diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-07 04:39:49 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-07 04:39:49 +0300 |
| commit | 1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21 (patch) | |
| tree | dcc97181d4d187252e0cc8fdf29d9b365fa3ffd0 /tools | |
| parent | 285767604576148fc1be7fcd112e4a90eb0d6ad2 (diff) | |
| parent | 7170e6045a6a8b33f4fa5753589dc77b16198e2d (diff) | |
| download | linux-1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Add Maglev hashing scheduler to IPVS, from Inju Song.
2) Lots of new TC subsystem tests from Roman Mashak.
3) Add TCP zero copy receive and fix delayed acks and autotuning with
SO_RCVLOWAT, from Eric Dumazet.
4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
Brouer.
5) Add ttl inherit support to vxlan, from Hangbin Liu.
6) Properly separate ipv6 routes into their logically independant
components. fib6_info for the routing table, and fib6_nh for sets of
nexthops, which thus can be shared. From David Ahern.
7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
messages from XDP programs. From Nikita V. Shirokov.
8) Lots of long overdue cleanups to the r8169 driver, from Heiner
Kallweit.
9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.
10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.
11) Plumb extack down into fib_rules, from Roopa Prabhu.
12) Add Flower classifier offload support to igb, from Vinicius Costa
Gomes.
13) Add UDP GSO support, from Willem de Bruijn.
14) Add documentation for eBPF helpers, from Quentin Monnet.
15) Add TLS tx offload to mlx5, from Ilya Lesokhin.
16) Allow applications to be given the number of bytes available to read
on a socket via a control message returned from recvmsg(), from
Soheil Hassas Yeganeh.
17) Add x86_32 eBPF JIT compiler, from Wang YanQing.
18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
From Björn Töpel.
19) Remove indirect load support from all of the BPF JITs and handle
these operations in the verifier by translating them into native BPF
instead. From Daniel Borkmann.
20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.
21) Allow XDP programs to do lookups in the main kernel routing tables
for forwarding. From David Ahern.
22) Allow drivers to store hardware state into an ELF section of kernel
dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.
23) Various RACK and loss detection improvements in TCP, from Yuchung
Cheng.
24) Add TCP SACK compression, from Eric Dumazet.
25) Add User Mode Helper support and basic bpfilter infrastructure, from
Alexei Starovoitov.
26) Support ports and protocol values in RTM_GETROUTE, from Roopa
Prabhu.
27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
Brouer.
28) Add lots of forwarding selftests, from Petr Machata.
29) Add generic network device failover driver, from Sridhar Samudrala.
* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
strparser: Add __strp_unpause and use it in ktls.
rxrpc: Fix terminal retransmission connection ID to include the channel
net: hns3: Optimize PF CMDQ interrupt switching process
net: hns3: Fix for VF mailbox receiving unknown message
net: hns3: Fix for VF mailbox cannot receiving PF response
bnx2x: use the right constant
Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
enic: fix UDP rss bits
netdev-FAQ: clarify DaveM's position for stable backports
rtnetlink: validate attributes in do_setlink()
mlxsw: Add extack messages for port_{un, }split failures
netdevsim: Add extack error message for devlink reload
devlink: Add extack to reload and port_{un, }split operations
net: metrics: add proper netlink validation
ipmr: fix error path when ipmr_new_table fails
ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
net: hns3: remove unused hclgevf_cfg_func_mta_filter
netfilter: provide udp*_lib_lookup for nf_tproxy
qed*: Utilize FW 8.37.2.0
...
