diff options
Diffstat (limited to 'tools')
146 files changed, 8412 insertions, 1156 deletions
diff --git a/tools/bpf/bpf_asm.c b/tools/bpf/bpf_asm.c index e5f95e3eede3..0063c3c029e7 100644 --- a/tools/bpf/bpf_asm.c +++ b/tools/bpf/bpf_asm.c @@ -11,7 +11,7 @@ * * How to get into it: * - * 1) read Documentation/networking/filter.txt + * 1) read Documentation/networking/filter.rst * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary * blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will * pretty print a C-like construct. diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c index 9d3766e653a9..a0ebcdf59c31 100644 --- a/tools/bpf/bpf_dbg.c +++ b/tools/bpf/bpf_dbg.c @@ -13,7 +13,7 @@ * for making a verdict when multiple simple BPF programs are combined * into one in order to prevent parsing same headers multiple times. * - * More on how to debug BPF opcodes see Documentation/networking/filter.txt + * More on how to debug BPF opcodes see Documentation/networking/filter.rst * which is the main document on BPF. Mini howto for getting started: * * 1) `./bpf_dbg` to enter the shell (shell cmds denoted with '>'): diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index 39615f8e145b..ce3a724f50c1 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -230,9 +230,14 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-map**\ (8), - **bpftool-prog**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 06a28b07787d..e4d9da654e84 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -20,7 +20,7 @@ SYNOPSIS CGROUP COMMANDS =============== -| **bpftool** **cgroup { show | list }** *CGROUP* [**effective**] +| **bpftool** **cgroup** { **show** | **list** } *CGROUP* [**effective**] | **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* @@ -160,9 +160,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index b04156cfd7a3..8609f06e71de 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -19,7 +19,7 @@ SYNOPSIS FEATURE COMMANDS ================ -| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] | **bpftool** **feature help** | | *COMPONENT* := { **kernel** | **dev** *NAME* } @@ -28,7 +28,7 @@ DESCRIPTION =========== **bpftool feature probe** [**kernel**] [**full**] [**macros** [**prefix** *PREFIX*]] Probe the running kernel and dump a number of eBPF-related - parameters, such as availability of the **bpf()** system call, + parameters, such as availability of the **bpf**\ () system call, JIT status, eBPF program types availability, eBPF helper functions availability, and more. @@ -49,6 +49,16 @@ DESCRIPTION Keyword **kernel** can be omitted. If no probe target is specified, probing the kernel is the default behaviour. + When the **unprivileged** keyword is used, bpftool will dump + only the features available to a user who does not have the + **CAP_SYS_ADMIN** capability set. The features available in + that case usually represent a small subset of the parameters + supported by the system. Unprivileged users MUST use the + **unprivileged** keyword: This is to avoid misdetection if + bpftool is inadvertently run as non-root, for example. This + keyword is unavailable if bpftool was compiled without + libcap. + **bpftool feature probe dev** *NAME* [**full**] [**macros** [**prefix** *PREFIX*]] Probe network device for supported eBPF features and dump results to the console. @@ -83,9 +93,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 94d91322895a..df85dbd962c0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -14,7 +14,7 @@ SYNOPSIS *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } - *COMMAND* := { **skeleton | **help** } + *COMMAND* := { **skeleton** | **help** } GEN COMMANDS ============= @@ -36,12 +36,12 @@ DESCRIPTION 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 + 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 + 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 @@ -82,14 +82,14 @@ DESCRIPTION - **example__open** and **example__open_opts**. These functions are used to instantiate skeleton. It - corresponds to libbpf's **bpf_object__open()** API. + 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. + libppf's **bpf_object__load**\ () API. - **example__open_and_load** combines **example__open** and **example__load** invocations in one commonly used @@ -296,10 +296,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-map**\ (8), - **bpftool-prog**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst new file mode 100644 index 000000000000..8dce698eab79 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -0,0 +1,81 @@ +============ +bpftool-iter +============ +------------------------------------------------------------------------------- +tool to create BPF iterators +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **iter** *COMMAND* + + *COMMANDS* := { **pin** | **help** } + +ITER COMMANDS +=================== + +| **bpftool** **iter pin** *OBJ* *PATH* +| **bpftool** **iter help** +| +| *OBJ* := /a/file/of/bpf_iter_target.o + +DESCRIPTION +=========== + **bpftool iter pin** *OBJ* *PATH* + A bpf iterator combines a kernel iterating of + particular kernel data (e.g., tasks, bpf_maps, etc.) + and a bpf program called for each kernel data object + (e.g., one task, one bpf_map, etc.). User space can + *read* kernel iterator output through *read()* syscall. + + The *pin* command creates a bpf iterator from *OBJ*, + and pin it to *PATH*. The *PATH* should be located + in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions + of *bpffs*. + + User can then *cat PATH* to see the bpf iterator output. + + **bpftool iter 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**). + + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf as well as from the verifier, when + attempting to load programs. + +EXAMPLES +======== +**# bpftool iter pin bpf_iter_netlink.o /sys/fs/bpf/my_netlink** + +:: + + Create a file-based bpf iterator from bpf_iter_netlink.o and pin it + to /sys/fs/bpf/my_netlink + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-btf**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst new file mode 100644 index 000000000000..0e43d7b06c11 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -0,0 +1,121 @@ +================ +bpftool-link +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF links +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **link** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + + *COMMANDS* := { **show** | **list** | **pin** | **help** } + +LINK COMMANDS +============= + +| **bpftool** **link { show | list }** [*LINK*] +| **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link help** +| +| *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } + + +DESCRIPTION +=========== + **bpftool link { show | list }** [*LINK*] + Show information about active links. If *LINK* is + specified show information only about given link, + otherwise list all links currently active on the system. + + Output will start with link ID followed by link type and + zero or more named attributes, some of which depend on type + of link. + + **bpftool link pin** *LINK* *FILE* + Pin link *LINK* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool link 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**. + + -f, --bpffs + When showing BPF links, show file names of pinned + links. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. + + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf. + +EXAMPLES +======== +**# bpftool link show** + +:: + + 10: cgroup prog 25 + cgroup_id 614 attach_type egress + +**# bpftool --json --pretty link show** + +:: + + [{ + "type": "cgroup", + "prog_id": 25, + "cgroup_id": 614, + "attach_type": "egress" + } + ] + +| +| **# bpftool link pin id 10 /sys/fs/bpf/link** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Apr 23 21:39 link + + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-btf**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-map**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index cdeae8ae90ba..31101643e57c 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -21,7 +21,7 @@ SYNOPSIS MAP COMMANDS ============= -| **bpftool** **map { show | list }** [*MAP*] +| **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ | **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] | **bpftool** **map dump** *MAP* @@ -49,7 +49,7 @@ MAP COMMANDS | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** -| | **queue** | **stack** } +| | **queue** | **stack** | **sk_storage** | **struct_ops** } DESCRIPTION =========== @@ -66,6 +66,13 @@ DESCRIPTION Create a new map with given parameters and pin it to *bpffs* as *FILE*. + *FLAGS* should be an integer which is the combination of + desired flags, e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h + UAPI header for existing flags). + + Keyword **dev** expects a network interface name, and is used + to request hardware offload for the map. + **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, *MAP* may match several maps which will all be dumped. @@ -78,7 +85,7 @@ DESCRIPTION exists; **noexist** update only if entry doesn't exist. If the **hex** keyword is provided in front of the bytes - sequence, the bytes are parsed as hexadeximal values, even if + sequence, the bytes are parsed as hexadecimal values, even if no "0x" prefix is added. If the keyword is not provided, then the bytes are parsed as decimal values, unless a "0x" prefix (for hexadecimal) or a "0" prefix (for octal) is provided. @@ -100,10 +107,10 @@ DESCRIPTION extensions of *bpffs*. **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] - Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map. + Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** map. Install perf rings into a perf event array map and dump - output of any bpf_perf_event_output() call in the kernel. + output of any **bpf_perf_event_output**\ () call in the kernel. By default read the number of CPUs on the system and install perf ring for each CPU in the corresponding index in the array. @@ -116,24 +123,24 @@ DESCRIPTION receiving events if it installed its rings earlier. **bpftool map peek** *MAP* - Peek next **value** in the queue or stack. + Peek next value in the queue or stack. **bpftool map push** *MAP* **value** *VALUE* - Push **value** onto the stack. + Push *VALUE* onto the stack. **bpftool map pop** *MAP* - Pop and print **value** from the stack. + Pop and print value from the stack. **bpftool map enqueue** *MAP* **value** *VALUE* - Enqueue **value** into the queue. + Enqueue *VALUE* into the queue. **bpftool map dequeue** *MAP* - Dequeue and print **value** from the queue. + Dequeue and print value from the queue. **bpftool map freeze** *MAP* Freeze the map as read-only from user space. Entries from a frozen map can not longer be updated or deleted with the - **bpf\ ()** system call. This operation is not reversible, + **bpf**\ () system call. This operation is not reversible, and the map remains immutable from user space until its destruction. However, read and write permissions for BPF programs to the map remain unchanged. @@ -269,9 +276,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 8651b00b81ea..aa7450736179 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -20,7 +20,7 @@ SYNOPSIS NET COMMANDS ============ -| **bpftool** **net { show | list }** [ **dev** *NAME* ] +| **bpftool** **net** { **show** | **list** } [ **dev** *NAME* ] | **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] | **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* | **bpftool** **net help** @@ -194,9 +194,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index e252bd0bc434..9c592b7c6775 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -20,7 +20,7 @@ SYNOPSIS PERF COMMANDS ============= -| **bpftool** **perf { show | list }** +| **bpftool** **perf** { **show** | **list** } | **bpftool** **perf help** DESCRIPTION @@ -85,9 +85,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), - **bpftool-btf**\ (8) + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9f19404f470e..5948e9d89c8d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -21,11 +21,11 @@ SYNOPSIS PROG COMMANDS ============= -| **bpftool** **prog { show | list }** [*PROG*] +| **bpftool** **prog** { **show** | **list** } [*PROG*] | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -49,7 +49,7 @@ PROG COMMANDS | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** | } -| *METRIC* := { +| *METRICs* := { | **cycles** | **instructions** | **l1d_loads** | **llc_misses** | } @@ -155,7 +155,7 @@ DESCRIPTION **bpftool prog tracelog** Dump the trace pipe of the system to the console (stdout). Hit <Ctrl+C> to stop printing. BPF programs can write to this - trace pipe at runtime with the **bpf_trace_printk()** helper. + trace pipe at runtime with the **bpf_trace_printk**\ () helper. This should be used only for debugging purposes. For streaming data from BPF programs to user space, one can use perf events (see also **bpftool-map**\ (8)). @@ -195,9 +195,9 @@ DESCRIPTION **bpftool prog profile** *PROG* [**duration** *DURATION*] *METRICs* Profile *METRICs* for bpf program *PROG* for *DURATION* - seconds or until user hits Ctrl-C. *DURATION* is optional. + seconds or until user hits <Ctrl+C>. *DURATION* is optional. If *DURATION* is not specified, the profiling will run up to - UINT_MAX seconds. + **UINT_MAX** seconds. **bpftool prog help** Print short help message. @@ -267,7 +267,7 @@ EXAMPLES | | **# bpftool prog dump xlated id 10 file /tmp/t** -| **# ls -l /tmp/t** +| **$ ls -l /tmp/t** :: @@ -325,6 +325,7 @@ EXAMPLES | **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses** :: + 51397 run_cnt 40176203 cycles (83.05%) 42518139 instructions # 1.06 insns per cycle (83.39%) @@ -335,9 +336,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst index f045cc89dd6d..d93cd1cb8b0f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -105,12 +105,13 @@ SEE ALSO **bpf**\ (2), **bpf-helpers**\ (7), **bpftool**\ (8), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) - **bpftool-gen**\ (8) - + **bpftool-prog**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 34239fda69ed..420d4d5df8b6 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -75,11 +75,14 @@ SEE ALSO ======== **bpf**\ (2), **bpf-helpers**\ (7), - **bpftool-prog**\ (8), - **bpftool-map**\ (8), + **bpftool-btf**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), + **bpftool-gen**\ (8), + **bpftool-iter**\ (8), + **bpftool-link**\ (8), + **bpftool-map**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8), - **bpftool-gen**\ (8), + **bpftool-prog**\ (8), + **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index f584d1fdfc64..2759f9cc3289 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -55,16 +55,15 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = $(LIBBPF) -lelf -lz - INSTALL ?= install RM ?= rm -f CLANG ?= clang FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib \ +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ + clang-bpf-global-var +FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ clang-bpf-global-var -FEATURE_DISPLAY = libbfd disassembler-four-args zlib clang-bpf-global-var check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -90,6 +89,12 @@ ifeq ($(feature-reallocarray), 0) CFLAGS += -DCOMPAT_NEED_REALLOCARRAY endif +LIBS = $(LIBBPF) -lelf -lz +ifeq ($(feature-libcap), 1) +CFLAGS += -DUSE_LIBCAP +LIBS += -lcap +endif + include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 45ee99b159e2..9f0f20e73b87 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -98,6 +98,12 @@ _bpftool_get_btf_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_link_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp link 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_obj_map_names() { local obj @@ -604,6 +610,19 @@ _bpftool() ;; esac ;; + iter) + case $command in + pin) + _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'pin help' \ + -- "$cur" ) ) + ;; + esac + ;; map) local MAP_TYPE='id pinned name' case $command in @@ -1073,7 +1092,7 @@ _bpftool() COMPREPLY+=( $( compgen -W 'macros' -- "$cur" ) ) fi _bpftool_one_of_list 'kernel dev' - _bpftool_once_attr 'full' + _bpftool_once_attr 'full unprivileged' return 0 ;; *) @@ -1082,6 +1101,39 @@ _bpftool() ;; esac ;; + link) + case $command in + show|list|pin) + case $prev in + id) + _bpftool_get_link_ids + return 0 + ;; + esac + ;; + esac + + local LINK_TYPE='id pinned' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + return 0 + ;; + pin) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + else + _filedir + fi + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help pin show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index bcaf55b59498..41a1346934a1 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -15,7 +15,6 @@ #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> -#include <unistd.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 497807bec675..ede162f83eea 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -271,8 +271,8 @@ static void btf_int128_print(json_writer_t *jw, const void *data, } } -static void btf_int128_shift(__u64 *print_num, u16 left_shift_bits, - u16 right_shift_bits) +static void btf_int128_shift(__u64 *print_num, __u16 left_shift_bits, + __u16 right_shift_bits) { __u64 upper_num, lower_num; diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c index 3e21f994f262..1951219a9af7 100644 --- a/tools/bpf/bpftool/cfg.c +++ b/tools/bpf/bpftool/cfg.c @@ -157,7 +157,7 @@ static bool cfg_partition_funcs(struct cfg *cfg, struct bpf_insn *cur, return false; } -static bool is_jmp_insn(u8 code) +static bool is_jmp_insn(__u8 code) { return BPF_CLASS(code) == BPF_JMP || BPF_CLASS(code) == BPF_JMP32; } @@ -176,7 +176,7 @@ static bool func_partition_bb_head(struct func_node *func) for (; cur <= end; cur++) { if (is_jmp_insn(cur->code)) { - u8 opcode = BPF_OP(cur->code); + __u8 opcode = BPF_OP(cur->code); if (opcode == BPF_EXIT || opcode == BPF_CALL) continue; diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 62c6a1d7cd18..1693c802bb20 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -31,42 +31,20 @@ static unsigned int query_flags; -static const char * const attach_type_strings[] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", - [BPF_CGROUP_SOCK_OPS] = "sock_ops", - [BPF_CGROUP_DEVICE] = "device", - [BPF_CGROUP_INET4_BIND] = "bind4", - [BPF_CGROUP_INET6_BIND] = "bind6", - [BPF_CGROUP_INET4_CONNECT] = "connect4", - [BPF_CGROUP_INET6_CONNECT] = "connect6", - [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", - [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [__MAX_BPF_ATTACH_TYPE] = NULL, -}; - static enum bpf_attach_type parse_attach_type(const char *str) { enum bpf_attach_type type; for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - if (attach_type_strings[type] && - is_prefix(str, attach_type_strings[type])) + if (attach_type_name[type] && + is_prefix(str, attach_type_name[type])) return type; } return __MAX_BPF_ATTACH_TYPE; } -static int show_bpf_prog(int id, const char *attach_type_str, +static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { @@ -86,18 +64,22 @@ static int show_bpf_prog(int id, const char *attach_type_str, if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); - jsonw_string_field(json_wtr, "attach_type", - attach_type_str); + if (attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); jsonw_string_field(json_wtr, "name", info.name); jsonw_end_object(json_wtr); } else { - printf("%s%-8u %-15s %-15s %-15s\n", level ? " " : "", - info.id, - attach_type_str, - attach_flags_str, - info.name); + printf("%s%-8u ", level ? " " : "", info.id); + if (attach_type < ARRAY_SIZE(attach_type_name)) + printf("%-15s", attach_type_name[attach_type]); + else + printf("type %-10u", attach_type); + printf(" %-15s %-15s\n", attach_flags_str, info.name); } close(prog_fd); @@ -171,7 +153,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, } for (iter = 0; iter < prog_cnt; iter++) - show_bpf_prog(prog_ids[iter], attach_type_strings[type], + show_bpf_prog(prog_ids[iter], type, attach_flags_str, level); return 0; diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index f2223dbdfb0a..c47bdc65de8e 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -262,6 +262,8 @@ int get_fd_type(int fd) return BPF_OBJ_MAP; else if (strstr(buf, "bpf-prog")) return BPF_OBJ_PROG; + else if (strstr(buf, "bpf-link")) + return BPF_OBJ_LINK; return BPF_OBJ_UNKNOWN; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 88718ee6a438..1b73e63274b5 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -6,6 +6,9 @@ #include <string.h> #include <unistd.h> #include <net/if.h> +#ifdef USE_LIBCAP +#include <sys/capability.h> +#endif #include <sys/utsname.h> #include <sys/vfs.h> @@ -35,6 +38,11 @@ static const char * const helper_name[] = { #undef BPF_HELPER_MAKE_ENTRY +static bool full_mode; +#ifdef USE_LIBCAP +static bool run_as_unprivileged; +#endif + /* Miscellaneous utility functions */ static bool check_procfs(void) @@ -72,13 +80,12 @@ print_bool_feature(const char *feat_name, const char *plain_name, printf("%s is %savailable\n", plain_name, res ? "" : "NOT "); } -static void print_kernel_option(const char *name, const char *value) +static void print_kernel_option(const char *name, const char *value, + const char *define_prefix) { char *endptr; int res; - /* No support for C-style ouptut */ - if (json_output) { if (!value) { jsonw_null_field(json_wtr, name); @@ -90,6 +97,12 @@ static void print_kernel_option(const char *name, const char *value) jsonw_int_field(json_wtr, name, res); else jsonw_string_field(json_wtr, name, value); + } else if (define_prefix) { + if (value) + printf("#define %s%s %s\n", define_prefix, + name, value); + else + printf("/* %s%s is not set */\n", define_prefix, name); } else { if (value) printf("%s is set to %s\n", name, value); @@ -307,77 +320,84 @@ static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, return false; } -static void probe_kernel_image_config(void) +static void probe_kernel_image_config(const char *define_prefix) { - static const char * const options[] = { + static const struct { + const char * const name; + bool macro_dump; + } options[] = { /* Enable BPF */ - "CONFIG_BPF", + { "CONFIG_BPF", }, /* Enable bpf() syscall */ - "CONFIG_BPF_SYSCALL", + { "CONFIG_BPF_SYSCALL", }, /* Does selected architecture support eBPF JIT compiler */ - "CONFIG_HAVE_EBPF_JIT", + { "CONFIG_HAVE_EBPF_JIT", }, /* Compile eBPF JIT compiler */ - "CONFIG_BPF_JIT", + { "CONFIG_BPF_JIT", }, /* Avoid compiling eBPF interpreter (use JIT only) */ - "CONFIG_BPF_JIT_ALWAYS_ON", + { "CONFIG_BPF_JIT_ALWAYS_ON", }, /* cgroups */ - "CONFIG_CGROUPS", + { "CONFIG_CGROUPS", }, /* BPF programs attached to cgroups */ - "CONFIG_CGROUP_BPF", + { "CONFIG_CGROUP_BPF", }, /* bpf_get_cgroup_classid() helper */ - "CONFIG_CGROUP_NET_CLASSID", + { "CONFIG_CGROUP_NET_CLASSID", }, /* bpf_skb_{,ancestor_}cgroup_id() helpers */ - "CONFIG_SOCK_CGROUP_DATA", + { "CONFIG_SOCK_CGROUP_DATA", }, /* Tracing: attach BPF to kprobes, tracepoints, etc. */ - "CONFIG_BPF_EVENTS", + { "CONFIG_BPF_EVENTS", }, /* Kprobes */ - "CONFIG_KPROBE_EVENTS", + { "CONFIG_KPROBE_EVENTS", }, /* Uprobes */ - "CONFIG_UPROBE_EVENTS", + { "CONFIG_UPROBE_EVENTS", }, /* Tracepoints */ - "CONFIG_TRACING", + { "CONFIG_TRACING", }, /* Syscall tracepoints */ - "CONFIG_FTRACE_SYSCALLS", + { "CONFIG_FTRACE_SYSCALLS", }, /* bpf_override_return() helper support for selected arch */ - "CONFIG_FUNCTION_ERROR_INJECTION", + { "CONFIG_FUNCTION_ERROR_INJECTION", }, /* bpf_override_return() helper */ - "CONFIG_BPF_KPROBE_OVERRIDE", + { "CONFIG_BPF_KPROBE_OVERRIDE", }, /* Network */ - "CONFIG_NET", + { "CONFIG_NET", }, /* AF_XDP sockets */ - "CONFIG_XDP_SOCKETS", + { "CONFIG_XDP_SOCKETS", }, /* BPF_PROG_TYPE_LWT_* and related helpers */ - "CONFIG_LWTUNNEL_BPF", + { "CONFIG_LWTUNNEL_BPF", }, /* BPF_PROG_TYPE_SCHED_ACT, TC (traffic control) actions */ - "CONFIG_NET_ACT_BPF", + { "CONFIG_NET_ACT_BPF", }, /* BPF_PROG_TYPE_SCHED_CLS, TC filters */ - "CONFIG_NET_CLS_BPF", + { "CONFIG_NET_CLS_BPF", }, /* TC clsact qdisc */ - "CONFIG_NET_CLS_ACT", + { "CONFIG_NET_CLS_ACT", }, /* Ingress filtering with TC */ - "CONFIG_NET_SCH_INGRESS", + { "CONFIG_NET_SCH_INGRESS", }, /* bpf_skb_get_xfrm_state() helper */ - "CONFIG_XFRM", + { "CONFIG_XFRM", }, /* bpf_get_route_realm() helper */ - "CONFIG_IP_ROUTE_CLASSID", + { "CONFIG_IP_ROUTE_CLASSID", }, /* BPF_PROG_TYPE_LWT_SEG6_LOCAL and related helpers */ - "CONFIG_IPV6_SEG6_BPF", + { "CONFIG_IPV6_SEG6_BPF", }, /* BPF_PROG_TYPE_LIRC_MODE2 and related helpers */ - "CONFIG_BPF_LIRC_MODE2", + { "CONFIG_BPF_LIRC_MODE2", }, /* BPF stream parser and BPF socket maps */ - "CONFIG_BPF_STREAM_PARSER", + { "CONFIG_BPF_STREAM_PARSER", }, /* xt_bpf module for passing BPF programs to netfilter */ - "CONFIG_NETFILTER_XT_MATCH_BPF", + { "CONFIG_NETFILTER_XT_MATCH_BPF", }, /* bpfilter back-end for iptables */ - "CONFIG_BPFILTER", + { "CONFIG_BPFILTER", }, /* bpftilter module with "user mode helper" */ - "CONFIG_BPFILTER_UMH", + { "CONFIG_BPFILTER_UMH", }, /* test_bpf module for BPF tests */ - "CONFIG_TEST_BPF", + { "CONFIG_TEST_BPF", }, + + /* Misc configs useful in BPF C programs */ + /* jiffies <-> sec conversion for bpf_jiffies64() helper */ + { "CONFIG_HZ", true, } }; char *values[ARRAY_SIZE(options)] = { }; struct utsname utsn; @@ -419,7 +439,8 @@ static void probe_kernel_image_config(void) while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { for (i = 0; i < ARRAY_SIZE(options); i++) { - if (values[i] || strcmp(buf, options[i])) + if ((define_prefix && !options[i].macro_dump) || + values[i] || strcmp(buf, options[i].name)) continue; values[i] = strdup(value); @@ -431,7 +452,9 @@ end_parse: gzclose(file); for (i = 0; i < ARRAY_SIZE(options); i++) { - print_kernel_option(options[i], values[i]); + if (define_prefix && !options[i].macro_dump) + continue; + print_kernel_option(options[i].name, values[i], define_prefix); free(values[i]); } } @@ -471,6 +494,13 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, } res = bpf_probe_prog_type(prog_type, ifindex); +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for unprivileged users + * check that we did not fail because of insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif supported_types[prog_type] |= res; @@ -499,6 +529,10 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, res = bpf_probe_map_type(map_type, ifindex); + /* Probe result depends on the success of map creation, no additional + * check required for unprivileged users + */ + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; if (strlen(map_type_name[map_type]) > maxlen) { p_info("map type name too long"); @@ -518,12 +552,19 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, const char *ptype_name, __u32 ifindex) { - bool res; + bool res = false; - if (!supported_type) - res = false; - else + if (supported_type) { res = bpf_probe_helper(id, prog_type, ifindex); +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for + * unprivileged users check that we did not fail because of + * insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + } if (json_output) { if (res) @@ -540,8 +581,7 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, static void probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, - const char *define_prefix, bool full_mode, - __u32 ifindex) + const char *define_prefix, __u32 ifindex) { const char *ptype_name = prog_type_name[prog_type]; char feat_name[128]; @@ -607,23 +647,22 @@ section_system_config(enum probe_component target, const char *define_prefix) switch (target) { case COMPONENT_KERNEL: case COMPONENT_UNSPEC: - if (define_prefix) - break; - print_start_section("system_config", "Scanning system configuration...", - NULL, /* define_comment never used here */ - NULL); /* define_prefix always NULL here */ - if (check_procfs()) { - probe_unprivileged_disabled(); - probe_jit_enable(); - probe_jit_harden(); - probe_jit_kallsyms(); - probe_jit_limit(); - } else { - p_info("/* procfs not mounted, skipping related probes */"); + "/*** Misc kernel config items ***/", + define_prefix); + if (!define_prefix) { + if (check_procfs()) { + probe_unprivileged_disabled(); + probe_jit_enable(); + probe_jit_harden(); + probe_jit_kallsyms(); + probe_jit_limit(); + } else { + p_info("/* procfs not mounted, skipping related probes */"); + } } - probe_kernel_image_config(); + probe_kernel_image_config(define_prefix); print_end_section(); break; default: @@ -678,8 +717,7 @@ static void section_map_types(const char *define_prefix, __u32 ifindex) } static void -section_helpers(bool *supported_types, const char *define_prefix, - bool full_mode, __u32 ifindex) +section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) { unsigned int i; @@ -704,8 +742,8 @@ section_helpers(bool *supported_types, const char *define_prefix, define_prefix, define_prefix, define_prefix, define_prefix); for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) - probe_helpers_for_progtype(i, supported_types[i], - define_prefix, full_mode, ifindex); + probe_helpers_for_progtype(i, supported_types[i], define_prefix, + ifindex); print_end_section(); } @@ -720,23 +758,86 @@ static void section_misc(const char *define_prefix, __u32 ifindex) print_end_section(); } -static int do_probe(int argc, char **argv) +static int handle_perms(void) { - enum probe_component target = COMPONENT_UNSPEC; - const char *define_prefix = NULL; - bool supported_types[128] = {}; - bool full_mode = false; - __u32 ifindex = 0; - char *ifname; +#ifdef USE_LIBCAP + cap_value_t cap_list[1] = { CAP_SYS_ADMIN }; + bool has_sys_admin_cap = false; + cap_flag_value_t val; + int res = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + p_err("failed to get capabilities for process: %s", + strerror(errno)); + return -1; + } + if (cap_get_flag(caps, CAP_SYS_ADMIN, CAP_EFFECTIVE, &val)) { + p_err("bug: failed to retrieve CAP_SYS_ADMIN status"); + goto exit_free; + } + if (val == CAP_SET) + has_sys_admin_cap = true; + + if (!run_as_unprivileged && !has_sys_admin_cap) { + p_err("full feature probing requires CAP_SYS_ADMIN, run as root or use 'unprivileged'"); + goto exit_free; + } + + if ((run_as_unprivileged && !has_sys_admin_cap) || + (!run_as_unprivileged && has_sys_admin_cap)) { + /* We are all good, exit now */ + res = 0; + goto exit_free; + } + + /* if (run_as_unprivileged && has_sys_admin_cap), drop CAP_SYS_ADMIN */ + + if (cap_set_flag(caps, CAP_EFFECTIVE, ARRAY_SIZE(cap_list), cap_list, + CAP_CLEAR)) { + p_err("bug: failed to clear CAP_SYS_ADMIN from capabilities"); + goto exit_free; + } + + if (cap_set_proc(caps)) { + p_err("failed to drop CAP_SYS_ADMIN: %s", strerror(errno)); + goto exit_free; + } + + res = 0; + +exit_free: + if (cap_free(caps) && !res) { + p_err("failed to clear storage object for capabilities: %s", + strerror(errno)); + res = -1; + } + + return res; +#else /* Detection assumes user has sufficient privileges (CAP_SYS_ADMIN). - * Let's approximate, and restrict usage to root user only. + * We do not use libpcap so let's approximate, and restrict usage to + * root user only. */ if (geteuid()) { - p_err("please run this command as root user"); + p_err("full feature probing requires root privileges"); return -1; } + return 0; +#endif /* USE_LIBCAP */ +} + +static int do_probe(int argc, char **argv) +{ + enum probe_component target = COMPONENT_UNSPEC; + const char *define_prefix = NULL; + bool supported_types[128] = {}; + __u32 ifindex = 0; + char *ifname; + set_max_rlimit(); while (argc) { @@ -785,6 +886,14 @@ static int do_probe(int argc, char **argv) if (!REQ_ARGS(1)) return -1; define_prefix = GET_ARG(); + } else if (is_prefix(*argv, "unprivileged")) { +#ifdef USE_LIBCAP + run_as_unprivileged = true; + NEXT_ARG(); +#else + p_err("unprivileged run not supported, recompile bpftool with libcap"); + return -1; +#endif } else { p_err("expected no more arguments, 'kernel', 'dev', 'macros' or 'prefix', got: '%s'?", *argv); @@ -792,6 +901,12 @@ static int do_probe(int argc, char **argv) } } + /* Full feature detection requires CAP_SYS_ADMIN privilege. + * Let's approximate, and warn if user is not root. + */ + if (handle_perms()) + return -1; + if (json_output) { define_prefix = NULL; jsonw_start_object(json_wtr); @@ -803,7 +918,7 @@ static int do_probe(int argc, char **argv) goto exit_close_json; section_program_types(supported_types, define_prefix, ifindex); section_map_types(define_prefix, ifindex); - section_helpers(supported_types, define_prefix, full_mode, ifindex); + section_helpers(supported_types, define_prefix, ifindex); section_misc(define_prefix, ifindex); exit_close_json: @@ -822,7 +937,7 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s probe [COMPONENT] [full] [macros [prefix PREFIX]]\n" + "Usage: %s %s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" " %s %s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index f8113b3646f5..0e5f0236cc76 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -17,7 +17,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> -#include <unistd.h> #include <bpf/btf.h> #include "bpf/libbpf_internal.h" diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c new file mode 100644 index 000000000000..eb5987a0c3b6 --- /dev/null +++ b/tools/bpf/bpftool/iter.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2020 Facebook + +#define _GNU_SOURCE +#include <linux/err.h> +#include <bpf/libbpf.h> + +#include "main.h" + +static int do_pin(int argc, char **argv) +{ + const char *objfile, *path; + struct bpf_program *prog; + struct bpf_object *obj; + struct bpf_link *link; + int err; + + if (!REQ_ARGS(2)) + usage(); + + objfile = GET_ARG(); + path = GET_ARG(); + + obj = bpf_object__open(objfile); + if (IS_ERR(obj)) { + p_err("can't open objfile %s", objfile); + return -1; + } + + err = bpf_object__load(obj); + if (err) { + p_err("can't load objfile %s", objfile); + goto close_obj; + } + + prog = bpf_program__next(NULL, obj); + if (!prog) { + p_err("can't find bpf program in objfile %s", objfile); + goto close_obj; + } + + link = bpf_program__attach_iter(prog, NULL); + if (IS_ERR(link)) { + err = PTR_ERR(link); + p_err("attach_iter failed for program %s", + bpf_program__name(prog)); + goto close_obj; + } + + err = mount_bpffs_for_pin(path); + if (err) + goto close_link; + + err = bpf_link__pin(link, path); + if (err) { + p_err("pin_iter failed for program %s to path %s", + bpf_program__name(prog), path); + goto close_link; + } + +close_link: + bpf_link__destroy(link); +close_obj: + bpf_object__close(obj); + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s pin OBJ PATH\n" + " %s %s help\n" + "\n", + bin_name, argv[-2], bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "pin", do_pin }, + { 0 } +}; + +int do_iter(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 f7f5885aa3ba..e7e7eee9f172 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -15,7 +15,6 @@ #include <stdio.h> #include <stdarg.h> #include <stdint.h> -#include <stdio.h> #include <stdlib.h> #include <assert.h> #include <unistd.h> diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c new file mode 100644 index 000000000000..b6a0b35c78ae --- /dev/null +++ b/tools/bpf/bpftool/link.