h" + +struct env { + pid_t pid; + __u64 min_us; + bool verbose; +} env = { + .min_us = 10000, +}; + +const char *argp_program_version = "runqslower 0.1"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = +"runqslower Trace long process scheduling delays.\n" +" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n" +"\n" +"This script traces high scheduling delays between tasks being\n" +"ready to run and them running on CPU after that.\n" +"\n" +"USAGE: runqslower [-p PID] [min_us]\n" +"\n" +"EXAMPLES:\n" +" runqslower # trace run queue latency higher than 10000 us (default)\n" +" runqslower 1000 # trace run queue latency higher than 1000 us\n" +" runqslower -p 123 # trace pid 123 only\n"; + +static const struct argp_option opts[] = { + { "pid", 'p', "PID", 0, "Process PID to trace"}, + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + static int pos_args; + int pid; + long long min_us; + + switch (key) { + case 'v': + env.verbose = true; + break; + case 'p': + errno = 0; + pid = strtol(arg, NULL, 10); + if (errno || pid <= 0) { + fprintf(stderr, "Invalid PID: %s\n", arg); + argp_usage(state); + } + env.pid = pid; + break; + case ARGP_KEY_ARG: + if (pos_args++) { + fprintf(stderr, + "Unrecognized positional argument: %s\n", arg); + argp_usage(state); + } + errno = 0; + min_us = strtoll(arg, NULL, 10); + if (errno || min_us <= 0) { + fprintf(stderr, "Invalid delay (in us): %s\n", arg); + argp_usage(state); + } + env.min_us = min_us; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static int bump_memlock_rlimit(void) +{ + struct rlimit rlim_new = { + .rlim_cur = RLIM_INFINITY, + .rlim_max = RLIM_INFINITY, + }; + + return setrlimit(RLIMIT_MEMLOCK, &rlim_new); +} + +void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) +{ + const struct event *e = data; + struct tm *tm; + char ts[32]; + time_t t; + + time(&t); + tm = localtime(&t); + strftime(ts, sizeof(ts), "%H:%M:%S", tm); + printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us); +} + +void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt) +{ + printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu); +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + struct perf_buffer_opts pb_opts; + struct perf_buffer *pb = NULL; + struct runqslower_bpf *obj; + int err; + + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + + err = bump_memlock_rlimit(); + if (err) { + fprintf(stderr, "failed to increase rlimit: %d", err); + return 1; + } + + obj = runqslower_bpf__open(); + if (!obj) { + fprintf(stderr, "failed to open and/or load BPF object\n"); + return 1; + } + + /* initialize global data (filtering options) */ + obj->rodata->targ_pid = env.pid; + obj->rodata->min_us = env.min_us; + + err = runqslower_bpf__load(obj); + if (err) { + fprintf(stderr, "failed to load BPF object: %d\n", err); + goto cleanup; + } + + err = runqslower_bpf__attach(obj); + if (err) { + fprintf(stderr, "failed to attach BPF programs\n"); + goto cleanup; + } + + printf("Tracing run queue latency higher than %llu us\n", env.min_us); + printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); + + pb_opts.sample_cb = handle_event; + pb_opts.lost_cb = handle_lost_events; + pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + pb = NULL; + fprintf(stderr, "failed to open perf buffer: %d\n", err); + goto cleanup; + } + + while ((err = perf_buffer__poll(pb, 100)) >= 0) + ; + printf("Error polling perf buffer: %d\n", err); + +cleanup: + perf_buffer__free(pb); + runqslower_bpf__destroy(obj); + + return err != 0; +} diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h new file mode 100644 index 000000000000..9db225425e5f --- /dev/null +++ b/tools/bpf/runqslower/runqslower.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __RUNQSLOWER_H +#define __RUNQSLOWER_H + +#define TASK_COMM_LEN 16 + +struct event { + char task[TASK_COMM_LEN]; + __u64 delta_us; + pid_t pid; +}; + +#endif /* __RUNQSLOWER_H */ diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h index 13a58531e6fa..39acc149d843 100644 --- a/tools/include/uapi/asm/bpf_perf_event.h +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -2,6 +2,8 @@ #include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" #elif defined(__s390__) #include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#elif defined(__riscv) +#include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h" #else #include <uapi/asm-generic/bpf_perf_event.h> #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index dbbcf0b02970..f1d74a2bd234 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -107,6 +107,10 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, }; enum bpf_map_type { @@ -136,6 +140,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, + BPF_MAP_TYPE_STRUCT_OPS, }; /* Note that tracing related programs such as @@ -174,6 +179,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_PROG_TYPE_TRACING, + BPF_PROG_TYPE_STRUCT_OPS, + BPF_PROG_TYPE_EXT, }; enum bpf_attach_type { @@ -231,6 +238,11 @@ enum bpf_attach_type { * When children program makes decision (like picking TCP CA or sock bind) * parent program has a chance to override it. * + * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of + * programs for a cgroup. Though it's possible to replace an old program at + * any position by also specifying BPF_F_REPLACE flag and position itself in + * replace_bpf_fd attribute. Old program at this position will be released. + * * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. * A cgroup with NONE doesn't allow any programs in sub-cgroups. * Ex1: @@ -249,6 +261,7 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +#define BPF_F_REPLACE (1U << 2) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -351,7 +364,12 @@ enum bpf_attach_type { /* Enable memory-mapping BPF map */ #define BPF_F_MMAPABLE (1U << 10) -/* flags for BPF_PROG_QUERY */ +/* Flags for BPF_PROG_QUERY. */ + +/* Query effective (directly attached + inherited from ancestor cgroups) + * programs that will be executed for events within a cgroup. + * attach_flags with this flag are returned only for directly attached programs. + */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) enum bpf_stack_build_id_status { @@ -391,6 +409,10 @@ union bpf_attr { __u32 btf_fd; /* fd pointing to a BTF type data */ __u32 btf_key_type_id; /* BTF type_id of the key */ __u32 btf_value_type_id; /* BTF type_id of the value */ + __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel- + * struct stored as the + * map value + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -403,6 +425,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; @@ -442,6 +481,10 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 replace_bpf_fd; /* previously attached eBPF + * program to replace if + * BPF_F_REPLACE is used + */ }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -2693,7 +2736,8 @@ union bpf_attr { * * int bpf_send_signal(u32 sig) * Description - * Send signal *sig* to the current task. + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. * Return * 0 on success or successfully queued. * @@ -2821,6 +2865,33 @@ union bpf_attr { * Return * 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) + * 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) + * Description + * Send signal *sig* to the thread corresponding to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * u64 bpf_jiffies64(void) + * Description + * Obtain the 64bit jiffies + * Return + * The 64 bit jiffies */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2938,7 +3009,10 @@ union bpf_attr { FN(probe_read_user), \ FN(probe_read_kernel), \ FN(probe_read_user_str), \ - FN(probe_read_kernel_str), + FN(probe_read_kernel_str), \ + FN(tcp_send_ack), \ + FN(send_signal_thread), \ + FN(jiffies64), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3339,7 +3413,7 @@ struct bpf_map_info { __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; - __u32 :32; + __u32 btf_vmlinux_value_type_id; __u64 netns_dev; __u64 netns_ino; __u32 btf_id; diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 63ae4a39e58b..5a667107ad2c 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -22,9 +22,9 @@ struct btf_header { }; /* Max # of type identifier */ -#define BTF_MAX_TYPE 0x0000ffff +#define BTF_MAX_TYPE 0x000fffff /* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x0000ffff +#define BTF_MAX_NAME_OFFSET 0x00ffffff /* Max # of struct/union/enum members or func args */ #define BTF_MAX_VLEN 0xffff @@ -142,7 +142,14 @@ struct btf_param { enum { BTF_VAR_STATIC = 0, - BTF_VAR_GLOBAL_ALLOCATED, + BTF_VAR_GLOBAL_ALLOCATED = 1, + BTF_VAR_GLOBAL_EXTERN = 2, +}; + +enum btf_func_linkage { + BTF_FUNC_STATIC = 0, + BTF_FUNC_GLOBAL = 1, + BTF_FUNC_EXTERN = 2, }; /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8aec8769d944..024af2d1d0af 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -169,6 +169,7 @@ enum { IFLA_MAX_MTU, IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ + IFLA_PERM_ADDRESS, __IFLA_MAX }; @@ -485,6 +486,13 @@ enum macsec_validation_type { MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, }; +enum macsec_offload { + MACSEC_OFFLOAD_OFF = 0, + MACSEC_OFFLOAD_PHY = 1, + __MACSEC_OFFLOAD_END, + MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1, +}; + /* IPVLAN section */ enum { IFLA_IPVLAN_UNSPEC, diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e7ad9d350a28..1521073b6348 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -76,6 +76,8 @@ enum { #define IPPROTO_MPLS IPPROTO_MPLS IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MPTCP = 262, /* Multipath TCP connection */ +#define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX }; #endif diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 97830e46d1a0..aee7f1a83c77 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -56,8 +56,8 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray -FEATURE_DISPLAY = libelf bpf +FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray +FEATURE_DISPLAY = libelf zlib bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) @@ -148,6 +148,7 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -160,7 +161,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -178,11 +179,11 @@ $(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h - $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ + $(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \ --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) @@ -190,7 +191,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(QUIET_LINK)$(CC) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so "versioned in $(VERSION_SCRIPT)." >&2; \ readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -250,6 +252,7 @@ install_headers: $(BPF_HELPER_DEFS) $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ $(call do_install,btf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ + $(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ @@ -270,20 +273,24 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ - *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ - $(SHARED_OBJDIR) $(STATIC_OBJDIR) + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ + $(addprefix $(OUTPUT), \ + *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf -PHONY += force elfdep bpfdep cscope tags +PHONY += force elfdep zdep bpfdep cscope tags force: elfdep: @if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + bpfdep: @if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 98596e15390f..c6dafe563176 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -32,6 +32,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. @@ -95,7 +98,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.btf_key_type_id = create_attr->btf_key_type_id; attr.btf_value_type_id = create_attr->btf_value_type_id; attr.map_ifindex = create_attr->map_ifindex; - attr.inner_map_fd = create_attr->inner_map_fd; + if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) + attr.btf_vmlinux_value_type_id = + create_attr->btf_vmlinux_value_type_id; + else + attr.inner_map_fd = create_attr->inner_map_fd; return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } @@ -228,7 +235,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; - if (attr.prog_type == BPF_PROG_TYPE_TRACING) { + if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) { + attr.attach_btf_id = load_attr->attach_btf_id; + } else if (attr.prog_type == BPF_PROG_TYPE_TRACING || + attr.prog_type == BPF_PROG_TYPE_EXT) { attr.attach_btf_id = load_attr->attach_btf_id; attr.attach_prog_fd = load_attr->attach_prog_fd; } else { @@ -443,6 +453,64 @@ int bpf_map_freeze(int fd) return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); } +static int bpf_map_batch_common(int cmd, int fd, void *in_batch, + void *out_batch, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_map_batch_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.batch.map_fd = fd; + attr.batch.in_batch = ptr_to_u64(in_batch); + attr.batch.out_batch = ptr_to_u64(out_batch); + attr.batch.keys = ptr_to_u64(keys); + attr.batch.values = ptr_to_u64(values); + attr.batch.count = *count; + attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); + attr.batch.flags = OPTS_GET(opts, flags, 0); + + ret = sys_bpf(cmd, &attr, sizeof(attr)); + *count = attr.batch.count; + + return ret; +} + +int bpf_map_delete_batch(int fd, void *keys, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, + NULL, keys, NULL, count, opts); +} + +int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch, + out_batch, keys, values, count, opts); +} + +int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH, + fd, in_batch, out_batch, keys, values, + count, opts); +} + +int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, + keys, values, count, opts); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -467,13 +535,28 @@ int bpf_obj_get(const char *pathname) int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, unsigned int flags) { + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts, + .flags = flags, + ); + + return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); +} + +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) +{ union bpf_attr attr; + if (!OPTS_VALID(opts, bpf_prog_attach_opts)) + return -EINVAL; + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - attr.attach_flags = flags; + attr.attach_flags = OPTS_GET(opts, flags, 0); + attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 3c791fa8e68e..b976e77316cc 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -28,14 +28,12 @@ #include <stddef.h> #include <stdint.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -48,7 +46,10 @@ struct bpf_create_map_attr { __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 map_ifindex; - __u32 inner_map_fd; + union { + __u32 inner_map_fd; + __u32 btf_vmlinux_value_type_id; + }; }; LIBBPF_API int @@ -126,10 +127,43 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); + +struct bpf_map_batch_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 elem_flags; + __u64 flags; +}; +#define bpf_map_batch_opts__last_field flags + +LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, + void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts); + LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); + +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + unsigned int flags; + int replace_prog_fd; +}; +#define bpf_prog_attach_opts__last_field replace_prog_fd + LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 0c7d28292898..f69cc208778a 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -25,6 +25,9 @@ #ifndef __always_inline #define __always_inline __attribute__((always_inline)) #endif +#ifndef __weak +#define __weak __attribute__((weak)) +#endif /* * Helper structure used by eBPF C program @@ -44,4 +47,12 @@ enum libbpf_pin_type { LIBBPF_PIN_BY_NAME, }; +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +#define __kconfig __attribute__((section(".kconfig"))) + #endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 3ed1a27b5f7c..bafca49cb1e6 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -8,6 +8,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + struct bpf_prog_linfo { void *raw_linfo; void *raw_jited_linfo; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 88efa2bb7137..3d1c25fc97ae 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -8,6 +8,10 @@ #include <fcntl.h> #include <unistd.h> #include <errno.h> +#include <sys/utsname.h> +#include <sys/param.h> +#include <sys/stat.h> +#include <linux/kernel.h> #include <linux/err.h> #include <linux/btf.h> #include <gelf.h> @@ -17,8 +21,11 @@ #include "libbpf_internal.h" #include "hashmap.h" -#define BTF_MAX_NR_TYPES 0x7fffffff -#define BTF_MAX_STR_OFFSET 0x7fffffff +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +#define BTF_MAX_NR_TYPES 0x7fffffffU +#define BTF_MAX_STR_OFFSET 0x7fffffffU static struct btf_type btf_void; @@ -50,7 +57,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; - expand_by = max(btf->types_size >> 2, 16); + expand_by = max(btf->types_size >> 2, 16U); new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); new_types = realloc(btf->types, sizeof(*new_types) * new_size); @@ -278,6 +285,45 @@ done: return nelems * size; } +int btf__align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u16 kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + return min(sizeof(void *), (size_t)t->size); + case BTF_KIND_PTR: + return sizeof(void *); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf__align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf__align_of(btf, btf_array(t)->type); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, max_align = 1, align; + + for (i = 0; i < vlen; i++, m++) { + align = btf__align_of(btf, m->type); + if (align <= 0) + return align; + max_align = max(max_align, align); + } + + return max_align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 0; + } +} + int btf__resolve_type(const struct btf *btf, __u32 type_id) { const struct btf_type *t; @@ -539,6 +585,12 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, return -ENOENT; } + /* .extern datasec size and var offsets were set correctly during + * extern collection step, so just skip straight to sorting variables + */ + if (t->size) + goto sort_vars; + ret = bpf_object__section_size(obj, name, &size); if (ret || !size || (t->size && t->size != size)) { pr_debug("Invalid size for section %s: %u bytes\n", name, size); @@ -575,7 +627,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, vsi->offset = off; } - qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); return 0; } @@ -1352,7 +1405,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d, if (d->hypot_cnt == d->hypot_cap) { __u32 *new_list; - d->hypot_cap += max(16, d->hypot_cap / 2); + d->hypot_cap += max((size_t)16, d->hypot_cap / 2); new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); if (!new_list) return -ENOMEM; @@ -1648,7 +1701,7 @@ static int btf_dedup_strings(struct btf_dedup *d) if (strs.cnt + 1 > strs.cap) { struct btf_str_ptr *new_ptrs; - strs.cap += max(strs.cnt / 2, 16); + strs.cap += max(strs.cnt / 2, 16U); new_ptrs = realloc(strs.ptrs, sizeof(strs.ptrs[0]) * strs.cap); if (!new_ptrs) { @@ -2882,3 +2935,89 @@ 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. + */ +struct btf *libbpf_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index d9ac73a02cde..70c1b7ec2bd0 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -8,14 +8,12 @@ #include <linux/btf.h> #include <linux/types.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" #define MAPS_ELF_SEC ".maps" @@ -79,6 +77,7 @@ LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); @@ -103,6 +102,8 @@ LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf, LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API struct btf *libbpf_find_kernel_btf(void); + struct btf_dedup_opts { unsigned int dedup_table_size; bool dont_resolve_fwds; @@ -127,6 +128,28 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +struct btf_dump_emit_type_decl_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* optional field name for type declaration, e.g.: + * - struct my_struct <FNAME> + * - void (*<FNAME>)(int) + * - char (*<FNAME>)[123] + */ + const char *field_name; + /* extra indentation level (in number of tabs) to emit for multi-line + * type declarations (e.g., anonymous struct); applies for lines + * starting from the second one (first line is assumed to have + * necessary indentation already + */ + int indent_level; +}; +#define btf_dump_emit_type_decl_opts__last_field indent_level + +LIBBPF_API int +btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts); + /* * A set of helpers for easier BTF types handling */ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cb126d8fcf75..bd09ed1710f1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -18,6 +18,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; @@ -116,6 +119,8 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_end(args); } +static int btf_dump_mark_referenced(struct btf_dump *d); + struct btf_dump *btf_dump__new(const struct btf *btf, const struct btf_ext *btf_ext, const struct btf_dump_opts *opts, @@ -137,18 +142,40 @@ struct btf_dump *btf_dump__new(const struct btf *btf, if (IS_ERR(d->type_names)) { err = PTR_ERR(d->type_names); d->type_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto err; } d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->ident_names)) { err = PTR_ERR(d->ident_names); d->ident_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto err; + } + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) { + err = -ENOMEM; + goto err; + } + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) { + err = -ENOMEM; + goto err; } + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + goto err; + return d; +err: + btf_dump__free(d); + return ERR_PTR(err); } void btf_dump__free(struct btf_dump *d) @@ -175,7 +202,6 @@ void btf_dump__free(struct btf_dump *d) free(d); } -static int btf_dump_mark_referenced(struct btf_dump *d); static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); @@ -202,27 +228,6 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) if (id > btf__get_nr_types(d->btf)) return -EINVAL; - /* type states are lazily allocated, as they might not be needed */ - if (!d->type_states) { - d->type_states = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->type_states[0])); - if (!d->type_states) - return -ENOMEM; - d->cached_names = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->cached_names[0])); - if (!d->cached_names) - return -ENOMEM; - - /* VOID is special */ - d->type_states[0].order_state = ORDERED; - d->type_states[0].emit_state = EMITTED; - - /* eagerly determine referenced types for anon enums */ - err = btf_dump_mark_referenced(d); - if (err) - return err; - } - d->emit_queue_cnt = 0; err = btf_dump_order_type(d, id, false); if (err < 0) @@ -752,41 +757,6 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } -static int btf_align_of(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind(t); - - switch (kind) { - case BTF_KIND_INT: - case BTF_KIND_ENUM: - return min(sizeof(void *), t->size); - case BTF_KIND_PTR: - return sizeof(void *); - case BTF_KIND_TYPEDEF: - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: - return btf_align_of(btf, btf_array(t)->type); - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - const struct btf_member *m = btf_members(t); - __u16 vlen = btf_vlen(t); - int i, align = 1; - - for (i = 0; i < vlen; i++, m++) - align = max(align, btf_align_of(btf, m->type)); - - return align; - } - default: - pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); - return 1; - } -} - static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { @@ -794,18 +764,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, int align, i, bit_sz; __u16 vlen; - align = btf_align_of(btf, id); + align = btf__align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ - if (t->size % align) + if (align && t->size % align) return true; m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { - align = btf_align_of(btf, m->type); + align = btf__align_of(btf, m->type); bit_sz = btf_member_bitfield_size(t, i); - if (bit_sz == 0 && m->offset % (8 * align) != 0) + if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -889,7 +859,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf_align_of(d->btf, m->type); + align = packed ? 1 : btf__align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); @@ -907,7 +877,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, /* pad at the end, if necessary */ if (is_struct) { - align = packed ? 1 : btf_align_of(d->btf, id); + align = packed ? 1 : btf__align_of(d->btf, id); btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, lvl + 1); } @@ -1051,6 +1021,21 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) * of a stack frame. Some care is required to "pop" stack frames after * processing type declaration chain. */ +int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts) +{ + const char *fname; + int lvl; + + if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) + return -EINVAL; + + fname = OPTS_GET(opts, field_name, NULL); + lvl = OPTS_GET(opts, indent_level, 0); + btf_dump_emit_type_decl(d, id, fname, lvl); + return 0; +} + static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, const char *fname, int lvl) { diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 6122272943e6..54c30c802070 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -12,6 +12,9 @@ #include <linux/err.h> #include "hashmap.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 3f09772192f1..514b1a524abb 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -18,6 +18,7 @@ #include <stdarg.h> #include <libgen.h> #include <inttypes.h> +#include <limits.h> #include <string.h> #include <unistd.h> #include <endian.h> @@ -41,9 +42,11 @@ #include <sys/types.h> #include <sys/vfs.h> #include <sys/utsname.h> +#include <sys/resource.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> +#include <zlib.h> #include "libbpf.h" #include "bpf.h" @@ -52,6 +55,9 @@ #include "libbpf_internal.h" #include "hashmap.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef EM_BPF #define EM_BPF 247 #endif @@ -67,6 +73,12 @@ #define __printf(a, b) __attribute__((format(printf, a, b))) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); +static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj, + int idx); +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); + static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { @@ -99,14 +111,33 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) va_end(args); } -#define STRERR_BUFSIZE 128 +static void pr_perm_msg(int err) +{ + struct rlimit limit; + char buf[100]; + + if (err != -EPERM || geteuid() != 0) + return; + + err = getrlimit(RLIMIT_MEMLOCK, &limit); + if (err) + return; + + if (limit.rlim_cur == RLIM_INFINITY) + return; -#define CHECK_ERR(action, err, out) do { \ - err = action; \ - if (err) \ - goto out; \ -} while (0) + if (limit.rlim_cur < 1024) + snprintf(buf, sizeof(buf), "%zu bytes", (size_t)limit.rlim_cur); + else if (limit.rlim_cur < 1024*1024) + snprintf(buf, sizeof(buf), "%.1f KiB", (double)limit.rlim_cur / 1024); + else + snprintf(buf, sizeof(buf), "%.1f MiB", (double)limit.rlim_cur / (1024*1024)); + + pr_warn("permission error while running as root; try raising 'ulimit -l'? current value: %s\n", + buf); +} +#define STRERR_BUFSIZE 128 /* Copied from tools/perf/util/util.h */ #ifndef zfree @@ -144,6 +175,22 @@ struct bpf_capabilities { __u32 btf_datasec:1; /* BPF_F_MMAPABLE is supported for arrays */ __u32 array_mmap:1; + /* BTF_FUNC_GLOBAL is supported */ + __u32 btf_func_global:1; +}; + +enum reloc_type { + RELO_LD64, + RELO_CALL, + RELO_DATA, + RELO_EXTERN, +}; + +struct reloc_desc { + enum reloc_type type; + int insn_idx; + int map_idx; + int sym_off; }; /* @@ -164,16 +211,7 @@ struct bpf_program { size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct reloc_desc { - enum { - RELO_LD64, - RELO_CALL, - RELO_DATA, - } type; - int insn_idx; - int map_idx; - int sym_off; - } *reloc_desc; + struct reloc_desc *reloc_desc; int nr_reloc; int log_level; @@ -202,22 +240,51 @@ struct bpf_program { __u32 prog_flags; }; +struct bpf_struct_ops { + const char *tname; + const struct btf_type *type; + struct bpf_program **progs; + __u32 *kern_func_off; + /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */ + void *data; + /* e.g. struct bpf_struct_ops_tcp_congestion_ops in + * btf_vmlinux's format. + * struct bpf_struct_ops_tcp_congestion_ops { + * [... some other kernel fields ...] + * struct tcp_congestion_ops data; + * } + * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops) + * bpf_map__init_kern_struct_ops() will populate the "kern_vdata" + * from "data". + */ + void *kern_vdata; + __u32 type_id; +}; + +#define DATA_SEC ".data" +#define BSS_SEC ".bss" +#define RODATA_SEC ".rodata" +#define KCONFIG_SEC ".kconfig" +#define STRUCT_OPS_SEC ".struct_ops" + enum libbpf_map_type { LIBBPF_MAP_UNSPEC, LIBBPF_MAP_DATA, LIBBPF_MAP_BSS, LIBBPF_MAP_RODATA, + LIBBPF_MAP_KCONFIG, }; static const char * const libbpf_type_to_btf_name[] = { - [LIBBPF_MAP_DATA] = ".data", - [LIBBPF_MAP_BSS] = ".bss", - [LIBBPF_MAP_RODATA] = ".rodata", + [LIBBPF_MAP_DATA] = DATA_SEC, + [LIBBPF_MAP_BSS] = BSS_SEC, + [LIBBPF_MAP_RODATA] = RODATA_SEC, + [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC, }; struct bpf_map { - int fd; char *name; + int fd; int sec_idx; size_t sec_offset; int map_ifindex; @@ -225,17 +292,37 @@ struct bpf_map { struct bpf_map_def def; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; enum libbpf_map_type libbpf_type; + void *mmaped; + struct bpf_struct_ops *st_ops; char *pin_path; bool pinned; bool reused; }; -struct bpf_secdata { - void *rodata; - void *data; +enum extern_type { + EXT_UNKNOWN, + EXT_CHAR, + EXT_BOOL, + EXT_INT, + EXT_TRISTATE, + EXT_CHAR_ARR, +}; + +struct extern_desc { + const char *name; + int sym_idx; + int btf_id; + enum extern_type type; + int sz; + int align; + int data_off; + bool is_signed; + bool is_weak; + bool is_set; }; static LIST_HEAD(bpf_objects_list); @@ -250,11 +337,14 @@ struct bpf_object { struct bpf_map *maps; size_t nr_maps; size_t maps_cap; - struct bpf_secdata sections; + + char *kconfig; + struct extern_desc *externs; + int nr_extern; + int kconfig_map_idx; bool loaded; bool has_pseudo_calls; - bool relaxed_core_relocs; /* * Information when doing elf related work. Only valid if fd @@ -270,6 +360,7 @@ struct bpf_object { Elf_Data *data; Elf_Data *rodata; Elf_Data *bss; + Elf_Data *st_ops_data; size_t strtabidx; struct { GElf_Shdr shdr; @@ -279,9 +370,11 @@ struct bpf_object { int maps_shndx; int btf_maps_shndx; int text_shndx; + int symbols_shndx; int data_shndx; int rodata_shndx; int bss_shndx; + int st_ops_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -291,6 +384,10 @@ struct bpf_object { struct list_head list; struct btf *btf; + /* Parse and load BTF vmlinux if any of the programs in the object need + * it at load time. + */ + struct btf *btf_vmlinux; struct btf_ext *btf_ext; void *priv; @@ -509,6 +606,348 @@ static __u32 get_kernel_version(void) return KERNEL_VERSION(major, minor, patch); } +static const struct btf_member * +find_member_by_offset(const struct btf_type *t, __u32 bit_offset) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (btf_member_bit_offset(t, i) == bit_offset) + return m; + } + + return NULL; +} + +static const struct btf_member * +find_member_by_name(const struct btf *btf, const struct btf_type *t, + const char *name) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (!strcmp(btf__name_by_offset(btf, m->name_off), name)) + return m; + } + + return NULL; +} + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind); + +static int +find_struct_ops_kern_types(const struct btf *btf, const char *tname, + const struct btf_type **type, __u32 *type_id, + const struct btf_type **vtype, __u32 *vtype_id, + const struct btf_member **data_member) +{ + const struct btf_type *kern_type, *kern_vtype; + const struct btf_member *kern_data_member; + __s32 kern_vtype_id, kern_type_id; + __u32 i; + + kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (kern_type_id < 0) { + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", + tname); + return kern_type_id; + } + kern_type = btf__type_by_id(btf, kern_type_id); + + /* Find the corresponding "map_value" type that will be used + * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example, + * find "struct bpf_struct_ops_tcp_congestion_ops" from the + * btf_vmlinux. + */ + kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX, + tname, BTF_KIND_STRUCT); + if (kern_vtype_id < 0) { + pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n", + STRUCT_OPS_VALUE_PREFIX, tname); + return kern_vtype_id; + } + kern_vtype = btf__type_by_id(btf, kern_vtype_id); + + /* Find "struct tcp_congestion_ops" from + * struct bpf_struct_ops_tcp_congestion_ops { + * [ ... ] + * struct tcp_congestion_ops data; + * } + */ + kern_data_member = btf_members(kern_vtype); + for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) { + if (kern_data_member->type == kern_type_id) + break; + } + if (i == btf_vlen(kern_vtype)) { + pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n", + tname, STRUCT_OPS_VALUE_PREFIX, tname); + return -EINVAL; + } + + *type = kern_type; + *type_id = kern_type_id; + *vtype = kern_vtype; + *vtype_id = kern_vtype_id; + *data_member = kern_data_member; + + return 0; +} + +static bool bpf_map__is_struct_ops(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_STRUCT_OPS; +} + +/* Init the map's fields that depend on kern_btf */ +static int bpf_map__init_kern_struct_ops(struct bpf_map *map, + const struct btf *btf, + const struct btf *kern_btf) +{ + const struct btf_member *member, *kern_member, *kern_data_member; + const struct btf_type *type, *kern_type, *kern_vtype; + __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_struct_ops *st_ops; + void *data, *kern_data; + const char *tname; + int err; + + st_ops = map->st_ops; + type = st_ops->type; + tname = st_ops->tname; + err = find_struct_ops_kern_types(kern_btf, tname, + &kern_type, &kern_type_id, + &kern_vtype, &kern_vtype_id, + &kern_data_member); + if (err) + return err; + + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", + map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + + map->def.value_size = kern_vtype->size; + map->btf_vmlinux_value_type_id = kern_vtype_id; + + st_ops->kern_vdata = calloc(1, kern_vtype->size); + if (!st_ops->kern_vdata) + return -ENOMEM; + + data = st_ops->data; + kern_data_off = kern_data_member->offset / 8; + kern_data = st_ops->kern_vdata + kern_data_off; + + member = btf_members(type); + for (i = 0; i < btf_vlen(type); i++, member++) { + const struct btf_type *mtype, *kern_mtype; + __u32 mtype_id, kern_mtype_id; + void *mdata, *kern_mdata; + __s64 msize, kern_msize; + __u32 moff, kern_moff; + __u32 kern_member_idx; + const char *mname; + + mname = btf__name_by_offset(btf, member->name_off); + kern_member = find_member_by_name(kern_btf, kern_type, mname); + if (!kern_member) { + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + map->name, mname); + return -ENOTSUP; + } + + kern_member_idx = kern_member - btf_members(kern_type); + if (btf_member_bitfield_size(type, i) || + btf_member_bitfield_size(kern_type, kern_member_idx)) { + pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + moff = member->offset / 8; + kern_moff = kern_member->offset / 8; + + mdata = data + moff; + kern_mdata = kern_data + kern_moff; + + mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type, + &kern_mtype_id); + if (BTF_INFO_KIND(mtype->info) != + BTF_INFO_KIND(kern_mtype->info)) { + pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n", + map->name, mname, BTF_INFO_KIND(mtype->info), + BTF_INFO_KIND(kern_mtype->info)); + return -ENOTSUP; + } + + if (btf_is_ptr(mtype)) { + struct bpf_program *prog; + + mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, + kern_mtype->type, + &kern_mtype_id); + if (!btf_is_func_proto(mtype) || + !btf_is_func_proto(kern_mtype)) { + pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + prog = st_ops->progs[i]; + if (!prog) { + pr_debug("struct_ops init_kern %s: func ptr %s is not set\n", + map->name, mname); + continue; + } + + prog->attach_btf_id = kern_type_id; + prog->expected_attach_type = kern_member_idx; + + st_ops->kern_func_off[i] = kern_data_off + kern_moff; + + pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n", + map->name, mname, prog->name, moff, + kern_moff); + + continue; + } + + msize = btf__resolve_size(btf, mtype_id); + kern_msize = btf__resolve_size(kern_btf, kern_mtype_id); + if (msize < 0 || kern_msize < 0 || msize != kern_msize) { + pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n", + map->name, mname, (ssize_t)msize, + (ssize_t)kern_msize); + return -ENOTSUP; + } + + pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n", + map->name, mname, (unsigned int)msize, + moff, kern_moff); + memcpy(kern_mdata, mdata, msize); + } + + return 0; +} + +static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) +{ + struct bpf_map *map; + size_t i; + int err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!bpf_map__is_struct_ops(map)) + continue; + + err = bpf_map__init_kern_struct_ops(map, obj->btf, + obj->btf_vmlinux); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) +{ + const struct btf_type *type, *datasec; + const struct btf_var_secinfo *vsi; + struct bpf_struct_ops *st_ops; + const char *tname, *var_name; + __s32 type_id, datasec_id; + const struct btf *btf; + struct bpf_map *map; + __u32 i; + + if (obj->efile.st_ops_shndx == -1) + return 0; + + btf = obj->btf; + datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC, + BTF_KIND_DATASEC); + if (datasec_id < 0) { + pr_warn("struct_ops init: DATASEC %s not found\n", + STRUCT_OPS_SEC); + return -EINVAL; + } + + datasec = btf__type_by_id(btf, datasec_id); + vsi = btf_var_secinfos(datasec); + for (i = 0; i < btf_vlen(datasec); i++, vsi++) { + type = btf__type_by_id(obj->btf, vsi->type); + var_name = btf__name_by_offset(obj->btf, type->name_off); + + type_id = btf__resolve_type(obj->btf, vsi->type); + if (type_id < 0) { + pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n", + vsi->type, STRUCT_OPS_SEC); + return -EINVAL; + } + + type = btf__type_by_id(obj->btf, type_id); + tname = btf__name_by_offset(obj->btf, type->name_off); + if (!tname[0]) { + pr_warn("struct_ops init: anonymous type is not supported\n"); + return -ENOTSUP; + } + if (!btf_is_struct(type)) { + pr_warn("struct_ops init: %s is not a struct\n", tname); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->sec_idx = obj->efile.st_ops_shndx; + map->sec_offset = vsi->offset; + map->name = strdup(var_name); + if (!map->name) + return -ENOMEM; + + map->def.type = BPF_MAP_TYPE_STRUCT_OPS; + map->def.key_size = sizeof(int); + map->def.value_size = type->size; + map->def.max_entries = 1; + + map->st_ops = calloc(1, sizeof(*map->st_ops)); + if (!map->st_ops) + return -ENOMEM; + st_ops = map->st_ops; + st_ops->data = malloc(type->size); + st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs)); + st_ops->kern_func_off = malloc(btf_vlen(type) * + sizeof(*st_ops->kern_func_off)); + if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off) + return -ENOMEM; + + if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) { + pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n", + var_name, STRUCT_OPS_SEC); + return -EINVAL; + } + + memcpy(st_ops->data, + obj->efile.st_ops_data->d_buf + vsi->offset, + type->size); + st_ops->tname = tname; + st_ops->type = type; + st_ops->type_id = type_id; + + pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n", + tname, type_id, var_name, vsi->offset); + } + + return 0; +} + static struct bpf_object *bpf_object__new(const char *path, const void *obj_buf, size_t obj_buf_sz, @@ -550,6 +989,8 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; + obj->efile.st_ops_shndx = -1; + obj->kconfig_map_idx = -1; obj->kern_version = get_kernel_version(); obj->loaded = false; @@ -572,6 +1013,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.data = NULL; obj->efile.rodata = NULL; obj->efile.bss = NULL; + obj->efile.st_ops_data = NULL; zfree(&obj->efile.reloc_sects); obj->efile.nr_reloc_sects = 0; @@ -677,16 +1119,6 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) return 0; } -static int compare_bpf_map(const void *_a, const void *_b) -{ - const struct bpf_map *a = _a; - const struct bpf_map *b = _b; - - if (a->sec_idx != b->sec_idx) - return a->sec_idx - b->sec_idx; - return a->sec_offset - b->sec_offset; -} - static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) { if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || @@ -748,15 +1180,18 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, *size = 0; if (!name) { return -EINVAL; - } else if (!strcmp(name, ".data")) { + } else if (!strcmp(name, DATA_SEC)) { if (obj->efile.data) *size = obj->efile.data->d_size; - } else if (!strcmp(name, ".bss")) { + } else if (!strcmp(name, BSS_SEC)) { if (obj->efile.bss) *size = obj->efile.bss->d_size; - } else if (!strcmp(name, ".rodata")) { + } else if (!strcmp(name, RODATA_SEC)) { if (obj->efile.rodata) *size = obj->efile.rodata->d_size; + } else if (!strcmp(name, STRUCT_OPS_SEC)) { + if (obj->efile.st_ops_data) + *size = obj->efile.st_ops_data->d_size; } else { ret = bpf_object_search_section_size(obj, name, &d_size); if (!ret) @@ -835,13 +1270,38 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return &obj->maps[obj->nr_maps++]; } +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static char *internal_map_name(struct bpf_object *obj, + enum libbpf_map_type type) +{ + char map_name[BPF_OBJ_NAME_LEN]; + const char *sfx = libbpf_type_to_btf_name[type]; + int sfx_len = max((size_t)7, strlen(sfx)); + int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, + strlen(obj->name)); + + snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, + sfx_len, libbpf_type_to_btf_name[type]); + + return strdup(map_name); +} + static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - int sec_idx, Elf_Data *data, void **data_buff) + int sec_idx, void *data, size_t data_sz) { - char map_name[BPF_OBJ_NAME_LEN]; struct bpf_map_def *def; struct bpf_map *map; + int err; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -850,9 +1310,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, map->libbpf_type = type; map->sec_idx = sec_idx; map->sec_offset = 0; - snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, - libbpf_type_to_btf_name[type]); - map->name = strdup(map_name); + map->name = internal_map_name(obj, type); if (!map->name) { pr_warn("failed to alloc map name\n"); return -ENOMEM; @@ -861,25 +1319,29 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); - def->value_size = data->d_size; + def->value_size = data_sz; def->max_entries = 1; - def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; - if (obj->caps.array_mmap) - def->map_flags |= BPF_F_MMAPABLE; + def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG + ? BPF_F_RDONLY_PROG : 0; + def->map_flags |= BPF_F_MMAPABLE; pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", - map_name, map->sec_idx, map->sec_offset, def->map_flags); + map->name, map->sec_idx, map->sec_offset, def->map_flags); - if (data_buff) { - *data_buff = malloc(data->d_size); - if (!*data_buff) { - zfree(&map->name); - pr_warn("failed to alloc map content buffer\n"); - return -ENOMEM; - } - memcpy(*data_buff, data->d_buf, data->d_size); + map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (map->mmaped == MAP_FAILED) { + err = -errno; + map->mmaped = NULL; + pr_warn("failed to alloc map '%s' content buffer: %d\n", + map->name, err); + zfree(&map->name); + return err; } + if (data) + memcpy(map->mmaped, data, data_sz); + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); return 0; } @@ -888,37 +1350,332 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) { int err; - if (!obj->caps.global_data) - return 0; /* * Populate obj->maps with libbpf internal maps. */ if (obj->efile.data_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, obj->efile.data_shndx, - obj->efile.data, - &obj->sections.data); + obj->efile.data->d_buf, + obj->efile.data->d_size); if (err) return err; } if (obj->efile.rodata_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, obj->efile.rodata_shndx, - obj->efile.rodata, - &obj->sections.rodata); + obj->efile.rodata->d_buf, + obj->efile.rodata->d_size); if (err) return err; } if (obj->efile.bss_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, obj->efile.bss_shndx, - obj->efile.bss, NULL); + NULL, + obj->efile.bss->d_size); if (err) return err; } return 0; } + +static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, + const void *name) +{ + int i; + + for (i = 0; i < obj->nr_extern; i++) { + if (strcmp(obj->externs[i].name, name) == 0) + return &obj->externs[i]; + } + return NULL; +} + +static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, + char value) +{ + switch (ext->type) { + case EXT_BOOL: + if (value == 'm') { + pr_warn("extern %s=%c should be tristate or char\n", + ext->name, value); + return -EINVAL; + } + *(bool *)ext_val = value == 'y' ? true : false; + break; + case EXT_TRISTATE: + if (value == 'y') + *(enum libbpf_tristate *)ext_val = TRI_YES; + else if (value == 'm') + *(enum libbpf_tristate *)ext_val = TRI_MODULE; + else /* value == 'n' */ + *(enum libbpf_tristate *)ext_val = TRI_NO; + break; + case EXT_CHAR: + *(char *)ext_val = value; + break; + case EXT_UNKNOWN: + case EXT_INT: + case EXT_CHAR_ARR: + default: + pr_warn("extern %s=%c should be bool, tristate, or char\n", + ext->name, value); + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int set_ext_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); + return -EINVAL; + } + + len = strlen(value); + if (value[len - 1] != '"') { + pr_warn("extern '%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; + } + memcpy(ext_val, value + 1, len); + ext_val[len] = '\0'; + ext->is_set = true; + return 0; +} + +static int parse_u64(const char *value, __u64 *res) +{ + char *value_end; + int err; + + errno = 0; + *res = strtoull(value, &value_end, 0); + if (errno) { + err = -errno; + pr_warn("failed to parse '%s' as integer: %d\n", value, err); + return err; + } + if (*value_end) { + pr_warn("failed to parse '%s' as integer completely\n", value); + return -EINVAL; + } + return 0; +} + +static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) +{ + int bit_sz = ext->sz * 8; + + if (ext->sz == 8) + return true; + + /* Validate that value stored in u64 fits in integer of `ext->sz` + * bytes size without any loss of information. If the target integer + * is signed, we rely on the following limits of integer type of + * Y bits and subsequent transformation: + * + * -2^(Y-1) <= X <= 2^(Y-1) - 1 + * 0 <= X + 2^(Y-1) <= 2^Y - 1 + * 0 <= X + 2^(Y-1) < 2^Y + * + * For unsigned target integer, check that all the (64 - Y) bits are + * zero. + */ + if (ext->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) +{ + if (ext->type != EXT_INT && ext->type != EXT_CHAR) { + pr_warn("extern %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); + return -ERANGE; + } + switch (ext->sz) { + case 1: *(__u8 *)ext_val = value; break; + case 2: *(__u16 *)ext_val = value; break; + case 4: *(__u32 *)ext_val = value; break; + case 8: *(__u64 *)ext_val = value; break; + default: + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int bpf_object__process_kconfig_line(struct bpf_object *obj, + char *buf, void *data) +{ + struct extern_desc *ext; + char *sep, *value; + int len, err = 0; + void *ext_val; + __u64 num; + + if (strncmp(buf, "CONFIG_", 7)) + return 0; + + sep = strchr(buf, '='); + if (!sep) { + pr_warn("failed to parse '%s': no separator\n", buf); + return -EINVAL; + } + + /* Trim ending '\n' */ + len = strlen(buf); + if (buf[len - 1] == '\n') + buf[len - 1] = '\0'; + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) { + *sep = '='; + pr_warn("failed to parse '%s': no value\n", buf); + return -EINVAL; + } + + ext = find_extern_by_name(obj, buf); + if (!ext || ext->is_set) + return 0; + + ext_val = data + ext->data_off; + value = sep + 1; + + switch (*value) { + case 'y': case 'n': case 'm': + err = set_ext_value_tri(ext, ext_val, *value); + break; + case '"': + err = set_ext_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", + ext->name, value); + return err; + } + err = set_ext_value_num(ext, ext_val, num); + break; + } + if (err) + return err; + pr_debug("extern %s=%s\n", ext->name, value); + return 0; +} + +static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) +{ + char buf[PATH_MAX]; + struct utsname uts; + int len, err = 0; + gzFile file; + + uname(&uts); + len = snprintf(buf, PATH_MAX, "/boot/config-%s", uts.release); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + /* gzopen also accepts uncompressed files. */ + file = gzopen(buf, "r"); + if (!file) + file = gzopen("/proc/config.gz", "r"); + + if (!file) { + pr_warn("failed to open system Kconfig\n"); + return -ENOENT; + } + + while (gzgets(file, buf, sizeof(buf))) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing system Kconfig line '%s': %d\n", + buf, err); + goto out; + } + } + +out: + gzclose(file); + return err; +} + +static int bpf_object__read_kconfig_mem(struct bpf_object *obj, + const char *config, void *data) +{ + char buf[PATH_MAX]; + int err = 0; + FILE *file; + + file = fmemopen((void *)config, strlen(config), "r"); + if (!file) { + err = -errno; + pr_warn("failed to open in-memory Kconfig: %d\n", err); + return err; + } + + while (fgets(buf, sizeof(buf), file)) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing in-memory Kconfig line '%s': %d\n", + buf, err); + break; + } + } + + fclose(file); + return err; +} + +static int bpf_object__init_kconfig_map(struct bpf_object *obj) +{ + struct extern_desc *last_ext; + size_t map_sz; + int err; + + if (obj->nr_extern == 0) + return 0; + + last_ext = &obj->externs[obj->nr_extern - 1]; + map_sz = last_ext->data_off + last_ext->sz; + + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, + obj->efile.symbols_shndx, + NULL, map_sz); + if (err) + return err; + + obj->kconfig_map_idx = obj->nr_maps - 1; + + return 0; +} + static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { Elf_Data *symbols = obj->efile.symbols; @@ -1060,6 +1817,20 @@ skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) return t; } +static const struct btf_type * +resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t; + + t = skip_mods_and_typedefs(btf, id, NULL); + if (!btf_is_ptr(t)) + return NULL; + + t = skip_mods_and_typedefs(btf, t->type, res_id); + + return btf_is_func_proto(t) ? t : NULL; +} + /* * Fetch integer attribute of BTF map definition. Such attributes are * represented using a pointer to an array, in which dimensionality of array @@ -1242,15 +2013,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine key size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found key [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found key [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warn("map '%s': conflicting key size %u != %lld.\n", - map_name, map->def.key_size, sz); + pr_warn("map '%s': conflicting key size %u != %zd.\n", + map_name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -1285,15 +2056,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine value size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found value [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found value [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warn("map '%s': conflicting value size %u != %lld.\n", - map_name, map->def.value_size, sz); + pr_warn("map '%s': conflicting value size %u != %zd.\n", + map_name, map->def.value_size, (ssize_t)sz); return -EINVAL; } map->def.value_size = sz; @@ -1393,28 +2164,24 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__init_maps(struct bpf_object *obj, + const struct bpf_object_open_opts *opts) { - bool strict = !relaxed_maps; + const char *pin_root_path; + bool strict; int err; - err = bpf_object__init_user_maps(obj, strict); - if (err) - return err; - - err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); - if (err) - return err; + strict = !OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = bpf_object__init_global_data_maps(obj); + err = bpf_object__init_user_maps(obj, strict); + err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = err ?: bpf_object__init_global_data_maps(obj); + err = err ?: bpf_object__init_kconfig_map(obj); + err = err ?: bpf_object__init_struct_ops_maps(obj); if (err) return err; - if (obj->nr_maps) { - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), - compare_bpf_map); - } return 0; } @@ -1438,13 +2205,14 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) static void bpf_object__sanitize_btf(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; struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - if (!obj->btf || (has_func && has_datasec)) + if (!obj->btf || (has_func && has_datasec && has_func_global)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { @@ -1492,6 +2260,9 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } else if (!has_func_global && btf_is_func(t)) { + /* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */ + t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0); } } } @@ -1509,28 +2280,27 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) { - return obj->efile.btf_maps_shndx >= 0; + return obj->efile.btf_maps_shndx >= 0 || + obj->efile.st_ops_shndx >= 0 || + obj->nr_extern > 0; } static int bpf_object__init_btf(struct bpf_object *obj, Elf_Data *btf_data, Elf_Data *btf_ext_data) { - bool btf_required = bpf_object__is_btf_mandatory(obj); - int err = 0; + int err = -ENOENT; if (btf_data) { obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); if (IS_ERR(obj->btf)) { + err = PTR_ERR(obj->btf); + obj->btf = NULL; pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); goto out; } - err = btf__finalize_data(obj, obj->btf); - if (err) { - pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); - goto out; - } + err = 0; } if (btf_ext_data) { if (!obj->btf) { @@ -1548,22 +2318,72 @@ static int bpf_object__init_btf(struct bpf_object *obj, } } out: - if (err || IS_ERR(obj->btf)) { - if (btf_required) - err = err ? : PTR_ERR(obj->btf); - else - err = 0; - if (!IS_ERR_OR_NULL(obj->btf)) - btf__free(obj->btf); - obj->btf = NULL; + if (err && bpf_object__is_btf_mandatory(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err; } - if (btf_required && !obj->btf) { + return 0; +} + +static int bpf_object__finalize_btf(struct bpf_object *obj) +{ + int err; + + if (!obj->btf) + 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 (bpf_object__is_btf_mandatory(obj)) { pr_warn("BTF is required, but is missing or corrupted.\n"); - return err == 0 ? -ENOENT : err; + return -ENOENT; } return 0; } +static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog) +{ + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return true; + + /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs + * also need vmlinux BTF + */ + if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd) + return true; + + return false; +} + +static int bpf_object__load_vmlinux_btf(struct bpf_object *obj) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + 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; + } + } + + return 0; +} + static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { int err = 0; @@ -1592,8 +2412,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return 0; } -static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; @@ -1665,6 +2484,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, return -LIBBPF_ERRNO__FORMAT; } obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { @@ -1683,12 +2503,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, name, obj->path, cp); return err; } - } else if (strcmp(name, ".data") == 0) { + } else if (strcmp(name, DATA_SEC) == 0) { obj->efile.data = data; obj->efile.data_shndx = idx; - } else if (strcmp(name, ".rodata") == 0) { + } else if (strcmp(name, RODATA_SEC) == 0) { obj->efile.rodata = data; obj->efile.rodata_shndx = idx; + } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { + obj->efile.st_ops_data = data; + obj->efile.st_ops_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } @@ -1698,7 +2521,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ - if (!section_have_execinstr(obj, sec)) { + if (!section_have_execinstr(obj, sec) && + strcmp(name, ".rel" STRUCT_OPS_SEC)) { pr_debug("skip relo %s(%d) for section(%d)\n", name, idx, sec); continue; @@ -1716,7 +2540,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, obj->efile.reloc_sects[nr_sects].shdr = sh; obj->efile.reloc_sects[nr_sects].data = data; - } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + } else if (sh.sh_type == SHT_NOBITS && + strcmp(name, BSS_SEC) == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { @@ -1728,14 +2553,217 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, pr_warn("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__init_btf(obj, btf_data, btf_ext_data); - if (!err) - err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); - if (!err) - err = bpf_object__sanitize_and_load_btf(obj); - if (!err) - err = bpf_object__init_prog_names(obj); - return err; + return bpf_object__init_btf(obj, btf_data, btf_ext_data); +} + +static bool sym_is_extern(const GElf_Sym *sym) +{ + int bind = GELF_ST_BIND(sym->st_info); + /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */ + return sym->st_shndx == SHN_UNDEF && + (bind == STB_GLOBAL || bind == STB_WEAK) && + GELF_ST_TYPE(sym->st_info) == STT_NOTYPE; +} + +static int find_extern_btf_id(const struct btf *btf, const char *ext_name) +{ + const struct btf_type *t; + const char *var_name; + int i, 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_var(t)) + continue; + + var_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(var_name, ext_name)) + continue; + + if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + + return i; + } + + return -ENOENT; +} + +static enum extern_type find_extern_type(const struct btf *btf, int id, + bool *is_signed) +{ + const struct btf_type *t; + const char *name; + + t = skip_mods_and_typedefs(btf, id, NULL); + name = btf__name_by_offset(btf, t->name_off); + + if (is_signed) + *is_signed = false; + switch (btf_kind(t)) { + case BTF_KIND_INT: { + int enc = btf_int_encoding(t); + + if (enc & BTF_INT_BOOL) + return t->size == 1 ? EXT_BOOL : EXT_UNKNOWN; + if (is_signed) + *is_signed = enc & BTF_INT_SIGNED; + if (t->size == 1) + return EXT_CHAR; + if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) + return EXT_UNKNOWN; + return EXT_INT; + } + case BTF_KIND_ENUM: + if (t->size != 4) + return EXT_UNKNOWN; + if (strcmp(name, "libbpf_tristate")) + return EXT_UNKNOWN; + return EXT_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; + default: + return EXT_UNKNOWN; + } +} + +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; + /* resolve ties by name */ + return strcmp(a->name, b->name); +} + +static int bpf_object__collect_externs(struct bpf_object *obj) +{ + const struct btf_type *t; + struct extern_desc *ext; + int i, n, off, btf_id; + struct btf_type *sec; + const char *ext_name; + Elf_Scn *scn; + GElf_Shdr sh; + + if (!obj->efile.symbols) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -LIBBPF_ERRNO__FORMAT; + if (gelf_getshdr(scn, &sh) != &sh) + return -LIBBPF_ERRNO__FORMAT; + n = sh.sh_size / sh.sh_entsize; + + pr_debug("looking for externs among %d symbols...