Diffstat (limited to 'tools')
118 files changed, 22859 insertions, 908 deletions
diff --git a/tools/bpf/bpf_exp.l b/tools/bpf/bpf_exp.l index bd83149e7be0..4da8d053d68f 100644 --- a/tools/bpf/bpf_exp.l +++ b/tools/bpf/bpf_exp.l @@ -175,7 +175,7 @@ extern void yyerror(const char *str); yylval.number = strtol(yytext, NULL, 10); return number; } -([0][0-9]+) { +([0][0-7]+) { yylval.number = strtol(yytext + 1, NULL, 8); return number; } diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore new file mode 100644 index 000000000000..d7e678c2d396 --- /dev/null +++ b/tools/bpf/bpftool/.gitignore @@ -0,0 +1,3 @@ +*.d +bpftool +FEATURE-DUMP.bpftool diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 0e4e923235b6..7b0e6d453e92 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -26,7 +26,9 @@ MAP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } +| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | +| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | +| **sendmsg4** | **sendmsg6** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -63,7 +65,17 @@ DESCRIPTION **egress** egress path of the inet socket (since 4.10); **sock_create** opening of an inet socket (since 4.10); **sock_ops** various socket operations (since 4.12); - **device** device access (since 4.15). + **device** device access (since 4.15); + **bind4** call to bind(2) for an inet4 socket (since 4.17); + **bind6** call to bind(2) for an inet6 socket (since 4.17); + **post_bind4** return from bind(2) for an inet4 socket (since 4.17); + **post_bind6** return from bind(2) for an inet6 socket (since 4.17); + **connect4** call to connect(2) for an inet4 socket (since 4.17); + **connect6** call to connect(2) for an inet6 socket (since 4.17); + **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an + unconnected udp4 socket (since 4.18); + **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an + unconnected udp6 socket (since 4.18). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 457e868bd32f..a6258bc8ec4f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -22,17 +22,19 @@ MAP COMMANDS ============= | **bpftool** **map { show | list }** [*MAP*] -| **bpftool** **map dump** *MAP* -| **bpftool** **map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] -| **bpftool** **map lookup** *MAP* **key** *BYTES* -| **bpftool** **map getnext** *MAP* [**key** *BYTES*] -| **bpftool** **map delete** *MAP* **key** *BYTES* -| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map dump** *MAP* +| **bpftool** **map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] +| **bpftool** **map lookup** *MAP* **key** *DATA* +| **bpftool** **map getnext** *MAP* [**key** *DATA*] +| **bpftool** **map delete** *MAP* **key** *DATA* +| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *DATA* := { [**hex**] *BYTES* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *VALUE* := { *BYTES* | *MAP* | *PROG* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } DESCRIPTION @@ -48,20 +50,26 @@ DESCRIPTION **bpftool map dump** *MAP* Dump all entries in a given *MAP*. - **bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] + **bpftool map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] Update map entry for a given *KEY*. *UPDATE_FLAGS* can be one of: **any** update existing entry or add if doesn't exit; **exist** update only if entry already exists; **noexist** update only if entry doesn't exist. - **bpftool map lookup** *MAP* **key** *BYTES* + If the **hex** keyword is provided in front of the bytes + sequence, the bytes are parsed as hexadeximal 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. + + **bpftool map lookup** *MAP* **key** *DATA* Lookup **key** in the map. - **bpftool map getnext** *MAP* [**key** *BYTES*] + **bpftool map getnext** *MAP* [**key** *DATA*] Get next key. If *key* is not specified, get first key. - **bpftool map delete** *MAP* **key** *BYTES* + **bpftool map delete** *MAP* **key** *DATA* Remove entry from the map. **bpftool map pin** *MAP* *FILE* @@ -69,6 +77,22 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. + **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] + 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. + By default read the number of CPUs on the system and + install perf ring for each CPU in the corresponding index + in the array. + + If **cpu** and **index** are specified, install perf ring + for given **cpu** at **index** in the array (single ring). + + Note that installing a perf ring into an array will silently + replace any existing ring. Any other application will stop + receiving events if it installed its rings earlier. + **bpftool map help** Print short help message. @@ -98,7 +122,12 @@ EXAMPLES 10: hash name some_map flags 0x0 key 4B value 8B max_entries 2048 memlock 167936B -**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** +The following three commands are equivalent: + +| +| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** +| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** +| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** **# bpftool map lookup id 10 key 0 1 2 3** diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst new file mode 100644 index 000000000000..e3eb0eab7641 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -0,0 +1,81 @@ +================ +bpftool-perf +================ +------------------------------------------------------------------------------- +tool for inspection of perf related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **perf** *COMMAND* + + *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + + *COMMANDS* := + { **show** | **list** | **help** } + +PERF COMMANDS +============= + +| **bpftool** **perf { show | list }** +| **bpftool** **perf help** + +DESCRIPTION +=========== + **bpftool perf { show | list }** + List all raw_tracepoint, tracepoint, kprobe attachment in the system. + + Output will start with process id and file descriptor in that process, + followed by bpf program id, attachment information, and attachment point. + The attachment point for raw_tracepoint/tracepoint is the trace probe name. + The attachment point for k[ret]probe is either symbol name and offset, + or a kernel virtual address. + The attachment point for u[ret]probe is the file name and the file offset. + + **bpftool perf 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**. + +EXAMPLES +======== + +| **# bpftool perf** + +:: + + pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 + pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 + pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep + pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 + +| +| **# bpftool -j perf** + +:: + + [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ + {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ + {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ + {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] + + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 67ca6c69376c..43d34a5c3ec5 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -95,7 +95,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 005a3d2123620c8b + 10: xdp name some_prog tag 005a3d2123620c8b gpl loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 @@ -108,6 +108,7 @@ EXAMPLES "id": 10, "type": "xdp", "tag": "005a3d2123620c8b", + "gpl_compatible": true, "loaded_at": "Sep 29/20:11", "uid": 0, "bytes_xlated": 528, diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 20689a321ffe..b6f5d560460d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -16,20 +16,22 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** } + *OBJECT* := { **map** | **program** | **cgroup** | **perf** } *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } | { **-j** | **--json** } [{ **-p** | **--pretty** }] } *MAP-COMMANDS* := { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **help** } + | **pin** | **event_pipe** | **help** } *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **help** } *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + *PERF-COMMANDS* := { **show** | **list** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects @@ -56,3 +58,4 @@ OPTIONS SEE ALSO ======== **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4e69782c4a79..892dbf095bff 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -39,7 +39,12 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers -CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' LIBS = -lelf -lbfd -lopcodes $(LIBBPF) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 490811b45fa7..1e1083321643 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1,6 +1,6 @@ # bpftool(8) bash completion -*- shell-script -*- # -# Copyright (C) 2017 Netronome Systems, Inc. +# Copyright (C) 2017-2018 Netronome Systems, Inc. # # This software is dual licensed under the GNU General License # Version 2, June 1991 as shown in the file COPYING in the top-level @@ -79,6 +79,14 @@ _bpftool_get_map_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_perf_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 perf_event_array | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -147,7 +155,7 @@ _bpftool() # Deal with simplest keywords case $prev in - help|key|opcodes|visual) + help|hex|opcodes|visual) return 0 ;; tag) @@ -283,7 +291,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; *) _bpftool_once_attr 