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <net/if.h> +#include <stdio.h> +#include <unistd.h> + +#include <bpf/bpf.h> + +#include "json_writer.h" +#include "main.h" + +static const char * const link_type_name[] = { + [BPF_LINK_TYPE_UNSPEC] = "unspec", + [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_LINK_TYPE_TRACING] = "tracing", + [BPF_LINK_TYPE_CGROUP] = "cgroup", + [BPF_LINK_TYPE_ITER] = "iter", +}; + +static int link_parse_fd(int *argc, char ***argv) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + return bpf_link_get_fd_by_id(id); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_LINK); + } + + p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + return -1; +} + +static void +show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(link_type_name)) + jsonw_string_field(wtr, "type", link_type_name[info->type]); + else + jsonw_uint_field(wtr, "type", info->type); + + jsonw_uint_field(json_wtr, "prog_id", info->prog_id); +} + +static int get_prog_info(int prog_id, struct bpf_prog_info *info) +{ + __u32 len = sizeof(*info); + int err, prog_fd; + + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + return prog_fd; + + memset(info, 0, sizeof(*info)); + err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + if (err) + p_err("can't get prog info: %s", strerror(errno)); + close(prog_fd); + return err; +} + +static int show_link_close_json(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + int err; + + jsonw_start_object(json_wtr); + + show_link_header_json(info, json_wtr); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "tp_name", + (const char *)info->raw_tracepoint.tp_name); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + if (prog_info.type < ARRAY_SIZE(prog_type_name)) + jsonw_string_field(json_wtr, "prog_type", + prog_type_name[prog_info.type]); + else + jsonw_uint_field(json_wtr, "prog_type", + prog_info.type); + + if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[info->tracing.attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", + info->tracing.attach_type); + break; + case BPF_LINK_TYPE_CGROUP: + jsonw_lluint_field(json_wtr, "cgroup_id", + info->cgroup.cgroup_id); + if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[info->cgroup.attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", + info->cgroup.attach_type); + break; + default: + break; + } + + if (!hash_empty(link_table.table)) { + struct pinned_obj *obj; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hash_for_each_possible(link_table.table, obj, hash, info->id) { + if (obj->id == info->id) + jsonw_string(json_wtr, obj->path); + } + jsonw_end_array(json_wtr); + } + jsonw_end_object(json_wtr); + + return 0; +} + +static void show_link_header_plain(struct bpf_link_info *info) +{ + printf("%u: ", info->id); + if (info->type < ARRAY_SIZE(link_type_name)) + printf("%s ", link_type_name[info->type]); + else + printf("type %u ", info->type); + + printf("prog %u ", info->prog_id); +} + +static int show_link_close_plain(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + int err; + + show_link_header_plain(info); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + printf("\n\ttp '%s' ", + (const char *)info->raw_tracepoint.tp_name); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + if (prog_info.type < ARRAY_SIZE(prog_type_name)) + printf("\n\tprog_type %s ", + prog_type_name[prog_info.type]); + else + printf("\n\tprog_type %u ", prog_info.type); + + if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name)) + printf("attach_type %s ", + attach_type_name[info->tracing.attach_type]); + else + printf("attach_type %u ", info->tracing.attach_type); + break; + case BPF_LINK_TYPE_CGROUP: + printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); + if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name)) + printf("attach_type %s ", + attach_type_name[info->cgroup.attach_type]); + else + printf("attach_type %u ", info->cgroup.attach_type); + break; + default: + break; + } + + if (!hash_empty(link_table.table)) { + struct pinned_obj *obj; + + hash_for_each_possible(link_table.table, obj, hash, info->id) { + if (obj->id == info->id) + printf("\n\tpinned %s", obj->path); + } + } + + printf("\n"); + + return 0; +} + +static int do_show_link(int fd) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + char raw_tp_name[256]; + int err; + + memset(&info, 0, sizeof(info)); +again: + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get link info: %s", + strerror(errno)); + close(fd); + return err; + } + if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && + !info.raw_tracepoint.tp_name) { + info.raw_tracepoint.tp_name = (unsigned long)&raw_tp_name; + info.raw_tracepoint.tp_name_len = sizeof(raw_tp_name); + goto again; + } + + if (json_output) + show_link_close_json(fd, &info); + else + show_link_close_plain(fd, &info); + + close(fd); + return 0; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err, fd; + + if (show_pinned) + build_pinned_obj_table(&link_table, BPF_OBJ_LINK); + + if (argc == 2) { + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return fd; + return do_show_link(fd); + } + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get link by id (%u): %s", + id, strerror(errno)); + break; + } + + err = do_show_link(fd); + if (err) + break; + } + if (json_output) + jsonw_end_array(json_wtr); + + return errno == ENOENT ? 0 : -1; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, link_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [LINK]\n" + " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_LINK "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "pin", do_pin }, + { 0 } +}; + +int do_link(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 466c269eabdd..46bd716a9d86 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -30,6 +30,7 @@ bool verifier_logs; bool relaxed_maps; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; +struct pinned_obj_table link_table; static void __noreturn clean_and_exit(int i) { @@ -58,7 +59,7 @@ 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 | gen | struct_ops }\n" + " OBJECT := { prog | map | link | cgroup | perf | net | feature | btf | gen | struct_ops | iter }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -215,6 +216,7 @@ static const struct cmd cmds[] = { { "batch", do_batch }, { "prog", do_prog }, { "map", do_map }, + { "link", do_link }, { "cgroup", do_cgroup }, { "perf", do_perf }, { "net", do_net }, @@ -222,6 +224,7 @@ static const struct cmd cmds[] = { { "btf", do_btf }, { "gen", do_gen }, { "struct_ops", do_struct_ops }, + { "iter", do_iter }, { "version", do_version }, { 0 } }; @@ -364,6 +367,7 @@ int main(int argc, char **argv) hash_init(prog_table.table); hash_init(map_table.table); + hash_init(link_table.table); opterr = 0; while ((opt = getopt_long(argc, argv, "Vhpjfmnd", @@ -422,6 +426,7 @@ int main(int argc, char **argv) if (show_pinned) { delete_pinned_obj_table(&prog_table); delete_pinned_obj_table(&map_table); + delete_pinned_obj_table(&link_table); } return ret; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 86f14ce26fd7..f89ac70ef973 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -18,6 +18,9 @@ #include "json_writer.h" +/* Make sure we do not use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) @@ -50,6 +53,8 @@ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" +#define HELP_SPEC_LINK \ + "LINK := { id LINK_ID | pinned FILE }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -83,6 +88,38 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_EXT] = "ext", }; +static const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { + [BPF_CGROUP_INET_INGRESS] = "ingress", + [BPF_CGROUP_INET_EGRESS] = "egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", + [BPF_CGROUP_SOCK_OPS] = "sock_ops", + [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", + [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", + [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", + [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", + + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "raw_tp", + [BPF_TRACE_FENTRY] = "fentry", + [BPF_TRACE_FEXIT] = "fexit", + [BPF_MODIFY_RETURN] = "mod_ret", + [BPF_LSM_MAC] = "lsm_mac", +}; + extern const char * const map_type_name[]; extern const size_t map_type_name_size; @@ -90,6 +127,7 @@ enum bpf_obj_type { BPF_OBJ_UNKNOWN, BPF_OBJ_PROG, BPF_OBJ_MAP, + BPF_OBJ_LINK, }; extern const char *bin_name; @@ -102,6 +140,7 @@ extern bool verifier_logs; extern bool relaxed_maps; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; +extern struct pinned_obj_table link_table; void __printf(1, 2) p_err(const char *fmt, ...); void __printf(1, 2) p_info(const char *fmt, ...); @@ -153,6 +192,7 @@ int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); int do_map(int argc, char **arg); +int do_link(int argc, char **arg); int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); int do_perf(int argc, char **arg); @@ -162,6 +202,7 @@ int do_feature(int argc, char **argv); int do_btf(int argc, char **argv); int do_gen(int argc, char **argv); int do_struct_ops(int argc, char **argv); +int do_iter(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 693a632f6813..85cbe9a19170 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1589,7 +1589,8 @@ static int do_help(int argc, char **argv) " percpu_array | stack_trace | cgroup_array | lru_hash |\n" " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" - " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" + " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" + " queue | stack | sk_storage | struct_ops }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index d9b29c17fbb8..825f29f93a57 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -39,7 +39,7 @@ struct event_ring_info { struct perf_event_sample { struct perf_event_header header; - u64 time; + __u64 time; __u32 size; unsigned char data[]; }; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f6a5974a7b0a..b6e5ba568f98 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -238,7 +238,7 @@ exit_free: return fd; } -static void show_prog_maps(int fd, u32 num_maps) +static void show_prog_maps(int fd, __u32 num_maps) { struct bpf_prog_info info = {}; __u32 len = sizeof(info); diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 8a6f82e56a24..fb1337d69868 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -8,7 +8,8 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL) LIBBPF_SRC := $(abspath ../../lib/bpf) BPFOBJ := $(OUTPUT)/libbpf.a BPF_INCLUDE := $(OUTPUT) -INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) +INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) \ + -I$(abspath ../../include/uapi) CFLAGS := -g -Wall # Try to detect best kernel BTF source diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7bbf1b65be10..146c742f1d49 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -113,6 +113,10 @@ enum bpf_cmd { BPF_MAP_DELETE_BATCH, BPF_LINK_CREATE, BPF_LINK_UPDATE, + BPF_LINK_GET_FD_BY_ID, + BPF_LINK_GET_NEXT_ID, + BPF_ENABLE_STATS, + BPF_ITER_CREATE, }; enum bpf_map_type { @@ -215,11 +219,22 @@ enum bpf_attach_type { BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, BPF_LSM_MAC, + BPF_TRACE_ITER, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_link_type { + BPF_LINK_TYPE_UNSPEC = 0, + BPF_LINK_TYPE_RAW_TRACEPOINT = 1, + BPF_LINK_TYPE_TRACING = 2, + BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, + + MAX_BPF_LINK_TYPE, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -379,6 +394,12 @@ enum { */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) +/* type for BPF_ENABLE_STATS */ +enum bpf_stats_type { + /* enabled run_time_ns and run_cnt */ + BPF_STATS_RUN_TIME = 0, +}; + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -523,6 +544,7 @@ union bpf_attr { __u32 prog_id; __u32 map_id; __u32 btf_id; + __u32 link_id; }; __u32 next_id; __u32 open_flags; @@ -589,6 +611,15 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { /* struct used by BPF_ENABLE_STATS command */ + __u32 type; + } enable_stats; + + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -644,14 +675,16 @@ union bpf_attr { * For tracing programs, safely attempt to read *size* bytes from * kernel space address *unsafe_ptr* and store the data in *dst*. * - * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() - * instead. + * Generally, use **bpf_probe_read_user**\ () or + * **bpf_probe_read_kernel**\ () instead. * Return * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_MONOTONIC**) * Return * Current *ktime*. * @@ -1510,11 +1543,11 @@ union bpf_attr { * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address - * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for * more details. * - * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() - * instead. + * Generally, use **bpf_probe_read_user_str**\ () or + * **bpf_probe_read_kernel_str**\ () instead. * Return * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative @@ -1542,7 +1575,7 @@ union bpf_attr { * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description - * Equivalent to bpf_get_socket_cookie() helper that accepts + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. @@ -1562,7 +1595,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1570,6 +1603,12 @@ union bpf_attr { * must be specified, see **setsockopt(2)** for more information. * The option value of length *optlen* is pointed by *optval*. * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: * @@ -1634,12 +1673,12 @@ union bpf_attr { * * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be - * one of the XDP program return codes up to XDP_TX, as chosen by - * the caller. Any higher bits in the *flags* argument must be + * one of the XDP program return codes up to **XDP_TX**, as chosen + * by the caller. Any higher bits in the *flags* argument must be * unset. * - * See also bpf_redirect(), which only supports redirecting to an - * ifindex, but doesn't require a map to do so. + * See also **bpf_redirect**\ (), which only supports redirecting + * to an ifindex, but doesn't require a map to do so. * Return * **XDP_REDIRECT** on success, or the value of the two lower bits * of the *flags* argument on error. @@ -1747,7 +1786,7 @@ union bpf_attr { * the time running for event since last normalization. The * enabled and running times are accumulated since the perf event * open. To achieve scaling factor between two invocations of an - * eBPF program, users can can use CPU id as the key (which is + * eBPF program, users can use CPU id as the key (which is * typical for perf array usage model) to remember the previous * value and do the calculation inside the eBPF program. * Return @@ -1764,7 +1803,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1773,6 +1812,12 @@ union bpf_attr { * The retrieved value is stored in the structure pointed by * *opval* and of length *optlen*. * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **getsockopt()**. * It supports the following *level*\ s: * @@ -1790,7 +1835,7 @@ union bpf_attr { * The first argument is the context *regs* on which the kprobe * works. * - * This helper works by setting setting the PC (program counter) + * This helper works by setting the PC (program counter) * to an override function which is run in place of the original * probed function. This means the probed function is not run at * all. The replacement function just returns with the required @@ -1959,10 +2004,11 @@ union bpf_attr { * * This helper works for IPv4 and IPv6, TCP and UDP sockets. The * domain (*addr*\ **->sa_family**) must be **AF_INET** (or - * **AF_INET6**). Looking for a free port to bind to can be - * expensive, therefore binding to port is not permitted by the - * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) - * must be set to zero. + * **AF_INET6**). It's advised to pass zero port (**sin_port** + * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like + * behavior and lets the kernel efficiently pick up an unused + * port as long as 4-tuple is unique. Passing non-zero port might + * lead to degraded performance. * Return * 0 on success, or a negative error in case of failure. * @@ -2256,7 +2302,7 @@ union bpf_attr { * **bpf_rc_keydown**\ () again with the same values, or calling * **bpf_rc_repeat**\ (). * - * Some protocols include a toggle bit, in case the button was + * Some protocols include a toggle bit, in case the button was * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into @@ -2602,7 +2648,6 @@ union bpf_attr { * * *th* points to the start of the TCP header, while *th_len* * contains **sizeof**\ (**struct tcphdr**). - * * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -2785,7 +2830,6 @@ union bpf_attr { * * *th* points to the start of the TCP header, while *th_len* * contains the length of the TCP header. - * * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -2868,7 +2912,7 @@ union bpf_attr { * // size, after checking its boundaries. * } * - * In comparison, using **bpf_probe_read_user()** helper here + * In comparison, using **bpf_probe_read_user**\ () helper here * instead to read the string would require to estimate the length * at compile time, and would often result in copying more memory * than necessary. @@ -2886,14 +2930,14 @@ union bpf_attr { * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* - * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. * Return - * On success, the strictly positive length of the string, including + * 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. + * 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. @@ -2921,19 +2965,19 @@ union bpf_attr { * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) * Description * For an eBPF program attached to a perf event, retrieve the - * branch records (struct perf_branch_entry) associated to *ctx* - * and store it in the buffer pointed by *buf* up to size + * branch records (**struct perf_branch_entry**) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size * *size* bytes. * Return * On success, number of bytes written to *buf*. On error, a * negative value. * * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to - * instead return the number of bytes required to store all the + * instead return the number of bytes required to store all the * branch entries. If this flag is set, *buf* may be NULL. * * **-EINVAL** if arguments invalid or **size** not a multiple - * of sizeof(struct perf_branch_entry). + * of **sizeof**\ (**struct perf_branch_entry**\ ). * * **-ENOENT** if architecture does not support branch records. * @@ -2941,8 +2985,8 @@ union bpf_attr { * Description * Returns 0 on success, values for *pid* and *tgid* as seen from the current * *namespace* will be returned in *nsdata*. - * - * On failure, the returned value is one of the following: + * Return + * 0 on success, or one of the following in case of failure: * * **-EINVAL** if dev and inum supplied don't match dev_t and inode number * with nsfs of current task, or if dev conversion to dev_t lost high bits. @@ -2981,8 +3025,8 @@ union bpf_attr { * a global identifier that can be assumed unique. If *ctx* is * NULL, then the helper returns the cookie for the initial * network namespace. The cookie itself is very similar to that - * of bpf_get_socket_cookie() helper, but for network namespaces - * instead of sockets. + * of **bpf_get_socket_cookie**\ () helper, but for network + * namespaces instead of sockets. * Return * A 8-byte long opaque number. * @@ -3017,14 +3061,98 @@ union bpf_attr { * * The *flags* argument must be zero. * Return - * 0 on success, or a negative errno in case of failure. - * - * * **-EINVAL** Unsupported flags specified. - * * **-ENOENT** Socket is unavailable for assignment. - * * **-ENETUNREACH** Socket is unreachable (wrong netns). - * * **-EOPNOTSUPP** Unsupported operation, for example a - * call from outside of TC ingress. - * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * 0 on success, or a negative error in case of failure: + * + * **-EINVAL** if specified *flags* are not supported. + * + * **-ENOENT** if the socket is unavailable for assignment. + * + * **-ENETUNREACH** if the socket is unreachable (wrong netns). + * + * **-EOPNOTSUPP** if the operation is not supported, for example + * a call from outside of TC ingress. + * + * **-ESOCKTNOSUPPORT** if the socket type is not supported + * (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_BOOTTIME**) + * Return + * Current *ktime*. + * + * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print + * out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a **u64** array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the size of *data* in bytes. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what **bpf_trace_printk**\ () does for now. + * Return + * 0 on success, or a negative error in case of failure: + * + * **-EBUSY** if per-CPU memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * + * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported. + * + * **-E2BIG** if *fmt* contains too many format specifiers. + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative error in case of failure: + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * u64 bpf_sk_cgroup_id(struct bpf_sock *sk) + * Description + * Return the cgroup v2 id of the socket *sk*. + * + * *sk* must be a non-**NULL** pointer to a full socket, e.g. one + * returned from **bpf_sk_lookup_xxx**\ (), + * **bpf_sk_fullsock**\ (), etc. The format of returned id is + * same as in **bpf_skb_cgroup_id**\ (). + * + * This helper is available only if the kernel was compiled with + * the **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *sk* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *sk*, then return value will be same as that + * of **bpf_sk_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *sk*. + * + * The format of returned id and helper limitations are same as in + * **bpf_sk_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3279,12 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), \ + FN(seq_printf), \ + FN(seq_write), \ + FN(sk_cgroup_id), \ + FN(sk_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3598,6 +3731,25 @@ struct bpf_btf_info { __u32 id; } __attribute__((aligned(8))); +struct bpf_link_info { + __u32 type; + __u32 id; + __u32 prog_id; + union { + struct { + __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ + __u32 tp_name_len; /* in/out: tp_name buffer len */ + } raw_tracepoint; + struct { + __u32 attach_type; + } tracing; + struct { + __u64 cgroup_id; + __u32 attach_type; + } cgroup; + }; +} __attribute__((aligned(8))); + /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on * attach attach type). @@ -3610,7 +3762,7 @@ struct bpf_sock_addr { __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ - __u32 user_port; /* Allows 4-byte read and write. + __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order */ __u32 family; /* Allows 4-byte read, but no write */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index ca6665ea758a..cafedbbfefbe 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -343,6 +343,7 @@ enum { IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, IFLA_BRPORT_BACKUP_PORT, + IFLA_BRPORT_MRP_RING_OPEN, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 5cc1b0785d18..a7329b671c41 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -619,6 +619,16 @@ int bpf_link_update(int link_fd, int new_prog_fd, return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); } +int bpf_iter_create(int link_fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.iter_create.link_fd = link_fd; + + return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr)); +} + int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) { @@ -721,6 +731,11 @@ int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id) return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID); } +int bpf_link_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID); +} + int bpf_prog_get_fd_by_id(__u32 id) { union bpf_attr attr; @@ -751,13 +766,23 @@ int bpf_btf_get_fd_by_id(__u32 id) return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); } -int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) +int bpf_link_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.link_id = id; + + return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) { union bpf_attr attr; int err; memset(&attr, 0, sizeof(attr)); - attr.info.bpf_fd = prog_fd; + attr.info.bpf_fd = bpf_fd; attr.info.info_len = *info_len; attr.info.info = ptr_to_u64(info); @@ -826,3 +851,13 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, return err; } + +int bpf_enable_stats(enum bpf_stats_type type) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.enable_stats.type = type; + + return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr)); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 46d47afdd887..1b6015b21ba8 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -187,6 +187,8 @@ struct bpf_link_update_opts { LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts); +LIBBPF_API int bpf_iter_create(int link_fd); + struct bpf_prog_test_run_attr { int prog_fd; int repeat; @@ -216,10 +218,12 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); +LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); @@ -229,6 +233,7 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); +LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index f69cc208778a..f67dce2af802 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -2,10 +2,17 @@ #ifndef __BPF_HELPERS__ #define __BPF_HELPERS__ +/* + * Note that bpf programs need to include either + * vmlinux.h (auto-generated from BTF) or linux/types.h + * in advance since bpf_helper_defs.h uses such types + * as __u64. + */ #include "bpf_helper_defs.h" #define __uint(name, val) int (*name)[val] #define __type(name, val) typeof(val) *name +#define __array(name, val) typeof(val) *name[] /* Helper macro to print out debug messages */ #define bpf_printk(fmt, ...) \ @@ -30,6 +37,20 @@ #endif /* + * Helper macro to manipulate data structures + */ +#ifndef offsetof +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) +#endif +#ifndef container_of +#define container_of(ptr, type, member) \ + ({ \ + void *__mptr = (void *)(ptr); \ + ((type *)(__mptr - offsetof(type, member))); \ + }) +#endif + +/* * Helper structure used by eBPF C program * to describe BPF map attributes to libbpf loader */ diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 48a9c7c69ef1..58eceb884df3 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -413,4 +413,20 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +/* + * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values + * in a structure. + */ +#define BPF_SEQ_PRINTF(seq, fmt, args...) \ + ({ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[] = { args }; \ + _Pragma("GCC diagnostic pop") \ + int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ + ___ret; \ + }) + #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0c28ee82834b..de07e559a11d 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -658,7 +658,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) if (!btf_dump_is_blacklisted(d, id)) { btf_dump_emit_typedef_def(d, id, t, 0); btf_dump_printf(d, ";\n\n"); - }; + } tstate->fwd_emitted = 1; break; default: diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 54c30c802070..cffb96202e0d 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -59,7 +59,14 @@ struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, void hashmap__clear(struct hashmap *map) { + struct hashmap_entry *cur, *tmp; + int bkt; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + free(cur); + } free(map->buckets); + map->buckets = NULL; map->cap = map->cap_bits = map->sz = 0; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8f480e29a6b0..292257995487 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -310,6 +310,7 @@ struct bpf_map { int map_ifindex; int inner_map_fd; struct bpf_map_def def; + __u32 btf_var_idx; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -318,6 +319,9 @@ struct bpf_map { enum libbpf_map_type libbpf_type; void *mmaped; struct bpf_struct_ops *st_ops; + struct bpf_map *inner_map; + void **init_slots; + int init_slots_sz; char *pin_path; bool pinned; bool reused; @@ -389,6 +393,7 @@ struct bpf_object { int nr_reloc_sects; int maps_shndx; int btf_maps_shndx; + __u32 btf_maps_sec_btf_id; int text_shndx; int symbols_shndx; int data_shndx; @@ -1914,109 +1919,54 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) return 0; } -static int bpf_object__init_user_btf_map(struct bpf_object *obj, - const struct btf_type *sec, - int var_idx, int sec_idx, - const Elf_Data *data, bool strict, - const char *pin_root_path) + +static int parse_btf_map_def(struct bpf_object *obj, + struct bpf_map *map, + const struct btf_type *def, + bool strict, bool is_inner, + const char *pin_root_path) { - const struct btf_type *var, *def, *t; - const struct btf_var_secinfo *vi; - const struct btf_var *var_extra; + const struct btf_type *t; const struct btf_member *m; - const char *map_name; - struct bpf_map *map; int vlen, i; - vi = btf_var_secinfos(sec) + var_idx; - var = btf__type_by_id(obj->btf, vi->type); - var_extra = btf_var(var); - map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = btf_vlen(var); - - if (map_name == NULL || map_name[0] == '\0') { - pr_warn("map #%d: empty name.\n", var_idx); - return -EINVAL; - } - if ((__u64)vi->offset + vi->size > data->d_size) { - pr_warn("map '%s' BTF data is corrupted.\n", map_name); - return -EINVAL; - } - if (!btf_is_var(var)) { - pr_warn("map '%s': unexpected var kind %u.\n", - map_name, btf_kind(var)); - return -EINVAL; - } - if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && - var_extra->linkage != BTF_VAR_STATIC) { - pr_warn("map '%s': unsupported var linkage %u.\n", - map_name, var_extra->linkage); - return -EOPNOTSUPP; - } - - def = skip_mods_and_typedefs(obj->btf, var->type, NULL); - if (!btf_is_struct(def)) { - pr_warn("map '%s': unexpected def kind %u.\n", - map_name, btf_kind(var)); - return -EINVAL; - } - if (def->size > vi->size) { - pr_warn("map '%s': invalid def size.\n", map_name); - return -EINVAL; - } - - map = bpf_object__add_map(obj); - if (IS_ERR(map)) - return PTR_ERR(map); - map->name = strdup(map_name); - if (!map->name) { - pr_warn("map '%s': failed to alloc map name.\n", map_name); - return -ENOMEM; - } - map->libbpf_type = LIBBPF_MAP_UNSPEC; - map->def.type = BPF_MAP_TYPE_UNSPEC; - map->sec_idx = sec_idx; - map->sec_offset = vi->offset; - pr_debug("map '%s': at sec_idx %d, offset %zu.\n", - map_name, map->sec_idx, map->sec_offset); - vlen = btf_vlen(def); m = btf_members(def); for (i = 0; i < vlen; i++, m++) { const char *name = btf__name_by_offset(obj->btf, m->name_off); if (!name) { - pr_warn("map '%s': invalid field #%d.\n", map_name, i); + pr_warn("map '%s': invalid field #%d.\n", map->name, i); return -EINVAL; } if (strcmp(name, "type") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.type)) return -EINVAL; pr_debug("map '%s': found type = %u.\n", - map_name, map->def.type); + map->name, map->def.type); } else if (strcmp(name, "max_entries") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.max_entries)) return -EINVAL; pr_debug("map '%s': found max_entries = %u.\n", - map_name, map->def.max_entries); + map->name, map->def.max_entries); } else if (strcmp(name, "map_flags") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.map_flags)) return -EINVAL; pr_debug("map '%s': found map_flags = %u.\n", - map_name, map->def.map_flags); + map->name, map->def.map_flags); } else if (strcmp(name, "key_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, m, &sz)) + if (!get_map_field_int(map->name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found key_size = %u.\n", - map_name, sz); + map->name, sz); if (map->def.key_size && map->def.key_size != sz) { pr_warn("map '%s': conflicting key size %u != %u.\n", - map_name, map->def.key_size, sz); + map->name, map->def.key_size, sz); return -EINVAL; } map->def.key_size = sz; @@ -2026,25 +1976,25 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { pr_warn("map '%s': key type [%d] not found.\n", - map_name, m->type); + map->name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': key spec is not PTR: %u.\n", - map_name, btf_kind(t)); + map->name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); return sz; } pr_debug("map '%s': found key [%u], sz = %zd.\n", - map_name, t->type, (ssize_t)sz); + 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 != %zd.\n", - map_name, map->def.key_size, (ssize_t)sz); + map->name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -2052,13 +2002,13 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } else if (strcmp(name, "value_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, m, &sz)) + if (!get_map_field_int(map->name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found value_size = %u.\n", - map_name, sz); + map->name, sz); if (map->def.value_size && map->def.value_size != sz) { pr_warn("map '%s': conflicting value size %u != %u.\n", - map_name, map->def.value_size, sz); + map->name, map->def.value_size, sz); return -EINVAL; } map->def.value_size = sz; @@ -2068,71 +2018,207 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { pr_warn("map '%s': value type [%d] not found.\n", - map_name, m->type); + map->name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': value spec is not PTR: %u.\n", - map_name, btf_kind(t)); + map->name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); return sz; } pr_debug("map '%s': found value [%u], sz = %zd.\n", - map_name, t->type, (ssize_t)sz); + 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 != %zd.\n", - map_name, map->def.value_size, (ssize_t)sz); + map->name, map->def.value_size, (ssize_t)sz); return -EINVAL; } map->def.value_size = sz; map->btf_value_type_id = t->type; + } + else if (strcmp(name, "values") == 0) { + int err; + + if (is_inner) { + pr_warn("map '%s': multi-level inner maps not supported.\n", + map->name); + return -ENOTSUP; + } + if (i != vlen - 1) { + pr_warn("map '%s': '%s' member should be last.\n", + map->name, name); + return -EINVAL; + } + if (!bpf_map_type__is_map_in_map(map->def.type)) { + pr_warn("map '%s': should be map-in-map.\n", + map->name); + return -ENOTSUP; + } + if (map->def.value_size && map->def.value_size != 4) { + pr_warn("map '%s': conflicting value size %u != 4.\n", + map->name, map->def.value_size); + return -EINVAL; + } + map->def.value_size = 4; + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': map-in-map inner type [%d] not found.\n", + map->name, m->type); + return -EINVAL; + } + if (!btf_is_array(t) || btf_array(t)->nelems) { + pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", + map->name); + return -EINVAL; + } + t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type, + NULL); + if (!btf_is_ptr(t)) { + pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", + map->name, btf_kind(t)); + return -EINVAL; + } + t = skip_mods_and_typedefs(obj->btf, t->type, NULL); + if (!btf_is_struct(t)) { + pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", + map->name, btf_kind(t)); + return -EINVAL; + } + + map->inner_map = calloc(1, sizeof(*map->inner_map)); + if (!map->inner_map) + return -ENOMEM; + map->inner_map->sec_idx = obj->efile.btf_maps_shndx; + map->inner_map->name = malloc(strlen(map->name) + + sizeof(".inner") + 1); + if (!map->inner_map->name) + return -ENOMEM; + sprintf(map->inner_map->name, "%s.inner", map->name); + + err = parse_btf_map_def(obj, map->inner_map, t, strict, + true /* is_inner */, NULL); + if (err) + return err; } else if (strcmp(name, "pinning") == 0) { __u32 val; int err; - if (!get_map_field_int(map_name, obj->btf, m, &val)) + if (is_inner) { + pr_debug("map '%s': inner def can't be pinned.\n", + map->name); + return -EINVAL; + } + if (!get_map_field_int(map->name, obj->btf, m, &val)) return -EINVAL; pr_debug("map '%s': found pinning = %u.\n", - map_name, val); + map->name, val); if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) { pr_warn("map '%s': invalid pinning value %u.\n", - map_name, val); + map->name, val); return -EINVAL; } if (val == LIBBPF_PIN_BY_NAME) { err = build_map_pin_path(map, pin_root_path); if (err) { pr_warn("map '%s': couldn't build pin path.\n", - map_name); + map->name); return err; } } } else { if (strict) { pr_warn("map '%s': unknown field '%s'.\n", - map_name, name); + map->name, name); return -ENOTSUP; } pr_debug("map '%s': ignoring unknown field '%s'.\n", - map_name, name); + map->name, name); } } if (map->def.type == BPF_MAP_TYPE_UNSPEC) { - pr_warn("map '%s': map type isn't specified.\n", map_name); + pr_warn("map '%s': map type isn't specified.\n", map->name); return -EINVAL; } return 0; } +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict, + const char *pin_root_path) +{ + const struct btf_type *var, *def; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const char *map_name; + struct bpf_map *map; + + vi = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warn("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + map->btf_var_idx = var_idx; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + return parse_btf_map_def(obj, map, def, strict, false, pin_root_path); +} + static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, const char *pin_root_path) { @@ -2163,6 +2249,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { sec = t; + obj->efile.btf_maps_sec_btf_id = i; break; } } @@ -2549,7 +2636,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* Only do relo for section with exec instructions */ if (!section_have_execinstr(obj, sec) && - strcmp(name, ".rel" STRUCT_OPS_SEC)) { + strcmp(name, ".rel" STRUCT_OPS_SEC) && + strcmp(name, ".rel" MAPS_ELF_SEC)) { pr_debug("skip relo %s(%d) for section(%d)\n", name, idx, sec); continue; @@ -3149,7 +3237,7 @@ int bpf_map__resize(struct bpf_map *map, __u32 max_entries) } static int -bpf_object__probe_name(struct bpf_object *obj) +bpf_object__probe_loading(struct bpf_object *obj) { struct bpf_load_program_attr attr; char *cp, errmsg[STRERR_BUFSIZE]; @@ -3169,15 +3257,36 @@ bpf_object__probe_name(struct bpf_object *obj) ret = bpf_load_program_xattr(&attr, NULL, 0); if (ret < 0) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", - __func__, cp, errno); - return -errno; + ret = errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't load trivial BPF " + "program. Make sure your kernel supports BPF " + "(CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is " + "set to big enough value.