\n", n); + for (i = 0; i < n; i++) { + GElf_Sym sym; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -LIBBPF_ERRNO__FORMAT; + if (!sym_is_extern(&sym)) + continue; + ext_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!ext_name || !ext_name[0]) + continue; + + ext = obj->externs; + ext = reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); + if (!ext) + return -ENOMEM; + obj->externs = ext; + ext = &ext[obj->nr_extern]; + memset(ext, 0, sizeof(*ext)); + obj->nr_extern++; + + ext->btf_id = find_extern_btf_id(obj->btf, ext_name); + if (ext->btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s': %d\n", + ext_name, ext->btf_id); + return ext->btf_id; + } + t = btf__type_by_id(obj->btf, ext->btf_id); + 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); + return -ENOTSUP; + } + } + pr_debug("collected %d externs total\n", obj->nr_extern); + + if (!obj->nr_extern) + return 0; + + /* sort externs by (alignment, size, name) and calculate their offsets + * within a map */ + 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; + } + + 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; + } + vs->offset = ext->data_off; + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + } + + return 0; } static struct bpf_program * @@ -1765,6 +2793,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, return NULL; } +struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + if (!strcmp(prog->name, name)) + return prog; + } + return NULL; +} + static bool bpf_object__shndx_is_data(const struct bpf_object *obj, int shndx) { @@ -1789,6 +2830,8 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) return LIBBPF_MAP_BSS; else if (shndx == obj->efile.rodata_shndx) return LIBBPF_MAP_RODATA; + else if (shndx == obj->efile.symbols_shndx) + return LIBBPF_MAP_KCONFIG; else return LIBBPF_MAP_UNSPEC; } @@ -1817,7 +2860,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } if (sym->st_value % 8) { - pr_warn("bad call relo offset: %llu\n", (__u64)sym->st_value); + pr_warn("bad call relo offset: %zu\n", + (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_CALL; @@ -1832,6 +2876,30 @@ static int bpf_program__record_reloc(struct bpf_program *prog, insn_idx, insn->code); return -LIBBPF_ERRNO__RELOC; } + + if (sym_is_extern(sym)) { + int sym_idx = GELF_R_SYM(rel->r_info); + int i, n = obj->nr_extern; + struct extern_desc *ext; + + for (i = 0; i < n; i++) { + ext = &obj->externs[i]; + if (ext->sym_idx == sym_idx) + break; + } + if (i >= n) { + pr_warn("extern relo failed to find extern for sym %d\n", + 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); + reloc_desc->type = RELO_EXTERN; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = ext->data_off; + return 0; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", name, shdr_idx); @@ -1859,8 +2927,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, break; } if (map_idx >= nr_maps) { - pr_warn("map relo failed to find map for sec %u, off %llu\n", - shdr_idx, (__u64)sym->st_value); + pr_warn("map relo failed to find map for sec %u, off %zu\n", + shdr_idx, (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_LD64; @@ -1875,11 +2943,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog, pr_warn("bad data relo against section %u\n", shdr_idx); return -LIBBPF_ERRNO__RELOC; } - if (!obj->caps.global_data) { - pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", - name, insn_idx); - return -LIBBPF_ERRNO__RELOC; - } for (map_idx = 0; map_idx < nr_maps; map_idx++) { map = &obj->maps[map_idx]; if (map->libbpf_type != type) @@ -1941,9 +3004,9 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name) ? : "<?>"; - pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", - (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), - (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + pr_debug("relo for shdr %u, symb %zu, value %zu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (size_t)GELF_R_SYM(rel.r_info), + (size_t)sym.st_value, GELF_ST_TYPE(sym.st_info), GELF_ST_BIND(sym.st_info), sym.st_name, name, insn_idx); @@ -1961,8 +3024,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; - /* if it's BTF-defined map, we don't need to search for type IDs */ - if (map->sec_idx == obj->efile.btf_maps_shndx) + /* if it's BTF-defined map, we don't need to search for type IDs. + * For struct_ops map, it does not need btf_key_type_id and + * btf_value_type_id. + */ + if (map->sec_idx == obj->efile.btf_maps_shndx || + bpf_map__is_struct_ops(map)) return 0; if (!bpf_map__is_internal(map)) { @@ -2166,6 +3233,32 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj) return 0; } +static int bpf_object__probe_btf_func_global(struct bpf_object *obj) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func_global = 1; + close(btf_fd); + return 1; + } + + return 0; +} + static int bpf_object__probe_btf_datasec(struct bpf_object *obj) { static const char strs[] = "\0x\0.data"; @@ -2221,6 +3314,7 @@ bpf_object__probe_caps(struct bpf_object *obj) bpf_object__probe_name, bpf_object__probe_global_data, bpf_object__probe_btf_func, + bpf_object__probe_btf_func_global, bpf_object__probe_btf_datasec, bpf_object__probe_array_mmap, }; @@ -2298,29 +3392,35 @@ bpf_object__reuse_map(struct bpf_map *map) static int bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) { + enum libbpf_map_type map_type = map->libbpf_type; char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; - __u8 *data; - /* Nothing to do here since kernel already zero-initializes .bss map. */ - if (map->libbpf_type == LIBBPF_MAP_BSS) + /* kernel already zero-initializes .bss map. */ + if (map_type == LIBBPF_MAP_BSS) return 0; - data = map->libbpf_type == LIBBPF_MAP_DATA ? - obj->sections.data : obj->sections.rodata; + err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); + if (err) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error setting initial map(%s) contents: %s\n", + map->name, cp); + return err; + } - err = bpf_map_update_elem(map->fd, &zero, data, 0); - /* Freeze .rodata map as read-only from syscall side. */ - if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + /* Freeze .rodata and .kconfig map as read-only from syscall side. */ + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) { err = bpf_map_freeze(map->fd); if (err) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("Error freezing map(%s) as read-only: %s\n", map->name, cp); - err = 0; + return err; } } - return err; + return 0; } static int @@ -2381,6 +3481,9 @@ bpf_object__create_maps(struct bpf_object *obj) if (bpf_map_type__is_map_in_map(def->type) && map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = + map->btf_vmlinux_value_type_id; if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); @@ -2411,6 +3514,7 @@ err_out: cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to create map (name: '%s'): %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -2536,6 +3640,21 @@ static bool str_is_empty(const char *s) return !s || !s[0]; } +static bool is_flex_arr(const struct btf *btf, + const struct bpf_core_accessor *acc, + const struct btf_array *arr) +{ + const struct btf_type *t; + + /* not a flexible array, if not inside a struct or has non-zero size */ + if (!acc->name || arr->nelems > 0) + return false; + + /* has to be the last member of enclosing struct */ + t = btf__type_by_id(btf, acc->type_id); + return acc->idx == btf_vlen(t) - 1; +} + /* * Turn bpf_field_reloc into a low- and high-level spec representation, * validating correctness along the way, as well as calculating resulting @@ -2573,6 +3692,7 @@ static int bpf_core_spec_parse(const struct btf *btf, struct bpf_core_spec *spec) { int access_idx, parsed_len, i; + struct bpf_core_accessor *acc; const struct btf_type *t; const char *name; __u32 id; @@ -2620,6 +3740,7 @@ static int bpf_core_spec_parse(const struct btf *btf, return -EINVAL; access_idx = spec->raw_spec[i]; + acc = &spec->spec[spec->len]; if (btf_is_composite(t)) { const struct btf_member *m; @@ -2637,18 +3758,23 @@ static int bpf_core_spec_parse(const struct btf *btf, if (str_is_empty(name)) return -EINVAL; - spec->spec[spec->len].type_id = id; - spec->spec[spec->len].idx = access_idx; - spec->spec[spec->len].name = name; + acc->type_id = id; + acc->idx = access_idx; + acc->name = name; spec->len++; } id = m->type; } else if (btf_is_array(t)) { const struct btf_array *a = btf_array(t); + bool flex; t = skip_mods_and_typedefs(btf, a->type, &id); - if (!t || access_idx >= a->nelems) + if (!t) + return -EINVAL; + + flex = is_flex_arr(btf, acc - 1, a); + if (!flex && access_idx >= a->nelems) return -EINVAL; spec->spec[spec->len].type_id = id; @@ -2743,7 +3869,9 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, if (strncmp(local_name, targ_name, local_essent_len) == 0) { pr_debug("[%d] %s: found candidate [%d] %s\n", local_type_id, local_name, i, targ_name); - new_ids = realloc(cand_ids->data, cand_ids->len + 1); + new_ids = reallocarray(cand_ids->data, + cand_ids->len + 1, + sizeof(*cand_ids->data)); if (!new_ids) { err = -ENOMEM; goto err_out; @@ -2953,12 +4081,14 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, */ if (i > 0) { const struct btf_array *a; + bool flex; if (!btf_is_array(targ_type)) return 0; a = btf_array(targ_type); - if (local_acc->idx >= a->nelems) + flex = is_flex_arr(targ_btf, targ_acc - 1, a); + if (!flex && local_acc->idx >= a->nelems) return 0; if (!skip_mods_and_typedefs(targ_btf, a->type, &targ_id)) @@ -3109,25 +4239,38 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog, */ static int bpf_core_reloc_insn(struct bpf_program *prog, const struct bpf_field_reloc *relo, + int relo_idx, const struct bpf_core_spec *local_spec, const struct bpf_core_spec *targ_spec) { - bool failed = false, validate = true; __u32 orig_val, new_val; struct bpf_insn *insn; + bool validate = true; int insn_idx, err; __u8 class; if (relo->insn_off % sizeof(struct bpf_insn)) return -EINVAL; insn_idx = relo->insn_off / sizeof(struct bpf_insn); + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); if (relo->kind == BPF_FIELD_EXISTS) { orig_val = 1; /* can't generate EXISTS relo w/o local field */ new_val = targ_spec ? 1 : 0; } else if (!targ_spec) { - failed = true; - new_val = (__u32)-1; + pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", + bpf_program__title(prog, false), relo_idx, insn_idx); + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with the following message: + * invalid func unknown#195896080 + */ + insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */ + return 0; } else { err = bpf_core_calc_field_relo(prog, relo, local_spec, &orig_val, &validate); @@ -3139,26 +4282,47 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, return err; } - insn = &prog->insns[insn_idx]; - class = BPF_CLASS(insn->code); - - if (class == BPF_ALU || class == BPF_ALU64) { + switch (class) { + case BPF_ALU: + case BPF_ALU64: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; - if (!failed && validate && insn->imm != orig_val) { - pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", - bpf_program__title(prog, false), insn_idx, - insn->imm, orig_val, new_val); + if (validate && insn->imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->imm, orig_val, new_val); return -EINVAL; } orig_val = insn->imm; insn->imm = new_val; - pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", - bpf_program__title(prog, false), insn_idx, - failed ? " w/ failed reloc" : "", orig_val, new_val); - } else { - pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", - bpf_program__title(prog, false), + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + case BPF_LDX: + case BPF_ST: + case BPF_STX: + if (validate && insn->off != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LD/LDX/ST/STX) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->off, orig_val, new_val); + return -EINVAL; + } + if (new_val > SHRT_MAX) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, new_val); + return -ERANGE; + } + orig_val = insn->off; + insn->off = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + default: + pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), relo_idx, insn_idx, insn->code, insn->src_reg, insn->dst_reg, insn->off, insn->imm); return -EINVAL; @@ -3167,92 +4331,6 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, return 0; } -static struct btf *btf_load_raw(const char *path) -{ - struct btf *btf; - size_t read_cnt; - struct stat st; - void *data; - FILE *f; - - if (stat(path, &st)) - return ERR_PTR(-errno); - - data = malloc(st.st_size); - if (!data) - return ERR_PTR(-ENOMEM); - - f = fopen(path, "rb"); - if (!f) { - btf = ERR_PTR(-errno); - goto cleanup; - } - - read_cnt = fread(data, 1, st.st_size, f); - fclose(f); - if (read_cnt < st.st_size) { - btf = ERR_PTR(-EBADF); - goto cleanup; - } - - btf = btf__new(data, read_cnt); - -cleanup: - free(data); - return btf; -} - -/* - * Probe few well-known locations for vmlinux kernel image and try to load BTF - * data out of it to use for target BTF. - */ -static struct btf *bpf_core_find_kernel_btf(void) -{ - struct { - const char *path_fmt; - bool raw_btf; - } locations[] = { - /* try canonical vmlinux BTF through sysfs first */ - { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, - /* fall back to trying to find vmlinux ELF on disk otherwise */ - { "/boot/vmlinux-%1$s" }, - { "/lib/modules/%1$s/vmlinux-%1$s" }, - { "/lib/modules/%1$s/build/vmlinux" }, - { "/usr/lib/modules/%1$s/kernel/vmlinux" }, - { "/usr/lib/debug/boot/vmlinux-%1$s" }, - { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, - { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, - }; - char path[PATH_MAX + 1]; - struct utsname buf; - struct btf *btf; - int i; - - uname(&buf); - - for (i = 0; i < ARRAY_SIZE(locations); i++) { - snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); - - if (access(path, R_OK)) - continue; - - if (locations[i].raw_btf) - btf = btf_load_raw(path); - else - btf = btf__parse_elf(path, NULL); - - pr_debug("loading kernel BTF '%s': %ld\n", - path, IS_ERR(btf) ? PTR_ERR(btf) : 0); - if (IS_ERR(btf)) - continue; - - return btf; - } - - pr_warn("failed to find valid kernel BTF\n"); - return ERR_PTR(-ESRCH); -} - /* Output spec definition in the format: * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b @@ -3443,24 +4521,33 @@ static int bpf_core_reloc_field(struct bpf_program *prog, } /* - * For BPF_FIELD_EXISTS relo or when relaxed CO-RE reloc mode is - * requested, it's expected that we might not find any candidates. - * In this case, if field wasn't found in any candidate, the list of - * candidates shouldn't change at all, we'll just handle relocating - * appropriately, depending on relo's kind. + * For BPF_FIELD_EXISTS relo or when used BPF program has field + * existence checks or kernel version/config checks, it's expected + * that we might not find any candidates. In this case, if field + * wasn't found in any candidate, the list of candidates shouldn't + * change at all, we'll just handle relocating appropriately, + * depending on relo's kind. */ if (j > 0) cand_ids->len = j; - if (j == 0 && !prog->obj->relaxed_core_relocs && - relo->kind != BPF_FIELD_EXISTS) { - pr_warn("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", - prog_name, relo_idx, local_id, local_name, spec_str); - return -ESRCH; - } + /* + * If no candidates were found, it might be both a programmer error, + * as well as expected case, depending whether instruction w/ + * relocation is guarded in some way that makes it unreachable (dead + * code) if relocation can't be resolved. This is handled in + * bpf_core_reloc_insn() uniformly by replacing that instruction with + * BPF helper call insn (using invalid helper ID). If that instruction + * is indeed unreachable, then it will be ignored and eliminated by + * verifier. If it was an error, then verifier will complain and point + * to a specific instruction number in its log. + */ + if (j == 0) + pr_debug("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); /* bpf_core_reloc_insn should know how to handle missing targ_spec */ - err = bpf_core_reloc_insn(prog, relo, &local_spec, + err = bpf_core_reloc_insn(prog, relo, relo_idx, &local_spec, j ? &targ_spec : NULL); if (err) { pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", @@ -3487,7 +4574,7 @@ 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 = bpf_core_find_kernel_btf(); + targ_btf = libbpf_find_kernel_btf(); if (IS_ERR(targ_btf)) { pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); return PTR_ERR(targ_btf); @@ -3559,16 +4646,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, size_t new_cnt; int err; - if (relo->type != RELO_CALL) - return -LIBBPF_ERRNO__RELOC; - - if (prog->idx == obj->efile.text_shndx) { - pr_warn("relo in .text insn %d into off %d (insn #%d)\n", - relo->insn_idx, relo->sym_off, relo->sym_off / 8); - return -LIBBPF_ERRNO__RELOC; - } - - if (prog->main_prog_cnt == 0) { + if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) { text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); if (!text) { pr_warn("no .text section found yet relo into text exist\n"); @@ -3598,6 +4676,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, text->insns_cnt, text->section_name, prog->section_name); } + insn = &prog->insns[relo->insn_idx]; insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx; return 0; @@ -3623,27 +4702,37 @@ 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]; - if (relo->type == RELO_LD64 || relo->type == RELO_DATA) { - struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - - if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { - pr_warn("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; - } + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } - if (relo->type != RELO_DATA) { - insn[0].src_reg = BPF_PSEUDO_MAP_FD; - } else { - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[1].imm = insn[0].imm + relo->sym_off; - } + switch (relo->type) { + case RELO_LD64: + insn[0].src_reg = BPF_PSEUDO_MAP_FD; insn[0].imm = obj->maps[relo->map_idx].fd; - } else if (relo->type == RELO_CALL) { + break; + case RELO_DATA: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; + 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; + break; + case RELO_CALL: err = bpf_program__reloc_text(prog, obj, relo); if (err) return err; + break; + default: + pr_warn("relo #%d: bad relo type %d\n", i, relo->type); + return -EINVAL; } } @@ -3667,8 +4756,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } + /* ensure .text is relocated first, as it's going to be copied as-is + * later for sub-program calls + */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog->idx != obj->efile.text_shndx) + continue; + + err = bpf_program__relocate(prog, obj); + if (err) { + pr_warn("failed to relocate '%s'\n", prog->section_name); + return err; + } + break; + } + /* now relocate everything but .text, which by now is relocated + * properly, so we can copy raw sub-program instructions as is safely + */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; + if (prog->idx == obj->efile.text_shndx) + continue; err = bpf_program__relocate(prog, obj); if (err) { @@ -3679,6 +4788,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return 0; } +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data); + static int bpf_object__collect_reloc(struct bpf_object *obj) { int i, err; @@ -3699,6 +4812,15 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return -LIBBPF_ERRNO__INTERNAL; } + if (idx == obj->efile.st_ops_shndx) { + err = bpf_object__collect_struct_ops_map_reloc(obj, + shdr, + data); + if (err) + return err; + continue; + } + prog = bpf_object__find_prog_by_idx(obj, idx); if (!prog) { pr_warn("relocation failed: no section(%d)\n", idx); @@ -3733,7 +4855,10 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; - if (prog->type == BPF_PROG_TYPE_TRACING) { + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + load_attr.attach_btf_id = prog->attach_btf_id; + } else if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { load_attr.attach_prog_fd = prog->attach_prog_fd; load_attr.attach_btf_id = prog->attach_btf_id; } else { @@ -3778,6 +4903,7 @@ retry_load: ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("load bpf program failed: %s\n", cp); + pr_perm_msg(ret); if (log_buf && log_buf[0] != '\0') { ret = -LIBBPF_ERRNO__VERIFY; @@ -3807,11 +4933,19 @@ out: return ret; } -int -bpf_program__load(struct bpf_program *prog, - char *license, __u32 kern_version) +static int libbpf_find_attach_btf_id(struct bpf_program *prog); + +int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { - int err = 0, fd, i; + int err = 0, fd, i, btf_id; + + if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { + btf_id = libbpf_find_attach_btf_id(prog); + if (btf_id <= 0) + return btf_id; + prog->attach_btf_id = btf_id; + } if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { @@ -3835,7 +4969,7 @@ bpf_program__load(struct bpf_program *prog, prog->section_name, prog->instances.nr); } err = load_program(prog, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -3864,9 +4998,7 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, - license, kern_version, &fd); - + result.new_insn_cnt, license, kern_ver, &fd); if (err) { pr_warn("Loading the %dth instance of program '%s' failed\n", i, prog->section_name); @@ -3910,20 +5042,14 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } -static int libbpf_find_attach_btf_id(const char *name, - enum bpf_attach_type attach_type, - __u32 attach_prog_fd); static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { - const char *pin_root_path; + const char *obj_name, *kconfig; struct bpf_program *prog; struct bpf_object *obj; - const char *obj_name; char tmp_name[64]; - bool relaxed_maps; - __u32 attach_prog_fd; int err; if (elf_version(EV_CURRENT) == EV_NONE) { @@ -3951,23 +5077,32 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, if (IS_ERR(obj)) return obj; - obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); - relaxed_maps = OPTS_GET(opts, relaxed_maps, false); - pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - - CHECK_ERR(bpf_object__elf_init(obj), err, out); - CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__probe_caps(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), - err, out); - CHECK_ERR(bpf_object__collect_reloc(obj), err, out); + kconfig = OPTS_GET(opts, kconfig, NULL); + if (kconfig) { + obj->kconfig = strdup(kconfig); + if (!obj->kconfig) + return ERR_PTR(-ENOMEM); + } + + err = bpf_object__elf_init(obj); + err = err ? : bpf_object__check_endianness(obj); + err = err ? : bpf_object__elf_collect(obj); + err = err ? : bpf_object__collect_externs(obj); + err = err ? : bpf_object__finalize_btf(obj); + err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object__init_prog_names(obj); + err = err ? : bpf_object__collect_reloc(obj); + if (err) + goto out; bpf_object__elf_finish(obj); bpf_object__for_each_program(prog, obj) { enum bpf_prog_type prog_type; enum bpf_attach_type attach_type; + if (prog->type != BPF_PROG_TYPE_UNSPEC) + continue; + err = libbpf_prog_type_by_name(prog->section_name, &prog_type, &attach_type); if (err == -ESRCH) @@ -3978,15 +5113,9 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_program__set_type(prog, prog_type); bpf_program__set_expected_attach_type(prog, attach_type); - if (prog_type == BPF_PROG_TYPE_TRACING) { - err = libbpf_find_attach_btf_id(prog->section_name, - attach_type, - attach_prog_fd); - if (err <= 0) - goto out; - prog->attach_btf_id = err; - prog->attach_prog_fd = attach_prog_fd; - } + if (prog_type == BPF_PROG_TYPE_TRACING || + prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); } return obj; @@ -4026,7 +5155,7 @@ struct bpf_object *bpf_object__open(const char *path) } struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) { if (!path) return ERR_PTR(-EINVAL); @@ -4038,7 +5167,7 @@ bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { if (!obj_buf || obj_buf_sz == 0) return ERR_PTR(-EINVAL); @@ -4070,8 +5199,11 @@ int bpf_object__unload(struct bpf_object *obj) if (!obj) return -EINVAL; - for (i = 0; i < obj->nr_maps; i++) + for (i = 0; i < obj->nr_maps; i++) { zclose(obj->maps[i].fd); + if (obj->maps[i].st_ops) + zfree(&obj->maps[i].st_ops->kern_vdata); + } for (i = 0; i < obj->nr_programs; i++) bpf_program__unload(&obj->programs[i]); @@ -4079,6 +5211,92 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } +static int bpf_object__sanitize_maps(struct bpf_object *obj) +{ + struct bpf_map *m; + + bpf_object__for_each_map(m, obj) { + if (!bpf_map__is_internal(m)) + continue; + if (!obj->caps.global_data) { + pr_warn("kernel doesn't support global data\n"); + return -ENOTSUP; + } + if (!obj->caps.array_mmap) + m->def.map_flags ^= BPF_F_MMAPABLE; + } + + return 0; +} + +static int bpf_object__resolve_externs(struct bpf_object *obj, + const char *extra_kconfig) +{ + bool need_config = false; + struct extern_desc *ext; + int err, i; + void *data; + + if (obj->nr_extern == 0) + return 0; + + 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; + __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); + if (err) + return err; + pr_debug("extern %s=0x%x\n", ext->name, kver); + } else if (strncmp(ext->name, "CONFIG_", 7) == 0) { + need_config = 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); + if (err) + return -EINVAL; + need_config = false; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (!ext->is_set) { + need_config = true; + break; + } + } + } + if (need_config) { + err = bpf_object__read_kconfig_file(obj, data); + if (err) + return -EINVAL; + } + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (!ext->is_set && !ext->is_weak) { + pr_warn("extern %s (strong) not resolved\n", ext->name); + return -ESRCH; + } else if (!ext->is_set) { + pr_debug("extern %s (weak) not resolved, defaulting to zero\n", + ext->name); + } + } + + return 0; +} + int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { struct bpf_object *obj; @@ -4097,9 +5315,21 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; - CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); - CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); + err = bpf_object__probe_caps(obj); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object__relocate(obj, attr->target_btf_path); + err = err ? : bpf_object__load_progs(obj, attr->log_level); + + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; + + if (err) + goto out; return 0; out: @@ -4670,17 +5900,33 @@ void bpf_object__close(struct bpf_object *obj) btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) { - zfree(&obj->maps[i].name); - zfree(&obj->maps[i].pin_path); - if (obj->maps[i].clear_priv) - obj->maps[i].clear_priv(&obj->maps[i], - obj->maps[i].priv); - obj->maps[i].priv = NULL; - obj->maps[i].clear_priv = NULL; + struct bpf_map *map = &obj->maps[i]; + + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->mmaped) { + munmap(map->mmaped, bpf_map_mmap_sz(map)); + map->mmaped = NULL; + } + + if (map->st_ops) { + zfree(&map->st_ops->data); + zfree(&map->st_ops->progs); + zfree(&map->st_ops->kern_func_off); + zfree(&map->st_ops); + } + + zfree(&map->name); + zfree(&map->pin_path); } - zfree(&obj->sections.rodata); - zfree(&obj->sections.data); + zfree(&obj->kconfig); + zfree(&obj->externs); + obj->nr_extern = 0; + zfree(&obj->maps); obj->nr_maps = 0; @@ -4820,6 +6066,11 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } +const char *bpf_program__name(const struct bpf_program *prog) +{ + return prog->name; +} + const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -4936,6 +6187,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); 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); enum bpf_attach_type bpf_program__get_expected_attach_type(struct bpf_program *prog) @@ -4972,7 +6225,28 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, */ #define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) -static const struct { +#define SEC_DEF(sec_pfx, ptype, ...) { \ + .sec = sec_pfx, \ + .len = sizeof(sec_pfx) - 1, \ + .prog_type = BPF_PROG_TYPE_##ptype, \ + __VA_ARGS__ \ +} + +struct bpf_sec_def; + +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +struct bpf_sec_def { const char *sec; size_t len; enum bpf_prog_type prog_type; @@ -4980,24 +6254,43 @@ static const struct { bool is_attachable; bool is_attach_btf; enum bpf_attach_type attach_type; -} section_names[] = { + attach_fn_t attach_fn; +}; + +static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), + SEC_DEF("kprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + SEC_DEF("kretprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_RAW_TP), - BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FENTRY), - BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FEXIT), + SEC_DEF("tracepoint/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("tp/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fentry/", TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fexit/", TRACING, + .expected_attach_type = BPF_TRACE_FEXIT, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("freplace/", EXT, + .is_attach_btf = true, + .attach_fn = attach_trace), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -5052,6 +6345,7 @@ static const struct { BPF_CGROUP_GETSOCKOPT), BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT), + BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), }; #undef BPF_PROG_SEC_IMPL @@ -5059,12 +6353,26 @@ static const struct { #undef BPF_APROG_SEC #undef BPF_EAPROG_SEC #undef BPF_APROG_COMPAT +#undef SEC_DEF #define MAX_TYPE_NAME_SIZE 32 +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + int i, n = ARRAY_SIZE(section_defs); + + for (i = 0; i < n; i++) { + if (strncmp(sec_name, + section_defs[i].sec, section_defs[i].len)) + continue; + return §ion_defs[i]; + } + return NULL; +} + static char *libbpf_get_type_names(bool attach_type) { - int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE; + int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; char *buf; buf = malloc(len); @@ -5073,16 +6381,16 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (attach_type && !section_names[i].is_attachable) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (attach_type && !section_defs[i].is_attachable) continue; - if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) { + if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); return NULL; } strcat(buf, " "); - strcat(buf, section_names[i].sec); + strcat(buf, section_defs[i].sec); } return buf; @@ -5091,57 +6399,205 @@ static char *libbpf_get_type_names(bool attach_type) int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type) { + const struct bpf_sec_def *sec_def; char *type_names; - int i; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) - continue; - *prog_type = section_names[i].prog_type; - *expected_attach_type = section_names[i].expected_attach_type; + sec_def = find_sec_def(name); + if (sec_def) { + *prog_type = sec_def->prog_type; + *expected_attach_type = sec_def->expected_attach_type; return 0; } - pr_warn("failed to guess program type from ELF section '%s'\n", name); + + pr_debug("failed to guess program type from ELF section '%s'\n", name); type_names = libbpf_get_type_names(false); if (type_names != NULL) { - pr_info("supported section(type) names are:%s\n", type_names); + pr_debug("supported section(type) names are:%s\n", type_names); free(type_names); } return -ESRCH; } -#define BTF_PREFIX "btf_trace_" +static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + size_t offset) +{ + struct bpf_map *map; + size_t i; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + if (!bpf_map__is_struct_ops(map)) + continue; + if (map->sec_offset <= offset && + offset - map->sec_offset < map->def.value_size) + return map; + } + + return NULL; +} + +/* Collect the reloc from ELF and populate the st_ops->progs[] */ +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data) +{ + const struct btf_member *member; + struct bpf_struct_ops *st_ops; + struct bpf_program *prog; + unsigned int shdr_idx; + const struct btf *btf; + struct bpf_map *map; + Elf_Data *symbols; + unsigned int moff; + const char *name; + __u32 member_idx; + GElf_Sym sym; + GElf_Rel rel; + int i, nrels; + + symbols = obj->efile.symbols; + btf = obj->btf; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + if (!gelf_getrel(data, i, &rel)) { + pr_warn("struct_ops reloc: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("struct_ops reloc: symbol %zx not found\n", + (size_t)GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + map = find_struct_ops_map_by_offset(obj, rel.r_offset); + if (!map) { + pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n", + (size_t)rel.r_offset); + return -EINVAL; + } + + moff = rel.r_offset - map->sec_offset; + shdr_idx = sym.st_shndx; + st_ops = map->st_ops; + pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n", + map->name, + (long long)(rel.r_info >> 32), + (long long)sym.st_value, + shdr_idx, (size_t)rel.r_offset, + map->sec_offset, sym.st_name, name); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n", + map->name, (size_t)rel.r_offset, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + member = find_member_by_offset(st_ops->type, moff * 8); + if (!member) { + pr_warn("struct_ops reloc %s: cannot find member at moff %u\n", + map->name, moff); + return -EINVAL; + } + member_idx = member - btf_members(st_ops->type); + name = btf__name_by_offset(btf, member->name_off); + + if (!resolve_func_ptr(btf, member->type, NULL)) { + pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n", + map->name, name); + return -EINVAL; + } + + prog = bpf_object__find_prog_by_idx(obj, shdr_idx); + if (!prog) { + pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n", + map->name, shdr_idx, name); + return -EINVAL; + } + + if (prog->type == BPF_PROG_TYPE_UNSPEC) { + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(prog->section_name); + if (sec_def && + sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { + /* for pr_warn */ + prog->type = sec_def->prog_type; + goto invalid_prog; + } + + prog->type = BPF_PROG_TYPE_STRUCT_OPS; + prog->attach_btf_id = st_ops->type_id; + prog->expected_attach_type = member_idx; + } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || + prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + goto invalid_prog; + } + st_ops->progs[member_idx] = prog; + } + + return 0; + +invalid_prog: + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->section_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; +} + +#define BTF_TRACE_PREFIX "btf_trace_" +#define BTF_MAX_NAME_SIZE 128 + +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind) +{ + char btf_type_name[BTF_MAX_NAME_SIZE]; + int ret; + + ret = snprintf(btf_type_name, sizeof(btf_type_name), + "%s%s", prefix, name); + /* snprintf returns the number of characters written excluding the + * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it + * indicates truncation. + */ + if (ret < 0 || ret >= sizeof(btf_type_name)) + return -ENAMETOOLONG; + return btf__find_by_name_kind(btf, btf_type_name, kind); +} + +static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, + enum bpf_attach_type attach_type) +{ + int err; + + if (attach_type == BPF_TRACE_RAW_TP) + err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, + BTF_KIND_TYPEDEF); + else + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + + return err; +} + int libbpf_find_vmlinux_btf_id(const char *name, enum bpf_attach_type attach_type) { - struct btf *btf = bpf_core_find_kernel_btf(); - char raw_tp_btf[128] = BTF_PREFIX; - char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1; - const char *btf_name; - int err = -EINVAL; - __u32 kind; + struct btf *btf; + btf = libbpf_find_kernel_btf(); if (IS_ERR(btf)) { pr_warn("vmlinux BTF is not found\n"); return -EINVAL; } - if (attach_type == BPF_TRACE_RAW_TP) { - /* prepend "btf_trace_" prefix per kernel convention */ - strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX)); - btf_name = raw_tp_btf; - kind = BTF_KIND_TYPEDEF; - } else { - btf_name = name; - kind = BTF_KIND_FUNC; - } - err = btf__find_by_name_kind(btf, btf_name, kind); - btf__free(btf); - return err; + return __find_vmlinux_btf_id(btf, name, attach_type); } static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) @@ -5177,26 +6633,28 @@ out: return err; } -static int libbpf_find_attach_btf_id(const char *name, - enum bpf_attach_type attach_type, - __u32 attach_prog_fd) +static int libbpf_find_attach_btf_id(struct bpf_program *prog) { + enum bpf_attach_type attach_type = prog->expected_attach_type; + __u32 attach_prog_fd = prog->attach_prog_fd; + const char *name = prog->section_name; int i, err; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (!section_names[i].is_attach_btf) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (!section_defs[i].is_attach_btf) continue; - if (strncmp(name, section_names[i].sec, section_names[i].len)) + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; if (attach_prog_fd) - err = libbpf_find_prog_btf_id(name + section_names[i].len, + err = libbpf_find_prog_btf_id(name + section_defs[i].len, attach_prog_fd); else - err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, - attach_type); + err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, + name + section_defs[i].len, + attach_type); if (err <= 0) pr_warn("%s is not found in vmlinux BTF\n", name); return err; @@ -5214,18 +6672,18 @@ int libbpf_attach_type_by_name(const char *name, if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; - if (!section_names[i].is_attachable) + if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_names[i].attach_type; + *attach_type = section_defs[i].attach_type; return 0; } - pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); type_names = libbpf_get_type_names(true); if (type_names != NULL) { - pr_info("attachable section(type) names are:%s\n", type_names); + pr_debug("attachable section(type) names are:%s\n", type_names); free(type_names); } @@ -5466,17 +6924,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } struct bpf_link { + int (*detach)(struct bpf_link *link); int (*destroy)(struct bpf_link *link); + bool disconnected; }; +/* Release "ownership" of underlying BPF resource (typically, BPF program + * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected + * link, when destructed through bpf_link__destroy() call won't attempt to + * detach/unregisted that BPF resource. This is useful in situations where, + * say, attached BPF program has to outlive userspace program that attached it + * in the system. Depending on type of BPF program, though, there might be + * additional steps (like pinning BPF program in BPF FS) necessary to ensure + * exit of userspace program doesn't trigger automatic detachment and clean up + * inside the kernel. + */ +void bpf_link__disconnect(struct bpf_link *link) +{ + link->disconnected = true; +} + int bpf_link__destroy(struct bpf_link *link) { - int err; + int err = 0; if (!link) return 0; - err = link->destroy(link); + if (!link->disconnected && link->detach) + err = link->detach(link); + if (link->destroy) + link->destroy(link); free(link); return err; @@ -5487,7 +6965,7 @@ struct bpf_link_fd { int fd; /* hook FD */ }; -static int bpf_link__destroy_perf_event(struct bpf_link *link) +static int bpf_link__detach_perf_event(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; int err; @@ -5519,10 +6997,10 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_perf_event; + link->link.detach = &bpf_link__detach_perf_event; link->fd = pfd; if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { @@ -5679,6 +7157,18 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return link; } +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *func_name; + bool retprobe; + + func_name = bpf_program__title(prog, false) + sec->len; + retprobe = strcmp(sec->sec, "kretprobe/") == 0; + + return bpf_program__attach_kprobe(prog, retprobe, func_name); +} + struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, @@ -5791,7 +7281,33 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, return link; } -static int bpf_link__destroy_fd(struct bpf_link *link) +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + char *sec_name, *tp_cat, *tp_name; + struct bpf_link *link; + + sec_name = strdup(bpf_program__title(prog, false)); + if (!sec_name) + return ERR_PTR(-ENOMEM); + + /* extract "tp/<category>/<name>" */ + tp_cat = sec_name + sec->len; + tp_name = strchr(tp_cat, '/'); + if (!tp_name) { + link = ERR_PTR(-EINVAL); + goto out; + } + *tp_name = '\0'; + tp_name++; + + link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); +out: + free(sec_name); + return link; +} + +static int bpf_link__detach_fd(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; @@ -5812,10 +7328,10 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); if (pfd < 0) { @@ -5830,6 +7346,14 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return (struct bpf_link *)link; } +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *tp_name = bpf_program__title(prog, false) + sec->len; + + return bpf_program__attach_raw_tracepoint(prog, tp_name); +} + struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; @@ -5843,10 +7367,10 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(NULL, prog_fd); if (pfd < 0) { @@ -5861,6 +7385,75 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return (struct bpf_link *)link; } +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_trace(prog); +} + +struct bpf_link *bpf_program__attach(struct bpf_program *prog) +{ + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(bpf_program__title(prog, false)); + if (!sec_def || !sec_def->attach_fn) + return ERR_PTR(-ESRCH); + + return sec_def->attach_fn(sec_def, prog); +} + +static int bpf_link__detach_struct_ops(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + __u32 zero = 0; + + if (bpf_map_delete_elem(l->fd, &zero)) + return -errno; + + return 0; +} + +struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +{ + struct bpf_struct_ops *st_ops; + struct bpf_link_fd *link; + __u32 i, zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map) || map->fd == -1) + return ERR_PTR(-EINVAL); + + link = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-EINVAL); + + st_ops = map->st_ops; + for (i = 0; i < btf_vlen(st_ops->type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; + + if (!prog) + continue; + + prog_fd = bpf_program__fd(prog); + kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; + *(unsigned long *)kern_data = prog_fd; + } + + err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0); + if (err) { + err = -errno; + free(link); + return ERR_PTR(err); + } + + link->link.detach = bpf_link__detach_struct_ops; + link->fd = map->fd; + + return (struct bpf_link *)link; +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -5944,7 +7537,7 @@ struct perf_buffer { size_t mmap_size; struct perf_cpu_buf **cpu_bufs; struct epoll_event *events; - int cpu_cnt; + int cpu_cnt; /* number of allocated CPU buffers */ int epoll_fd; /* perf event FD */ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ }; @@ -6078,11 +7671,13 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, 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 = {}; char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; + bool *online = NULL; __u32 map_info_len; - int err, i; + int err, i, j, n; if (page_cnt & (page_cnt - 1)) { pr_warn("page count should be power of two, but is %zu\n", @@ -6151,20 +7746,32 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - for (i = 0; i < pb->cpu_cnt; i++) { + err = parse_cpu_mask_file(online_cpus_file, &online, &n); + if (err) { + pr_warn("failed to get online CPU mask: %d\n", err); + goto error; + } + + for (i = 0, j = 0; i < pb->cpu_cnt; i++) { struct perf_cpu_buf *cpu_buf; int cpu, map_key; cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + /* in case user didn't explicitly requested particular CPUs to + * be attached to, skip offline/not present CPUs + */ + if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu])) + continue; + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); if (IS_ERR(cpu_buf)) { err = PTR_ERR(cpu_buf); goto error; } - pb->cpu_bufs[i] = cpu_buf; + pb->cpu_bufs[j] = cpu_buf; err = bpf_map_update_elem(pb->map_fd, &map_key, &cpu_buf->fd, 0); @@ -6176,21 +7783,25 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - pb->events[i].events = EPOLLIN; - pb->events[i].data.ptr = cpu_buf; + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, - &pb->events[i]) < 0) { + &pb->events[j]) < 0) { err = -errno; pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", cpu, cpu_buf->fd, libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } + j++; } + pb->cpu_cnt = j; + free(online); return pb; error: + free(online); if (pb) perf_buffer__free(pb); return ERR_PTR(err); @@ -6521,62 +8132,267 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } -int libbpf_num_possible_cpus(void) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - int len = 0, n = 0, il = 0, ir = 0; - unsigned int start = 0, end = 0; - int tmp_cpus = 0; - static int cpus; - char buf[128]; - int error = 0; - int fd = -1; + int err = 0, n, len, start, end = -1; + bool *tmp; - tmp_cpus = READ_ONCE(cpus); - if (tmp_cpus > 0) - return tmp_cpus; + *mask = NULL; + *mask_sz = 0; + + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + while (*s) { + if (*s == ',' || *s == '\n') { + s++; + continue; + } + n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len); + if (n <= 0 || n > 2) { + pr_warn("Failed to get CPU range %s: %d\n", s, n); + err = -EINVAL; + goto cleanup; + } else if (n == 1) { + end = start; + } + if (start < 0 || start > end) { + pr_warn("Invalid CPU range [%d,%d] in %s\n", + start, end, s); + err = -EINVAL; + goto cleanup; + } + tmp = realloc(*mask, end + 1); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + *mask = tmp; + memset(tmp + *mask_sz, 0, start - *mask_sz); + memset(tmp + start, 1, end - start + 1); + *mask_sz = end + 1; + s += len; + } + if (!*mask_sz) { + pr_warn("Empty CPU range\n"); + return -EINVAL; + } + return 0; +cleanup: + free(*mask); + *mask = NULL; + return err; +} + +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) +{ + int fd, err = 0, len; + char buf[128]; fd = open(fcpu, O_RDONLY); if (fd < 0) { - error = errno; - pr_warn("Failed to open file %s: %s\n", fcpu, strerror(error)); - return -error; + err = -errno; + pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { - error = len ? errno : EINVAL; - pr_warn("Failed to read # of possible cpus from %s: %s\n", - fcpu, strerror(error)); - return -error; + err = len ? -errno : -EINVAL; + pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; } - if (len == sizeof(buf)) { - pr_warn("File %s size overflow\n", fcpu); - return -EOVERFLOW; + if (len >= sizeof(buf)) { + pr_warn("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; } buf[len] = '\0'; - for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { - /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ - if (buf[ir] == ',' || buf[ir] == '\0') { - buf[ir] = '\0'; - n = sscanf(&buf[il], "%u-%u", &start, &end); - if (n <= 0) { - pr_warn("Failed to get # CPUs from %s\n", - &buf[il]); - return -EINVAL; - } else if (n == 1) { - end = start; - } - tmp_cpus += end - start + 1; - il = ir + 1; - } - } - if (tmp_cpus <= 0) { - pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); - return -EINVAL; + return parse_cpu_mask_str(buf, mask, mask_sz); +} + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + static int cpus; + int err, n, i, tmp_cpus; + bool *mask; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + err = parse_cpu_mask_file(fcpu, &mask, &n); + if (err) + return err; + + tmp_cpus = 0; + for (i = 0; i < n; i++) { + if (mask[i]) + tmp_cpus++; } + free(mask); WRITE_ONCE(cpus, tmp_cpus); return tmp_cpus; } + +int bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, + .object_name = s->name, + ); + struct bpf_object *obj; + int i; + + /* Attempt to preserve opts->object_name, unless overriden by user + * explicitly. Overwriting object name for skeletons is discouraged, + * as it breaks global data maps, because they contain object name + * prefix as their own map name prefix. When skeleton is generated, + * bpftool is making an assumption that this name will stay the same. + */ + if (opts) { + memcpy(&skel_opts, opts, sizeof(*opts)); + if (!opts->object_name) + skel_opts.object_name = s->name; + } + + obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); + if (IS_ERR(obj)) { + pr_warn("failed to initialize skeleton BPF object '%s': %ld\n", + s->name, PTR_ERR(obj)); + return PTR_ERR(obj); + } + + *s->obj = obj; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map **map = s->maps[i].map; + const char *name = s->maps[i].name; + void **mmaped = s->maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program **prog = s->progs[i].prog; + const char *name = s->progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + + return 0; +} + +int bpf_object__load_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + err = bpf_object__load(*s->obj); + if (err) { + pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + return err; + } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + size_t mmap_sz = bpf_map_mmap_sz(map); + int prot, map_fd = bpf_map__fd(map); + void **mmaped = s->maps[i].mmaped; + + if (!mmaped) + continue; + + if (!(map->def.map_flags & BPF_F_MMAPABLE)) { + *mmaped = NULL; + continue; + } + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure, so we don't need to worry + * about it from skeleton's clean up perspective. + */ + *mmaped = mmap(map->mmaped, mmap_sz, prot, + MAP_SHARED | MAP_FIXED, map_fd, 0); + if (*mmaped == MAP_FAILED) { + err = -errno; + *mmaped = NULL; + pr_warn("failed to re-mmap() map '%s': %d\n", + bpf_map__name(map), err); + return err; + } + } + + return 0; +} + +int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program *prog = *s->progs[i].prog; + struct bpf_link **link = s->progs[i].link; + const struct bpf_sec_def *sec_def; + const char *sec_name = bpf_program__title(prog, false); + + sec_def = find_sec_def(sec_name); + if (!sec_def || !sec_def->attach_fn) + continue; + + *link = sec_def->attach_fn(sec_def, prog); + if (IS_ERR(*link)) { + pr_warn("failed to auto-attach program '%s': %ld\n", + bpf_program__name(prog), PTR_ERR(*link)); + return PTR_ERR(*link); + } + } + + return 0; +} + +void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + 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); + *link = NULL; + } +} + +void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) +{ + if (s->progs) + bpf_object__detach_skeleton(s); + if (s->obj) + bpf_object__close(*s->obj); + free(s->maps); + free(s->progs); + free(s); +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0dbf4bfba0c4..3fe12c9d1f92 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -17,14 +17,12 @@ #include <sys/types.h> // for size_t #include <linux/bpf.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -67,28 +65,6 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; -/* Helper macro to declare and initialize libbpf options struct - * - * This dance with uninitialized declaration, followed by memset to zero, - * followed by assignment using compound literal syntax is done to preserve - * ability to use a nice struct field initialization syntax and **hopefully** - * have all the padding bytes initialized to zero. It's not guaranteed though, - * when copying literal, that compiler won't copy garbage in literal's padding - * bytes, but that's the best way I've found and it seems to work in practice. - * - * Macro declares opts struct of given type and name, zero-initializes, - * including any extra padding, it with memset() and then assigns initial - * values provided by users in struct initializer-syntax as varargs. - */ -#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ - struct TYPE NAME = ({ \ - memset(&NAME, 0, sizeof(struct TYPE)); \ - (struct TYPE) { \ - .sz = sizeof(struct TYPE), \ - __VA_ARGS__ \ - }; \ - }) - struct bpf_object_open_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -101,7 +77,11 @@ struct bpf_object_open_opts { const char *object_name; /* parse map definitions non-strictly, allowing extra attributes/data */ bool relaxed_maps; - /* process CO-RE relocations non-strictly, allowing them to fail */ + /* DEPRECATED: handle CO-RE relocations non-strictly, allowing failures. + * Value is ignored. Relocations always are processed non-strictly. + * Non-relocatable instructions are replaced with invalid ones to + * prevent accidental errors. + * */ bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be @@ -109,15 +89,19 @@ struct bpf_object_open_opts { */ const char *pin_root_path; __u32 attach_prog_fd; + /* Additional kernel config content that augments and overrides + * system Kconfig for CONFIG_xxx externs. + */ + const char *kconfig; }; -#define bpf_object_open_opts__last_field attach_prog_fd +#define bpf_object_open_opts__last_field kconfig LIBBPF_API struct bpf_object *bpf_object__open(const char *path); LIBBPF_API struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts); +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts); + const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ LIBBPF_API struct bpf_object * @@ -126,11 +110,6 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); -int bpf_object__section_size(const struct bpf_object *obj, const char *name, - __u32 *size); -int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, - __u32 *off); - enum libbpf_pin_type { LIBBPF_PIN_NONE, /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ @@ -161,6 +140,7 @@ struct bpf_object_load_attr { LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); + LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -171,6 +151,9 @@ LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -214,6 +197,7 @@ LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); +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); @@ -235,9 +219,12 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_link; +LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * +bpf_program__attach(struct bpf_program *prog); +LIBBPF_API struct bpf_link * bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, @@ -256,6 +243,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog, LIBBPF_API struct bpf_link * bpf_program__attach_trace(struct bpf_program *prog); +struct bpf_map; +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); struct bpf_insn; /* @@ -332,6 +321,8 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); LIBBPF_API 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 enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, @@ -352,6 +343,8 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); 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); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -371,7 +364,6 @@ struct bpf_map_def { * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, * so no need to worry about a name clash. */ -struct bpf_map; LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -512,18 +504,6 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, bpf_perf_event_print_t fn, void *private_data); -struct nlattr; -typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); -int libbpf_netlink_open(unsigned int *nl_pid); -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); - struct bpf_prog_linfo; struct bpf_prog_info; @@ -550,6 +530,7 @@ LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); /* * Get bpf_prog_info in continuous memory @@ -630,6 +611,50 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); */ LIBBPF_API int libbpf_num_possible_cpus(void); +struct bpf_map_skeleton { + const char *name; + struct bpf_map **map; + void **mmaped; +}; + +struct bpf_prog_skeleton { + const char *name; + struct bpf_program **prog; + struct bpf_link **link; +}; + +struct bpf_object_skeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const char *name; + void *data; + size_t data_sz; + + struct bpf_object **obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + struct bpf_prog_skeleton *progs; +}; + +LIBBPF_API int +bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts); +LIBBPF_API int bpf_object__load_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 8ddc2c40e482..b035122142bb 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -208,3 +208,30 @@ LIBBPF_0.0.6 { btf__find_by_name_kind; libbpf_find_vmlinux_btf_id; } LIBBPF_0.0.5; + +LIBBPF_0.0.7 { + global: + btf_dump__emit_type_decl; + bpf_link__disconnect; + bpf_map__attach_struct_ops; + bpf_map_delete_batch; + bpf_map_lookup_and_delete_batch; + bpf_map_lookup_batch; + bpf_map_update_batch; + bpf_object__find_program_by_name; + bpf_object__attach_skeleton; + bpf_object__destroy_skeleton; + bpf_object__detach_skeleton; + bpf_object__load_skeleton; + bpf_object__open_skeleton; + bpf_probe_large_insn_limit; + bpf_prog_attach_xattr; + bpf_program__attach; + bpf_program__name; + bpf_program__is_extension; + bpf_program__is_struct_ops; + bpf_program__set_extension; + bpf_program__set_struct_ops; + btf__align_of; + libbpf_find_kernel_btf; +} LIBBPF_0.0.6; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template index ac17fcef2108..b45ed534bdfb 100644 --- a/tools/lib/bpf/libbpf.pc.template +++ b/tools/lib/bpf/libbpf.pc.template @@ -8,5 +8,5 @@ Name: libbpf Description: BPF library Version: @VERSION@ Libs: -L${libdir} -lbpf -Requires.private: libelf +Requires.private: libelf zlib Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h new file mode 100644 index 000000000000..a23ae1ac27eb --- /dev/null +++ b/tools/lib/bpf/libbpf_common.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common user-facing libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_COMMON_H +#define __LIBBPF_LIBBPF_COMMON_H + +#include <string.h> + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * followed by assignment using compound literal syntax is done to preserve + * ability to use a nice struct field initialization syntax and **hopefully** + * have all the padding bytes initialized to zero. It's not guaranteed though, + * when copying literal, that compiler won't copy garbage in literal's padding + * bytes, but that's the best way I've found and it seems to work in practice. + * + * Macro declares opts struct of given type and name, zero-initializes, + * including any extra padding, it with memset() and then assigns initial + * values provided by users in struct initializer-syntax as varargs. + */ +#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ + struct TYPE NAME = ({ \ + memset(&NAME, 0, sizeof(struct TYPE)); \ + (struct TYPE) { \ + .sz = sizeof(struct TYPE), \ + __VA_ARGS__ \ + }; \ + }) + +#endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index 4343e40588c6..0afb51f7a919 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -13,6 +13,9 @@ #include "libbpf.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) #define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 97ac17a64a58..8c3afbd97747 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -76,7 +76,7 @@ static inline bool libbpf_validate_opts(const char *opts, for (i = opts_sz; i < user_sz; i++) { if (opts[i]) { - pr_warn("%s has non-zero extra bytes", + pr_warn("%s has non-zero extra bytes\n", type_name); return false; } @@ -95,9 +95,28 @@ static inline bool libbpf_validate_opts(const char *opts, #define OPTS_GET(opts, field, fallback_value) \ (OPTS_HAS(opts, field) ? (opts)->field : fallback_value) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + struct btf_ext_info { /* * info points to the individual info section (e.g. func_info and diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index a9eb8b322671..b782ebef6ac9 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -17,6 +17,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static bool grep(const char *buffer, const char *pattern) { return !!strstr(buffer, pattern); @@ -103,6 +106,8 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_EXT: default: break; } @@ -251,6 +256,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_XSKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + case BPF_MAP_TYPE_STRUCT_OPS: default: break; } @@ -321,3 +327,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, return res; } + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +bool bpf_probe_large_insn_limit(__u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + errno = 0; + probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, + ifindex); + + return errno != E2BIG && errno != EINVAL; +} diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 5065c1aa1061..431bd25c6cdb 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -15,6 +15,9 @@ #include "libbpf_internal.h" #include "nlattr.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_NETLINK #define SOL_NETLINK 270 #endif diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 8db44bbfc66d..0ad41dfea8eb 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -13,6 +13,9 @@ #include <string.h> #include <stdio.h> +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { [LIBBPF_NLA_U8] = sizeof(uint8_t), [LIBBPF_NLA_U16] = sizeof(uint16_t), diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c index b8064eedc177..146da01979c7 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -4,6 +4,9 @@ #include <stdio.h> #include "str_error.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl * libc, while checking strerror_r() return to avoid having to check this in diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 8e0ffa800a71..9807903f121e 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -32,6 +32,9 @@ #include "libbpf_internal.h" #include "xsk.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_XDP #define SOL_XDP 283 #endif diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c index e6b6181c6dc6..65c4ff6892d9 100644 --- a/tools/perf/examples/bpf/5sec.c +++ b/tools/perf/examples/bpf/5sec.c @@ -39,7 +39,7 @@ Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include <bpf.h> +#include <bpf/bpf.h> #define NSEC_PER_SEC 1000000000L diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c index 3776d26db9e7..7d7fb0c9fe76 100644 --- a/tools/perf/examples/bpf/empty.c +++ b/tools/perf/examples/bpf/empty.c @@ -1,3 +1,3 @@ -#include <bpf.h> +#include <bpf/bpf.h> license(GPL); diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c index 9cd124b09392..c4481c390d23 100644 --- a/tools/perf/examples/bpf/sys_enter_openat.c +++ b/tools/perf/examples/bpf/sys_enter_openat.c @@ -14,7 +14,7 @@ * the return value. */ -#include <bpf.h> +#include <bpf/bpf.h> struct syscall_enter_openat_args { unsigned long long unused; diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h index 6e61c4bdf548..607189a315b2 100644 --- a/tools/perf/include/bpf/pid_filter.h +++ b/tools/perf/include/bpf/pid_filter.h @@ -3,7 +3,7 @@ #ifndef _PERF_BPF_PID_FILTER_ #define _PERF_BPF_PID_FILTER_ -#include <bpf.h> +#include <bpf/bpf.h> #define pid_filter(name) pid_map(name, bool) diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h index 316af5b2ff35..7ca6fa5463ee 100644 --- a/tools/perf/include/bpf/stdio.h +++ b/tools/perf/include/bpf/stdio.