'key' @@ -302,7 +310,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; value) # We can have bytes, or references to a prog or a @@ -321,6 +329,8 @@ _bpftool() return 0 ;; *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) return 0 ;; esac @@ -357,10 +367,34 @@ _bpftool() fi return 0 ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_perf_map_ids + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu' + _bpftool_once_attr 'index' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ - lookup pin show list update' -- "$cur" ) ) + lookup pin event_pipe show list update' -- \ + "$cur" ) ) ;; esac ;; @@ -372,7 +406,8 @@ _bpftool() ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ - device' + device bind4 bind6 post_bind4 post_bind6 connect4 \ + connect6 sendmsg4 sendmsg6' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -380,7 +415,9 @@ _bpftool() _filedir return 0 ;; - ingress|egress|sock_create|sock_ops|device) + ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ + post_bind4|post_bind6|connect4|connect6|sendmsg4|\ + sendmsg6) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 @@ -412,6 +449,15 @@ _bpftool() ;; esac ;; + perf) + case $command in + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index cae32a61cb18..16bee011e16c 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -16,8 +16,11 @@ #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - "ATTACH_TYPE := { ingress | egress | sock_create | sock_ops | device }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ + " sock_ops | device | bind4 | bind6 |\n" \ + " post_bind4 | post_bind6 | connect4 |\n" \ + " connect6 | sendmsg4 | sendmsg6 }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -25,6 +28,14 @@ static const char * const attach_type_strings[] = { [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", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -282,7 +293,7 @@ static int do_help(int argc, char **argv) " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" "\n" - " " HELP_SPEC_ATTACH_TYPES "\n" + HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 465995281dcd..32f9e397a6c0 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -33,6 +33,7 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ +#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <fts.h> @@ -330,6 +331,16 @@ char *get_fdinfo(int fd, const char *key) return NULL; } +void print_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "%d", data[i]); + jsonw_end_array(json_wtr); +} + void print_hex_data_json(uint8_t *data, size_t len) { unsigned int i; @@ -420,6 +431,70 @@ void delete_pinned_obj_table(struct pinned_obj_table *tab) } } +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + static unsigned int result; + char buf[128]; + long int n; + char *ptr; + int fd; + + if (result) + return result; + + fd = open("/sys/devices/system/cpu/possible", O_RDONLY); + if (fd < 0) { + p_err("can't open sysfs possible cpus"); + exit(-1); + } + + n = read(fd, buf, sizeof(buf)); + if (n < 2) { + p_err("can't read sysfs possible cpus"); + exit(-1); + } + close(fd); + + if (n == sizeof(buf)) { + p_err("read sysfs possible cpus overflow"); + exit(-1); + } + + ptr = buf; + n = 0; + while (*ptr && *ptr != '\n') { + unsigned int a, b; + + if (sscanf(ptr, "%u-%u", &a, &b) == 2) { + n += b - a + 1; + + ptr = strchr(ptr, '-') + 1; + } else if (sscanf(ptr, "%u", &a) == 1) { + n++; + } else { + assert(0); + } + + while (isdigit(*ptr)) + ptr++; + if (*ptr == ',') + ptr++; + } + + result = n; + + return result; +} + static char * ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) { diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 1ec852d21d44..eea7f14355f3 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -87,7 +87,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup }\n" + " OBJECT := { prog | map | cgroup | perf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -216,6 +216,7 @@ static const struct cmd cmds[] = { { "prog", do_prog }, { "map", do_map }, { "cgroup", do_cgroup }, + { "perf", do_perf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index b8e9584d6246..63fdb310b9a4 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -117,14 +117,20 @@ 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_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); +int do_perf(int argc, char **arg); int prog_parse_fd(int *argc, char ***argv); +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch); +void print_data_json(uint8_t *data, size_t len); void print_hex_data_json(uint8_t *data, size_t len); +unsigned int get_page_size(void); +unsigned int get_possible_cpus(void); const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index