\n", __func__, cp, ret); + return -ret; } close(ret); - /* now try the same program, but with the name */ + return 0; +} + +static int +bpf_object__probe_name(struct bpf_object *obj) +{ + struct bpf_load_program_attr attr; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret; + + /* make sure loading with name works */ + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; attr.name = "test"; ret = bpf_load_program_xattr(&attr, NULL, 0); if (ret >= 0) { @@ -3482,124 +3591,181 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) return 0; } +static void bpf_map__destroy(struct bpf_map *map); + +static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) +{ + struct bpf_create_map_attr create_attr; + struct bpf_map_def *def = &map->def; + + memset(&create_attr, 0, sizeof(create_attr)); + + if (obj->caps.name) + create_attr.name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { + int nr_cpus; + + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("map '%s': failed to determine number of system CPUs: %d\n", + map->name, nr_cpus); + return nr_cpus; + } + pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } + + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = + map->btf_vmlinux_value_type_id; + + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_type_id = map->btf_key_type_id; + create_attr.btf_value_type_id = map->btf_value_type_id; + } + + if (bpf_map_type__is_map_in_map(def->type)) { + if (map->inner_map) { + int err; + + err = bpf_object__create_map(obj, map->inner_map); + if (err) { + pr_warn("map '%s': failed to create inner map: %d\n", + map->name, err); + return err; + } + map->inner_map_fd = bpf_map__fd(map->inner_map); + } + if (map->inner_map_fd >= 0) + create_attr.inner_map_fd = map->inner_map_fd; + } + + map->fd = bpf_create_map_xattr(&create_attr); + if (map->fd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { + char *cp, errmsg[STRERR_BUFSIZE]; + int err = -errno; + + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, err); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + map->fd = bpf_create_map_xattr(&create_attr); + } + + if (map->fd < 0) + return -errno; + + if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { - struct bpf_create_map_attr create_attr = {}; - int nr_cpus = 0; - unsigned int i; + struct bpf_map *map; + char *cp, errmsg[STRERR_BUFSIZE]; + unsigned int i, j; int err; for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map *map = &obj->maps[i]; - struct bpf_map_def *def = &map->def; - char *cp, errmsg[STRERR_BUFSIZE]; - int *pfd = &map->fd; + map = &obj->maps[i]; if (map->pin_path) { err = bpf_object__reuse_map(map); if (err) { - pr_warn("error reusing pinned map %s\n", + pr_warn("map '%s': error reusing pinned map\n", map->name); - return err; + goto err_out; } } if (map->fd >= 0) { - pr_debug("skip map create (preset) %s: fd=%d\n", + pr_debug("map '%s': skipping creation (preset fd=%d)\n", map->name, map->fd); continue; } - if (obj->caps.name) - create_attr.name = map->name; - create_attr.map_ifindex = map->map_ifindex; - create_attr.map_type = def->type; - create_attr.map_flags = def->map_flags; - create_attr.key_size = def->key_size; - create_attr.value_size = def->value_size; - if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && - !def->max_entries) { - if (!nr_cpus) - nr_cpus = libbpf_num_possible_cpus(); - if (nr_cpus < 0) { - pr_warn("failed to determine number of system CPUs: %d\n", - nr_cpus); - err = nr_cpus; - goto err_out; - } - pr_debug("map '%s': setting size to %d\n", - map->name, nr_cpus); - create_attr.max_entries = nr_cpus; - } else { - create_attr.max_entries = def->max_entries; - } - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; - 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); - create_attr.btf_key_type_id = map->btf_key_type_id; - create_attr.btf_value_type_id = map->btf_value_type_id; - } - - *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && (create_attr.btf_key_type_id || - create_attr.btf_value_type_id)) { - err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, err); - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; - map->btf_key_type_id = 0; - map->btf_value_type_id = 0; - *pfd = bpf_create_map_xattr(&create_attr); - } + err = bpf_object__create_map(obj, map); + if (err) + goto err_out; - if (*pfd < 0) { - size_t j; - - err = -errno; -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; - } + pr_debug("map '%s': created successfully, fd=%d\n", map->name, + map->fd); if (bpf_map__is_internal(map)) { err = bpf_object__populate_internal_map(obj, map); if (err < 0) { - zclose(*pfd); + zclose(map->fd); goto err_out; } } + if (map->init_slots_sz) { + for (j = 0; j < map->init_slots_sz; j++) { + const struct bpf_map *targ_map; + int fd; + + if (!map->init_slots[j]) + continue; + + targ_map = map->init_slots[j]; + fd = bpf_map__fd(targ_map); + err = bpf_map_update_elem(map->fd, &j, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", + map->name, j, targ_map->name, + fd, err); + goto err_out; + } + pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", + map->name, j, targ_map->name, fd); + } + zfree(&map->init_slots); + map->init_slots_sz = 0; + } + if (map->pin_path && !map->pinned) { err = bpf_map__pin(map, NULL); if (err) { - pr_warn("failed to auto-pin map name '%s' at '%s'\n", - map->name, map->pin_path); - return err; + pr_warn("map '%s': failed to auto-pin at '%s': %d\n", + map->name, map->pin_path, err); + zclose(map->fd); + goto err_out; } } - - pr_debug("created map %s: fd=%d\n", map->name, *pfd); } return 0; + +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("map '%s': failed to create: %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); + for (j = 0; j < i; j++) + zclose(obj->maps[j].fd); + return err; } static int @@ -4851,9 +5017,118 @@ 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_st_ops_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data); + +static int bpf_object__collect_map_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data) +{ + int i, j, nrels, new_sz, ptr_sz = sizeof(void *); + const struct btf_var_secinfo *vi = NULL; + const struct btf_type *sec, *var, *def; + const struct btf_member *member; + struct bpf_map *map, *targ_map; + const char *name, *mname; + Elf_Data *symbols; + unsigned int moff; + GElf_Sym sym; + GElf_Rel rel; + void *tmp; + + if (!obj->efile.btf_maps_sec_btf_id || !obj->btf) + return -EINVAL; + sec = btf__type_by_id(obj->btf, obj->efile.btf_maps_sec_btf_id); + if (!sec) + return -EINVAL; + + symbols = obj->efile.symbols; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + if (!gelf_getrel(data, i, &rel)) { + pr_warn(".maps relo #%d: failed to get ELF relo\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn(".maps relo #%d: symbol %zx not found\n", + i, (size_t)GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + if (sym.st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + + pr_debug(".maps relo #%d: for %zd value %zd rel.r_offset %zu name %d ('%s')\n", + i, (ssize_t)(rel.r_info >> 32), (size_t)sym.st_value, + (size_t)rel.r_offset, sym.st_name, name); + + for (j = 0; j < obj->nr_maps; j++) { + map = &obj->maps[j]; + if (map->sec_idx != obj->efile.btf_maps_shndx) + continue; + + vi = btf_var_secinfos(sec) + map->btf_var_idx; + if (vi->offset <= rel.r_offset && + rel.r_offset + sizeof(void *) <= vi->offset + vi->size) + break; + } + if (j == obj->nr_maps) { + pr_warn(".maps relo #%d: cannot find map '%s' at rel.r_offset %zu\n", + i, name, (size_t)rel.r_offset); + return -EINVAL; + } + + if (!bpf_map_type__is_map_in_map(map->def.type)) + return -EINVAL; + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) + return -ESRCH; + + var = btf__type_by_id(obj->btf, vi->type); + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (btf_vlen(def) == 0) + return -EINVAL; + member = btf_members(def) + btf_vlen(def) - 1; + mname = btf__name_by_offset(obj->btf, member->name_off); + if (strcmp(mname, "values")) + return -EINVAL; + + moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8; + if (rel.r_offset - vi->offset < moff) + return -EINVAL; + + moff = rel.r_offset - vi->offset - moff; + if (moff % ptr_sz) + return -EINVAL; + moff /= ptr_sz; + if (moff >= map->init_slots_sz) { + new_sz = moff + 1; + tmp = realloc(map->init_slots, new_sz * ptr_sz); + if (!tmp) + return -ENOMEM; + map->init_slots = tmp; + memset(map->init_slots + map->init_slots_sz, 0, + (new_sz - map->init_slots_sz) * ptr_sz); + map->init_slots_sz = new_sz; + } + map->init_slots[moff] = targ_map; + + pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n", + i, map->name, moff, name); + } + + return 0; +} static int bpf_object__collect_reloc(struct bpf_object *obj) { @@ -4876,21 +5151,17 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) } 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); - return -LIBBPF_ERRNO__RELOC; + err = bpf_object__collect_st_ops_relos(obj, shdr, data); + } else if (idx == obj->efile.btf_maps_shndx) { + err = bpf_object__collect_map_relos(obj, shdr, data); + } else { + prog = bpf_object__find_prog_by_idx(obj, idx); + if (!prog) { + pr_warn("relocation failed: no prog in section(%d)\n", idx); + return -LIBBPF_ERRNO__RELOC; + } + err = bpf_program__collect_reloc(prog, shdr, data, obj); } - - err = bpf_program__collect_reloc(prog, shdr, data, obj); if (err) return err; } @@ -5386,7 +5657,8 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; - err = bpf_object__probe_caps(obj); + err = bpf_object__probe_loading(obj); + err = 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); @@ -5955,6 +6227,40 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +static void bpf_map__destroy(struct bpf_map *map) +{ + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + 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); + + if (map->fd >= 0) + zclose(map->fd); +} + void bpf_object__close(struct bpf_object *obj) { size_t i; @@ -5970,29 +6276,8 @@ void bpf_object__close(struct bpf_object *obj) btf__free(obj->btf); btf_ext__free(obj->btf_ext); - for (i = 0; i < obj->nr_maps; i++) { - 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); - } + for (i = 0; i < obj->nr_maps; i++) + bpf_map__destroy(&obj->maps[i]); zfree(&obj->kconfig); zfree(&obj->externs); @@ -6323,6 +6608,8 @@ static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, struct bpf_program *prog); static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, struct bpf_program *prog); +static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, + struct bpf_program *prog); static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), @@ -6366,6 +6653,10 @@ static const struct bpf_sec_def section_defs[] = { .is_attach_btf = true, .expected_attach_type = BPF_LSM_MAC, .attach_fn = attach_lsm), + SEC_DEF("iter/", TRACING, + .expected_attach_type = BPF_TRACE_ITER, + .is_attach_btf = true, + .attach_fn = attach_iter), 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), @@ -6516,9 +6807,8 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, } /* 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) +static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data) { const struct btf_member *member; struct bpf_struct_ops *st_ops; @@ -6629,6 +6919,7 @@ invalid_prog: #define BTF_TRACE_PREFIX "btf_trace_" #define BTF_LSM_PREFIX "bpf_lsm_" +#define BTF_ITER_PREFIX "bpf_iter_" #define BTF_MAX_NAME_SIZE 128 static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, @@ -6659,6 +6950,9 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, else if (attach_type == BPF_LSM_MAC) err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name, BTF_KIND_FUNC); + else if (attach_type == BPF_TRACE_ITER) + err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name, + BTF_KIND_FUNC); else err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); @@ -6672,6 +6966,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, enum bpf_attach_type attach_type) { struct btf *btf; + int err; btf = libbpf_find_kernel_btf(); if (IS_ERR(btf)) { @@ -6679,7 +6974,9 @@ int libbpf_find_vmlinux_btf_id(const char *name, return -EINVAL; } - return __find_vmlinux_btf_id(btf, name, attach_type); + err = __find_vmlinux_btf_id(btf, name, attach_type); + btf__free(btf); + return err; } static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) @@ -7006,7 +7303,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, err = bpf_object__load(obj); if (err) { bpf_object__close(obj); - return -EINVAL; + return err; } *pobj = obj; @@ -7583,6 +7880,12 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, return bpf_program__attach_lsm(prog); } +static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_iter(prog, NULL); +} + struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) { @@ -7617,6 +7920,42 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) return link; } +struct bpf_link * +bpf_program__attach_iter(struct bpf_program *prog, + const struct bpf_iter_attach_opts *opts) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int prog_fd, link_fd; + + if (!OPTS_VALID(opts, bpf_iter_attach_opts)) + return ERR_PTR(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->detach = &bpf_link__detach_fd; + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_ITER, NULL); + if (link_fd < 0) { + link_fd = -errno; + free(link); + pr_warn("program '%s': failed to attach to iterator: %s\n", + bpf_program__title(prog, false), + libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return ERR_PTR(link_fd); + } + link->fd = link_fd; + return link; +} + struct bpf_link *bpf_program__attach(struct bpf_program *prog) { const struct bpf_sec_def *sec_def; @@ -8035,7 +8374,7 @@ error: struct perf_sample_raw { struct perf_event_header header; uint32_t size; - char data[0]; + char data[]; }; struct perf_sample_lost { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f1dacecb1619..8ea69558f0a8 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -258,6 +258,15 @@ struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); +struct bpf_iter_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ +}; +#define bpf_iter_attach_opts__last_field sz + +LIBBPF_API struct bpf_link * +bpf_program__attach_iter(struct bpf_program *prog, + const struct bpf_iter_attach_opts *opts); + struct bpf_insn; /* diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index bb8831605b25..0133d469d30b 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -254,3 +254,12 @@ LIBBPF_0.0.8 { bpf_program__set_lsm; bpf_set_link_xdp_fd_opts; } LIBBPF_0.0.7; + +LIBBPF_0.0.9 { + global: + bpf_enable_stats; + bpf_iter_create; + bpf_link_get_fd_by_id; + bpf_link_get_next_id; + bpf_program__attach_iter; +} LIBBPF_0.0.8; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 8c3afbd97747..50d70e90d5f1 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -153,7 +153,7 @@ struct btf_ext_info_sec { __u32 sec_name_off; __u32 num_info; /* Followed by num_info * record_size number of bytes */ - __u8 data[0]; + __u8 data[]; }; /* The minimum bpf_func_info checked by the loader */ diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index ec053dc1e35c..9207b6c45475 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -686,8 +686,11 @@ try_again_reset: break; } } - if (child_pid != -1) + if (child_pid != -1) { + if (timeout) + kill(child_pid, SIGTERM); wait4(child_pid, &status, 0, &stat_config.ru_data); + } if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f1ea0d61eb5b..9760d58e979a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1821,6 +1821,24 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, } #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +static int +symbol__disassemble_bpf_image(struct symbol *sym, + struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *dl; + + args->offset = -1; + args->line = strdup("to be implemented"); + args->line_nr = 0; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + free(args->line); + return 0; +} + /* * Possibly create a new version of line with tabs expanded. Returns the * existing or new line, storage is updated if a new line is allocated. If @@ -1920,6 +1938,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) { return symbol__disassemble_bpf(sym, args); + } else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) { + return symbol__disassemble_bpf_image(sym, args); } else if (dso__is_kcore(dso)) { kce.kcore_filename = symfs_filename; kce.addr = map__rip_2objdump(map, sym->start); diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index a3207d900339..0cd41a862952 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -6,6 +6,9 @@ #include <bpf/libbpf.h> #include <linux/btf.h> #include <linux/err.h> +#include <linux/string.h> +#include <internal/lib.h> +#include <symbol/kallsyms.h> #include "bpf-event.h" #include "debug.h" #include "dso.h" @@ -290,11 +293,82 @@ out: return err ? -1 : 0; } +struct kallsyms_parse { + union perf_event *event; + perf_event__handler_t process; + struct machine *machine; + struct perf_tool *tool; +}; + +static int +process_bpf_image(char *name, u64 addr, struct kallsyms_parse *data) +{ + struct machine *machine = data->machine; + union perf_event *event = data->event; + struct perf_record_ksymbol *ksymbol; + int len; + + ksymbol = &event->ksymbol; + + *ksymbol = (struct perf_record_ksymbol) { + .header = { + .type = PERF_RECORD_KSYMBOL, + .size = offsetof(struct perf_record_ksymbol, name), + }, + .addr = addr, + .len = page_size, + .ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF, + .flags = 0, + }; + + len = scnprintf(ksymbol->name, KSYM_NAME_LEN, "%s", name); + ksymbol->header.size += PERF_ALIGN(len + 1, sizeof(u64)); + memset((void *) event + event->header.size, 0, machine->id_hdr_size); + event->header.size += machine->id_hdr_size; + + return perf_tool__process_synth_event(data->tool, event, machine, + data->process); +} + +static int +kallsyms_process_symbol(void *data, const char *_name, + char type __maybe_unused, u64 start) +{ + char disp[KSYM_NAME_LEN]; + char *module, *name; + unsigned long id; + int err = 0; + + module = strchr(_name, '\t'); + if (!module) + return 0; + + /* We are going after [bpf] module ... */ + if (strcmp(module + 1, "[bpf]")) + return 0; + + name = memdup(_name, (module - _name) + 1); + if (!name) + return -ENOMEM; + + name[module - _name] = 0; + + /* .. and only for trampolines and dispatchers */ + if ((sscanf(name, "bpf_trampoline_%lu", &id) == 1) || + (sscanf(name, "bpf_dispatcher_%s", disp) == 1)) + err = process_bpf_image(name, start, data); + + free(name); + return err; +} + int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, struct machine *machine, struct record_opts *opts) { + const char *kallsyms_filename = "/proc/kallsyms"; + struct kallsyms_parse arg; union perf_event *event; __u32 id = 0; int err; @@ -303,6 +377,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size); if (!event) return -1; + + /* Synthesize all the bpf programs in system. */ while (true) { err = bpf_prog_get_next_id(id, &id); if (err) { @@ -335,6 +411,23 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, break; } } + + /* Synthesize all the bpf images - trampolines/dispatchers. */ + if (symbol_conf.kallsyms_name != NULL) + kallsyms_filename = symbol_conf.kallsyms_name; + + arg = (struct kallsyms_parse) { + .event = event, + .process = process, + .machine = machine, + .tool = session->tool, + }; + + if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) { + pr_err("%s: failed to synthesize bpf images: %s\n", + __func__, strerror(errno)); + } + free(event); return err; } diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 91f21239608b..f338990e0fe6 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -191,6 +191,7 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__GUEST_KALLSYMS: case DSO_BINARY_TYPE__JAVA_JIT: case DSO_BINARY_TYPE__BPF_PROG_INFO: + case DSO_BINARY_TYPE__BPF_IMAGE: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; break; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 2db64b79617a..9553a1fd9e8a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -40,6 +40,7 @@ enum dso_binary_type { DSO_BINARY_TYPE__GUEST_KCORE, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__BPF_PROG_INFO, + DSO_BINARY_TYPE__BPF_IMAGE, DSO_BINARY_TYPE__NOT_FOUND, }; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 97142e9671be..09845eae9c03 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -736,6 +736,12 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } +static int is_bpf_image(const char *name) +{ + return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) || + strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1); +} + static int machine__process_ksymbol_register(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) @@ -759,6 +765,12 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; maps__insert(&machine->kmaps, map); + dso__set_loaded(dso); + + if (is_bpf_image(event->ksymbol.name)) { + dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE; + dso__set_long_name(dso, "", false); + } } sym = symbol__new(map->map_ip(map, map->start), diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 26bc6a0096ce..8f4300492dc7 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1544,6 +1544,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, return true; case DSO_BINARY_TYPE__BPF_PROG_INFO: + case DSO_BINARY_TYPE__BPF_IMAGE: case DSO_BINARY_TYPE__NOT_FOUND: default: return false; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index c30079c86998..1bb204cee853 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -30,8 +30,6 @@ test_tcpnotify_user test_libbpf test_tcp_check_syncookie_user test_sysctl -test_hashmap -test_btf_dump test_current_pid_tgid_new_ns xdping test_cpp @@ -39,4 +37,5 @@ test_cpp /no_alu32 /bpf_gcc /tools - +/runqslower +/bench diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7729892e0b04..e716e931d0c9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -20,9 +20,10 @@ CLANG ?= clang LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) -CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR) \ - -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \ - -I$(APIDIR) \ +SAN_CFLAGS ?= +CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS) \ + -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ + -I$(TOOLSINCDIR) -I$(APIDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program LDLIBS += -lcap -lelf -lz -lrt -lpthread @@ -32,7 +33,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test 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_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ + test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \ test_progs-no_alu32 \ test_current_pid_tgid_new_ns @@ -76,7 +77,7 @@ 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 runqslower + test_lirc_mode2_user xdping test_cpp runqslower bench TEST_CUSTOM_PROGS = urandom_read @@ -141,7 +142,8 @@ VMLINUX_BTF := $(abspath $(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=$(INCLUDE_DIR) + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + cp $(SCRATCH_DIR)/runqslower $@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ) @@ -241,7 +243,7 @@ define GCC_BPF_BUILD_RULE $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef -SKEL_BLACKLIST := btf__% test_pinning_invalid.c +SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. @@ -263,6 +265,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS) TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(filter-out $(SKEL_BLACKLIST), \ $$(TRUNNER_BPF_SRCS))) +TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) # Evaluate rules now with extra TRUNNER_XXX variables above already defined $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2)) @@ -323,7 +326,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) - cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) + cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ %.c \ @@ -352,6 +355,7 @@ endef TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ + network_helpers.c testing_helpers.c \ flow_dissector_load.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(wildcard progs/btf_dump_test_case_*.c) @@ -403,6 +407,21 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ +# Benchmark runner +$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h + $(call msg,CC,,$@) + $(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ +$(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h +$(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h +$(OUTPUT)/bench.o: bench.h testing_helpers.h +$(OUTPUT)/bench: LDLIBS += -lm +$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ + $(OUTPUT)/bench_count.o \ + $(OUTPUT)/bench_rename.o \ + $(OUTPUT)/bench_trigger.o + $(call msg,BINARY,,$@) + $(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) + EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature \ diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst new file mode 100644 index 000000000000..0f67f1b470b0 --- /dev/null +++ b/tools/testing/selftests/bpf/README.rst @@ -0,0 +1,43 @@ +================== +BPF Selftest Notes +================== + +Additional information about selftest failures are +documented here. + +bpf_iter test failures with clang/llvm 10.0.0 +============================================= + +With clang/llvm 10.0.0, the following two bpf_iter tests failed: + * ``bpf_iter/ipv6_route`` + * ``bpf_iter/netlink`` + +The symptom for ``bpf_iter/ipv6_route`` looks like + +.. code-block:: c + + 2: (79) r8 = *(u64 *)(r1 +8) + ... + 14: (bf) r2 = r8 + 15: (0f) r2 += r1 + ; BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); + 16: (7b) *(u64 *)(r8 +64) = r2 + only read is supported + +The symptom for ``bpf_iter/netlink`` looks like + +.. code-block:: c + + ; struct netlink_sock *nlk = ctx->sk; + 2: (79) r7 = *(u64 *)(r1 +8) + ... + 15: (bf) r2 = r7 + 16: (0f) r2 += r1 + ; BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol); + 17: (7b) *(u64 *)(r7 +0) = r2 + only read is supported + +This is due to a llvm BPF backend bug. The fix + https://reviews.llvm.org/D78466 +has been pushed to llvm 10.x release branch and will be +available in 10.0.1. The fix is available in llvm 11.0.0 trunk. diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c new file mode 100644 index 000000000000..14390689ef90 --- /dev/null +++ b/tools/testing/selftests/bpf/bench.c @@ -0,0 +1,449 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define _GNU_SOURCE +#include <argp.h> +#include <linux/compiler.h> +#include <sys/time.h> +#include <sched.h> +#include <fcntl.h> +#include <pthread.h> +#include <sys/sysinfo.h> +#include <sys/resource.h> +#include <signal.h> +#include "bench.h" +#include "testing_helpers.h" + +struct env env = { + .warmup_sec = 1, + .duration_sec = 5, + .affinity = false, + .consumer_cnt = 1, + .producer_cnt = 1, +}; + +static 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 setup_libbpf() +{ + int err; + + libbpf_set_print(libbpf_print_fn); + + err = bump_memlock_rlimit(); + if (err) + fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err); +} + +void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + double hits_per_sec, drops_per_sec; + double hits_per_prod; + + hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0); + hits_per_prod = hits_per_sec / env.producer_cnt; + drops_per_sec = res->drops / 1000000.0 / (delta_ns / 1000000000.0); + + printf("Iter %3d (%7.3lfus): ", + iter, (delta_ns - 1000000000) / 1000.0); + + printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n", + hits_per_sec, hits_per_prod, drops_per_sec); +} + +void hits_drops_report_final(struct bench_res res[], int res_cnt) +{ + int i; + double hits_mean = 0.0, drops_mean = 0.0; + double hits_stddev = 0.0, drops_stddev = 0.0; + + for (i = 0; i < res_cnt; i++) { + hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); + drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt); + } + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + hits_stddev += (hits_mean - res[i].hits / 1000000.0) * + (hits_mean - res[i].hits / 1000000.0) / + (res_cnt - 1.0); + drops_stddev += (drops_mean - res[i].drops / 1000000.0) * + (drops_mean - res[i].drops / 1000000.0) / + (res_cnt - 1.0); + } + hits_stddev = sqrt(hits_stddev); + drops_stddev = sqrt(drops_stddev); + } + printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ", + hits_mean, hits_stddev, hits_mean / env.producer_cnt); + printf("drops %8.3lf \u00B1 %5.3lfM/s\n", + drops_mean, drops_stddev); +} + +const char *argp_program_version = "benchmark"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = +"benchmark Generic benchmarking framework.\n" +"\n" +"This tool runs benchmarks.\n" +"\n" +"USAGE: benchmark <bench-name>\n" +"\n" +"EXAMPLES:\n" +" # run 'count-local' benchmark with 1 producer and 1 consumer\n" +" benchmark count-local\n" +" # run 'count-local' with 16 producer and 8 consumer thread, pinned to CPUs\n" +" benchmark -p16 -c8 -a count-local\n"; + +enum { + ARG_PROD_AFFINITY_SET = 1000, + ARG_CONS_AFFINITY_SET = 1001, +}; + +static const struct argp_option opts[] = { + { "list", 'l', NULL, 0, "List available benchmarks"}, + { "duration", 'd', "SEC", 0, "Duration of benchmark, seconds"}, + { "warmup", 'w', "SEC", 0, "Warm-up period, seconds"}, + { "producers", 'p', "NUM", 0, "Number of producer threads"}, + { "consumers", 'c', "NUM", 0, "Number of consumer threads"}, + { "verbose", 'v', NULL, 0, "Verbose debug output"}, + { "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"}, + { "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0, + "Set of CPUs for producer threads; implies --affinity"}, + { "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0, + "Set of CPUs for consumer threads; implies --affinity"}, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + static int pos_args; + + switch (key) { + case 'v': + env.verbose = true; + break; + case 'l': + env.list = true; + break; + case 'd': + env.duration_sec = strtol(arg, NULL, 10); + if (env.duration_sec <= 0) { + fprintf(stderr, "Invalid duration: %s\n", arg); + argp_usage(state); + } + break; + case 'w': + env.warmup_sec = strtol(arg, NULL, 10); + if (env.warmup_sec <= 0) { + fprintf(stderr, "Invalid warm-up duration: %s\n", arg); + argp_usage(state); + } + break; + case 'p': + env.producer_cnt = strtol(arg, NULL, 10); + if (env.producer_cnt <= 0) { + fprintf(stderr, "Invalid producer count: %s\n", arg); + argp_usage(state); + } + break; + case 'c': + env.consumer_cnt = strtol(arg, NULL, 10); + if (env.consumer_cnt <= 0) { + fprintf(stderr, "Invalid consumer count: %s\n", arg); + argp_usage(state); + } + break; + case 'a': + env.affinity = true; + break; + case ARG_PROD_AFFINITY_SET: + env.affinity = true; + if (parse_num_list(arg, &env.prod_cpus.cpus, + &env.prod_cpus.cpus_len)) { + fprintf(stderr, "Invalid format of CPU set for producers."); + argp_usage(state); + } + break; + case ARG_CONS_AFFINITY_SET: + env.affinity = true; + if (parse_num_list(arg, &env.cons_cpus.cpus, + &env.cons_cpus.cpus_len)) { + fprintf(stderr, "Invalid format of CPU set for consumers."); + argp_usage(state); + } + break; + case ARGP_KEY_ARG: + if (pos_args++) { + fprintf(stderr, + "Unrecognized positional argument: %s\n", arg); + argp_usage(state); + } + env.bench_name = strdup(arg); + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +static void parse_cmdline_args(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + if (argp_parse(&argp, argc, argv, 0, NULL, NULL)) + exit(1); + if (!env.list && !env.bench_name) { + argp_help(&argp, stderr, ARGP_HELP_DOC, "bench"); + exit(1); + } +} + +static void collect_measurements(long delta_ns); + +static __u64 last_time_ns; +static void sigalarm_handler(int signo) +{ + long new_time_ns = get_time_ns(); + long delta_ns = new_time_ns - last_time_ns; + + collect_measurements(delta_ns); + + last_time_ns = new_time_ns; +} + +/* set up periodic 1-second timer */ +static void setup_timer() +{ + static struct sigaction sigalarm_action = { + .sa_handler = sigalarm_handler, + }; + struct itimerval timer_settings = {}; + int err; + + last_time_ns = get_time_ns(); + err = sigaction(SIGALRM, &sigalarm_action, NULL); + if (err < 0) { + fprintf(stderr, "failed to install SIGALRM handler: %d\n", -errno); + exit(1); + } + timer_settings.it_interval.tv_sec = 1; + timer_settings.it_value.tv_sec = 1; + err = setitimer(ITIMER_REAL, &timer_settings, NULL); + if (err < 0) { + fprintf(stderr, "failed to arm interval timer: %d\n", -errno); + exit(1); + } +} + +static void set_thread_affinity(pthread_t thread, int cpu) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) { + fprintf(stderr, "setting affinity to CPU #%d failed: %d\n", + cpu, errno); + exit(1); + } +} + +static int next_cpu(struct cpu_set *cpu_set) +{ + if (cpu_set->cpus) { + int i; + + /* find next available CPU */ + for (i = cpu_set->next_cpu; i < cpu_set->cpus_len; i++) { + if (cpu_set->cpus[i]) { + cpu_set->next_cpu = i + 1; + return i; + } + } + fprintf(stderr, "Not enough CPUs specified, need CPU #%d or higher.\n", i); + exit(1); + } + + return cpu_set->next_cpu++; +} + +static struct bench_state { + int res_cnt; + struct bench_res *results; + pthread_t *consumers; + pthread_t *producers; +} state; + +const struct bench *bench = NULL; + +extern const struct bench bench_count_global; +extern const struct bench bench_count_local; +extern const struct bench bench_rename_base; +extern const struct bench bench_rename_kprobe; +extern const struct bench bench_rename_kretprobe; +extern const struct bench bench_rename_rawtp; +extern const struct bench bench_rename_fentry; +extern const struct bench bench_rename_fexit; +extern const struct bench bench_rename_fmodret; +extern const struct bench bench_trig_base; +extern const struct bench bench_trig_tp; +extern const struct bench bench_trig_rawtp; +extern const struct bench bench_trig_kprobe; +extern const struct bench bench_trig_fentry; +extern const struct bench bench_trig_fmodret; + +static const struct bench *benchs[] = { + &bench_count_global, + &bench_count_local, + &bench_rename_base, + &bench_rename_kprobe, + &bench_rename_kretprobe, + &bench_rename_rawtp, + &bench_rename_fentry, + &bench_rename_fexit, + &bench_rename_fmodret, + &bench_trig_base, + &bench_trig_tp, + &bench_trig_rawtp, + &bench_trig_kprobe, + &bench_trig_fentry, + &bench_trig_fmodret, +}; + +static void setup_benchmark() +{ + int i, err; + + if (!env.bench_name) { + fprintf(stderr, "benchmark name is not specified\n"); + exit(1); + } + + for (i = 0; i < ARRAY_SIZE(benchs); i++) { + if (strcmp(benchs[i]->name, env.bench_name) == 0) { + bench = benchs[i]; + break; + } + } + if (!bench) { + fprintf(stderr, "benchmark '%s' not found\n", env.bench_name); + exit(1); + } + + printf("Setting up benchmark '%s'...\n", bench->name); + + state.producers = calloc(env.producer_cnt, sizeof(*state.producers)); + state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers)); + state.results = calloc(env.duration_sec + env.warmup_sec + 2, + sizeof(*state.results)); + if (!state.producers || !state.consumers || !state.results) + exit(1); + + if (bench->validate) + bench->validate(); + if (bench->setup) + bench->setup(); + + for (i = 0; i < env.consumer_cnt; i++) { + err = pthread_create(&state.consumers[i], NULL, + bench->consumer_thread, (void *)(long)i); + if (err) { + fprintf(stderr, "failed to create consumer thread #%d: %d\n", + i, -errno); + exit(1); + } + if (env.affinity) + set_thread_affinity(state.consumers[i], + next_cpu(&env.cons_cpus)); + } + + /* unless explicit producer CPU list is specified, continue after + * last consumer CPU + */ + if (!env.prod_cpus.cpus) + env.prod_cpus.next_cpu = env.cons_cpus.next_cpu; + + for (i = 0; i < env.producer_cnt; i++) { + err = pthread_create(&state.producers[i], NULL, + bench->producer_thread, (void *)(long)i); + if (err) { + fprintf(stderr, "failed to create producer thread #%d: %d\n", + i, -errno); + exit(1); + } + if (env.affinity) + set_thread_affinity(state.producers[i], + next_cpu(&env.prod_cpus)); + } + + printf("Benchmark '%s' started.