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include <bpf.h> +#include <bpf/bpf.h> struct bpf_map SEC("maps") __bpf_stdout__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h index ca7877f9a976..d1a35b6c649d 100644 --- a/tools/perf/include/bpf/unistd.h +++ b/tools/perf/include/bpf/unistd.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 -#include <bpf.h> +#include <bpf/bpf.h> static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c4939a2a5f5d..35027b129650 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -32,6 +32,7 @@ TARGETS += memory-hotplug TARGETS += mount TARGETS += mqueue TARGETS += net +TARGETS += net/mptcp TARGETS += netfilter TARGETS += networking/timestamping TARGETS += nsfs diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1ff0a9f49c01..ec464859c6b6 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -21,23 +21,20 @@ test_lirc_mode2_user get_cgroup_id_user test_skb_cgroup_id_user test_socket_cookie -test_cgroup_attach test_cgroup_storage -test_select_reuseport test_flow_dissector flow_dissector_load test_netcnt -test_section_names test_tcpnotify_user test_libbpf test_tcp_check_syncookie_user test_sysctl -libbpf.pc -libbpf.so.* test_hashmap test_btf_dump xdping test_cpp +*.skel.h /no_alu32 /bpf_gcc -bpf_helper_defs.h +/tools + diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e2fd6f8d579c..257a1aaaa37d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -3,10 +3,12 @@ include ../../../../scripts/Kbuild.include include ../../../scripts/Makefile.arch CURDIR := $(abspath .) -LIBDIR := $(abspath ../../../lib) +TOOLSDIR := $(abspath ../../..) +LIBDIR := $(TOOLSDIR)/lib BPFDIR := $(LIBDIR)/bpf -TOOLSDIR := $(abspath ../../../include) -APIDIR := $(TOOLSDIR)/uapi +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +APIDIR := $(TOOLSINCDIR)/uapi GENDIR := $(abspath ../../../../include/generated) GENHDR := $(GENDIR)/autoconf.h @@ -18,19 +20,19 @@ CLANG ?= clang LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) -CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) \ - -I$(GENDIR) -I$(TOOLSDIR) -I$(CURDIR) \ +CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \ + -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program -LDLIBS += -lcap -lelf -lrt -lpthread +LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ - test_cgroup_storage test_select_reuseport \ + test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_cgroup_attach test_progs-no_alu32 + test_progs-no_alu32 # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) @@ -71,12 +73,39 @@ TEST_PROGS_EXTENDED := with_addr.sh \ # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ - test_lirc_mode2_user xdping test_cpp + test_lirc_mode2_user xdping test_cpp runqslower TEST_CUSTOM_PROGS = urandom_read +# Emit succinct information message describing current building step +# $1 - generic step name (e.g., CC, LINK, etc); +# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor]; +# $3 - target (assumed to be file); only file name will be emitted; +# $4 - optional extra arg, emitted as-is, if provided. +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +override define CLEAN + $(call msg,CLEAN) + $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) +endef + include ../lib.mk +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +INCLUDE_DIR := $(SCRATCH_DIR)/include +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + # Define simple and short `make test_progs`, `make test_sysctl`, etc targets # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static @@ -87,13 +116,26 @@ $(notdir $(TEST_GEN_PROGS) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; +$(OUTPUT)/%:%.c + $(call msg,BINARY,,$@) + $(LINK.c) $^ $(LDLIBS) -o $@ + $(OUTPUT)/urandom_read: urandom_read.c - $(CC) -o $@ $< -Wl,--build-id + $(call msg,BINARY,,$@) + $(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id -$(OUTPUT)/test_stub.o: test_stub.c +$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) + $(call msg,CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< -BPFOBJ := $(OUTPUT)/libbpf.a +VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS))) +$(OUTPUT)/runqslower: $(BPFOBJ) + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ + OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ) @@ -110,19 +152,24 @@ $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c $(OUTPUT)/test_sysctl: cgroup_helpers.c -$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c - -.PHONY: force -# force a rebuild of BPFOBJ when its dependencies are updated -force: +DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ + $(BPFOBJ) | $(BUILD_DIR)/bpftool + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ + OUTPUT=$(BUILD_DIR)/bpftool/ \ + prefix= DESTDIR=$(SCRATCH_DIR)/ install -$(BPFOBJ): force - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + ../../../include/uapi/linux/bpf.h \ + | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf + $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers -BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) -$(OUTPUT)/bpf_helper_defs.h: - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h +$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): + $(call msg,MKDIR,,$@) + mkdir -p $@ # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, @@ -142,8 +189,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ - -I. -I./include/uapi -I$(APIDIR) \ - -I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include) + -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \ + -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include) CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types @@ -159,27 +206,33 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h # $3 - CFLAGS # $4 - LDFLAGS define CLANG_BPF_BUILD_RULE + $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE + $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC define CLANG_NATIVE_BPF_BUILD_RULE + $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE + $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef +SKEL_BLACKLIST := btf__% test_pinning_invalid.c + # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. # Parameters: @@ -195,8 +248,11 @@ TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ $$(filter %.c,$(TRUNNER_EXTRA_SOURCES))) TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES)) TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h -TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ - $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))) +TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c)) +TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)) +TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ + $$(filter-out $(SKEL_BLACKLIST), \ + $$(TRUNNER_BPF_SRCS))) # Evaluate rules now with extra TRUNNER_XXX variables above already defined $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2)) @@ -212,6 +268,7 @@ define DEFINE_TEST_RUNNER_RULES ifeq ($($(TRUNNER_OUTPUT)-dir),) $(TRUNNER_OUTPUT)-dir := y $(TRUNNER_OUTPUT): + $$(call msg,MKDIR,,$$@) mkdir -p $$@ endif @@ -222,16 +279,23 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ - $$(BPF_HELPERS) | $(TRUNNER_OUTPUT) + $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS), \ $(TRUNNER_BPF_LDFLAGS)) + +$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \ + $(TRUNNER_OUTPUT)/%.o \ + | $(BPFTOOL) $(TRUNNER_OUTPUT) + $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) + $$(BPFTOOL) gen skeleton $$< > $$@ endif # ensure we set up tests.h header generation rule just once ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),) $(TRUNNER_TESTS_DIR)-tests-hdr := y $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c + $$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@) $$(shell ( cd $(TRUNNER_TESTS_DIR); \ echo '/* Generated header, do not edit */'; \ ls *.c 2> /dev/null | \ @@ -245,7 +309,9 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_TESTS_DIR)/%.c \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_OBJS) \ + $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ @@ -253,17 +319,20 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_TESTS_HDR) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@) $$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ +# only copy extra resources if in flavored build $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT) ifneq ($2,) - # only copy extra resources if in flavored build + $$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES)) cp -a $$^ $(TRUNNER_OUTPUT)/ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ | $(TRUNNER_BINARY)-extras + $$(call msg,BINARY,,$$@) $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ endef @@ -276,7 +345,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(wildcard progs/btf_dump_test_case_*.c) TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE -TRUNNER_BPF_CFLAGS := -I. -I$(OUTPUT) $(BPF_CFLAGS) $(CLANG_CFLAGS) +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) TRUNNER_BPF_LDFLAGS := -mattr=+alu32 $(eval $(call DEFINE_TEST_RUNNER,test_progs)) @@ -315,12 +384,15 @@ verifier/tests.h: verifier/*.c echo '#endif' \ ) > verifier/tests.h) $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) + $(call msg,BINARY,,$@) $(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. -$(OUTPUT)/test_cpp: test_cpp.cpp $(BPFOBJ) +$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) + $(call msg,CXX,,$@) $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \ +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc + feature \ + $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc) diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h new file mode 100644 index 000000000000..8f21965ffc6c --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_TCP_HELPERS_H +#define __BPF_TCP_HELPERS_H + +#include <stdbool.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_trace_helpers.h" + +#define BPF_STRUCT_OPS(name, args...) \ +SEC("struct_ops/"#name) \ +BPF_PROG(name, args) + +#define tcp_jiffies32 ((__u32)bpf_jiffies64()) + +struct sock_common { + unsigned char skc_state; +} __attribute__((preserve_access_index)); + +enum sk_pacing { + SK_PACING_NONE = 0, + SK_PACING_NEEDED = 1, + SK_PACING_FQ = 2, +}; + +struct sock { + struct sock_common __sk_common; + unsigned long sk_pacing_rate; + __u32 sk_pacing_status; /* see enum sk_pacing */ +} __attribute__((preserve_access_index)); + +struct inet_sock { + struct sock sk; +} __attribute__((preserve_access_index)); + +struct inet_connection_sock { + struct inet_sock icsk_inet; + __u8 icsk_ca_state:6, + icsk_ca_setsockopt:1, + icsk_ca_dst_locked:1; + struct { + __u8 pending; + } icsk_ack; + __u64 icsk_ca_priv[104 / sizeof(__u64)]; +} __attribute__((preserve_access_index)); + +struct tcp_sock { + struct inet_connection_sock inet_conn; + + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u8 ecn_flags; + __u32 delivered; + __u32 delivered_ce; + __u32 snd_cwnd; + __u32 snd_cwnd_cnt; + __u32 snd_cwnd_clamp; + __u32 snd_ssthresh; + __u8 syn_data:1, /* SYN includes data */ + syn_fastopen:1, /* SYN includes Fast Open option */ + syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ + syn_fastopen_ch:1, /* Active TFO re-enabling probe */ + syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + save_syn:1, /* Save headers of SYN packet */ + is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ + syn_smc:1; /* SYN includes SMC */ + __u32 max_packets_out; + __u32 lsndtime; + __u32 prior_cwnd; + __u64 tcp_mstamp; /* most recent packet received/sent */ +} __attribute__((preserve_access_index)); + +static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk) +{ + return (struct inet_connection_sock *)sk; +} + +static __always_inline void *inet_csk_ca(const struct sock *sk) +{ + return (void *)inet_csk(sk)->icsk_ca_priv; +} + +static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +static __always_inline bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1-seq2) < 0; +} +#define after(seq2, seq1) before(seq1, seq2) + +#define TCP_ECN_OK 1 +#define TCP_ECN_QUEUE_CWR 2 +#define TCP_ECN_DEMAND_CWR 4 +#define TCP_ECN_SEEN 8 + +enum inet_csk_ack_state_t { + ICSK_ACK_SCHED = 1, + ICSK_ACK_TIMER = 2, + ICSK_ACK_PUSHED = 4, + ICSK_ACK_PUSHED2 = 8, + ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ +}; + +enum tcp_ca_event { + CA_EVENT_TX_START = 0, + CA_EVENT_CWND_RESTART = 1, + CA_EVENT_COMPLETE_CWR = 2, + CA_EVENT_LOSS = 3, + CA_EVENT_ECN_NO_CE = 4, + CA_EVENT_ECN_IS_CE = 5, +}; + +enum tcp_ca_state { + TCP_CA_Open = 0, + TCP_CA_Disorder = 1, + TCP_CA_CWR = 2, + TCP_CA_Recovery = 3, + TCP_CA_Loss = 4 +}; + +struct ack_sample { + __u32 pkts_acked; + __s32 rtt_us; + __u32 in_flight; +} __attribute__((preserve_access_index)); + +struct rate_sample { + __u64 prior_mstamp; /* starting timestamp for interval */ + __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + __s32 delivered; /* number of packets delivered over interval */ + long interval_us; /* time for tp->delivered to incr "delivered" */ + __u32 snd_interval_us; /* snd interval for delivered packets */ + __u32 rcv_interval_us; /* rcv interval for delivered packets */ + long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ + int losses; /* number of packets marked lost upon ACK */ + __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ + __u32 prior_in_flight; /* in flight before this ACK */ + bool is_app_limited; /* is sample from packet with bubble in pipe? */ + bool is_retrans; /* is sample from retransmission? */ + bool is_ack_delayed; /* is this (likely) a delayed ACK? */ +} __attribute__((preserve_access_index)); + +#define TCP_CA_NAME_MAX 16 +#define TCP_CONG_NEEDS_ECN 0x2 + +struct tcp_congestion_ops { + char name[TCP_CA_NAME_MAX]; + __u32 flags; + + /* initialize private data (optional) */ + void (*init)(struct sock *sk); + /* cleanup private data (optional) */ + void (*release)(struct sock *sk); + + /* return slow start threshold (required) */ + __u32 (*ssthresh)(struct sock *sk); + /* do new cwnd calculation (required) */ + void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked); + /* call before changing ca_state (optional) */ + void (*set_state)(struct sock *sk, __u8 new_state); + /* call when cwnd event occurs (optional) */ + void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); + /* call when ack arrives (optional) */ + void (*in_ack_event)(struct sock *sk, __u32 flags); + /* new value of cwnd after loss (required) */ + __u32 (*undo_cwnd)(struct sock *sk); + /* hook for packet ack accounting (optional) */ + void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); + /* override sysctl_tcp_min_tso_segs */ + __u32 (*min_tso_segs)(struct sock *sk); + /* returns the multiplier used in tcp_sndbuf_expand (optional) */ + __u32 (*sndbuf_expand)(struct sock *sk); + /* call when packets are delivered to update cwnd and pacing rate, + * after all the ca_state processing. (optional) + */ + void (*cong_control)(struct sock *sk, const struct rate_sample *rs); +}; + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) + +static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) +{ + __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); + + acked -= cwnd - tp->snd_cwnd; + tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); + + return acked; +} + +static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp) +{ + return tp->snd_cwnd < tp->snd_ssthresh; +} + +static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ + if (tcp_in_slow_start(tp)) + return tp->snd_cwnd < 2 * tp->max_packets_out; + + return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited); +} + +static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) +{ + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd++; + } + + tp->snd_cwnd_cnt += acked; + if (tp->snd_cwnd_cnt >= w) { + __u32 delta = tp->snd_cwnd_cnt / w; + + tp->snd_cwnd_cnt -= delta * w; + tp->snd_cwnd += delta; + } + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp); +} + +#endif diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h index c76a214a53b0..c6f1354d93fb 100644 --- a/tools/testing/selftests/bpf/bpf_trace_helpers.h +++ b/tools/testing/selftests/bpf/bpf_trace_helpers.h @@ -1,58 +1,120 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ #ifndef __BPF_TRACE_HELPERS_H #define __BPF_TRACE_HELPERS_H -#include "bpf_helpers.h" - -#define __BPF_MAP_0(i, m, v, ...) v -#define __BPF_MAP_1(i, m, v, t, a, ...) m(t, a, ctx[i]) -#define __BPF_MAP_2(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_1(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_3(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_2(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_4(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_3(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_5(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_4(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_6(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_5(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_7(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_6(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_8(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_7(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_9(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_8(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_10(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_9(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_11(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_10(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_12(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_11(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP(n, ...) __BPF_MAP_##n(0, __VA_ARGS__) - -/* BPF sizeof(void *) is always 8, so no need to cast to long first - * for ptr to avoid compiler warning. +#include <bpf/bpf_helpers.h> + +#define ___bpf_concat(a, b) a ## b +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#define ___bpf_empty(...) \ + ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) + +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] +#define ___bpf_ctx_cast(args...) \ + ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) + +/* + * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and + * similar kinds of BPF programs, that accept input arguments as a single + * pointer to untyped u64 array, where each u64 can actually be a typed + * pointer or integer of different size. Instead of requring user to write + * manual casts and work with array elements by index, BPF_PROG macro + * allows user to declare a list of named and typed input arguments in the + * same syntax as for normal C function. All the casting is hidden and + * performed transparently, while user code can just assume working with + * function arguments of specified type and name. + * + * Original raw context argument is preserved as well as 'ctx' argument. + * This is useful when using BPF helpers that expect original context + * as one of the parameters (e.g., for bpf_perf_event_output()). */ -#define __BPF_CAST(t, a, ctx) (t) ctx -#define __BPF_V void -#define __BPF_N - -#define __BPF_DECL_ARGS(t, a, ctx) t a - -#define BPF_TRACE_x(x, sec_name, fname, ret_type, ...) \ -static __always_inline ret_type \ -____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - \ -SEC(sec_name) \ -ret_type fname(__u64 *ctx) \ -{ \ - return ____##fname(__BPF_MAP(x, __BPF_CAST, __BPF_N, __VA_ARGS__));\ -} \ - \ -static __always_inline \ -ret_type ____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) - -#define BPF_TRACE_0(sec, fname, ...) BPF_TRACE_x(0, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_1(sec, fname, ...) BPF_TRACE_x(1, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_2(sec, fname, ...) BPF_TRACE_x(2, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_3(sec, fname, ...) BPF_TRACE_x(3, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_4(sec, fname, ...) BPF_TRACE_x(4, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_5(sec, fname, ...) BPF_TRACE_x(5, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_6(sec, fname, ...) BPF_TRACE_x(6, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_7(sec, fname, ...) BPF_TRACE_x(7, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_8(sec, fname, ...) BPF_TRACE_x(8, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_9(sec, fname, ...) BPF_TRACE_x(9, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_10(sec, fname, ...) BPF_TRACE_x(10, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_11(sec, fname, ...) BPF_TRACE_x(11, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_12(sec, fname, ...) BPF_TRACE_x(12, sec, fname, int, __VA_ARGS__) +#define BPF_PROG(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_ctx_cast(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args) + +struct pt_regs; + +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) \ + ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) \ + ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) \ + ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) \ + ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) \ + ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args(args...) \ + ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) +/* + * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for + * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific + * low-level way of getting kprobe input arguments from struct pt_regs, and + * provides a familiar typed and named function arguments syntax and + * semantics of accessing kprobe input paremeters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + */ +#define BPF_KPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) + +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_argsN(x, args...) \ + ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx) +#define ___bpf_kretprobe_args(args...) \ + ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args) + +/* + * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all + * input kprobe arguments, one last extra argument has to be specified, which + * captures kprobe return value. + */ +#define BPF_KRETPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kretprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) #endif diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index ec219f84e041..a3352a64c067 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -6,7 +6,7 @@ #include <stdlib.h> #include <string.h> #include <errno.h> -#include <libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ static inline unsigned int bpf_num_possible_cpus(void) { diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c new file mode 100644 index 000000000000..f0a64d8ac59a --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <errno.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_maps.h> + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + int *values) +{ + int i, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + for (i = 0; i < max_entries; i++) { + keys[i] = i; + values[i] = i + 1; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, int *values) +{ + int i; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + CHECK(keys[i] + 1 != values[i], "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], values[i]); + visited[i] = 1; + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void test_array_map_batch_ops(void) +{ + struct bpf_create_map_attr xattr = { + .name = "array_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + int map_fd, *keys, *values, *visited; + __u32 count, total, total_success; + const __u32 max_entries = 10; + bool nospace_err; + __u64 batch = 0; + int err, step; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + keys = malloc(max_entries * sizeof(int)); + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", "error:%s\n", + strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values); + + /* test 1: lookup in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values); + map_batch_verify(visited, max_entries, keys, values); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * sizeof(*values)); + batch = 0; + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each. + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, &batch, + keys + total, + values + total, + &count, &opts); + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + + printf("%s:PASS\n", __func__); + + free(keys); + free(values); + free(visited); +} diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c new file mode 100644 index 000000000000..976bf415fbdd --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <stdio.h> +#include <errno.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <bpf_util.h> +#include <test_maps.h> + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + if (is_pcpu) + v = (value *)values; + + for (i = 0; i < max_entries; i++) { + keys[i] = i + 1; + if (is_pcpu) + for (j = 0; j < bpf_num_possible_cpus(); j++) + bpf_percpu(v[i], j) = i + 2 + j; + else + ((int *)values)[i] = i + 2; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j; + + if (is_pcpu) + v = (value *)values; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + + if (is_pcpu) { + for (j = 0; j < bpf_num_possible_cpus(); j++) { + CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j), + "key/value checking", + "error: i %d j %d key %d value %d\n", + i, j, keys[i], bpf_percpu(v[i], j)); + } + } else { + CHECK(keys[i] + 1 != ((int *)values)[i], + "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], + ((int *)values)[i]); + } + + visited[i] = 1; + + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void __test_map_lookup_and_delete_batch(bool is_pcpu) +{ + __u32 batch, count, total, total_success; + typedef BPF_DECLARE_PERCPU(int, value); + int map_fd, *keys, *visited, key; + const __u32 max_entries = 10; + value pcpu_values[max_entries]; + int err, step, value_size; + bool nospace_err; + void *values; + struct bpf_create_map_attr xattr = { + .name = "hash_map", + .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : + BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + value_size = is_pcpu ? sizeof(value) : sizeof(int); + keys = malloc(max_entries * sizeof(int)); + if (is_pcpu) + values = pcpu_values; + else + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", + "error:%s\n", strerror(errno)); + + /* test 1: lookup/delete an empty hash table, -ENOENT */ + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "empty map", + "error: %s\n", strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + + /* test 2: lookup/delete with count = 0, success */ + count = 0; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK(err, "count = 0", "error: %s\n", strerror(errno)); + + /* test 3: lookup/delete with count = max_entries, success */ + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "count = max_entries", + "error: %s\n", strerror(errno)); + CHECK(count != max_entries, "count = max_entries", + "count = %u, max_entries = %u\n", count, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + /* bpf_map_get_next_key() should return -ENOENT for an empty map. */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno)); + + /* test 4: lookup/delete in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + total = 0; + count = step; + while (total < max_entries) { + if (max_entries - total < step) + count = max_entries - total; + err = bpf_map_delete_batch(map_fd, + keys + total, + &count, &opts); + CHECK((err && errno != ENOENT), "delete batch", + "error: %s\n", strerror(errno)); + total += count; + if (err) + break; + } + CHECK(total != max_entries, "delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + /* check map is empty, errono == ENOENT */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()", + "error: %s\n", strerror(errno)); + + /* iteratively lookup/delete elements with 'step' + * elements each + */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_and_delete_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup/delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", + strerror(errno)); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + free(keys); + free(visited); + if (!is_pcpu) + free(values); +} + +void htab_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(false); + printf("test_%s:PASS\n", __func__); +} + +void htab_percpu_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(true); + printf("test_%s:PASS\n", __func__); +} + +void test_htab_map_batch_ops(void) +{ + htab_map_batch_ops(); + htab_percpu_map_batch_ops(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index a83111a32d4a..a0ee87c8e1ea 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -1,26 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> - -#define EMBED_FILE(NAME, PATH) \ -asm ( \ -" .pushsection \".rodata\", \"a\", @progbits \n" \ -" .global "#NAME"_data \n" \ -#NAME"_data: \n" \ -" .incbin \"" PATH "\" \n" \ -#NAME"_data_end: \n" \ -" .global "#NAME"_size \n" \ -" .type "#NAME"_size, @object \n" \ -" .size "#NAME"_size, 4 \n" \ -" .align 4, \n" \ -#NAME"_size: \n" \ -" .int "#NAME"_data_end - "#NAME"_data \n" \ -" .popsection \n" \ -); \ -extern char NAME##_data[]; \ -extern int NAME##_size; +#include "test_attach_probe.skel.h" ssize_t get_base_addr() { - size_t start; + size_t start, offset; char buf[256]; FILE *f; @@ -28,10 +11,11 @@ ssize_t get_base_addr() { if (!f) return -errno; - while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) { + while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", + &start, buf, &offset) == 3) { if (strcmp(buf, "r-xp") == 0) { fclose(f); - return start; + return start - offset; } } @@ -39,30 +23,12 @@ ssize_t get_base_addr() { return -EINVAL; } -EMBED_FILE(probe, "test_attach_probe.o"); - void test_attach_probe(void) { - const char *kprobe_name = "kprobe/sys_nanosleep"; - const char *kretprobe_name = "kretprobe/sys_nanosleep"; - const char *uprobe_name = "uprobe/trigger_func"; - const char *uretprobe_name = "uretprobe/trigger_func"; - const int kprobe_idx = 0, kretprobe_idx = 1; - const int uprobe_idx = 2, uretprobe_idx = 3; - const char *obj_name = "attach_probe"; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, - .object_name = obj_name, - .relaxed_maps = true, - ); - struct bpf_program *kprobe_prog, *kretprobe_prog; - struct bpf_program *uprobe_prog, *uretprobe_prog; - struct bpf_object *obj; - int err, duration = 0, res; - struct bpf_link *kprobe_link = NULL; - struct bpf_link *kretprobe_link = NULL; - struct bpf_link *uprobe_link = NULL; - struct bpf_link *uretprobe_link = NULL; - int results_map_fd; + int duration = 0; + struct bpf_link *kprobe_link, *kretprobe_link; + struct bpf_link *uprobe_link, *uretprobe_link; + struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr; @@ -72,123 +38,68 @@ void test_attach_probe(void) return; uprobe_offset = (size_t)&get_base_addr - base_addr; - /* open object */ - obj = bpf_object__open_mem(probe_data, probe_size, &open_opts); - if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj))) + skel = test_attach_probe__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) return; - - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", - "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n")) goto cleanup; - kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name); - if (CHECK(!kprobe_prog, "find_probe", - "prog '%s' not found\n", kprobe_name)) - goto cleanup; - kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name); - if (CHECK(!kretprobe_prog, "find_probe", - "prog '%s' not found\n", kretprobe_name)) - goto cleanup; - uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name); - if (CHECK(!uprobe_prog, "find_probe", - "prog '%s' not found\n", uprobe_name)) - goto cleanup; - uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name); - if (CHECK(!uretprobe_prog, "find_probe", - "prog '%s' not found\n", uretprobe_name)) - goto cleanup; - - /* create maps && load programs */ - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "err %d\n", err)) - goto cleanup; - - /* load maps */ - results_map_fd = bpf_find_map(__func__, obj, "results_map"); - if (CHECK(results_map_fd < 0, "find_results_map", - "err %d\n", results_map_fd)) - goto cleanup; - - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, + kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe, false /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", - "err %ld\n", PTR_ERR(kprobe_link))) { - kprobe_link = NULL; + "err %ld\n", PTR_ERR(kprobe_link))) goto cleanup; - } - kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog, + skel->links.handle_kprobe = kprobe_link; + + kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe, true /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", - "err %ld\n", PTR_ERR(kretprobe_link))) { - kretprobe_link = NULL; + "err %ld\n", PTR_ERR(kretprobe_link))) goto cleanup; - } - uprobe_link = bpf_program__attach_uprobe(uprobe_prog, + skel->links.handle_kretprobe = kretprobe_link; + + uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe, false /* retprobe */, 0 /* self pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uprobe_link), "attach_uprobe", - "err %ld\n", PTR_ERR(uprobe_link))) { - uprobe_link = NULL; + "err %ld\n", PTR_ERR(uprobe_link))) goto cleanup; - } - uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog, + skel->links.handle_uprobe = uprobe_link; + + uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe, true /* retprobe */, -1 /* any pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe", - "err %ld\n", PTR_ERR(uretprobe_link))) { - uretprobe_link = NULL; + "err %ld\n", PTR_ERR(uretprobe_link))) goto cleanup; - } + skel->links.handle_uretprobe = uretprobe_link; /* trigger & validate kprobe && kretprobe */ usleep(1); - err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res); - if (CHECK(err, "get_kprobe_res", - "failed to get kprobe res: %d\n", err)) + if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res", + "wrong kprobe res: %d\n", skel->bss->kprobe_res)) goto cleanup; - if (CHECK(res != kprobe_idx + 1, "check_kprobe_res", - "wrong kprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res); - if (CHECK(err, "get_kretprobe_res", - "failed to get kretprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res", - "wrong kretprobe res: %d\n", res)) + if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res", + "wrong kretprobe res: %d\n", skel->bss->kretprobe_res)) goto cleanup; /* trigger & validate uprobe & uretprobe */ get_base_addr(); - err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res); - if (CHECK(err, "get_uprobe_res", - "failed to get uprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != uprobe_idx + 1, "check_uprobe_res", - "wrong uprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res); - if (CHECK(err, "get_uretprobe_res", - "failed to get uretprobe res: %d\n", err)) + if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", + "wrong uprobe res: %d\n", skel->bss->uprobe_res)) goto cleanup; - if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res", - "wrong uretprobe res: %d\n", res)) + if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res", + "wrong uretprobe res: %d\n", skel->bss->uretprobe_res)) goto cleanup; cleanup: - bpf_link__destroy(kprobe_link); - bpf_link__destroy(kretprobe_link); - bpf_link__destroy(uprobe_link); - bpf_link__destroy(uretprobe_link); - bpf_object__close(obj); + test_attach_probe__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c new file mode 100644 index 000000000000..8482bbc67eec --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/err.h> +#include <test_progs.h> +#include "bpf_dctcp.skel.h" +#include "bpf_cubic.skel.h" + +#define min(a, b) ((a) < (b) ? (a) : (b)) + +static const unsigned int total_bytes = 10 * 1024 * 1024; +static const struct timeval timeo_sec = { .tv_sec = 10 }; +static const size_t timeo_optlen = sizeof(timeo_sec); +static int stop, duration; + +static int settimeo(int fd) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, + timeo_optlen); + if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n", + errno)) + return -1; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec, + timeo_optlen); + if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n", + errno)) + return -1; + + return 0; +} + +static int settcpca(int fd, const char *tcp_ca) +{ + int err; + + err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca)); + if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n", + errno)) + return -1; + + return 0; +} + +static void *server(void *arg) +{ + int lfd = (int)(long)arg, err = 0, fd; + ssize_t nr_sent = 0, bytes = 0; + char batch[1500]; + + fd = accept(lfd, NULL, NULL); + while (fd == -1) { + if (errno == EINTR) + continue; + err = -errno; + goto done; + } + + if (settimeo(fd)) { + err = -errno; + goto done; + } + + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_sent = send(fd, &batch, + min(total_bytes - bytes, sizeof(batch)), 0); + if (nr_sent == -1 && errno == EINTR) + continue; + if (nr_sent == -1) { + err = -errno; + break; + } + bytes += nr_sent; + } + + CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n", + bytes, total_bytes, nr_sent, errno); + +done: + if (fd != -1) + close(fd); + if (err) { + WRITE_ONCE(stop, 1); + return ERR_PTR(err); + } + return NULL; +} + +static void do_test(const char *tcp_ca) +{ + struct sockaddr_in6 sa6 = {}; + ssize_t nr_recv = 0, bytes = 0; + int lfd = -1, fd = -1; + pthread_t srv_thread; + socklen_t addrlen = sizeof(sa6); + void *thread_ret; + char batch[1500]; + int err; + + WRITE_ONCE(stop, 0); + + lfd = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(lfd == -1, "socket", "errno:%d\n", errno)) + return; + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) { + close(lfd); + return; + } + + if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) || + settimeo(lfd) || settimeo(fd)) + goto done; + + /* bind, listen and start server thread to accept */ + sa6.sin6_family = AF_INET6; + sa6.sin6_addr = in6addr_loopback; + err = bind(lfd, (struct sockaddr *)&sa6, addrlen); + if (CHECK(err == -1, "bind", "errno:%d\n", errno)) + goto done; + err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen); + if (CHECK(err == -1, "getsockname", "errno:%d\n", errno)) + goto done; + err = listen(lfd, 1); + if (CHECK(err == -1, "listen", "errno:%d\n", errno)) + goto done; + err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); + if (CHECK(err != 0, "pthread_create", "err:%d\n", err)) + goto done; + + /* connect to server */ + err = connect(fd, (struct sockaddr *)&sa6, addrlen); + if (CHECK(err == -1, "connect", "errno:%d\n", errno)) + goto wait_thread; + + /* recv total_bytes */ + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_recv = recv(fd, &batch, + min(total_bytes - bytes, sizeof(batch)), 0); + if (nr_recv == -1 && errno == EINTR) + continue; + if (nr_recv == -1) + break; + bytes += nr_recv; + } + + CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n", + bytes, total_bytes, nr_recv, errno); + +wait_thread: + WRITE_ONCE(stop, 1); + pthread_join(srv_thread, &thread_ret); + CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld", + PTR_ERR(thread_ret)); +done: + close(lfd); + close(fd); +} + +static void test_cubic(void) +{ + struct bpf_cubic *cubic_skel; + struct bpf_link *link; + + cubic_skel = bpf_cubic__open_and_load(); + if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n")) + return; + + link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic); + if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", + PTR_ERR(link))) { + bpf_cubic__destroy(cubic_skel); + return; + } + + do_test("bpf_cubic"); + + bpf_link__destroy(link); + bpf_cubic__destroy(cubic_skel); +} + +static void test_dctcp(void) +{ + struct bpf_dctcp *dctcp_skel; + struct bpf_link *link; + + dctcp_skel = bpf_dctcp__open_and_load(); + if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n")) + return; + + link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp); + if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", + PTR_ERR(link))) { + bpf_dctcp__destroy(dctcp_skel); + return; + } + + do_test("bpf_dctcp"); + + bpf_link__destroy(link); + bpf_dctcp__destroy(dctcp_skel); +} + +void test_bpf_tcp_ca(void) +{ + if (test__start_subtest("dctcp")) + test_dctcp(); + if (test__start_subtest("cubic")) + test_cubic(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 9486c13af6b2..e9f2f12ba06b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -48,6 +48,8 @@ void test_bpf_verif_scale(void) { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, + { "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + /* full unroll by llvm */ { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c new file mode 100644 index 000000000000..5b13f2c6c402 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(void) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_autodetach(void) +{ + __u32 duration = 0, prog_cnt = 4, attach_flags; + int allow_prog[2] = {-1}; + __u32 prog_ids[2] = {0}; + void *ptr = NULL; + int cg = 0, i; + int attempts; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load(); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + /* create a cgroup, attach two programs and remember their ids */ + cg = create_and_get_cgroup("/cg_autodetach"); + if (CHECK_FAIL(cg < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg_autodetach"))) + goto err; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (CHECK(bpf_prog_attach(allow_prog[i], cg, + BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog_attach", "prog[%d], errno=%d\n", i, errno)) + goto err; + + /* make sure that programs are attached and run some traffic */ + if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, + prog_ids, &prog_cnt), + "prog_query", "errno=%d\n", errno)) + goto err; + if (CHECK_FAIL(system(PING_CMD))) + goto err; + + /* allocate some memory (4Mb) to pin the original cgroup */ + ptr = malloc(4 * (1 << 20)); + if (CHECK_FAIL(!ptr)) + goto err; + + /* close programs and cgroup fd */ + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + close(allow_prog[i]); + allow_prog[i] = -1; + } + + close(cg); + cg = 0; + + /* leave the cgroup and remove it. don't detach programs */ + cleanup_cgroup_environment(); + + /* wait for the asynchronous auto-detachment. + * wait for no more than 5 sec and give up. + */ + for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { + for (attempts = 5; attempts >= 0; attempts--) { + int fd = bpf_prog_get_fd_by_id(prog_ids[i]); + + if (fd < 0) + break; + + /* don't leave the fd open */ + close(fd); + + if (CHECK_FAIL(!attempts)) + goto err; + + sleep(1); + } + } + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + if (cg) + close(cg); + free(ptr); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c new file mode 100644 index 000000000000..2ff21dbce179 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int map_fd = -1; + +static int prog_load_cnt(int verdict, int val) +{ + int cgroup_storage_fd, percpu_cgroup_storage_fd; + + if (map_fd < 0) + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + percpu_cgroup_storage_fd = bpf_create_map( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (percpu_cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + struct bpf_insn prog[] = { + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_MOV64_IMM(BPF_REG_1, val), + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), + + BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + int ret; + + ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); + + close(cgroup_storage_fd); + return ret; +} + +void test_cgroup_attach_multi(void) +{ + __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; + int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts); + int allow_prog[7] = {-1}; + unsigned long long value; + __u32 duration = 0; + int i = 0; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load_cnt(1, 1 << i); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + cg1 = create_and_get_cgroup("/cg1"); + if (CHECK_FAIL(cg1 < 0)) + goto err; + cg2 = create_and_get_cgroup("/cg1/cg2"); + if (CHECK_FAIL(cg2 < 0)) + goto err; + cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); + if (CHECK_FAIL(cg3 < 0)) + goto err; + cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); + if (CHECK_FAIL(cg4 < 0)) + goto err; + cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); + if (CHECK_FAIL(cg5 < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg1/cg2/cg3/cg4/cg5"))) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog0_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "fail_same_prog_attach_to_cg1", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog1_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog2_attach_to_cg2_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog3_attach_to_cg3_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog4_attach_to_cg4_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0), + "prog5_attach_to_cg5_none", "errno=%d\n", errno)) + goto err; + + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 32); + + /* query the number of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, NULL, NULL, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + /* retrieve prog_ids of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + CHECK_FAIL(attach_flags != 0); + saved_prog_id = prog_ids[0]; + /* check enospc handling */ + prog_ids[0] = 0; + prog_cnt = 2; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt) != -1); + CHECK_FAIL(errno != ENOSPC); + CHECK_FAIL(prog_cnt != 4); + /* check that prog_ids are returned even when buffer is too small */ + CHECK_FAIL(prog_ids[0] != saved_prog_id); + /* retrieve prog_id of single attached prog in cg5 */ + prog_ids[0] = 0; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 1); + CHECK_FAIL(prog_ids[0] != saved_prog_id); + + /* detach bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg5", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 16); + + /* test replace */ + + attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_override", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_REPLACE; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_multi", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; + attach_opts.replace_prog_fd = -1; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_bad_fd", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EBADF); + + /* replacing a program that is not attached to cgroup should fail */ + attach_opts.replace_prog_fd = allow_prog[3]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_ent", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != ENOENT); + + /* replace 1st from the top program */ + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "prog_replace", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 8 + 16); + + /* detach 3rd from bottom program and ping again */ + if (CHECK(!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_from_cg3", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS), + "prog3_detach_from_cg3", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 16); + + /* detach 2nd from bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg4", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 4); + + prog_cnt = 4; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 3); + CHECK_FAIL(attach_flags != 0); + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 0); + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + close(cg1); + close(cg2); + close(cg3); + close(cg4); + close(cg5); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c new file mode 100644 index 000000000000..9d8cb48b99de --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define FOO "/foo" +#define BAR "/foo/bar/" +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(int verdict) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_override(void) +{ + int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1; + __u32 duration = 0; + + allow_prog = prog_load(1); + if (CHECK(allow_prog < 0, "prog_load_allow", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + drop_prog = prog_load(0); + if (CHECK(drop_prog < 0, "prog_load_drop", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + foo = test__join_cgroup(FOO); + if (CHECK(foo < 0, "cgroup_join_foo", "cgroup setup failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_drop_foo_override", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + bar = test__join_cgroup(BAR); + if (CHECK(bar < 0, "cgroup_join_bar", "cgroup setup failed\n")) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "prog_detach_foo", + "detach prog from %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_foo", + "double detach from %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_allow_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_bar_override", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_foo_override", + "attach prog to %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_drop_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + +err: + close(foo); + close(bar); + close(allow_prog); + close(drop_prog); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c new file mode 100644 index 000000000000..b093787e9448 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> +#include <sys/mman.h> +#include <sys/utsname.h> +#include <linux/version.h> +#include "test_core_extern.skel.h" + +static uint32_t get_kernel_version(void) +{ + uint32_t major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + +#define CFG "CONFIG_BPF_SYSCALL=n\n" + +static struct test_case { + const char *name; + const char *cfg; + bool fails; + struct test_core_extern__data data; +} test_cases[] = { + { .name = "default search path", .data = { .bpf_syscall = true } }, + { + .name = "custom values", + .cfg = "CONFIG_BPF_SYSCALL=n\n" + "CONFIG_TRISTATE=m\n" + "CONFIG_BOOL=y\n" + "CONFIG_CHAR=100\n" + "CONFIG_USHORT=30000\n" + "CONFIG_INT=123456\n" + "CONFIG_ULONG=0xDEADBEEFC0DE\n" + "CONFIG_STR=\"abracad\"\n" + "CONFIG_MISSING=0", + .data = { + .bpf_syscall = false, + .tristate_val = TRI_MODULE, + .bool_val = true, + .char_val = 100, + .ushort_val = 30000, + .int_val = 123456, + .ulong_val = 0xDEADBEEFC0DE, + .str_val = "abracad", + }, + }, + /* TRISTATE */ + { .name = "tristate (y)", .cfg = CFG"CONFIG_TRISTATE=y\n", + .data = { .tristate_val = TRI_YES } }, + { .name = "tristate (n)", .cfg = CFG"CONFIG_TRISTATE=n\n", + .data = { .tristate_val = TRI_NO } }, + { .name = "tristate (m)", .cfg = CFG"CONFIG_TRISTATE=m\n", + .data = { .tristate_val = TRI_MODULE } }, + { .name = "tristate (int)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=1" }, + { .name = "tristate (bad)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=M" }, + /* BOOL */ + { .name = "bool (y)", .cfg = CFG"CONFIG_BOOL=y\n", + .data = { .bool_val = true } }, + { .name = "bool (n)", .cfg = CFG"CONFIG_BOOL=n\n", + .data = { .bool_val = false } }, + { .name = "bool (tristate)", .fails = 1, .cfg = CFG"CONFIG_BOOL=m" }, + { .name = "bool (int)", .fails = 1, .cfg = CFG"CONFIG_BOOL=1" }, + /* CHAR */ + { .name = "char (tristate)", .cfg = CFG"CONFIG_CHAR=m\n", + .data = { .char_val = 'm' } }, + { .name = "char (bad)", .fails = 1, .cfg = CFG"CONFIG_CHAR=q\n" }, + { .name = "char (empty)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\n" }, + { .name = "char (str)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\"y\"\n" }, + /* STRING */ + { .name = "str (empty)", .cfg = CFG"CONFIG_STR=\"\"\n", + .data = { .str_val = "\0\0\0\0\0\0\0" } }, + { .name = "str (padded)", .cfg = CFG"CONFIG_STR=\"abra\"\n", + .data = { .str_val = "abra\0\0\0" } }, + { .name = "str (too long)", .cfg = CFG"CONFIG_STR=\"abracada\"\n", + .data = { .str_val = "abracad" } }, + { .name = "str (no value)", .fails = 1, .cfg = CFG"CONFIG_STR=\n" }, + { .name = "str (bad value)", .fails = 1, .cfg = CFG"CONFIG_STR=bla\n" }, + /* INTEGERS */ + { + .name = "integer forms", + .cfg = CFG + "CONFIG_CHAR=0xA\n" + "CONFIG_USHORT=0462\n" + "CONFIG_INT=-100\n" + "CONFIG_ULONG=+1000000000000", + .data = { + .char_val = 0xA, + .ushort_val = 0462, + .int_val = -100, + .ulong_val = 1000000000000, + }, + }, + { .name = "int (bad)", .fails = 1, .cfg = CFG"CONFIG_INT=abc" }, + { .name = "int (str)", .fails = 1, .cfg = CFG"CONFIG_INT=\"abc\"" }, + { .name = "int (empty)", .fails = 1, .cfg = CFG"CONFIG_INT=" }, + { .name = "int (mixed)", .fails = 1, .cfg = CFG"CONFIG_INT=123abc" }, + { .name = "int (max)", .cfg = CFG"CONFIG_INT=2147483647", + .data = { .int_val = 2147483647 } }, + { .name = "int (min)", .cfg = CFG"CONFIG_INT=-2147483648", + .data = { .int_val = -2147483648 } }, + { .name = "int (max+1)", .fails = 1, .cfg = CFG"CONFIG_INT=2147483648" }, + { .name = "int (min-1)", .fails = 1, .cfg = CFG"CONFIG_INT=-2147483649" }, + { .name = "ushort (max)", .cfg = CFG"CONFIG_USHORT=65535", + .data = { .ushort_val = 65535 } }, + { .name = "ushort (min)", .cfg = CFG"CONFIG_USHORT=0", + .data = { .ushort_val = 0 } }, + { .name = "ushort (max+1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=65536" }, + { .name = "ushort (min-1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=-1" }, + { .name = "u64 (max)", .cfg = CFG"CONFIG_ULONG=0xffffffffffffffff", + .data = { .ulong_val = 0xffffffffffffffff } }, + { .name = "u64 (min)", .cfg = CFG"CONFIG_ULONG=0", + .data = { .ulong_val = 0 } }, + { .name = "u64 (max+1)", .fails = 1, .cfg = CFG"CONFIG_ULONG=0x10000000000000000" }, +}; + +void test_core_extern(void) +{ + const uint32_t kern_ver = get_kernel_version(); + int err, duration = 0, i, j; + struct test_core_extern *skel = NULL; + uint64_t *got, *exp; + int n = sizeof(*skel->data) / sizeof(uint64_t); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + struct test_case *t = &test_cases[i]; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .kconfig = t->cfg, + ); + + if (!test__start_subtest(t->name)) + continue; + + skel = test_core_extern__open_opts(&opts); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + goto cleanup; + err = test_core_extern__load(skel); + if (t->fails) { + CHECK(!err, "skel_load", + "shouldn't succeed open/load of skeleton\n"); + goto cleanup; + } else if (CHECK(err, "skel_load", + "failed to open/load skeleton\n")) { + goto cleanup; + } + err = test_core_extern__attach(skel); + if (CHECK(err, "attach_raw_tp", "failed attach: %d\n", err)) + goto cleanup; + + usleep(1); + + t->data.kern_ver = kern_ver; + t->data.missing_val = 0xDEADC0DE; + got = (uint64_t *)skel->data; + exp = (uint64_t *)&t->data; + for (j = 0; j < n; j++) { + CHECK(got[j] != exp[j], "check_res", + "result #%d: expected %lx, but got %lx\n", + j, exp[j], got[j]); + } +cleanup: + test_core_extern__destroy(skel); + skel = NULL; + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 05fe85281ff7..31e177adbdf1 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -74,6 +74,7 @@ .b123 = 2, \ .c1c = 3, \ .d00d = 4, \ + .f10c = 0, \ }, \ .output_len = sizeof(struct core_reloc_arrays_output) \ } @@ -308,12 +309,15 @@ static struct core_reloc_test_case test_cases[] = { ARRAYS_CASE(arrays), ARRAYS_CASE(arrays___diff_arr_dim), ARRAYS_CASE(arrays___diff_arr_val_sz), + ARRAYS_CASE(arrays___equiv_zero_sz_arr), + ARRAYS_CASE(arrays___fixed_arr), ARRAYS_ERR_CASE(arrays___err_too_small), ARRAYS_ERR_CASE(arrays___err_too_shallow), ARRAYS_ERR_CASE(arrays___err_non_array), ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr), /* enum/ptr/int handling scenarios */ PRIMITIVES_CASE(primitives), diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c new file mode 100644 index 000000000000..f7c7e25232be --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/btf.h> +#include "bpf/libbpf_internal.h" + +static int duration = 0; + +static void validate_mask(int case_nr, const char *exp, bool *mask, int n) +{ + int i; + + for (i = 0; exp[i]; i++) { + if (exp[i] == '1') { + if (CHECK(i + 1 > n, "mask_short", + "case #%d: mask too short, got n=%d, need at least %d\n", + case_nr, n, i + 1)) + return; + CHECK(!mask[i], "cpu_not_set", + "case #%d: mask differs, expected cpu#%d SET\n", + case_nr, i); + } else { + CHECK(i < n && mask[i], "cpu_set", + "case #%d: mask differs, expected cpu#%d UNSET\n", + case_nr, i); + } + } + CHECK(i < n, "mask_long", + "case #%d: mask too long, got n=%d, expected at most %d\n", + case_nr, n, i); +} + +static struct { + const char *cpu_mask; + const char *expect; + bool fails; +} test_cases[] = { + { "0\n", "1", false }, + { "0,2\n", "101", false }, + { "0-2\n", "111", false }, + { "0-2,3-4\n", "11111", false }, + { "0", "1", false }, + { "0-2", "111", false }, + { "0,2", "101", false }, + { "0,1-3", "1111", false }, + { "0,1,2,3", "1111", false }, + { "0,2-3,5", "101101", false }, + { "3-3", "0001", false }, + { "2-4,6,9-10", "00111010011", false }, + /* failure cases */ + { "", "", true }, + { "0-", "", true }, + { "0 ", "", true }, + { "0_1", "", true }, + { "1-0", "", true }, + { "-1", "", true }, +}; + +void test_cpu_mask() +{ + int i, err, n; + bool *mask; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + mask = NULL; + err = parse_cpu_mask_str(test_cases[i].cpu_mask, &mask, &n); + if (test_cases[i].fails) { + CHECK(!err, "should_fail", + "case #%d: parsing should fail!