f509c86faede..097b1a5e046b 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -34,7 +34,6 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ #include <assert.h> -#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <stdbool.h> @@ -67,63 +66,9 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_DEVMAP] = "devmap", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", }; -static unsigned int get_possible_cpus(void) -{ - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); - - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); - exit(-1); - } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; -} - static bool map_is_per_cpu(__u32 type) { return type == BPF_MAP_TYPE_PERCPU_HASH || @@ -186,8 +131,7 @@ static int map_parse_fd(int *argc, char ***argv) return -1; } -static int -map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; int fd; @@ -283,11 +227,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, static char **parse_bytes(char **argv, const char *name, unsigned char *val, unsigned int n) { - unsigned int i = 0; + unsigned int i = 0, base = 0; char *endptr; + if (is_prefix(*argv, "hex")) { + base = 16; + argv++; + } + while (i < n && argv[i]) { - val[i] = strtoul(argv[i], &endptr, 0); + val[i] = strtoul(argv[i], &endptr, base); if (*endptr) { p_err("error parsing byte: %s", argv[i]); return NULL; @@ -868,23 +817,25 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [MAP]\n" - " %s %s dump MAP\n" - " %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" - " %s %s lookup MAP key BYTES\n" - " %s %s getnext MAP [key BYTES]\n" - " %s %s delete MAP key BYTES\n" - " %s %s pin MAP FILE\n" + " %s %s dump MAP\n" + " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n" + " %s %s lookup MAP key DATA\n" + " %s %s getnext MAP [key DATA]\n" + " %s %s delete MAP key DATA\n" + " %s %s pin MAP FILE\n" + " %s %s event_pipe MAP [cpu N index M]\n" " %s %s help\n" "\n" " MAP := { id MAP_ID | pinned FILE }\n" + " DATA := { [hex] BYTES }\n" " " HELP_SPEC_PROGRAM "\n" - " VALUE := { BYTES | MAP | PROG }\n" + " VALUE := { DATA | MAP | PROG }\n" " UPDATE_FLAGS := { any | exist | noexist }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -899,6 +850,7 @@ static const struct cmd cmds[] = { { "getnext", do_getnext }, { "delete", do_delete }, { "pin", do_pin }, + { "event_pipe", do_event_pipe }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 000000000000..1832100d1b27 --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2018 Netronome Systems, Inc. */ +/* This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <errno.h> +#include <fcntl.h> +#include <libbpf.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> + +#include <bpf.h> +#include <perf-sys.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static bool stop; + +struct event_ring_info { + int fd; + int key; + unsigned int cpu; + void *mem; +}; + +struct perf_event_sample { + struct perf_event_header header; + u64 time; + __u32 size; + unsigned char data[]; +}; + +static void int_exit(int signo) +{ + fprintf(stderr, "Stopping...\n"); + stop = true; +} + +static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv) +{ + struct event_ring_info *ring = priv; + struct perf_event_sample *e = event; + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = event; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "type"); + jsonw_uint(json_wtr, e->header.type); + jsonw_name(json_wtr, "cpu"); + jsonw_uint(json_wtr, ring->cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, ring->key); + if (e->header.type == PERF_RECORD_SAMPLE) { + jsonw_name(json_wtr, "timestamp"); + jsonw_uint(json_wtr, e->time); + jsonw_name(json_wtr, "data"); + print_data_json(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + jsonw_name(json_wtr, "lost"); + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "id"); + jsonw_uint(json_wtr, lost->id); + jsonw_name(json_wtr, "count"); + jsonw_uint(json_wtr, lost->lost); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } else { + if (e->header.type == PERF_RECORD_SAMPLE) { + printf("== @%lld.%09lld CPU: %d index: %d =====\n", + e->time / 1000000000ULL, e->time % 1000000000ULL, + ring->cpu, ring->key); + fprint_hex(stdout, e->data, e->size, " "); + printf("\n"); + } else if (e->header.type == PERF_RECORD_LOST) { + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } + + return LIBBPF_PERF_EVENT_CONT; +} + +static void +perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(ring->mem, + MMAP_PAGE_CNT * get_page_size(), + get_page_size(), buf, buf_len, + print_bpf_output, ring); + if (ret != LIBBPF_PERF_EVENT_CONT) { + fprintf(stderr, "perf read loop failed with %d\n", ret); + stop = true; + } +} + +static int perf_mmap_size(void) +{ + return get_page_size() * (MMAP_PAGE_CNT + 1); +} + +static void *perf_event_mmap(int fd) +{ + int mmap_size = perf_mmap_size(); + void *base; + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + p_err("event mmap failed: %s\n", strerror(errno)); + return NULL; + } + + return base; +} + +static void perf_event_unmap(void *mem) +{ + if (munmap(mem, perf_mmap_size())) + fprintf(stderr, "Can't unmap ring memory!