\n", bench->name); +} + +static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t bench_done = PTHREAD_COND_INITIALIZER; + +static void collect_measurements(long delta_ns) { + int iter = state.res_cnt++; + struct bench_res *res = &state.results[iter]; + + bench->measure(res); + + if (bench->report_progress) + bench->report_progress(iter, res, delta_ns); + + if (iter == env.duration_sec + env.warmup_sec) { + pthread_mutex_lock(&bench_done_mtx); + pthread_cond_signal(&bench_done); + pthread_mutex_unlock(&bench_done_mtx); + } +} + +int main(int argc, char **argv) +{ + parse_cmdline_args(argc, argv); + + if (env.list) { + int i; + + printf("Available benchmarks:\n"); + for (i = 0; i < ARRAY_SIZE(benchs); i++) { + printf("- %s\n", benchs[i]->name); + } + return 0; + } + + setup_benchmark(); + + setup_timer(); + + pthread_mutex_lock(&bench_done_mtx); + pthread_cond_wait(&bench_done, &bench_done_mtx); + pthread_mutex_unlock(&bench_done_mtx); + + if (bench->report_final) + /* skip first sample */ + bench->report_final(state.results + env.warmup_sec, + state.res_cnt - env.warmup_sec); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h new file mode 100644 index 000000000000..c1f48a473b02 --- /dev/null +++ b/tools/testing/selftests/bpf/bench.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#pragma once +#include <stdlib.h> +#include <stdbool.h> +#include <linux/err.h> +#include <errno.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <math.h> +#include <time.h> +#include <sys/syscall.h> + +struct cpu_set { + bool *cpus; + int cpus_len; + int next_cpu; +}; + +struct env { + char *bench_name; + int duration_sec; + int warmup_sec; + bool verbose; + bool list; + bool affinity; + int consumer_cnt; + int producer_cnt; + struct cpu_set prod_cpus; + struct cpu_set cons_cpus; +}; + +struct bench_res { + long hits; + long drops; +}; + +struct bench { + const char *name; + void (*validate)(); + void (*setup)(); + void *(*producer_thread)(void *ctx); + void *(*consumer_thread)(void *ctx); + void (*measure)(struct bench_res* res); + void (*report_progress)(int iter, struct bench_res* res, long delta_ns); + void (*report_final)(struct bench_res res[], int res_cnt); +}; + +struct counter { + long value; +} __attribute__((aligned(128))); + +extern struct env env; +extern const struct bench *bench; + +void setup_libbpf(); +void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns); +void hits_drops_report_final(struct bench_res res[], int res_cnt); + +static inline __u64 get_time_ns() { + struct timespec t; + + clock_gettime(CLOCK_MONOTONIC, &t); + + return (u64)t.tv_sec * 1000000000 + t.tv_nsec; +} + +static inline void atomic_inc(long *value) +{ + (void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED); +} + +static inline void atomic_add(long *value, long n) +{ + (void)__atomic_add_fetch(value, n, __ATOMIC_RELAXED); +} + +static inline long atomic_swap(long *value, long n) +{ + return __atomic_exchange_n(value, n, __ATOMIC_RELAXED); +} diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c new file mode 100644 index 000000000000..befba7a82643 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_count.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bench.h" + +/* COUNT-GLOBAL benchmark */ + +static struct count_global_ctx { + struct counter hits; +} count_global_ctx; + +static void *count_global_producer(void *input) +{ + struct count_global_ctx *ctx = &count_global_ctx; + + while (true) { + atomic_inc(&ctx->hits.value); + } + return NULL; +} + +static void *count_global_consumer(void *input) +{ + return NULL; +} + +static void count_global_measure(struct bench_res *res) +{ + struct count_global_ctx *ctx = &count_global_ctx; + + res->hits = atomic_swap(&ctx->hits.value, 0); +} + +/* COUNT-local benchmark */ + +static struct count_local_ctx { + struct counter *hits; +} count_local_ctx; + +static void count_local_setup() +{ + struct count_local_ctx *ctx = &count_local_ctx; + + ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits)); + if (!ctx->hits) + exit(1); +} + +static void *count_local_producer(void *input) +{ + struct count_local_ctx *ctx = &count_local_ctx; + int idx = (long)input; + + while (true) { + atomic_inc(&ctx->hits[idx].value); + } + return NULL; +} + +static void *count_local_consumer(void *input) +{ + return NULL; +} + +static void count_local_measure(struct bench_res *res) +{ + struct count_local_ctx *ctx = &count_local_ctx; + int i; + + for (i = 0; i < env.producer_cnt; i++) { + res->hits += atomic_swap(&ctx->hits[i].value, 0); + } +} + +const struct bench bench_count_global = { + .name = "count-global", + .producer_thread = count_global_producer, + .consumer_thread = count_global_consumer, + .measure = count_global_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_count_local = { + .name = "count-local", + .setup = count_local_setup, + .producer_thread = count_local_producer, + .consumer_thread = count_local_consumer, + .measure = count_local_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c new file mode 100644 index 000000000000..e74cff40f4fe --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <fcntl.h> +#include "bench.h" +#include "test_overhead.skel.h" + +/* BPF triggering benchmarks */ +static struct ctx { + struct test_overhead *skel; + struct counter hits; + int fd; +} ctx; + +static void validate() +{ + if (env.producer_cnt != 1) { + fprintf(stderr, "benchmark doesn't support multi-producer!\n"); + exit(1); + } + if (env.consumer_cnt != 1) { + fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + exit(1); + } +} + +static void *producer(void *input) +{ + char buf[] = "test_overhead"; + int err; + + while (true) { + err = write(ctx.fd, buf, sizeof(buf)); + if (err < 0) { + fprintf(stderr, "write failed\n"); + exit(1); + } + atomic_inc(&ctx.hits.value); + } +} + +static void measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.hits.value, 0); +} + +static void setup_ctx() +{ + setup_libbpf(); + + ctx.skel = test_overhead__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + ctx.fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); + if (ctx.fd < 0) { + fprintf(stderr, "failed to open /proc/self/comm: %d\n", -errno); + exit(1); + } +} + +static void attach_bpf(struct bpf_program *prog) +{ + struct bpf_link *link; + + link = bpf_program__attach(prog); + if (IS_ERR(link)) { + fprintf(stderr, "failed to attach program!\n"); + exit(1); + } +} + +static void setup_base() +{ + setup_ctx(); +} + +static void setup_kprobe() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog1); +} + +static void setup_kretprobe() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog2); +} + +static void setup_rawtp() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog3); +} + +static void setup_fentry() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog4); +} + +static void setup_fexit() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog5); +} + +static void setup_fmodret() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.prog6); +} + +static void *consumer(void *input) +{ + return NULL; +} + +const struct bench bench_rename_base = { + .name = "rename-base", + .validate = validate, + .setup = setup_base, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_kprobe = { + .name = "rename-kprobe", + .validate = validate, + .setup = setup_kprobe, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_kretprobe = { + .name = "rename-kretprobe", + .validate = validate, + .setup = setup_kretprobe, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_rawtp = { + .name = "rename-rawtp", + .validate = validate, + .setup = setup_rawtp, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_fentry = { + .name = "rename-fentry", + .validate = validate, + .setup = setup_fentry, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_fexit = { + .name = "rename-fexit", + .validate = validate, + .setup = setup_fexit, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rename_fmodret = { + .name = "rename-fmodret", + .validate = validate, + .setup = setup_fmodret, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c new file mode 100644 index 000000000000..49c22832f216 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bench.h" +#include "trigger_bench.skel.h" + +/* BPF triggering benchmarks */ +static struct trigger_ctx { + struct trigger_bench *skel; +} ctx; + +static struct counter base_hits; + +static void trigger_validate() +{ + if (env.consumer_cnt != 1) { + fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + exit(1); + } +} + +static void *trigger_base_producer(void *input) +{ + while (true) { + (void)syscall(__NR_getpgid); + atomic_inc(&base_hits.value); + } + return NULL; +} + +static void trigger_base_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&base_hits.value, 0); +} + +static void *trigger_producer(void *input) +{ + while (true) + (void)syscall(__NR_getpgid); + return NULL; +} + +static void trigger_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.skel->bss->hits, 0); +} + +static void setup_ctx() +{ + setup_libbpf(); + + ctx.skel = trigger_bench__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } +} + +static void attach_bpf(struct bpf_program *prog) +{ + struct bpf_link *link; + + link = bpf_program__attach(prog); + if (IS_ERR(link)) { + fprintf(stderr, "failed to attach program!\n"); + exit(1); + } +} + +static void trigger_tp_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_tp); +} + +static void trigger_rawtp_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_raw_tp); +} + +static void trigger_kprobe_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_kprobe); +} + +static void trigger_fentry_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_fentry); +} + +static void trigger_fmodret_setup() +{ + setup_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_fmodret); +} + +static void *trigger_consumer(void *input) +{ + return NULL; +} + +const struct bench bench_trig_base = { + .name = "trig-base", + .validate = trigger_validate, + .producer_thread = trigger_base_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_base_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_tp = { + .name = "trig-tp", + .validate = trigger_validate, + .setup = trigger_tp_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_rawtp = { + .name = "trig-rawtp", + .validate = trigger_validate, + .setup = trigger_rawtp_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_kprobe = { + .name = "trig-kprobe", + .validate = trigger_validate, + .setup = trigger_kprobe_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_fentry = { + .name = "trig-fentry", + .validate = trigger_validate, + .setup = trigger_fentry_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_fmodret = { + .name = "trig-fmodret", + .validate = trigger_validate, + .setup = trigger_fmodret_setup, + .producer_thread = trigger_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh new file mode 100755 index 000000000000..16f774b1cdbe --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh @@ -0,0 +1,9 @@ +#!/bin/bash + +set -eufo pipefail + +for i in base kprobe kretprobe rawtp fentry fexit fmodret +do + summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-) + printf "%-10s: %s\n" $i "$summary" +done diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh new file mode 100755 index 000000000000..78e83f243294 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh @@ -0,0 +1,9 @@ +#!/bin/bash + +set -eufo pipefail + +for i in base tp rawtp kprobe fentry fmodret +do + summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-) + printf "%-10s: %s\n" $i "$summary" +done diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c new file mode 100644 index 000000000000..999a775484c1 --- /dev/null +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <sys/epoll.h> + +#include <linux/err.h> +#include <linux/in.h> +#include <linux/in6.h> + +#include "bpf_util.h" +#include "network_helpers.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) + +struct ipv4_packet pkt_v4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +struct ipv6_packet pkt_v6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +int start_server(int family, int type) +{ + struct sockaddr_storage addr = {}; + socklen_t len; + int fd; + + if (family == AF_INET) { + struct sockaddr_in *sin = (void *)&addr; + + sin->sin_family = AF_INET; + len = sizeof(*sin); + } else { + struct sockaddr_in6 *sin6 = (void *)&addr; + + sin6->sin6_family = AF_INET6; + len = sizeof(*sin6); + } + + fd = socket(family, type | SOCK_NONBLOCK, 0); + if (fd < 0) { + log_err("Failed to create server socket"); + return -1; + } + + if (bind(fd, (const struct sockaddr *)&addr, len) < 0) { + log_err("Failed to bind socket"); + close(fd); + return -1; + } + + if (type == SOCK_STREAM) { + if (listen(fd, 1) < 0) { + log_err("Failed to listed on socket"); + close(fd); + return -1; + } + } + + return fd; +} + +static const struct timeval timeo_sec = { .tv_sec = 3 }; +static const size_t timeo_optlen = sizeof(timeo_sec); + +int connect_to_fd(int family, int type, int server_fd) +{ + int fd, save_errno; + + fd = socket(family, type, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) { + save_errno = errno; + close(fd); + errno = save_errno; + return -1; + } + + return fd; +} + +int connect_fd_to_fd(int client_fd, int server_fd) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int save_errno; + + if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, + timeo_optlen)) { + log_err("Failed to set SO_RCVTIMEO"); + return -1; + } + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return -1; + } + + if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) { + if (errno != EINPROGRESS) { + save_errno = errno; + log_err("Failed to connect to server"); + errno = save_errno; + } + return -1; + } + + return 0; +} + +int connect_wait(int fd) +{ + struct epoll_event ev = {}, events[2]; + int timeout_ms = 1000; + int efd, nfd; + + efd = epoll_create1(EPOLL_CLOEXEC); + if (efd < 0) { + log_err("Failed to open epoll fd"); + return -1; + } + + ev.events = EPOLLRDHUP | EPOLLOUT; + ev.data.fd = fd; + + if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) { + log_err("Failed to register fd=%d on epoll fd=%d", fd, efd); + close(efd); + return -1; + } + + nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms); + if (nfd < 0) + log_err("Failed to wait for I/O event on epoll fd=%d", efd); + + close(efd); + return nfd; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h new file mode 100644 index 000000000000..86914e6e7b53 --- /dev/null +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NETWORK_HELPERS_H +#define __NETWORK_HELPERS_H +#include <sys/socket.h> +#include <sys/types.h> +#include <linux/types.h> +typedef __u16 __sum16; +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <netinet/tcp.h> +#include <bpf/bpf_endian.h> + +#define MAGIC_VAL 0x1234 +#define NUM_ITER 100000 +#define VIP_NUM 5 +#define MAGIC_BYTES 123 + +/* ipv4 test vector */ +struct ipv4_packet { + struct ethhdr eth; + struct iphdr iph; + struct tcphdr tcp; +} __packed; +extern struct ipv4_packet pkt_v4; + +/* ipv6 test vector */ +struct ipv6_packet { + struct ethhdr eth; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed; +extern struct ipv6_packet pkt_v6; + +int start_server(int family, int type); +int connect_to_fd(int family, int type, int server_fd); +int connect_fd_to_fd(int client_fd, int server_fd); +int connect_wait(int client_fd); + +#endif diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c new file mode 100644 index 000000000000..87c29dde1cf9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <test_progs.h> +#include "bpf_iter_ipv6_route.skel.h" +#include "bpf_iter_netlink.skel.h" +#include "bpf_iter_bpf_map.skel.h" +#include "bpf_iter_task.skel.h" +#include "bpf_iter_task_file.skel.h" +#include "bpf_iter_test_kern1.skel.h" +#include "bpf_iter_test_kern2.skel.h" +#include "bpf_iter_test_kern3.skel.h" +#include "bpf_iter_test_kern4.skel.h" + +static int duration; + +static void test_btf_id_or_null(void) +{ + struct bpf_iter_test_kern3 *skel; + + skel = bpf_iter_test_kern3__open_and_load(); + if (CHECK(skel, "bpf_iter_test_kern3__open_and_load", + "skeleton open_and_load unexpectedly succeeded\n")) { + bpf_iter_test_kern3__destroy(skel); + return; + } +} + +static void do_dummy_read(struct bpf_program *prog) +{ + struct bpf_link *link; + char buf[16] = {}; + int iter_fd, len; + + link = bpf_program__attach_iter(prog, NULL); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* not check contents, but ensure read() ends without error */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +} + +static void test_ipv6_route(void) +{ + struct bpf_iter_ipv6_route *skel; + + skel = bpf_iter_ipv6_route__open_and_load(); + if (CHECK(!skel, "bpf_iter_ipv6_route__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_ipv6_route); + + bpf_iter_ipv6_route__destroy(skel); +} + +static void test_netlink(void) +{ + struct bpf_iter_netlink *skel; + + skel = bpf_iter_netlink__open_and_load(); + if (CHECK(!skel, "bpf_iter_netlink__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_netlink); + + bpf_iter_netlink__destroy(skel); +} + +static void test_bpf_map(void) +{ + struct bpf_iter_bpf_map *skel; + + skel = bpf_iter_bpf_map__open_and_load(); + if (CHECK(!skel, "bpf_iter_bpf_map__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_bpf_map); + + bpf_iter_bpf_map__destroy(skel); +} + +static void test_task(void) +{ + struct bpf_iter_task *skel; + + skel = bpf_iter_task__open_and_load(); + if (CHECK(!skel, "bpf_iter_task__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_task); + + bpf_iter_task__destroy(skel); +} + +static void test_task_file(void) +{ + struct bpf_iter_task_file *skel; + + skel = bpf_iter_task_file__open_and_load(); + if (CHECK(!skel, "bpf_iter_task_file__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_task_file); + + bpf_iter_task_file__destroy(skel); +} + +/* The expected string is less than 16 bytes */ +static int do_read_with_fd(int iter_fd, const char *expected, + bool read_one_char) +{ + int err = -1, len, read_buf_len, start; + char buf[16] = {}; + + read_buf_len = read_one_char ? 1 : 16; + start = 0; + while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) { + start += len; + if (CHECK(start >= 16, "read", "read len %d\n", len)) + return -1; + read_buf_len = read_one_char ? 1 : 16 - start; + } + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + return -1; + + err = strcmp(buf, expected); + if (CHECK(err, "read", "incorrect read result: buf %s, expected %s\n", + buf, expected)) + return -1; + + return 0; +} + +static void test_anon_iter(bool read_one_char) +{ + struct bpf_iter_test_kern1 *skel; + struct bpf_link *link; + int iter_fd, err; + + skel = bpf_iter_test_kern1__open_and_load(); + if (CHECK(!skel, "bpf_iter_test_kern1__open_and_load", + "skeleton open_and_load failed\n")) + return; + + err = bpf_iter_test_kern1__attach(skel); + if (CHECK(err, "bpf_iter_test_kern1__attach", + "skeleton attach failed\n")) { + goto out; + } + + link = skel->links.dump_task; + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto out; + + do_read_with_fd(iter_fd, "abcd", read_one_char); + close(iter_fd); + +out: + bpf_iter_test_kern1__destroy(skel); +} + +static int do_read(const char *path, const char *expected) +{ + int err, iter_fd; + + iter_fd = open(path, O_RDONLY); + if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n", + path, strerror(errno))) + return -1; + + err = do_read_with_fd(iter_fd, expected, false); + close(iter_fd); + return err; +} + +static void test_file_iter(void) +{ + const char *path = "/sys/fs/bpf/bpf_iter_test1"; + struct bpf_iter_test_kern1 *skel1; + struct bpf_iter_test_kern2 *skel2; + struct bpf_link *link; + int err; + + skel1 = bpf_iter_test_kern1__open_and_load(); + if (CHECK(!skel1, "bpf_iter_test_kern1__open_and_load", + "skeleton open_and_load failed\n")) + return; + + link = bpf_program__attach_iter(skel1->progs.dump_task, NULL); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + /* unlink this path if it exists. */ + unlink(path); + + err = bpf_link__pin(link, path); + if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err)) + goto free_link; + + err = do_read(path, "abcd"); + if (err) + goto unlink_path; + + /* file based iterator seems working fine. Let us a link update + * of the underlying link and `cat` the iterator again, its content + * should change. + */ + skel2 = bpf_iter_test_kern2__open_and_load(); + if (CHECK(!skel2, "bpf_iter_test_kern2__open_and_load", + "skeleton open_and_load failed\n")) + goto unlink_path; + + err = bpf_link__update_program(link, skel2->progs.dump_task); + if (CHECK(err, "update_prog", "update_prog failed\n")) + goto destroy_skel2; + + do_read(path, "ABCD"); + +destroy_skel2: + bpf_iter_test_kern2__destroy(skel2); +unlink_path: + unlink(path); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_test_kern1__destroy(skel1); +} + +static void test_overflow(bool test_e2big_overflow, bool ret1) +{ + __u32 map_info_len, total_read_len, expected_read_len; + int err, iter_fd, map1_fd, map2_fd, len; + struct bpf_map_info map_info = {}; + struct bpf_iter_test_kern4 *skel; + struct bpf_link *link; + __u32 page_size; + char *buf; + + skel = bpf_iter_test_kern4__open(); + if (CHECK(!skel, "bpf_iter_test_kern4__open", + "skeleton open failed\n")) + return; + + /* create two maps: bpf program will only do bpf_seq_write + * for these two maps. The goal is one map output almost + * fills seq_file buffer and then the other will trigger + * overflow and needs restart. + */ + map1_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (CHECK(map1_fd < 0, "bpf_create_map", + "map_creation failed: %s\n", strerror(errno))) + goto out; + map2_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (CHECK(map2_fd < 0, "bpf_create_map", + "map_creation failed: %s\n", strerror(errno))) + goto free_map1; + + /* bpf_seq_printf kernel buffer is one page, so one map + * bpf_seq_write will mostly fill it, and the other map + * will partially fill and then trigger overflow and need + * bpf_seq_read restart. + */ + page_size = sysconf(_SC_PAGE_SIZE); + + if (test_e2big_overflow) { + skel->rodata->print_len = (page_size + 8) / 8; + expected_read_len = 2 * (page_size + 8); + } else if (!ret1) { + skel->rodata->print_len = (page_size - 8) / 8; + expected_read_len = 2 * (page_size - 8); + } else { + skel->rodata->print_len = 1; + expected_read_len = 2 * 8; + } + skel->rodata->ret1 = ret1; + + if (CHECK(bpf_iter_test_kern4__load(skel), + "bpf_iter_test_kern4__load", "skeleton load failed\n")) + goto free_map2; + + /* setup filtering map_id in bpf program */ + map_info_len = sizeof(map_info); + err = bpf_obj_get_info_by_fd(map1_fd, &map_info, &map_info_len); + if (CHECK(err, "get_map_info", "get map info failed: %s\n", + strerror(errno))) + goto free_map2; + skel->bss->map1_id = map_info.id; + + err = bpf_obj_get_info_by_fd(map2_fd, &map_info, &map_info_len); + if (CHECK(err, "get_map_info", "get map info failed: %s\n", + strerror(errno))) + goto free_map2; + skel->bss->map2_id = map_info.id; + + link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto free_map2; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + buf = malloc(expected_read_len); + if (!buf) + goto close_iter; + + /* do read */ + total_read_len = 0; + if (test_e2big_overflow) { + while ((len = read(iter_fd, buf, expected_read_len)) > 0) + total_read_len += len; + + CHECK(len != -1 || errno != E2BIG, "read", + "expected ret -1, errno E2BIG, but get ret %d, error %s\n", + len, strerror(errno)); + goto free_buf; + } else if (!ret1) { + while ((len = read(iter_fd, buf, expected_read_len)) > 0) + total_read_len += len; + + if (CHECK(len < 0, "read", "read failed: %s\n", + strerror(errno))) + goto free_buf; + } else { + do { + len = read(iter_fd, buf, expected_read_len); + if (len > 0) + total_read_len += len; + } while (len > 0 || len == -EAGAIN); + + if (CHECK(len < 0, "read", "read failed: %s\n", + strerror(errno))) + goto free_buf; + } + + if (CHECK(total_read_len != expected_read_len, "read", + "total len %u, expected len %u\n", total_read_len, + expected_read_len)) + goto free_buf; + + if (CHECK(skel->bss->map1_accessed != 1, "map1_accessed", + "expected 1 actual %d\n", skel->bss->map1_accessed)) + goto free_buf; + + if (CHECK(skel->bss->map2_accessed != 2, "map2_accessed", + "expected 2 actual %d\n", skel->bss->map2_accessed)) + goto free_buf; + + CHECK(skel->bss->map2_seqnum1 != skel->bss->map2_seqnum2, + "map2_seqnum", "two different seqnum %lld %lld\n", + skel->bss->map2_seqnum1, skel->bss->map2_seqnum2); + +free_buf: + free(buf); +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +free_map2: + close(map2_fd); +free_map1: + close(map1_fd); +out: + bpf_iter_test_kern4__destroy(skel); +} + +void test_bpf_iter(void) +{ + if (test__start_subtest("btf_id_or_null")) + test_btf_id_or_null(); + if (test__start_subtest("ipv6_route")) + test_ipv6_route(); + if (test__start_subtest("netlink")) + test_netlink(); + if (test__start_subtest("bpf_map")) + test_bpf_map(); + if (test__start_subtest("task")) + test_task(); + if (test__start_subtest("task_file")) + test_task_file(); + if (test__start_subtest("anon")) + test_anon_iter(false); + if (test__start_subtest("anon-read-one-char")) + test_anon_iter(true); + if (test__start_subtest("file")) + test_file_iter(); + if (test__start_subtest("overflow")) + test_overflow(false, false); + if (test__start_subtest("overflow-e2big")) + test_overflow(true, false); + if (test__start_subtest("prog-ret-1")) + test_overflow(false, true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index f10029821e16..7afa4160416f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -1,26 +1,30 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#define nr_iters 2 + void test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; - const int nr_iters = 2; const char *file = "./test_obj_id.o"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; - struct bpf_object *objs[nr_iters]; + struct bpf_object *objs[nr_iters] = {}; + struct bpf_link *links[nr_iters] = {}; + struct bpf_program *prog; int prog_fds[nr_iters], map_fds[nr_iters]; /* +1 to test for the info_len returned by kernel */ struct bpf_prog_info prog_infos[nr_iters + 1]; struct bpf_map_info map_infos[nr_iters + 1]; + struct bpf_link_info link_infos[nr_iters + 1]; /* Each prog only uses one map. +1 to test nr_map_ids * returned by kernel. */ __u32 map_ids[nr_iters + 1]; - char jited_insns[128], xlated_insns[128], zeros[128]; + char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; int err = 0; @@ -36,14 +40,15 @@ void test_bpf_obj_id(void) CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno); - for (i = 0; i < nr_iters; i++) - objs[i] = NULL; + err = bpf_link_get_fd_by_id(0); + CHECK(err >= 0 || errno != ENOENT, + "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno); /* Check bpf_obj_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { now = time(NULL); - err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail * to load. @@ -60,6 +65,17 @@ void test_bpf_obj_id(void) if (CHECK_FAIL(err)) goto done; + prog = bpf_object__find_program_by_title(objs[i], + "raw_tp/sys_enter"); + if (CHECK_FAIL(!prog)) + goto done; + links[i] = bpf_program__attach(prog); + err = libbpf_get_error(links[i]); + if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) { + links[i] = NULL; + goto done; + } + /* Check getting map info */ info_len = sizeof(struct bpf_map_info) * 2; bzero(&map_infos[i], info_len); @@ -107,7 +123,7 @@ void test_bpf_obj_id(void) load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + (prog_infos[i].load_time / nsec_per_sec); if (CHECK(err || - prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || + prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT || info_len != sizeof(struct bpf_prog_info) || (env.jit_enabled && !prog_infos[i].jited_prog_len) || (env.jit_enabled && @@ -120,7 +136,11 @@ void test_bpf_obj_id(void) *(int *)(long)prog_infos[i].map_ids != map_infos[i].id || strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", + "err %d errno %d i %d type %d(%d) info_len %u(%zu) " + "jit_enabled %d jited_prog_len %u xlated_prog_len %u " + "jited_prog %d xlated_prog %d load_time %lu(%lu) " + "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) " + "name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -135,6 +155,33 @@ void test_bpf_obj_id(void) *(int *)(long)prog_infos[i].map_ids, map_infos[i].id, prog_infos[i].name, expected_prog_name)) goto done; + + /* Check getting link info */ + info_len = sizeof(struct bpf_link_info) * 2; + bzero(&link_infos[i], info_len); + link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name; + link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); + err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), + &link_infos[i], &info_len); + if (CHECK(err || + link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || + link_infos[i].prog_id != prog_infos[i].id || + link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name || + strcmp((char *)link_infos[i].raw_tracepoint.tp_name, + "sys_enter") || + info_len != sizeof(struct bpf_link_info), + "get-link-info(fd)", + "err %d errno %d info_len %u(%zu) type %d(%d) id %d " + "prog_id %d (%d) tp_name %s(%s)\n", + err, errno, + info_len, sizeof(struct bpf_link_info), + link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, + link_infos[i].id, + link_infos[i].prog_id, prog_infos[i].id, + (char *)link_infos[i].raw_tracepoint.tp_name, + "sys_enter")) + goto done; + } /* Check bpf_prog_get_next_id() */ @@ -247,7 +294,52 @@ void test_bpf_obj_id(void) "nr_id_found %u(%u)\n", nr_id_found, nr_iters); + /* Check bpf_link_get_next_id() */ + nr_id_found = 0; + next_id = 0; + while (!bpf_link_get_next_id(next_id, &next_id)) { + struct bpf_link_info link_info; + int link_fd, cmp_res; + + info_len = sizeof(link_info); + memset(&link_info, 0, info_len); + + link_fd = bpf_link_get_fd_by_id(next_id); + if (link_fd < 0 && errno == ENOENT) + /* The bpf_link is in the dead row */ + continue; + if (CHECK(link_fd < 0, "get-link-fd(next_id)", + "link_fd %d next_id %u errno %d\n", + link_fd, next_id, errno)) + break; + + for (i = 0; i < nr_iters; i++) + if (link_infos[i].id == next_id) + break; + + if (i == nr_iters) + continue; + + nr_id_found++; + + err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len); + cmp_res = memcmp(&link_info, &link_infos[i], + offsetof(struct bpf_link_info, raw_tracepoint)); + CHECK(err || info_len != sizeof(link_info) || cmp_res, + "check get-link-info(next_id->fd)", + "err %d errno %d info_len %u(%zu) memcmp %d\n", + err, errno, info_len, sizeof(struct bpf_link_info), + cmp_res); + + close(link_fd); + } + CHECK(nr_id_found != nr_iters, + "check total link id found by get_next_id", + "nr_id_found %u(%u)\n", nr_id_found, nr_iters); + done: - for (i = 0; i < nr_iters; i++) + for (i = 0; i < nr_iters; i++) { + bpf_link__destroy(links[i]); bpf_object__close(objs[i]); + } } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c new file mode 100644 index 000000000000..f7ee8fa377ad --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> + +#include "test_btf_map_in_map.skel.h" + +void test_btf_map_in_map(void) +{ + int duration = 0, err, key = 0, val; + struct test_btf_map_in_map* skel; + + skel = test_btf_map_in_map__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) + return; + + err = test_btf_map_in_map__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* inner1 = input, inner2 = input + 1 */ + val = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); + val = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + skel->bss->input = 1; + usleep(1); + + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); + + /* inner1 = input + 1, inner2 = input */ + val = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); + val = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + skel->bss->input = 3; + usleep(1); + + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + +cleanup: + test_btf_map_in_map__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c new file mode 100644 index 000000000000..059047af7df3 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <test_progs.h> + +#include "network_helpers.h" +#include "cgroup_skb_sk_lookup_kern.skel.h" + +static void run_lookup_test(__u16 *g_serv_port, int out_sk) +{ + int serv_sk = -1, in_sk = -1, serv_in_sk = -1, err; + struct sockaddr_in6 addr = {}; + socklen_t addr_len = sizeof(addr); + __u32 duration = 0; + + serv_sk = start_server(AF_INET6, SOCK_STREAM); + if (CHECK(serv_sk < 0, "start_server", "failed to start server\n")) + return; + + err = getsockname(serv_sk, (struct sockaddr *)&addr, &addr_len); + if (CHECK(err, "getsockname", "errno %d\n", errno)) + goto cleanup; + + *g_serv_port = addr.sin6_port; + + /* Client outside of test cgroup should fail to connect by timeout. */ + err = connect_fd_to_fd(out_sk, serv_sk); + if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd", + "unexpected result err %d errno %d\n", err, errno)) + goto cleanup; + + err = connect_wait(out_sk); + if (CHECK(err, "connect_wait", "unexpected result %d\n", err)) + goto cleanup; + + /* Client inside test cgroup should connect just fine. */ + in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk); + if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno)) + goto cleanup; + + serv_in_sk = accept(serv_sk, NULL, NULL); + if (CHECK(serv_in_sk < 0, "accept", "errno %d\n", errno)) + goto cleanup; + +cleanup: + close(serv_in_sk); + close(in_sk); + close(serv_sk); +} + +static void run_cgroup_bpf_test(const char *cg_path, int out_sk) +{ + struct cgroup_skb_sk_lookup_kern *skel; + struct bpf_link *link; + __u32 duration = 0; + int cgfd = -1; + + skel = cgroup_skb_sk_lookup_kern__open_and_load(); + if (CHECK(!skel, "skel_open_load", "open_load failed\n")) + return; + + cgfd = test__join_cgroup(cg_path); + if (CHECK(cgfd < 0, "cgroup_join", "cgroup setup failed\n")) + goto cleanup; + + link = bpf_program__attach_cgroup(skel->progs.ingress_lookup, cgfd); + if (CHECK(IS_ERR(link), "cgroup_attach", "err: %ld\n", PTR_ERR(link))) + goto cleanup; + + run_lookup_test(&skel->bss->g_serv_port, out_sk); + + bpf_link__destroy(link); + +cleanup: + close(cgfd); + cgroup_skb_sk_lookup_kern__destroy(skel); +} + +void test_cgroup_skb_sk_lookup(void) +{ + const char *cg_path = "/foo"; + int out_sk; + + /* Create a socket before joining testing cgroup so that its cgroup id + * differs from that of testing cgroup. Moving selftests process to + * testing cgroup won't change cgroup id of an already created socket. + */ + out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0); + if (CHECK_FAIL(out_sk < 0)) + return; + + run_cgroup_bpf_test(cg_path, out_sk); + + close(out_sk); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c new file mode 100644 index 000000000000..f259085cca6a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <string.h> + +#include <linux/pkt_cls.h> + +#include <test_progs.h> + +#include "progs/test_cls_redirect.h" +#include "test_cls_redirect.skel.h" + +#define ENCAP_IP INADDR_LOOPBACK +#define ENCAP_PORT (1234) + +struct addr_port { + in_port_t port; + union { + struct in_addr in_addr; + struct in6_addr in6_addr; + }; +}; + +struct tuple { + int family; + struct addr_port src; + struct addr_port dst; +}; + +static int start_server(const struct sockaddr *addr, socklen_t len, int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(bind(fd, addr, len) == -1)) + goto err; + if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1)) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static int connect_to_server(const struct sockaddr *addr, socklen_t len, + int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(connect(fd, addr, len))) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap) +{ + const struct sockaddr_in6 *in6; + const struct sockaddr_in *in; + + switch (sa->sa_family) { + case AF_INET: + in = (const struct