\n", i + 1); + } else { + if (CHECK(err, "parse_err", + "case #%d: cpu mask parsing failed: %d\n", + i + 1, err)) + continue; + validate_mask(i + 1, test_cases[i].expect, mask, n); + } + free(mask); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 40bcff2cc274..235ac4f67f5b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,90 +1,55 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" +#include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct bpf_prog_load_attr attr_fentry = { - .file = "./fentry_test.o", - }; - struct bpf_prog_load_attr attr_fexit = { - .file = "./fexit_test.o", - }; - - struct bpf_object *obj_fentry = NULL, *obj_fexit = NULL, *pkt_obj; - struct bpf_map *data_map_fentry, *data_map_fexit; - char fentry_name[] = "fentry/bpf_fentry_testX"; - char fexit_name[] = "fexit/bpf_fentry_testX"; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[12] = {}; - struct bpf_program *prog[12]; - __u32 duration, retval; - const int zero = 0; - u64 result[12]; - - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + struct fexit_test *fexit_skel = NULL; + __u64 *fentry_res, *fexit_res; + __u32 duration = 0, retval; + int err, pkt_fd, i; + + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr_fentry, &obj_fentry, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto close_prog; - err = bpf_prog_load_xattr(&attr_fexit, &obj_fexit, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fexit_skel = fexit_test__open_and_load(); + if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) goto close_prog; - for (i = 0; i < 6; i++) { - fentry_name[sizeof(fentry_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj_fentry, fentry_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fentry_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fentry = bpf_object__find_map_by_name(obj_fentry, "fentry_t.bss"); - if (CHECK(!data_map_fentry, "find_data_map", "data map not found\n")) + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) goto close_prog; - - for (i = 6; i < 12; i++) { - fexit_name[sizeof(fexit_name) - 2] = '1' + i - 6; - prog[i] = bpf_object__find_program_by_title(obj_fexit, fexit_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fexit_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fexit = bpf_object__find_map_by_name(obj_fexit, "fexit_te.bss"); - if (CHECK(!data_map_fexit, "find_data_map", "data map not found\n")) + err = fexit_test__attach(fexit_skel); + if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fentry), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fexit), &zero, result + 6); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 12; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i % 6 + 1, result[i])) - goto close_prog; + fentry_res = (__u64 *)fentry_skel->bss; + fexit_res = (__u64 *)fexit_skel->bss; + printf("%lld\n", fentry_skel->bss->test1_result); + for (i = 0; i < 6; i++) { + CHECK(fentry_res[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); + CHECK(fexit_res[i] != 1, "result", + "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + } close_prog: - for (i = 0; i < 12; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj_fentry); - bpf_object__close(obj_fexit); - bpf_object__close(pkt_obj); + test_pkt_access__destroy(pkt_skel); + fentry_test__destroy(fentry_skel); + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 9fb103193878..5cc06021f27d 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,64 +1,43 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" void test_fentry_test(void) { - struct bpf_prog_load_attr attr = { - .file = "./fentry_test.o", - }; - - char prog_name[] = "fentry/bpf_fentry_testX"; - struct bpf_object *obj = NULL, *pkt_obj; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[6] = {}; - struct bpf_program *prog[6]; - __u32 duration, retval; - struct bpf_map *data_map; - const int zero = 0; - u64 result[6]; - - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + int err, pkt_fd, i; + __u32 duration = 0, retval; + __u64 *result; + + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) - goto close_prog; + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + goto cleanup; - for (i = 0; i < 6; i++) { - prog_name[sizeof(prog_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map = bpf_object__find_map_by_name(obj, "fentry_t.bss"); - if (CHECK(!data_map, "find_data_map", "data map not found\n")) - goto close_prog; + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + goto cleanup; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 6; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i + 1, result[i])) - goto close_prog; + result = (__u64 *)fentry_skel->bss; + for (i = 0; i < 6; i++) { + if (CHECK(result[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, result[i])) + goto cleanup; + } -close_prog: - for (i = 0; i < 6; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj); - bpf_object__close(pkt_obj); +cleanup: + fentry_test__destroy(fentry_skel); + test_pkt_access__destroy(pkt_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index b426bf2f97e4..cde463af7071 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -11,7 +11,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, int err, pkt_fd, i; struct bpf_link **link = NULL; struct bpf_program **prog = NULL; - __u32 duration, retval; + __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; u64 *result = NULL; @@ -26,7 +26,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, link = calloc(sizeof(struct bpf_link *), prog_cnt); prog = calloc(sizeof(struct bpf_program *), prog_cnt); - result = malloc(prog_cnt * sizeof(u64)); + result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64)); if (CHECK(!link || !prog || !result, "alloc_memory", "failed to alloc memory")) goto close_prog; @@ -98,6 +98,24 @@ static void test_target_yes_callees(void) "fexit/test_pkt_access", "fexit/test_pkt_access_subprog1", "fexit/test_pkt_access_subprog2", + "fexit/test_pkt_access_subprog3", + }; + test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", + "./test_pkt_access.o", + ARRAY_SIZE(prog_name), + prog_name); +} + +static void test_func_replace(void) +{ + const char *prog_name[] = { + "fexit/test_pkt_access", + "fexit/test_pkt_access_subprog1", + "fexit/test_pkt_access_subprog2", + "fexit/test_pkt_access_subprog3", + "freplace/get_skb_len", + "freplace/get_skb_ifindex", + "freplace/get_constant", }; test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", "./test_pkt_access.o", @@ -109,4 +127,5 @@ void test_fexit_bpf2bpf(void) { test_target_no_callees(); test_target_yes_callees(); + test_func_replace(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index f99013222c74..d2c3655dd7a3 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -13,7 +13,7 @@ void test_fexit_test(void) int err, pkt_fd, kfree_skb_fd, i; struct bpf_link *link[6] = {}; struct bpf_program *prog[6]; - __u32 duration, retval; + __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; u64 result[6]; diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 051a6d48762c..16a814eb4d64 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -1,16 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include <sys/mman.h> +#include "test_mmap.skel.h" struct map_data { __u64 val[512 * 4]; }; -struct bss_data { - __u64 in_val; - __u64 out_val; -}; - static size_t roundup_page(size_t sz) { long page_size = sysconf(_SC_PAGE_SIZE); @@ -19,41 +15,25 @@ static size_t roundup_page(size_t sz) void test_mmap(void) { - const char *file = "test_mmap.o"; - const char *probe_name = "raw_tracepoint/sys_enter"; - const char *tp_name = "sys_enter"; - const size_t bss_sz = roundup_page(sizeof(struct bss_data)); + const size_t bss_sz = roundup_page(sizeof(struct test_mmap__bss)); const size_t map_sz = roundup_page(sizeof(struct map_data)); const int zero = 0, one = 1, two = 2, far = 1500; const long page_size = sysconf(_SC_PAGE_SIZE); int err, duration = 0, i, data_map_fd; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; - volatile struct bss_data *bss_data; - volatile struct map_data *map_data; + struct test_mmap__bss *bss_data; + struct map_data *map_data; + struct test_mmap *skel; __u64 val = 0; - obj = bpf_object__open_file("test_mmap.o", NULL); - if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n", - file, PTR_ERR(obj))) + + skel = test_mmap__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, probe_name); - if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name)) - goto cleanup; - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n", - probe_name, err)) - goto cleanup; - bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss"); - if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n")) - goto cleanup; - data_map = bpf_object__find_map_by_name(obj, "data_map"); - if (CHECK(!data_map, "find_data_map", "data_map map not found\n")) - goto cleanup; + bss_map = skel->maps.bss; + data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED, @@ -77,13 +57,15 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val); CHECK_FAIL(bss_data->out_val); + CHECK_FAIL(skel->bss->in_val); + CHECK_FAIL(skel->bss->out_val); CHECK_FAIL(map_data->val[0]); CHECK_FAIL(map_data->val[1]); CHECK_FAIL(map_data->val[2]); CHECK_FAIL(map_data->val[far]); - link = bpf_program__attach_raw_tracepoint(prog, tp_name); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + err = test_mmap__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) goto cleanup; bss_data->in_val = 123; @@ -94,6 +76,8 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val != 123); CHECK_FAIL(bss_data->out_val != 123); + CHECK_FAIL(skel->bss->in_val != 123); + CHECK_FAIL(skel->bss->out_val != 123); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 123); @@ -160,6 +144,8 @@ void test_mmap(void) usleep(1); CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -203,6 +189,8 @@ void test_mmap(void) map_data = tmp2; CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -214,7 +202,5 @@ cleanup: CHECK_FAIL(munmap(bss_mmaped, bss_sz)); if (map_mmaped) CHECK_FAIL(munmap(map_mmaped, map_sz)); - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); - bpf_object__close(obj); + test_mmap__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 3003fddc0613..1450ea2dd4cc 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 "bpf/libbpf_internal.h" static void on_sample(void *ctx, int cpu, void *data, __u32 size) { @@ -19,7 +20,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void test_perf_buffer(void) { - int err, prog_fd, nr_cpus, i, duration = 0; + 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"; struct perf_buffer_opts pb_opts = {}; @@ -29,15 +30,27 @@ void test_perf_buffer(void) struct bpf_object *obj; struct perf_buffer *pb; struct bpf_link *link; + bool *online; nr_cpus = libbpf_num_possible_cpus(); if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus)) return; + err = parse_cpu_mask_file("/sys/devices/system/cpu/online", + &online, &on_len); + if (CHECK(err, "nr_on_cpus", "err %d\n", err)) + return; + + for (i = 0; i < on_len; i++) + if (online[i]) + 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)) - return; + 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)) @@ -64,6 +77,11 @@ void test_perf_buffer(void) /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); for (i = 0; i < nr_cpus; i++) { + if (i >= on_len || !online[i]) { + printf("skipping offline CPU #%d\n", i); + continue; + } + CPU_ZERO(&cpu_set); CPU_SET(i, &cpu_set); @@ -81,8 +99,8 @@ void test_perf_buffer(void) if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) goto out_free_pb; - if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt", - "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen))) + if (CHECK(CPU_COUNT(&cpu_seen) != nr_on_cpus, "seen_cpu_cnt", + "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen))) goto out_free_pb; out_free_pb: @@ -91,4 +109,5 @@ out_detach: bpf_link__destroy(link); out_close: bpf_object__close(obj); + free(online); } diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 8a3187dec048..7aecfd9e87d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,8 +3,7 @@ void test_probe_user(void) { -#define kprobe_name "__sys_connect" - const char *prog_name = "kprobe/" kprobe_name; + const char *prog_name = "kprobe/__sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -33,8 +32,7 @@ void test_probe_user(void) "err %d\n", results_map_fd)) goto cleanup; - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false, - kprobe_name); + kprobe_link = bpf_program__attach(kprobe_prog); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", "err %ld\n", PTR_ERR(kprobe_link))) { kprobe_link = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c index d90acc13d1ec..563e12120e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c +++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c @@ -16,14 +16,11 @@ struct rdonly_map_subtest { void test_rdonly_maps(void) { - const char *prog_name_skip_loop = "raw_tracepoint/sys_enter:skip_loop"; - const char *prog_name_part_loop = "raw_tracepoint/sys_enter:part_loop"; - const char *prog_name_full_loop = "raw_tracepoint/sys_enter:full_loop"; const char *file = "test_rdonly_maps.o"; struct rdonly_map_subtest subtests[] = { - { "skip loop", prog_name_skip_loop, 0, 0 }, - { "part loop", prog_name_part_loop, 3, 2 + 3 + 4 }, - { "full loop", prog_name_full_loop, 4, 2 + 3 + 4 + 5 }, + { "skip loop", "skip_loop", 0, 0 }, + { "part loop", "part_loop", 3, 2 + 3 + 4 }, + { "full loop", "full_loop", 4, 2 + 3 + 4 + 5 }, }; int i, err, zero = 0, duration = 0; struct bpf_link *link = NULL; @@ -50,7 +47,7 @@ void test_rdonly_maps(void) if (!test__start_subtest(t->subtest_name)) continue; - prog = bpf_object__find_program_by_title(obj, t->prog_name); + prog = bpf_object__find_program_by_name(obj, t->prog_name); if (CHECK(!prog, "find_prog", "prog '%s' not found\n", t->prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 7566c13eb51a..098bcae5f827 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -20,8 +20,11 @@ #include <bpf/libbpf.h> #include "bpf_rlimit.h" #include "bpf_util.h" + +#include "test_progs.h" #include "test_select_reuseport_common.h" +#define MAX_TEST_NAME 80 #define MIN_TCPHDR_LEN 20 #define UDPHDR_LEN 8 @@ -30,13 +33,13 @@ #define REUSEPORT_ARRAY_SIZE 32 static int result_map, tmp_index_ovr_map, linum_map, data_check_map; -static enum result expected_results[NR_RESULTS]; +static __u32 expected_results[NR_RESULTS]; static int sk_fds[REUSEPORT_ARRAY_SIZE]; -static int reuseport_array, outer_map; +static int reuseport_array = -1, outer_map = -1; static int select_by_skb_data_prog; -static int saved_tcp_syncookie; +static int saved_tcp_syncookie = -1; static struct bpf_object *obj; -static int saved_tcp_fo; +static int saved_tcp_fo = -1; static __u32 index_zero; static int epfd; @@ -46,16 +49,21 @@ static union sa46 { sa_family_t family; } srv_sa; -#define CHECK(condition, tag, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ - printf(format); \ - exit(-1); \ +#define RET_IF(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return; \ + } \ +}) + +#define RET_ERR(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return -1; \ } \ }) -static void create_maps(void) +static int create_maps(void) { struct bpf_create_map_attr attr = {}; @@ -67,8 +75,8 @@ static void create_maps(void) attr.max_entries = REUSEPORT_ARRAY_SIZE; reuseport_array = bpf_create_map_xattr(&attr); - CHECK(reuseport_array == -1, "creating reuseport_array", - "reuseport_array:%d errno:%d\n", reuseport_array, errno); + RET_ERR(reuseport_array == -1, "creating reuseport_array", + "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ attr.name = "outer_map"; @@ -78,63 +86,61 @@ static void create_maps(void) attr.max_entries = 1; attr.inner_map_fd = reuseport_array; outer_map = bpf_create_map_xattr(&attr); - CHECK(outer_map == -1, "creating outer_map", - "outer_map:%d errno:%d\n", outer_map, errno); + RET_ERR(outer_map == -1, "creating outer_map", + "outer_map:%d errno:%d\n", outer_map, errno); + + return 0; } -static void prepare_bpf_obj(void) +static int prepare_bpf_obj(void) { struct bpf_program *prog; struct bpf_map *map; int err; - struct bpf_object_open_attr attr = { - .file = "test_select_reuseport_kern.o", - .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, - }; - - obj = bpf_object__open_xattr(&attr); - CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", - "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); - prog = bpf_program__next(NULL, obj); - CHECK(!prog, "get first bpf_program", "!prog\n"); - bpf_program__set_type(prog, attr.prog_type); + obj = bpf_object__open("test_select_reuseport_kern.o"); + RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", + "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); map = bpf_object__find_map_by_name(obj, "outer_map"); - CHECK(!map, "find outer_map", "!map\n"); + RET_ERR(!map, "find outer_map", "!map\n"); err = bpf_map__reuse_fd(map, outer_map); - CHECK(err, "reuse outer_map", "err:%d\n", err); + RET_ERR(err, "reuse outer_map", "err:%d\n", err); err = bpf_object__load(obj); - CHECK(err, "load bpf_object", "err:%d\n", err); + RET_ERR(err, "load bpf_object", "err:%d\n", err); + prog = bpf_program__next(NULL, obj); + RET_ERR(!prog, "get first bpf_program", "!prog\n"); select_by_skb_data_prog = bpf_program__fd(prog); - CHECK(select_by_skb_data_prog == -1, "get prog fd", - "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); + RET_ERR(select_by_skb_data_prog == -1, "get prog fd", + "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); map = bpf_object__find_map_by_name(obj, "result_map"); - CHECK(!map, "find result_map", "!map\n"); + RET_ERR(!map, "find result_map", "!map\n"); result_map = bpf_map__fd(map); - CHECK(result_map == -1, "get result_map fd", - "result_map:%d\n", result_map); + RET_ERR(result_map == -1, "get result_map fd", + "result_map:%d\n", result_map); map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map"); - CHECK(!map, "find tmp_index_ovr_map", "!map\n"); + RET_ERR(!map, "find tmp_index_ovr_map\n", "!map"); tmp_index_ovr_map = bpf_map__fd(map); - CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", - "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); + RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", + "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); map = bpf_object__find_map_by_name(obj, "linum_map"); - CHECK(!map, "find linum_map", "!map\n"); + RET_ERR(!map, "find linum_map", "!map\n"); linum_map = bpf_map__fd(map); - CHECK(linum_map == -1, "get linum_map fd", - "linum_map:%d\n", linum_map); + RET_ERR(linum_map == -1, "get linum_map fd", + "linum_map:%d\n", linum_map); map = bpf_object__find_map_by_name(obj, "data_check_map"); - CHECK(!map, "find data_check_map", "!map\n"); + RET_ERR(!map, "find data_check_map", "!map\n"); data_check_map = bpf_map__fd(map); - CHECK(data_check_map == -1, "get data_check_map fd", - "data_check_map:%d\n", data_check_map); + RET_ERR(data_check_map == -1, "get data_check_map fd", + "data_check_map:%d\n", data_check_map); + + return 0; } static void sa46_init_loopback(union sa46 *sa, sa_family_t family) @@ -163,65 +169,73 @@ static int read_int_sysctl(const char *sysctl) int fd, ret; fd = open(sysctl, 0); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); ret = read(fd, buf, sizeof(buf)); - CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n", - sysctl, ret, errno); - close(fd); + RET_ERR(ret <= 0, "read(sysctl)", + "sysctl:%s ret:%d errno:%d\n", sysctl, ret, errno); + close(fd); return atoi(buf); } -static void write_int_sysctl(const char *sysctl, int v) +static int write_int_sysctl(const char *sysctl, int v) { int fd, ret, size; char buf[16]; fd = open(sysctl, O_RDWR); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); size = snprintf(buf, sizeof(buf), "%d", v); ret = write(fd, buf, size); - CHECK(ret != size, "write(sysctl)", - "sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno); + RET_ERR(ret != size, "write(sysctl)", + "sysctl:%s ret:%d size:%d errno:%d\n", + sysctl, ret, size, errno); + close(fd); + return 0; } static void restore_sysctls(void) { - write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); + if (saved_tcp_fo != -1) + write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); + if (saved_tcp_syncookie != -1) + write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); } -static void enable_fastopen(void) +static int enable_fastopen(void) { int fo; fo = read_int_sysctl(TCP_FO_SYSCTL); - write_int_sysctl(TCP_FO_SYSCTL, fo | 7); + if (fo < 0) + return -1; + + return write_int_sysctl(TCP_FO_SYSCTL, fo | 7); } -static void enable_syncookie(void) +static int enable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); } -static void disable_syncookie(void) +static int disable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); } -static __u32 get_linum(void) +static long get_linum(void) { __u32 linum; int err; err = bpf_map_lookup_elem(linum_map, &index_zero, &linum); - CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", - err, errno); + RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", + err, errno); return linum; } @@ -237,12 +251,12 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, addrlen = sizeof(cli_sa); err = getsockname(cli_fd, (struct sockaddr *)&cli_sa, &addrlen); - CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", + err, errno); err = bpf_map_lookup_elem(data_check_map, &index_zero, &result); - CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", + err, errno); if (type == SOCK_STREAM) { expected.len = MIN_TCPHDR_LEN; @@ -284,22 +298,42 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, printf("expected: (0x%x, %u, %u)\n", expected.eth_protocol, expected.ip_protocol, expected.bind_inany); - CHECK(1, "data_check result != expected", - "bpf_prog_linum:%u\n", get_linum()); + RET_IF(1, "data_check result != expected", + "bpf_prog_linum:%ld\n", get_linum()); } - CHECK(!result.hash, "data_check result.hash empty", - "result.hash:%u", result.hash); + RET_IF(!result.hash, "data_check result.hash empty", + "result.hash:%u", result.hash); expected.len += cmd ? sizeof(*cmd) : 0; if (type == SOCK_STREAM) - CHECK(expected.len > result.len, "expected.len > result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len > result.len, "expected.len > result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); else - CHECK(expected.len != result.len, "expected.len != result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len != result.len, "expected.len != result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); +} + +static const char *result_to_str(enum result res) +{ + switch (res) { + case DROP_ERR_INNER_MAP: + return "DROP_ERR_INNER_MAP"; + case DROP_ERR_SKB_DATA: + return "DROP_ERR_SKB_DATA"; + case DROP_ERR_SK_SELECT_REUSEPORT: + return "DROP_ERR_SK_SELECT_REUSEPORT"; + case DROP_MISC: + return "DROP_MISC"; + case PASS: + return "PASS"; + case PASS_ERR_SK_SELECT_REUSEPORT: + return "PASS_ERR_SK_SELECT_REUSEPORT"; + default: + return "UNKNOWN"; + } } static void check_results(void) @@ -310,8 +344,8 @@ static void check_results(void) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &results[i]); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); } for (i = 0; i < NR_RESULTS; i++) { @@ -337,10 +371,10 @@ static void check_results(void) printf(", %u", expected_results[i]); printf("]\n"); - CHECK(expected_results[broken] != results[broken], - "unexpected result", - "expected_results[%u] != results[%u] bpf_prog_linum:%u\n", - broken, broken, get_linum()); + printf("mismatch on %s (bpf_prog_linum:%ld)\n", result_to_str(broken), + get_linum()); + + CHECK_FAIL(true); } static int send_data(int type, sa_family_t family, void *data, size_t len, @@ -350,17 +384,17 @@ static int send_data(int type, sa_family_t family, void *data, size_t len, int fd, err; fd = socket(family, type, 0); - CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); + RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); sa46_init_loopback(&cli_sa, family); err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa)); - CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); + RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa, sizeof(srv_sa)); - CHECK(err != len && expected >= PASS, - "sendto()", "family:%u err:%d errno:%d expected:%d\n", - family, err, errno, expected); + RET_ERR(err != len && expected >= PASS, + "sendto()", "family:%u err:%d errno:%d expected:%d\n", + family, err, errno, expected); return fd; } @@ -375,47 +409,49 @@ static void do_test(int type, sa_family_t family, struct cmd *cmd, cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0, expected); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0); - CHECK((nev <= 0 && expected >= PASS) || - (nev > 0 && expected < PASS), - "nev <> expected", - "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", - nev, expected, type, family, - cmd ? cmd->reuseport_index : -1, - cmd ? cmd->pass_on_failure : -1); + RET_IF((nev <= 0 && expected >= PASS) || + (nev > 0 && expected < PASS), + "nev <> expected", + "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", + nev, expected, type, family, + cmd ? cmd->reuseport_index : -1, + cmd ? cmd->pass_on_failure : -1); check_results(); check_data(type, family, cmd, cli_fd); if (expected < PASS) return; - CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT && - cmd->reuseport_index != ev.data.u32, - "check cmd->reuseport_index", - "cmd:(%u, %u) ev.data.u32:%u\n", - cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); + RET_IF(expected != PASS_ERR_SK_SELECT_REUSEPORT && + cmd->reuseport_index != ev.data.u32, + "check cmd->reuseport_index", + "cmd:(%u, %u) ev.data.u32:%u\n", + cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); srv_fd = sk_fds[ev.data.u32]; if (type == SOCK_STREAM) { int new_fd = accept(srv_fd, NULL, 0); - CHECK(new_fd == -1, "accept(srv_fd)", - "ev.data.u32:%u new_fd:%d errno:%d\n", - ev.data.u32, new_fd, errno); + RET_IF(new_fd == -1, "accept(srv_fd)", + "ev.data.u32:%u new_fd:%d errno:%d\n", + ev.data.u32, new_fd, errno); nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(new_fd)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(new_fd)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); close(new_fd); } else { nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(sk_fds)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(sk_fds)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); } close(cli_fd); @@ -428,18 +464,14 @@ static void test_err_inner_map(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_INNER_MAP]++; do_test(type, family, &cmd, DROP_ERR_INNER_MAP); - printf("OK\n"); } static void test_err_skb_data(int type, sa_family_t family) { - printf("%s: ", __func__); expected_results[DROP_ERR_SKB_DATA]++; do_test(type, family, NULL, DROP_ERR_SKB_DATA); - printf("OK\n"); } static void test_err_sk_select_port(int type, sa_family_t family) @@ -449,10 +481,8 @@ static void test_err_sk_select_port(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++; do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_pass(int type, sa_family_t family) @@ -460,14 +490,12 @@ static void test_pass(int type, sa_family_t family) struct cmd cmd; int i; - printf("%s: ", __func__); cmd.pass_on_failure = 0; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { expected_results[PASS]++; cmd.reuseport_index = i; do_test(type, family, &cmd, PASS); } - printf("OK\n"); } static void test_syncookie(int type, sa_family_t family) @@ -481,7 +509,6 @@ static void test_syncookie(int type, sa_family_t family) if (type != SOCK_STREAM) return; - printf("%s: ", __func__); /* * +1 for TCP-SYN and * +1 for the TCP-ACK (ack the syncookie) @@ -497,17 +524,16 @@ static void test_syncookie(int type, sa_family_t family) */ err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &tmp_index, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", + "err:%d errno:%d\n", err, errno); do_test(type, family, &cmd, PASS); err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero, &tmp_index); - CHECK(err == -1 || tmp_index != -1, - "lookup_elem(tmp_index_ovr_map)", - "err:%d errno:%d tmp_index:%d\n", - err, errno, tmp_index); + RET_IF(err == -1 || tmp_index != -1, + "lookup_elem(tmp_index_ovr_map)", + "err:%d errno:%d tmp_index:%d\n", + err, errno, tmp_index); disable_syncookie(); - printf("OK\n"); } static void test_pass_on_err(int type, sa_family_t family) @@ -517,10 +543,8 @@ static void test_pass_on_err(int type, sa_family_t family) .pass_on_failure = 1, }; - printf("%s: ", __func__); expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1; do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_detach_bpf(int type, sa_family_t family) @@ -532,46 +556,47 @@ static void test_detach_bpf(int type, sa_family_t family) struct cmd cmd = {}; int optvalue = 0; - printf("%s: ", __func__); err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == 0 || errno != ENOENT, + "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_before += tmp; } cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, 5); - CHECK(nev <= 0, "nev <= 0", - "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", - nev, type, family); + RET_IF(nev <= 0, "nev <= 0", + "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", + nev, type, family); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_after += tmp; } - CHECK(nr_run_before != nr_run_after, - "nr_run_before != nr_run_after", - "nr_run_before:%u nr_run_after:%u\n", - nr_run_before, nr_run_after); + RET_IF(nr_run_before != nr_run_after, + "nr_run_before != nr_run_after", + "nr_run_before:%u nr_run_after:%u\n", + nr_run_before, nr_run_after); - printf("OK\n"); close(cli_fd); #else - printf("%s: SKIP\n", __func__); + test__skip(); #endif } @@ -594,149 +619,220 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany) */ for (i = first; i >= 0; i--) { sk_fds[i] = socket(family, type, 0); - CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", - i, sk_fds[i], errno); + RET_IF(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", + i, sk_fds[i], errno); err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT, &optval, sizeof(optval)); - CHECK(err == -1, "setsockopt(SO_REUSEPORT)", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "setsockopt(SO_REUSEPORT)", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (i == first) { err = setsockopt(sk_fds[i], SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &select_by_skb_data_prog, sizeof(select_by_skb_data_prog)); - CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", + "err:%d errno:%d\n", err, errno); } err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen); - CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (type == SOCK_STREAM) { err = listen(sk_fds[i], 10); - CHECK(err == -1, "listen()", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "listen()", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); } err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i], BPF_NOEXIST); - CHECK(err == -1, "update_elem(reuseport_array)", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "update_elem(reuseport_array)", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); if (i == first) { socklen_t addrlen = sizeof(srv_sa); err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa, &addrlen); - CHECK(err == -1, "getsockname()", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "getsockname()", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); } } epfd = epoll_create(1); - CHECK(epfd == -1, "epoll_create(1)", - "epfd:%d errno:%d\n", epfd, errno); + RET_IF(epfd == -1, "epoll_create(1)", + "epfd:%d errno:%d\n", epfd, errno); ev.events = EPOLLIN; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { ev.data.u32 = i; err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev); - CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); + RET_IF(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); } } -static void setup_per_test(int type, unsigned short family, bool inany) +static void setup_per_test(int type, sa_family_t family, bool inany, + bool no_inner_map) { int ovr = -1, err; prepare_sk_fds(type, family, inany); err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", + "err:%d errno:%d\n", err, errno); + + /* Install reuseport_array to outer_map? */ + if (no_inner_map) + return; + + err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array, + BPF_ANY); + RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)", + "err:%d errno:%d\n", err, errno); } -static void cleanup_per_test(void) +static void cleanup_per_test(bool no_inner_map) { - int i, err; + int i, err, zero = 0; + + memset(expected_results, 0, sizeof(expected_results)); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY); + RET_IF(err, "reset elem in result_map", + "i:%u err:%d errno:%d\n", i, err, errno); + } + + err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY); + RET_IF(err, "reset line number in linum_map", "err:%d errno:%d\n", + err, errno); for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) close(sk_fds[i]); close(epfd); + /* Delete reuseport_array from outer_map? */ + if (no_inner_map) + return; + err = bpf_map_delete_elem(outer_map, &index_zero); - CHECK(err == -1, "delete_elem(outer_map)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "delete_elem(outer_map)", + "err:%d errno:%d\n", err, errno); } static void cleanup(void) { - close(outer_map); - close(reuseport_array); - bpf_object__close(obj); + if (outer_map != -1) + close(outer_map); + if (reuseport_array != -1) + close(reuseport_array); + if (obj) + bpf_object__close(obj); } -static void test_all(void) +static const char *family_str(sa_family_t family) { - /* Extra SOCK_STREAM to test bind_inany==true */ - const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM }; - const char * const type_strings[] = { "TCP", "UDP", "TCP" }; - const char * const family_strings[] = { "IPv6", "IPv4" }; - const unsigned short families[] = { AF_INET6, AF_INET }; - const bool bind_inany[] = { false, false, true }; - int t, f, err; - - for (f = 0; f < ARRAY_SIZE(families); f++) { - unsigned short family = families[f]; - - for (t = 0; t < ARRAY_SIZE(types); t++) { - bool inany = bind_inany[t]; - int type = types[t]; - - printf("######## %s/%s %s ########\n", - family_strings[f], type_strings[t], - inany ? " INANY " : "LOOPBACK"); - - setup_per_test(type, family, inany); - - test_err_inner_map(type, family); - - /* Install reuseport_array to the outer_map */ - err = bpf_map_update_elem(outer_map, &index_zero, - &reuseport_array, BPF_ANY); - CHECK(err == -1, "update_elem(outer_map)", - "err:%d errno:%d\n", err, errno); - - test_err_skb_data(type, family); - test_err_sk_select_port(type, family); - test_pass(type, family); - test_syncookie(type, family); - test_pass_on_err(type, family); - /* Must be the last test */ - test_detach_bpf(type, family); - - cleanup_per_test(); - printf("\n"); - } + switch (family) { + case AF_INET: + return "IPv4"; + case AF_INET6: + return "IPv6"; + default: + return "unknown"; + } +} + +static const char *sotype_str(int sotype) +{ + switch (sotype) { + case SOCK_STREAM: + return "TCP"; + case SOCK_DGRAM: + return "UDP"; + default: + return "unknown"; } } -int main(int argc, const char **argv) +#define TEST_INIT(fn, ...) { fn, #fn, __VA_ARGS__ } + +static void test_config(int sotype, sa_family_t family, bool inany) { - create_maps(); - prepare_bpf_obj(); + const struct test { + void (*fn)(int sotype, sa_family_t family); + const char *name; + bool no_inner_map; + } tests[] = { + TEST_INIT(test_err_inner_map, true /* no_inner_map */), + TEST_INIT(test_err_skb_data), + TEST_INIT(test_err_sk_select_port), + TEST_INIT(test_pass), + TEST_INIT(test_syncookie), + TEST_INIT(test_pass_on_err), + TEST_INIT(test_detach_bpf), + }; + char s[MAX_TEST_NAME]; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s/%s %s %s", + family_str(family), sotype_str(sotype), + inany ? "INANY" : "LOOPBACK", t->name); + + if (!test__start_subtest(s)) + continue; + + setup_per_test(sotype, family, inany, t->no_inner_map); + t->fn(sotype, family); + cleanup_per_test(t->no_inner_map); + } +} + +#define BIND_INANY true + +static void test_all(void) +{ + const struct config { + int sotype; + sa_family_t family; + bool inany; + } configs[] = { + { SOCK_STREAM, AF_INET }, + { SOCK_STREAM, AF_INET, BIND_INANY }, + { SOCK_STREAM, AF_INET6 }, + { SOCK_STREAM, AF_INET6, BIND_INANY }, + { SOCK_DGRAM, AF_INET }, + { SOCK_DGRAM, AF_INET6 }, + }; + const struct config *c; + + for (c = configs; c < configs + ARRAY_SIZE(configs); c++) + test_config(c->sotype, c->family, c->inany); +} + +void test_select_reuseport(void) +{ + if (create_maps()) + goto out; + if (prepare_bpf_obj()) + goto out; + saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - enable_fastopen(); - disable_syncookie(); - atexit(restore_sysctls); + if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + goto out; - test_all(); + if (enable_fastopen()) + goto out; + if (disable_syncookie()) + goto out; + test_all(); +out: cleanup(); - return 0; + restore_sysctls(); } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index b607112c64e7..504abb7bfb95 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_send_signal_kern.skel.h" static volatile int sigusr1_received = 0; @@ -9,17 +10,15 @@ static void sigusr1_handler(int signum) } static void test_send_signal_common(struct perf_event_attr *attr, - int prog_type, + bool signal_thread, const char *test_name) { - int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd; - const char *file = "./test_send_signal_kern.o"; - struct bpf_object *obj = NULL; + struct test_send_signal_kern *skel; int pipe_c2p[2], pipe_p2c[2]; - __u32 key = 0, duration = 0; + int err = -1, pmu_fd = -1; + __u32 duration = 0; char buf[256]; pid_t pid; - __u64 val; if (CHECK(pipe(pipe_c2p), test_name, "pipe pipe_c2p error: %s\n", strerror(errno))) @@ -73,45 +72,39 @@ static void test_send_signal_common(struct perf_event_attr *attr, close(pipe_c2p[1]); /* close write */ close(pipe_p2c[0]); /* close read */ - err = bpf_prog_load(file, prog_type, &obj, &prog_fd); - if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n", - strerror(errno))) - goto prog_load_failure; - - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, - -1 /* group id */, 0 /* flags */); - if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n", - strerror(errno))) { - err = -1; - goto close_prog; - } + skel = test_send_signal_kern__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n")) + goto skel_open_load_failure; - err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n", - strerror(errno))) - goto disable_pmu; - - err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); - if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n", - strerror(errno))) - goto disable_pmu; - - err = -1; - info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map"); - if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map")) - goto disable_pmu; + if (!attr) { + err = test_send_signal_kern__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed\n")) { + err = -1; + goto destroy_skel; + } + } else { + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + -1 /* group id */, 0 /* flags */); + if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n", + strerror(errno))) { + err = -1; + goto destroy_skel; + } - status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map"); - if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map")) - goto disable_pmu; + skel->links.send_signal_perf = + bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd); + if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.send_signal_perf))) + goto disable_pmu; + } /* wait until child signal handler installed */ read(pipe_c2p[0], buf, 1); /* trigger the bpf send_signal */ - key = 0; - val = (((__u64)(SIGUSR1)) << 32) | pid; - bpf_map_update_elem(info_map_fd, &key, &val, 0); + skel->bss->pid = pid; + skel->bss->sig = SIGUSR1; + skel->bss->signal_thread = signal_thread; /* notify child that bpf program can send_signal now */ write(pipe_p2c[1], buf, 1); @@ -132,46 +125,20 @@ static void test_send_signal_common(struct perf_event_attr *attr, disable_pmu: close(pmu_fd); -close_prog: - bpf_object__close(obj); -prog_load_failure: +destroy_skel: + test_send_signal_kern__destroy(skel); +skel_open_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); wait(NULL); } -static void test_send_signal_tracepoint(void) +static void test_send_signal_tracepoint(bool signal_thread) { - const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id"; - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN, - .sample_period = 1, - .wakeup_events = 1, - }; - __u32 duration = 0; - int bytes, efd; - char buf[256]; - - efd = open(id_path, O_RDONLY, 0); - if (CHECK(efd < 0, "tracepoint", - "open syscalls/sys_enter_nanosleep/id failure: %s\n", - strerror(errno))) - return; - - bytes = read(efd, buf, sizeof(buf)); - close(efd); - if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint", - "read syscalls/sys_enter_nanosleep/id failure: %s\n", - strerror(errno))) - return; - - attr.config = strtol(buf, NULL, 0); - - test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); + test_send_signal_common(NULL, signal_thread, "tracepoint"); } -static void test_send_signal_perf(void) +static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { .sample_period = 1, @@ -179,15 +146,13 @@ static void test_send_signal_perf(void) .config = PERF_COUNT_SW_CPU_CLOCK, }; - test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_sw_event"); + test_send_signal_common(&attr, signal_thread, "perf_sw_event"); } -static void test_send_signal_nmi(void) +static void test_send_signal_nmi(bool signal_thread) { struct perf_event_attr attr = { - .sample_freq = 50, - .freq = 1, + .sample_period = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; @@ -210,16 +175,21 @@ static void test_send_signal_nmi(void) close(pmu_fd); } - test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_hw_event"); + test_send_signal_common(&attr, signal_thread, "perf_hw_event"); } void test_send_signal(void) { if (test__start_subtest("send_signal_tracepoint")) - test_send_signal_tracepoint(); + test_send_signal_tracepoint(false); if (test__start_subtest("send_signal_perf")) - test_send_signal_perf(); + test_send_signal_perf(false); if (test__start_subtest("send_signal_nmi")) - test_send_signal_nmi(); + test_send_signal_nmi(false); + if (test__start_subtest("send_signal_tracepoint_thread")) + test_send_signal_tracepoint(true); + if (test__start_subtest("send_signal_perf_thread")) + test_send_signal_perf(true); + if (test__start_subtest("send_signal_nmi_thread")) + test_send_signal_nmi(true); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index a2eb8db8dafb..c6d6b685a946 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,6 +11,9 @@ void test_skb_ctx(void) .cb[4] = 5, .priority = 6, .tstamp = 7, + .wire_len = 100, + .gso_segs = 8, + .mark = 9, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -91,4 +94,8 @@ void test_skb_ctx(void) "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", skb.tstamp, 8); + CHECK_ATTR(skb.mark != 10, + "ctx_out_mark", + "skb->mark == %u, expected %d\n", + skb.mark, 10); } diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c new file mode 100644 index 000000000000..9264a2736018 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> + +struct s { + int a; + long long b; +} __attribute__((packed)); + +#include "test_skeleton.skel.h" + +void test_skeleton(void) +{ + int duration = 0, err; + struct test_skeleton* skel; + struct test_skeleton__bss *bss; + struct test_skeleton__kconfig *kcfg; + + skel = test_skeleton__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + if (CHECK(skel->kconfig, "skel_kconfig", "kconfig is mmaped()!\n")) + goto cleanup; + + err = test_skeleton__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + bss = skel->bss; + bss->in1 = 1; + bss->in2 = 2; + bss->in3 = 3; + bss->in4 = 4; + bss->in5.a = 5; + bss->in5.b = 6; + kcfg = skel->kconfig; + + err = test_skeleton__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + CHECK(bss->out1 != 1, "res1", "got %d != exp %d\n", bss->out1, 1); + CHECK(bss->out2 != 2, "res2", "got %lld != exp %d\n", bss->out2, 2); + CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3); + CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4); + CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n", + bss->handler_out5.a, 5); + CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n", + bss->handler_out5.b, 6); + + CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1", + "got %d != exp %d\n", bss->bpf_syscall, kcfg->CONFIG_BPF_SYSCALL); + CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", + "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + +cleanup: + test_skeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c index d841dced971f..e8399ae50e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c @@ -1,16 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" void test_stacktrace_build_id(void) { + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, prog_fd, stack_trace_len; + struct test_stacktrace_build_id *skel; + int err, stack_trace_len; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -18,43 +16,24 @@ void test_stacktrace_build_id(void) int retry = 1; retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; - - link = bpf_program__attach_tracepoint(prog, "random", "urandom_read"); - if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link))) - goto close_prog; + err = test_stacktrace_build_id__attach(skel); + if (CHECK(err, "attach_tp", "err %d\n", err)) + goto cleanup; /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("./urandom_read"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -66,23 +45,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -90,7 +69,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -108,8 +87,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -117,17 +95,14 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; - stack_trace_len = PERF_MAX_STACK_DEPTH - * sizeof(struct bpf_stack_build_id); + stack_trace_len = PERF_MAX_STACK_DEPTH * + sizeof(struct bpf_stack_build_id); err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); CHECK(err, "compare_stack_ips stackmap vs. stack_amap", "err %d errno %d\n", err, errno); -disable_pmu: - bpf_link__destroy(link); - -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index f62aa0eb959b..f002e3090d92 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" static __u64 read_perf_max_sample_freq(void) { @@ -16,19 +17,15 @@ static __u64 read_perf_max_sample_freq(void) void test_stacktrace_build_id_nmi(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, pmu_fd, prog_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd; + struct test_stacktrace_build_id *skel; + int err, pmu_fd; struct perf_event_attr attr = { .freq = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -38,54 +35,46 @@ void test_stacktrace_build_id_nmi(void) attr.sample_freq = read_perf_max_sample_freq(); retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open(); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; + /* 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 (CHECK(pmu_fd < 0, "perf_event_open", - "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n", + if (pmu_fd < 0 && errno == ENOENT) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__); + test__skip(); + goto cleanup; + } + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, errno)) - goto close_prog; + goto cleanup; - link = bpf_program__attach_perf_event(prog, pmu_fd); - if (CHECK(IS_ERR(link), "attach_perf_event", - "err %ld\n", PTR_ERR(link))) { + 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 close_prog; + goto cleanup; } /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("taskset 0x1 ./urandom_read 100000"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -97,23 +86,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -121,7 +110,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -139,8 +128,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -148,7 +136,7 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; /* * We intentionally skip compare_stack_ips(). This is because we @@ -157,8 +145,6 @@ retry: * BPF_STACK_BUILD_ID_IP; */ -disable_pmu: - bpf_link__destroy(link); -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c new file mode 100644 index 000000000000..25b068591e9a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <test_progs.h> + +const char *err_str; +bool found; + +static int libbpf_debug_print(enum libbpf_print_level level, + const char *format, va_list args) +{ + char *log_buf; + + if (level != LIBBPF_WARN || + strcmp(format, "libbpf: \n%s\n")) { + vprintf(format, args); + return 0; + } + + log_buf = va_arg(args, char *); + if (!log_buf) + goto out; + if (strstr(log_buf, err_str) == 0) + found = true; +out: + printf(format, log_buf); + return 0; +} + +extern int extra_prog_load_log_flags; + +static int check_load(const char *file) +{ + struct bpf_prog_load_attr attr; + struct bpf_object *obj = NULL; + int err, prog_fd; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = BPF_PROG_TYPE_UNSPEC; + attr.log_level = extra_prog_load_log_flags; + attr.prog_flags = BPF_F_TEST_RND_HI32; + found = false; + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + bpf_object__close(obj); + return err; +} + +struct test_def { + const char *file; + const char *err_str; +}; + +void test_test_global_funcs(void) +{ + struct test_def tests[] = { + { "test_global_func1.o", "combined stack size of 4 calls is 544" }, + { "test_global_func2.o" }, + { "test_global_func3.o" , "the call stack of 8 frames" }, + { "test_global_func4.o" }, + { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, + { "test_global_func6.o" , "modified ctx ptr R2" }, + { "test_global_func7.o" , "foo() doesn't return scalar" }, + }; + libbpf_print_fn_t old_print_fn = NULL; + int err, i, duration = 0; + + old_print_fn = libbpf_set_print(libbpf_debug_print); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct test_def *test = &tests[i]; + + if (!test__start_subtest(test->file)) + continue; + + err_str = test->err_str; + err = check_load(test->file); + CHECK_FAIL(!!err ^ !!err_str); + if (err_str) + CHECK(found, "", "expected string '%s'", err_str); + } + libbpf_set_print(old_print_fn); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index c32aa28bd93f..465b371a561d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Facebook */ #define _GNU_SOURCE #include <sched.h> +#include <sys/prctl.h> #include <test_progs.h> #define MAX_CNT 100000 @@ -17,7 +18,7 @@ static __u64 time_get_ns(void) static int test_task_rename(const char *prog) { int i, fd, duration = 0, err; - char buf[] = "test\n"; + char buf[] = "test_overhead"; __u64 start_time; fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); @@ -66,6 +67,10 @@ void test_test_overhead(void) struct bpf_object *obj; struct bpf_link *link; int err, duration = 0; + char comm[16] = {}; + + if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L))) + return; obj = bpf_object__open_file("./test_overhead.o", NULL); if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) @@ -138,5 +143,6 @@ void test_test_overhead(void) test_run("fexit"); bpf_link__destroy(link); cleanup: + prctl(PR_SET_NAME, comm, 0L, 0L, 0L); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c new file mode 100644 index 000000000000..1235f3d1cc50 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE +#include <sched.h> +#include <sys/prctl.h> +#include <test_progs.h> + +#define MAX_TRAMP_PROGS 40 + +struct inst { + struct bpf_object *obj; + struct bpf_link *link_fentry; + struct bpf_link *link_fexit; +}; + +static int test_task_rename(void) +{ + int fd, duration = 0, err; + char buf[] = "test_overhead"; + + fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); + if (CHECK(fd < 0, "open /proc", "err %d", errno)) + return -1; + err = write(fd, buf, sizeof(buf)); + if (err < 0) { + CHECK(err < 0, "task rename", "err %d", errno); + close(fd); + return -1; + } + close(fd); + return 0; +} + +static struct bpf_link *load(struct bpf_object *obj, const char *name) +{ + struct bpf_program *prog; + int duration = 0; + + prog = bpf_object__find_program_by_title(obj, name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name)) + return ERR_PTR(-EINVAL); + return bpf_program__attach_trace(prog); +} + +void test_trampoline_count(void) +{ + const char *fentry_name = "fentry/__set_task_comm"; + const char *fexit_name = "fexit/__set_task_comm"; + const char *object = "test_trampoline_count.o"; + struct inst inst[MAX_TRAMP_PROGS] = { 0 }; + int err, i = 0, duration = 0; + struct bpf_object *obj; + struct bpf_link *link; + char comm[16] = {}; + + /* attach 'allowed' 40 trampoline programs */ + for (i = 0; i < MAX_TRAMP_PROGS; i++) { + obj = bpf_object__open_file(object, NULL); + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + goto cleanup; + + err = bpf_object__load(obj); + if (CHECK(err, "obj_load", "err %d\n", err)) + goto cleanup; + inst[i].obj = obj; + + if (rand() % 2) { + link = load(obj, fentry_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + goto cleanup; + inst[i].link_fentry = link; + } else { + link = load(obj, fexit_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + goto cleanup; + inst[i].link_fexit = link; + } + } + + /* and try 1 extra.. */ + obj = bpf_object__open_file(object, NULL); + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + goto cleanup; + + err = bpf_object__load(obj); + if (CHECK(err, "obj_load", "err %d\n", err)) + goto cleanup_extra; + + /* ..that needs to fail */ + link = load(obj, fentry_name); + if (CHECK(!IS_ERR(link), "cannot attach over the limit", "err %ld\n", PTR_ERR(link))) { + bpf_link__destroy(link); + goto cleanup_extra; + } + + /* with E2BIG error */ + CHECK(PTR_ERR(link) != -E2BIG, "proper error check", "err %ld\n", PTR_ERR(link)); + + /* and finaly execute the probe */ + if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L))) + goto cleanup_extra; + CHECK_FAIL(test_task_rename()); + CHECK_FAIL(prctl(PR_SET_NAME, comm, 0L, 0L, 0L)); + +cleanup_extra: + bpf_object__close(obj); +cleanup: + while (--i) { + bpf_link__destroy(inst[i].link_fentry); + bpf_link__destroy(inst[i].link_fexit); + bpf_object__close(inst[i].obj); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c new file mode 100644 index 000000000000..6b56bdc73ebc --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <net/if.h> +#include "test_xdp.skel.h" +#include "test_xdp_bpf2bpf.skel.h" + +void test_xdp_bpf2bpf(void) +{ + __u32 duration = 0, retval, size; + char buf[128]; + int err, pkt_fd, map_fd; + struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iptnl_info value4 = {.family = AF_INET}; + struct test_xdp *pkt_skel = NULL; + struct test_xdp_bpf2bpf *ftrace_skel = NULL; + struct vip key4 = {.protocol = 6, .family = AF_INET}; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + + /* Load XDP program to introspect */ + pkt_skel = test_xdp__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + return; + + pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); + + map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl); + bpf_map_update_elem(map_fd, &key4, &value4, 0); + + /* Load trace program */ + opts.attach_prog_fd = pkt_fd, + ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts); + if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + goto out; + + err = test_xdp_bpf2bpf__load(ftrace_skel); + if (CHECK(err, "__load", "ftrace skeleton failed\n")) + goto out; + + err = test_xdp_bpf2bpf__attach(ftrace_skel); + if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + goto out; + + /* Run test program */ + err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + if (CHECK(err || retval != XDP_TX || size != 74 || + iph->protocol != IPPROTO_IPIP, "ipv4", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size)) + goto out; + + /* Verify test results */ + if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), + "result", "fentry failed err %llu\n", + ftrace_skel->bss->test_result_fentry)) + goto out; + + CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", + "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); + +out: + test_xdp__destroy(pkt_skel); + test_xdp_bpf2bpf__destroy(ftrace_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c new file mode 100644 index 000000000000..7185bee16fe4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_xdp_perf(void) +{ + const char *file = "./xdp_dummy.o"; + __u32 duration, retval, size; + struct bpf_object *obj; + char in[128], out[128]; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, + out, &size, &retval, &duration); + + CHECK(err || retval != XDP_PASS || size != 128, + "xdp-perf", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c new file mode 100644 index 000000000000..7897c8f4d363 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_cubic.c. The purpose is mainly for testing + * the kernel BPF logic. + * + * Highlights: + * 1. CONFIG_HZ .kconfig map is used. + * 2. In bictcp_update(), calculation is changed to use usec + * resolution (i.e. USEC_PER_JIFFY) instead of using jiffies. + * Thus, usecs_to_jiffies() is not used in the bpf_cubic.c. + * 3. In bitctcp_update() [under tcp_friendliness], the original + * "while (ca->ack_cnt > delta)" loop is changed to the equivalent + * "ca->ack_cnt / delta" operation. + */ + +#include <linux/bpf.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) + +#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation + * max_cwnd = snd_cwnd * beta + */ +#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ + +/* Two methods of hybrid slow start */ +#define HYSTART_ACK_TRAIN 0x1 +#define HYSTART_DELAY 0x2 + +/* Number of delay samples for detecting the increase of delay */ +#define HYSTART_MIN_SAMPLES 8 +#define HYSTART_DELAY_MIN (4000U) /* 4ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ +#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) + +static int fast_convergence = 1; +static const int beta = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ +static int initial_ssthresh; +static const int bic_scale = 41; +static int tcp_friendliness = 1; + +static int hystart = 1; +static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY; +static int hystart_low_window = 16; +static int hystart_ack_delta_us = 2000; + +static const __u32 cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ +static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 + / (BICTCP_BETA_SCALE - beta); +/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 + * so K = cubic_root( (wmax-cwnd)*rtt/c ) + * the unit of K is bictcp_HZ=2^10, not HZ + * + * c = bic_scale >> 10 + * rtt = 100ms + * + * the following code has been designed and tested for + * cwnd < 1 million packets + * RTT < 100 seconds + * HZ < 1,000,00 (corresponding to 10 nano-second) + */ + +/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */ +static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ)) + / (bic_scale * 10); + +/* BIC TCP Parameters */ +struct bictcp { + __u32 cnt; /* increase cwnd by 1 after ACKs */ + __u32 last_max_cwnd; /* last maximum snd_cwnd */ + __u32 last_cwnd; /* the last snd_cwnd */ + __u32 last_time; /* time when updated last_cwnd */ + __u32 bic_origin_point;/* origin point of bic function */ + __u32 bic_K; /* time to origin point + from the beginning of the current epoch */ + __u32 delay_min; /* min delay (usec) */ + __u32 epoch_start; /* beginning of an epoch */ + __u32 ack_cnt; /* number of acks */ + __u32 tcp_cwnd; /* estimated tcp cwnd */ + __u16 unused; + __u8 sample_cnt; /* number of samples to decide curr_rtt */ + __u8 found; /* the exit point is found? */ + __u32 round_start; /* beginning of each round */ + __u32 end_seq; /* end_seq of the round */ + __u32 last_ack; /* last time when the ACK spacing is close */ + __u32 curr_rtt; /* the minimum rtt of current round */ +}; + +static inline void bictcp_reset(struct bictcp *ca) +{ + ca->cnt = 0; + ca->last_max_cwnd = 0; + ca->last_cwnd = 0; + ca->last_time = 0; + ca->bic_origin_point = 0; + ca->bic_K = 0; + ca->delay_min = 0; + ca->epoch_start = 0; + ca->ack_cnt = 0; + ca->tcp_cwnd = 0; + ca->found = 0; +} + +extern unsigned long CONFIG_HZ __kconfig; +#define HZ CONFIG_HZ +#define USEC_PER_MSEC 1000UL +#define USEC_PER_SEC 1000000UL +#define USEC_PER_JIFFY (USEC_PER_SEC / HZ) + +static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor) +{ + return dividend / divisor; +} + +#define div64_ul div64_u64 + +#define BITS_PER_U64 (sizeof(__u64) * 8) +static __always_inline int fls64(__u64 x) +{ + int num = BITS_PER_U64 - 1; + + if (x == 0) + return 0; + + if (!(x & (~0ull << (BITS_PER_U64-32)))) { + num -= 32; + x <<= 32; + } + if (!(x & (~0ull << (BITS_PER_U64-16)))) { + num -= 16; + x <<= 16; + } + if (!(x & (~0ull << (BITS_PER_U64-8)))) { + num -= 8; + x <<= 8; + } + if (!(x & (~0ull << (BITS_PER_U64-4)))) { + num -= 4; + x <<= 4; + } + if (!(x & (~0ull << (BITS_PER_U64-2)))) { + num -= 2; + x <<= 2; + } + if (!