\n"); +} + +static int bpf_perf_event_open(int map_fd, int key, int cpu) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int pmu_fd; + + pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + if (pmu_fd < 0) { + p_err("failed to open perf event %d for CPU %d", key, cpu); + return -1; + } + + if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { + p_err("failed to update map for event %d for CPU %d", key, cpu); + goto err_close; + } + if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + p_err("failed to enable event %d for CPU %d", key, cpu); + goto err_close; + } + + return pmu_fd; + +err_close: + close(pmu_fd); + return -1; +} + +int do_event_pipe(int argc, char **argv) +{ + int i, nfds, map_fd, index = -1, cpu = -1; + struct bpf_map_info map_info = {}; + struct event_ring_info *rings; + size_t tmp_buf_sz = 0; + void *tmp_buf = NULL; + struct pollfd *pfds; + __u32 map_info_len; + bool do_all = true; + + map_info_len = sizeof(map_info); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); + if (map_fd < 0) + return -1; + + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + p_err("map is not a perf event array"); + goto err_close_map; + } + + while (argc) { + if (argc < 2) + BAD_ARG(); + + if (is_prefix(*argv, "cpu")) { + char *endptr; + + NEXT_ARG(); + cpu = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as CPU ID", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "index")) { + char *endptr; + + NEXT_ARG(); + index = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as index", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else { + BAD_ARG(); + } + + do_all = false; + } + + if (!do_all) { + if (index == -1 || cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + + nfds = 1; + } else { + nfds = min(get_possible_cpus(), map_info.max_entries); + cpu = 0; + index = 0; + } + + rings = calloc(nfds, sizeof(rings[0])); + if (!rings) + goto err_close_map; + + pfds = calloc(nfds, sizeof(pfds[0])); + if (!pfds) + goto err_free_rings; + + for (i = 0; i < nfds; i++) { + rings[i].cpu = cpu + i; + rings[i].key = index + i; + + rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, + rings[i].cpu); + if (rings[i].fd < 0) + goto err_close_fds_prev; + + rings[i].mem = perf_event_mmap(rings[i].fd); + if (!rings[i].mem) + goto err_close_fds_current; + + pfds[i].fd = rings[i].fd; + pfds[i].events = POLLIN; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + poll(pfds, nfds, 200); + for (i = 0; i < nfds; i++) + perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + } + free(tmp_buf); + + if (json_output) + jsonw_end_array(json_wtr); + + for (i = 0; i < nfds; i++) { + perf_event_unmap(rings[i].mem); + close(rings[i].fd); + } + free(pfds); + free(rings); + close(map_fd); + + return 0; + +err_close_fds_prev: + while (i--) { + perf_event_unmap(rings[i].mem); +err_close_fds_current: + close(rings[i].fd); + } + free(pfds); +err_free_rings: + free(rings); +err_close_map: + close(map_fd); + return -1; +} diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c new file mode 100644 index 000000000000..ac6b1a12c9b7 --- /dev/null +++ b/tools/bpf/bpftool/perf.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (C) 2018 Facebook +// Author: Yonghong Song <yhs@fb.com> + +#define _GNU_SOURCE +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <ftw.h> + +#include <bpf.h> + +#include "main.h" + +/* 0: undecided, 1: supported, 2: not supported */ +static int perf_query_supported; +static bool has_perf_query_support(void) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + char buf[256]; + int fd; + + if (perf_query_supported) + goto out; + + fd = open(bin_name, O_RDONLY); + if (fd < 0) { + p_err("perf_query_support: %s", strerror(errno)); + goto out; + } + + /* the following query will fail as no bpf attachment, + * the expected errno is ENOTSUPP + */ + errno = 0; + len = sizeof(buf); + bpf_task_fd_query(getpid(), fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + + if (errno == 524 /* ENOTSUPP */) { + perf_query_supported = 1; + goto close_fd; + } + + perf_query_supported = 2; + p_err("perf_query_support: %s", strerror(errno)); + fprintf(stderr, + "HINT: non root or kernel doesn't support TASK_FD_QUERY\n"); + +close_fd: + close(fd); +out: + return