sockaddr_in *)sa; + ap->in_addr = in->sin_addr; + ap->port = in->sin_port; + return true; + + case AF_INET6: + in6 = (const struct sockaddr_in6 *)sa; + ap->in6_addr = in6->sin6_addr; + ap->port = in6->sin6_port; + return true; + + default: + return false; + } +} + +static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type, + int *server, int *conn, struct tuple *tuple) +{ + struct sockaddr_storage ss; + socklen_t slen = sizeof(ss); + struct sockaddr *sa = (struct sockaddr *)&ss; + + *server = start_server(addr, len, type); + if (*server < 0) + return false; + + if (CHECK_FAIL(getsockname(*server, sa, &slen))) + goto close_server; + + *conn = connect_to_server(sa, slen, type); + if (*conn < 0) + goto close_server; + + /* We want to simulate packets arriving at conn, so we have to + * swap src and dst. + */ + slen = sizeof(ss); + if (CHECK_FAIL(getsockname(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst))) + goto close_conn; + + slen = sizeof(ss); + if (CHECK_FAIL(getpeername(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src))) + goto close_conn; + + tuple->family = ss.ss_family; + return true; + +close_conn: + close(*conn); + *conn = -1; +close_server: + close(*server); + *server = -1; + return false; +} + +static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) +{ + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = family; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + return sizeof(*addr4); + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = family; + addr6->sin6_addr = in6addr_loopback; + return sizeof(*addr6); + default: + fprintf(stderr, "Invalid family %d", family); + return 0; + } +} + +static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +{ + return tattr->data_size_out < tattr->data_size_in; +} + +enum type { + UDP, + TCP, + __NR_KIND, +}; + +enum hops { + NO_HOPS, + ONE_HOP, +}; + +enum flags { + NONE, + SYN, + ACK, +}; + +enum conn { + KNOWN_CONN, + UNKNOWN_CONN, +}; + +enum result { + ACCEPT, + FORWARD, +}; + +struct test_cfg { + enum type type; + enum result result; + enum conn conn; + enum hops hops; + enum flags flags; +}; + +static int test_str(void *buf, size_t len, const struct test_cfg *test, + int family) +{ + const char *family_str, *type, *conn, *hops, *result, *flags; + + family_str = "IPv4"; + if (family == AF_INET6) + family_str = "IPv6"; + + type = "TCP"; + if (test->type == UDP) + type = "UDP"; + + conn = "known"; + if (test->conn == UNKNOWN_CONN) + conn = "unknown"; + + hops = "no hops"; + if (test->hops == ONE_HOP) + hops = "one hop"; + + result = "accept"; + if (test->result == FORWARD) + result = "forward"; + + flags = "none"; + if (test->flags == SYN) + flags = "SYN"; + else if (test->flags == ACK) + flags = "ACK"; + + return snprintf(buf, len, "%s %s %s %s (%s, flags: %s)", family_str, + type, result, conn, hops, flags); +} + +static struct test_cfg tests[] = { + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, SYN }, + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, ACK }, + { TCP, FORWARD, UNKNOWN_CONN, ONE_HOP, ACK }, + { TCP, ACCEPT, KNOWN_CONN, ONE_HOP, ACK }, + { UDP, ACCEPT, UNKNOWN_CONN, NO_HOPS, NONE }, + { UDP, FORWARD, UNKNOWN_CONN, ONE_HOP, NONE }, + { UDP, ACCEPT, KNOWN_CONN, ONE_HOP, NONE }, +}; + +static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto) +{ + const uint8_t hlen = + (sizeof(struct guehdr) / sizeof(uint32_t)) + hop_count; + *encap = (encap_headers_t){ + .eth = { .h_proto = htons(ETH_P_IP) }, + .ip = { + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = IPPROTO_UDP, + .daddr = htonl(ENCAP_IP) + }, + .udp = { + .dest = htons(ENCAP_PORT), + }, + .gue = { + .hlen = hlen, + .proto_ctype = proto + }, + .unigue = { + .hop_count = hop_count + }, + }; +} + +static size_t build_input(const struct test_cfg *test, void *const buf, + const struct tuple *tuple) +{ + in_port_t sport = tuple->src.port; + encap_headers_t encap; + struct iphdr ip; + struct ipv6hdr ipv6; + struct tcphdr tcp; + struct udphdr udp; + struct in_addr next_hop; + uint8_t *p = buf; + int proto; + + proto = IPPROTO_IPIP; + if (tuple->family == AF_INET6) + proto = IPPROTO_IPV6; + + encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto); + p = mempcpy(p, &encap, sizeof(encap)); + + if (test->hops == ONE_HOP) { + next_hop = (struct in_addr){ .s_addr = htonl(0x7f000002) }; + p = mempcpy(p, &next_hop, sizeof(next_hop)); + } + + proto = IPPROTO_TCP; + if (test->type == UDP) + proto = IPPROTO_UDP; + + switch (tuple->family) { + case AF_INET: + ip = (struct iphdr){ + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = proto, + .saddr = tuple->src.in_addr.s_addr, + .daddr = tuple->dst.in_addr.s_addr, + }; + p = mempcpy(p, &ip, sizeof(ip)); + break; + case AF_INET6: + ipv6 = (struct ipv6hdr){ + .version = 6, + .hop_limit = IPDEFTTL, + .nexthdr = proto, + .saddr = tuple->src.in6_addr, + .daddr = tuple->dst.in6_addr, + }; + p = mempcpy(p, &ipv6, sizeof(ipv6)); + break; + default: + return 0; + } + + if (test->conn == UNKNOWN_CONN) + sport--; + + switch (test->type) { + case TCP: + tcp = (struct tcphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + if (test->flags == SYN) + tcp.syn = true; + if (test->flags == ACK) + tcp.ack = true; + p = mempcpy(p, &tcp, sizeof(tcp)); + break; + case UDP: + udp = (struct udphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + p = mempcpy(p, &udp, sizeof(udp)); + break; + default: + return 0; + } + + return (void *)p - buf; +} + +static void close_fds(int *fds, int n) +{ + int i; + + for (i = 0; i < n; i++) + if (fds[i] > 0) + close(fds[i]); +} + +void test_cls_redirect(void) +{ + struct test_cls_redirect *skel = NULL; + struct bpf_prog_test_run_attr tattr = {}; + int families[] = { AF_INET, AF_INET6 }; + struct sockaddr_storage ss; + struct sockaddr *addr; + socklen_t slen; + int i, j, err; + + int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; + int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; + struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; + + skel = test_cls_redirect__open(); + if (CHECK_FAIL(!skel)) + return; + + skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP); + skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT); + + if (CHECK_FAIL(test_cls_redirect__load(skel))) + goto cleanup; + + addr = (struct sockaddr *)&ss; + for (i = 0; i < ARRAY_SIZE(families); i++) { + slen = prepare_addr(&ss, families[i]); + if (CHECK_FAIL(!slen)) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM, + &servers[UDP][i], &conns[UDP][i], + &tuples[UDP][i]))) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM, + &servers[TCP][i], &conns[TCP][i], + &tuples[TCP][i]))) + goto cleanup; + } + + tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect); + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct test_cfg *test = &tests[i]; + + for (j = 0; j < ARRAY_SIZE(families); j++) { + struct tuple *tuple = &tuples[test->type][j]; + char input[256]; + char tmp[256]; + + test_str(tmp, sizeof(tmp), test, tuple->family); + if (!test__start_subtest(tmp)) + continue; + + tattr.data_out = tmp; + tattr.data_size_out = sizeof(tmp); + + tattr.data_in = input; + tattr.data_size_in = build_input(test, input, tuple); + if (CHECK_FAIL(!tattr.data_size_in)) + continue; + + err = bpf_prog_test_run_xattr(&tattr); + if (CHECK_FAIL(err)) + continue; + + if (tattr.retval != TC_ACT_REDIRECT) { + PRINT_FAIL("expected TC_ACT_REDIRECT, got %d\n", + tattr.retval); + continue; + } + + switch (test->result) { + case ACCEPT: + if (CHECK_FAIL(!was_decapsulated(&tattr))) + continue; + break; + case FORWARD: + if (CHECK_FAIL(was_decapsulated(&tattr))) + continue; + break; + default: + PRINT_FAIL("unknown result %d\n", test->result); + continue; + } + } + } + +cleanup: + test_cls_redirect__destroy(skel); + close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0])); + close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0])); +} diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c new file mode 100644 index 000000000000..47fbb20cb6a6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int verify_port(int family, int fd, int expected) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + __u16 port; + + if (getsockname(fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return -1; + } + + if (family == AF_INET) + port = ((struct sockaddr_in *)&addr)->sin_port; + else + port = ((struct sockaddr_in6 *)&addr)->sin6_port; + + if (ntohs(port) != expected) { + log_err("Unexpected port %d, expected %d", ntohs(port), + expected); + return -1; + } + + return 0; +} + +static int run_test(int cgroup_fd, int server_fd, int family, int type) +{ + struct bpf_prog_load_attr attr = { + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + }; + struct bpf_object *obj; + int expected_port; + int prog_fd; + int err; + int fd; + + if (family == AF_INET) { + attr.file = "./connect_force_port4.o"; + attr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + expected_port = 22222; + } else { + attr.file = "./connect_force_port6.o"; + attr.expected_attach_type = BPF_CGROUP_INET6_CONNECT; + expected_port = 22223; + } + + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + if (err) { + log_err("Failed to load BPF object"); + return -1; + } + + err = bpf_prog_attach(prog_fd, cgroup_fd, attr.expected_attach_type, + 0); + if (err) { + log_err("Failed to attach BPF program"); + goto close_bpf_object; + } + + fd = connect_to_fd(family, type, server_fd); + if (fd < 0) { + err = -1; + goto close_bpf_object; + } + + err = verify_port(family, fd, expected_port); + + close(fd); + +close_bpf_object: + bpf_object__close(obj); + return err; +} + +void test_connect_force_port(void) +{ + int server_fd, cgroup_fd; + + cgroup_fd = test__join_cgroup("/connect_force_port"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; + + server_fd = start_server(AF_INET, SOCK_STREAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM)); + close(server_fd); + + server_fd = start_server(AF_INET6, SOCK_STREAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM)); + close(server_fd); + + server_fd = start_server(AF_INET, SOCK_DGRAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM)); + close(server_fd); + + server_fd = start_server(AF_INET6, SOCK_DGRAM); + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; + CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM)); + close(server_fd); + +close_cgroup_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 31e177adbdf1..084ed26a7d78 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -392,7 +392,7 @@ static struct core_reloc_test_case test_cases[] = { .input = STRUCT_TO_CHAR_PTR(core_reloc_existence___minimal) { .a = 42, }, - .input_len = sizeof(struct core_reloc_existence), + .input_len = sizeof(struct core_reloc_existence___minimal), .output = STRUCT_TO_CHAR_PTR(core_reloc_existence_output) { .a_exists = 1, .b_exists = 0, diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c new file mode 100644 index 000000000000..2cb2085917e7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "test_enable_stats.skel.h" + +void test_enable_stats(void) +{ + struct test_enable_stats *skel; + int stats_fd, err, prog_fd; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + int duration = 0; + + skel = test_enable_stats__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) + return; + + stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); + if (CHECK(stats_fd < 0, "get_stats_fd", "failed %d\n", errno)) { + test_enable_stats__destroy(skel); + return; + } + + err = test_enable_stats__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) + goto cleanup; + + test_enable_stats__detach(skel); + + prog_fd = bpf_program__fd(skel->progs.test_enable_stats); + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err, "get_prog_info", + "failed to get bpf_prog_info for fd %d\n", prog_fd)) + goto cleanup; + if (CHECK(info.run_time_ns == 0, "check_stats_enabled", + "failed to enable run_time_ns stats\n")) + goto cleanup; + + CHECK(info.run_cnt != skel->bss->count, "check_run_cnt_valid", + "invalid run_cnt stats\n"); + +cleanup: + test_enable_stats__destroy(skel); + close(stats_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index c2642517e1d8..a895bfed55db 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include <network_helpers.h> static void test_fexit_bpf2bpf_common(const char *obj_file, const char *target_obj_file, diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 92563898867c..2301c4d3ecec 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> #include <error.h> #include <linux/if.h> #include <linux/if_tun.h> diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c index dc5ef155ec28..0e8a4d2f023d 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_flow_dissector_load_bytes(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index c680926fce73..e3cb62b0a110 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> static void test_global_data_number(struct bpf_object *obj, __u32 duration) { diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c index c490e012c23f..428d488830c6 100644 --- a/tools/testing/selftests/bpf/test_hashmap.c +++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c @@ -5,26 +5,17 @@ * * Copyright (c) 2019 Facebook */ -#include <stdio.h> -#include <errno.h> -#include <linux/err.h> +#include "test_progs.h" #include "bpf/hashmap.h" -#define CHECK(condition, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \ - fprintf(stderr, format); \ - } \ - __ret; \ -}) +static int duration = 0; -size_t hash_fn(const void *k, void *ctx) +static size_t hash_fn(const void *k, void *ctx) { return (long)k; } -bool equal_fn(const void *a, const void *b, void *ctx) +static bool equal_fn(const void *a, const void *b, void *ctx) { return (long)a == (long)b; } @@ -49,53 +40,55 @@ static inline size_t exp_cap(size_t sz) #define ELEM_CNT 62 -int test_hashmap_generic(void) +static void test_hashmap_generic(void) { struct hashmap_entry *entry, *tmp; int err, bkt, found_cnt, i; long long found_msk; struct hashmap *map; - fprintf(stderr, "%s: ", __func__); - map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + return; for (i = 0; i < ELEM_CNT; i++) { const void *oldk, *k = (const void *)(long)i; void *oldv, *v = (void *)(long)(1024 + i); err = hashmap__update(map, k, v, &oldk, &oldv); - if (CHECK(err != -ENOENT, "unexpected result: %d\n", err)) - return 1; + if (CHECK(err != -ENOENT, "hashmap__update", + "unexpected result: %d\n", err)) + goto cleanup; if (i % 2) { err = hashmap__add(map, k, v); } else { err = hashmap__set(map, k, v, &oldk, &oldv); - if (CHECK(oldk != NULL || oldv != NULL, + if (CHECK(oldk != NULL || oldv != NULL, "check_kv", "unexpected k/v: %p=%p\n", oldk, oldv)) - return 1; + goto cleanup; } - if (CHECK(err, "failed to add k/v %ld = %ld: %d\n", + if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n", (long)k, (long)v, err)) - return 1; + goto cleanup; - if (CHECK(!hashmap__find(map, k, &oldv), + if (CHECK(!hashmap__find(map, k, &oldv), "elem_find", "failed to find key %ld\n", (long)k)) - return 1; - if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv)) - return 1; + goto cleanup; + if (CHECK(oldv != v, "elem_val", + "found value is wrong: %ld\n", (long)oldv)) + goto cleanup; } - if (CHECK(hashmap__size(map) != ELEM_CNT, + if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap_cap", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; found_msk = 0; hashmap__for_each_entry(map, entry, bkt) { @@ -103,42 +96,47 @@ int test_hashmap_generic(void) long v = (long)entry->value; found_msk |= 1ULL << k; - if (CHECK(v - k != 1024, "invalid k/v pair: %ld = %ld\n", k, v)) - return 1; + if (CHECK(v - k != 1024, "check_kv", + "invalid k/v pair: %ld = %ld\n", k, v)) + goto cleanup; } - if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, + if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt", "not all keys iterated: %llx\n", found_msk)) - return 1; + goto cleanup; for (i = 0; i < ELEM_CNT; i++) { const void *oldk, *k = (const void *)(long)i; void *oldv, *v = (void *)(long)(256 + i); err = hashmap__add(map, k, v); - if (CHECK(err != -EEXIST, "unexpected add result: %d\n", err)) - return 1; + if (CHECK(err != -EEXIST, "hashmap__add", + "unexpected add result: %d\n", err)) + goto cleanup; if (i % 2) err = hashmap__update(map, k, v, &oldk, &oldv); else err = hashmap__set(map, k, v, &oldk, &oldv); - if (CHECK(err, "failed to update k/v %ld = %ld: %d\n", - (long)k, (long)v, err)) - return 1; - if (CHECK(!hashmap__find(map, k, &oldv), + if (CHECK(err, "elem_upd", + "failed to update k/v %ld = %ld: %d\n", + (long)k, (long)v, err)) + goto cleanup; + if (CHECK(!hashmap__find(map, k, &oldv), "elem_find", "failed to find key %ld\n", (long)k)) - return 1; - if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv)) - return 1; + goto cleanup; + if (CHECK(oldv != v, "elem_val", + "found value is wrong: %ld\n", (long)oldv)) + goto cleanup; } - if (CHECK(hashmap__size(map) != ELEM_CNT, + if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size", "invalid updated map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap__capacity", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; found_msk = 0; hashmap__for_each_entry_safe(map, entry, tmp, bkt) { @@ -146,20 +144,21 @@ int test_hashmap_generic(void) long v = (long)entry->value; found_msk |= 1ULL << k; - if (CHECK(v - k != 256, + if (CHECK(v - k != 256, "elem_check", "invalid updated k/v pair: %ld = %ld\n", k, v)) - return 1; + goto cleanup; } - if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, + if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt", "not all keys iterated after update: %llx\n", found_msk)) - return 1; + goto cleanup; found_cnt = 0; hashmap__for_each_key_entry(map, entry, (void *)0) { found_cnt++; } - if (CHECK(!found_cnt, "didn't find any entries for key 0\n")) - return 1; + if (CHECK(!found_cnt, "found_cnt", + "didn't find any entries for key 0\n")) + goto cleanup; found_msk = 0; found_cnt = 0; @@ -173,30 +172,31 @@ int test_hashmap_generic(void) found_cnt++; found_msk |= 1ULL << (long)k; - if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), + if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del", "failed to delete k/v %ld = %ld\n", (long)k, (long)v)) - return 1; - if (CHECK(oldk != k || oldv != v, + goto cleanup; + if (CHECK(oldk != k || oldv != v, "check_old", "invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n", (long)k, (long)v, (long)oldk, (long)oldv)) - return 1; - if (CHECK(hashmap__delete(map, k, &oldk, &oldv), + goto cleanup; + if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del", "unexpectedly deleted k/v %ld = %ld\n", (long)oldk, (long)oldv)) - return 1; + goto cleanup; } - if (CHECK(!found_cnt || !found_msk, + if (CHECK(!found_cnt || !found_msk, "found_entries", "didn't delete any key entries\n")) - return 1; - if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, + goto cleanup; + if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, "elem_cnt", "invalid updated map size (already deleted: %d): %zu\n", found_cnt, hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap__capacity", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; hashmap__for_each_entry_safe(map, entry, tmp, bkt) { const void *oldk, *k; @@ -208,53 +208,56 @@ int test_hashmap_generic(void) found_cnt++; found_msk |= 1ULL << (long)k; - if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), + if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del", "failed to delete k/v %ld = %ld\n", (long)k, (long)v)) - return 1; - if (CHECK(oldk != k || oldv != v, + goto cleanup; + if (CHECK(oldk != k || oldv != v, "elem_check", "invalid old k/v: expect %ld = %ld, got %ld = %ld\n", (long)k, (long)v, (long)oldk, (long)oldv)) - return 1; - if (CHECK(hashmap__delete(map, k, &oldk, &oldv), + goto cleanup; + if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del", "unexpectedly deleted k/v %ld = %ld\n", (long)k, (long)v)) - return 1; + goto cleanup; } if (CHECK(found_cnt != ELEM_CNT || found_msk != (1ULL << ELEM_CNT) - 1, + "found_cnt", "not all keys were deleted: found_cnt:%d, found_msk:%llx\n", found_cnt, found_msk)) - return 1; - if (CHECK(hashmap__size(map) != 0, + goto cleanup; + if (CHECK(hashmap__size(map) != 0, "hashmap__size", "invalid updated map size (already deleted: %d): %zu\n", found_cnt, hashmap__size(map))) - return 1; + goto cleanup; found_cnt = 0; hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected map entries left: %ld = %ld\n", - (long)entry->key, (long)entry->value); - return 1; + CHECK(false, "elem_exists", + "unexpected map entries left: %ld = %ld\n", + (long)entry->key, (long)entry->value); + goto cleanup; } - hashmap__free(map); + hashmap__clear(map); hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected map entries left: %ld = %ld\n", - (long)entry->key, (long)entry->value); - return 1; + CHECK(false, "elem_exists", + "unexpected map entries left: %ld = %ld\n", + (long)entry->key, (long)entry->value); + goto cleanup; } - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -size_t collision_hash_fn(const void *k, void *ctx) +static size_t collision_hash_fn(const void *k, void *ctx) { return 0; } -int test_hashmap_multimap(void) +static void test_hashmap_multimap(void) { void *k1 = (void *)0, *k2 = (void *)1; struct hashmap_entry *entry; @@ -262,121 +265,116 @@ int test_hashmap_multimap(void) long found_msk; int err, bkt; - fprintf(stderr, "%s: ", __func__); - /* force collisions */ map = hashmap__new(collision_hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; - + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + return; /* set up multimap: * [0] -> 1, 2, 4; * [1] -> 8, 16, 32; */ err = hashmap__append(map, k1, (void *)1); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k1, (void *)2); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k1, (void *)4); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)8); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)16); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)32); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; - if (CHECK(hashmap__size(map) != 6, + if (CHECK(hashmap__size(map) != 6, "hashmap_size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; /* verify global iteration still works and sees all values */ found_msk = 0; hashmap__for_each_entry(map, entry, bkt) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (1 << 6) - 1, + if (CHECK(found_msk != (1 << 6) - 1, "found_msk", "not all keys iterated: %lx\n", found_msk)) - return 1; + goto cleanup; /* iterate values for key 1 */ found_msk = 0; hashmap__for_each_key_entry(map, entry, k1) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (1 | 2 | 4), + if (CHECK(found_msk != (1 | 2 | 4), "found_msk", "invalid k1 values: %lx\n", found_msk)) - return 1; + goto cleanup; /* iterate values for key 2 */ found_msk = 0; hashmap__for_each_key_entry(map, entry, k2) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (8 | 16 | 32), + if (CHECK(found_msk != (8 | 16 | 32), "found_msk", "invalid k2 values: %lx\n", found_msk)) - return 1; + goto cleanup; - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -int test_hashmap_empty() +static void test_hashmap_empty() { struct hashmap_entry *entry; int bkt; struct hashmap *map; void *k = (void *)0; - fprintf(stderr, "%s: ", __func__); - /* force collisions */ map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + goto cleanup; - if (CHECK(hashmap__size(map) != 0, + if (CHECK(hashmap__size(map) != 0, "hashmap__size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; - if (CHECK(hashmap__capacity(map) != 0, + goto cleanup; + if (CHECK(hashmap__capacity(map) != 0, "hashmap__capacity", "invalid map capacity: %zu\n", hashmap__capacity(map))) - return 1; - if (CHECK(hashmap__find(map, k, NULL), "unexpected find\n")) - return 1; - if (CHECK(hashmap__delete(map, k, NULL, NULL), "unexpected delete\n")) - return 1; + goto cleanup; + if (CHECK(hashmap__find(map, k, NULL), "elem_find", + "unexpected find\n")) + goto cleanup; + if (CHECK(hashmap__delete(map, k, NULL, NULL), "elem_del", + "unexpected delete\n")) + goto cleanup; hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected iterated entry\n"); - return 1; + CHECK(false, "elem_found", "unexpected iterated entry\n"); + goto cleanup; } hashmap__for_each_key_entry(map, entry, k) { - CHECK(false, "unexpected key entry\n"); - return 1; + CHECK(false, "key_found", "unexpected key entry\n"); + goto cleanup; } - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -int main(int argc, char **argv) +void test_hashmap() { - bool failed = false; - - if (test_hashmap_generic()) - failed = true; - if (test_hashmap_multimap()) - failed = true; - if (test_hashmap_empty()) - failed = true; - - return failed; + if (test__start_subtest("generic")) + test_hashmap_generic(); + if (test__start_subtest("multimap")) + test_hashmap_multimap(); + if (test__start_subtest("empty")) + test_hashmap_empty(); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index 7507c8f689bc..42c3a3103c26 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> struct meta { int ifindex; diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index eaf64595be88..c2d373e294bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> static void test_l4lb(const char *file) { diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 8f91f1881d11..ce17b1ed8709 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -1,5 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> + +static void *spin_lock_thread(void *arg) +{ + __u32 duration, retval; + int err, prog_fd = *(u32 *) arg; + + err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || retval, "", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + pthread_exit(arg); +} static void *parallel_map_access(void *arg) { diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c index 542240e16564..e74dc501b27f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -80,9 +80,6 @@ void test_ns_current_pid_tgid(void) "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid)) goto cleanup; cleanup: - if (!link) { - bpf_link__destroy(link); - link = NULL; - } + bpf_link__destroy(link); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 1450ea2dd4cc..a122ce3b360e 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -6,6 +6,11 @@ #include <test_progs.h> #include "bpf/libbpf_internal.h" +/* AddressSanitizer sometimes crashes due to data dereference below, due to + * this being mmap()'ed memory. Disable instrumentation with + * no_sanitize_address attribute + */ +__attribute__((no_sanitize_address)) static void on_sample(void *ctx, int cpu, void *data, __u32 size) { int cpu_data = *(int *)data, duration = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index a2537dfa899c..44b514fabccd 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_pkt_access(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index 5f7aea605019..939015cd6dba 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_pkt_md_access(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c index 5dd89b941f53..dde2b7ae7bc9 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_prog_run_xattr(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index faccc66f4e39..f47e7b1cb32c 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> enum { QUEUE, diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c index 996e808f43a2..dfcbddcbe4d3 100644 --- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c +++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> static void sigalrm_handler(int s) {} static struct sigaction sigalrm_action = { diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index d572e1a2c297..47fa04adc147 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -20,6 +20,7 @@ #define CONNECT_PORT 4321 #define TEST_DADDR (0xC0A80203) #define NS_SELF "/proc/self/ns/net" +#define SERVER_MAP_PATH "/sys/fs/bpf/tc/globals/server_map" static const struct timeval timeo_sec = { .tv_sec = 3 }; static const size_t timeo_optlen = sizeof(timeo_sec); @@ -265,6 +266,7 @@ void test_sk_assign(void) TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true), }; int server = -1; + int server_map; int self_net; self_net = open(NS_SELF, O_RDONLY); @@ -278,9 +280,17 @@ void test_sk_assign(void) goto cleanup; } + server_map = bpf_obj_get(SERVER_MAP_PATH); + if (CHECK_FAIL(server_map < 0)) { + perror("Unable to open " SERVER_MAP_PATH); + goto cleanup; + } + for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) { struct test_sk_cfg *test = &tests[i]; const struct sockaddr *addr; + const int zero = 0; + int err; if (!test__start_subtest(test->name)) continue; @@ -288,7 +298,13 @@ void test_sk_assign(void) addr = (const struct sockaddr *)test->addr; server = start_server(addr, test->len, test->type); if (server == -1) - goto cleanup; + goto close; + + err = bpf_map_update_elem(server_map, &zero, &server, BPF_ANY); + if (CHECK_FAIL(err)) { + perror("Unable to update server_map"); + goto close; + } /* connect to unbound ports */ prepare_addr(test->addr, test->family, CONNECT_PORT, @@ -302,7 +318,10 @@ void test_sk_assign(void) close: close(server); + close(server_map); cleanup: + if (CHECK_FAIL(unlink(SERVER_MAP_PATH))) + perror("Unable to unlink " SERVER_MAP_PATH); if (CHECK_FAIL(setns(self_net, CLONE_NEWNET))) perror("Failed to setns("NS_SELF")"); close(self_net); diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 4538bd08203f..7021b92af313 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_skb_ctx(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 1ae00cd3174e..7577a77a4c4c 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -1,5 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> + +static void *spin_lock_thread(void *arg) +{ + __u32 duration, retval; + int err, prog_fd = *(u32 *) arg; + + err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || retval, "", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + pthread_exit(arg); +} void test_spinlock(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index e56b52ab41da..9013a0c01eed 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include "cgroup_helpers.h" +#include "network_helpers.h" struct tcp_rtt_storage { __u32 invoked; @@ -87,34 +88,6 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, return err; } -static int connect_to_server(int server_fd) -{ - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int fd; - - fd = socket(AF_INET, SOCK_STREAM, 0); - if (fd < 0) { - log_err("Failed to create client socket"); - return -1; - } - - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - if (connect(fd, (const struct sockaddr *)&addr, len) < 0) { - log_err("Fail to connect to server"); - goto out; - } - - return fd; - -out: - close(fd); - return -1; -} static int run_test(int cgroup_fd, int server_fd) { @@ -145,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd) goto close_bpf_object; } - client_fd = connect_to_server(server_fd); + client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd); if (client_fd < 0) { err = -1; goto close_bpf_object; @@ -180,103 +153,22 @@ close_bpf_object: return err; } -static int start_server(void) -{ - struct sockaddr_in addr = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_LOOPBACK), - }; - int fd; - - fd = socket(AF_INET, SOCK_STREAM | SOCK_NONBLOCK, 0); - if (fd < 0) { - log_err("Failed to create server socket"); - return -1; - } - - if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { - log_err("Failed to bind socket"); - close(fd); - return -1; - } - - return fd; -} - -static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER; -static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER; -static volatile bool server_done = false; - -static void *server_thread(void *arg) -{ - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int fd = *(int *)arg; - int client_fd; - int err; - - err = listen(fd, 1); - - pthread_mutex_lock(&server_started_mtx); - pthread_cond_signal(&server_started); - pthread_mutex_unlock(&server_started_mtx); - - if (CHECK_FAIL(err < 0)) { - perror("Failed to listed on socket"); - return ERR_PTR(err); - } - - while (true) { - client_fd = accept(fd, (struct sockaddr *)&addr, &len); - if (client_fd == -1 && errno == EAGAIN) { - usleep(50); - continue; - } - break; - } - if (CHECK_FAIL(client_fd < 0)) { - perror("Failed to accept client"); - return ERR_PTR(err); - } - - while (!server_done) - usleep(50); - - close(client_fd); - - return NULL; -} - void test_tcp_rtt(void) { int server_fd, cgroup_fd; - pthread_t tid; - void *server_res; cgroup_fd = test__join_cgroup("/tcp_rtt"); if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server(); + server_fd = start_server(AF_INET, SOCK_STREAM); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; - if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, - (void *)&server_fd))) - goto close_server_fd; - - pthread_mutex_lock(&server_started_mtx); - pthread_cond_wait(&server_started, &server_started_mtx); - pthread_mutex_unlock(&server_started_mtx); - CHECK_FAIL(run_test(cgroup_fd, server_fd)); - server_done = true; - CHECK_FAIL(pthread_join(tid, &server_res)); - CHECK_FAIL(IS_ERR(server_res)); - -close_server_fd: close(server_fd); + close_cgroup_fd: close(cgroup_fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index 465b371a561d..2702df2b2343 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -61,9 +61,10 @@ void test_test_overhead(void) const char *raw_tp_name = "raw_tp/task_rename"; const char *fentry_name = "fentry/__set_task_comm"; const char *fexit_name = "fexit/__set_task_comm"; + const char *fmodret_name = "fmod_ret/__set_task_comm"; const char *kprobe_func = "__set_task_comm"; struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog; - struct bpf_program *fentry_prog, *fexit_prog; + struct bpf_program *fentry_prog, *fexit_prog, *fmodret_prog; struct bpf_object *obj; struct bpf_link *link; int err, duration = 0; @@ -96,6 +97,10 @@ void test_test_overhead(void) if (CHECK(!fexit_prog, "find_probe", "prog '%s' not found\n", fexit_name)) goto cleanup; + fmodret_prog = bpf_object__find_program_by_title(obj, fmodret_name); + if (CHECK(!fmodret_prog, "find_probe", + "prog '%s' not found\n", fmodret_name)) + goto cleanup; err = bpf_object__load(obj); if (CHECK(err, "obj_load", "err %d\n", err)) @@ -142,6 +147,13 @@ void test_test_overhead(void) goto cleanup; test_run("fexit"); bpf_link__destroy(link); + + /* attach fmod_ret */ + link = bpf_program__attach_trace(fmodret_prog); + if (CHECK(IS_ERR(link), "attach fmod_ret", "err %ld\n", PTR_ERR(link))) + goto cleanup; + test_run("fmod_ret"); + 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/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index dcb5ecac778e..48921ff74850 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_xdp(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 3744196d7cba..d5c98f2cb12f 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -1,13 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> -void test_xdp_adjust_tail(void) +void test_xdp_adjust_tail_shrink(void) { - const char *file = "./test_adjust_tail.o"; + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 duration, retval, size, expect_sz; struct bpf_object *obj; - char buf[128]; - __u32 duration, retval, size; int err, prog_fd; + char buf[128]; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -20,10 +21,121 @@ void test_xdp_adjust_tail(void) "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size); + expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != 54, - "ipv6", "err %d errno %d retval %d size %d\n", + CHECK(err || retval != XDP_TX || size != expect_sz, + "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", + err, errno, retval, size, expect_sz); + bpf_object__close(obj); +} + +void test_xdp_adjust_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + struct bpf_object *obj; + char buf[4096]; /* avoid segfault: large buf to hold grow results */ + __u32 duration, retval, size, expect_sz; + 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, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + CHECK(err || retval != XDP_DROP, + "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size); + + expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */ + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */, + buf, &size, &retval, &duration); + CHECK(err || retval != XDP_TX || size != expect_sz, + "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", + err, errno, retval, size, expect_sz); + + bpf_object__close(obj); +} + +void test_xdp_adjust_tail_grow2(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + char buf[4096]; /* avoid segfault: large buf to hold grow results */ + int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; + struct bpf_object *obj; + int err, cnt, i; + int max_grow; + + struct bpf_prog_test_run_attr tattr = { + .repeat = 1, + .data_in = &buf, + .data_out = &buf, + .data_size_in = 0, /* Per test */ + .data_size_out = 0, /* Per test */ + }; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); + if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + return; + + /* Test case-64 */ + memset(buf, 1, sizeof(buf)); + tattr.data_size_in = 64; /* Determine test case via pkt size */ + tattr.data_size_out = 128; /* Limit copy_size */ + /* Kernel side alloc packet memory area that is zero init */ + err = bpf_prog_test_run_xattr(&tattr); + + CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */ + || tattr.retval != XDP_TX + || tattr.data_size_out != 192, /* Expected grow size */ + "case-64", + "err %d errno %d retval %d size %d\n", + err, errno, tattr.retval, tattr.data_size_out); + + /* Extra checks for data contents */ + CHECK_ATTR(tattr.data_size_out != 192 + || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */ + || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */ + || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */ + "case-64-data", + "err %d errno %d retval %d size %d\n", + err, errno, tattr.retval, tattr.data_size_out); + + /* Test case-128 */ + memset(buf, 2, sizeof(buf)); + tattr.data_size_in = 128; /* Determine test case via pkt size */ + tattr.data_size_out = sizeof(buf); /* Copy everything */ + err = bpf_prog_test_run_xattr(&tattr); + + max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */ + CHECK_ATTR(err + || tattr.retval != XDP_TX + || tattr.data_size_out != max_grow,/* Expect max grow size */ + "case-128", + "err %d errno %d retval %d size %d expect-size %d\n", + err, errno, tattr.retval, tattr.data_size_out, max_grow); + + /* Extra checks for data content: Count grow size, will contain zeros */ + for (i = 0, cnt = 0; i < sizeof(buf); i++) { + if (buf[i] == 0) + cnt++; + } + CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */ + || tattr.data_size_out != max_grow, /* Total grow size */ + "case-128-data", + "err %d errno %d retval %d size %d grow-size %d\n", + err, errno, tattr.retval, tattr.data_size_out, cnt); + bpf_object__close(obj); } + +void test_xdp_adjust_tail(void) +{ + if (test__start_subtest("xdp_adjust_tail_shrink")) + test_xdp_adjust_tail_shrink(); + if (test__start_subtest("xdp_adjust_tail_grow")) + test_xdp_adjust_tail_grow(); + if (test__start_subtest("xdp_adjust_tail_grow2")) + test_xdp_adjust_tail_grow2(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index a0f688c37023..2c6c570b21f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> #include <net/if.h> #include "test_xdp.skel.h" #include "test_xdp_bpf2bpf.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index c9404e6b226e..f284f72158ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <network_helpers.h> void test_xdp_noinline(void) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c new file mode 100644 index 000000000000..4867cd3445c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + + if (map == (void *)0) { + BPF_SEQ_PRINTF(seq, " %%%%%% END %%%%%%\n"); + return 0; + } + + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " id refcnt usercnt locked_vm\n"); + + BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter, + map->usercnt.counter, + map->memory.user->locked_vm.counter); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c new file mode 100644 index 000000000000..ab9e2650e021 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +extern bool CONFIG_IPV6_SUBTREES __kconfig __weak; + +#define RTF_GATEWAY 0x0002 +#define IFNAMSIZ 16 +#define fib_nh_gw_family nh_common.nhc_gw_family +#define fib_nh_gw6 nh_common.nhc_gw.ipv6 +#define fib_nh_dev nh_common.nhc_dev + +SEC("iter/ipv6_route") +int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct fib6_info *rt = ctx->rt; + const struct net_device *dev; + struct fib6_nh *fib6_nh; + unsigned int flags; + struct nexthop *nh; + + if (rt == (void *)0) + return 0; + + fib6_nh = &rt->fib6_nh[0]; + flags = rt->fib6_flags; + + /* FIXME: nexthop_is_multipath is not handled here. */ + nh = rt->nh; + if (rt->nh) + fib6_nh = &nh->nh_info->fib6_nh; + + BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); + + if (CONFIG_IPV6_SUBTREES) + BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_src.addr, + rt->fib6_src.plen); + else + BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 00 "); + + if (fib6_nh->fib_nh_gw_family) { + flags |= RTF_GATEWAY; + BPF_SEQ_PRINTF(seq, "%pi6 ", &fib6_nh->fib_nh_gw6); + } else { + BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 "); + } + + dev = fib6_nh->fib_nh_dev; + if (dev) + BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x %8s\n", rt->fib6_metric, + rt->fib6_ref.refs.counter, 0, flags, dev->name); + else + BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x\n", rt->fib6_metric, + rt->fib6_ref.refs.counter, 0, flags); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c new file mode 100644 index 000000000000..6b40a233d4e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define sk_rmem_alloc sk_backlog.rmem_alloc +#define sk_refcnt __sk_common.skc_refcnt + +static inline struct inode *SOCK_INODE(struct socket *socket) +{ + return &container_of(socket, struct socket_alloc, socket)->vfs_inode; +} + +SEC("iter/netlink") +int dump_netlink(struct bpf_iter__netlink *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct netlink_sock *nlk = ctx->sk; + unsigned long group, ino; + struct inode *inode; + struct socket *sk; + struct sock *s; + + if (nlk == (void *)0) + return 0; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "sk Eth Pid Groups " + "Rmem Wmem Dump Locks Drops " + "Inode\n"); + + s = &nlk->sk; + BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol); + + if (!nlk->groups) { + group = 0; + } else { + /* FIXME: temporary use bpf_probe_read here, needs + * verifier support to do direct access. + */ + bpf_probe_read(&group, sizeof(group), &nlk->groups[0]); + } + BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ", + nlk->portid, (u32)group, + s->sk_rmem_alloc.counter, + s->sk_wmem_alloc.refs.counter - 1, + nlk->cb_running, s->sk_refcnt.refs.counter); + + sk = s->sk_socket; + if (!sk) { + ino = 0; + } else { + /* FIXME: container_of inside SOCK_INODE has a forced + * type conversion, and direct access cannot be used + * with current verifier. + */ + inode = SOCK_INODE(sk); + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + } + BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c new file mode 100644 index 000000000000..90f9011c57ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, " === END ===\n"); + return 0; + } + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c new file mode 100644 index 000000000000..c6ced38f0880 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/task_file") +int dump_task_file(struct bpf_iter__task_file *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + __u32 fd = ctx->fd; + struct file *file = ctx->file; + + if (task == (void *)0 || file == (void *)0) + return 0; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid fd file\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d %lx\n", task->tgid, task->pid, fd, + (long)file->f_op); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c new file mode 100644 index 000000000000..c71a7c283108 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define START_CHAR 'a' +#include "bpf_iter_test_kern_common.h" diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c new file mode 100644 index 000000000000..8bdc8dc07444 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define START_CHAR 'A' +#include "bpf_iter_test_kern_common.h" diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c new file mode 100644 index 000000000000..636a00fa074d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + int tgid; + + tgid = task->tgid; + bpf_seq_write(seq, &tgid, sizeof(tgid)); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c new file mode 100644 index 000000000000..b18dc0471d07 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 map1_id = 0, map2_id = 0; +__u32 map1_accessed = 0, map2_accessed = 0; +__u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; + +static volatile const __u32 print_len; +static volatile const __u32 ret1; + +SEC("iter/bpf_map") +int dump_bpf_map(struct bpf_iter__bpf_map *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct bpf_map *map = ctx->map; + __u64 seq_num; + int i, ret = 0; + + if (map == (void *)0) + return 0; + + /* only dump map1_id and map2_id */ + if (map->id != map1_id && map->id != map2_id) + return 0; + + seq_num = ctx->meta->seq_num; + if (map->id == map1_id) { + map1_seqnum = seq_num; + map1_accessed++; + } + + if (map->id == map2_id) { + if (map2_accessed == 0) { + map2_seqnum1 = seq_num; + if (ret1) + ret = 1; + } else { + map2_seqnum2 = seq_num; + } + map2_accessed++; + } + + /* fill seq_file buffer */ + for (i = 0; i < print_len; i++) + bpf_seq_write(seq, &seq_num, sizeof(seq_num)); + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h new file mode 100644 index 000000000000..bdd51cf14b54 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; +int count = 0; + +SEC("iter/task") +int dump_task(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + char c; + + if (count < 4) { + c = START_CHAR + count; + bpf_seq_write(seq, &c, sizeof(c)); + count++; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c new file mode 100644 index 000000000000..3f757e30d7a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/types.h> +#include <sys/socket.h> + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +__u16 g_serv_port = 0; + +static inline void set_ip(__u32 *dst, const struct in6_addr *src) +{ + dst[0] = src->in6_u.u6_addr32[0]; + dst[1] = src->in6_u.u6_addr32[1]; + dst[2] = src->in6_u.u6_addr32[2]; + dst[3] = src->in6_u.u6_addr32[3]; +} + +static inline void set_tuple(struct bpf_sock_tuple *tuple, + const struct ipv6hdr *ip6h, + const struct tcphdr *tcph) +{ + set_ip(tuple->ipv6.saddr, &ip6h->daddr); + set_ip(tuple->ipv6.daddr, &ip6h->saddr); + tuple->ipv6.sport = tcph->dest; + tuple->ipv6.dport = tcph->source; +} + +static inline int is_allowed_peer_cg(struct __sk_buff *skb, + const struct ipv6hdr *ip6h, + const struct tcphdr *tcph) +{ + __u64 cgid, acgid, peer_cgid, peer_acgid; + struct bpf_sock_tuple tuple; + size_t tuple_len = sizeof(tuple.ipv6); + struct bpf_sock *peer_sk; + + set_tuple(&tuple, ip6h, tcph); + + peer_sk = bpf_sk_lookup_tcp(skb, &tuple, tuple_len, + BPF_F_CURRENT_NETNS, 0); + if (!peer_sk) + return 0; + + cgid = bpf_skb_cgroup_id(skb); + peer_cgid = bpf_sk_cgroup_id(peer_sk); + + acgid = bpf_skb_ancestor_cgroup_id(skb, 2); + peer_acgid = bpf_sk_ancestor_cgroup_id(peer_sk, 2); + + bpf_sk_release(peer_sk); + + return cgid && cgid == peer_cgid && acgid && acgid == peer_acgid; +} + +SEC("cgroup_skb/ingress") +int ingress_lookup(struct __sk_buff *skb) +{ + __u32 serv_port_key = 0; + struct ipv6hdr ip6h; + struct tcphdr tcph; + + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return 1; + + /* For SYN packets coming to listening socket skb->remote_port will be + * zero, so IPv6/TCP headers are loaded to identify remote peer + * instead. + */ + if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h))) + return 1; + + if (ip6h.nexthdr != IPPROTO_TCP) + return 1; + + if (bpf_skb_load_bytes(skb, sizeof(ip6h), &tcph, sizeof(tcph))) + return 1; + + if (!g_serv_port) + return 0; + + if (tcph.dest != g_serv_port) + return 1; + + return is_allowed_peer_cg(skb, &ip6h, &tcph); +} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index ad3c498a8150..c2c85c31cffd 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -8,6 +8,7 @@ #include <linux/in.h> #include <linux/in6.h> #include <sys/socket.h> +#include <netinet/tcp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> @@ -16,6 +17,10 @@ #define DST_REWRITE_IP4 0x7f000001U #define DST_REWRITE_PORT4 4444 +#ifndef TCP_CA_NAME_MAX +#define TCP_CA_NAME_MAX 16 +#endif + int _version SEC("version") = 1; __attribute__ ((noinline)) @@ -33,6 +38,43 @@ int do_bind(struct bpf_sock_addr *ctx) return 1; } +static __inline int verify_cc(struct bpf_sock_addr *ctx, + char expected[TCP_CA_NAME_MAX]) +{ + char buf[TCP_CA_NAME_MAX]; + int i; + + if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) + return 1; + + for (i = 0; i < TCP_CA_NAME_MAX; i++) { + if (buf[i] != expected[i]) + return 1; + if (buf[i] == 0) + break; + } + + return 0; +} + +static __inline int set_cc(struct bpf_sock_addr *ctx) +{ + char reno[TCP_CA_NAME_MAX] = "reno"; + char cubic[TCP_CA_NAME_MAX] = "cubic"; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno))) + return 1; + if (verify_cc(ctx, reno)) + return 1; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic))) + return 1; + if (verify_cc(ctx, cubic)) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -66,6 +108,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) bpf_sk_release(sk); + /* Rewrite congestion control. */ + if (ctx->type == SOCK_STREAM && set_cc(ctx)) + return 0; + /* Rewrite destination. */ ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); ctx->user_port = bpf_htons(DST_REWRITE_PORT4); diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c new file mode 100644 index 000000000000..1b8eb34b2db0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> + +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = 1; + +SEC("cgroup/connect4") +int _connect4(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(22222); + sa.sin_addr.s_addr = bpf_htonl(0x7f000001); /* 127.0.0.1 */ + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c new file mode 100644 index 000000000000..ae6f7d750b4c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> + +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = 1; + +SEC("cgroup/connect6") +int _connect6(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in6 sa = {}; + + sa.sin6_family = AF_INET6; + sa.sin6_port = bpf_htons(22223); + sa.sin6_addr.s6_addr32[3] = bpf_htonl(1); /* ::1 */ + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 6d598cfbdb3e..34d84717c946 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -379,7 +379,7 @@ struct core_reloc_arrays___equiv_zero_sz_arr { 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_substruct f[][2]; }; struct core_reloc_arrays___fixed_arr { diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c new file mode 100644 index 000000000000..e5093796be97 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"), + inner_map2 SEC(".maps"); + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 3); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + /* it's possible to use anonymous struct as inner map definition here */ + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + /* changing max_entries to 2 will fail during load + * due to incompatibility with inner_map definition */ + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} outer_arr SEC(".maps") = { + /* (void *) cast is necessary because we didn't use `struct inner_map` + * in __inner(values, ...) + * Actually, a conscious effort is required to screw up initialization + * of inner map slots, which is a great thing! + */ + .values = { (void *)&inner_map1, 0, (void *)&inner_map2 }, +}; + +struct outer_hash { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 5); + __uint(key_size, sizeof(int)); + /* Here everything works flawlessly due to reuse of struct inner_map + * and compiler will complain at the attempt to use non-inner_map + * references below. This is great experience. + */ + __array(values, struct inner_map); +} outer_hash SEC(".maps") = { + .values = { + [0] = &inner_map2, + [4] = &inner_map1, + }, +}; + +int input = 0; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + struct inner_map *inner_map; + int key = 0, val; + + inner_map = bpf_map_lookup_elem(&outer_arr, &key); + if (!inner_map) + return 1; + val = input; + bpf_map_update_elem(inner_map, &key, &val, 0); + + inner_map = bpf_map_lookup_elem(&outer_hash, &key); + if (!inner_map) + return 1; + val = input + 1; + bpf_map_update_elem(inner_map, &key, &val, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c new file mode 100644 index 000000000000..1668b993eb86 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -0,0 +1,1058 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2019, 2020 Cloudflare + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "test_cls_redirect.h" + +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) + +#define IP_OFFSET_MASK (0x1FFF) +#define IP_MF (0x2000) + +char _license[] SEC("license") = "Dual BSD/GPL"; + +/** + * Destination port and IP used for UDP encapsulation. + */ +static volatile const __be16 ENCAPSULATION_PORT; +static volatile const __be32 ENCAPSULATION_IP; + +typedef struct { + uint64_t processed_packets_total; + uint64_t l3_protocol_packets_total_ipv4; + uint64_t l3_protocol_packets_total_ipv6; + uint64_t l4_protocol_packets_total_tcp; + uint64_t l4_protocol_packets_total_udp; + uint64_t accepted_packets_total_syn; + uint64_t accepted_packets_total_syn_cookies; + uint64_t accepted_packets_total_last_hop; + uint64_t accepted_packets_total_icmp_echo_request; + uint64_t accepted_packets_total_established; + uint64_t forwarded_packets_total_gue; + uint64_t forwarded_packets_total_gre; + + uint64_t errors_total_unknown_l3_proto; + uint64_t errors_total_unknown_l4_proto; + uint64_t errors_total_malformed_ip; + uint64_t errors_total_fragmented_ip; + uint64_t errors_total_malformed_icmp; + uint64_t errors_total_unwanted_icmp; + uint64_t errors_total_malformed_icmp_pkt_too_big; + uint64_t errors_total_malformed_tcp; + uint64_t errors_total_malformed_udp; + uint64_t errors_total_icmp_echo_replies; + uint64_t errors_total_malformed_encapsulation; + uint64_t errors_total_encap_adjust_failed; + uint64_t errors_total_encap_buffer_too_small; + uint64_t errors_total_redirect_loop; +} metrics_t; + +typedef enum { + INVALID = 0, + UNKNOWN, + ECHO_REQUEST, + SYN, + SYN_COOKIE, + ESTABLISHED, +} verdict_t; + +typedef struct { + uint16_t src, dst; +} flow_ports_t; + +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv4.dport) - + offsetof(struct bpf_sock_tuple, ipv4.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv6.dport) - + offsetof(struct bpf_sock_tuple, ipv6.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); + +typedef int ret_t; + +/* This is a bit of a hack. We need a return value which allows us to + * indicate that the regular flow of the program should continue, + * while allowing functions to use XDP_PASS and XDP_DROP, etc. + */ +static const ret_t CONTINUE_PROCESSING = -1; + +/* Convenience macro to call functions which return ret_t. + */ +#define MAYBE_RETURN(x) \ + do { \ + ret_t __ret = x; \ + if (__ret != CONTINUE_PROCESSING) \ + return __ret; \ + } while (0) + +/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes), + * or not aligned if the arch supports efficient unaligned access. + * + * Since the verifier ensures that eBPF packet accesses follow these rules, + * we can tell LLVM to emit code as if we always had a larger alignment. + * It will yell at us if we end up on a platform where this is not valid. + */ +typedef uint8_t *net_ptr __attribute__((align_value(8))); + +typedef struct buf { + struct __sk_buff *skb; + net_ptr head; + /* NB: tail musn't have alignment other than 1, otherwise + * LLVM will go and eliminate code, e.g. when checking packet lengths. + */ + uint8_t *const tail; +} buf_t; + +static size_t buf_off(const buf_t *buf) +{ + /* Clang seems to optimize constructs like + * a - b + c + * if c is known: + * r? = c + * r? -= b + * r? += a + * + * This is a problem if a and b are packet pointers, + * since the verifier allows subtracting two pointers to + * get a scalar, but not a scalar and a pointer. + * + * Use inline asm to break this optimization. + */ + size_t off = (size_t)buf->head; + asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data)); + return off; +} + +static bool buf_copy(buf_t *buf, void *dst, size_t len) +{ + if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) { + return false; + } + + buf->head += len; + return true; +} + +static bool buf_skip(buf_t *buf, const size_t len) +{ + /* Check whether off + len is valid in the non-linear part. */ + if (buf_off(buf) + len > buf->skb->len) { + return false; + } + + buf->head += len; + return true; +} + +/* Returns a pointer to the start of buf, or NULL if len is + * larger than the remaining data. Consumes len bytes on a successful + * call. + * + * If scratch is not NULL, the function will attempt to load non-linear + * data via bpf_skb_load_bytes. On success, scratch is returned. + */ +static void *buf_assign(buf_t *buf, const size_t len, void *scratch) +{ + if (buf->head + len > buf->tail) { + if (scratch == NULL) { + return NULL; + } + + return buf_copy(buf, scratch, len) ? scratch : NULL; + } + + void *ptr = buf->head; + buf->head += len; + return ptr; +} + +static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4) +{ + if (ipv4->ihl <= 5) { + return true; + } + + return buf_skip(buf, (ipv4->ihl - 5) * 4); +} + +static bool ipv4_is_fragment(const struct iphdr *ip) +{ + uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK); + return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0; +} + +static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch) +{ + struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch); + if (ipv4 == NULL) { + return NULL; + } + + if (ipv4->ihl < 5) { + return NULL; + } + + if (!pkt_skip_ipv4_options(pkt, ipv4)) { + return NULL; + } + + return ipv4; +} + +/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */ +static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports) +{ + if (!buf_copy(pkt, ports, sizeof(*ports))) { + return false; + } + + /* Ports in the L4 headers are reversed, since we are parsing an ICMP + * payload which is going towards the eyeball. + */ + uint16_t dst = ports->src; + ports->src = ports->dst; + ports->dst = dst; + return true; +} + +static uint16_t pkt_checksum_fold(uint32_t csum) +{ + /* The highest reasonable value for an IPv4 header + * checksum requires two folds, so we just do that always. + */ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (uint16_t)~csum; +} + +static void pkt_ipv4_checksum(struct iphdr *iph) +{ + iph->check = 0; + + /* An IP header without options is 20 bytes. Two of those + * are the checksum, which we always set to zero. Hence, + * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7, + * which fits in 32 bit. + */ + _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes"); + uint32_t acc = 0; + uint16_t *ipw = (uint16_t *)iph; + +#pragma clang loop unroll(full) + for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) { + acc += ipw[i]; + } + + iph->check = pkt_checksum_fold(acc); +} + +static bool pkt_skip_ipv6_extension_headers(buf_t *pkt, + const struct ipv6hdr *ipv6, + uint8_t *upper_proto, + bool *is_fragment) +{ + /* We understand five extension headers. + * https://tools.ietf.org/html/rfc8200#section-4.1 states that all + * headers should occur once, except Destination Options, which may + * occur twice. Hence we give up after 6 headers. + */ + struct { + uint8_t next; + uint8_t len; + } exthdr = { + .next = ipv6->nexthdr, + }; + *is_fragment = false; + +#pragma clang loop unroll(full) + for (int i = 0; i < 6; i++) { + switch (exthdr.next) { + case IPPROTO_FRAGMENT: + *is_fragment = true; + /* NB: We don't check that hdrlen == 0 as per spec. */ + /* fallthrough; */ + + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + case IPPROTO_MH: + if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) { + return false; + } + + /* hdrlen is in 8-octet units, and excludes the first 8 octets. */ + if (!buf_skip(pkt, + (exthdr.len + 1) * 8 - sizeof(exthdr))) { + return false; + } + + /* Decode next header */ + break; + + default: + /* The next header is not one of the known extension + * headers, treat it as the upper layer header. + * + * This handles IPPROTO_NONE. + * + * Encapsulating Security Payload (50) and Authentication + * Header (51) also end up here (and will trigger an + * unknown proto error later). They have a custom header + * format and seem too esoteric to care about. + */ + *upper_proto = exthdr.next; + return true; + } + } + + /* We never found an upper layer header. */ + return false; +} + +/* This function has to be inlined, because the verifier otherwise rejects it + * due to returning a pointer to the stack. This is technically correct, since + * scratch is allocated on the stack. However, this usage should be safe since + * it's the callers stack after all. + */ +static inline __attribute__((__always_inline__)) struct ipv6hdr * +pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto, + bool *is_fragment) +{ + struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch); + if (ipv6 == NULL) { + return NULL; + } + + if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) { + return NULL; + } + + return ipv6; +} + +/* Global metrics, per CPU + */ +struct bpf_map_def metrics_map SEC("maps") = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(unsigned int), + .value_size = sizeof(metrics_t), + .max_entries = 1, +}; + +static metrics_t *get_global_metrics(void) +{ + uint64_t key = 0; + return bpf_map_lookup_elem(&metrics_map, &key); +} + +static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = payload_off - sizeof(struct ethhdr); + + // Changing the ethertype if the encapsulated packet is ipv6 + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + encap->eth.h_proto = bpf_htons(ETH_P_IPV6); + } + + if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + metrics->forwarded_packets_total_gre++; + + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = + payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr); + int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead; + uint16_t proto = ETH_P_IP; + + /* Loop protection: the inner packet's TTL is decremented as a safeguard + * against any forwarding loop. As the only interesting field is the TTL + * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes + * as they handle the split packets if needed (no need for the data to be + * in the linear section). + */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + proto = ETH_P_IPV6; + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1, 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } else { + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, + 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + /* IPv4 also has a checksum to patch. While the TTL is only one byte, + * this function only works for 2 and 4 bytes arguments (the result is + * the same). + */ + rc = bpf_l3_csum_replace( + skb, payload_off + offsetof(struct iphdr, check), ttl, + ttl - 1, 2); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1, + 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } + + if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + metrics->errors_total_encap_adjust_failed++; + return TC_ACT_SHOT; + } + + if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL); + if (encap_gre == NULL) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre->ip.protocol = IPPROTO_GRE; + encap_gre->ip.daddr = next_hop->s_addr; + encap_gre->ip.saddr = ENCAPSULATION_IP; + encap_gre->ip.tot_len = + bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta); + encap_gre->gre.flags = 0; + encap_gre->gre.protocol = bpf_htons(proto); + pkt_ipv4_checksum((void *)&encap_gre->ip); + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + /* swap L2 addresses */ + /* This assumes that packets are received from a router. + * So just swapping the MAC addresses here will make the packet go back to + * the router, which will send it to the appropriate machine. + */ + unsigned char temp[ETH_ALEN]; + memcpy(temp, encap->eth.h_dest, sizeof(temp)); + memcpy(encap->eth.h_dest, encap->eth.h_source, + sizeof(encap->eth.h_dest)); + memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source)); + + if (encap->unigue.next_hop == encap->unigue.hop_count - 1 && + encap->unigue.last_hop_gre) { + return forward_with_gre(skb, encap, next_hop, metrics); + } + + metrics->forwarded_packets_total_gue++; + uint32_t old_saddr = encap->ip.saddr; + encap->ip.saddr = encap->ip.daddr; + encap->ip.daddr = next_hop->s_addr; + if (encap->unigue.next_hop < encap->unigue.hop_count) { + encap->unigue.next_hop++; + } + + /* Remove ip->saddr, add next_hop->s_addr */ + const uint64_t off = offsetof(typeof(*encap), ip.check); + int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4); + if (ret < 0) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t skip_next_hops(buf_t *pkt, int n) +{ + switch (n) { + case 1: + if (!buf_skip(pkt, sizeof(struct in_addr))) + return TC_ACT_SHOT; + case 0: + return CONTINUE_PROCESSING; + + default: + return TC_ACT_SHOT; + } +} + +/* Get the next hop from the GLB header. + * + * Sets next_hop->s_addr to 0 if there are no more hops left. + * pkt is positioned just after the variable length GLB header + * iff the call is successful. + */ +static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, + struct in_addr *next_hop) +{ + if (encap->unigue.next_hop > encap->unigue.hop_count) { + return TC_ACT_SHOT; + } + + /* Skip "used" next hops. */ + MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop)); + + if (encap->unigue.next_hop == encap->unigue.hop_count) { + /* No more next hops, we are at the end of the GLB header. */ + next_hop->s_addr = 0; + return CONTINUE_PROCESSING; + } + + if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) { + return TC_ACT_SHOT; + } + + /* Skip the remainig next hops (may be zero). */ + return skip_next_hops(pkt, encap->unigue.hop_count - + encap->unigue.next_hop - 1); +} + +/* Fill a bpf_sock_tuple to be used with the socket lookup functions. + * This is a kludge that let's us work around verifier limitations: + * + * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) + * + * clang will substitue a costant for sizeof, which allows the verifier + * to track it's value. Based on this, it can figure out the constant + * return value, and calling code works while still being "generic" to + * IPv4 and IPv6. + */ +static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph, + uint64_t iphlen, uint16_t sport, uint16_t dport) +{ + switch (iphlen) { + case sizeof(struct iphdr): { + struct iphdr *ipv4 = (struct iphdr *)iph; + tuple->ipv4.daddr = ipv4->daddr; + tuple->ipv4.saddr = ipv4->saddr; + tuple->ipv4.sport = sport; + tuple->ipv4.dport = dport; + return sizeof(tuple->ipv4); + } + + case sizeof(struct ipv6hdr): { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph; + memcpy(&tuple->ipv6.daddr, &ipv6->daddr, + sizeof(tuple->ipv6.daddr)); + memcpy(&tuple->ipv6.saddr, &ipv6->saddr, + sizeof(tuple->ipv6.saddr)); + tuple->ipv6.sport = sport; + tuple->ipv6.dport = dport; + return sizeof(tuple->ipv6); + } + + default: + return 0; + } +} + +static verdict_t classify_tcp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + void *iph, struct tcphdr *tcp) +{ + struct bpf_sock *sk = + bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + if (iph != NULL && tcp != NULL) { + /* Kludge: we've run out of arguments, but need the length of the ip header. */ + uint64_t iphlen = sizeof(struct iphdr); + if (tuplen == sizeof(tuple->ipv6)) { + iphlen = sizeof(struct ipv6hdr); + } + + if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp, + sizeof(*tcp)) == 0) { + bpf_sk_release(sk); + return SYN_COOKIE; + } + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_udp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen) +{ + struct bpf_sock *sk = + bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state == BPF_TCP_ESTABLISHED) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + metrics_t *metrics) +{ + switch (proto) { + case IPPROTO_TCP: + return classify_tcp(skb, tuple, tuplen, NULL, NULL); + + case IPPROTO_UDP: + return classify_udp(skb, tuple, tuplen); + + default: + metrics->errors_total_malformed_icmp++; + return INVALID; + } +} + +static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics) +{ + struct icmphdr icmp; + if (!buf_copy(pkt, &icmp, sizeof(icmp))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp.type == ICMP_ECHOREPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp.type == ICMP_ECHO) { + return ECHO_REQUEST; + } + + if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + struct iphdr _ip4; + const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + /* The source address in the outer IP header is from the entity that + * originated the ICMP message. Use the original IP header to restore + * the correct flow tuple. + */ + struct bpf_sock_tuple tuple; + tuple.ipv4.saddr = ipv4->daddr; + tuple.ipv4.daddr = ipv4->saddr; + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, ipv4->protocol, &tuple, + sizeof(tuple.ipv4), metrics); +} + +static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics) +{ + struct icmp6hdr icmp6; + if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) { + return ECHO_REQUEST; + } + + if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + bool is_fragment; + uint8_t l4_proto; + struct ipv6hdr _ipv6; + const struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + /* Swap source and dest addresses. */ + struct bpf_sock_tuple tuple; + memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr)); + memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr)); + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6), + metrics); +} + +static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_tcp++; + + struct tcphdr _tcp; + struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp); + if (tcp == NULL) { + metrics->errors_total_malformed_tcp++; + return INVALID; + } + + if (tcp->syn) { + return SYN; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest); + return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp); +} + +static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_udp++; + + struct udphdr _udp; + struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp); + if (udph == NULL) { + metrics->errors_total_malformed_udp++; + return INVALID; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest); + return classify_udp(pkt->skb, &tuple, tuplen); +} + +static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv4++; + + struct iphdr _ip4; + struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4->version != 4) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4_is_fragment(ipv4)) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (ipv4->protocol) { + case IPPROTO_ICMP: + return process_icmpv4(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv4, sizeof(*ipv4), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv6++; + + uint8_t l4_proto; + bool is_fragment; + struct ipv6hdr _ipv6; + struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv6->version != 6) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (l4_proto) { + case IPPROTO_ICMPV6: + return process_icmpv6(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv6, sizeof(*ipv6), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +SEC("classifier/cls_redirect") +int cls_redirect(struct __sk_buff *skb) +{ + metrics_t *metrics = get_global_metrics(); + if (metrics == NULL) { + return TC_ACT_SHOT; + } + + metrics->processed_packets_total++; + + /* Pass bogus packets as long as we're not sure they're + * destined for us. + */ + if (skb->protocol != bpf_htons(ETH_P_IP)) { + return TC_ACT_OK; + } + + encap_headers_t *encap; + + /* Make sure that all encapsulation headers are available in + * the linear portion of the skb. This makes it easy to manipulate them. + */ + if (bpf_skb_pull_data(skb, sizeof(*encap))) { + return TC_ACT_OK; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap = buf_assign(&pkt, sizeof(*encap), NULL); + if (encap == NULL) { + return TC_ACT_OK; + } + + if (encap->ip.ihl != 5) { + /* We never have any options. */ + return TC_ACT_OK; + } + + if (encap->ip.daddr != ENCAPSULATION_IP || + encap->ip.protocol != IPPROTO_UDP) { + return TC_ACT_OK; + } + + /* TODO Check UDP length? */ + if (encap->udp.dest != ENCAPSULATION_PORT) { + return TC_ACT_OK; + } + + /* We now know that the packet is destined to us, we can + * drop bogus ones. + */ + if (ipv4_is_fragment((void *)&encap->ip)) { + metrics->errors_total_fragmented_ip++; + return TC_ACT_SHOT; + } + + if (encap->gue.variant != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.control != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.flags != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.hlen != + sizeof(encap->unigue) / 4 + encap->unigue.hop_count) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.version != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.reserved != 0) { + return TC_ACT_SHOT; + } + + struct in_addr next_hop; + MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop)); + + if (next_hop.s_addr == 0) { + metrics->accepted_packets_total_last_hop++; + return accept_locally(skb, encap); + } + + verdict_t verdict; + switch (encap->gue.proto_ctype) { + case IPPROTO_IPIP: + verdict = process_ipv4(&pkt, metrics); + break; + + case IPPROTO_IPV6: + verdict = process_ipv6(&pkt, metrics); + break; + + default: + metrics->errors_total_unknown_l3_proto++; + return TC_ACT_SHOT; + } + + switch (verdict) { + case INVALID: + /* metrics have already been bumped */ + return TC_ACT_SHOT; + + case UNKNOWN: + return forward_to_next_hop(skb, encap, &next_hop, metrics); + + case ECHO_REQUEST: + metrics->accepted_packets_total_icmp_echo_request++; + break; + + case SYN: + if (encap->unigue.forward_syn) { + return forward_to_next_hop(skb, encap, &next_hop, + metrics); + } + + metrics->accepted_packets_total_syn++; + break; + + case SYN_COOKIE: + metrics->accepted_packets_total_syn_cookies++; + break; + + case ESTABLISHED: + metrics->accepted_packets_total_established++; + break; + } + + return accept_locally(skb, encap); +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h new file mode 100644 index 000000000000..76eab0aacba0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright 2019, 2020 Cloudflare */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> + +struct gre_base_hdr { + uint16_t flags; + uint16_t protocol; +} __attribute__((packed)); + +struct guehdr { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t hlen : 5, control : 1, variant : 2; +#else + uint8_t variant : 2, control : 1, hlen : 5; +#endif + uint8_t proto_ctype; + uint16_t flags; +}; + +struct unigue { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4; +#else + uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2; +#endif + uint8_t reserved; + uint8_t next_hop; + uint8_t hop_count; + // Next hops go here +} __attribute__((packed)); + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct gre_base_hdr gre; +} __attribute__((packed)) encap_gre_t; + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct udphdr udp; + struct guehdr gue; + struct unigue unigue; +} __attribute__((packed)) encap_headers_t; diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c new file mode 100644 index 000000000000..01a002ade529 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u64 count = 0; + +SEC("raw_tracepoint/sys_enter") +int test_enable_stats(void *ctx) +{ + count += 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c index 98b9de2fafd0..ded71b3ff6b4 100644 --- a/tools/testing/selftests/bpf/progs/test_obj_id.c +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c @@ -3,16 +3,8 @@ */ #include <stddef.h> #include <linux/bpf.h> -#include <linux/pkt_cls.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 - * not the focus here. - */ - -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); @@ -20,13 +12,13 @@ struct { __type(value, __u64); } test_map_id SEC(".maps"); -SEC("test_obj_id_dummy") -int test_obj_id(struct __sk_buff *skb) +SEC("raw_tp/sys_enter") +int test_obj_id(void *ctx) { __u32 key = 0; __u64 *value; value = bpf_map_lookup_elem(&test_map_id, &key); - return TC_ACT_OK; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index abb7344b531f..42403d088abc 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -39,4 +39,10 @@ int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) return 0; } +SEC("fmod_ret/__set_task_comm") +int BPF_PROG(prog6, struct task_struct *tsk, const char *buf, bool exec) +{ + return !tsk; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 8f530843b4da..1ecd987005d2 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -16,6 +16,26 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +/* Pin map under /sys/fs/bpf/tc/globals/<map name> */ +#define PIN_GLOBAL_NS 2 + +/* Must match struct bpf_elf_map layout from iproute2 */ +struct { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +} server_map SEC("maps") = { + .type = BPF_MAP_TYPE_SOCKMAP, + .size_key = sizeof(int), + .size_value = sizeof(__u64), + .max_elem = 1, + .pinning = PIN_GLOBAL_NS, +}; + int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; @@ -72,7 +92,9 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) { struct bpf_sock_tuple ln = {0}; struct bpf_sock *sk; + const int zero = 0; size_t tuple_len; + __be16 dport; int ret; tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); @@ -83,32 +105,11 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) if (sk) goto assign; - if (ipv4) { - if (tuple->ipv4.dport != bpf_htons(4321)) - return TC_ACT_OK; - - ln.ipv4.daddr = bpf_htonl(0x7f000001); - ln.ipv4.dport = bpf_htons(1234); - - sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv4), - BPF_F_CURRENT_NETNS, 0); - } else { - if (tuple->ipv6.dport != bpf_htons(4321)) - return TC_ACT_OK; - - /* Upper parts of daddr are already zero. */ - ln.ipv6.daddr[3] = bpf_htonl(0x1); - ln.ipv6.dport = bpf_htons(1234); - - sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv6), - BPF_F_CURRENT_NETNS, 0); - } + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; - /* workaround: We can't do a single socket lookup here, because then - * the compiler will likely spill tuple_len to the stack. This makes it - * lose all bounds information in the verifier, which then rejects the - * call as unsafe. - */ + sk = bpf_map_lookup_elem(&server_map, &zero); if (!sk) return TC_ACT_SHOT; @@ -123,7 +124,9 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) { struct bpf_sock_tuple ln = {0}; struct bpf_sock *sk; + const int zero = 0; size_t tuple_len; + __be16 dport; int ret; tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); @@ -137,32 +140,11 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) bpf_sk_release(sk); } - if (ipv4) { - if (tuple->ipv4.dport != bpf_htons(4321)) - return TC_ACT_OK; + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; - ln.ipv4.daddr = bpf_htonl(0x7f000001); - ln.ipv4.dport = bpf_htons(1234); - - sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv4), - BPF_F_CURRENT_NETNS, 0); - } else { - if (tuple->ipv6.dport != bpf_htons(4321)) - return TC_ACT_OK; - - /* Upper parts of daddr are already zero. */ - ln.ipv6.daddr[3] = bpf_htonl(0x1); - ln.ipv6.dport = bpf_htons(1234); - - sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv6), - BPF_F_CURRENT_NETNS, 0); - } - - /* workaround: We can't do a single socket lookup here, because then - * the compiler will likely spill tuple_len to the stack. This makes it - * lose all bounds information in the verifier, which then rejects the - * call as unsafe. - */ + sk = bpf_map_lookup_elem(&server_map, &zero); if (!sk) return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index 2d0b0b82a78a..50525235380e 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -45,7 +45,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx) unsigned long tcp_mem[3] = {0, 0, 0}; char value[MAX_VALUE_STR_LEN]; unsigned char i, off = 0; - int ret; + volatile int ret; if (ctx->write) return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c new file mode 100644 index 000000000000..3d66599eee2e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp_adjust_tail_grow") +int _xdp_adjust_tail_grow(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + unsigned int data_len; + int offset = 0; + + /* Data length determine test case */ + data_len = data_end - data; + + if (data_len == 54) { /* sizeof(pkt_v4) */ + offset = 4096; /* test too large offset */ + } else if (data_len == 74) { /* sizeof(pkt_v6) */ + offset = 40; + } else if (data_len == 64) { + offset = 128; + } else if (data_len == 128) { + offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + } else { + return XDP_ABORTED; /* No matching test */ + } + + if (bpf_xdp_adjust_tail(xdp, offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index b7fc85769bdc..22065a9cfb25 100644 --- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2018 Facebook +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -11,15 +11,15 @@ int _version SEC("version") = 1; -SEC("xdp_adjust_tail") -int _xdp_adjust_tail(struct xdp_md *xdp) +SEC("xdp_adjust_tail_shrink") +int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) - offset = 256; + if (data_end - data == 54) /* sizeof(pkt_v4) */ + offset = 256; /* shrink too much */ else offset = 20; if (bpf_xdp_adjust_tail(xdp, 0 - offset)) diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c new file mode 100644 index 000000000000..8b36b6640e7e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <asm/unistd.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +long hits = 0; + +SEC("tp/syscalls/sys_enter_getpgid") +int bench_trigger_tp(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) +{ + if (id == __NR_getpgid) + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("kprobe/__x64_sys_getpgid") +int bench_trigger_kprobe(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fentry/__x64_sys_getpgid") +int bench_trigger_fentry(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} + +SEC("fmod_ret/__x64_sys_getpgid") +int bench_trigger_fmodret(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return -22; +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b521e0a512b6..54fa5fa688ce 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -222,23 +222,6 @@ int test__join_cgroup(const char *path) return fd; } -struct ipv4_packet pkt_v4 = { - .eth.h_proto = __bpf_constant_htons(ETH_P_IP), - .iph.ihl = 5, - .iph.protocol = IPPROTO_TCP, - .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), - .tcp.urg_ptr = 123, - .tcp.doff = 5, -}; - -struct ipv6_packet pkt_v6 = { - .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), - .iph.nexthdr = IPPROTO_TCP, - .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), - .tcp.urg_ptr = 123, - .tcp.doff = 5, -}; - int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { struct bpf_map *map; @@ -351,25 +334,13 @@ int extract_build_id(char *build_id, size_t size) len = size; memcpy(build_id, line, len); build_id[len] = '\0'; + free(line); return 0; err: fclose(fp); return -1; } -void *spin_lock_thread(void *arg) -{ - __u32 duration, retval; - int err, prog_fd = *(u32 *) arg; - - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); - pthread_exit(arg); -} - /* extern declarations for test funcs */ #define DEFINE_TEST(name) extern void test_##name(void); #include <prog_tests/tests.h> @@ -420,6 +391,18 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } +static void free_str_set(const struct str_set *set) +{ + int i; + + if (!set) + return; + + for (i = 0; i < set->cnt; i++) + free((void *)set->strs[i]); + free(set->strs); +} + static int parse_str_list(const char *s, struct str_set *set) { char *input, *state = NULL, *next, **tmp, **strs = NULL; @@ -455,67 +438,6 @@ err: return -ENOMEM; } -int parse_num_list(const char *s, struct test_selector *sel) -{ - int i, set_len = 0, new_len, num, start = 0, end = -1; - bool *set = NULL, *tmp, parsing_end = false; - char *next; - - while (s[0]) { - errno = 0; - num = strtol(s, &next, 10); - if (errno) - return -errno; - - if (parsing_end) - end = num; - else - start = num; - - if (!parsing_end && *next == '-') { - s = next + 1; - parsing_end = true; - continue; - } else if (*next == ',') { - parsing_end = false; - s = next + 1; - end = num; - } else if (*next == '\0') { - parsing_end = false; - s = next; - end = num; - } else { - return -EINVAL; - } - - if (start > end) - return -EINVAL; - - if (end + 1 > set_len) { - new_len = end + 1; - tmp = realloc(set, new_len); - if (!tmp) { - free(set); - return -ENOMEM; - } - for (i = set_len; i < start; i++) - tmp[i] = false; - set = tmp; - set_len = new_len; - } - for (i = start; i <= end; i++) - set[i] = true; - } - - if (!set) - return -EINVAL; - - sel->num_set = set; - sel->num_set_len = set_len; - - return 0; -} - extern int extra_prog_load_log_flags; static error_t parse_arg(int key, char *arg, struct argp_state *state) @@ -529,13 +451,15 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) if (subtest_str) { *subtest_str = '\0'; if (parse_num_list(subtest_str + 1, - &env->subtest_selector)) { + &env->subtest_selector.num_set, + &env->subtest_selector.num_set_len)) { fprintf(stderr, "Failed to parse subtest numbers.\n"); return -EINVAL; } } - if (parse_num_list(arg, &env->test_selector)) { + if (parse_num_list(arg, &env->test_selector.num_set, + &env->test_selector.num_set_len)) { fprintf(stderr, "Failed to parse test numbers.\n"); return -EINVAL; } @@ -756,11 +680,11 @@ int main(int argc, char **argv) fprintf(stdout, "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_str_set(&env.test_selector.blacklist); + free_str_set(&env.test_selector.whitelist); free(env.test_selector.num_set); - free(env.subtest_selector.blacklist.strs); - free(env.subtest_selector.whitelist.strs); + free_str_set(&env.subtest_selector.blacklist); + free_str_set(&env.subtest_selector.whitelist); 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 f4aff6b8284b..f4503c926aca 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -37,6 +37,7 @@ typedef __u16 __sum16; #include "bpf_util.h" #include <bpf/bpf_endian.h> #include "trace_helpers.h" +#include "testing_helpers.h" #include "flow_dissector_load.h" enum verbosity { @@ -87,23 +88,12 @@ extern void test__skip(void); extern void test__fail(void); extern int test__join_cgroup(const char *path); -#define MAGIC_BYTES 123 - -/* ipv4 test vector */ -struct ipv4_packet { - struct ethhdr eth; - struct iphdr iph; - struct tcphdr tcp; -} __packed; -extern struct ipv4_packet pkt_v4; - -/* ipv6 test vector */ -struct ipv6_packet { - struct ethhdr eth; - struct ipv6hdr iph; - struct tcphdr tcp; -} __packed; -extern struct ipv6_packet pkt_v6; +#define PRINT_FAIL(format...) \ + ({ \ + test__fail(); \ + fprintf(stdout, "%s:FAIL:%d ", __func__, __LINE__); \ + fprintf(stdout, ##format); \ + }) #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ @@ -136,10 +126,6 @@ extern struct ipv6_packet pkt_v6; #define CHECK_ATTR(condition, tag, format...) \ _CHECK(condition, tag, tattr.duration, format) -#define MAGIC_VAL 0x1234 -#define NUM_ITER 100000 -#define VIP_NUM 5 - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -149,7 +135,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); -void *spin_lock_thread(void *arg); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 61fd95b89af8..0358814c67dc 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -677,7 +677,7 @@ static int bind4_prog_load(const struct sock_addr_test *test) uint8_t u4_addr8[4]; uint16_t u4_addr16[2]; uint32_t u4_addr32; - } ip4; + } ip4, port; struct sockaddr_in addr4_rw; if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) { @@ -685,6 +685,8 @@ static int bind4_prog_load(const struct sock_addr_test *test) return -1; } + port.u4_addr32 = htons(SERV4_PORT); + if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, (struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1) return -1; @@ -696,49 +698,65 @@ static int bind4_prog_load(const struct sock_addr_test *test) /* if (sk.family == AF_INET && */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32), /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, type)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1), BPF_JMP_A(1), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28), /* 1st_byte_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26), /* 2nd_byte_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4) + 1), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24), /* 3rd_byte_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4) + 2), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22), /* 4th_byte_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4) + 3), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20), /* 1st_half_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18), /* 2nd_half_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4) + 2), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16), - /* whole_user_ip4 == expected) { */ + /* whole_user_ip4 == expected && */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4)), BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */ + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12), + + /* 1st_byte_of_user_port == expected && */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10), + + /* 1st_half_of_user_port == expected && */ + BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8), + + /* user_port == expected) { */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_port)), + BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4), /* user_ip4 = addr4_rw.sin_addr */ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 87eaa49609a0..78a6bae56ea6 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 19 +#define MAX_NR_MAPS 20 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -86,6 +86,7 @@ struct bpf_test { int fixup_map_array_small[MAX_FIXUPS]; int fixup_sk_storage_map[MAX_FIXUPS]; int fixup_map_event_output[MAX_FIXUPS]; + int fixup_map_reuseport_array[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -637,6 +638,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_small = test->fixup_map_array_small; int *fixup_sk_storage_map = test->fixup_sk_storage_map; int *fixup_map_event_output = test->fixup_map_event_output; + int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -806,12 +808,28 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_event_output++; } while (*fixup_map_event_output); } + if (*fixup_map_reuseport_array) { + map_fds[19] = __create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + sizeof(u32), sizeof(u64), 1, 0); + do { + prog[*fixup_map_reuseport_array].imm = map_fds[19]; + fixup_map_reuseport_array++; + } while (*fixup_map_reuseport_array); + } } +struct libcap { + struct __user_cap_header_struct hdr; + struct __user_cap_data_struct data[2]; +}; + static int set_admin(bool admin) { cap_t caps; - const cap_value_t cap_val = CAP_SYS_ADMIN; + /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ + const cap_value_t cap_net_admin = CAP_NET_ADMIN; + const cap_value_t cap_sys_admin = CAP_SYS_ADMIN; + struct libcap *cap; int ret = -1; caps = cap_get_proc(); @@ -819,11 +837,26 @@ static int set_admin(bool admin) perror("cap_get_proc"); return -1; } - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val, + cap = (struct libcap *)caps; + if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) { + perror("cap_set_flag clear admin"); + goto out; + } + if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin, admin ? CAP_SET : CAP_CLEAR)) { - perror("cap_set_flag"); + perror("cap_set_flag set_or_clear net"); goto out; } + /* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON, + * so update effective bits manually + */ + if (admin) { + cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32); + cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32); + } else { + cap->data[1].effective &= ~(1 << (38 - 32)); + cap->data[1].effective &= ~(1 << (39 - 32)); + } if (cap_set_proc(caps)) { perror("cap_set_proc"); goto out; @@ -943,7 +976,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv, attr.insns = prog; attr.insns_cnt = prog_len; attr.license = "GPL"; - attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4; + if (verbose) + attr.log_level = 1; + else if (expected_ret == VERBOSE_ACCEPT) + attr.log_level = 2; + else + attr.log_level = 4; attr.prog_flags = pflags; fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); @@ -1052,9 +1090,11 @@ fail_log: static bool is_admin(void) { + cap_flag_value_t net_priv = CAP_CLEAR; + bool perfmon_priv = false; + bool bpf_priv = false; + struct libcap *cap; cap_t caps; - cap_flag_value_t sysadmin = CAP_CLEAR; - const cap_value_t cap_val = CAP_SYS_ADMIN; #ifdef CAP_IS_SUPPORTED if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { @@ -1067,11 +1107,14 @@ static bool is_admin(void) perror("cap_get_proc"); return false; } - if (cap_get_flag(caps, cap_val, CAP_EFFECTIVE, &sysadmin)) - perror("cap_get_flag"); + cap = (struct libcap *)caps; + bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32)); + perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32)); + if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv)) + perror("cap_get_flag NET"); if (cap_free(caps)) perror("cap_free"); - return (sysadmin == CAP_SET); + return bpf_priv && perfmon_priv && net_priv == CAP_SET; } static void get_unpriv_disabled() diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c new file mode 100644 index 000000000000..0af6337a8962 --- /dev/null +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook, Inc. */ +#include <stdlib.h> +#include <errno.h> +#include "testing_helpers.h" + +int parse_num_list(const char *s, bool **num_set, int *num_set_len) +{ + int i, set_len = 0, new_len, num, start = 0, end = -1; + bool *set = NULL, *tmp, parsing_end = false; + char *next; + + while (s[0]) { + errno = 0; + num = strtol(s, &next, 10); + if (errno) + return -errno; + + if (parsing_end) + end = num; + else + start = num; + + if (!parsing_end && *next == '-') { + s = next + 1; + parsing_end = true; + continue; + } else if (*next == ',') { + parsing_end = false; + s = next + 1; + end = num; + } else if (*next == '\0') { + parsing_end = false; + s = next; + end = num; + } else { + return -EINVAL; + } + + if (start > end) + return -EINVAL; + + if (end + 1 > set_len) { + new_len = end + 1; + tmp = realloc(set, new_len); + if (!tmp) { + free(set); + return -ENOMEM; + } + for (i = set_len; i < start; i++) + tmp[i] = false; + set = tmp; + set_len = new_len; + } + for (i = start; i <= end; i++) + set[i] = true; + } + + if (!set) + return -EINVAL; + + *num_set = set; + *num_set_len = set_len; + + return 0; +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h new file mode 100644 index 000000000000..923b51762759 --- /dev/null +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (C) 2020 Facebook, Inc. */ +#include <stdbool.h> + +int parse_num_list(const char *s, bool **set, int *set_len); diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 2d752c4f8d9d..7629a0cebb9b 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -19,7 +19,7 @@ BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 1, @@ -315,7 +315,7 @@ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "allowed for root only", + .errstr_unpriv = "allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = POINTER_VALUE, @@ -346,7 +346,7 @@ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), BPF_EXIT_INSN(), }, - .errstr_unpriv = "allowed for root only", + .errstr_unpriv = "allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = TEST_DATA_LEN + TEST_DATA_LEN - ETH_HLEN - ETH_HLEN, @@ -397,7 +397,7 @@ BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .fixup_map_hash_48b = { 3 }, .result_unpriv = REJECT, .result = ACCEPT, @@ -1064,7 +1064,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "allowed for root only", + .errstr_unpriv = "allowed for", .result_unpriv = REJECT, .errstr = "R0 !read_ok", .result = REJECT, @@ -1977,7 +1977,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, }, @@ -2003,7 +2003,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .errstr = "!read_ok", .result = REJECT, }, @@ -2028,7 +2028,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .errstr = "!read_ok", .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c index 50a8a63be4ac..5cf361d8eb1c 100644 --- a/tools/testing/selftests/bpf/verifier/dead_code.c +++ b/tools/testing/selftests/bpf/verifier/dead_code.c @@ -85,7 +85,7 @@ BPF_MOV64_IMM(BPF_REG_0, 12), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, @@ -103,7 +103,7 @@ BPF_MOV64_IMM(BPF_REG_0, 12), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, @@ -121,7 +121,7 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, @@ -137,7 +137,7 @@ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -152,7 +152,7 @@ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr_unpriv = "function calls to other bpf functions are allowed for", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 130553e19eca..99f8f582c02b 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -92,3 +92,27 @@ .result = ACCEPT, .retval = 1, }, +{ + "perfevent for cgroup dev", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_DEVICE, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sysctl", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sockopt", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c index da7a4b37cb98..fc4e301260f6 100644 --- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c +++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c @@ -1,34 +1,4 @@ { - "prevent map lookup in sockmap", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_sockmap = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_SOCK_OPS, -}, -{ - "prevent map lookup in sockhash", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_sockhash = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_SOCK_OPS, -}, -{ "prevent map lookup in stack trace", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 9ed192e14f5f..0bc51ad9e0fb 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -516,3 +516,118 @@ .prog_type = BPF_PROG_TYPE_XDP, .result = ACCEPT, }, +{ + "bpf_map_lookup_elem(sockmap, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = REJECT, + .errstr = "Unreleased reference id=2 alloc_insn=5", +}, +{ + "bpf_map_lookup_elem(sockhash, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_sockhash = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = REJECT, + .errstr = "Unreleased reference id=2 alloc_insn=5", +}, +{ + "bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = ACCEPT, +}, +{ + "bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_map_sockhash = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_reuseport_array = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, sockmap, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, sockhash, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 68c80d0ec1ec..9241250c5921 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -7,6 +7,10 @@ ALL_TESTS=" shared_block_drop_test egress_redirect_test multi_mirror_test + matchall_sample_egress_test + matchall_mirror_behind_flower_ingress_test + matchall_sample_behind_flower_ingress_test + matchall_mirror_behind_flower_egress_test " NUM_NETIFS=2 @@ -155,6 +159,134 @@ multi_mirror_test() log_test "multi mirror" } +matchall_sample_egress_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have matchall with sample action + # bound on egress + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol all pref 1 handle 101 \ + matchall skip_sw action sample rate 100 group 1 + check_err $? "Failed to add rule with sample action on ingress" + + tc filter del dev $swp1 ingress protocol all pref 1 handle 101 matchall + + tc filter add dev $swp1 egress protocol all pref 1 handle 101 \ + matchall skip_sw action sample rate 100 group 1 + check_fail $? "Incorrect success to add rule with sample action on egress" + + tc qdisc del dev $swp1 clsact + + log_test "matchall sample egress" +} + +matchall_behind_flower_ingress_test() +{ + local action=$1 + local action_args=$2 + + RET=0 + + # On ingress, all matchall-mirror and matchall-sample + # rules have to be in front of the flower rules + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol ip pref 10 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + + tc filter add dev $swp1 ingress protocol all pref 9 handle 102 \ + matchall skip_sw action $action_args + check_err $? "Failed to add matchall rule in front of a flower rule" + + tc filter del dev $swp1 ingress protocol all pref 9 handle 102 matchall + + tc filter add dev $swp1 ingress protocol all pref 11 handle 102 \ + matchall skip_sw action $action_args + check_fail $? "Incorrect success to add matchall rule behind a flower rule" + + tc filter del dev $swp1 ingress protocol ip pref 10 handle 101 flower + + tc filter add dev $swp1 ingress protocol all pref 9 handle 102 \ + matchall skip_sw action $action_args + + tc filter add dev $swp1 ingress protocol ip pref 10 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add flower rule behind a matchall rule" + + tc filter del dev $swp1 ingress protocol ip pref 10 handle 101 flower + + tc filter add dev $swp1 ingress protocol ip pref 8 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_fail $? "Incorrect success to add flower rule in front of a matchall rule" + + tc qdisc del dev $swp1 clsact + + log_test "matchall $action flower ingress" +} + +matchall_mirror_behind_flower_ingress_test() +{ + matchall_behind_flower_ingress_test "mirror" "mirred egress mirror dev $swp2" +} + +matchall_sample_behind_flower_ingress_test() +{ + matchall_behind_flower_ingress_test "sample" "sample rate 100 group 1" +} + +matchall_behind_flower_egress_test() +{ + local action=$1 + local action_args=$2 + + RET=0 + + # On egress, all matchall-mirror rules have to be behind the flower rules + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 egress protocol ip pref 10 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + + tc filter add dev $swp1 egress protocol all pref 11 handle 102 \ + matchall skip_sw action $action_args + check_err $? "Failed to add matchall rule in front of a flower rule" + + tc filter del dev $swp1 egress protocol all pref 11 handle 102 matchall + + tc filter add dev $swp1 egress protocol all pref 9 handle 102 \ + matchall skip_sw action $action_args + check_fail $? "Incorrect success to add matchall rule behind a flower rule" + + tc filter del dev $swp1 egress protocol ip pref 10 handle 101 flower + + tc filter add dev $swp1 egress protocol all pref 11 handle 102 \ + matchall skip_sw action $action_args + + tc filter add dev $swp1 egress protocol ip pref 10 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add flower rule behind a matchall rule" + + tc filter del dev $swp1 egress protocol ip pref 10 handle 101 flower + + tc filter add dev $swp1 egress protocol ip pref 12 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_fail $? "Incorrect success to add flower rule in front of a matchall rule" + + tc qdisc del dev $swp1 clsact + + log_test "matchall $action flower egress" +} + +matchall_mirror_behind_flower_egress_test() +{ + matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2" +} + setup_prepare() { swp1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 9f9741444549..de4b32fc4223 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -146,11 +146,39 @@ regions_test() check_region_snapshot_count dummy post-first-request 3 + devlink region dump $DL_HANDLE/dummy snapshot 25 >> /dev/null + check_err $? "Failed to dump snapshot with id 25" + + devlink region read $DL_HANDLE/dummy snapshot 25 addr 0 len 1 >> /dev/null + check_err $? "Failed to read snapshot with id 25 (1 byte)" + + devlink region read $DL_HANDLE/dummy snapshot 25 addr 128 len 128 >> /dev/null + check_err $? "Failed to read snapshot with id 25 (128 bytes)" + + devlink region read $DL_HANDLE/dummy snapshot 25 addr 128 len $((1<<32)) >> /dev/null + check_err $? "Failed to read snapshot with id 25 (oversized)" + + devlink region read $DL_HANDLE/dummy snapshot 25 addr $((1<<32)) len 128 >> /dev/null 2>&1 + check_fail $? "Bad read of snapshot with id 25 did not fail" + devlink region del $DL_HANDLE/dummy snapshot 25 check_err $? "Failed to delete snapshot with id 25" check_region_snapshot_count dummy post-second-delete 2 + sid=$(devlink -j region new $DL_HANDLE/dummy | jq '.[][][][]') + check_err $? "Failed to create a new snapshot with id allocated by the kernel" + + check_region_snapshot_count dummy post-first-request 3 + + devlink region dump $DL_HANDLE/dummy snapshot $sid >> /dev/null + check_err $? "Failed to dump a snapshot with id allocated by the kernel" + + devlink region del $DL_HANDLE/dummy snapshot $sid + check_err $? "Failed to delete snapshot with id allocated by the kernel" + + check_region_snapshot_count dummy post-first-request 2 + log_test "regions test" } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 2bb8c81fc0b4..c9f03ef93338 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -168,9 +168,17 @@ #define __TEST_IMPL(test_name, _signal) \ static void test_name(struct __test_metadata *_metadata); \ + static inline void wrapper_##test_name( \ + struct __test_metadata *_metadata, \ + struct __fixture_variant_metadata *variant) \ + { \ + test_name(_metadata); \ + } \ static struct __test_metadata _##test_name##_object = \ - { .name = "global." #test_name, \ - .fn = &test_name, .termsig = _signal, \ + { .name = #test_name, \ + .fn = &wrapper_##test_name, \ + .fixture = &_fixture_global, \ + .termsig = _signal, \ .timeout = TEST_TIMEOUT_DEFAULT, }; \ static void __attribute__((constructor)) _register_##test_name(void) \ { \ @@ -212,10 +220,13 @@ * populated and cleaned up using FIXTURE_SETUP() and FIXTURE_TEARDOWN(). */ #define FIXTURE(fixture_name) \ + FIXTURE_VARIANT(fixture_name); \ + static struct __fixture_metadata _##fixture_name##_fixture_object = \ + { .name = #fixture_name, }; \ static void __attribute__((constructor)) \ _register_##fixture_name##_data(void) \ { \ - __fixture_count++; \ + __register_fixture(&_##fixture_name##_fixture_object); \ } \ FIXTURE_DATA(fixture_name) @@ -241,7 +252,10 @@ #define FIXTURE_SETUP(fixture_name) \ void fixture_name##_setup( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) + /** * FIXTURE_TEARDOWN(fixture_name) * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. @@ -264,6 +278,59 @@ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) /** + * FIXTURE_VARIANT(fixture_name) - Optionally called once per fixture + * to declare fixture variant + * + * @fixture_name: fixture name + * + * .. code-block:: c + * + * FIXTURE_VARIANT(datatype name) { + * type property1; + * ... + * }; + * + * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() + * as *variant*. Variants allow the same tests to be run with different + * arguments. + */ +#define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name + +/** + * FIXTURE_VARIANT_ADD(fixture_name, variant_name) - Called once per fixture + * variant to setup and register the data + * + * @fixture_name: fixture name + * @variant_name: name of the parameter set + * + * .. code-block:: c + * + * FIXTURE_ADD(datatype name) { + * .property1 = val1; + * ... + * }; + * + * Defines a variant of the test fixture, provided to FIXTURE_SETUP() and + * TEST_F() as *variant*. Tests of each fixture will be run once for each + * variant. + */ +#define FIXTURE_VARIANT_ADD(fixture_name, variant_name) \ + extern FIXTURE_VARIANT(fixture_name) \ + _##fixture_name##_##variant_name##_variant; \ + static struct __fixture_variant_metadata \ + _##fixture_name##_##variant_name##_object = \ + { .name = #variant_name, \ + .data = &_##fixture_name##_##variant_name##_variant}; \ + static void __attribute__((constructor)) \ + _register_##fixture_name##_##variant_name(void) \ + { \ + __register_fixture_variant(&_##fixture_name##_fixture_object, \ + &_##fixture_name##_##variant_name##_object); \ + } \ + FIXTURE_VARIANT(fixture_name) \ + _##fixture_name##_##variant_name##_variant = + +/** * TEST_F(fixture_name, test_name) - Emits test registration and helpers for * fixture-based test cases * @@ -293,24 +360,27 @@ #define __TEST_F_IMPL(fixture_name, test_name, signal, tmout) \ static void fixture_name##_##test_name( \ struct __test_metadata *_metadata, \ - FIXTURE_DATA(fixture_name) *self); \ + FIXTURE_DATA(fixture_name) *self, \ + const FIXTURE_VARIANT(fixture_name) *variant); \ static inline void wrapper_##fixture_name##_##test_name( \ - struct __test_metadata *_metadata) \ + struct __test_metadata *_metadata, \ + struct __fixture_variant_metadata *variant) \ { \ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self); \ + fixture_name##_setup(_metadata, &self, variant->data); \ /* Let setup failure terminate early. */ \ if (!