(x & (~0ull << (BITS_PER_U64-1)))) + num -= 1; + + return num + 1; +} + +static __always_inline __u32 bictcp_clock_us(const struct sock *sk) +{ + return tcp_sk(sk)->tcp_mstamp; +} + +static __always_inline void bictcp_hystart_reset(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->round_start = ca->last_ack = bictcp_clock_us(sk); + ca->end_seq = tp->snd_nxt; + ca->curr_rtt = ~0U; + ca->sample_cnt = 0; +} + +/* "struct_ops/" prefix is not a requirement + * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS + * as long as it is used in one of the func ptr + * under SEC(".struct_ops"). + */ +SEC("struct_ops/bictcp_init") +void BPF_PROG(bictcp_init, struct sock *sk) +{ + struct bictcp *ca = inet_csk_ca(sk); + + bictcp_reset(ca); + + if (hystart) + bictcp_hystart_reset(sk); + + if (!hystart && initial_ssthresh) + tcp_sk(sk)->snd_ssthresh = initial_ssthresh; +} + +/* No prefix in SEC will also work. + * The remaining tcp-cubic functions have an easier way. + */ +SEC("no-sec-prefix-bictcp_cwnd_event") +void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct bictcp *ca = inet_csk_ca(sk); + __u32 now = tcp_jiffies32; + __s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) { + ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } + return; + } +} + +/* + * cbrt(x) MSB values for x MSB values in [0..63]. + * Precomputed then refined by hand - Willy Tarreau + * + * For x in [0..63], + * v = cbrt(x << 18) - 1 + * cbrt(x) = (v[x] + 10) >> 6 + */ +static const __u8 v[] = { + /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, + /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, + /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, + /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, + /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, + /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, + /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, + /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, +}; + +/* calculate the cubic root of x using a table lookup followed by one + * Newton-Raphson iteration. + * Avg err ~= 0.195% + */ +static __always_inline __u32 cubic_root(__u64 a) +{ + __u32 x, b, shift; + + if (a < 64) { + /* a in [0..63] */ + return ((__u32)v[(__u32)a] + 35) >> 6; + } + + b = fls64(a); + b = ((b * 84) >> 8) - 1; + shift = (a >> (b * 3)); + + /* it is needed for verifier's bound check on v */ + if (shift >= 64) + return 0; + + x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6; + + /* + * Newton-Raphson iteration + * 2 + * x = ( 2 * x + a / x ) / 3 + * k+1 k k + */ + x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1))); + x = ((x * 341) >> 10); + return x; +} + +/* + * Compute congestion window to use. + */ +static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd, + __u32 acked) +{ + __u32 delta, bic_target, max_cnt; + __u64 offs, t; + + ca->ack_cnt += acked; /* count the number of ACKed packets */ + + if (ca->last_cwnd == cwnd && + (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) + return; + + /* The CUBIC function can update ca->cnt at most once per jiffy. + * On all cwnd reduction events, ca->epoch_start is set to 0, + * which will force a recalculation of ca->cnt. + */ + if (ca->epoch_start && tcp_jiffies32 == ca->last_time) + goto tcp_friendliness; + + ca->last_cwnd = cwnd; + ca->last_time = tcp_jiffies32; + + if (ca->epoch_start == 0) { + ca->epoch_start = tcp_jiffies32; /* record beginning */ + ca->ack_cnt = acked; /* start counting */ + ca->tcp_cwnd = cwnd; /* syn with cubic */ + + if (ca->last_max_cwnd <= cwnd) { + ca->bic_K = 0; + ca->bic_origin_point = cwnd; + } else { + /* Compute new K based on + * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) + */ + ca->bic_K = cubic_root(cube_factor + * (ca->last_max_cwnd - cwnd)); + ca->bic_origin_point = ca->last_max_cwnd; + } + } + + /* cubic function - calc*/ + /* calculate c * time^3 / rtt, + * while considering overflow in calculation of time^3 + * (so time^3 is done by using 64 bit) + * and without the support of division of 64bit numbers + * (so all divisions are done by using 32 bit) + * also NOTE the unit of those veriables + * time = (t - K) / 2^bictcp_HZ + * c = bic_scale >> 10 + * rtt = (srtt >> 3) / HZ + * !!! The following code does not have overflow problems, + * if the cwnd < 1 million packets !!! + */ + + t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY; + t += ca->delay_min; + /* change the unit from usec to bictcp_HZ */ + t <<= BICTCP_HZ; + t /= USEC_PER_SEC; + + if (t < ca->bic_K) /* t - K */ + offs = ca->bic_K - t; + else + offs = t - ca->bic_K; + + /* c/rtt * (t-K)^3 */ + delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); + if (t < ca->bic_K) /* below origin*/ + bic_target = ca->bic_origin_point - delta; + else /* above origin*/ + bic_target = ca->bic_origin_point + delta; + + /* cubic function - calc bictcp_cnt*/ + if (bic_target > cwnd) { + ca->cnt = cwnd / (bic_target - cwnd); + } else { + ca->cnt = 100 * cwnd; /* very small increment*/ + } + + /* + * The initial growth of cubic function may be too conservative + * when the available bandwidth is still unknown. + */ + if (ca->last_max_cwnd == 0 && ca->cnt > 20) + ca->cnt = 20; /* increase cwnd 5% per RTT */ + +tcp_friendliness: + /* TCP Friendly */ + if (tcp_friendliness) { + __u32 scale = beta_scale; + __u32 n; + + /* update tcp cwnd */ + delta = (cwnd * scale) >> 3; + if (ca->ack_cnt > delta && delta) { + n = ca->ack_cnt / delta; + ca->ack_cnt -= n * delta; + ca->tcp_cwnd += n; + } + + if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ + delta = ca->tcp_cwnd - cwnd; + max_cnt = cwnd / delta; + if (ca->cnt > max_cnt) + ca->cnt = max_cnt; + } + } + + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); +} + +/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */ +void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + if (tcp_in_slow_start(tp)) { + if (hystart && after(ack, ca->end_seq)) + bictcp_hystart_reset(sk); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + bictcp_update(ca, tp->snd_cwnd, acked); + tcp_cong_avoid_ai(tp, ca->cnt, acked); +} + +__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->epoch_start = 0; /* end of epoch */ + + /* Wmax and fast convergence */ + if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence) + ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta)) + / (2 * BICTCP_BETA_SCALE); + else + ca->last_max_cwnd = tp->snd_cwnd; + + return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); +} + +void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Loss) { + bictcp_reset(inet_csk_ca(sk)); + bictcp_hystart_reset(sk); + } +} + +#define GSO_MAX_SIZE 65536 + +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static __always_inline __u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = sk->sk_pacing_rate; + if (!rate) + return 0; + return min((__u64)USEC_PER_MSEC, + div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + +static __always_inline void hystart_update(struct sock *sk, __u32 delay) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 threshold; + + if (hystart_detect & HYSTART_ACK_TRAIN) { + __u32 now = bictcp_clock_us(sk); + + /* first detection parameter - ack-train detection */ + if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) { + ca->last_ack = now; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((__s32)(now - ca->round_start) > threshold) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } + + if (hystart_detect & HYSTART_DELAY) { + /* obtain the minimum delay of more than sampling packets */ + if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; + + ca->sample_cnt++; + } else { + if (ca->curr_rtt > ca->delay_min + + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } +} + +void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk, + const struct ack_sample *sample) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 delay; + + /* Some calls are for duplicates without timetamps */ + if (sample->rtt_us < 0) + return; + + /* Discard delay samples right after fast recovery */ + if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ) + return; + + delay = sample->rtt_us; + if (delay == 0) + delay = 1; + + /* first time call or link delay decreases */ + if (ca->delay_min == 0 || ca->delay_min > delay) + ca->delay_min = delay; + + /* hystart triggers when cwnd is larger than some threshold */ + if (!ca->found && tcp_in_slow_start(tp) && hystart && + tp->snd_cwnd >= hystart_low_window) + hystart_update(sk, delay); +} + +__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + return max(tp->snd_cwnd, tp->prior_cwnd); +} + +SEC(".struct_ops") +struct tcp_congestion_ops cubic = { + .init = (void *)bictcp_init, + .ssthresh = (void *)bictcp_recalc_ssthresh, + .cong_avoid = (void *)bictcp_cong_avoid, + .set_state = (void *)bictcp_state, + .undo_cwnd = (void *)tcp_reno_undo_cwnd, + .cwnd_event = (void *)bictcp_cwnd_event, + .pkts_acked = (void *)bictcp_acked, + .name = "bpf_cubic", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c new file mode 100644 index 000000000000..b631fb5032d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_dctcp.c. The purpose is mainly for testing + * the kernel BPF logic. + */ + +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define DCTCP_MAX_ALPHA 1024U + +struct dctcp { + __u32 old_delivered; + __u32 old_delivered_ce; + __u32 prior_rcv_nxt; + __u32 dctcp_alpha; + __u32 next_seq; + __u32 ce_state; + __u32 loss_cwnd; +}; + +static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */ +static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA; + +static __always_inline void dctcp_reset(const struct tcp_sock *tp, + struct dctcp *ca) +{ + ca->next_seq = tp->snd_nxt; + + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; +} + +SEC("struct_ops/dctcp_init") +void BPF_PROG(dctcp_init, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); + ca->loss_cwnd = 0; + ca->ce_state = 0; + + dctcp_reset(tp, ca); +} + +SEC("struct_ops/dctcp_ssthresh") +__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); +} + +SEC("struct_ops/dctcp_update_alpha") +void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + /* Expired RTT */ + if (!before(tp->snd_una, ca->next_seq)) { + __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; + __u32 alpha = ca->dctcp_alpha; + + /* alpha = (1 - g) * alpha + g * F */ + + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); + if (delivered_ce) { + __u32 delivered = tp->delivered - ca->old_delivered; + + /* If dctcp_shift_g == 1, a 32bit value would overflow + * after 8 M packets. + */ + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); + + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); + } + ca->dctcp_alpha = alpha; + dctcp_reset(tp, ca); + } +} + +static __always_inline void dctcp_react_to_loss(struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +SEC("struct_ops/dctcp_state") +void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state)) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ +} + +static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (ce_state == 1) + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + else + tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; +} + +/* Minimal DCTP CE state machine: + * + * S: 0 <- last pkt was non-CE + * 1 <- last pkt was CE + */ +static __always_inline +void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, + __u32 *prior_rcv_nxt, __u32 *ce_state) +{ + __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; + + if (*ce_state != new_ce_state) { + /* CE state has changed, force an immediate ACK to + * reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + dctcp_ece_ack_cwr(sk, *ce_state); + bpf_tcp_send_ack(sk, *prior_rcv_nxt); + } + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } + *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt; + *ce_state = new_ce_state; + dctcp_ece_ack_cwr(sk, new_ce_state); +} + +SEC("struct_ops/dctcp_cwnd_event") +void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev) +{ + struct dctcp *ca = inet_csk_ca(sk); + + switch (ev) { + case CA_EVENT_ECN_IS_CE: + case CA_EVENT_ECN_NO_CE: + dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); + break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; + default: + /* Don't care for the rest. */ + break; + } +} + +SEC("struct_ops/dctcp_cwnd_undo") +__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + +SEC("struct_ops/tcp_reno_cong_avoid") +void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + /* In "safe" area, increase. */ + if (tcp_in_slow_start(tp)) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + /* In dangerous area, increase slowly. */ + tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked); +} + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp_nouse = { + .init = (void *)dctcp_init, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp_nouse", +}; + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp = { + .init = (void *)dctcp_init, + .in_ack_event = (void *)dctcp_update_alpha, + .cwnd_event = (void *)dctcp_cwnd_event, + .ssthresh = (void *)dctcp_ssthresh, + .cong_avoid = (void *)tcp_reno_cong_avoid, + .undo_cwnd = (void *)dctcp_cwnd_undo, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 040a44206f29..9941f0ba471e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -16,8 +16,8 @@ #include <sys/socket.h> #include <linux/if_tunnel.h> #include <linux/mpls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; #define PROG(F) SEC(#F) int bpf_func_##F diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c new file mode 100644 index 000000000000..65eac371b061 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___equiv_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c new file mode 100644 index 000000000000..ecda2b545ac2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_bad_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c new file mode 100644 index 000000000000..fe1d01232c22 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___fixed_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 1fd244d35ba9..75085119c5bb 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -9,8 +9,8 @@ #include <linux/in6.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP4 0x7f000004U #define DST_REWRITE_IP4 0x7f000001U diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c index 26397ab7b3c7..506d0f81a375 100644 --- a/tools/testing/selftests/bpf/progs/connect6_prog.c +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c @@ -9,8 +9,8 @@ #include <linux/in6.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP6_0 0 #define SRC_REWRITE_IP6_1 0 diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 9311489e14b2..6d598cfbdb3e 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -327,6 +327,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f10c; }; struct core_reloc_arrays_substruct { @@ -339,6 +340,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; /* bigger array dimensions */ @@ -347,6 +349,7 @@ struct core_reloc_arrays___diff_arr_dim { char b[3][4][5]; struct core_reloc_arrays_substruct c[4]; struct core_reloc_arrays_substruct d[2][3]; + struct core_reloc_arrays_substruct f[1][3]; }; /* different size of array's value (struct) */ @@ -363,6 +366,29 @@ struct core_reloc_arrays___diff_arr_val_sz { int d; int __padding2; } d[1][2]; + struct { + int __padding1; + int c; + int __padding2; + } f[][2]; +}; + +struct core_reloc_arrays___equiv_zero_sz_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* equivalent to flexible array */ + struct core_reloc_arrays_substruct f[0][2]; +}; + +struct core_reloc_arrays___fixed_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* not a flexible array anymore, but within access bounds */ + struct core_reloc_arrays_substruct f[1][2]; }; struct core_reloc_arrays___err_too_small { @@ -370,6 +396,7 @@ struct core_reloc_arrays___err_too_small { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_too_shallow { @@ -377,6 +404,7 @@ struct core_reloc_arrays___err_too_shallow { char b[2][3]; /* this one lacks one dimension */ struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_non_array { @@ -384,6 +412,7 @@ struct core_reloc_arrays___err_non_array { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_wrong_val_type { @@ -391,6 +420,16 @@ struct core_reloc_arrays___err_wrong_val_type { char b[2][3][4]; int c[3]; /* value is not a struct */ struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_bad_zero_sz_arr { + /* zero-sized array, but not at the end */ + struct core_reloc_arrays_substruct f[0][2]; + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; }; /* diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c index ce41a3475f27..8924e06bdef0 100644 --- a/tools/testing/selftests/bpf/progs/dev_cgroup.c +++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c @@ -7,7 +7,7 @@ #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("cgroup/dev") int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx) diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 615f7c6bca77..38d3a82144ca 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -1,43 +1,46 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; __u64 test1_result = 0; -BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a) +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) { test1_result = a == 1; return 0; } __u64 test2_result = 0; -BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b) +SEC("fentry/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b) { test2_result = a == 2 && b == 3; return 0; } __u64 test3_result = 0; -BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c) +SEC("fentry/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c) { test3_result = a == 4 && b == 5 && c == 6; return 0; } __u64 test4_result = 0; -BPF_TRACE_4("fentry/bpf_fentry_test4", test4, - void *, a, char, b, int, c, __u64, d) +SEC("fentry/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d) { test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10; return 0; } __u64 test5_result = 0; -BPF_TRACE_5("fentry/bpf_fentry_test5", test5, - __u64, a, void *, b, short, c, int, d, __u64, e) +SEC("fentry/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e) { test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && e == 15; @@ -45,8 +48,8 @@ BPF_TRACE_5("fentry/bpf_fentry_test5", test5, } __u64 test6_result = 0; -BPF_TRACE_6("fentry/bpf_fentry_test6", test6, - __u64, a, void *, b, short, c, int, d, void *, e, __u64, f) +SEC("fentry/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) { test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && e == (void *)20 && f == 21; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 2d211ee98a1c..c329fccf9842 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <linux/stddef.h> +#include <linux/ipv6.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "bpf_trace_helpers.h" struct sk_buff { @@ -9,8 +12,8 @@ struct sk_buff { }; __u64 test_result = 0; -BPF_TRACE_2("fexit/test_pkt_access", test_main, - struct sk_buff *, skb, int, ret) +SEC("fexit/test_pkt_access") +int BPF_PROG(test_main, struct sk_buff *skb, int ret) { int len; @@ -24,8 +27,8 @@ BPF_TRACE_2("fexit/test_pkt_access", test_main, } __u64 test_result_subprog1 = 0; -BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1, - struct sk_buff *, skb, int, ret) +SEC("fexit/test_pkt_access_subprog1") +int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret) { int len; @@ -79,4 +82,73 @@ int test_subprog2(struct args_subprog2 *ctx) test_result_subprog2 = 1; return 0; } + +__u64 test_result_subprog3 = 0; +SEC("fexit/test_pkt_access_subprog3") +int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 74 * val || val != 3) + return 0; + test_result_subprog3 = 1; + return 0; +} + +__u64 test_get_skb_len = 0; +SEC("freplace/get_skb_len") +int new_get_skb_len(struct __sk_buff *skb) +{ + int len = skb->len; + + if (len != 74) + return 0; + test_get_skb_len = 1; + return 74; /* original get_skb_len() returns skb->len */ +} + +__u64 test_get_skb_ifindex = 0; +SEC("freplace/get_skb_ifindex") +int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ipv6hdr ip6, *ip6p; + int ifindex = skb->ifindex; + __u32 eth_proto; + __u32 nh_off; + + /* check that BPF extension can read packet via direct packet access */ + if (data + 14 + sizeof(ip6) > data_end) + return 0; + ip6p = data + 14; + + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + /* check that legacy packet access helper works too */ + if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0) + return 0; + ip6p = &ip6; + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + if (ifindex != 1 || val != 3 || var != 1) + return 0; + test_get_skb_ifindex = 1; + return 3; /* original get_skb_ifindex() returns val * ifindex * var */ +} + +volatile __u64 test_get_constant = 0; +SEC("freplace/get_constant") +int new_get_constant(long val) +{ + if (val != 123) + return 0; + test_get_constant = 1; + return test_get_constant; /* original get_constant() returns val - 122 */ +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c index ebc0ab7f0f5c..92f3fa47cf40 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" struct sk_buff { @@ -9,8 +9,9 @@ struct sk_buff { }; __u64 test_result = 0; -BPF_TRACE_2("fexit/test_pkt_md_access", test_main2, - struct sk_buff *, skb, int, ret) + +SEC("fexit/test_pkt_md_access") +int BPF_PROG(test_main2, struct sk_buff *skb, int ret) { int len; diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index 86db0d60fb6e..348109b9ea07 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -1,45 +1,47 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; __u64 test1_result = 0; -BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret) +SEC("fexit/bpf_fentry_test1") +int BPF_PROG(test1, int a, int ret) { test1_result = a == 1 && ret == 2; return 0; } __u64 test2_result = 0; -BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret) +SEC("fexit/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b, int ret) { test2_result = a == 2 && b == 3 && ret == 5; return 0; } __u64 test3_result = 0; -BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret) +SEC("fexit/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c, int ret) { test3_result = a == 4 && b == 5 && c == 6 && ret == 15; return 0; } __u64 test4_result = 0; -BPF_TRACE_5("fexit/bpf_fentry_test4", test4, - void *, a, char, b, int, c, __u64, d, int, ret) +SEC("fexit/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret) { - test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 && ret == 34; return 0; } __u64 test5_result = 0; -BPF_TRACE_6("fexit/bpf_fentry_test5", test5, - __u64, a, void *, b, short, c, int, d, __u64, e, int, ret) +SEC("fexit/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret) { test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && e == 15 && ret == 65; @@ -47,9 +49,8 @@ BPF_TRACE_6("fexit/bpf_fentry_test5", test5, } __u64 test6_result = 0; -BPF_TRACE_7("fexit/bpf_fentry_test6", test6, - __u64, a, void *, b, short, c, int, d, void *, e, __u64, f, - int, ret) +SEC("fexit/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) { test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && e == (void *)20 && f == 21 && ret == 111; diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c index 16c54ade6888..6b42db2fe391 100644 --- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 974d6f3bb319..8f48a909f079 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -2,8 +2,8 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <stdbool.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; @@ -57,8 +57,8 @@ struct meta { /* TRACE_EVENT(kfree_skb, * TP_PROTO(struct sk_buff *skb, void *location), */ -BPF_TRACE_2("tp_btf/kfree_skb", trace_kfree_skb, - struct sk_buff *, skb, void *, location) +SEC("tp_btf/kfree_skb") +int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location) { struct net_device *dev; struct callback_head *ptr; @@ -114,9 +114,9 @@ static volatile struct { bool fexit_test_ok; } result; -BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans, - struct sk_buff *, skb, struct net_device *, dev, - unsigned short, protocol) +SEC("fentry/eth_type_trans") +int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) { int len, ifindex; @@ -132,9 +132,9 @@ BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans, return 0; } -BPF_TRACE_3("fexit/eth_type_trans", fexit_eth_type_trans, - struct sk_buff *, skb, struct net_device *, dev, - unsigned short, protocol) +SEC("fexit/eth_type_trans") +int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) { int len, ifindex; diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c index 40ac722a9da5..50e66772c046 100644 --- a/tools/testing/selftests/bpf/progs/loop1.c +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c index bb80f29aa7f7..947bb7e988c2 100644 --- a/tools/testing/selftests/bpf/progs/loop2.c +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 2b9165a7afe1..76e93b31c14b 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c index 650859022771..b35337926d66 100644 --- a/tools/testing/selftests/bpf/progs/loop4.c +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c index 28d1d668f07c..913791923fa3 100644 --- a/tools/testing/selftests/bpf/progs/loop5.c +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define barrier() __asm__ __volatile__("": : :"memory") char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 38a997852cad..d071adf178bd 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -2,7 +2,7 @@ #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "netcnt_common.h" #define MAX_BPS (3 * 1024 * 1024) diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 71d383cc9b85..cc615b82b56e 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -6,7 +6,7 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define FUNCTION_NAME_LEN 64 #define FILE_NAME_LEN 128 @@ -154,7 +154,12 @@ struct { __uint(value_size, sizeof(long long) * 127); } stackmap SEC(".maps"); -static __always_inline int __on_event(struct pt_regs *ctx) +#ifdef GLOBAL_FUNC +__attribute__((noinline)) +#else +static __always_inline +#endif +int __on_event(struct bpf_raw_tracepoint_args *ctx) { uint64_t pid_tgid = bpf_get_current_pid_tgid(); pid_t pid = (pid_t)(pid_tgid >> 32); @@ -254,7 +259,7 @@ static __always_inline int __on_event(struct pt_regs *ctx) } SEC("raw_tracepoint/kfree_skb") -int on_event(struct pt_regs* ctx) +int on_event(struct bpf_raw_tracepoint_args* ctx) { int i, ret = 0; ret |= __on_event(ctx); diff --git a/tools/testing/selftests/bpf/progs/pyperf_global.c b/tools/testing/selftests/bpf/progs/pyperf_global.c new file mode 100644 index 000000000000..079e78a7562b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf_global.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define STACK_MAX_LEN 50 +#define GLOBAL_FUNC +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 0756303676ac..1612a32007b6 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") htab = { .type = BPF_MAP_TYPE_HASH, diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c index a91536b1c47e..092d9da536f3 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c @@ -5,8 +5,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ #define SRC2_IP4 0x00000000U diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index a68062820410..255a432bc163 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -5,8 +5,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP6_0 0 #define SRC_REWRITE_IP6_1 0 diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index e4440fdd94cb..0cb5656a22b0 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -4,8 +4,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct socket_cookie { __u64 cookie_key; diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 9390e0244259..a5c6d5903b22 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -1,6 +1,6 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index e80484d98a1a..fdb4bf4408fa 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -1,7 +1,7 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 433e23918a62..4797dc985064 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -1,6 +1,6 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index dede0fcd6102..c6d428a8d785 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 4afd2595c08e..9d8c212dde9f 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <netinet/in.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 1bafbb944e37..d5a5eeb5fb52 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -3,7 +3,7 @@ #include <netinet/in.h> #include <netinet/tcp.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 4bf16e0a1b0e..ad61b722a9de 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -8,7 +8,7 @@ #include <linux/ptrace.h> #include <linux/sched.h> #include <linux/types.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> typedef uint32_t pid_t; struct task_struct {}; diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 63531e1a9fa4..1f407e65ae52 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 21c85c477210..a093e739cf0e 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 1ecae198b8c1..cabda877cf0a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index 499388758119..f82075b47d7d 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index 49c64eb53f19..ce5450744fd4 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c index 2cf813a06b83..0cb3204ddb18 100644 --- a/tools/testing/selftests/bpf/progs/tcp_rtt.c +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c index 4cd5e860c903..b7fc85769bdc 100644 --- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c +++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c @@ -7,7 +7,7 @@ */ #include <linux/bpf.h> #include <linux/if_ether.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index 534621e38906..dd8fae6660ab 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -3,48 +3,38 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 4); - __type(key, int); - __type(value, int); -} results_map SEC(".maps"); +int kprobe_res = 0; +int kretprobe_res = 0; +int uprobe_res = 0; +int uretprobe_res = 0; SEC("kprobe/sys_nanosleep") -int handle_sys_nanosleep_entry(struct pt_regs *ctx) +int handle_kprobe(struct pt_regs *ctx) { - const int key = 0, value = 1; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kprobe_res = 1; return 0; } SEC("kretprobe/sys_nanosleep") -int handle_sys_getpid_return(struct pt_regs *ctx) +int handle_kretprobe(struct pt_regs *ctx) { - const int key = 1, value = 2; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kretprobe_res = 2; return 0; } SEC("uprobe/trigger_func") -int handle_uprobe_entry(struct pt_regs *ctx) +int handle_uprobe(struct pt_regs *ctx) { - const int key = 2, value = 3; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uprobe_res = 3; return 0; } SEC("uretprobe/trigger_func") -int handle_uprobe_return(struct pt_regs *ctx) +int handle_uretprobe(struct pt_regs *ctx) { - const int key = 3, value = 4; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uretprobe_res = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 62ad7e22105e..88b0566da13d 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_legacy.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index fb8d91a1dbe0..a924e53c8e9d 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_legacy.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 3f4422044759..983aedd1c072 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c new file mode 100644 index 000000000000..3ac3603ad53d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_extern.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdint.h> +#include <stdbool.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* non-existing BPF helper, to test dead code elimination */ +static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999; + +extern int LINUX_KERNEL_VERSION __kconfig; +extern bool CONFIG_BPF_SYSCALL __kconfig; /* strong */ +extern enum libbpf_tristate CONFIG_TRISTATE __kconfig __weak; +extern bool CONFIG_BOOL __kconfig __weak; +extern char CONFIG_CHAR __kconfig __weak; +extern uint16_t CONFIG_USHORT __kconfig __weak; +extern int CONFIG_INT __kconfig __weak; +extern uint64_t CONFIG_ULONG __kconfig __weak; +extern const char CONFIG_STR[8] __kconfig __weak; +extern uint64_t CONFIG_MISSING __kconfig __weak; + +uint64_t kern_ver = -1; +uint64_t bpf_syscall = -1; +uint64_t tristate_val = -1; +uint64_t bool_val = -1; +uint64_t char_val = -1; +uint64_t ushort_val = -1; +uint64_t int_val = -1; +uint64_t ulong_val = -1; +char str_val[8] = {-1, -1, -1, -1, -1, -1, -1, -1}; +uint64_t missing_val = -1; + +SEC("raw_tp/sys_enter") +int handle_sys_enter(struct pt_regs *ctx) +{ + int i; + + kern_ver = LINUX_KERNEL_VERSION; + bpf_syscall = CONFIG_BPF_SYSCALL; + tristate_val = CONFIG_TRISTATE; + bool_val = CONFIG_BOOL; + char_val = CONFIG_CHAR; + ushort_val = CONFIG_USHORT; + int_val = CONFIG_INT; + ulong_val = CONFIG_ULONG; + + for (i = 0; i < sizeof(CONFIG_STR); i++) { + str_val[i] = CONFIG_STR[i]; + } + + if (CONFIG_MISSING) + /* invalid, but dead code - never executed */ + missing_val = bpf_missing_helper(ctx, 123); + else + missing_val = 0xDEADC0DE; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c index 89951b684282..51b3f79df523 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; @@ -18,6 +18,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f01c; }; struct core_reloc_arrays_substruct { @@ -30,6 +31,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; #define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) @@ -40,18 +42,16 @@ int test_core_arrays(void *ctx) struct core_reloc_arrays *in = (void *)&data.in; struct core_reloc_arrays_output *out = (void *)&data.out; - /* in->a[2] */ if (CORE_READ(&out->a2, &in->a[2])) return 1; - /* in->b[1][2][3] */ if (CORE_READ(&out->b123, &in->b[1][2][3])) return 1; - /* in->c[1].c */ if (CORE_READ(&out->c1c, &in->c[1].c)) return 1; - /* in->d[0][0].d */ if (CORE_READ(&out->d00d, &in->d[0][0].d)) return 1; + if (CORE_READ(&out->f01c, &in->f[0][1].c)) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c index edc0f7c9e56d..56aec20212b5 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c index 6c20e433558b..ab1e647aeb31 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c index 1b7f0ae49cfb..7e45e2bdf6cd 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c index b5dbeef540fd..525acc2f841b 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c index c78ab6d28a14..6b5290739806 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c index 270de441b60a..aba928fd60d3 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c index 292a5c4ee76a..d5756dbdef82 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c index 0b28bfacc8fd..8b533db4a7a5 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c index 39279bf0c9db..2b4b6d49c677 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c index ea57973cdd19..2a8975678aa6 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c index d1eb59d4ea64..ca61a5183b88 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c index 9e091124d3bd..d7fb6cfc7891 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> 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 6a4a8f57f174..29817a703984 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* Permit pretty deep stack traces */ #define MAX_STACK_RAWTP 100 diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 32a6073acb99..dd7a4d3dbc0d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -5,7 +5,7 @@ #include <linux/pkt_cls.h> #include <string.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c new file mode 100644 index 000000000000..880260f6d536 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#ifndef MAX_STACK +#define MAX_STACK (512 - 3 * 32 + 8) +#endif + +static __attribute__ ((noinline)) +int f0(int var, struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + return f0(0, skb) + skb->len; +} + +int f3(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb, 1); +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->ifindex * val * var; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c new file mode 100644 index 000000000000..2c18d82923a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func2.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#define MAX_STACK (512 - 3 * 32) +#include "test_global_func1.c" diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c new file mode 100644 index 000000000000..86f0ecb304fc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + val; +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + return f2(var, skb) + val; +} + +__attribute__ ((noinline)) +int f4(struct __sk_buff *skb) +{ + return f3(1, skb, 2); +} + +__attribute__ ((noinline)) +int f5(struct __sk_buff *skb) +{ + return f4(skb); +} + +__attribute__ ((noinline)) +int f6(struct __sk_buff *skb) +{ + return f5(skb); +} + +__attribute__ ((noinline)) +int f7(struct __sk_buff *skb) +{ + return f6(skb); +} + +#ifndef NO_FN8 +__attribute__ ((noinline)) +int f8(struct __sk_buff *skb) +{ + return f7(skb); +} +#endif + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ +#ifndef NO_FN8 + return f8(skb); +#else + return f7(skb); +#endif +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c new file mode 100644 index 000000000000..610f75edf276 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func4.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#define NO_FN8 +#include "test_global_func3.c" diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c new file mode 100644 index 000000000000..260c25b827ef --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, (void *)&val); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c new file mode 100644 index 000000000000..69e19c64e10b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb + 1); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c new file mode 100644 index 000000000000..309b3f6136bd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +void foo(struct __sk_buff *skb) +{ + skb->tc_index = 0; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + foo(skb); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1d652ee8e73d..33493911d87a 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -17,9 +17,9 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "test_iptunnel_common.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index 2e4efe70b1e5..28351936a438 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -13,9 +13,9 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "test_iptunnel_common.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c index 4147130cc3b7..7a6620671a83 100644 --- a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c +++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <linux/lirc.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("lirc_mode2") int bpf_decoder(unsigned int *sample) diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c index c957d6dfe6d7..d6cb986e7533 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c @@ -4,8 +4,8 @@ #include <linux/bpf.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct grehdr { __be16 flags; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index 41a3ebcd593d..48ff2b2ad5e7 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -3,8 +3,8 @@ #include <errno.h> #include <linux/seg6_local.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 113226115365..1cfeb940cf9f 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -3,7 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <linux/types.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index bb7ce35f691b..b5c07ae7b68f 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -2,7 +2,7 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define VAR_NUM 16 diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c index e808791b7047..6239596cd14e 100644 --- a/tools/testing/selftests/bpf/progs/test_mmap.c +++ b/tools/testing/selftests/bpf/progs/test_mmap.c @@ -3,7 +3,7 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c index 3d30c02bdae9..98b9de2fafd0 100644 --- a/tools/testing/selftests/bpf/progs/test_obj_id.c +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c @@ -4,7 +4,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* It is a dumb bpf program such that it must have no * issue to be loaded since testing the verifier is diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 96c0124a04ba..bfe9fbcb9684 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -1,39 +1,45 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <stdbool.h> +#include <stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <linux/ptrace.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_trace_helpers.h" +struct task_struct; + SEC("kprobe/__set_task_comm") -int prog1(struct pt_regs *ctx) +int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } SEC("kretprobe/__set_task_comm") -int prog2(struct pt_regs *ctx) +int BPF_KRETPROBE(prog2, + struct task_struct *tsk, const char *buf, bool exec, + int ret) { - return 0; + return !PT_REGS_PARM1(ctx) && ret; } SEC("raw_tp/task_rename") int prog3(struct bpf_raw_tracepoint_args *ctx) { - return 0; + return !ctx->args[0]; } -struct task_struct; -BPF_TRACE_3("fentry/__set_task_comm", prog4, - struct task_struct *, tsk, const char *, buf, __u8, exec) +SEC("fentry/__set_task_comm") +int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } -BPF_TRACE_3("fexit/__set_task_comm", prog5, - struct task_struct *, tsk, const char *, buf, __u8, exec) +SEC("fexit/__set_task_comm") +int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } 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 07c09ca5546a..ebfcc9f50c35 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -3,7 +3,8 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -12,7 +13,7 @@ struct { } perf_buf_map SEC(".maps"); SEC("kprobe/sys_nanosleep") -int handle_sys_nanosleep_entry(struct pt_regs *ctx) +int BPF_KPROBE(handle_sys_nanosleep_entry) { int cpu = bpf_get_smp_processor_id(); diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c index f20e7e00373f..4ef2630292b2 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning.c +++ b/tools/testing/selftests/bpf/progs/test_pinning.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c index 51b38abe7ba1..5412e0c732c7 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 3a7b4b607ed3..e72eba4a93d2 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -11,8 +11,8 @@ #include <linux/in.h> #include <linux/tcp.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define barrier() __asm__ __volatile__("": : :"memory") int _version SEC("version") = 1; @@ -47,6 +47,38 @@ int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb) return skb->len * val; } +#define MAX_STACK (512 - 2 * 32) + +__attribute__ ((noinline)) +int get_skb_len(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->len; +} + +__attribute__ ((noinline)) +int get_constant(long val) +{ + return val - 122; +} + +int get_skb_ifindex(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int test_pkt_access_subprog3(int val, struct __sk_buff *skb) +{ + return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); +} + +__attribute__ ((noinline)) +int get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->ifindex * val * var; +} + SEC("classifier/test_pkt_access") int test_pkt_access(struct __sk_buff *skb) { @@ -82,6 +114,8 @@ int test_pkt_access(struct __sk_buff *skb) return TC_ACT_SHOT; if (test_pkt_access_subprog2(2, skb) != skb->len * 2) return TC_ACT_SHOT; + if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) + return TC_ACT_SHOT; if (tcp) { if (((void *)(tcp) + 20) > data_end || proto != 6) return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 1db2623021ad..610c74ea9f64 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -5,7 +5,7 @@ #include <string.h> #include <linux/bpf.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 1871e2ece0c4..d556b1572cc6 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -5,13 +5,14 @@ #include <netinet/in.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_trace_helpers.h" static struct sockaddr_in old; SEC("kprobe/__sys_connect") -int handle_sys_connect(struct pt_regs *ctx) +int BPF_KPROBE(handle_sys_connect) { void *ptr = (void *)PT_REGS_PARM2(ctx); struct sockaddr_in new; diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h index 0e014d3b2b36..4dd9806ad73b 100644 --- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h +++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h @@ -6,7 +6,7 @@ #include <linux/if_ether.h> #include <linux/ip.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index 52d94e8b214d..ecbeea2df259 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -3,7 +3,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> static volatile const struct { unsigned a[4]; diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index 69880c1e7700..a7278f064368 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -3,8 +3,8 @@ #include <errno.h> #include <linux/seg6_local.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index ea7d84f01235..26e77dcc7e91 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -11,8 +11,8 @@ #include <linux/types.h> #include <linux/if_ether.h> -#include "bpf_endian.h" -#include "bpf_helpers.h" +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> #include "test_select_reuseport_common.h" int _version SEC("version") = 1; @@ -62,7 +62,7 @@ struct { goto done; \ }) -SEC("select_by_skb_data") +SEC("sk_reuseport") int _select_by_skb_data(struct sk_reuseport_md *reuse_md) { __u32 linum, index = 0, flags = 0, index_zero = 0; @@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reuseport_md *reuse_md) data_check.skb_ports[0] = th->source; data_check.skb_ports[1] = th->dest; + if (th->fin) + /* The connection is being torn down at the end of a + * test. It can't contain a cmd, so return early. + */ + return SK_PASS; + if ((th->doff << 2) + sizeof(*cmd) > data_check.len) GOTO_DONE(DROP_ERR_SKB_DATA); if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy, diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index 0e6be01157e6..1acc91e87bfc 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -2,46 +2,39 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __type(value, __u64); -} info_map SEC(".maps"); - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __type(value, __u64); -} status_map SEC(".maps"); - -SEC("send_signal_demo") -int bpf_send_signal_test(void *ctx) +#include <bpf/bpf_helpers.h> + +__u32 sig = 0, pid = 0, status = 0, signal_thread = 0; + +static __always_inline int bpf_send_signal_test(void *ctx) { - __u64 *info_val, *status_val; - __u32 key = 0, pid, sig; int ret; - status_val = bpf_map_lookup_elem(&status_map, &key); - if (!status_val || *status_val != 0) - return 0; - - info_val = bpf_map_lookup_elem(&info_map, &key); - if (!info_val || *info_val == 0) + if (status != 0 || sig == 0 || pid == 0) return 0; - sig = *info_val >> 32; - pid = *info_val & 0xffffFFFF; - if ((bpf_get_current_pid_tgid() >> 32) == pid) { - ret = bpf_send_signal(sig); + if (signal_thread) + ret = bpf_send_signal_thread(sig); + else + ret = bpf_send_signal(sig); if (ret == 0) - *status_val = 1; + status = 1; } return 0; } + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int send_signal_tp(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + +SEC("perf_event") +int send_signal_perf(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index cb49ccb707d1..d2b38fa6a5b0 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -12,8 +12,8 @@ #include <linux/pkt_cls.h> #include <linux/tcp.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index 68cf9829f5a7..552f2090665c 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -6,7 +6,7 @@ #include <string.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define NUM_CGROUP_LEVELS 4 diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index 2a9f4c736ebc..202de3938494 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; @@ -17,6 +17,12 @@ int process(struct __sk_buff *skb) } skb->priority++; skb->tstamp++; + skb->mark++; + + if (skb->wire_len != 100) + return 1; + if (skb->gso_segs != 8) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c new file mode 100644 index 000000000000..de03a90f78ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct s { + int a; + long long b; +} __attribute__((packed)); + +int in1 = 0; +long long in2 = 0; +char in3 = '\0'; +long long in4 __attribute__((aligned(64))) = 0; +struct s in5 = {}; + +long long out2 = 0; +char out3 = 0; +long long out4 = 0; +int out1 = 0; + +extern bool CONFIG_BPF_SYSCALL __kconfig; +extern int LINUX_KERNEL_VERSION __kconfig; +bool bpf_syscall = 0; +int kern_ver = 0; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + static volatile struct s out5; + + out1 = in1; + out2 = in2; + out3 = in3; + out4 = in4; + out5 = in5; + + bpf_syscall = CONFIG_BPF_SYSCALL; + kern_ver = LINUX_KERNEL_VERSION; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index a47b003623ef..9bcaa37f476a 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -5,8 +5,8 @@ #include <netinet/in.h> #include <stdbool.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> enum bpf_addr_array_idx { ADDR_SRV_IDX, diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index a43b999c8da2..0d31a3b3505f 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -2,7 +2,7 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct hmap_elem { volatile int cnt; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index f5638e26865d..0cf0134631b4 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH #define PERF_MAX_STACK_DEPTH 127 diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 3b7e1dca8829..00ed48672620 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH #define PERF_MAX_STACK_DEPTH 127 diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c index d22e438198cf..458b0d69133e 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c index cb201cbe11e7..b2e6f9b0894d 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index 5cbbff416998..2d0b0b82a78a 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ #define MAX_ULONG_STR_LEN 0xF diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index 0961415ba477..bf28814bfde5 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -7,8 +7,8 @@ #include <linux/ip.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* the maximum delay we are willing to add (drop packets beyond that) */ #define TIME_HORIZON_NS (2000 * 1000 * 1000) diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index 74370e7e286d..37bce7a7c394 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -17,8 +17,8 @@ #include <linux/pkt_cls.h> #include <linux/types.h> -#include "bpf_endian.h" -#include "bpf_helpers.h" +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> static const int cfg_port = 8000; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index d8803dfa8d32..47cbe2eeae43 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -13,8 +13,8 @@ #include <sys/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct bpf_map_def SEC("maps") results = { .type = BPF_MAP_TYPE_ARRAY, diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index 87b7d934ce73..adc83a54c352 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -36,7 +36,7 @@ #include <linux/ipv6.h> #include <linux/version.h> #include <sys/socket.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;}) #define TCP_ESTATS_MAGIC 0xBAADBEEF diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 7fa4595d2b66..1f1966e86e9f 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -10,8 +10,8 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_tcpbpf.h" struct { diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index 08346e7765d5..ac63410bb541 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -10,8 +10,8 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_tcpnotify.h" struct { diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index 04bf084517e0..4b825ee122cf 100644 --- a/tools/testing/selftests/bpf/progs/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -2,7 +2,7 @@ // Copyright (c) 2017 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c new file mode 100644 index 000000000000..e51e6e3a81c2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdbool.h> +#include <stddef.h> +#include <linux/bpf.h> +#include "bpf_trace_helpers.h" + +struct task_struct; + +SEC("fentry/__set_task_comm") +int BPF_PROG(prog1, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +SEC("fexit/__set_task_comm") +int BPF_PROG(prog2, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 504df69c83df..f48dbfe24ddc 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -19,8 +19,8 @@ #include <linux/socket.h> #include <linux/pkt_cls.h> #include <linux/erspan.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define ERROR(ret) do {\ char fmt[] = "ERROR line:%d ret:%d\n";\ diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c index f3236ce35f31..d38153dab3dd 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale1.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __attribute__((noinline)) #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c index 9897150ed516..f024154c7be7 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __always_inline #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c index 1848da04ea41..9beb5bf80373 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale3.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __attribute__((noinline)) #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 0941c655b07b..31f9bce37491 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -16,8 +16,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_iptunnel_common.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c new file mode 100644 index 000000000000..cb8a04ab7a78 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" + +struct net_device { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + int ifindex; +} __attribute__((preserve_access_index)); + +struct xdp_rxq_info { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + struct net_device *dev; + __u32 queue_index; +} __attribute__((preserve_access_index)); + +struct xdp_buff { + void *data; + void *data_end; + void *data_meta; + void *data_hard_start; + unsigned long handle; + struct xdp_rxq_info *rxq; +} __attribute__((preserve_access_index)); + +__u64 test_result_fentry = 0; +SEC("fentry/_xdp_tx_iptunnel") +int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) +{ + test_result_fentry = xdp->rxq->dev->ifindex; + return 0; +} + +__u64 test_result_fexit = 0; +SEC("fexit/_xdp_tx_iptunnel") +int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret) +{ + test_result_fexit = ret; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index 97175f73c3fe..fcabcda30ba3 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -12,8 +12,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_iptunnel_common.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index 8d0182650653..a7c4a7d49fe6 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -2,7 +2,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define __round_mask(x, y) ((__typeof__(x))((y) - 1)) #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index e88d7b9d65ab..8beecec166d9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -13,8 +13,8 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> static __u32 rol32(__u32 word, unsigned int shift) { @@ -86,7 +86,7 @@ u32 jhash(const void *key, u32 length, u32 initval) return c; } -static __attribute__ ((noinline)) +__attribute__ ((noinline)) u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; @@ -96,7 +96,7 @@ u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) return c; } -static __attribute__ ((noinline)) +__attribute__ ((noinline)) u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c index ef9e704be140..a5337cd9400b 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c @@ -10,7 +10,7 @@ * General Public License for more details. */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index 365a7d2d9f5c..134768f6b788 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -22,8 +22,8 @@ #include <linux/in.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here * diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index 43b0ef1001ed..ea25e8881992 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -2,7 +2,7 @@ #define KBUILD_MODNAME "xdp_dummy" #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("xdp_dummy") int xdp_dummy_prog(struct xdp_md *ctx) diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c index 1c5f298d7196..d037262c8937 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_DEVMAP); diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c index 57912e7c94b0..94e6c2b281cb 100644 --- a/tools/testing/selftests/bpf/progs/xdp_tx.c +++ b/tools/testing/selftests/bpf/progs/xdp_tx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("tx") int xdp_tx(struct xdp_md *xdp) diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 112a2857f4e2..6b9ca40bd1f4 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -12,8 +12,8 @@ #include <linux/if_vlan.h> #include <linux/ip.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "xdping.h" diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 3d617e806054..93040ca83e60 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4148,10 +4148,6 @@ static int do_test_file(unsigned int test_num) if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj))) return PTR_ERR(obj); - err = bpf_object__btf_fd(obj); - if (CHECK(err == -1, "bpf_object__btf_fd: -1")) - goto done; - prog = bpf_program__next(NULL, obj); if (CHECK(!prog, "Cannot find bpf_prog")) { err = -1; diff --git a/tools/testing/selftests/bpf/test_cgroup_attach.c b/tools/testing/selftests/bpf/test_cgroup_attach.c deleted file mode 100644 index 7671909ee1cb..000000000000 --- a/tools/testing/selftests/bpf/test_cgroup_attach.c +++ /dev/null @@ -1,571 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* eBPF example program: - * - * - Creates arraymap in kernel with 4 bytes keys and 8 byte values - * - * - Loads eBPF program - * - * The eBPF program accesses the map passed in to store two pieces of - * information. The number of invocations of the program, which maps - * to the number of packets received, is stored to key 0. Key 1 is - * incremented on each iteration by the number of bytes stored in - * the skb. The program also stores the number of received bytes - * in the cgroup storage. - * - * - Attaches the new program to a cgroup using BPF_PROG_ATTACH - * - * - Every second, reads map[0] and map[1] to see how many bytes and - * packets were seen on any socket of tasks in the given cgroup. - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <assert.h> -#include <sys/resource.h> -#include <sys/time.h> -#include <unistd.h> -#include <linux/filter.h> - -#include <linux/bpf.h> -#include <bpf/bpf.h> - -#include "bpf_util.h" -#include "bpf_rlimit.h" -#include "cgroup_helpers.h" - -#define FOO "/foo" -#define BAR "/foo/bar/" -#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -#ifdef DEBUG -#define debug(args...) printf(args) -#else -#define debug(args...) -#endif - -static int prog_load(int verdict) -{ - int ret; - struct bpf_insn prog[] = { - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - return ret; -} - -static int test_foo_bar(void) -{ - int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0; - - allow_prog = prog_load(1); - if (!allow_prog) - goto err; - - drop_prog = prog_load(0); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - /* Create cgroup /foo, get fd, and join it */ - foo = create_and_get_cgroup(FOO); - if (foo < 0) - goto err; - - if (join_cgroup(FOO)) - goto err; - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo"); - goto err; - } - - debug("Attached DROP prog. This ping in cgroup /foo should fail...\n"); - assert(system(PING_CMD) != 0); - - /* Create cgroup /foo/bar, get fd, and join it */ - bar = create_and_get_cgroup(BAR); - if (bar < 0) - goto err; - - if (join_cgroup(BAR)) - goto err; - - debug("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - debug("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - debug("Detached PASS from /foo/bar while DROP is attached to /foo.\n" - "This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo"); - goto err; - } - - debug("Attached PASS from /foo/bar and detached DROP from /foo.\n" - "This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - errno = 0; - log_err("Unexpected success in double detach from /foo"); - goto err; - } - - if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching non-overridable prog to /foo"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching non-overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo"); - goto err; - } - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching different non-overridable prog to /foo"); - goto err; - } - - goto out; - -err: - rc = 1; - -out: - close(foo); - close(bar); - cleanup_cgroup_environment(); - if (!rc) - printf("#override:PASS\n"); - else - printf("#override:FAIL\n"); - return rc; -} - -static int map_fd = -1; - -static int prog_load_cnt(int verdict, int val) -{ - int cgroup_storage_fd, percpu_cgroup_storage_fd; - - if (map_fd < 0) - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (map_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - percpu_cgroup_storage_fd = bpf_create_map( - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (percpu_cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - struct bpf_insn prog[] = { - BPF_MOV32_IMM(BPF_REG_0, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ - BPF_LD_MAP_FD(BPF_REG_1, map_fd), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ - - BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_MOV64_IMM(BPF_REG_1, val), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), - - BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), - BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), - - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - int ret; - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - close(cgroup_storage_fd); - return ret; -} - - -static int test_multiprog(void) -{ - __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; - int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; - int drop_prog, allow_prog[6] = {}, rc = 0; - unsigned long long value; - int i = 0; - - for (i = 0; i < 6; i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - drop_prog = prog_load_cnt(0, 1); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - cg1 = create_and_get_cgroup("/cg1"); - if (cg1 < 0) - goto err; - cg2 = create_and_get_cgroup("/cg1/cg2"); - if (cg2 < 0) - goto err; - cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); - if (cg3 < 0) - goto err; - cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); - if (cg4 < 0) - goto err; - cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); - if (cg5 < 0) - goto err; - - if (join_cgroup("/cg1/cg2/cg3/cg4/cg5")) - goto err; - - if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg1"); - goto err; - } - if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Unexpected success attaching the same prog to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog2 to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg2"); - goto err; - } - if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg3"); - goto err; - } - if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg4"); - goto err; - } - if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching prog to cg5"); - goto err; - } - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 32); - - /* query the number of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - NULL, NULL, &prog_cnt) == 0); - assert(prog_cnt == 4); - /* retrieve prog_ids of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 4); - assert(attach_flags == 0); - saved_prog_id = prog_ids[0]; - /* check enospc handling */ - prog_ids[0] = 0; - prog_cnt = 2; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == -1 && - errno == ENOSPC); - assert(prog_cnt == 4); - /* check that prog_ids are returned even when buffer is too small */ - assert(prog_ids[0] == saved_prog_id); - /* retrieve prog_id of single attached prog in cg5 */ - prog_ids[0] = 0; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 1); - assert(prog_ids[0] == saved_prog_id); - - /* detach bottom program and ping again */ - if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg5"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 16); - - /* detach 3rd from bottom program and ping again */ - errno = 0; - if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Unexpected success on detach from cg3"); - goto err; - } - if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching from cg3"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 16); - - /* detach 2nd from bottom program and ping again */ - if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg4"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 4); - - prog_cnt = 4; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 3); - assert(attach_flags == 0); - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 0); - goto out; -err: - rc = 1; - -out: - for (i = 0; i < 6; i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - close(cg1); - close(cg2); - close(cg3); - close(cg4); - close(cg5); - cleanup_cgroup_environment(); - if (!rc) - printf("#multi:PASS\n"); - else - printf("#multi:FAIL\n"); - return rc; -} - -static int test_autodetach(void) -{ - __u32 prog_cnt = 4, attach_flags; - int allow_prog[2] = {0}; - __u32 prog_ids[2] = {0}; - int cg = 0, i, rc = -1; - void *ptr = NULL; - int attempts; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - - if (setup_cgroup_environment()) - goto err; - - /* create a cgroup, attach two programs and remember their ids */ - cg = create_and_get_cgroup("/cg_autodetach"); - if (cg < 0) - goto err; - - if (join_cgroup("/cg_autodetach")) - goto err; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - if (bpf_prog_attach(allow_prog[i], cg, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog[%d] to cg:egress", i); - goto err; - } - } - - /* make sure that programs are attached and run some traffic */ - assert(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, - prog_ids, &prog_cnt) == 0); - assert(system(PING_CMD) == 0); - - /* allocate some memory (4Mb) to pin the original cgroup */ - ptr = malloc(4 * (1 << 20)); - if (!ptr) - goto err; - - /* close programs and cgroup fd */ - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - close(allow_prog[i]); - allow_prog[i] = 0; - } - - close(cg); - cg = 0; - - /* leave the cgroup and remove it. don't detach programs */ - cleanup_cgroup_environment(); - - /* wait for the asynchronous auto-detachment. - * wait for no more than 5 sec and give up. - */ - for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { - for (attempts = 5; attempts >= 0; attempts--) { - int fd = bpf_prog_get_fd_by_id(prog_ids[i]); - - if (fd < 0) - break; - - /* don't leave the fd open */ - close(fd); - - if (!attempts) - goto err; - - sleep(1); - } - } - - rc = 0; -err: - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - if (cg) - close(cg); - free(ptr); - cleanup_cgroup_environment(); - if (!rc) - printf("#autodetach:PASS\n"); - else - printf("#autodetach:FAIL\n"); - return rc; -} - -int main(void) -{ - int (*tests[])(void) = { - test_foo_bar, - test_multiprog, - test_autodetach, - }; - int errors = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(tests); i++) - if (tests[i]()) - errors++; - - if (errors) - printf("test_cgroup_attach:FAIL\n"); - else - printf("test_cgroup_attach:PASS\n"); - - return errors ? EXIT_FAILURE : EXIT_SUCCESS; -} diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index f0eb2727b766..a8d2e9a87fbf 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -1,12 +1,16 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#include "libbpf.h" -#include "bpf.h" -#include "btf.h" +#include <iostream> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include "test_core_extern.skel.h" /* do nothing, just make sure we can link successfully */ int main(int argc, char *argv[]) { + struct test_core_extern *skel; + /* libbpf.h */ libbpf_set_print(NULL); @@ -16,5 +20,11 @@ int main(int argc, char *argv[]) /* btf.h */ btf__new(NULL, 0); + /* BPF skeleton */ + skel = test_core_extern__open_and_load(); + test_core_extern__destroy(skel); + + std::cout << "DONE!" << std::endl; + return 0; } diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index a8485ae103d1..174b72a64a4c 100755 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -139,6 +139,20 @@ echo "Testing IPv4 + GRE..." tc filter del dev lo ingress pref 1337 +echo "Testing port range..." +# Drops all IP/UDP packets coming from port 8-10 +tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ + udp src_port 8-10 action drop + +# Send 10 IPv4/UDP packets from port 7. Filter should not drop any. +./test_flow_dissector -i 4 -f 7 +# Send 10 IPv4/UDP packets from port 9. Filter should drop all. +./test_flow_dissector -i 4 -f 9 -F +# Send 10 IPv4/UDP packets from port 11. Filter should not drop any. +./test_flow_dissector -i 4 -f 11 + +tc filter del dev lo ingress pref 1337 + echo "Testing IPv6..." # Drops all IPv6/UDP packets coming from port 9 tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \ diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/test_hashmap.c index b64094c981e3..c490e012c23f 100644 --- a/tools/testing/selftests/bpf/test_hashmap.c +++ b/tools/testing/selftests/bpf/test_hashmap.c @@ -8,7 +8,7 @@ #include <stdio.h> #include <errno.h> #include <linux/err.h> -#include "hashmap.h" +#include "bpf/hashmap.h" #define CHECK(condition, format...) ({ \ int __ret = !!