_metadata->passed) \ return; \ - fixture_name##_##test_name(_metadata, &self); \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ fixture_name##_teardown(_metadata, &self); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ - .name = #fixture_name "." #test_name, \ + .name = #test_name, \ .fn = &wrapper_##fixture_name##_##test_name, \ + .fixture = &_##fixture_name##_fixture_object, \ .termsig = signal, \ .timeout = tmout, \ }; \ @@ -321,7 +391,9 @@ } \ static void fixture_name##_##test_name( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * TEST_HARNESS_MAIN - Simple wrapper to run the test harness @@ -631,11 +703,74 @@ } \ } while (0); OPTIONAL_HANDLER(_assert) +/* List helpers */ +#define __LIST_APPEND(head, item) \ +{ \ + /* Circular linked list where only prev is circular. */ \ + if (head == NULL) { \ + head = item; \ + item->next = NULL; \ + item->prev = item; \ + return; \ + } \ + if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { \ + item->next = NULL; \ + item->prev = head->prev; \ + item->prev->next = item; \ + head->prev = item; \ + } else { \ + item->next = head; \ + item->next->prev = item; \ + item->prev = item; \ + head = item; \ + } \ +} + +struct __test_metadata; +struct __fixture_variant_metadata; + +/* Contains all the information about a fixture. */ +struct __fixture_metadata { + const char *name; + struct __test_metadata *tests; + struct __fixture_variant_metadata *variant; + struct __fixture_metadata *prev, *next; +} _fixture_global __attribute__((unused)) = { + .name = "global", + .prev = &_fixture_global, +}; + +static struct __fixture_metadata *__fixture_list = &_fixture_global; +static int __constructor_order; + +#define _CONSTRUCTOR_ORDER_FORWARD 1 +#define _CONSTRUCTOR_ORDER_BACKWARD -1 + +static inline void __register_fixture(struct __fixture_metadata *f) +{ + __LIST_APPEND(__fixture_list, f); +} + +struct __fixture_variant_metadata { + const char *name; + const void *data; + struct __fixture_variant_metadata *prev, *next; +}; + +static inline void +__register_fixture_variant(struct __fixture_metadata *f, + struct __fixture_variant_metadata *variant) +{ + __LIST_APPEND(f->variant, variant); +} + /* Contains all the information for test execution and status checking. */ struct __test_metadata { const char *name; - void (*fn)(struct __test_metadata *); + void (*fn)(struct __test_metadata *, + struct __fixture_variant_metadata *); pid_t pid; /* pid of test when being run */ + struct __fixture_metadata *fixture; int termsig; int passed; int trigger; /* extra handler after the evaluation */ @@ -646,15 +781,6 @@ struct __test_metadata { struct __test_metadata *prev, *next; }; -/* Storage for the (global) tests to be run. */ -static struct __test_metadata *__test_list; -static unsigned int __test_count; -static unsigned int __fixture_count; -static int __constructor_order; - -#define _CONSTRUCTOR_ORDER_FORWARD 1 -#define _CONSTRUCTOR_ORDER_BACKWARD -1 - /* * Since constructors are called in reverse order, reverse the test * list so tests are run in source declaration order. @@ -666,25 +792,7 @@ static int __constructor_order; */ static inline void __register_test(struct __test_metadata *t) { - __test_count++; - /* Circular linked list where only prev is circular. */ - if (__test_list == NULL) { - __test_list = t; - t->next = NULL; - t->prev = t; - return; - } - if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { - t->next = NULL; - t->prev = __test_list->prev; - t->prev->next = t; - __test_list->prev = t; - } else { - t->next = __test_list; - t->next->prev = t; - t->prev = t; - __test_list = t; - } + __LIST_APPEND(t->fixture->tests, t); } static inline int __bail(int for_realz, bool no_print, __u8 step) @@ -790,43 +898,67 @@ void __wait_for_test(struct __test_metadata *t) } } -void __run_test(struct __test_metadata *t) +void __run_test(struct __fixture_metadata *f, + struct __fixture_variant_metadata *variant, + struct __test_metadata *t) { + /* reset test struct */ t->passed = 1; t->trigger = 0; - printf("[ RUN ] %s\n", t->name); + t->step = 0; + t->no_print = 0; + + printf("[ RUN ] %s%s%s.%s\n", + f->name, variant->name[0] ? "." : "", variant->name, t->name); t->pid = fork(); if (t->pid < 0) { printf("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { - t->fn(t); + t->fn(t, variant); /* return the step that failed or 0 */ _exit(t->passed ? 0 : t->step); } else { __wait_for_test(t); } - printf("[ %4s ] %s\n", (t->passed ? "OK" : "FAIL"), t->name); + printf("[ %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"), + f->name, variant->name[0] ? "." : "", variant->name, t->name); } static int test_harness_run(int __attribute__((unused)) argc, char __attribute__((unused)) **argv) { + struct __fixture_variant_metadata no_variant = { .name = "", }; + struct __fixture_variant_metadata *v; + struct __fixture_metadata *f; struct __test_metadata *t; int ret = 0; + unsigned int case_count = 0, test_count = 0; unsigned int count = 0; unsigned int pass_count = 0; + for (f = __fixture_list; f; f = f->next) { + for (v = f->variant ?: &no_variant; v; v = v->next) { + case_count++; + for (t = f->tests; t; t = t->next) + test_count++; + } + } + /* TODO(wad) add optional arguments similar to gtest. */ printf("[==========] Running %u tests from %u test cases.\n", - __test_count, __fixture_count + 1); - for (t = __test_list; t; t = t->next) { - count++; - __run_test(t); - if (t->passed) - pass_count++; - else - ret = 1; + test_count, case_count); + for (f = __fixture_list; f; f = f->next) { + for (v = f->variant ?: &no_variant; v; v = v->next) { + for (t = f->tests; t; t = t->next) { + count++; + __run_test(f, v, t); + if (t->passed) + pass_count++; + else + ret = 1; + } + } } printf("[==========] %u / %u tests passed.\n", pass_count, count); printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3f386eb9e7d7..895ec992b2f1 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -16,6 +16,7 @@ TEST_PROGS += altnames.sh icmp_redirect.sh ip6_gre_headroom.sh TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh +TEST_PROGS += vrf-xfrm-tests.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 6560ed796ac4..dd0e5fec6367 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -19,8 +19,8 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime" -IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime" +IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime ipv4_compat_mode" +IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime ipv6_compat_mode" ALL_TESTS="basic ${IPV4_TESTS} ${IPV6_TESTS}" TESTS="${ALL_TESTS}" @@ -150,31 +150,31 @@ setup() $IP li add veth1 type veth peer name veth2 $IP li set veth1 up $IP addr add 172.16.1.1/24 dev veth1 - $IP -6 addr add 2001:db8:91::1/64 dev veth1 + $IP -6 addr add 2001:db8:91::1/64 dev veth1 nodad $IP li add veth3 type veth peer name veth4 $IP li set veth3 up $IP addr add 172.16.2.1/24 dev veth3 - $IP -6 addr add 2001:db8:92::1/64 dev veth3 + $IP -6 addr add 2001:db8:92::1/64 dev veth3 nodad $IP li set veth2 netns peer up ip -netns peer addr add 172.16.1.2/24 dev veth2 - ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 + ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad $IP li set veth4 netns peer up ip -netns peer addr add 172.16.2.2/24 dev veth4 - ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 + ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad ip -netns remote li add veth5 type veth peer name veth6 ip -netns remote li set veth5 up ip -netns remote addr add dev veth5 172.16.101.1/24 - ip -netns remote addr add dev veth5 2001:db8:101::1/64 + ip -netns remote -6 addr add dev veth5 2001:db8:101::1/64 nodad ip -netns remote ro add 172.16.0.0/22 via 172.16.101.2 ip -netns remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2 ip -netns remote li set veth6 netns peer up ip -netns peer addr add dev veth6 172.16.101.2/24 - ip -netns peer addr add dev veth6 2001:db8:101::2/64 + ip -netns peer -6 addr add dev veth6 2001:db8:101::2/64 nodad set +e } @@ -248,11 +248,38 @@ check_route6() local expected="$2" local out - out=$($IP -6 route ls match ${pfx} 2>/dev/null) + out=$($IP -6 route ls match ${pfx} 2>/dev/null | sed -e 's/pref medium//') check_output "${out}" "${expected}" } +start_ip_monitor() +{ + local mtype=$1 + + # start the monitor in the background + tmpfile=`mktemp /var/run/nexthoptestXXX` + mpid=`($IP monitor $mtype > $tmpfile & echo $!) 2>/dev/null` + sleep 0.2 + echo "$mpid $tmpfile" +} + +stop_ip_monitor() +{ + local mpid=$1 + local tmpfile=$2 + local el=$3 + + # check the monitor results + kill $mpid + lines=`wc -l $tmpfile | cut "-d " -f1` + test $lines -eq $el + rc=$? + rm -rf $tmpfile + + return $rc +} + ################################################################################ # basic operations (add, delete, replace) on nexthops and nexthop groups # @@ -423,8 +450,6 @@ ipv6_fcnal_runtime() echo "IPv6 functional runtime" echo "-----------------------" - sleep 5 - # # IPv6 - the basics # @@ -481,12 +506,12 @@ ipv6_fcnal_runtime() run_cmd "$IP -6 nexthop add id 85 dev veth1" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85" log_test $? 0 "IPv6 route with device only nexthop" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024" run_cmd "$IP nexthop add id 123 group 81/85" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123" log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1" # # IPv6 route with v4 nexthop - not allowed @@ -866,6 +891,11 @@ ipv4_fcnal_runtime() $IP neigh sh | grep 'dev veth1' fi + run_cmd "$IP ro del 172.16.101.1/32 via inet6 ${lladdr} dev veth1" + run_cmd "$IP -4 ro add default via inet6 ${lladdr} dev veth1" + run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" + log_test $? 0 "IPv4 default route with IPv6 gateway" + # # MPLS as an example of LWT encap # @@ -880,6 +910,173 @@ ipv4_fcnal_runtime() log_test $? 0 "IPv4 route with MPLS encap, v6 gw - check" } +sysctl_nexthop_compat_mode_check() +{ + local sysctlname="net.ipv4.nexthop_compat_mode" + local lprefix=$1 + + IPE="ip netns exec me" + + $IPE sysctl -q $sysctlname 2>&1 >/dev/null + if [ $? -ne 0 ]; then + echo "SKIP: kernel lacks nexthop compat mode sysctl control" + return $ksft_skip + fi + + out=$($IPE sysctl $sysctlname 2>/dev/null) + log_test $? 0 "$lprefix default nexthop compat mode check" + check_output "${out}" "$sysctlname = 1" +} + +sysctl_nexthop_compat_mode_set() +{ + local sysctlname="net.ipv4.nexthop_compat_mode" + local mode=$1 + local lprefix=$2 + + IPE="ip netns exec me" + + out=$($IPE sysctl -w $sysctlname=$mode) + log_test $? 0 "$lprefix set compat mode - $mode" + check_output "${out}" "net.ipv4.nexthop_compat_mode = $mode" +} + +ipv6_compat_mode() +{ + local rc + + echo + echo "IPv6 nexthop api compat mode test" + echo "--------------------------------" + + sysctl_nexthop_compat_mode_check "IPv6" + if [ $? -eq $ksft_skip ]; then + return $ksft_skip + fi + + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 122 group 62/63" + ipmout=$(start_ip_monitor route) + + run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122" + # route add notification should contain expanded nexthops + stop_ip_monitor $ipmout 3 + log_test $? 0 "IPv6 compat mode on - route add notification" + + # route dump should contain expanded nexthops + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024 pref medium nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop via 2001:db8:91::3 dev veth1 weight 1" + log_test $? 0 "IPv6 compat mode on - route dump" + + # change in nexthop group should generate route notification + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop replace id 122 group 62/64" + stop_ip_monitor $ipmout 3 + + log_test $? 0 "IPv6 compat mode on - nexthop change" + + # set compat mode off + sysctl_nexthop_compat_mode_set 0 "IPv6" + + run_cmd "$IP -6 ro del 2001:db8:101::1/128 nhid 122" + + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 122 group 62/63" + ipmout=$(start_ip_monitor route) + + run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122" + # route add notification should not contain expanded nexthops + stop_ip_monitor $ipmout 1 + log_test $? 0 "IPv6 compat mode off - route add notification" + + # route dump should not contain expanded nexthops + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024 pref medium" + log_test $? 0 "IPv6 compat mode off - route dump" + + # change in nexthop group should not generate route notification + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop replace id 122 group 62/64" + stop_ip_monitor $ipmout 0 + log_test $? 0 "IPv6 compat mode off - nexthop change" + + # nexthop delete should not generate route notification + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop del id 122" + stop_ip_monitor $ipmout 0 + log_test $? 0 "IPv6 compat mode off - nexthop delete" + + # set compat mode back on + sysctl_nexthop_compat_mode_set 1 "IPv6" +} + +ipv4_compat_mode() +{ + local rc + + echo + echo "IPv4 nexthop api compat mode" + echo "----------------------------" + + sysctl_nexthop_compat_mode_check "IPv4" + if [ $? -eq $ksft_skip ]; then + return $ksft_skip + fi + + run_cmd "$IP nexthop add id 21 via 172.16.1.2 dev veth1" + run_cmd "$IP nexthop add id 22 via 172.16.1.2 dev veth1" + run_cmd "$IP nexthop add id 122 group 21/22" + ipmout=$(start_ip_monitor route) + + run_cmd "$IP ro add 172.16.101.1/32 nhid 122" + stop_ip_monitor $ipmout 3 + + # route add notification should contain expanded nexthops + log_test $? 0 "IPv4 compat mode on - route add notification" + + # route dump should contain expanded nexthops + check_route "172.16.101.1" "172.16.101.1 nhid 122 nexthop via 172.16.1.2 dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" + log_test $? 0 "IPv4 compat mode on - route dump" + + # change in nexthop group should generate route notification + run_cmd "$IP nexthop add id 23 via 172.16.1.3 dev veth1" + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop replace id 122 group 21/23" + stop_ip_monitor $ipmout 3 + log_test $? 0 "IPv4 compat mode on - nexthop change" + + sysctl_nexthop_compat_mode_set 0 "IPv4" + + # cleanup + run_cmd "$IP ro del 172.16.101.1/32 nhid 122" + + ipmout=$(start_ip_monitor route) + run_cmd "$IP ro add 172.16.101.1/32 nhid 122" + stop_ip_monitor $ipmout 1 + # route add notification should not contain expanded nexthops + log_test $? 0 "IPv4 compat mode off - route add notification" + + # route dump should not contain expanded nexthops + check_route "172.16.101.1" "172.16.101.1 nhid 122" + log_test $? 0 "IPv4 compat mode off - route dump" + + # change in nexthop group should not generate route notification + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop replace id 122 group 21/22" + stop_ip_monitor $ipmout 0 + log_test $? 0 "IPv4 compat mode off - nexthop change" + + # nexthop delete should not generate route notification + ipmout=$(start_ip_monitor route) + run_cmd "$IP nexthop del id 122" + stop_ip_monitor $ipmout 0 + log_test $? 0 "IPv4 compat mode off - nexthop delete" + + sysctl_nexthop_compat_mode_set 1 "IPv4" +} + basic() { echo diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index b50081855913..1181d647f6a7 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -20,10 +20,14 @@ ALL_TESTS=" ping_ipv4 + ping_ipv6 test_ip_dsfield test_ip_dscp test_ip_ecn test_ip_dscp_ecn + test_ip6_dsfield + test_ip6_dscp + test_ip6_ecn " NUM_NETIFS=4 @@ -107,6 +111,11 @@ ping_ipv4() ping_test $h1 192.0.2.2 } +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + do_test_pedit_dsfield_common() { local pedit_locus=$1; shift @@ -228,6 +237,63 @@ test_ip_dscp_ecn() do_test_ip_dscp_ecn "dev $swp2 egress" } +do_test_ip6_dsfield() +{ + local locus=$1; shift + local dsfield + + for dsfield in 0 1 2 3 128 252 253 254 255; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $dsfield" \ + ipv6 "ip_tos $dsfield" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_dsfield() +{ + do_test_ip6_dsfield "dev $swp1 ingress" + do_test_ip6_dsfield "dev $swp2 egress" +} + +do_test_ip6_dscp() +{ + local locus=$1; shift + local dscp + + for dscp in 0 1 2 3 32 61 62 63; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $((dscp << 2)) retain 0xfc" \ + ipv6 "ip_tos $(((dscp << 2) | 1))" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_dscp() +{ + do_test_ip6_dscp "dev $swp1 ingress" + do_test_ip6_dscp "dev $swp2 egress" +} + +do_test_ip6_ecn() +{ + local locus=$1; shift + local ecn + + for ecn in 0 1 2 3; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $ecn retain 0x3" \ + ipv6 "ip_tos $((124 | $ecn))" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_ecn() +{ + do_test_ip6_ecn "dev $swp1 ingress" + do_test_ip6_ecn "dev $swp2 egress" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 813d02d1939d..d9eca227136b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -2,7 +2,8 @@ # SPDX-License-Identifier: GPL-2.0 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ - mirred_egress_mirror_test gact_trap_test" + mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ + gact_trap_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -50,6 +51,9 @@ switch_destroy() mirred_egress_test() { local action=$1 + local protocol=$2 + local classifier=$3 + local classifier_args=$4 RET=0 @@ -62,9 +66,9 @@ mirred_egress_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched without redirect rule inserted" - tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ - $tcflags dst_ip 192.0.2.2 action mirred egress $action \ - dev $swp2 + tc filter add dev $swp1 ingress protocol $protocol pref 1 handle 101 \ + $classifier $tcflags $classifier_args \ + action mirred egress $action dev $swp2 $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ -t ip -q @@ -72,10 +76,11 @@ mirred_egress_test() tc_check_packets "dev $h2 ingress" 101 1 check_err $? "Did not match incoming $action packet" - tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $swp1 ingress protocol $protocol pref 1 handle 101 \ + $classifier tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower - log_test "mirred egress $action ($tcflags)" + log_test "mirred egress $classifier $action ($tcflags)" } gact_drop_and_ok_test() @@ -187,12 +192,17 @@ cleanup() mirred_egress_redirect_test() { - mirred_egress_test "redirect" + mirred_egress_test "redirect" "ip" "flower" "dst_ip 192.0.2.2" } mirred_egress_mirror_test() { - mirred_egress_test "mirror" + mirred_egress_test "mirror" "ip" "flower" "dst_ip 192.0.2.2" +} + +matchall_mirred_egress_mirror_test() +{ + mirred_egress_test "mirror" "all" "matchall" "" } trap cleanup EXIT diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 71a62e7e35b1..77c09cd339c3 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -67,6 +67,10 @@ # Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6 # encapsulation (GUE) over IPv4/IPv6, instead of VXLAN # +# - pmtu_ipv{4,6}_ipv{4,6}_exception +# Same as pmtu_ipv4_vxlan4, but using a IPv4/IPv6 tunnel over IPv4/IPv6, +# instead of VXLAN +# # - pmtu_vti4_exception # Set up vti tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is not @@ -151,6 +155,10 @@ tests=" pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions 1 pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions 1 pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions 1 + pmtu_ipv4_ipv4_exception IPv4 over IPv4: PMTU exceptions 1 + pmtu_ipv6_ipv4_exception IPv6 over IPv4: PMTU exceptions 1 + pmtu_ipv4_ipv6_exception IPv4 over IPv6: PMTU exceptions 1 + pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1 pmtu_vti6_exception vti6: PMTU exceptions 0 pmtu_vti4_exception vti4: PMTU exceptions 0 pmtu_vti4_default_mtu vti4: default MTU assignment 0 @@ -363,6 +371,62 @@ setup_gue66() { setup_fou_or_gue 6 6 gue } +setup_ipvX_over_ipvY() { + inner=${1} + outer=${2} + + if [ "${outer}" -eq 4 ]; then + a_addr="${prefix4}.${a_r1}.1" + b_addr="${prefix4}.${b_r1}.1" + if [ "${inner}" -eq 4 ]; then + type="ipip" + mode="ipip" + else + type="sit" + mode="ip6ip" + fi + else + a_addr="${prefix6}:${a_r1}::1" + b_addr="${prefix6}:${b_r1}::1" + type="ip6tnl" + if [ "${inner}" -eq 4 ]; then + mode="ipip6" + else + mode="ip6ip6" + fi + fi + + run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2 + run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode} + + run_cmd ${ns_a} ip link set ip_a up + run_cmd ${ns_b} ip link set ip_b up + + if [ "${inner}" = "4" ]; then + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ip_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ip_b + else + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ip_a + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ip_b + fi +} + +setup_ip4ip4() { + setup_ipvX_over_ipvY 4 4 +} + +setup_ip6ip4() { + setup_ipvX_over_ipvY 6 4 +} + +setup_ip4ip6() { + setup_ipvX_over_ipvY 4 6 +} + +setup_ip6ip6() { + setup_ipvX_over_ipvY 6 6 +} + setup_namespaces() { for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 @@ -908,6 +972,64 @@ test_pmtu_ipv6_gue6_exception() { test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue } +test_pmtu_ipvX_over_ipvY_exception() { + inner=${1} + outer=${2} + ll_mtu=4000 + + setup namespaces routing ip${inner}ip${outer} || return 2 + + trace "${ns_a}" ip_a "${ns_b}" ip_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B + + if [ ${inner} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + if [ ${outer} -eq 4 ]; then + # IPv4 header + exp_mtu=$((${ll_mtu} - 20)) + else + # IPv6 header Option 4 + exp_mtu=$((${ll_mtu} - 40 - 8)) + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ip_a $((${ll_mtu} + 1000)) || return + mtu "${ns_b}" ip_b $((${ll_mtu} + 1000)) || return + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ip${inner}ip${outer} interface" +} + +test_pmtu_ipv4_ipv4_exception() { + test_pmtu_ipvX_over_ipvY_exception 4 4 +} + +test_pmtu_ipv6_ipv4_exception() { + test_pmtu_ipvX_over_ipvY_exception 6 4 +} + +test_pmtu_ipv4_ipv6_exception() { + test_pmtu_ipvX_over_ipvY_exception 4 6 +} + +test_pmtu_ipv6_ipv6_exception() { + test_pmtu_ipvX_over_ipvY_exception 6 6 +} + test_pmtu_vti4_exception() { setup namespaces veth vti4 xfrm4 || return 2 trace "${ns_a}" veth_a "${ns_b}" veth_b \ diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 0ea44d975b6c..c5282e62df75 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -101,6 +101,21 @@ FIXTURE(tls) bool notls; }; +FIXTURE_VARIANT(tls) +{ + unsigned int tls_version; +}; + +FIXTURE_VARIANT_ADD(tls, 12) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls, 13) +{ + .tls_version = TLS_1_3_VERSION, +}; + FIXTURE_SETUP(tls) { struct tls12_crypto_info_aes_gcm_128 tls12; @@ -112,7 +127,7 @@ FIXTURE_SETUP(tls) len = sizeof(addr); memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_3_VERSION; + tls12.info.version = variant->tls_version; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; addr.sin_family = AF_INET; @@ -733,7 +748,7 @@ TEST_F(tls, bidir) struct tls12_crypto_info_aes_gcm_128 tls12; memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_3_VERSION; + tls12.info.version = variant->tls_version; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, @@ -1258,78 +1273,4 @@ TEST(keysizes) { close(cfd); } -TEST(tls12) { - int fd, cfd; - bool notls; - - struct tls12_crypto_info_aes_gcm_128 tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - notls = false; - len = sizeof(addr); - - memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_2_VERSION; - tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; - - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; - - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); - - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); - - ret = getsockname(sfd, &addr, &len); - ASSERT_EQ(ret, 0); - - ret = connect(fd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - - ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!notls) { - ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, - sizeof(tls12)); - ASSERT_EQ(ret, 0); - } - - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); - - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, - sizeof(tls12)); - ASSERT_EQ(ret, 0); - } - - close(sfd); - - char const *test_str = "test_read"; - int send_len = 10; - char buf[10]; - - send_len = strlen(test_str) + 1; - EXPECT_EQ(send(fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(cfd, buf, send_len, 0), -1); - EXPECT_EQ(memcmp(buf, test_str, send_len), 0); - - close(fd); - close(cfd); -} - TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh new file mode 100755 index 000000000000..184da81f554f --- /dev/null +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -0,0 +1,436 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Various combinations of VRF with xfrms and qdisc. + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +PAUSE_ON_FAIL=no +VERBOSE=0 +ret=0 + +HOST1_4=192.168.1.1 +HOST2_4=192.168.1.2 +HOST1_6=2001:db8:1::1 +HOST2_6=2001:db8:1::2 + +XFRM1_4=10.0.1.1 +XFRM2_4=10.0.1.2 +XFRM1_6=fc00:1000::1 +XFRM2_6=fc00:1000::2 +IF_ID=123 + +VRF=red +TABLE=300 + +AUTH_1=0xd94fcfea65fddf21dc6e0d24a0253508 +AUTH_2=0xdc6e0d24a0253508d94fcfea65fddf21 +ENC_1=0xfc46c20f8048be9725930ff3fb07ac2a91f0347dffeacf62 +ENC_2=0x3fb07ac2a91f0347dffeacf62fc46c20f8048be9725930ff +SPI_1=0x02122b77 +SPI_2=0x2b770212 + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +run_cmd_host1() +{ + local cmd="$*" + local out + local rc + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out=$(eval ip netns exec host1 $cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" ]; then + if [ -n "$out" ]; then + echo + echo " $out" + fi + echo + fi + + return $rc +} + +################################################################################ +# create namespaces for hosts and sws + +create_vrf() +{ + local ns=$1 + local vrf=$2 + local table=$3 + + if [ -n "${ns}" ]; then + ns="-netns ${ns}" + fi + + ip ${ns} link add ${vrf} type vrf table ${table} + ip ${ns} link set ${vrf} up + ip ${ns} route add vrf ${vrf} unreachable default metric 8192 + ip ${ns} -6 route add vrf ${vrf} unreachable default metric 8192 + + ip ${ns} addr add 127.0.0.1/8 dev ${vrf} + ip ${ns} -6 addr add ::1 dev ${vrf} nodad + + ip ${ns} ru del pref 0 + ip ${ns} ru add pref 32765 from all lookup local + ip ${ns} -6 ru del pref 0 + ip ${ns} -6 ru add pref 32765 from all lookup local +} + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + [ -z "${addr}" ] && addr="-" + [ -z "${addr6}" ] && addr6="-" + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + local ns1arg + local ns2arg + + if [ -n "${ns1}" ]; then + ns1arg="-netns ${ns1}" + fi + if [ -n "${ns2}" ]; then + ns2arg="-netns ${ns2}" + fi + + ip ${ns1arg} li add ${ns1_dev} type veth peer name tmp + ip ${ns1arg} li set ${ns1_dev} up + ip ${ns1arg} li set tmp netns ${ns2} name ${ns2_dev} + ip ${ns2arg} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr} + ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr6} nodad + ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr6} nodad + fi +} + +################################################################################ + +cleanup() +{ + ip netns del host1 + ip netns del host2 +} + +setup() +{ + create_ns "host1" + create_ns "host2" + + connect_ns "host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \ + "host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64 + + create_vrf "host1" ${VRF} ${TABLE} + ip -netns host1 link set dev eth0 master ${VRF} +} + +cleanup_xfrm() +{ + for ns in host1 host2 + do + for x in state policy + do + ip -netns ${ns} xfrm ${x} flush + ip -6 -netns ${ns} xfrm ${x} flush + done + done +} + +setup_xfrm() +{ + local h1_4=$1 + local h2_4=$2 + local h1_6=$3 + local h2_6=$4 + local devarg="$5" + + # + # policy + # + + # host1 - IPv4 out + ip -netns host1 xfrm policy add \ + src ${h1_4} dst ${h2_4} ${devarg} dir out \ + tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel + + # host2 - IPv4 in + ip -netns host2 xfrm policy add \ + src ${h1_4} dst ${h2_4} dir in \ + tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel + + # host1 - IPv4 in + ip -netns host1 xfrm policy add \ + src ${h2_4} dst ${h1_4} ${devarg} dir in \ + tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel + + # host2 - IPv4 out + ip -netns host2 xfrm policy add \ + src ${h2_4} dst ${h1_4} dir out \ + tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel + + + # host1 - IPv6 out + ip -6 -netns host1 xfrm policy add \ + src ${h1_6} dst ${h2_6} ${devarg} dir out \ + tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel + + # host2 - IPv6 in + ip -6 -netns host2 xfrm policy add \ + src ${h1_6} dst ${h2_6} dir in \ + tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel + + # host1 - IPv6 in + ip -6 -netns host1 xfrm policy add \ + src ${h2_6} dst ${h1_6} ${devarg} dir in \ + tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel + + # host2 - IPv6 out + ip -6 -netns host2 xfrm policy add \ + src ${h2_6} dst ${h1_6} dir out \ + tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel + + # + # state + # + ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_4} dst ${h2_4} ${devarg} + + ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_4} dst ${h2_4} + + + ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_4} dst ${h1_4} ${devarg} + + ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_4} dst ${h1_4} + + + ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_6} dst ${h2_6} ${devarg} + + ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_6} dst ${h2_6} + + + ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_6} dst ${h1_6} ${devarg} + + ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_6} dst ${h1_6} +} + +cleanup_xfrm_dev() +{ + ip -netns host1 li del xfrm0 + ip -netns host2 addr del ${XFRM2_4}/24 dev eth0 + ip -netns host2 addr del ${XFRM2_6}/64 dev eth0 +} + +setup_xfrm_dev() +{ + local vrfarg="vrf ${VRF}" + + ip -netns host1 li add type xfrm dev eth0 if_id ${IF_ID} + ip -netns host1 li set xfrm0 ${vrfarg} up + ip -netns host1 addr add ${XFRM1_4}/24 dev xfrm0 + ip -netns host1 addr add ${XFRM1_6}/64 dev xfrm0 + + ip -netns host2 addr add ${XFRM2_4}/24 dev eth0 + ip -netns host2 addr add ${XFRM2_6}/64 dev eth0 + + setup_xfrm ${XFRM1_4} ${XFRM2_4} ${XFRM1_6} ${XFRM2_6} "if_id ${IF_ID}" +} + +run_tests() +{ + cleanup_xfrm + + # no IPsec + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + log_test $? 0 "IPv4 no xfrm policy" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 no xfrm policy" + + # xfrm without VRF in sel + setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + log_test $? 0 "IPv4 xfrm policy based on address" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 xfrm policy based on address" + cleanup_xfrm + + # xfrm with VRF in sel + # Known failure: ipv4 resets the flow oif after the lookup. Fix is + # not straightforward. + # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev ${VRF}" + # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + # log_test $? 0 "IPv4 xfrm policy with VRF in selector" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 xfrm policy with VRF in selector" + cleanup_xfrm + + # xfrm with enslaved device in sel + # Known failures: combined with the above, __xfrm{4,6}_selector_match + # needs to consider both l3mdev and enslaved device index. + # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev eth0" + # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + # log_test $? 0 "IPv4 xfrm policy with enslaved device in selector" + # run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + # log_test $? 0 "IPv6 xfrm policy with enslaved device in selector" + # cleanup_xfrm + + # xfrm device + setup_xfrm_dev + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${XFRM2_4} + log_test $? 0 "IPv4 xfrm policy with xfrm device" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${XFRM2_6} + log_test $? 0 "IPv6 xfrm policy with xfrm device" + cleanup_xfrm_dev +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -p Pause on fail + -v verbose mode (show commands and output) + +done +EOF +} + +################################################################################ +# main + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +cleanup 2>/dev/null +setup + +echo +echo "No qdisc on VRF device" +run_tests + +run_cmd_host1 tc qdisc add dev ${VRF} root netem delay 100ms +echo +echo "netem qdisc on VRF device" +run_tests + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} + +exit $ret diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index c0dd10257df5..da7a9dda9490 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -269,14 +269,16 @@ int main(int argc, char *argv[]) " %d programmable periodic signals\n" " %d pulse per second\n" " %d programmable pins\n" - " %d cross timestamping\n", + " %d cross timestamping\n" + " %d adjust_phase\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, caps.n_per_out, caps.pps, caps.n_pins, - caps.cross_timestamping); + caps.cross_timestamping, + caps.adjust_phase); } } diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json index f8ea6f5fa8e9..72cdc3c800a5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json @@ -1472,6 +1472,31 @@ ] }, { + "id": "94bb", + "name": "Add pedit action with LAYERED_OP ip6 traffic_class", + "category": [ + "actions", + "pedit", + "layered_op" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pedit ex munge ip6 traffic_class set 0x40 continue", + "expExitCode": "0", + "verifyCmd": "$TC actions list action pedit", + "matchPattern": "ipv6\\+0: val 04000000 mask f00fffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + }, + { "id": "6f5e", "name": "Add pedit action with LAYERED_OP ip6 flow_lbl", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 8877f7b2b809..bb543bf69d69 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -32,7 +32,7 @@ "setup": [ "$TC qdisc add dev $DEV2 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 parent ffff: handle 0xffffffff flower action ok", + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress handle 0xffffffff flower action ok", "expExitCode": "0", "verifyCmd": "$TC filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff", @@ -77,9 +77,9 @@ }, "setup": [ "$TC qdisc add dev $DEV2 ingress", - "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop" + "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop" ], - "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop", + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop", "expExitCode": "2", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -87,5 +87,43 @@ "teardown": [ "$TC qdisc del dev $DEV2 ingress" ] + }, + { + "id": "7c65", + "name": "Add flower filter and then terse dump it", + "category": [ + "filter", + "flower" + ], + "setup": [ + "$TC qdisc add dev $DEV2 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "matchPattern": "filter protocol ip pref 1 flower.*handle", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV2 ingress" + ] + }, + { + "id": "d45e", + "name": "Add flower filter and verify that terse dump doesn't output filter key", + "category": [ + "filter", + "flower" + ], + "setup": [ + "$TC qdisc add dev $DEV2 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "matchPattern": " dst_mac e4:11:22:11:4a:51", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV2 ingress" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py index 6a2bd2cf528e..995f66ce43eb 100755 --- a/tools/testing/selftests/tc-testing/tdc_batch.py +++ b/tools/testing/selftests/tc-testing/tdc_batch.py @@ -72,21 +72,21 @@ mac_prefix = args.mac_prefix def format_add_filter(device, prio, handle, skip, src_mac, dst_mac, share_action): - return ("filter add dev {} {} protocol ip parent ffff: handle {} " + return ("filter add dev {} {} protocol ip ingress handle {} " " flower {} src_mac {} dst_mac {} action drop {}".format( device, prio, handle, skip, src_mac, dst_mac, share_action)) def format_rep_filter(device, prio, handle, skip, src_mac, dst_mac, share_action): - return ("filter replace dev {} {} protocol ip parent ffff: handle {} " + return ("filter replace dev {} {} protocol ip ingress handle {} " " flower {} src_mac {} dst_mac {} action drop {}".format( device, prio, handle, skip, src_mac, dst_mac, share_action)) def format_del_filter(device, prio, handle, skip, src_mac, dst_mac, share_action): - return ("filter del dev {} {} protocol ip parent ffff: handle {} " + return ("filter del dev {} {} protocol ip ingress handle {} " "flower".format(device, prio, handle)) |