(condition); \ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 7fa7d08a8104..bab1e6f1d8f1 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -8,7 +8,7 @@ #include <string.h> /* defined in test_progs.h */ -struct test_env env; +struct test_env env = {}; struct prog_test_def { const char *test_name; @@ -29,10 +29,19 @@ struct prog_test_def { static bool should_run(struct test_selector *sel, int num, const char *name) { - if (sel->name && sel->name[0] && !strstr(name, sel->name)) - return false; + int i; + + for (i = 0; i < sel->blacklist.cnt; i++) { + if (strstr(name, sel->blacklist.strs[i])) + return false; + } - if (!sel->num_set) + for (i = 0; i < sel->whitelist.cnt; i++) { + if (strstr(name, sel->whitelist.strs[i])) + return true; + } + + if (!sel->whitelist.cnt && !sel->num_set) return true; return num < sel->num_set_len && sel->num_set[num]; @@ -334,6 +343,7 @@ const char argp_program_doc[] = "BPF selftests test runner"; enum ARG_KEYS { ARG_TEST_NUM = 'n', ARG_TEST_NAME = 't', + ARG_TEST_NAME_BLACKLIST = 'b', ARG_VERIFIER_STATS = 's', ARG_VERBOSE = 'v', }; @@ -341,8 +351,10 @@ enum ARG_KEYS { static const struct argp_option opts[] = { { "num", ARG_TEST_NUM, "NUM", 0, "Run test number NUM only " }, - { "name", ARG_TEST_NAME, "NAME", 0, - "Run tests with names containing NAME" }, + { "name", ARG_TEST_NAME, "NAMES", 0, + "Run tests with names containing any string from NAMES list" }, + { "name-blacklist", ARG_TEST_NAME_BLACKLIST, "NAMES", 0, + "Don't run tests with names containing any string from NAMES list" }, { "verifier-stats", ARG_VERIFIER_STATS, NULL, 0, "Output verifier statistics", }, { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, @@ -359,6 +371,41 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } +static int parse_str_list(const char *s, struct str_set *set) +{ + char *input, *state = NULL, *next, **tmp, **strs = NULL; + int cnt = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; + + set->cnt = 0; + set->strs = NULL; + + while ((next = strtok_r(state ? NULL : input, ",", &state))) { + tmp = realloc(strs, sizeof(*strs) * (cnt + 1)); + if (!tmp) + goto err; + strs = tmp; + + strs[cnt] = strdup(next); + if (!strs[cnt]) + goto err; + + cnt++; + } + + set->cnt = cnt; + set->strs = (const char **)strs; + free(input); + return 0; +err: + free(strs); + free(input); + return -ENOMEM; +} + int parse_num_list(const char *s, struct test_selector *sel) { int i, set_len = 0, num, start = 0, end = -1; @@ -449,12 +496,24 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) if (subtest_str) { *subtest_str = '\0'; - env->subtest_selector.name = strdup(subtest_str + 1); - if (!env->subtest_selector.name) + if (parse_str_list(subtest_str + 1, + &env->subtest_selector.whitelist)) + return -ENOMEM; + } + if (parse_str_list(arg, &env->test_selector.whitelist)) + return -ENOMEM; + break; + } + case ARG_TEST_NAME_BLACKLIST: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + if (parse_str_list(subtest_str + 1, + &env->subtest_selector.blacklist)) return -ENOMEM; } - env->test_selector.name = strdup(arg); - if (!env->test_selector.name) + if (parse_str_list(arg, &env->test_selector.blacklist)) return -ENOMEM; break; } @@ -617,7 +676,11 @@ int main(int argc, char **argv) printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + free(env.test_selector.blacklist.strs); + free(env.test_selector.whitelist.strs); free(env.test_selector.num_set); + free(env.subtest_selector.blacklist.strs); + free(env.subtest_selector.whitelist.strs); free(env.subtest_selector.num_set); 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 8477df835979..bcfa9ef23fda 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -35,7 +35,7 @@ typedef __u16 __sum16; #include "test_iptunnel_common.h" #include "bpf_util.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "trace_helpers.h" #include "flow_dissector_load.h" @@ -46,8 +46,14 @@ enum verbosity { VERBOSE_SUPER, }; +struct str_set { + const char **strs; + int cnt; +}; + struct test_selector { - const char *name; + struct str_set whitelist; + struct str_set blacklist; bool *num_set; int num_set_len; }; @@ -100,6 +106,7 @@ extern struct ipv6_packet pkt_v6; #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%s ", __func__, tag); \ @@ -108,15 +115,18 @@ extern struct ipv6_packet pkt_v6; printf("%s:PASS:%s %d nsec\n", \ __func__, tag, duration); \ } \ + errno = __save_errno; \ __ret; \ }) #define CHECK_FAIL(condition) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%d\n", __func__, __LINE__); \ } \ + errno = __save_errno; \ __ret; \ }) diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 0e6652733462..52bf14955797 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,7 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "bpf_rlimit.h" #include "bpf_util.h" diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 4a851513c842..779e11da979c 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, FILE *file; int i, fp; - file = fopen(".sendpage_tst.tmp", "w+"); + file = tmpfile(); if (!file) { perror("create file for sendpage"); return 1; @@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fwrite(&k, sizeof(char), 1, file); fflush(file); fseek(file, 0, SEEK_SET); - fclose(file); - fp = open(".sendpage_tst.tmp", O_RDONLY); - if (fp < 0) { - perror("reopen file for sendpage"); - return 1; - } + fp = fileno(file); clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { @@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, if (!drop && sent < 0) { perror("send loop error"); - close(fp); + fclose(file); return sent; } else if (drop && sent >= 0) { printf("sendpage loop error expected: %i\n", sent); - close(fp); + fclose(file); return -EIO; } @@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, s->bytes_sent += sent; } clock_gettime(CLOCK_MONOTONIC, &s->end); - close(fp); + fclose(file); return 0; } diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h index d008b41b7d8d..9b4d3a68a91a 100644 --- a/tools/testing/selftests/bpf/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/test_sockmap_kern.h @@ -12,8 +12,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Sockmap sample program connects a client and a backend together * using cgroups. diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index 40bd93a6e7ae..d196e2a4a6e0 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -13,7 +13,7 @@ #include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "bpf_rlimit.h" #include "bpf_util.h" #include "cgroup_helpers.h" diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index aa4dcfe18050..0383c9b8adc1 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -2,7 +2,7 @@ #ifndef __TRACE_HELPER_H #define __TRACE_HELPER_H -#include <libbpf.h> +#include <bpf/libbpf.h> struct ksym { long addr; diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index b4efb023ae51..d88d8e47d11b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -50,6 +50,8 @@ ALL_TESTS=" ipv6_mc_dip_reserved_scope_test ipv6_mc_dip_interface_local_scope_test blackhole_route_test + irif_disabled_test + erif_disabled_test " NUM_NETIFS=4 @@ -553,6 +555,116 @@ blackhole_route_test() __blackhole_route_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6 "icmpv6" } +irif_disabled_test() +{ + local trap_name="irif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + + # When RIF of a physical port ("Sub-port RIF") is destroyed, we first + # block the STP of the {Port, VLAN} so packets cannot get into the RIF. + # Using bridge enables us to see this trap because when bridge is + # destroyed, there is a small time window that packets can go into the + # RIF, while it is disabled. + ip link add dev br0 type bridge + ip link set dev $rp1 master br0 + ip address flush dev $rp1 + __addr_add_del br0 add 192.0.2.2/24 + ip li set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + # Generate packets to h2 through br0 RIF that will be removed later + $MZ $h1 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp1mac \ + -B $h2_ipv4 -q & + mz_pid=$! + + # Wait before removing br0 RIF to allow packets to go into the bridge. + sleep 1 + + # Flushing address will dismantle the RIF + ip address flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Ingress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + +erif_disabled_test() +{ + local trap_name="erif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + ip link add dev br0 type bridge + ip add flush dev $rp1 + ip link set dev $rp1 master br0 + __addr_add_del br0 add 192.0.2.2/24 + ip link set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + rp2mac=$(mac_get $rp2) + + # Generate packets that should go out through br0 RIF that will be + # removed later + $MZ $h2 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp2mac \ + -B 192.0.2.1 -q & + mz_pid=$! + + sleep 5 + # In order to see this trap we need a route that points to disabled RIF. + # When ipv6 address is flushed, there is a delay and the routes are + # deleted before the RIF and we cannot get state that we have route + # to disabled RIF. + # Delete IPv6 address first and then check this trap with flushing IPv4. + ip -6 add flush dev br0 + ip -4 add flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Egress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh new file mode 100755 index 000000000000..039629bb92a3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -0,0 +1,265 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 192.0.2.2/28 | +# | | +# | + g1a (gre) | +# | loc=192.0.2.65 | +# | rem=192.0.2.66 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 198.51.100.1/28 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 198.51.100.2/28 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +vrf2_create() +{ + simple_if_init $rp2 198.51.100.2/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 198.51.100.2/28 +} + +switch_create() +{ + __addr_add_del $swp1 add 192.0.2.2/28 + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 up + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit + __addr_add_del g1 add 192.0.2.65/32 + ip link set dev g1 up + + __addr_add_del $rp1 add 198.51.100.1/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + __addr_add_del $rp1 del 198.51.100.1/28 + + ip link set dev g1 down + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + ip link set dev $swp1 down + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 192.0.2.2/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ecn_payload_get() +{ + p=$(: + )"0"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 192.0.2.66 -B 192.0.2.65 -t ip \ + len=48,tos=$outer_tos,proto=47,p=$payload -q & + + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +ipip_payload_get() +{ + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"$key"$( : Key + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 192.0.2.65 -t ip len=48,proto=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=192.0.2.66 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 192.0.2.68 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" ":E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit key 233 + __addr_add_del g1 add 192.0.2.65/32 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" "E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh new file mode 100755 index 000000000000..fd19161dd4ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -0,0 +1,330 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel drops and exceptions functionality over mlxsw. +# Check all traps to make sure they are triggered under the right +# conditions. + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | +--|--------------------------------------------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +-----------------------------------------------------------------------+ | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | VRF2 | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# +-------------------------------------------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test + overlay_smac_is_mc_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +: ${VXPORT:=4789} +export VXPORT + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip link set dev br1 address $(mac_get $swp1) + ip link set dev br1 up + + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link add name vx1 type vxlan id 1000 local 192.0.2.17 \ + dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx1 master br1 + ip link set dev vx1 up + + ip address add dev $rp1 192.0.2.17/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + ip address del dev $rp1 192.0.2.17/28 + + ip link set dev vx1 down + ip link set dev vx1 nomaster + ip link del dev vx1 + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + tc qdisc del dev $swp1 clsact + + ip link set dev br1 down + ip link del dev br1 +} + +vrf2_create() +{ + simple_if_init $rp2 192.0.2.18/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + forwarding_restore + vrf_cleanup +} + +ecn_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"D6:E5:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac -B 192.0.2.17 \ + -t udp sp=12345,dp=$VXPORT,tos=$outer_tos,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +reserved_bits_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +short_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + ) + echo $p +} + +corrupted_packet_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local payload_get=$1; shift + local mz_pid + + RET=0 + + # In case of too short packet, there is no any inner packet, + # so the matching will always succeed + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower skip_hw src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$($payload_get) + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + corrupted_packet_test "Decap error: Reserved bits in use" \ + "reserved_bits_payload_get" + corrupted_packet_test "Decap error: No L2 header" "short_payload_get" +} + +mc_smac_payload_get() +{ + dest_mac=$(mac_get $h1) + source_mac=01:02:03:04:05:06 + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"$source_mac:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +overlay_smac_is_mc_test() +{ + local trap_name="overlay_smac_is_mc" + local group_name="tunnel_drops" + local mz_pid + + RET=0 + + # The matching will be checked on devlink_trap_drop_test() + # and the filter will be removed on devlink_trap_drop_cleanup() + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_mac 01:02:03:04:05:06 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(mc_smac_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_drop_test $trap_name $group_name $swp1 + + log_test "Overlay source MAC is multicast" + + devlink_trap_drop_cleanup $mz_pid $swp1 "ip" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh new file mode 100755 index 000000000000..45115f81c2b1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh @@ -0,0 +1,180 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API on top of mlxsw. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath +" +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +setup_prepare() +{ + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + devlink -N testns1 dev reload $DEVLINK_DEV netns $$ + ip netns del testns1 +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh new file mode 100755 index 000000000000..eff6393ce974 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh @@ -0,0 +1,176 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for port-default priority. Non-IP packets ingress $swp1 and are +# prioritized according to the default priority specified at the port. +# rx_octets_prio_* counters are used to verify the prioritization. +# +# +-----------------------+ +# | H1 | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|------------------+ +# | +# +----|------------------+ +# | SW | | +# | + $swp1 | +# | 192.0.2.2/28 | +# | APP=<prio>,1,0 | +# +-----------------------+ + +ALL_TESTS=" + ping_ipv4 + test_defprio +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=2 +: ${HIT_TIMEOUT:=1000} # ms +source $lib_dir/lib.sh + +declare -a APP + +defprio_install() +{ + local dev=$1; shift + local prio=$1; shift + local app="app=$prio,1,0" + + lldptool -T -i $dev -V APP $app >/dev/null + lldpad_app_wait_set $dev + APP[$prio]=$app +} + +defprio_uninstall() +{ + local dev=$1; shift + local prio=$1; shift + local app=${APP[$prio]} + + lldptool -T -i $dev -V APP -d $app >/dev/null + lldpad_app_wait_del + unset APP[$prio] +} + +defprio_flush() +{ + local dev=$1; shift + local prio + + if ((${#APP[@]})); then + lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null + fi + lldpad_app_wait_del + APP=() +} + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link set dev $swp1 up + ip addr add dev $swp1 192.0.2.2/28 +} + +switch_destroy() +{ + defprio_flush $swp1 + ip addr del dev $swp1 192.0.2.2/28 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +wait_for_packets() +{ + local t0=$1; shift + local prio_observe=$1; shift + + local t1=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + local delta=$((t1 - t0)) + echo $delta + ((delta >= 10)) +} + +__test_defprio() +{ + local prio_install=$1; shift + local prio_observe=$1; shift + local delta + local key + local i + + RET=0 + + defprio_install $swp1 $prio_install + + local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + mausezahn -q $h1 -d 100m -c 10 -t arp reply + delta=$(busywait "$HIT_TIMEOUT" wait_for_packets $t0 $prio_observe) + + check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $delta." + log_test "Default priority $prio_install/$prio_observe" + + defprio_uninstall $swp1 $prio_install +} + +test_defprio() +{ + local prio + + for prio in {0..7}; do + __test_defprio $prio $prio + done + + defprio_install $swp1 3 + __test_defprio 0 3 + __test_defprio 1 3 + __test_defprio 2 3 + __test_defprio 4 4 + __test_defprio 5 5 + __test_defprio 6 6 + __test_defprio 7 7 + defprio_uninstall $swp1 3 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index e80be65799ad..faa51012cdac 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -1,47 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -humanize() -{ - local speed=$1; shift - - for unit in bps Kbps Mbps Gbps; do - if (($(echo "$speed < 1024" | bc))); then - break - fi - - speed=$(echo "scale=1; $speed / 1024" | bc) - done - - echo "$speed${unit}" -} - -rate() -{ - local t0=$1; shift - local t1=$1; shift - local interval=$1; shift - - echo $((8 * (t1 - t0) / interval)) -} - -start_traffic() -{ - local h_in=$1; shift # Where the traffic egresses the host - local sip=$1; shift - local dip=$1; shift - local dmac=$1; shift - - $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ - -a own -b $dmac -t udp -q & - sleep 1 -} - -stop_traffic() -{ - # Suppress noise from killing mausezahn. - { kill %% && wait %%; } 2>/dev/null -} - check_rate() { local rate=$1; shift @@ -96,3 +54,31 @@ measure_rate() echo $ir $er return $ret } + +bail_on_lldpad() +{ + if systemctl is-active --quiet lldpad; then + + cat >/dev/stderr <<-EOF + WARNING: lldpad is running + + lldpad will likely configure DCB, and this test will + configure Qdiscs. mlxsw does not support both at the + same time, one of them is arbitrarily going to overwrite + the other. That will cause spurious failures (or, + unlikely, passes) of this test. + EOF + + if [[ -z $ALLOW_LLDPAD ]]; then + cat >/dev/stderr <<-EOF + + If you want to run the test anyway, please set + an environment variable ALLOW_LLDPAD to a + non-empty string. + EOF + exit 1 + else + return + fi + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh new file mode 100755 index 000000000000..c9fc4d4885c1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh @@ -0,0 +1,67 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in offloaded datapath. +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/sch_ets_core.sh +source $lib_dir/devlink_lib.sh +source qos_lib.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + ethtool -s $h2 speed 1000 autoneg off + ethtool -s $swp2 speed 1000 autoneg off + + # Set the ingress quota high and use the three egress TCs to limit the + # amount of traffic that is admitted to the shared buffers. This makes + # sure that there is always enough traffic of all types to select from + # for the DWRR process. + devlink_port_pool_th_set $swp1 0 12 + devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12 + devlink_port_pool_th_set $swp2 4 12 + devlink_tc_bind_pool_th_set $swp2 7 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 6 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 5 egress 4 5 + + # Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet + # priorities at $swp1 based on their 802.1p headers. ingress-qos-map is + # not offloaded by mlxsw as of this writing, but the mapping used is + # 1:1, which is the mapping currently hard-coded by the driver. +} + +switch_destroy() +{ + devlink_tc_bind_pool_th_restore $swp2 5 egress + devlink_tc_bind_pool_th_restore $swp2 6 egress + devlink_tc_bind_pool_th_restore $swp2 7 egress + devlink_port_pool_th_restore $swp2 4 + devlink_tc_bind_pool_th_restore $swp1 0 ingress + devlink_port_pool_th_restore $swp1 0 + + ethtool -s $swp2 autoneg on + ethtool -s $h2 autoneg on + + ets_switch_destroy +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local band=$1; shift + + ethtool_stats_get "$h2" rx_octets_prio_$band +} + +bail_on_lldpad +ets_run diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh new file mode 100755 index 000000000000..c6ce0b448bf3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_ets.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh new file mode 100755 index 000000000000..8d245f331619 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_prio.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh new file mode 100755 index 000000000000..013886061f15 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_root.sh diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh new file mode 100755 index 000000000000..2f87c3be76a9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh @@ -0,0 +1,341 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API. It makes use of netdevsim +# which registers a listener to the FIB notification chain. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv4_error_path + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath + ipv6_error_path +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv4_error_path_add() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 \ + &> /dev/null + done + + log_test "IPv4 error path - add" + + ip -n testns1 link del dev dummy1 +} + +ipv4_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv4 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv4_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv4/fib" resource. + ipv4_error_path_add + ipv4_error_path_replay +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +ipv6_error_path_add_single() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 \ + &> /dev/null + done + + log_test "IPv6 error path - add single" + + ip -n testns1 link del dev dummy1 +} + +ipv6_error_path_add_multipath() +{ + local lsb + + RET=0 + + for i in $(seq 1 2); do + ip -n testns1 link add name dummy$i type dummy + ip -n testns1 link set dev dummy$i up + ip -n testns1 address add 2001:db8:$i::1/64 dev dummy$i + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:10::${lsb}/128 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 &> /dev/null + done + + log_test "IPv6 error path - add multipath" + + for i in $(seq 1 2); do + ip -n testns1 link del dev dummy$i + done +} + +ipv6_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv6 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv6_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv6/fib" resource. + ipv6_error_path_add_single + ipv6_error_path_add_multipath + ipv6_error_path_replay +} + +setup_prepare() +{ + local netdev + + modprobe netdevsim &> /dev/null + + echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $SYSFS_NET_DIR ] ; do :; done + + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + ip netns del testns1 + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device + modprobe -r netdevsim &> /dev/null +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 9fd3a0b97f0d..fb5c55dd6df8 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -32,12 +32,17 @@ # lo2: 127.0.0.1/8, ::1/128 # 172.16.2.2/32, 2001:db8:2::2/128 # +# ns-A to ns-C connection - only for VRF and same config +# as ns-A to ns-B +# # server / client nomenclature relative to ns-A VERBOSE=0 NSA_DEV=eth1 +NSA_DEV2=eth2 NSB_DEV=eth1 +NSC_DEV=eth2 VRF=red VRF_TABLE=1101 @@ -45,17 +50,22 @@ VRF_TABLE=1101 NSA_IP=172.16.1.1 NSB_IP=172.16.1.2 VRF_IP=172.16.3.1 +NS_NET=172.16.1.0/24 # IPv6 config NSA_IP6=2001:db8:1::1 NSB_IP6=2001:db8:1::2 VRF_IP6=2001:db8:3::1 +NS_NET6=2001:db8:1::/120 NSA_LO_IP=172.16.2.1 NSB_LO_IP=172.16.2.2 NSA_LO_IP6=2001:db8:2::1 NSB_LO_IP6=2001:db8:2::2 +MD5_PW=abc123 +MD5_WRONG_PW=abc1234 + MCAST=ff02::1 # set after namespace create NSA_LINKIP6= @@ -63,9 +73,11 @@ NSB_LINKIP6= NSA=ns-A NSB=ns-B +NSC=ns-C NSA_CMD="ip netns exec ${NSA}" NSB_CMD="ip netns exec ${NSB}" +NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -195,6 +207,11 @@ run_cmd_nsb() do_run_cmd ${NSB_CMD} $* } +run_cmd_nsc() +{ + do_run_cmd ${NSC_CMD} $* +} + setup_cmd() { local cmd="$*" @@ -401,6 +418,7 @@ cleanup() fi ip netns del ${NSB} + ip netns del ${NSC} >/dev/null 2>&1 } setup() @@ -432,6 +450,12 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} @@ -714,6 +738,218 @@ ipv4_ping() ################################################################################ # IPv4 TCP +# +# MD5 tests without VRF +# +ipv4_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv4_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv4_tcp_novrf() { local a @@ -831,6 +1067,8 @@ ipv4_tcp_novrf() show_hint "Should fail 'Connection refused'" run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" + + ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -883,6 +1121,9 @@ ipv4_tcp_vrf() run_cmd nettest -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv4_tcp_md5 + # # enable VRF global server # @@ -924,8 +1165,8 @@ ipv4_tcp_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start - show_hint "Should fail 'No route to host' since client is not bound to VRF" - run_cmd nettest -s -2 ${VRF} & + show_hint "Should fail 'Connection refused' since client is not bound to VRF" + run_cmd nettest -s -d ${VRF} & sleep 1 run_cmd nettest -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" @@ -1961,6 +2202,218 @@ ipv6_ping() ################################################################################ # IPv6 TCP +# +# MD5 tests without VRF +# +ipv6_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv6_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP6} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET6} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv6_tcp_novrf() { local a @@ -2077,6 +2530,8 @@ ipv6_tcp_novrf() run_cmd nettest -6 -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" done + + ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2145,6 +2600,9 @@ ipv6_tcp_vrf() run_cmd nettest -6 -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv6_tcp_md5 + # # enable VRF global server # @@ -2205,8 +2663,8 @@ ipv6_tcp_vrf() for a in ${NSA_IP6} ${VRF_IP6} do log_start - show_hint "Fails 'No route to host' since client is not in VRF" - run_cmd nettest -6 -s -2 ${VRF} & + show_hint "Fails 'Connection refused' since client is not in VRF" + run_cmd nettest -6 -s -d ${VRF} & sleep 1 run_cmd nettest -6 -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh new file mode 100644 index 000000000000..66496659bea7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -0,0 +1,873 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Various helpers and tests to verify FIB offload. + +__fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + local ret + + ip -n $ns -j -p -$family route show $route \ + | jq -e '.[]["flags"] | contains(["trap"])' &> /dev/null + ret=$? + if [[ $should_fail == "true" ]]; then + if [[ $ret -ne 0 ]]; then + return 0 + else + return 1 + fi + fi + + return $ret +} + +fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + + busywait 5000 __fib_trap_check $ns $family "$route" $should_fail +} + +fib4_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 4 "$route" $should_fail +} + +fib6_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 6 "$route" $should_fail +} + +fib_ipv4_identical_routes_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 192.0.2.0/24 dev dummy2 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 tos 0 metric 1024" true + check_err $? "Appended route in hardware when should not" + + ip -n $ns route prepend 192.0.2.0/24 dev dummy3 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy3 tos 0 metric 1024" false + check_err $? "Prepended route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Route was not replaced in hardware by prepended one" + + log_test "IPv4 identical routes" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_tos_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Lowest TOS route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + check_err $? "Middle TOS route in hardware when should not" + + log_test "IPv4 routes with TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1022 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1023 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv4 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replace_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1025 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_delete_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Insert multiple routes with the same prefix and length and varying + # metrics. Make sure that throughout delete operations the lowest + # metric route is the one in hardware. + for metric in $(seq 1024 1026); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1026 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Sole route not in hardware when should" + + log_test "IPv4 route delete" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_plen_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Add two routes with the same key and different prefix length and + # make sure both are in hardware. It can be verfied that both are + # sharing the same leaf by checking the /proc/net/fib_trie + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes with different prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_metric_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 routes replay - metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_tos_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true + check_err $? "Lowest TOS route in hardware when should not" + + log_test "IPv4 routes replay - TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_plen_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes replay - prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_flush_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Exercise the routes flushing code paths by inserting various + # prefix routes on a netdev and then deleting it. + for metric in $(seq 1 20); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + ip -n $ns link del dev dummy1 + + log_test "IPv4 routes flushing" +} + +fib_ipv6_add_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after appending route" + + log_test "IPv6 single route add" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1022 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1023 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv6_append_single_test() +{ + local ns=$1; shift + + # When an IPv6 multipath route is added without the 'nexthop' keyword, + # different code paths are taken compared to when the keyword is used. + # This test tries to verify the former. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append single route without 'nexthop' keyword" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_single_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1025 + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1025 + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 single route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1022 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1023 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 multipath routes with metric" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append multipath route with 'nexthop' keyword" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_multipath_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route replace 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 multipath route replace" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_to_single_test() +{ + local ns=$1; shift + + # Test that when the first route in the leaf is not a multipath route + # and we try to append a multipath route with the same metric to it, it + # is not notified. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after append" + + log_test "IPv6 append multipath route to non-multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_single_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where only a single route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a single route when it is the only route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + log_test "IPv6 delete sole single route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete single route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + # Test deletion of a single nexthop from a multipath route. + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting a single nexthop" + + log_test "IPv6 delete single nexthop" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_multipath_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where an entire multipath route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a multipath route when it is the only route in the + # FIB node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + log_test "IPv6 delete sole multipath route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete multipath route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_single_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 + ip -n $ns route append 2001:db8:1::/64 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - single route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_multipath_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1f64e7348f69..2f5da414aaa7 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -225,6 +225,47 @@ log_info() echo "INFO: $msg" } +busywait() +{ + local timeout=$1; shift + + local start_time="$(date -u +%s%3N)" + while true + do + local out + out=$("$@") + local ret=$? + if ((!ret)); then + echo -n "$out" + return 0 + fi + + local current_time="$(date -u +%s%3N)" + if ((current_time - start_time > timeout)); then + echo -n "$out" + return 1 + fi + done +} + +until_counter_is() +{ + local value=$1; shift + local current=$("$@") + + echo $((current)) + ((current >= value)) +} + +busywait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + busywait "$timeout" until_counter_is $((base + delta)) "$@" +} + setup_wait_dev() { local dev=$1; shift @@ -552,9 +593,10 @@ tc_rule_stats_get() local dev=$1; shift local pref=$1; shift local dir=$1; shift + local selector=${1:-.packets}; shift tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ - | jq '.[1].options.actions[].stats.packets' + | jq ".[1].options.actions[].stats$selector" } ethtool_stats_get() @@ -565,6 +607,30 @@ ethtool_stats_get() ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } +humanize() +{ + local speed=$1; shift + + for unit in bps Kbps Mbps Gbps; do + if (($(echo "$speed < 1024" | bc))); then + break + fi + + speed=$(echo "scale=1; $speed / 1024" | bc) + done + + echo "$speed${unit}" +} + +rate() +{ + local t0=$1; shift + local t1=$1; shift + local interval=$1; shift + + echo $((8 * (t1 - t0) / interval)) +} + mac_get() { local if_name=$1 @@ -1065,3 +1131,21 @@ flood_test() flood_unicast_test $br_port $host1_if $host2_if flood_multicast_test $br_port $host1_if $host2_if } + +start_traffic() +{ + local h_in=$1; shift # Where the traffic egresses the host + local sip=$1; shift + local dip=$1; shift + local dmac=$1; shift + + $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ + -a own -b $dmac -t udp -q & + sleep 1 +} + +stop_traffic() +{ + # Suppress noise from killing mausezahn. + { kill %% && wait %%; } 2>/dev/null +} diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index a75cb51cc5bd..057f91b05098 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,9 +1,23 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6" +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + sip_in_class_e + mc_mac_mismatch + ipv4_sip_equal_dip + ipv6_sip_equal_dip + ipv4_dip_link_local +" + NUM_NETIFS=4 source lib.sh +source tc_common.sh + +require_command $MCD +require_command $MC_CLI +table_name=selftests h1_create() { @@ -64,6 +78,8 @@ router_create() ip link set dev $rp1 up ip link set dev $rp2 up + tc qdisc add dev $rp2 clsact + ip address add 192.0.2.1/24 dev $rp1 ip address add 2001:db8:1::1/64 dev $rp1 @@ -79,10 +95,31 @@ router_destroy() ip address del 2001:db8:1::1/64 dev $rp1 ip address del 192.0.2.1/24 dev $rp1 + tc qdisc del dev $rp2 clsact + ip link set dev $rp2 down ip link set dev $rp1 down } +start_mcd() +{ + SMCROUTEDIR="$(mktemp -d)" + + for ((i = 1; i <= $NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + $SMCROUTEDIR/$table_name.conf + done + + $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ + -P $SMCROUTEDIR/$table_name.pid +} + +kill_mcd() +{ + pkill $MCD + rm -rf $SMCROUTEDIR +} + setup_prepare() { h1=${NETIFS[p1]} @@ -91,6 +128,10 @@ setup_prepare() rp2=${NETIFS[p3]} h2=${NETIFS[p4]} + rp1mac=$(mac_get $rp1) + + start_mcd + vrf_prepare h1_create @@ -113,6 +154,8 @@ cleanup() h1_destroy vrf_cleanup + + kill_mcd } ping_ipv4() @@ -125,6 +168,150 @@ ping_ipv6() ping6_test $h1 2001:db8:2::2 } +sip_in_class_e() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 240.0.0.1 ip_proto udp action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 240.0.0.1 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP in class E" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +create_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs +} + +delete_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs +} + +__mc_mac_mismatch() +{ + local desc=$1; shift + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local flags=${1:-""}; shift + local dmac=01:02:03:04:05:06 + + RET=0 + + tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \ + flower dst_ip $dip action pass + + create_mcast_sg $rp1 $sip $dip $rp2 + + $MZ $flags $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $dmac \ + -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Multicast MAC mismatch: $desc" + + delete_mcast_sg $rp1 $sip $dip $rp2 + tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower +} + +mc_mac_mismatch() +{ + __mc_mac_mismatch "IPv4" "ip" 192.0.2.2 225.1.2.3 + __mc_mac_mismatch "IPv6" "ipv6" 2001:db8:1::2 ff0e::3 "-6" +} + +ipv4_sip_equal_dip() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 198.51.100.2 action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 198.51.100.2 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv4" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +ipv6_sip_equal_dip() +{ + RET=0 + + tc filter add dev $rp2 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::2 action pass + + $MZ -6 $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 2001:db8:2::2 -b $rp1mac -B 2001:db8:2::2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv6" + + tc filter del dev $rp2 egress protocol ipv6 pref 1 handle 101 flower +} + +ipv4_dip_link_local() +{ + local dip=169.254.1.1 + + RET=0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower dst_ip $dip action pass + + ip neigh add 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + ip route add 169.254.1.0/24 dev $rp2 + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $rp1mac -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 destination IP is link-local" + + ip route del 169.254.1.0/24 dev $rp2 + ip neigh del 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh new file mode 100755 index 000000000000..40e0ad1bc4f2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -0,0 +1,44 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in slowpath. +lib_dir=. +source sch_ets_core.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr + classifier_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + tc qdisc add dev $swp2 root handle 1: tbf \ + rate 1Gbit burst 1Mbit latency 100ms + PARENT="parent 1:" +} + +switch_destroy() +{ + ets_switch_destroy + tc qdisc del dev $swp2 root +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local stream=$1; shift + + link_stats_get $h2.1$stream rx bytes +} + +ets_run diff --git a/tools/testing/selftests/net/forwarding/sch_ets_core.sh b/tools/testing/selftests/net/forwarding/sch_ets_core.sh new file mode 100644 index 000000000000..f906fcc66572 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_core.sh @@ -0,0 +1,300 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is a template for ETS Qdisc test. +# +# This test sends from H1 several traffic streams with 802.1p-tagged packets. +# The tags are used at $swp1 to prioritize the traffic. Each stream is then +# queued at a different ETS band according to the assigned priority. After +# runnig for a while, counters at H2 are consulted to determine whether the +# traffic scheduling was according to the ETS configuration. +# +# This template is supposed to be embedded by a test driver, which implements +# statistics collection, any HW-specific stuff, and prominently configures the +# system to assure that there is overcommitment at $swp2. That is necessary so +# that the ETS traffic selection algorithm kicks in and has to schedule some +# traffic at the expense of other. +# +# A driver for veth-based testing is in sch_ets.sh, an example of a driver for +# an offloaded data path is in selftests/drivers/net/mlxsw/sch_ets.sh. +# +# +---------------------------------------------------------------------+ +# | H1 | +# | + $h1.10 + $h1.11 + $h1.12 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | 192.0.2.33/28 | +# | | egress-qos-map | egress-qos-map | egress-qos-map | +# | | 0:0 | 0:1 | 0:2 | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $h1 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | SW + $swp1 | +# | | >1Gbps | +# | ____________________/|\____________________ | +# | / | \ | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | | + $swp1.10 | | + $swp1.11 | | + $swp1.12 | | +# | | ingress-qos-map| | ingress-qos-map| | ingress-qos-map| | +# | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | +# | | | | | | | | +# | | BR10 | | BR11 | | BR12 | | +# | | | | | | | | +# | | + $swp2.10 | | + $swp2.11 | | + $swp2.12 | | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $swp2 | +# | | 1Gbps (ethtool or HTB qdisc) | +# | | qdisc ets quanta $W0 $W1 $W2 | +# | | priomap 0 1 2 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | H2 + $h2 | +# | ____________________/|\____________________ | +# | / | \ | +# | + $h2.10 + $h2.11 + $h2.12 | +# | 192.0.2.2/28 192.0.2.18/28 192.0.2.34/28 | +# +---------------------------------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC=yes +source $lib_dir/lib.sh +source $lib_dir/sch_ets_tests.sh + +PARENT=root +QDISC_DEV= + +sip() +{ + echo 192.0.2.$((16 * $1 + 1)) +} + +dip() +{ + echo 192.0.2.$((16 * $1 + 2)) +} + +# Callback from sch_ets_tests.sh +ets_start_traffic() +{ + local dst_mac=$(mac_get $h2) + local i=$1; shift + + start_traffic $h1.1$i $(sip $i) $(dip $i) $dst_mac +} + +ETS_CHANGE_QDISC= + +priomap_mode() +{ + echo "Running in priomap mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_priomap +} + +classifier_mode() +{ + echo "Running in classifier mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_classifier +} + +ets_change_qdisc_priomap() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) \ + priomap $priomap + QDISC_DEV=$dev +} + +ets_change_qdisc_classifier() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) + + if [[ $op == add ]]; then + local prio=0 + local band + + for band in $priomap; do + tc filter add dev $dev parent 10: basic \ + match "meta(priority eq $prio)" \ + flowid 10:$((band + 1)) + ((prio++)) + done + fi + QDISC_DEV=$dev +} + +# Callback from sch_ets_tests.sh +ets_change_qdisc() +{ + if [[ -z "$ETS_CHANGE_QDISC" ]]; then + exit 1 + fi + $ETS_CHANGE_QDISC "$@" +} + +ets_delete_qdisc() +{ + if [[ -n $QDISC_DEV ]]; then + tc qdisc del dev $QDISC_DEV $PARENT + QDISC_DEV= + fi +} + +h1_create() +{ + local i; + + simple_if_init $h1 + mtu_set $h1 9900 + for i in {0..2}; do + vlan_create $h1 1$i v$h1 $(sip $i)/28 + ip link set dev $h1.1$i type vlan egress 0:$i + done +} + +h1_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h1 1$i + done + mtu_restore $h1 + simple_if_fini $h1 +} + +h2_create() +{ + local i + + simple_if_init $h2 + mtu_set $h2 9900 + for i in {0..2}; do + vlan_create $h2 1$i v$h2 $(dip $i)/28 + done +} + +h2_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h2 1$i + done + mtu_restore $h2 + simple_if_fini $h2 +} + +ets_switch_create() +{ + local i + + ip link set dev $swp1 up + mtu_set $swp1 9900 + + ip link set dev $swp2 up + mtu_set $swp2 9900 + + for i in {0..2}; do + vlan_create $swp1 1$i + ip link set dev $swp1.1$i type vlan ingress 0:0 1:1 2:2 + + vlan_create $swp2 1$i + + ip link add dev br1$i type bridge + ip link set dev $swp1.1$i master br1$i + ip link set dev $swp2.1$i master br1$i + + ip link set dev br1$i up + ip link set dev $swp1.1$i up + ip link set dev $swp2.1$i up + done +} + +ets_switch_destroy() +{ + local i + + ets_delete_qdisc + + for i in {0..2}; do + ip link del dev br1$i + vlan_destroy $swp2 1$i + vlan_destroy $swp1 1$i + done + + mtu_restore $swp2 + ip link set dev $swp2 down + + mtu_restore $swp1 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + put=$swp2 + hut=$h2 + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(dip 0) " vlan 10" + ping_test $h1.11 $(dip 1) " vlan 11" + ping_test $h1.12 $(dip 2) " vlan 12" +} + +ets_run() +{ + trap cleanup EXIT + + setup_prepare + setup_wait + + tests_run + + exit $EXIT_STATUS +} diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh new file mode 100644 index 000000000000..3c3b204d47e8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -0,0 +1,227 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Global interface: +# $put -- port under test (e.g. $swp2) +# get_stats($band) -- A function to collect stats for band +# ets_start_traffic($band) -- Start traffic for this band +# ets_change_qdisc($op, $dev, $nstrict, $quanta...) -- Add or change qdisc + +# WS describes the Qdisc configuration. It has one value per band (so the +# number of array elements indicates the number of bands). If the value is +# 0, it is a strict band, otherwise the it's a DRR band and the value is +# that band's quantum. +declare -a WS + +qdisc_describe() +{ + local nbands=${#WS[@]} + local nstrict=0 + local i + + for ((i = 0; i < nbands; i++)); do + if ((!${WS[$i]})); then + : $((nstrict++)) + fi + done + + echo -n "ets bands $nbands" + if ((nstrict)); then + echo -n " strict $nstrict" + fi + if ((nstrict < nbands)); then + echo -n " quanta" + for ((i = nstrict; i < nbands; i++)); do + echo -n " ${WS[$i]}" + done + fi +} + +__strict_eval() +{ + local desc=$1; shift + local d=$1; shift + local total=$1; shift + local above=$1; shift + + RET=0 + + if ((! total)); then + check_err 1 "No traffic observed" + log_test "$desc" + return + fi + + local ratio=$(echo "scale=2; 100 * $d / $total" | bc -l) + if ((above)); then + test $(echo "$ratio > 95.0" | bc -l) -eq 1 + check_err $? "Not enough traffic" + log_test "$desc" + log_info "Expected ratio >95% Measured ratio $ratio" + else + test $(echo "$ratio < 5" | bc -l) -eq 1 + check_err $? "Too much traffic" + log_test "$desc" + log_info "Expected ratio <5% Measured ratio $ratio" + fi +} + +strict_eval() +{ + __strict_eval "$@" 1 +} + +notraf_eval() +{ + __strict_eval "$@" 0 +} + +__ets_dwrr_test() +{ + local -a streams=("$@") + + local low_stream=${streams[0]} + local seen_strict=0 + local -a t0 t1 d + local stream + local total + local i + + echo "Testing $(qdisc_describe), streams ${streams[@]}" + + for stream in ${streams[@]}; do + ets_start_traffic $stream + done + + sleep 10 + + t0=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + + sleep 10 + + t1=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + d=($(for ((i = 0; i < ${#streams[@]}; i++)); do + echo $((${t1[$i]} - ${t0[$i]})) + done)) + total=$(echo ${d[@]} | sed 's/ /+/g' | bc) + + for ((i = 0; i < ${#streams[@]}; i++)); do + local stream=${streams[$i]} + if ((seen_strict)); then + notraf_eval "band $stream" ${d[$i]} $total + elif ((${WS[$stream]} == 0)); then + strict_eval "band $stream" ${d[$i]} $total + seen_strict=1 + elif ((stream == low_stream)); then + # Low stream is used as DWRR evaluation reference. + continue + else + multipath_eval "bands $low_stream:$stream" \ + ${WS[$low_stream]} ${WS[$stream]} \ + ${d[0]} ${d[$i]} + fi + done + + for stream in ${streams[@]}; do + stop_traffic + done +} + +ets_dwrr_test_012() +{ + __ets_dwrr_test 0 1 2 +} + +ets_dwrr_test_01() +{ + __ets_dwrr_test 0 1 +} + +ets_dwrr_test_12() +{ + __ets_dwrr_test 1 2 +} + +ets_qdisc_setup() +{ + local dev=$1; shift + local nstrict=$1; shift + local -a quanta=("$@") + + local ndwrr=${#quanta[@]} + local nbands=$((nstrict + ndwrr)) + local nstreams=$(if ((nbands > 3)); then echo 3; else echo $nbands; fi) + local priomap=$(seq 0 $((nstreams - 1))) + local i + + WS=($( + for ((i = 0; i < nstrict; i++)); do + echo 0 + done + for ((i = 0; i < ndwrr; i++)); do + echo ${quanta[$i]} + done + )) + + ets_change_qdisc $dev $nstrict "$priomap" ${quanta[@]} +} + +ets_set_dwrr_uniform() +{ + ets_qdisc_setup $put 0 3300 3300 3300 +} + +ets_set_dwrr_varying() +{ + ets_qdisc_setup $put 0 5000 3500 1500 +} + +ets_set_strict() +{ + ets_qdisc_setup $put 3 +} + +ets_set_mixed() +{ + ets_qdisc_setup $put 1 5000 2500 1500 +} + +ets_change_quantum() +{ + tc class change dev $put classid 10:2 ets quantum 8000 + WS[1]=8000 +} + +ets_set_dwrr_two_bands() +{ + ets_qdisc_setup $put 0 5000 2500 +} + +ets_test_strict() +{ + ets_set_strict + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_mixed() +{ + ets_set_mixed + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_dwrr() +{ + ets_set_dwrr_uniform + ets_dwrr_test_012 + ets_set_dwrr_varying + ets_dwrr_test_012 + ets_change_quantum + ets_dwrr_test_012 + ets_set_dwrr_two_bands + ets_dwrr_test_01 +} diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh new file mode 100644 index 000000000000..d1f26cb7cd73 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh @@ -0,0 +1,233 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends a stream of traffic from H1 through a switch, to H2. On the +# egress port from the switch ($swp2), a shaper is installed. The test verifies +# that the rates on the port match the configured shaper. +# +# In order to test per-class shaping, $swp2 actually contains TBF under PRIO or +# ETS, with two different configurations. Traffic is prioritized using 802.1p. +# +# +-------------------------------------------+ +# | H1 | +# | + $h1.10 $h1.11 + | +# | | 192.0.2.1/28 192.0.2.17/28 | | +# | | | | +# | \______________ _____________/ | +# | \ / | +# | + $h1 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | SW + $swp1 | +# | _______________/ \_______________ | +# | / \ | +# | +-|--------------+ +--------------|-+ | +# | | + $swp1.10 | | $swp1.11 + | | +# | | | | | | +# | | BR10 | | BR11 | | +# | | | | | | +# | | + $swp2.10 | | $swp2.11 + | | +# | +-|--------------+ +--------------|-+ | +# | \_______________ ______________/ | +# | \ / | +# | + $swp2 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | H2 + $h2 | +# | ______________/ \______________ | +# | / \ | +# | | | | +# | + $h2.10 $h2.11 + | +# | 192.0.2.2/28 192.0.2.18/28 | +# +-------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC="yes" +source $lib_dir/lib.sh + +ipaddr() +{ + local host=$1; shift + local vlan=$1; shift + + echo 192.0.2.$((16 * (vlan - 10) + host)) +} + +host_create() +{ + local dev=$1; shift + local host=$1; shift + + simple_if_init $dev + mtu_set $dev 10000 + + vlan_create $dev 10 v$dev $(ipaddr $host 10)/28 + ip link set dev $dev.10 type vlan egress 0:0 + + vlan_create $dev 11 v$dev $(ipaddr $host 11)/28 + ip link set dev $dev.11 type vlan egress 0:1 +} + +host_destroy() +{ + local dev=$1; shift + + vlan_destroy $dev 11 + vlan_destroy $dev 10 + mtu_restore $dev + simple_if_fini $dev +} + +h1_create() +{ + host_create $h1 1 +} + +h1_destroy() +{ + host_destroy $h1 +} + +h2_create() +{ + host_create $h2 2 + + tc qdisc add dev $h2 clsact + tc filter add dev $h2 ingress pref 1010 prot 802.1q \ + flower $TCFLAGS vlan_id 10 action pass + tc filter add dev $h2 ingress pref 1011 prot 802.1q \ + flower $TCFLAGS vlan_id 11 action pass +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + host_destroy $h2 +} + +switch_create() +{ + local intf + local vlan + + ip link add dev br10 type bridge + ip link add dev br11 type bridge + + for intf in $swp1 $swp2; do + ip link set dev $intf up + mtu_set $intf 10000 + + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br$vlan + ip link set dev $intf.$vlan up + done + done + + for vlan in 10 11; do + ip link set dev $swp1.$vlan type vlan ingress 0:0 1:1 + done + + ip link set dev br10 up + ip link set dev br11 up +} + +switch_destroy() +{ + local intf + local vlan + + # A test may have been interrupted mid-run, with Qdisc installed. Delete + # it here. + tc qdisc del dev $swp2 root 2>/dev/null + + ip link set dev br11 down + ip link set dev br10 down + + for intf in $swp2 $swp1; do + for vlan in 11 10; do + ip link set dev $intf.$vlan down + ip link set dev $intf.$vlan nomaster + vlan_destroy $intf $vlan + done + + mtu_restore $intf + ip link set dev $intf down + done + + ip link del dev br11 + ip link del dev br10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + swp4=${NETIFS[p7]} + swp5=${NETIFS[p8]} + + h2_mac=$(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 $h1.10 $(ipaddr 2 10) " vlan 10" + ping_test $h1.11 $(ipaddr 2 11) " vlan 11" +} + +tbf_get_counter() +{ + local vlan=$1; shift + + tc_rule_stats_get $h2 10$vlan ingress .bytes +} + +do_tbf_test() +{ + local vlan=$1; shift + local mbit=$1; shift + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 2 $vlan) $h2_mac + sleep 5 # Wait for the burst to dwindle + + local t2=$(busywait_for_counter 1000 +1 tbf_get_counter $vlan) + sleep 10 + local t3=$(tbf_get_counter $vlan) + stop_traffic + + RET=0 + + # Note: TBF uses 10^6 Mbits, not 2^20 ones. + local er=$((mbit * 1000 * 1000)) + local nr=$(rate $t2 $t3 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-5 <= nr_pct && nr_pct <= 5)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-5%." + + log_test "TC $((vlan - 10)): TBF rate ${mbit}Mbit" +} diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh new file mode 100755 index 000000000000..84fb6cab88e4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="ets strict" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh new file mode 100644 index 000000000000..8bd85da1905a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh @@ -0,0 +1,39 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 parent 10:3 handle 103: tbf \ + rate 400Mbit burst $bs limit 1M + tc qdisc replace dev $swp2 parent 10:2 handle 102: tbf \ + rate 800Mbit burst $bs limit 1M + + do_tbf_test 10 400 $bs + do_tbf_test 11 800 $bs +} + +tbf_test() +{ + # This test is used for both ETS and PRIO. Even though we only need two + # bands, PRIO demands a minimum of three. + tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0 + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh new file mode 100755 index 000000000000..9c8cb1cb9ba4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="prio bands" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh new file mode 100755 index 000000000000..72aa21ba88c7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh @@ -0,0 +1,33 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 root handle 108: tbf \ + rate 400Mbit burst $bs limit 1M + do_tbf_test 10 400 $bs +} + +tbf_test() +{ + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore new file mode 100644 index 000000000000..d72f07642738 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -0,0 +1,2 @@ +mptcp_connect +*.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile new file mode 100644 index 000000000000..93de52016dde --- /dev/null +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g + +TEST_PROGS := mptcp_connect.sh + +TEST_GEN_FILES = mptcp_connect + +EXTRA_CLEAN := *.pcap + +include ../../lib.mk diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config new file mode 100644 index 000000000000..2499824d9e1c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/config @@ -0,0 +1,4 @@ +CONFIG_MPTCP=y +CONFIG_MPTCP_IPV6=y +CONFIG_VETH=y +CONFIG_NET_SCH_NETEM=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c new file mode 100644 index 000000000000..a3dccd816ae4 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <errno.h> +#include <limits.h> +#include <fcntl.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> + +#include <sys/poll.h> +#include <sys/sendfile.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/mman.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +extern int optind; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef TCP_ULP +#define TCP_ULP 31 +#endif + +static bool listen_mode; +static int poll_timeout; + +enum cfg_mode { + CFG_MODE_POLL, + CFG_MODE_MMAP, + CFG_MODE_SENDFILE, +}; + +static enum cfg_mode cfg_mode = CFG_MODE_POLL; +static const char *cfg_host; +static const char *cfg_port = "12000"; +static int cfg_sock_proto = IPPROTO_MPTCP; +static bool tcpulp_audit; +static int pf = AF_INET; +static int cfg_sndbuf; + +static void die_usage(void) +{ + fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] -m mode]" + "[ -l ] [ -t timeout ] connect_address\n"); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen, + char *host, socklen_t hostlen, + char *serv, socklen_t servlen) +{ + int flags = NI_NUMERICHOST | NI_NUMERICSERV; + int err = getnameinfo(addr, addrlen, host, hostlen, serv, servlen, + flags); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getnameinfo: %s\n", errstr); + exit(1); + } +} + +static void xgetaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + int err = getaddrinfo(node, service, hints, res); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", + node ? node : "", service ? service : "", errstr); + exit(1); + } +} + +static void set_sndbuf(int fd, unsigned int size) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size)); + if (err) { + perror("set SO_SNDBUF"); + exit(1); + } +} + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock; + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + .ai_flags = AI_PASSIVE | AI_NUMERICHOST + }; + + hints.ai_family = pf; + + struct addrinfo *a, *addr; + int one = 1; + + xgetaddrinfo(listenaddr, port, &hints, &addr); + hints.ai_family = pf; + + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, cfg_sock_proto); + if (sock < 0) + continue; + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("bind"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + + if (sock < 0) { + fprintf(stderr, "Could not create listen socket\n"); + return sock; + } + + if (listen(sock, 20)) { + perror("listen"); + close(sock); + return -1; + } + + return sock; +} + +static bool sock_test_tcpulp(const char * const remoteaddr, + const char * const port) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1, ret = 0; + bool test_pass = false; + + hints.ai_family = AF_INET; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, IPPROTO_TCP); + if (sock < 0) { + perror("socket"); + continue; + } + ret = setsockopt(sock, IPPROTO_TCP, TCP_ULP, "mptcp", + sizeof("mptcp")); + if (ret == -1 && errno == EOPNOTSUPP) + test_pass = true; + close(sock); + + if (test_pass) + break; + if (!ret) + fprintf(stderr, + "setsockopt(TCP_ULP) returned 0\n"); + else + perror("setsockopt(TCP_ULP)"); + } + return test_pass; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1; + + hints.ai_family = pf; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, proto); + if (sock < 0) { + perror("socket"); + continue; + } + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("connect()"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + return sock; +} + +static size_t do_rnd_write(const int fd, char *buf, const size_t len) +{ + unsigned int do_w; + ssize_t bw; + + do_w = rand() & 0xffff; + if (do_w == 0 || do_w > len) + do_w = len; + + bw = write(fd, buf, do_w); + if (bw < 0) + perror("write"); + + return bw; +} + +static size_t do_write(const int fd, char *buf, const size_t len) +{ + size_t offset = 0; + + while (offset < len) { + size_t written; + ssize_t bw; + + bw = write(fd, buf + offset, len - offset); + if (bw < 0) { + perror("write"); + return 0; + } + + written = (size_t)bw; + offset += written; + } + + return offset; +} + +static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) +{ + size_t cap = rand(); + + cap &= 0xffff; + + if (cap == 0) + cap = 1; + else if (cap > len) + cap = len; + + return read(fd, buf, cap); +} + +static void set_nonblock(int fd) +{ + int flags = fcntl(fd, F_GETFL); + + if (flags == -1) + return; + + fcntl(fd, F_SETFL, flags | O_NONBLOCK); +} + +static int copyfd_io_poll(int infd, int peerfd, int outfd) +{ + struct pollfd fds = { + .fd = peerfd, + .events = POLLIN | POLLOUT, + }; + unsigned int woff = 0, wlen = 0; + char wbuf[8192]; + + set_nonblock(peerfd); + + for (;;) { + char rbuf[8192]; + ssize_t len; + + if (fds.events == 0) + break; + + switch (poll(&fds, 1, poll_timeout)) { + case -1: + if (errno == EINTR) + continue; + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: poll timed out (events: " + "POLLIN %u, POLLOUT %u)\n", __func__, + fds.events & POLLIN, fds.events & POLLOUT); + return 2; + } + + if (fds.revents & POLLIN) { + len = do_rnd_read(peerfd, rbuf, sizeof(rbuf)); + if (len == 0) { + /* no more data to receive: + * peer has closed its write side + */ + fds.events &= ~POLLIN; + + if ((fds.events & POLLOUT) == 0) + /* and nothing more to send */ + break; + + /* Else, still have data to transmit */ + } else if (len < 0) { + perror("read"); + return 3; + } + + do_write(outfd, rbuf, len); + } + + if (fds.revents & POLLOUT) { + if (wlen == 0) { + woff = 0; + wlen = read(infd, wbuf, sizeof(wbuf)); + } + + if (wlen > 0) { + ssize_t bw; + + bw = do_rnd_write(peerfd, wbuf + woff, wlen); + if (bw < 0) + return 111; + + woff += bw; + wlen -= bw; + } else if (wlen == 0) { + /* We have no more data to send. */ + fds.events &= ~POLLOUT; + + if ((fds.events & POLLIN) == 0) + /* ... and peer also closed already */ + break; + + /* ... but we still receive. + * Close our write side. + */ + shutdown(peerfd, SHUT_WR); + } else { + if (errno == EINTR) + continue; + perror("read"); + return 4; + } + } + + if (fds.revents & (POLLERR | POLLNVAL)) { + fprintf(stderr, "Unexpected revents: " + "POLLERR/POLLNVAL(%x)\n", fds.revents); + return 5; + } + } + + close(peerfd); + return 0; +} + +static int do_recvfile(int infd, int outfd) +{ + ssize_t r; + + do { + char buf[16384]; + + r = do_rnd_read(infd, buf, sizeof(buf)); + if (r > 0) { + if (write(outfd, buf, r) != r) + break; + } else if (r < 0) { + perror("read"); + } + } while (r > 0); + + return (int)r; +} + +static int do_mmap(int infd, int outfd, unsigned int size) +{ + char *inbuf = mmap(NULL, size, PROT_READ, MAP_SHARED, infd, 0); + ssize_t ret = 0, off = 0; + size_t rem; + + if (inbuf == MAP_FAILED) { + perror("mmap"); + return 1; + } + + rem = size; + + while (rem > 0) { + ret = write(outfd, inbuf + off, rem); + + if (ret < 0) { + perror("write"); + break; + } + + off += ret; + rem -= ret; + } + + munmap(inbuf, size); + return rem; +} + +static int get_infd_size(int fd) +{ + struct stat sb; + ssize_t count; + int err; + + err = fstat(fd, &sb); + if (err < 0) { + perror("fstat"); + return -1; + } + + if ((sb.st_mode & S_IFMT) != S_IFREG) { + fprintf(stderr, "%s: stdin is not a regular file\n", __func__); + return -2; + } + + count = sb.st_size; + if (count > INT_MAX) { + fprintf(stderr, "File too large: %zu\n", count); + return -3; + } + + return (int)count; +} + +static int do_sendfile(int infd, int outfd, unsigned int count) +{ + while (count > 0) { + ssize_t r; + + r = sendfile(outfd, infd, NULL, count); + if (r < 0) { + perror("sendfile"); + return 3; + } + + count -= r; + } + + return 0; +} + +static int copyfd_io_mmap(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_mmap(infd, peerfd, size); + } else { + err = do_mmap(infd, peerfd, size); + if (err) + return err; + + shutdown(peerfd, SHUT_WR); + + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io_sendfile(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_sendfile(infd, peerfd, size); + } else { + err = do_sendfile(infd, peerfd, size); + if (err) + return err; + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io(int infd, int peerfd, int outfd) +{ + int file_size; + + switch (cfg_mode) { + case CFG_MODE_POLL: + return copyfd_io_poll(infd, peerfd, outfd); + case CFG_MODE_MMAP: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_mmap(infd, peerfd, outfd, file_size); + case CFG_MODE_SENDFILE: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_sendfile(infd, peerfd, outfd, file_size); + } + + fprintf(stderr, "Invalid mode %d\n", cfg_mode); + + die_usage(); + return 1; +} + +static void check_sockaddr(int pf, struct sockaddr_storage *ss, + socklen_t salen) +{ + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + socklen_t wanted_size = 0; + + switch (pf) { + case AF_INET: + wanted_size = sizeof(*sin); + sin = (void *)ss; + if (!sin->sin_port) + fprintf(stderr, "accept: something wrong: ip connection from port 0"); + break; + case AF_INET6: + wanted_size = sizeof(*sin6); + sin6 = (void *)ss; + if (!sin6->sin6_port) + fprintf(stderr, "accept: something wrong: ipv6 connection from port 0"); + break; + default: + fprintf(stderr, "accept: Unknown pf %d, salen %u\n", pf, salen); + return; + } + + if (salen != wanted_size) + fprintf(stderr, "accept: size mismatch, got %d expected %d\n", + (int)salen, wanted_size); + + if (ss->ss_family != pf) + fprintf(stderr, "accept: pf mismatch, expect %d, ss_family is %d\n", + (int)ss->ss_family, pf); +} + +static void check_getpeername(int fd, struct sockaddr_storage *ss, socklen_t salen) +{ + struct sockaddr_storage peerss; + socklen_t peersalen = sizeof(peerss); + + if (getpeername(fd, (struct sockaddr *)&peerss, &peersalen) < 0) { + perror("getpeername"); + return; + } + + if (peersalen != salen) { + fprintf(stderr, "%s: %d vs %d\n", __func__, peersalen, salen); + return; + } + + if (memcmp(ss, &peerss, peersalen)) { + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + char c[INET6_ADDRSTRLEN]; + char d[INET6_ADDRSTRLEN]; + + xgetnameinfo((struct sockaddr *)ss, salen, + a, sizeof(a), b, sizeof(b)); + + xgetnameinfo((struct sockaddr *)&peerss, peersalen, + c, sizeof(c), d, sizeof(d)); + + fprintf(stderr, "%s: memcmp failure: accept %s vs peername %s, %s vs %s salen %d vs %d\n", + __func__, a, c, b, d, peersalen, salen); + } +} + +static void check_getpeername_connect(int fd) +{ + struct sockaddr_storage ss; + socklen_t salen = sizeof(ss); + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + + if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { + perror("getpeername"); + return; + } + + xgetnameinfo((struct sockaddr *)&ss, salen, + a, sizeof(a), b, sizeof(b)); + + if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, + cfg_host, a, cfg_port, b); +} + +int main_loop_s(int listensock) +{ + struct sockaddr_storage ss; + struct pollfd polls; + socklen_t salen; + int remotesock; + + polls.fd = listensock; + polls.events = POLLIN; + + switch (poll(&polls, 1, poll_timeout)) { + case -1: + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: timed out\n", __func__); + close(listensock); + return 2; + } + + salen = sizeof(ss); + remotesock = accept(listensock, (struct sockaddr *)&ss, &salen); + if (remotesock >= 0) { + check_sockaddr(pf, &ss, salen); + check_getpeername(remotesock, &ss, salen); + + return copyfd_io(0, remotesock, 1); + } + + perror("accept"); + + return 1; +} + +static void init_rng(void) +{ + int fd = open("/dev/urandom", O_RDONLY); + unsigned int foo; + + if (fd > 0) { + int ret = read(fd, &foo, sizeof(foo)); + + if (ret < 0) + srand(fd + foo); + close(fd); + } + + srand(foo); +} + +int main_loop(void) +{ + int fd; + + /* listener is ready. */ + fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto); + if (fd < 0) + return 2; + + check_getpeername_connect(fd); + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return copyfd_io(0, fd, 1); +} + +int parse_proto(const char *proto) +{ + if (!strcasecmp(proto, "MPTCP")) + return IPPROTO_MPTCP; + if (!strcasecmp(proto, "TCP")) + return IPPROTO_TCP; + + fprintf(stderr, "Unknown protocol: %s\n.", proto); + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_mode(const char *mode) +{ + if (!strcasecmp(mode, "poll")) + return CFG_MODE_POLL; + if (!strcasecmp(mode, "mmap")) + return CFG_MODE_MMAP; + if (!strcasecmp(mode, "sendfile")) + return CFG_MODE_SENDFILE; + + fprintf(stderr, "Unknown test mode: %s\n", mode); + fprintf(stderr, "Supported modes are:\n"); + fprintf(stderr, "\t\t\"poll\" - interleaved read/write using poll()\n"); + fprintf(stderr, "\t\t\"mmap\" - send entire input file (mmap+write), then read response (-l will read input first)\n"); + fprintf(stderr, "\t\t\"sendfile\" - send entire input file (sendfile), then read response (-l will read input first)\n"); + + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_sndbuf(const char *size) +{ + unsigned long s; + + errno = 0; + + s = strtoul(size, NULL, 0); + + if (errno) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(errno)); + die_usage(); + } + + if (s > INT_MAX) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(ERANGE)); + die_usage(); + } + + cfg_sndbuf = s; + + return 0; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "6lp:s:hut:m:b:")) != -1) { + switch (c) { + case 'l': + listen_mode = true; + break; + case 'p': + cfg_port = optarg; + break; + case 's': + cfg_sock_proto = parse_proto(optarg); + break; + case 'h': + die_usage(); + break; + case 'u': + tcpulp_audit = true; + break; + case '6': + pf = AF_INET6; + break; + case 't': + poll_timeout = atoi(optarg) * 1000; + if (poll_timeout <= 0) + poll_timeout = -1; + break; + case 'm': + cfg_mode = parse_mode(optarg); + break; + case 'b': + cfg_sndbuf = parse_sndbuf(optarg); + break; + } + } + + if (optind + 1 != argc) + die_usage(); + cfg_host = argv[optind]; + + if (strchr(cfg_host, ':')) + pf = AF_INET6; +} + +int main(int argc, char *argv[]) +{ + init_rng(); + + parse_opts(argc, argv); + + if (tcpulp_audit) + return sock_test_tcpulp(cfg_host, cfg_port) ? 0 : 1; + + if (listen_mode) { + int fd = sock_listen_mptcp(cfg_host, cfg_port); + + if (fd < 0) + return 1; + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return main_loop_s(fd); + } + + return main_loop(); +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh new file mode 100755 index 000000000000..d573a0feb98d --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -0,0 +1,595 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +time_start=$(date +%s) + +optstring="b:d:e:l:r:h4cm:" +ret=0 +sin="" +sout="" +cin="" +cout="" +ksft_skip=4 +capture=false +timeout=30 +ipv6=true +ethtool_random_on=true +tc_delay="$((RANDOM%400))" +tc_loss=$((RANDOM%101)) +tc_reorder="" +testmode="" +sndbuf=0 +options_log=true + +if [ $tc_loss -eq 100 ];then + tc_loss=1% +elif [ $tc_loss -ge 10 ]; then + tc_loss=0.$tc_loss% +elif [ $tc_loss -ge 1 ]; then + tc_loss=0.0$tc_loss% +else + tc_loss="" +fi + +usage() { + echo "Usage: $0 [ -a ]" + echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)" + echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)" + echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)" + echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" + echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" + echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-b: set sndbuf value (default: use kernel default)" + echo -e "\t-m: test mode (poll, sendfile; default: poll)" +} + +while getopts "$optstring" option;do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "d") + if [ $OPTARG -ge 0 ];then + tc_delay="$OPTARG" + else + echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "e") + ethtool_args="$ethtool_args $OPTARG off" + ethtool_random_on=false + ;; + "l") + tc_loss="$OPTARG" + ;; + "r") + tc_reorder="$OPTARG" + ;; + "4") + ipv6=false + ;; + "c") + capture=true + ;; + "b") + if [ $OPTARG -ge 0 ];then + sndbuf="$OPTARG" + else + echo "-s requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "m") + testmode="$OPTARG" + ;; + "?") + usage $0 + exit 1 + ;; + esac +done + +sec=$(date +%s) +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +ns2="ns2-$rndh" +ns3="ns3-$rndh" +ns4="ns4-$rndh" + +TEST_COUNT=0 + +cleanup() +{ + rm -f "$cin" "$cout" + rm -f "$sin" "$sout" + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns del $netns + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +sin=$(mktemp) +sout=$(mktemp) +cin=$(mktemp) +cout=$(mktemp) +capout=$(mktemp) +trap cleanup EXIT + +for i in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up +done + +# "$ns1" ns2 ns3 ns4 +# ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3 +# - drop 1% -> reorder 25% +# <- TSO off - + +ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" +ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth2 netns "$ns3" +ip link add ns3eth4 netns "$ns3" type veth peer name ns4eth3 netns "$ns4" + +ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2 +ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad + +ip -net "$ns1" link set ns1eth2 up +ip -net "$ns1" route add default via 10.0.1.2 +ip -net "$ns1" route add default via dead:beef:1::2 + +ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1 +ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad +ip -net "$ns2" link set ns2eth1 up + +ip -net "$ns2" addr add 10.0.2.1/24 dev ns2eth3 +ip -net "$ns2" addr add dead:beef:2::1/64 dev ns2eth3 nodad +ip -net "$ns2" link set ns2eth3 up +ip -net "$ns2" route add default via 10.0.2.2 +ip -net "$ns2" route add default via dead:beef:2::2 +ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns3" addr add 10.0.2.2/24 dev ns3eth2 +ip -net "$ns3" addr add dead:beef:2::2/64 dev ns3eth2 nodad +ip -net "$ns3" link set ns3eth2 up + +ip -net "$ns3" addr add 10.0.3.2/24 dev ns3eth4 +ip -net "$ns3" addr add dead:beef:3::2/64 dev ns3eth4 nodad +ip -net "$ns3" link set ns3eth4 up +ip -net "$ns3" route add default via 10.0.2.1 +ip -net "$ns3" route add default via dead:beef:2::1 +ip netns exec "$ns3" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns3" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns4" addr add 10.0.3.1/24 dev ns4eth3 +ip -net "$ns4" addr add dead:beef:3::1/64 dev ns4eth3 nodad +ip -net "$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 + +set_ethtool_flags() { + local ns="$1" + local dev="$2" + local flags="$3" + + ip netns exec $ns ethtool -K $dev $flags 2>/dev/null + [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" +} + +set_random_ethtool_flags() { + local flags="" + local r=$RANDOM + + local pick1=$((r & 1)) + local pick2=$((r & 2)) + local pick3=$((r & 4)) + + [ $pick1 -ne 0 ] && flags="tso off" + [ $pick2 -ne 0 ] && flags="$flags gso off" + [ $pick3 -ne 0 ] && flags="$flags gro off" + + [ -z "$flags" ] && return + + set_ethtool_flags "$1" "$2" "$flags" +} + +if $ethtool_random_on;then + set_random_ethtool_flags "$ns3" ns3eth2 + set_random_ethtool_flags "$ns4" ns4eth3 +else + set_ethtool_flags "$ns3" ns3eth2 "$ethtool_args" + set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args" +fi + +print_file_err() +{ + ls -l "$1" 1>&2 + echo "Trailing bytes are: " + tail -c 27 "$1" +} + +check_transfer() +{ + local in=$1 + local out=$2 + local what=$3 + + cmp "$in" "$out" > /dev/null 2>&1 + if [ $? -ne 0 ] ;then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + + return 1 + fi + + return 0 +} + +check_mptcp_disabled() +{ + local disabled_ns + disabled_ns="ns_disabled-$sech-$(mktemp -u XXXXXX)" + ip netns add ${disabled_ns} || exit $ksft_skip + + # net.mptcp.enabled should be enabled by default + if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then + echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]" + ret=1 + return 1 + fi + ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0 + + local err=0 + LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \ + grep -q "^socket: Protocol not available$" && err=1 + ip netns delete ${disabled_ns} + + if [ ${err} -eq 0 ]; then + echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" + ret=1 + return 1 + fi + + echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]" + return 0 +} + +check_mptcp_ulp_setsockopt() +{ + local t retval + t="ns_ulp-$sech-$(mktemp -u XXXXXX)" + + ip netns add ${t} || exit $ksft_skip + if ! ip netns exec ${t} ./mptcp_connect -u -p 10000 -s TCP 127.0.0.1 2>&1; then + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) allowed\t[ FAIL ]\n" + retval=1 + ret=$retval + else + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) blocked\t[ OK ]\n" + retval=0 + fi + ip netns del ${t} + return $retval +} + +# $1: IP address +is_v6() +{ + [ -z "${1##*:*}" ] +} + +do_ping() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local ping_args="-q -c 1" + + if is_v6 "${connect_addr}"; then + $ipv6 || return 0 + ping_args="${ping_args} -6" + fi + + ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null + if [ $? -ne 0 ] ; then + echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 + ret=1 + + return 1 + fi + + return 0 +} + +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local local_addr="$6" + local extra_args="" + + local port + port=$((10000+$TEST_COUNT)) + TEST_COUNT=$((TEST_COUNT+1)) + + if [ "$sndbuf" -gt 0 ]; then + extra_args="$extra_args -b $sndbuf" + fi + + if [ -n "$testmode" ]; then + extra_args="$extra_args -m $testmode" + fi + + if [ -n "$extra_args" ] && $options_log; then + options_log=false + echo "INFO: extra options: $extra_args" + fi + + :> "$cout" + :> "$sout" + :> "$capout" + + local addr_port + addr_port=$(printf "%s:%d" ${connect_addr} ${port}) + printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto} + + if $capture; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap" + + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + local cappid=$! + + sleep 1 + fi + + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + local start + start=$(date +%s%3N) + ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" & + local cpid=$! + + wait $cpid + local retc=$? + wait $spid + local rets=$? + + local stop + stop=$(date +%s%3N) + + if $capture; then + sleep 1 + kill $cappid + fi + + local duration + duration=$((stop-start)) + duration=$(printf "(duration %05sms)" $duration) + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2 + echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2 + ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port" + echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2 + ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port" + + cat "$capout" + return 1 + fi + + check_transfer $sin $cout "file received by client" + retc=$? + check_transfer $cin $sout "file received by server" + rets=$? + + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + echo "$duration [ OK ]" + cat "$capout" + return 0 + fi + + cat "$capout" + return 1 +} + +make_file() +{ + local name=$1 + local who=$2 + + local SIZE TSIZE + SIZE=$((RANDOM % (1024 * 8))) + TSIZE=$((SIZE * 1024)) + + dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + + SIZE=$((RANDOM % 1024)) + SIZE=$((SIZE + 128)) + TSIZE=$((TSIZE + SIZE)) + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $TSIZE) containing data sent by $who" +} + +run_tests_lo() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local loopback="$4" + local lret=0 + + # skip if test programs are running inside same netns for subsequent runs. + if [ $loopback -eq 0 ] && [ ${listener_ns} = ${connector_ns} ]; then + return 0 + fi + + # skip if we don't want v6 + if ! $ipv6 && is_v6 "${connect_addr}"; then + return 0 + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + else + local_addr="0.0.0.0" + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + return 0 +} + +run_tests() +{ + run_tests_lo $1 $2 $3 0 +} + +make_file "$cin" "client" +make_file "$sin" "server" + +check_mptcp_disabled + +check_mptcp_ulp_setsockopt + +echo "INFO: validating network environment with pings" +for sender in "$ns1" "$ns2" "$ns3" "$ns4";do + do_ping "$ns1" $sender 10.0.1.1 + do_ping "$ns1" $sender dead:beef:1::1 + + do_ping "$ns2" $sender 10.0.1.2 + do_ping "$ns2" $sender dead:beef:1::2 + do_ping "$ns2" $sender 10.0.2.1 + do_ping "$ns2" $sender dead:beef:2::1 + + do_ping "$ns3" $sender 10.0.2.2 + do_ping "$ns3" $sender dead:beef:2::2 + do_ping "$ns3" $sender 10.0.3.2 + do_ping "$ns3" $sender dead:beef:3::2 + + do_ping "$ns4" $sender 10.0.3.1 + do_ping "$ns4" $sender dead:beef:3::1 +done + +[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss +echo -n "INFO: Using loss of $tc_loss " +test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " + +if [ -z "${tc_reorder}" ]; then + reorder1=$((RANDOM%10)) + reorder1=$((100 - reorder1)) + reorder2=$((RANDOM%100)) + + if [ $tc_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then + tc_reorder="reorder ${reorder1}% ${reorder2}%" + echo -n "$tc_reorder " + fi +elif [ "$tc_reorder" = "0" ];then + tc_reorder="" +elif [ "$tc_delay" -gt 0 ];then + # reordering requires some delay + tc_reorder="reorder $tc_reorder" + echo -n "$tc_reorder " +fi + +echo "on ns3eth4" + +tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${tc_delay}ms $tc_reorder + +for sender in $ns1 $ns2 $ns3 $ns4;do + run_tests_lo "$ns1" "$sender" 10.0.1.1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback test" 1>&2 + exit $ret + fi + run_tests_lo "$ns1" $sender dead:beef:1::1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback v6 test" 2>&1 + exit $ret + fi + + run_tests "$ns2" $sender 10.0.1.2 + run_tests "$ns2" $sender dead:beef:1::2 + run_tests "$ns2" $sender 10.0.2.1 + run_tests "$ns2" $sender dead:beef:2::1 + + run_tests "$ns3" $sender 10.0.2.2 + run_tests "$ns3" $sender dead:beef:2::2 + run_tests "$ns3" $sender 10.0.3.2 + run_tests "$ns3" $sender dead:beef:3::2 + + run_tests "$ns4" $sender 10.0.3.1 + run_tests "$ns4" $sender dead:beef:3::1 +done + +time_end=$(date +%s) +time_run=$((time_end-time_start)) + +echo "Time: ${time_run} seconds" + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings new file mode 100644 index 000000000000..026384c189c9 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/settings @@ -0,0 +1 @@ +timeout=450 diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index c08f4db8330d..93208caacbe6 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -74,7 +74,14 @@ struct sock_args { int use_cmsg; const char *dev; int ifindex; + const char *password; + /* prefix for MD5 password */ + union { + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } md5_prefix; + unsigned int prefix_len; /* expected addresses and device index for connection */ int expected_ifindex; @@ -200,20 +207,33 @@ static void log_address(const char *desc, struct sockaddr *sa) fflush(stdout); } -static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args) { - struct tcp_md5sig md5sig; - int keylen = password ? strlen(password) : 0; + int keylen = strlen(args->password); + struct tcp_md5sig md5sig = {}; + int opt = TCP_MD5SIG; int rc; - memset(&md5sig, 0, sizeof(md5sig)); - memcpy(&md5sig.tcpm_addr, addr, alen); md5sig.tcpm_keylen = keylen; + memcpy(md5sig.tcpm_key, args->password, keylen); + + if (args->prefix_len) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_PREFIX; + + md5sig.tcpm_prefixlen = args->prefix_len; + addr = &args->md5_prefix; + } + memcpy(&md5sig.tcpm_addr, addr, alen); + + if (args->ifindex) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; - if (keylen) - memcpy(md5sig.tcpm_key, password, keylen); + md5sig.tcpm_ifindex = args->ifindex; + } - rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); if (rc < 0) { /* ENOENT is harmless. Returned when a password is cleared */ if (errno == ENOENT) @@ -254,7 +274,7 @@ static int tcp_md5_remote(int sd, struct sock_args *args) exit(1); } - if (tcp_md5sig(sd, addr, alen, args->password)) + if (tcp_md5sig(sd, addr, alen, args)) return -1; return 0; @@ -1194,7 +1214,7 @@ static int do_server(struct sock_args *args) if (args->password && tcp_md5_remote(lsd, args)) { close(lsd); - return -1; + return 1; } while (1) { @@ -1313,7 +1333,7 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (args->type != SOCK_STREAM) goto out; - if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + if (args->password && tcp_md5sig(sd, addr, alen, args)) goto err; if (args->bind_test_only) @@ -1405,16 +1425,18 @@ enum addr_type { ADDR_TYPE_MCAST, ADDR_TYPE_EXPECTED_LOCAL, ADDR_TYPE_EXPECTED_REMOTE, + ADDR_TYPE_MD5_PREFIX, }; static int convert_addr(struct sock_args *args, const char *_str, enum addr_type atype) { + int pfx_len_max = args->version == AF_INET6 ? 128 : 32; int family = args->version; + char *str, *dev, *sep; struct in6_addr *in6; struct in_addr *in; const char *desc; - char *str, *dev; void *addr; int rc = 0; @@ -1443,6 +1465,30 @@ static int convert_addr(struct sock_args *args, const char *_str, desc = "expected remote"; addr = &args->expected_raddr; break; + case ADDR_TYPE_MD5_PREFIX: + desc = "md5 prefix"; + if (family == AF_INET) { + args->md5_prefix.v4.sin_family = AF_INET; + addr = &args->md5_prefix.v4.sin_addr; + } else if (family == AF_INET6) { + args->md5_prefix.v6.sin6_family = AF_INET6; + addr = &args->md5_prefix.v6.sin6_addr; + } else + return 1; + + sep = strchr(str, '/'); + if (sep) { + *sep = '\0'; + sep++; + if (str_to_uint(sep, 1, pfx_len_max, + &args->prefix_len) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + } else { + args->prefix_len = pfx_len_max; + } + break; default: log_error("unknown address type"); exit(1); @@ -1522,7 +1568,7 @@ static char *random_msg(int len) return m; } -#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:m:d:SCi6L:0:1:2:Fbq" static void print_usage(char *prog) { @@ -1551,6 +1597,7 @@ static void print_usage(char *prog) " -n num number of times to send message\n" "\n" " -M password use MD5 sum protection\n" + " -m prefix/len prefix and length to use for MD5 key\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1642,6 +1689,10 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case 'm': + if (convert_addr(&args, optarg, ADDR_TYPE_MD5_PREFIX) < 0) + return 1; + break; case 'S': args.use_setsockopt = 1; break; @@ -1706,11 +1757,16 @@ int main(int argc, char *argv[]) } if (args.password && - (!args.has_remote_ip || args.type != SOCK_STREAM)) { + ((!args.has_remote_ip && !args.prefix_len) || args.type != SOCK_STREAM)) { log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); return 1; } + if (args.prefix_len && !args.password) { + log_error("Prefix range for MD5 protection specified without a password\n"); + return 1; + } + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { fprintf(stderr, "Device binding not specified\n"); return 1; diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 34df4c8882af..383bac05ac32 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -12,7 +12,11 @@ #include <arpa/inet.h> #include <error.h> #include <errno.h> +#include <inttypes.h> #include <linux/net_tstamp.h> +#include <linux/errqueue.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> #include <stdbool.h> #include <stdlib.h> #include <stdio.h> @@ -28,7 +32,7 @@ static int cfg_clockid = CLOCK_TAI; static bool cfg_do_ipv4; static bool cfg_do_ipv6; static uint16_t cfg_port = 8000; -static int cfg_variance_us = 2000; +static int cfg_variance_us = 4000; static uint64_t glob_tstart; @@ -43,6 +47,9 @@ static struct timed_send cfg_in[MAX_NUM_PKT]; static struct timed_send cfg_out[MAX_NUM_PKT]; static int cfg_num_pkt; +static int cfg_errq_level; +static int cfg_errq_type; + static uint64_t gettime_ns(void) { struct timespec ts; @@ -90,13 +97,15 @@ static void do_send_one(int fdt, struct timed_send *ts) } -static void do_recv_one(int fdr, struct timed_send *ts) +static bool do_recv_one(int fdr, struct timed_send *ts) { int64_t tstop, texpect; char rbuf[2]; int ret; ret = recv(fdr, rbuf, sizeof(rbuf), 0); + if (ret == -1 && errno == EAGAIN) + return true; if (ret == -1) error(1, errno, "read"); if (ret != 1) @@ -113,6 +122,8 @@ static void do_recv_one(int fdr, struct timed_send *ts) if (labs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); + + return false; } static void do_recv_verify_empty(int fdr) @@ -125,12 +136,70 @@ static void do_recv_verify_empty(int fdr) error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno); } +static void do_recv_errqueue_timeout(int fdt) +{ + char control[CMSG_SPACE(sizeof(struct sock_extended_err)) + + CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0}; + char data[sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + 1]; + struct sock_extended_err *err; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + int64_t tstamp = 0; + int ret; + + iov.iov_base = data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + while (1) { + ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != MSG_ERRQUEUE) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + + cm = CMSG_FIRSTHDR(&msg); + if (cm->cmsg_level != cfg_errq_level || + cm->cmsg_type != cfg_errq_type) + error(1, 0, "errqueue: type 0x%x.0x%x\n", + cm->cmsg_level, cm->cmsg_type); + + err = (struct sock_extended_err *)CMSG_DATA(cm); + if (err->ee_origin != SO_EE_ORIGIN_TXTIME) + error(1, 0, "errqueue: origin 0x%x\n", err->ee_origin); + if (err->ee_code != ECANCELED) + error(1, 0, "errqueue: code 0x%x\n", err->ee_code); + + tstamp = ((int64_t) err->ee_data) << 32 | err->ee_info; + tstamp -= (int64_t) glob_tstart; + tstamp /= 1000 * 1000; + fprintf(stderr, "send: pkt %c at %" PRId64 "ms dropped\n", + data[ret - 1], tstamp); + + msg.msg_flags = 0; + msg.msg_controllen = sizeof(control); + } + + error(1, 0, "recv: timeout"); +} + static void setsockopt_txtime(int fd) { struct sock_txtime so_txtime_val = { .clockid = cfg_clockid }; struct sock_txtime so_txtime_val_read = { 0 }; socklen_t vallen = sizeof(so_txtime_val); + so_txtime_val.flags = SOF_TXTIME_REPORT_ERRORS; + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, &so_txtime_val, sizeof(so_txtime_val))) error(1, errno, "setsockopt txtime"); @@ -194,7 +263,8 @@ static void do_test(struct sockaddr *addr, socklen_t alen) for (i = 0; i < cfg_num_pkt; i++) do_send_one(fdt, &cfg_in[i]); for (i = 0; i < cfg_num_pkt; i++) - do_recv_one(fdr, &cfg_out[i]); + if (do_recv_one(fdr, &cfg_out[i])) + do_recv_errqueue_timeout(fdt); do_recv_verify_empty(fdr); @@ -280,6 +350,10 @@ int main(int argc, char **argv) addr6.sin6_family = AF_INET6; addr6.sin6_port = htons(cfg_port); addr6.sin6_addr = in6addr_loopback; + + cfg_errq_level = SOL_IPV6; + cfg_errq_type = IPV6_RECVERR; + do_test((void *)&addr6, sizeof(addr6)); } @@ -289,6 +363,10 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_port = htons(cfg_port); addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + + cfg_errq_level = SOL_IP; + cfg_errq_type = IP_RECVERR; + do_test((void *)&addr4, sizeof(addr4)); } diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh index 5aa519328a5b..3f7800eaecb1 100755 --- a/tools/testing/selftests/net/so_txtime.sh +++ b/tools/testing/selftests/net/so_txtime.sh @@ -5,7 +5,12 @@ # Run in network namespace if [[ $# -eq 0 ]]; then - ./in_netns.sh $0 __subprocess + if ! ./in_netns.sh $0 __subprocess; then + # test is time sensitive, can be flaky + echo "test failed: retry once" + ./in_netns.sh $0 __subprocess + fi + exit $? fi @@ -18,7 +23,7 @@ tc qdisc add dev lo root fq ./so_txtime -4 -6 -c mono a,10,b,20 a,10,b,20 ./so_txtime -4 -6 -c mono a,20,b,10 b,20,a,20 -if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 200000; then +if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 400000; then ! ./so_txtime -4 -6 -c tai a,-1 a,-1 ! ./so_txtime -4 -6 -c tai a,0 a,0 ./so_txtime -4 -6 -c tai a,10 a,10 diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index de1032b5ddea..08194aa44006 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -2,6 +2,7 @@ # Makefile for netfilter selftests TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ - conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh + conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ + nft_concat_range.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh new file mode 100755 index 000000000000..aca21dde102a --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -0,0 +1,1481 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# nft_concat_range.sh - Tests for sets with concatenation of ranged fields +# +# Copyright (c) 2019 Red Hat GmbH +# +# Author: Stefano Brivio <sbrivio@redhat.com> +# +# shellcheck disable=SC2154,SC2034,SC2016,SC2030,SC2031 +# ^ Configuration and templates sourced with eval, counters reused in subshells + +KSELFTEST_SKIP=4 + +# Available test groups: +# - correctness: check that packets match given entries, and only those +# - concurrency: attempt races between insertion, deletion and lookup +# - timeout: check that packets match entries until they expire +# - performance: estimate matching rate, compare with rbtree and hash baselines +TESTS="correctness concurrency timeout" +[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" + +# Set types, defined by TYPE_ variables below +TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto + net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port + net_port_mac_proto_net" + +# List of possible paths to pktgen script from kernel tree for performance tests +PKTGEN_SCRIPT_PATHS=" + ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh + pktgen/pktgen_bench_xmit_mode_netif_receive.sh" + +# Definition of set types: +# display display text for test report +# type_spec nftables set type specifier +# chain_spec nftables type specifier for rules mapping to set +# dst call sequence of format_*() functions for destination fields +# src call sequence of format_*() functions for source fields +# start initial integer used to generate addresses and ports +# count count of entries to generate and match +# src_delta number summed to destination generator for source fields +# tools list of tools for correctness and timeout tests, any can be used +# proto L4 protocol of test packets +# +# race_repeat race attempts per thread, 0 disables concurrency test for type +# flood_tools list of tools for concurrency tests, any can be used +# flood_proto L4 protocol of test packets for concurrency tests +# flood_spec nftables type specifier for concurrency tests +# +# perf_duration duration of single pktgen injection test +# perf_spec nftables type specifier for performance tests +# perf_dst format_*() functions for destination fields in performance test +# perf_src format_*() functions for source fields in performance test +# perf_entries number of set entries for performance test +# perf_proto L3 protocol of test packets +TYPE_net_port=" +display net,port +type_spec ipv4_addr . inet_service +chain_spec ip daddr . udp dport +dst addr4 port +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec ip daddr . udp dport + +perf_duration 5 +perf_spec ip daddr . udp dport +perf_dst addr4 port +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_port_net=" +display port,net +type_spec inet_service . ipv4_addr +chain_spec udp dport . ip daddr +dst port addr4 +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec udp dport . ip daddr + +perf_duration 5 +perf_spec udp dport . ip daddr +perf_dst port addr4 +perf_src +perf_entries 100 +perf_proto ipv4 +" + +TYPE_net6_port=" +display net6,port +type_spec ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport +dst addr6 port +src +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . udp dport + +perf_duration 5 +perf_spec ip6 daddr . udp dport +perf_dst addr6 port +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_port_proto=" +display port,proto +type_spec inet_service . inet_proto +chain_spec udp dport . meta l4proto +dst port proto +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec udp dport . meta l4proto +perf_dst port proto +perf_src +perf_entries 30000 +perf_proto ipv4 +" + +TYPE_net6_port_mac=" +display net6,port,mac +type_spec ipv6_addr . inet_service . ether_addr +chain_spec ip6 daddr . udp dport . ether saddr +dst addr6 port +src mac +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr +perf_dst addr6 port mac +perf_src +perf_entries 10 +perf_proto ipv6 +" + +TYPE_net6_port_mac_proto=" +display net6,port,mac,proto +type_spec ipv6_addr . inet_service . ether_addr . inet_proto +chain_spec ip6 daddr . udp dport . ether saddr . meta l4proto +dst addr6 port +src mac proto +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr . meta l4proto +perf_dst addr6 port mac proto +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_net_port_net=" +display net,port,net +type_spec ipv4_addr . inet_service . ipv4_addr +chain_spec ip daddr . udp dport . ip saddr +dst addr4 port +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . udp dport . ip saddr + +perf_duration 0 +" + +TYPE_net6_port_net6_port=" +display net6,port,net6,port +type_spec ipv6_addr . inet_service . ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport . ip6 saddr . udp sport +dst addr6 port +src addr6 port +start 10 +count 5 +src_delta 2000 +tools sendip nc +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . tcp dport . ip6 saddr . tcp sport + +perf_duration 0 +" + +TYPE_net_port_mac_proto_net=" +display net,port,mac,proto,net +type_spec ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . ether saddr . meta l4proto . ip saddr +dst addr4 port +src mac proto addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_mac=" +display net,mac +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec ip daddr . ether daddr +perf_dst addr4 mac +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_net_mac_icmp=" +display net,mac - ICMP +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools ping +proto icmp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net6_mac_icmp=" +display net6,mac - ICMPv6 +type_spec ipv6_addr . ether_addr +chain_spec ip6 daddr . ether saddr +dst addr6 +src mac +start 10 +count 50 +src_delta 2000 +tools ping +proto icmp6 + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_port_proto_net=" +display net,port,proto,net +type_spec ipv4_addr . inet_service . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . meta l4proto . ip saddr +dst addr4 port proto +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . tcp dport . meta l4proto . ip saddr + +perf_duration 0 +" + +# Set template for all tests, types and rules are filled in depending on test +set_template=' +flush ruleset + +table inet filter { + counter test { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval,timeout + } + + chain input { + type filter hook prerouting priority 0; policy accept; + ${chain_spec} @test counter name \"test\" + } +} + +table netdev perf { + counter test { + packets 0 bytes 0 + } + + counter match { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval + } + + set norange { + type ${type_spec} + } + + set noconcat { + type ${type_spec%% *} + flags interval + } + + chain test { + type filter hook ingress device veth_a priority 0; + } +} +' + +err_buf= +info_buf= + +# Append string to error buffer +err() { + err_buf="${err_buf}${1} +" +} + +# Append string to information buffer +info() { + info_buf="${info_buf}${1} +" +} + +# Flush error buffer to stdout +err_flush() { + printf "%s" "${err_buf}" + err_buf= +} + +# Flush information buffer to stdout +info_flush() { + printf "%s" "${info_buf}" + info_buf= +} + +# Setup veth pair: this namespace receives traffic, B generates it +setup_veth() { + ip netns add B + ip link add veth_a type veth peer name veth_b || return 1 + + ip link set veth_a up + ip link set veth_b netns B + + ip -n B link set veth_b up + + ip addr add dev veth_a 10.0.0.1 + ip route add default dev veth_a + + ip -6 addr add fe80::1/64 dev veth_a nodad + ip -6 addr add 2001:db8::1/64 dev veth_a nodad + ip -6 route add default dev veth_a + + ip -n B route add default dev veth_b + + ip -6 -n B addr add fe80::2/64 dev veth_b nodad + ip -6 -n B addr add 2001:db8::2/64 dev veth_b nodad + ip -6 -n B route add default dev veth_b + + B() { + ip netns exec B "$@" >/dev/null 2>&1 + } + + sleep 2 +} + +# Fill in set template and initialise set +setup_set() { + eval "echo \"${set_template}\"" | nft -f - +} + +# Check that at least one of the needed tools is available +check_tools() { + __tools= + for tool in ${tools}; do + if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ + ! nc -u -w0 1.1.1.1 1 2>/dev/null; then + # Some GNU netcat builds might not support IPv6 + __tools="${__tools} netcat-openbsd" + continue + fi + __tools="${__tools} ${tool}" + + command -v "${tool}" >/dev/null && return 0 + done + err "need one of:${__tools}, skipping" && return 1 +} + +# Set up function to send ICMP packets +setup_send_icmp() { + send_icmp() { + B ping -c1 -W1 "${dst_addr4}" >/dev/null 2>&1 + } +} + +# Set up function to send ICMPv6 packets +setup_send_icmp6() { + if command -v ping6 >/dev/null; then + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping6 -q -c1 -W1 "${dst_addr6}" + } + else + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping -q -6 -c1 -W1 "${dst_addr6}" + } + fi +} + +# Set up function to send single UDP packets on IPv4 +setup_send_udp() { + if command -v sendip >/dev/null; then + send_udp() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + [ -n "${src_addr4}" ] && src_addr4="-is ${src_addr4}" + + # shellcheck disable=SC2086 # sendip needs split options + B sendip -p ipv4 -p udp ${src_addr4} ${src_port} \ + ${dst_port} "${dst_addr4}" + + src_port= + dst_port= + src_addr4= + } + elif command -v nc >/dev/null; then + if nc -u -w0 1.1.1.1 1 2>/dev/null; then + # OpenBSD netcat + nc_opt="-w0" + else + # GNU netcat + nc_opt="-q0" + fi + + send_udp() { + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}" dev veth_b + __src_addr4="-s ${src_addr4}" + fi + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + echo "" | B nc -u "${nc_opt}" "${__src_addr4}" \ + "${src_port}" "${dst_addr4}" "${dst_port}" + + src_addr4= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp() { + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + B ip route add default dev veth_b + fi + + B bash -c "echo > /dev/udp/${dst_addr4}/${dst_port}" + + if [ -n "${src_addr4}" ]; then + B ip addr del "${src_addr4}/16" dev veth_b + fi + src_addr4= + } + else + return 1 + fi +} + +# Set up function to send single UDP packets on IPv6 +setup_send_udp6() { + if command -v sendip >/dev/null; then + send_udp6() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + if [ -n "${src_addr6}" ]; then + src_addr6="-6s ${src_addr6}" + else + src_addr6="-6s 2001:db8::2" + fi + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + B sendip -p ipv6 -p udp ${src_addr6} ${src_port} \ + ${dst_port} "${dst_addr6}" + + src_port= + dst_port= + src_addr6= + } + elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then + # GNU netcat might not work with IPv6, try next tool + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + # shellcheck disable=SC2086 # this needs split options + echo "" | B nc -u w0 "-s${src_addr6}" ${src_port} \ + ${dst_addr6} ${dst_port} + + src_addr6= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ip addr add "${src_addr6}" dev veth_b nodad + B bash -c "echo > /dev/udp/${dst_addr6}/${dst_port}" + ip -6 addr del "${dst_addr6}" dev veth_a 2>/dev/null + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv4 +setup_flood_tcp() { + if command -v iperf3 >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b 2>/dev/null + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr4}" ${dst_port} ${src_port} \ + ${src_addr4} -l16 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr4}" ${dst_port} ${src_addr4} \ + -l20 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t TCP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv6 +setup_flood_tcp6() { + if command -v iperf3 >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr6}" ${dst_port} \ + ${src_port} ${src_addr6} -l16 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_addr6="${src_addr6}:${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -VDB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr6}" -V ${dst_port} \ + ${src_addr6} -l1 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -6 ${dst_port} -L "${dst_addr6}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -6 -H "${dst_addr6}" ${dst_port} \ + -L "${src_addr6}" -l 1000 -t TCP_STREAM + + src_addr6= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send UDP traffic on IPv4 +setup_flood_udp() { + if command -v iperf3 >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -u -c "${dst_addr4}" -Z -b 100M -l16 -t1000 \ + ${dst_port} ${src_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -u -sDB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -u -c "${dst_addr4}" -b 100M -l1 -t1000 \ + ${dst_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t UDP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Find pktgen script and set up function to start pktgen injection +setup_perf() { + for pktgen_script_path in ${PKTGEN_SCRIPT_PATHS} __notfound; do + command -v "${pktgen_script_path}" >/dev/null && break + done + [ "${pktgen_script_path}" = "__notfound" ] && return 1 + + perf_ipv4() { + ${pktgen_script_path} -s80 \ + -i veth_a -d "${dst_addr4}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } + perf_ipv6() { + IP6=6 ${pktgen_script_path} -s100 \ + -i veth_a -d "${dst_addr6}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } +} + +# Clean up before each test +cleanup() { + nft reset counter inet filter test >/dev/null 2>&1 + nft flush ruleset >/dev/null 2>&1 + ip link del dummy0 2>/dev/null + ip route del default 2>/dev/null + ip -6 route del default 2>/dev/null + ip netns del B 2>/dev/null + ip link del veth_a 2>/dev/null + timeout= + killall iperf3 2>/dev/null + killall iperf 2>/dev/null + killall netperf 2>/dev/null + killall netserver 2>/dev/null + rm -f ${tmp} + sleep 2 +} + +# Entry point for setup functions +setup() { + if [ "$(id -u)" -ne 0 ]; then + echo " need to run as root" + exit ${KSELFTEST_SKIP} + fi + + cleanup + check_tools || return 1 + for arg do + if ! eval setup_"${arg}"; then + err " ${arg} not supported" + return 1 + fi + done +} + +# Format integer into IPv4 address, summing 10.0.0.5 (arbitrary) to it +format_addr4() { + a=$((${1} + 16777216 * 10 + 5)) + printf "%i.%i.%i.%i" \ + "$((a / 16777216))" "$((a % 16777216 / 65536))" \ + "$((a % 65536 / 256))" "$((a % 256))" +} + +# Format integer into IPv6 address, summing 2001:db8:: to it +format_addr6() { + printf "2001:db8::%04x:%04x" "$((${1} / 65536))" "$((${1} % 65536))" +} + +# Format integer into EUI-48 address, summing 00:01:00:00:00:00 to it +format_mac() { + printf "00:01:%02x:%02x:%02x:%02x" \ + "$((${1} / 16777216))" "$((${1} % 16777216 / 65536))" \ + "$((${1} % 65536 / 256))" "$((${1} % 256))" +} + +# Format integer into port, avoid 0 port +format_port() { + printf "%i" "$((${1} % 65534 + 1))" +} + +# Drop suffixed '6' from L4 protocol, if any +format_proto() { + printf "%s" "${proto}" | tr -d 6 +} + +# Format destination and source fields into nft concatenated type +format() { + __start= + __end= + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + for f in ${src}; do + __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" + __end="$(eval format_"${f}" "${srcend}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + + if [ -n "${timeout}" ]; then + echo "${__expr} timeout ${timeout}s }" + else + echo "${__expr} }" + fi +} + +# Format destination and source fields into nft type, start element only +format_norange() { + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __expr="${__expr}$(eval format_"${f}" "${start}")" + done + for f in ${src}; do + __expr="${__expr} . $(eval format_"${f}" "${start}")" + done + + echo "${__expr} }" +} + +# Format first destination field into nft type +format_noconcat() { + for f in ${dst}; do + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + echo "{ ${__start} }" + else + echo "{ ${__start}-${__end} }" + fi + return + done +} + +# Add single entry to 'test' set in 'inet filter' table +add() { + if ! nft add element inet filter test "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Format and output entries for sets in 'netdev perf' table +add_perf() { + if [ "${1}" = "test" ]; then + echo "add element netdev perf test $(format)" + elif [ "${1}" = "norange" ]; then + echo "add element netdev perf norange $(format_norange)" + elif [ "${1}" = "noconcat" ]; then + echo "add element netdev perf noconcat $(format_noconcat)" + fi +} + +# Add single entry to 'norange' set in 'netdev perf' table +add_perf_norange() { + if ! nft add element netdev perf norange "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Add single entry to 'noconcat' set in 'netdev perf' table +add_perf_noconcat() { + if ! nft add element netdev perf noconcat "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Delete single entry from set +del() { + if ! nft delete element inet filter test "${1}"; then + err "Failed to delete ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Return packet count from 'test' counter in 'inet filter' table +count_packets() { + found=0 + for token in $(nft list counter inet filter test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Return packet count from 'test' counter in 'netdev perf' table +count_perf_packets() { + found=0 + for token in $(nft list counter netdev perf test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Set MAC addresses, send traffic according to specifier +flood() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval flood_\$proto +} + +# Set MAC addresses, start pktgen injection +perf() { + dst_mac="$(format_mac "${1}")" + ip link set veth_a address "${dst_mac}" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval perf_\$perf_proto +} + +# Set MAC addresses, send single packet, check that it matches, reset counter +send_match() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "1" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi + nft reset counter inet filter test >/dev/null +} + +# Set MAC addresses, send single packet, check that it doesn't match +send_nomatch() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "0" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should not have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Correctness test template: +# - add ranged element, check that packets match it +# - check that packets outside range don't match it +# - remove some elements, check that packets don't match anymore +test_correctness() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1 + + # Delete elements now and then + if [ $((i % 3)) -eq 0 ]; then + del "$(format)" || return 1 + for j in $(seq ${start} \ + $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) \ + || return 1 + done + fi + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Concurrency test template: +# - add all the elements +# - start a thread for each physical thread that: +# - adds all the elements +# - flushes the set +# - adds all the elements +# - flushes the entire ruleset +# - adds the set back +# - adds all the elements +# - delete all the elements +test_concurrency() { + proto=${flood_proto} + tools=${flood_tools} + chain_spec=${flood_spec} + setup veth flood_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + cstart=${start} + flood_pids= + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + flood "${i}" $((i + src_delta)) & flood_pids="${flood_pids} $!" + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + sleep 10 + + pids= + for c in $(seq 1 "$(nproc)"); do ( + for r in $(seq 1 "${race_repeat}"); do + range_size=1 + + # $start needs to be local to this subshell + # shellcheck disable=SC2030 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush inet filter test 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset + setup set 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + del "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + done + ) & pids="${pids} $!" + done + + # shellcheck disable=SC2046,SC2086 # word splitting wanted here + wait $(for pid in ${pids}; do echo ${pid}; done) + # shellcheck disable=SC2046,SC2086 + kill $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + # shellcheck disable=SC2046,SC2086 + wait $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + + return 0 +} + +# Timeout test template: +# - add all the elements with 3s timeout while checking that packets match +# - wait 3s after the last insertion, check that packets don't match any entry +test_timeout() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + timeout=3 + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + sleep 3 + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Performance test template: +# - add concatenated ranged entries +# - add non-ranged concatenated entries (for hash set matching rate baseline) +# - add ranged entries with first field only (for rbhash baseline) +# - start pktgen injection directly on device rx path of this namespace +# - measure drop only rate, hash and rbtree baselines, then matching rate +test_performance() { + chain_spec=${perf_spec} + dst="${perf_dst}" + src="${perf_src}" + setup veth perf set || return ${KSELFTEST_SKIP} + + first=${start} + range_size=1 + for set in test norange noconcat; do + start=${first} + for i in $(seq ${start} $((start + perf_entries))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + elif [ ${start} -eq ${end} ]; then + end=$((start + 1)) + fi + + add_perf ${set} + + start=$((end + range_size)) + done > "${tmp}" + nft -f "${tmp}" + done + + perf $((end - 1)) ${srcstart} + + sleep 2 + + nft add rule netdev perf test counter name \"test\" drop + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline (drop from netdev hook): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @norange \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline hash (non-ranged entries): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec%%. *} @noconcat \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline rbtree (match on first field only): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @test \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + p5="$(printf %5s "${perf_entries}")" + info " set with ${p5} full, ranged entries: ${pps}pps" + kill "${perf_pid}" +} + +# Run everything in a separate network namespace +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } +tmp="$(mktemp)" +trap cleanup EXIT + +# Entry point for test runs +passed=0 +for name in ${TESTS}; do + printf "TEST: %s\n" "${name}" + for type in ${TYPES}; do + eval desc=\$TYPE_"${type}" + IFS=' +' + for __line in ${desc}; do + # shellcheck disable=SC2086 + eval ${__line%% *}=\"${__line##* }\"; + done + IFS=' +' + + if [ "${name}" = "concurrency" ] && \ + [ "${race_repeat}" = "0" ]; then + continue + fi + if [ "${name}" = "performance" ] && \ + [ "${perf_duration}" = "0" ]; then + continue + fi + + printf " %-60s " "${display}" + eval test_"${name}" + ret=$? + + if [ $ret -eq 0 ]; then + printf "[ OK ]\n" + info_flush + passed=$((passed + 1)) + elif [ $ret -eq 1 ]; then + printf "[FAIL]\n" + err_flush + exit 1 + elif [ $ret -eq ${KSELFTEST_SKIP} ]; then + printf "[SKIP]\n" + err_flush + fi + done +done + +[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json new file mode 100644 index 000000000000..180593010675 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json @@ -0,0 +1,940 @@ +[ + { + "id": "e90e", + "name": "Add ETS qdisc using bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 2", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b059", + "name": "Add ETS qdisc using quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8e7", + "name": "Add ETS qdisc using strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "233c", + "name": "Add ETS qdisc using bands + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "3d35", + "name": "Add ETS qdisc using bands + strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f3b", + "name": "Add ETS qdisc using strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4593", + "name": "Add ETS qdisc using strict 0 + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 0 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8938", + "name": "Add ETS qdisc using bands + strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 .*strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0782", + "name": "Add ETS qdisc with more bands than quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 .*quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "501b", + "name": "Add ETS qdisc with more bands than strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta ([1-9][0-9]* ){2}priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "671a", + "name": "Add ETS qdisc with more bands than strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2a23", + "name": "Add ETS qdisc with 16 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8daf", + "name": "Add ETS qdisc with 17 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f95", + "name": "Add ETS qdisc with 17 strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "837a", + "name": "Add ETS qdisc with 16 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "65b6", + "name": "Add ETS qdisc with 17 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b9e9", + "name": "Add ETS qdisc with 16 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 8 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9877", + "name": "Add ETS qdisc with 17 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 9 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c696", + "name": "Add ETS qdisc with priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "30c4", + "name": "Add ETS qdisc with quanta + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8ac", + "name": "Add ETS qdisc with strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "5a7e", + "name": "Add ETS qdisc with quanta + strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb8b", + "name": "Show ETS class :1", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root quantum 4000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "1b4e", + "name": "Show ETS class :2", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:2", + "matchPattern": "class ets 1:2 root quantum 3000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f642", + "name": "Show ETS class :3", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:3", + "matchPattern": "class ets 1:3 root quantum 2000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0a5f", + "name": "Show ETS strict class", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root $", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f7c8", + "name": "Add ETS qdisc with too many quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2389", + "name": "Add ETS qdisc with too many strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "fe3c", + "name": "Add ETS qdisc with too many strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb04", + "name": "Add ETS qdisc with excess priomap elements", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c32e", + "name": "Add ETS qdisc with priomap above bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "744c", + "name": "Add ETS qdisc with priomap above quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 500 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7b33", + "name": "Add ETS qdisc with priomap above strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "dbe6", + "name": "Add ETS qdisc with priomap above strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "bdb2", + "name": "Add ETS qdisc with priomap within bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39a3", + "name": "Add ETS qdisc with priomap above bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3 4", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "557c", + "name": "Unset priorities default to the last band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 priomap 0 0 0 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 0 0 0 0 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "a347", + "name": "Unset priorities default to the last band -- no priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39c4", + "name": "Add ETS qdisc with too few bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "930b", + "name": "Add ETS qdisc with too many bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "406a", + "name": "Add ETS qdisc without parameters", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e51a", + "name": "Zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 0 800 700", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e7f2", + "name": "Sole zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "d6e6", + "name": "No values after the quanta keyword", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "28c6", + "name": "Change ETS band quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets quantum 1500", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1500 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4714", + "name": "Change ETS band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "6979", + "name": "Change quantum of a strict ETS band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets quantum 1500", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9a7d", + "name": "Change ETS strict band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh new file mode 100755 index 000000000000..d5c85c7494f2 --- /dev/null +++ b/tools/testing/selftests/wireguard/netns.sh @@ -0,0 +1,534 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. +# +# This script tests the below topology: +# +# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│ +# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││ +# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│ +# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││ +# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││ +# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│ +# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘ +# └──────────────────────────────────┘ +# +# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the +# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0 +# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further +# details on how this is accomplished. +set -e + +exec 3>&1 +export WG_HIDE_KEYS=never +netns0="wg-test-$$-0" +netns1="wg-test-$$-1" +netns2="wg-test-$$-2" +pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; } +pp() { pretty "" "$*"; "$@"; } +maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; } +n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; } +n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; } +n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; } +ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } +ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } +ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } +sleep() { read -t "$1" -N 1 || true; } +waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } +waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } + +cleanup() { + set +e + exec 2>/dev/null + printf "$orig_message_cost" > /proc/sys/net/core/message_cost + ip0 link del dev wg0 + ip1 link del dev wg0 + ip2 link del dev wg0 + local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" + [[ -n $to_kill ]] && kill $to_kill + pp ip netns del $netns1 + pp ip netns del $netns2 + pp ip netns del $netns0 + exit +} + +orig_message_cost="$(< /proc/sys/net/core/message_cost)" +trap cleanup EXIT +printf 0 > /proc/sys/net/core/message_cost + +ip netns del $netns0 2>/dev/null || true +ip netns del $netns1 2>/dev/null || true +ip netns del $netns2 2>/dev/null || true +pp ip netns add $netns0 +pp ip netns add $netns1 +pp ip netns add $netns2 +ip0 link set up dev lo + +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns1 +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns2 +key1="$(pp wg genkey)" +key2="$(pp wg genkey)" +key3="$(pp wg genkey)" +pub1="$(pp wg pubkey <<<"$key1")" +pub2="$(pp wg pubkey <<<"$key2")" +pub3="$(pp wg pubkey <<<"$key3")" +psk="$(pp wg genpsk)" +[[ -n $key1 && -n $key2 && -n $psk ]] + +configure_peers() { + ip1 addr add 192.168.241.1/24 dev wg0 + ip1 addr add fd00::1/24 dev wg0 + + ip2 addr add 192.168.241.2/24 dev wg0 + ip2 addr add fd00::2/24 dev wg0 + + n1 wg set wg0 \ + private-key <(echo "$key1") \ + listen-port 1 \ + peer "$pub2" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.2/32,fd00::2/128 + n2 wg set wg0 \ + private-key <(echo "$key2") \ + listen-port 2 \ + peer "$pub1" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.1/32,fd00::1/128 + + ip1 link set up dev wg0 + ip2 link set up dev wg0 +} +configure_peers + +tests() { + # Ping over IPv4 + n2 ping -c 10 -f -W 1 192.168.241.1 + n1 ping -c 10 -f -W 1 192.168.241.2 + + # Ping over IPv6 + n2 ping6 -c 10 -f -W 1 fd00::1 + n1 ping6 -c 10 -f -W 1 fd00::2 + + # TCP over IPv4 + n2 iperf3 -s -1 -B 192.168.241.2 & + waitiperf $netns2 + n1 iperf3 -Z -t 3 -c 192.168.241.2 + + # TCP over IPv6 + n1 iperf3 -s -1 -B fd00::1 & + waitiperf $netns1 + n2 iperf3 -Z -t 3 -c fd00::1 + + # UDP over IPv4 + n1 iperf3 -s -1 -B 192.168.241.1 & + waitiperf $netns1 + n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 + + # UDP over IPv6 + n2 iperf3 -s -1 -B fd00::2 & + waitiperf $netns2 + n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 +} + +[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" +big_mtu=$(( 34816 - 1500 + $orig_mtu )) + +# Test using IPv4 as outer transport +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +# Before calling tests, we first make sure that the stats counters and timestamper are working +n2 ping -c 10 -f -W 1 192.168.241.1 +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ timestamp < <(n1 wg show wg0 latest-handshakes) +(( timestamp != 0 )) + +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv6 as outer transport +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n2 wg set wg0 peer "$pub1" endpoint [::1]:1 +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +# Test that route MTUs work with the padding +ip1 link set wg0 mtu 1300 +ip2 link set wg0 mtu 1300 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +n0 iptables -A INPUT -m length --length 1360 -j DROP +n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 +n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 +n2 ping -c 1 -W 1 -s 1269 192.168.241.1 +n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 +n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 +n0 iptables -F INPUT + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv4 that roaming works +ip0 -4 addr del 127.0.0.1/8 dev lo +ip0 -4 addr add 127.212.121.99/8 dev lo +n1 wg set wg0 listen-port 9999 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n1 ping6 -W 1 -c 1 fd00::2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]] + +# Test using IPv6 that roaming works +n1 wg set wg0 listen-port 9998 +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]] + +# Test that crypto-RP filter works +n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 +n2 ncat -u 192.168.241.1 1111 <<<"X" +read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] +kill $ncat_pid +more_specific_key="$(pp wg genkey | pp wg pubkey)" +n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32 +n2 wg set wg0 listen-port 9997 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 +n2 ncat -u 192.168.241.1 1111 <<<"X" +! read -r -N 1 -t 1 out <&4 || false +kill $ncat_pid +n1 wg set wg0 peer "$more_specific_key" remove +[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]] + +# Test that we can change private keys keys and immediately handshake +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 private-key <(echo "$key3") +n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove +n1 ping -W 1 -c 1 192.168.241.2 + +ip1 link del wg0 +ip2 link del wg0 + +# Test using NAT. We now change the topology to this: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers + +ip0 link add vethrc type veth peer name vethc +ip0 link add vethrs type veth peer name veths +ip0 link set vethc netns $netns1 +ip0 link set veths netns $netns2 +ip0 link set vethrc up +ip0 link set vethrs up +ip0 addr add 192.168.1.1/24 dev vethrc +ip0 addr add 10.0.0.1/24 dev vethrs +ip1 addr add 192.168.1.100/24 dev vethc +ip1 link set vethc up +ip1 route add default via 192.168.1.1 +ip2 addr add 10.0.0.100/24 dev veths +ip2 link set veths up +waitiface $netns0 vethrc +waitiface $netns0 vethrs +waitiface $netns1 vethc +waitiface $netns2 veths + +n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' +n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 + +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 +n1 ping -W 1 -c 1 192.168.241.2 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`). +pp sleep 3 +n2 ping -W 1 -c 1 192.168.241.1 +n1 wg set wg0 peer "$pub2" persistent-keepalive 0 + +# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. +ip1 -6 addr add fc00::9/96 dev vethc +ip1 -6 route add default via fc00::1 +ip2 -4 addr add 192.168.99.7/32 dev wg0 +ip2 -6 addr add abab::1111/128 dev wg0 +n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111 +ip1 -6 route add default dev wg0 table 51820 +ip1 -6 rule add not fwmark 51820 table 51820 +ip1 -6 rule add table main suppress_prefixlength 0 +ip1 -4 route add default dev wg0 table 51820 +ip1 -4 rule add not fwmark 51820 table 51820 +ip1 -4 rule add table main suppress_prefixlength 0 +# Flood the pings instead of sending just one, to trigger routing table reference counting bugs. +n1 ping -W 1 -c 100 -f 192.168.99.7 +n1 ping -W 1 -c 100 -f abab::1111 + +n0 iptables -t nat -F +ip0 link del vethrc +ip0 link del vethrs +ip1 link del wg0 +ip2 link del wg0 + +# Test that saddr routing is sticky but not too sticky, changing to this topology: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns2 namespace │ +# │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers +ip1 link add veth1 type veth peer name veth2 +ip1 link set veth2 netns $netns2 +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad' +n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries' + +# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip2 addr add fd00:aa::2/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add 10.0.0.10/24 dev veth1 +ip1 addr del 10.0.0.1/24 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add fd00:aa::10/96 dev veth1 +ip1 addr del fd00:aa::1/96 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 + +# Now we show that we can successfully do reply to sender routing +ip1 link set veth1 down +ip2 link set veth2 down +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add 10.0.0.2/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip1 addr add fd00:aa::2/96 dev veth1 +ip2 addr add 10.0.0.3/24 dev veth2 +ip2 addr add fd00:aa::3/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]] +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]] + +# What happens if the inbound destination address belongs to a different interface as the default route? +ip1 link add dummy0 type dummy +ip1 addr add 10.50.0.1/24 dev dummy0 +ip1 link set dummy0 up +ip2 route add 10.50.0.0/24 dev veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]] + +ip1 link del dummy0 +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 route flush dev veth1 +ip2 route flush dev veth2 + +# Now we see what happens if another interface route takes precedence over an ongoing one +ip1 link add veth3 type veth peer name veth4 +ip1 link set veth4 netns $netns2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip1 addr add 10.0.0.3/24 dev veth3 +ip1 link set veth1 up +ip2 link set veth2 up +ip1 link set veth3 up +ip2 link set veth4 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +waitiface $netns1 veth3 +waitiface $netns2 veth4 +ip1 route flush dev veth1 +ip1 route flush dev veth3 +ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter' +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] + +ip1 link del veth1 +ip1 link del veth3 +ip1 link del wg0 +ip2 link del wg0 + +# We test that Netlink/IPC is working properly by doing things that usually cause split responses +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" ) +for a in {1..255}; do + for b in {0..255}; do + config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +for ip in $(n0 wg show wg0 allowed-ips); do + ((++i)) +done +((i == 255*256*2+1)) +ip0 link del wg0 +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" ) +for a in {1..40}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) + for b in {1..52}; do + config+=( "AllowedIPs=$a.$b.0.0/16" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +while read -r line; do + j=0 + for ip in $line; do + ((++j)) + done + ((j == 53)) + ((++i)) +done < <(n0 wg show wg0 allowed-ips) +((i == 40)) +ip0 link del wg0 +ip0 link add wg0 type wireguard +config=( ) +for i in {1..29}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) +done +config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" ) +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +n0 wg showconf wg0 > /dev/null +ip0 link del wg0 + +allowedips=( ) +for i in {1..197}; do + allowedips+=( abcd::$i ) +done +saved_ifs="$IFS" +IFS=, +allowedips="${allowedips[*]}" +IFS="$saved_ifs" +ip0 link add wg0 type wireguard +n0 wg set wg0 peer "$pub1" +n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" +{ + read -r pub allowedips + [[ $pub == "$pub1" && $allowedips == "(none)" ]] + read -r pub allowedips + [[ $pub == "$pub2" ]] + i=0 + for _ in $allowedips; do + ((++i)) + done + ((i == 197)) +} < <(n0 wg show wg0 allowed-ips) +ip0 link del wg0 + +! n0 wg show doesnotexist || false + +ip0 link add wg0 type wireguard +n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") +[[ $(n0 wg show wg0 private-key) == "$key1" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]] +n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null +[[ $(n0 wg show wg0 private-key) == "(none)" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]] +n0 wg set wg0 peer "$pub2" +n0 wg set wg0 private-key <(echo "$key2") +[[ $(n0 wg show wg0 public-key) == "$pub2" ]] +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 peer "$pub2" +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 private-key <(echo "$key1") +n0 wg set wg0 peer "$pub2" +[[ $(n0 wg show wg0 peers) == "$pub2" ]] +n0 wg set wg0 private-key <(echo "/${key1:1}") +[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]] +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16 +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0 +ip0 link del wg0 + +declare -A objects +while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do + [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue + objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" +done < /dev/kmsg +alldeleted=1 +for object in "${!objects[@]}"; do + if [[ ${objects["$object"]} != *createddestroyed ]]; then + echo "Error: $object: merely ${objects["$object"]}" >&3 + alldeleted=0 + fi +done +[[ $alldeleted -eq 1 ]] +pretty "" "Objects that were created were also destroyed." diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore new file mode 100644 index 000000000000..415b542a9d59 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -0,0 +1,2 @@ +build/ +distfiles/ diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile new file mode 100644 index 000000000000..f10aa3590adc --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -0,0 +1,387 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + +PWD := $(shell pwd) + +CHOST := $(shell gcc -dumpmachine) +HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) +ifneq (,$(ARCH)) +CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) +ifeq (,$(CBUILD)) +$(error The toolchain for $(ARCH) is not installed) +endif +else +CBUILD := $(CHOST) +ARCH := $(firstword $(subst -, ,$(CBUILD))) +endif + +# Set these from the environment to override +KERNEL_PATH ?= $(PWD)/../../../../.. +BUILD_PATH ?= $(PWD)/build/$(ARCH) +DISTFILES_PATH ?= $(PWD)/distfiles +NR_CPUS ?= 4 + +MIRROR := https://download.wireguard.com/qemu-test/distfiles/ + +default: qemu + +# variable name, tarball project name, version, tarball extension, default URI base +define tar_download = +$(1)_VERSION := $(3) +$(1)_NAME := $(2)-$$($(1)_VERSION) +$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4) +$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME) +$(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) +endef + +define file_download = +$(DISTFILES_PATH)/$(1): + mkdir -p $(DISTFILES_PATH) + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' + if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi +endef + +$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) +$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) +$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) +$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) +$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) +$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) +$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) +$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) + +KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) +rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) + +export CFLAGS ?= -O3 -pipe +export LDFLAGS ?= +export CPPFLAGS := -I$(BUILD_PATH)/include + +ifeq ($(HOST_ARCH),$(ARCH)) +CROSS_COMPILE_FLAG := --host=$(CHOST) +CFLAGS += -march=native +STRIP := strip +else +$(info Cross compilation: building for $(CBUILD) using $(CHOST)) +CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) +export CROSS_COMPILE=$(CBUILD)- +STRIP := $(CBUILD)-strip +endif +ifeq ($(ARCH),aarch64) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),aarch64_be) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),arm) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux +endif +else ifeq ($(ARCH),armeb) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian. +LDFLAGS += -Wl,--be8 +endif +else ifeq ($(ARCH),x86_64) +QEMU_ARCH := x86_64 +KERNEL_ARCH := x86_64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu Skylake-Server -machine q35 +CFLAGS += -march=skylake-avx512 +endif +else ifeq ($(ARCH),i686) +QEMU_ARCH := i386 +KERNEL_ARCH := x86 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu coreduo -machine q35 +CFLAGS += -march=prescott +endif +else ifeq ($(ARCH),mips64) +QEMU_ARCH := mips64 +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EB +endif +else ifeq ($(ARCH),mips64el) +QEMU_ARCH := mips64el +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EL +endif +else ifeq ($(ARCH),mips) +QEMU_ARCH := mips +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EB +endif +else ifeq ($(ARCH),mipsel) +QEMU_ARCH := mipsel +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EL +endif +else ifeq ($(ARCH),powerpc64le) +QEMU_ARCH := ppc64 +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine pseries +else +QEMU_MACHINE := -machine pseries +endif +CFLAGS += -mcpu=powerpc64le -mlong-double-64 +else ifeq ($(ARCH),powerpc) +QEMU_ARCH := ppc +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 +else +QEMU_MACHINE := -machine ppce500 +endif +CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt +else ifeq ($(ARCH),m68k) +QEMU_ARCH := m68k +KERNEL_ARCH := m68k +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +else +QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +endif +else +$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +endif + +REAL_CC := $(CBUILD)-gcc +MUSL_CC := $(BUILD_PATH)/musl-gcc +export CC := $(MUSL_CC) +USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed + +build: $(KERNEL_BZIMAGE) +qemu: $(KERNEL_BZIMAGE) + rm -f $(BUILD_PATH)/result + timeout --foreground 20m qemu-system-$(QEMU_ARCH) \ + -nodefaults \ + -nographic \ + -smp $(NR_CPUS) \ + $(QEMU_MACHINE) \ + -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ + -serial stdio \ + -serial file:$(BUILD_PATH)/result \ + -no-reboot \ + -monitor none \ + -kernel $< + grep -Fq success $(BUILD_PATH)/result + +$(BUILD_PATH)/init-cpio-spec.txt: + mkdir -p $(BUILD_PATH) + echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ + echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ + echo "dir /dev 755 0 0" >> $@ + echo "nod /dev/console 644 0 0 c 5 1" >> $@ + echo "dir /bin 755 0 0" >> $@ + echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@ + echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@ + echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@ + echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@ + echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@ + echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@ + echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@ + echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@ + echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ + echo "slink /bin/ping6 ping 777 0 0" >> $@ + echo "dir /lib 755 0 0" >> $@ + echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ + echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ + +$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config + mkdir -p $(KERNEL_BUILD_PATH) + cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config + printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config + cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig + cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config + $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) + +$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) + +$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install + touch $@ + +$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) + $(MAKE) -C $(MUSL_PATH) + $(STRIP) -s $@ + +$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so + $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers + touch $@ + +$(MUSL_CC): $(MUSL_PATH)/lib/libc.so + sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs + printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc + chmod +x $(BUILD_PATH)/musl-gcc + +$(IPERF_PATH)/.installed: $(IPERF_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i '1s/^/#include <stdint.h>/' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h + sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile* + touch $@ + +$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no + $(MAKE) -C $(IPERF_PATH) + $(STRIP) -s $@ + +$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) + cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared + $(MAKE) -C $(LIBMNL_PATH) + sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc + +$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg + $(STRIP) -s $@ + +$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) + mkdir -p $(BUILD_PATH) + $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< + $(STRIP) -s $@ + +$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS) + sed -i /atexit/d $(IPUTILS_PATH)/ping.c + cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS) + $(STRIP) -s $@ + +$(BASH_PATH)/.installed: $(BASH_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) + cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble + $(MAKE) -C $(BASH_PATH) + $(STRIP) -s $@ + +$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk + printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + touch $@ + +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $(IPROUTE2_PATH)/ip/ip + +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $(IPROUTE2_PATH)/misc/ss + +$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure + touch $@ + +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include + $(MAKE) -C $(IPTABLES_PATH) + $(STRIP) -s $@ + +$(NMAP_PATH)/.installed: $(NMAP_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS) + cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh + $(MAKE) -C $(NMAP_PATH)/libpcap + $(MAKE) -C $(NMAP_PATH)/ncat + $(STRIP) -s $@ + +clean: + rm -rf $(BUILD_PATH) + +distclean: clean + rm -rf $(DISTFILES_PATH) + +menuconfig: $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig + +.PHONY: qemu build clean distclean menuconfig +.DELETE_ON_ERROR: diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config new file mode 100644 index 000000000000..3d063bb247bb --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config new file mode 100644 index 000000000000..dbdc7e406a7b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -0,0 +1,6 @@ +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config new file mode 100644 index 000000000000..148f49905418 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config new file mode 100644 index 000000000000..bd76b07d00a2 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -0,0 +1,10 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config new file mode 100644 index 000000000000..a85025d7206e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config new file mode 100644 index 000000000000..62a15bdb877e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_M68KCLASSIC=y +CONFIG_M68040=y +CONFIG_MAC=y +CONFIG_SERIAL_PMACZILOG=y +CONFIG_SERIAL_PMACZILOG_TTYS=y +CONFIG_SERIAL_PMACZILOG_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config new file mode 100644 index 000000000000..df71d6b95546 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config @@ -0,0 +1,11 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config new file mode 100644 index 000000000000..90c783f725c4 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config @@ -0,0 +1,14 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config new file mode 100644 index 000000000000..435b0b43e00c --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config @@ -0,0 +1,15 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config new file mode 100644 index 000000000000..62bb50c4a85f --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config @@ -0,0 +1,12 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config new file mode 100644 index 000000000000..57957093b71b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config @@ -0,0 +1,10 @@ +CONFIG_PPC_QEMU_E500=y +CONFIG_FSL_SOC_BOOKE=y +CONFIG_PPC_85xx=y +CONFIG_PHYS_64BIT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_MATH_EMULATION=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config new file mode 100644 index 000000000000..990c510a9cfa --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -0,0 +1,12 @@ +CONFIG_PPC64=y +CONFIG_PPC_PSERIES=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_HVC_CONSOLE=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config new file mode 100644 index 000000000000..00a1ef4869d5 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config new file mode 100644 index 000000000000..b9c72706fe4d --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -0,0 +1,67 @@ +CONFIG_LOCALVERSION="-debug" +CONFIG_ENABLE_WARN_DEPRECATED=y +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_POINTER=y +CONFIG_STACK_VALIDATION=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_PAGE_EXTENSION=y +CONFIG_PAGE_POISONING=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_SLUB_DEBUG_ON=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_HAVE_DEBUG_STACKOVERFLOW=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_HAVE_ARCH_KMEMCHECK=y +CONFIG_HAVE_ARCH_KASAN=y +CONFIG_KASAN=y +CONFIG_KASAN_INLINE=y +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +CONFIG_UBSAN_NO_ALIGNMENT=y +CONFIG_UBSAN_NULL=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHED_DEBUG=y +CONFIG_SCHED_INFO=y +CONFIG_SCHEDSTATS=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_DEBUG_TIMEKEEPING=y +CONFIG_TIMER_STATS=y +CONFIG_DEBUG_PREEMPT=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_TRACE_IRQFLAGS=y +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PI_LIST=y +CONFIG_PROVE_RCU=y +CONFIG_SPARSE_RCU_POINTER=y +CONFIG_RCU_CPU_STALL_TIMEOUT=21 +CONFIG_RCU_TRACE=y +CONFIG_RCU_EQS_DEBUG=y +CONFIG_USER_STACKTRACE_SUPPORT=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_DOUBLEFAULT=y +CONFIG_X86_DEBUG_FPU=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y +CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c new file mode 100644 index 000000000000..90bc9813cadc --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/init.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#define _GNU_SOURCE +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <sys/mount.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/io.h> +#include <sys/ioctl.h> +#include <sys/reboot.h> +#include <sys/utsname.h> +#include <sys/sendfile.h> +#include <sys/sysmacros.h> +#include <linux/random.h> +#include <linux/version.h> + +__attribute__((noreturn)) static void poweroff(void) +{ + fflush(stdout); + fflush(stderr); + reboot(RB_AUTOBOOT); + sleep(30); + fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n"); + exit(1); +} + +static void panic(const char *what) +{ + fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno)); + poweroff(); +} + +#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m") + +static void print_banner(void) +{ + struct utsname utsname; + int len; + + if (uname(&utsname) < 0) + panic("uname"); + + len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine); + printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, ""); +} + +static void seed_rng(void) +{ + int fd; + struct { + int entropy_count; + int buffer_size; + unsigned char buffer[256]; + } entropy = { + .entropy_count = sizeof(entropy.buffer) * 8, + .buffer_size = sizeof(entropy.buffer), + .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!" + }; + + if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9))) + panic("mknod(/dev/urandom)"); + fd = open("/dev/urandom", O_WRONLY); + if (fd < 0) + panic("open(urandom)"); + for (int i = 0; i < 256; ++i) { + if (ioctl(fd, RNDADDENTROPY, &entropy) < 0) + panic("ioctl(urandom)"); + } + close(fd); +} + +static void mount_filesystems(void) +{ + pretty_message("[+] Mounting filesystems..."); + mkdir("/dev", 0755); + mkdir("/proc", 0755); + mkdir("/sys", 0755); + mkdir("/tmp", 0755); + mkdir("/run", 0755); + mkdir("/var", 0755); + if (mount("none", "/dev", "devtmpfs", 0, NULL)) + panic("devtmpfs mount"); + if (mount("none", "/proc", "proc", 0, NULL)) + panic("procfs mount"); + if (mount("none", "/sys", "sysfs", 0, NULL)) + panic("sysfs mount"); + if (mount("none", "/tmp", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/run", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL)) + ; /* Not a problem if it fails.*/ + if (symlink("/run", "/var/run")) + panic("run symlink"); + if (symlink("/proc/self/fd", "/dev/fd")) + panic("fd symlink"); +} + +static void enable_logging(void) +{ + int fd; + pretty_message("[+] Enabling logging..."); + fd = open("/proc/sys/kernel/printk", O_WRONLY); + if (fd >= 0) { + if (write(fd, "9\n", 2) != 2) + panic("write(printk)"); + close(fd); + } + fd = open("/proc/sys/debug/exception-trace", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(exception-trace)"); + close(fd); + } + fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(panic_on_warn)"); + close(fd); + } +} + +static void kmod_selftests(void) +{ + FILE *file; + char line[2048], *start, *pass; + bool success = true; + pretty_message("[+] Module self-tests:"); + file = fopen("/proc/kmsg", "r"); + if (!file) + panic("fopen(kmsg)"); + if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0) + panic("fcntl(kmsg, nonblock)"); + while (fgets(line, sizeof(line), file)) { + start = strstr(line, "wireguard: "); + if (!start) + continue; + start += 11; + *strchrnul(start, '\n') = '\0'; + if (strstr(start, "www.wireguard.com")) + break; + pass = strstr(start, ": pass"); + if (!pass || pass[6] != '\0') { + success = false; + printf(" \x1b[31m* %s\x1b[0m\n", start); + } else + printf(" \x1b[32m* %s\x1b[0m\n", start); + } + fclose(file); + if (!success) { + puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m"); + poweroff(); + } +} + +static void launch_tests(void) +{ + char cmdline[4096], *success_dev; + int status, fd; + pid_t pid; + + pretty_message("[+] Launching tests..."); + pid = fork(); + if (pid == -1) + panic("fork"); + else if (pid == 0) { + execl("/init.sh", "init", NULL); + panic("exec"); + } + if (waitpid(pid, &status, 0) < 0) + panic("waitpid"); + if (WIFEXITED(status) && WEXITSTATUS(status) == 0) { + pretty_message("[+] Tests successful! :-)"); + fd = open("/proc/cmdline", O_RDONLY); + if (fd < 0) + panic("open(/proc/cmdline)"); + if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0) + panic("read(/proc/cmdline)"); + cmdline[sizeof(cmdline) - 1] = '\0'; + for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) { + if (strncmp(success_dev, "wg.success=", 11)) + continue; + memcpy(success_dev + 11 - 5, "/dev/", 5); + success_dev += 11 - 5; + break; + } + if (!success_dev || !strlen(success_dev)) + panic("Unable to find success device"); + + fd = open(success_dev, O_WRONLY); + if (fd < 0) + panic("open(success_dev)"); + if (write(fd, "success\n", 8) != 8) + panic("write(success_dev)"); + close(fd); + } else { + const char *why = "unknown cause"; + int what = -1; + + if (WIFEXITED(status)) { + why = "exit code"; + what = WEXITSTATUS(status); + } else if (WIFSIGNALED(status)) { + why = "signal"; + what = WTERMSIG(status); + } + printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what); + } +} + +static void ensure_console(void) +{ + for (unsigned int i = 0; i < 1000; ++i) { + int fd = open("/dev/console", O_RDWR); + if (fd < 0) { + usleep(50000); + continue; + } + dup2(fd, 0); + dup2(fd, 1); + dup2(fd, 2); + close(fd); + if (write(1, "\0\0\0\0\n", 5) == 5) + return; + } + panic("Unable to open console device"); +} + +static void clear_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Starting memory leak detection..."); + write(fd, "clear\n", 5); + close(fd); +} + +static void check_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Scanning for memory leaks..."); + sleep(2); /* Wait for any grace periods. */ + write(fd, "scan\n", 5); + close(fd); + + fd = open("/sys/kernel/debug/kmemleak", O_RDONLY); + if (fd < 0) + return; + if (sendfile(1, fd, NULL, 0x7ffff000) > 0) + panic("Memory leaks encountered"); + close(fd); +} + +int main(int argc, char *argv[]) +{ + seed_rng(); + ensure_console(); + print_banner(); + mount_filesystems(); + kmod_selftests(); + enable_logging(); + clear_leaks(); + launch_tests(); + check_leaks(); + poweroff(); + return 1; +} diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config new file mode 100644 index 000000000000..af9323a0b6e0 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -0,0 +1,88 @@ +CONFIG_LOCALVERSION="" +CONFIG_NET=y +CONFIG_NETDEVICES=y +CONFIG_NET_CORE=y +CONFIG_NET_IPIP=y +CONFIG_DUMMY=y +CONFIG_VETH=y +CONFIG_MULTIUSER=y +CONFIG_NAMESPACES=y +CONFIG_NET_NS=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IPV6=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_NAT=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_NAT=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_NAT_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_TTY=y +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_SCRIPT=y +CONFIG_VDSO=y +CONFIG_VIRTUALIZATION=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_KVM_GUEST=y +CONFIG_PARAVIRT_SPINLOCKS=y +CONFIG_PRINTK=y +CONFIG_KALLSYMS=y +CONFIG_BUG=y +CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y +CONFIG_JUMP_LABEL=y +CONFIG_EMBEDDED=n +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_SHMEM=y +CONFIG_SLUB=y +CONFIG_SPARSEMEM_VMEMMAP=y +CONFIG_SMP=y +CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y +CONFIG_NUMA=y +CONFIG_PREEMPT=y +CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_HZ_PERIODIC=n +CONFIG_HIGH_RES_TIMERS=y +CONFIG_COMPAT_32BIT_TIME=y +CONFIG_ARCH_RANDOM=y +CONFIG_FILE_LOCKING=y +CONFIG_POSIX_TIMERS=y +CONFIG_DEVTMPFS=y +CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_PRINTK_TIME=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_LEGACY_VSYSCALL_NONE=y +CONFIG_KERNEL_GZIP=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y +CONFIG_PANIC_TIMEOUT=-1 +CONFIG_STACKTRACE=y +CONFIG_EARLY_PRINTK=y +CONFIG_GDB_SCRIPTS=y +CONFIG_WIREGUARD=y +CONFIG_WIREGUARD_DEBUG=y diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore index dc5f11faf530..7f7a2ccc30c4 100644 --- a/tools/testing/vsock/.gitignore +++ b/tools/testing/vsock/.gitignore @@ -1,2 +1,3 @@ *.d +vsock_test vsock_diag_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 5be687b1e16c..f8293c6910c9 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only all: test -test: vsock_diag_test -vsock_diag_test: vsock_diag_test.o timeout.o control.o +test: vsock_test vsock_diag_test +vsock_test: vsock_test.o timeout.o control.o util.o +vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o -CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE +CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean clean: - ${RM} *.o *.d vsock_diag_test + ${RM} *.o *.d vsock_test vsock_diag_test -include *.d diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 2cc6d7302db6..4d5045e7d2c3 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -5,12 +5,13 @@ Hyper-V. The following tests are available: + * vsock_test - core AF_VSOCK socket functionality * vsock_diag_test - vsock_diag.ko module for listing open sockets The following prerequisite steps are not automated and must be performed prior to running tests: -1. Build the kernel and these tests. +1. Build the kernel, make headers_install, and build these tests. 2. Install the kernel and tests on the host. 3. Install the kernel and tests inside the guest. 4. Boot the guest and ensure that the AF_VSOCK transport is enabled. diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index 45f328c6ff23..4874872fc5a3 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -205,11 +205,22 @@ void control_expectln(const char *str) char *line; line = control_readln(); - if (strcmp(str, line) != 0) { + + control_cmpln(line, str, true); + + free(line); +} + +bool control_cmpln(char *line, const char *str, bool fail) +{ + if (strcmp(str, line) == 0) + return true; + + if (fail) { fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n", str, line); exit(EXIT_FAILURE); } - free(line); + return false; } diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h index 54a07efd267c..51814b4f9ac1 100644 --- a/tools/testing/vsock/control.h +++ b/tools/testing/vsock/control.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef CONTROL_H #define CONTROL_H @@ -9,5 +10,6 @@ void control_cleanup(void); void control_writeln(const char *str); char *control_readln(void); void control_expectln(const char *str); +bool control_cmpln(char *line, const char *str, bool fail); #endif /* CONTROL_H */ diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h index 77db9ce9860a..ecb7c840e65a 100644 --- a/tools/testing/vsock/timeout.h +++ b/tools/testing/vsock/timeout.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef TIMEOUT_H #define TIMEOUT_H diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c new file mode 100644 index 000000000000..93cbd6f603f9 --- /dev/null +++ b/tools/testing/vsock/util.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock test utilities + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <errno.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <assert.h> +#include <sys/epoll.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +/* Install signal handlers */ +void init_signals(void) +{ + struct sigaction act = { + .sa_handler = sigalrm, + }; + + sigaction(SIGALRM, &act, NULL); + signal(SIGPIPE, SIG_IGN); +} + +/* Parse a CID in string representation */ +unsigned int parse_cid(const char *str) +{ + char *endptr = NULL; + unsigned long n; + + errno = 0; + n = strtoul(str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed CID \"%s\"\n", str); + exit(EXIT_FAILURE); + } + return n; +} + +/* Wait for the remote to close the connection */ +void vsock_wait_remote_close(int fd) +{ + struct epoll_event ev; + int epollfd, nfds; + + epollfd = epoll_create1(0); + if (epollfd == -1) { + perror("epoll_create1"); + exit(EXIT_FAILURE); + } + + ev.events = EPOLLRDHUP | EPOLLHUP; + ev.data.fd = fd; + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) { + perror("epoll_ctl"); + exit(EXIT_FAILURE); + } + + nfds = epoll_wait(epollfd, &ev, 1, TIMEOUT * 1000); + if (nfds == -1) { + perror("epoll_wait"); + exit(EXIT_FAILURE); + } + + if (nfds == 0) { + fprintf(stderr, "epoll_wait timed out\n"); + exit(EXIT_FAILURE); + } + + assert(nfds == 1); + assert(ev.events & (EPOLLRDHUP | EPOLLHUP)); + assert(ev.data.fd == fd); + + close(epollfd); +} + +/* Connect to <cid, port> and return the file descriptor. */ +int vsock_stream_connect(unsigned int cid, unsigned int port) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + int ret; + int fd; + + control_expectln("LISTENING"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + int old_errno = errno; + + close(fd); + fd = -1; + errno = old_errno; + } + return fd; +} + +/* Listen on <cid, port> and return the first incoming connection. The remote + * address is stored to clientaddrp. clientaddrp may be NULL. + */ +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + socklen_t clientaddr_len = sizeof(clientaddr.svm); + int fd; + int client_fd; + int old_errno; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + old_errno = errno; + close(fd); + errno = old_errno; + + if (client_fd < 0) + return client_fd; + + if (clientaddr_len != sizeof(clientaddr.svm)) { + fprintf(stderr, "unexpected addrlen from accept(2), %zu\n", + (size_t)clientaddr_len); + exit(EXIT_FAILURE); + } + if (clientaddr.sa.sa_family != AF_VSOCK) { + fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", + clientaddr.sa.sa_family); + exit(EXIT_FAILURE); + } + + if (clientaddrp) + *clientaddrp = clientaddr.svm; + return client_fd; +} + +/* Transmit one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void send_byte(int fd, int expected_ret, int flags) +{ + const uint8_t byte = 'A'; + ssize_t nwritten; + + timeout_begin(TIMEOUT); + do { + nwritten = send(fd, &byte, sizeof(byte), flags); + timeout_check("write"); + } while (nwritten < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nwritten != -1) { + fprintf(stderr, "bogus send(2) return value %zd\n", + nwritten); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("write"); + exit(EXIT_FAILURE); + } + return; + } + + if (nwritten < 0) { + perror("write"); + exit(EXIT_FAILURE); + } + if (nwritten == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while sending byte\n"); + exit(EXIT_FAILURE); + } + if (nwritten != sizeof(byte)) { + fprintf(stderr, "bogus send(2) return value %zd\n", nwritten); + exit(EXIT_FAILURE); + } +} + +/* Receive one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void recv_byte(int fd, int expected_ret, int flags) +{ + uint8_t byte; + ssize_t nread; + + timeout_begin(TIMEOUT); + do { + nread = recv(fd, &byte, sizeof(byte), flags); + timeout_check("read"); + } while (nread < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nread != -1) { + fprintf(stderr, "bogus recv(2) return value %zd\n", + nread); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("read"); + exit(EXIT_FAILURE); + } + return; + } + + if (nread < 0) { + perror("read"); + exit(EXIT_FAILURE); + } + if (nread == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while receiving byte\n"); + exit(EXIT_FAILURE); + } + if (nread != sizeof(byte)) { + fprintf(stderr, "bogus recv(2) return value %zd\n", nread); + exit(EXIT_FAILURE); + } + if (byte != 'A') { + fprintf(stderr, "unexpected byte read %c\n", byte); + exit(EXIT_FAILURE); + } +} + +/* Run test cases. The program terminates if a failure occurs. */ +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts) +{ + int i; + + for (i = 0; test_cases[i].name; i++) { + void (*run)(const struct test_opts *opts); + char *line; + + printf("%d - %s...", i, test_cases[i].name); + fflush(stdout); + + /* Full barrier before executing the next test. This + * ensures that client and server are executing the + * same test case. In particular, it means whoever is + * faster will not see the peer still executing the + * last test. This is important because port numbers + * can be used by multiple test cases. + */ + if (test_cases[i].skip) + control_writeln("SKIP"); + else + control_writeln("NEXT"); + + line = control_readln(); + if (control_cmpln(line, "SKIP", false) || test_cases[i].skip) { + + printf("skipped\n"); + + free(line); + continue; + } + + control_cmpln(line, "NEXT", true); + free(line); + + if (opts->mode == TEST_MODE_CLIENT) + run = test_cases[i].run_client; + else + run = test_cases[i].run_server; + + if (run) + run(opts); + + printf("ok\n"); + } +} + +void list_tests(const struct test_case *test_cases) +{ + int i; + + printf("ID\tTest name\n"); + + for (i = 0; test_cases[i].name; i++) + printf("%d\t%s\n", i, test_cases[i].name); + + exit(EXIT_FAILURE); +} + +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + unsigned long test_id; + char *endptr = NULL; + + errno = 0; + test_id = strtoul(test_id_str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed test ID \"%s\"\n", test_id_str); + exit(EXIT_FAILURE); + } + + if (test_id >= test_cases_len) { + fprintf(stderr, "test ID (%lu) larger than the max allowed (%lu)\n", + test_id, test_cases_len - 1); + exit(EXIT_FAILURE); + } + + test_cases[test_id].skip = true; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h new file mode 100644 index 000000000000..e53dd09d26d9 --- /dev/null +++ b/tools/testing/vsock/util.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef UTIL_H +#define UTIL_H + +#include <sys/socket.h> +#include <linux/vm_sockets.h> + +/* Tests can either run as the client or the server */ +enum test_mode { + TEST_MODE_UNSET, + TEST_MODE_CLIENT, + TEST_MODE_SERVER +}; + +/* Test runner options */ +struct test_opts { + enum test_mode mode; + unsigned int peer_cid; +}; + +/* A test case definition. Test functions must print failures to stderr and + * terminate with exit(EXIT_FAILURE). + */ +struct test_case { + const char *name; /* human-readable name */ + + /* Called when test mode is TEST_MODE_CLIENT */ + void (*run_client)(const struct test_opts *opts); + + /* Called when test mode is TEST_MODE_SERVER */ + void (*run_server)(const struct test_opts *opts); + + bool skip; +}; + +void init_signals(void); +unsigned int parse_cid(const char *str); +int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp); +void vsock_wait_remote_close(int fd); +void send_byte(int fd, int expected_ret, int flags); +void recv_byte(int fd, int expected_ret, int flags); +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts); +void list_tests(const struct test_case *test_cases); +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str); +#endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index c481101364a4..cec6f5a738e1 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -9,32 +9,22 @@ #include <getopt.h> #include <stdio.h> -#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <errno.h> #include <unistd.h> -#include <signal.h> -#include <sys/socket.h> #include <sys/stat.h> #include <sys/types.h> #include <linux/list.h> #include <linux/net.h> #include <linux/netlink.h> #include <linux/sock_diag.h> +#include <linux/vm_sockets_diag.h> #include <netinet/tcp.h> -#include "../../../include/uapi/linux/vm_sockets.h" -#include "../../../include/uapi/linux/vm_sockets_diag.h" - #include "timeout.h" #include "control.h" - -enum test_mode { - TEST_MODE_UNSET, - TEST_MODE_CLIENT, - TEST_MODE_SERVER -}; +#include "util.h" /* Per-socket status */ struct vsock_stat { @@ -335,7 +325,7 @@ static void free_sock_stat(struct list_head *sockets) free(st); } -static void test_no_sockets(unsigned int peer_cid) +static void test_no_sockets(const struct test_opts *opts) { LIST_HEAD(sockets); @@ -346,7 +336,7 @@ static void test_no_sockets(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_listen_socket_server(unsigned int peer_cid) +static void test_listen_socket_server(const struct test_opts *opts) { union { struct sockaddr sa; @@ -384,35 +374,14 @@ static void test_listen_socket_server(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_client(unsigned int peer_cid) +static void test_connect_client(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = peer_cid, - }, - }; int fd; - int ret; LIST_HEAD(sockets); struct vsock_stat *st; - control_expectln("LISTENING"); - - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { perror("connect"); exit(EXIT_FAILURE); } @@ -430,68 +399,21 @@ static void test_connect_client(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_server(unsigned int peer_cid) +static void test_connect_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = VMADDR_CID_ANY, - }, - }; - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } clientaddr; - socklen_t clientaddr_len = sizeof(clientaddr.svm); - LIST_HEAD(sockets); struct vsock_stat *st; - int fd; + LIST_HEAD(sockets); int client_fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } - - if (listen(fd, 1) < 0) { - perror("listen"); - exit(EXIT_FAILURE); - } - - control_writeln("LISTENING"); - - timeout_begin(TIMEOUT); - do { - client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); - timeout_check("accept"); - } while (client_fd < 0 && errno == EINTR); - timeout_end(); - + client_fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); if (client_fd < 0) { perror("accept"); exit(EXIT_FAILURE); } - if (clientaddr.sa.sa_family != AF_VSOCK) { - fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", - clientaddr.sa.sa_family); - exit(EXIT_FAILURE); - } - if (clientaddr.svm.svm_cid != peer_cid) { - fprintf(stderr, "expected peer CID %u from accept(2), got %u\n", - peer_cid, clientaddr.svm.svm_cid); - exit(EXIT_FAILURE); - } read_vsock_stat(&sockets); - check_num_sockets(&sockets, 2); - find_vsock_stat(&sockets, fd); + check_num_sockets(&sockets, 1); st = find_vsock_stat(&sockets, client_fd); check_socket_state(st, TCP_ESTABLISHED); @@ -499,15 +421,10 @@ static void test_connect_server(unsigned int peer_cid) control_expectln("DONE"); close(client_fd); - close(fd); free_sock_stat(&sockets); } -static struct { - const char *name; - void (*run_client)(unsigned int peer_cid); - void (*run_server)(unsigned int peer_cid); -} test_cases[] = { +static struct test_case test_cases[] = { { .name = "No sockets", .run_server = test_no_sockets, @@ -524,30 +441,6 @@ static struct { {}, }; -static void init_signals(void) -{ - struct sigaction act = { - .sa_handler = sigalrm, - }; - - sigaction(SIGALRM, &act, NULL); - signal(SIGPIPE, SIG_IGN); -} - -static unsigned int parse_cid(const char *str) -{ - char *endptr = NULL; - unsigned long int n; - - errno = 0; - n = strtoul(str, &endptr, 10); - if (errno || *endptr != '\0') { - fprintf(stderr, "malformed CID \"%s\"\n", str); - exit(EXIT_FAILURE); - } - return n; -} - static const char optstring[] = ""; static const struct option longopts[] = { { @@ -571,6 +464,16 @@ static const struct option longopts[] = { .val = 'p', }, { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { .name = "help", .has_arg = no_argument, .val = '?', @@ -580,7 +483,7 @@ static const struct option longopts[] = { static void usage(void) { - fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n" + fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" "\n" " Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n" " Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" @@ -594,7 +497,18 @@ static void usage(void) "listen address and the client requires an address to\n" "connect to.\n" "\n" - "The CID of the other side must be given with --peer-cid=<cid>.\n"); + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); exit(EXIT_FAILURE); } @@ -602,9 +516,10 @@ int main(int argc, char **argv) { const char *control_host = NULL; const char *control_port = NULL; - int mode = TEST_MODE_UNSET; - unsigned int peer_cid = VMADDR_CID_ANY; - int i; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; init_signals(); @@ -620,20 +535,27 @@ int main(int argc, char **argv) break; case 'm': if (strcmp(optarg, "client") == 0) - mode = TEST_MODE_CLIENT; + opts.mode = TEST_MODE_CLIENT; else if (strcmp(optarg, "server") == 0) - mode = TEST_MODE_SERVER; + opts.mode = TEST_MODE_SERVER; else { fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); return EXIT_FAILURE; } break; case 'p': - peer_cid = parse_cid(optarg); + opts.peer_cid = parse_cid(optarg); break; case 'P': control_port = optarg; break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; case '?': default: usage(); @@ -642,35 +564,21 @@ int main(int argc, char **argv) if (!control_port) usage(); - if (mode == TEST_MODE_UNSET) + if (opts.mode == TEST_MODE_UNSET) usage(); - if (peer_cid == VMADDR_CID_ANY) + if (opts.peer_cid == VMADDR_CID_ANY) usage(); if (!control_host) { - if (mode != TEST_MODE_SERVER) + if (opts.mode != TEST_MODE_SERVER) usage(); control_host = "0.0.0.0"; } - control_init(control_host, control_port, mode == TEST_MODE_SERVER); + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); - for (i = 0; test_cases[i].name; i++) { - void (*run)(unsigned int peer_cid); - - printf("%s...", test_cases[i].name); - fflush(stdout); - - if (mode == TEST_MODE_CLIENT) - run = test_cases[i].run_client; - else - run = test_cases[i].run_server; - - if (run) - run(peer_cid); - - printf("ok\n"); - } + run_tests(test_cases, &opts); control_cleanup(); return EXIT_SUCCESS; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c new file mode 100644 index 000000000000..1d8b93f1af31 --- /dev/null +++ b/tools/testing/vsock/vsock_test.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock_test - vsock.ko test suite + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <linux/kernel.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +static void test_stream_connection_reset(const struct test_opts *opts) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = opts->peer_cid, + }, + }; + int ret; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret != -1) { + fprintf(stderr, "expected connect(2) failure, got %d\n", ret); + exit(EXIT_FAILURE); + } + if (errno != ECONNRESET) { + fprintf(stderr, "unexpected connect(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_client_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_client_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +/* With the standard socket sizes, VMCI is able to support about 100 + * concurrent stream connections. + */ +#define MULTICONN_NFDS 100 + +static void test_stream_multiconn_client(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_connect(opts->peer_cid, 1234); + if (fds[i] < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + recv_byte(fds[i], 1, 0); + else + send_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_multiconn_server(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fds[i] < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + send_byte(fds[i], 1, 0); + else + recv_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_msg_peek_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_msg_peek_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_byte(fd, 1, MSG_PEEK); + recv_byte(fd, 1, 0); + close(fd); +} + +static struct test_case test_cases[] = { + { + .name = "SOCK_STREAM connection reset", + .run_client = test_stream_connection_reset, + }, + { + .name = "SOCK_STREAM client close", + .run_client = test_stream_client_close_client, + .run_server = test_stream_client_close_server, + }, + { + .name = "SOCK_STREAM server close", + .run_client = test_stream_server_close_client, + .run_server = test_stream_server_close_server, + }, + { + .name = "SOCK_STREAM multiple connections", + .run_client = test_stream_multiconn_client, + .run_server = test_stream_multiconn_server, + }, + { + .name = "SOCK_STREAM MSG_PEEK", + .run_client = test_stream_msg_peek_client, + .run_server = test_stream_msg_peek_server, + }, + {}, +}; + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "control-host", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "control-port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "mode", + .has_arg = required_argument, + .val = 'm', + }, + { + .name = "peer-cid", + .has_arg = required_argument, + .val = 'p', + }, + { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { + .name = "help", + .has_arg = no_argument, + .val = '?', + }, + {}, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: vsock_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" + "\n" + " Server: vsock_test --control-port=1234 --mode=server --peer-cid=3\n" + " Client: vsock_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" + "\n" + "Run vsock.ko tests. Must be launched in both guest\n" + "and host. One side must use --mode=client and\n" + "the other side must use --mode=server.\n" + "\n" + "A TCP control socket connection is used to coordinate tests\n" + "between the client and the server. The server requires a\n" + "listen address and the client requires an address to\n" + "connect to.\n" + "\n" + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); + exit(EXIT_FAILURE); +} + +int main(int argc, char **argv) +{ + const char *control_host = NULL; + const char *control_port = NULL; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; + + init_signals(); + + for (;;) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'H': + control_host = optarg; + break; + case 'm': + if (strcmp(optarg, "client") == 0) + opts.mode = TEST_MODE_CLIENT; + else if (strcmp(optarg, "server") == 0) + opts.mode = TEST_MODE_SERVER; + else { + fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); + return EXIT_FAILURE; + } + break; + case 'p': + opts.peer_cid = parse_cid(optarg); + break; + case 'P': + control_port = optarg; + break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; + case '?': + default: + usage(); + } + } + + if (!control_port) + usage(); + if (opts.mode == TEST_MODE_UNSET) + usage(); + if (opts.peer_cid == VMADDR_CID_ANY) + usage(); + + if (!control_host) { + if (opts.mode != TEST_MODE_SERVER) + usage(); + control_host = "0.0.0.0"; + } + + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); + + run_tests(test_cases, &opts); + + control_cleanup(); + return EXIT_SUCCESS; +} |