perf_query_supported == 1; +} + +static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + jsonw_start_object(json_wtr); + jsonw_int_field(json_wtr, "pid", pid); + jsonw_int_field(json_wtr, "fd", fd); + jsonw_uint_field(json_wtr, "prog_id", prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "raw_tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_KPROBE: + jsonw_string_field(json_wtr, "fd_type", "kprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_KRETPROBE: + jsonw_string_field(json_wtr, "fd_type", "kretprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_UPROBE: + jsonw_string_field(json_wtr, "fd_type", "uprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + jsonw_string_field(json_wtr, "fd_type", "uretprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + } + jsonw_end_object(json_wtr); +} + +static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + printf("pid %d fd %d: prog_id %u ", pid, fd, prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + printf("raw_tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + printf("tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_KPROBE: + if (buf[0] != '\0') + printf("kprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_KRETPROBE: + if (buf[0] != '\0') + printf("kretprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kretprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_UPROBE: + printf("uprobe filename %s offset %llu\n", buf, probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + printf("uretprobe filename %s offset %llu\n", buf, + probe_offset); + break; + } +} + +static int show_proc(const char *fpath, const struct stat *sb, + int tflag, struct FTW *ftwbuf) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + int err, pid = 0, fd = 0; + const char *pch; + char buf[4096]; + + /* prefix always /proc */ + pch = fpath + 5; + if (*pch == '\0') + return 0; + + /* pid should be all numbers */ + pch++; + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd directory */ + pch++; + if (strncmp(pch, "fd", 2)) + return FTW_SKIP_SUBTREE; + pch += 2; + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd/<fd_num> */ + pch++; + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + return FTW_SKIP_SUBTREE; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + return 0; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, probe_offset, + probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, probe_offset, + probe_addr); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + int flags = FTW_ACTIONRETVAL | FTW_PHYS; + int err = 0, nopenfd = 16; + + if (!has_perf_query_support()) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + if (nftw("/proc", show_proc, nopenfd, flags) == -1) { + p_err("%s", strerror(errno)); + err = -1; + } + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s { show | list | help }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_perf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f7a810897eac..a4f435203fef 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -68,6 +68,10 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", [BPF_PROG_TYPE_SK_SKB] = "sk_skb", [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", }; static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) @@ -93,7 +97,10 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) return; } - strftime(buf, size, "%b %d/%H:%M", &load_tm); + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); } static int prog_fd_by_tag(unsigned char *tag) @@ -232,6 +239,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) info->tag[0], info->tag[1], info->tag[2], info->tag[3], info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -240,7 +249,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) print_boot_time(info->load_time, buf, sizeof(buf)); /* Piggy back on load_time, since 0 uid is a valid one */ - jsonw_string_field(json_wtr, "loaded_at", buf); + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); jsonw_uint_field(json_wtr, "uid", info->created_by_uid); } @@ -292,6 +302,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); printf("\n"); if (info->load_time) { @@ -410,7 +421,11 @@ static int do_show(int argc, char **argv) static int do_dump(int argc, char **argv) { + unsigned long *func_ksyms = NULL; struct bpf_prog_info info = {}; + unsigned int *func_lens = NULL; + unsigned int nr_func_ksyms; + unsigned int nr_func_lens; struct dump_data dd = {}; __u32 len = sizeof(info); unsigned int buf_size; @@ -486,10 +501,34 @@ static int do_dump(int argc, char **argv) return -1; } + nr_func_ksyms = info.nr_jited_ksyms; + if (nr_func_ksyms) { + func_ksyms = malloc(nr_func_ksyms * sizeof(__u64)); + if (!func_ksyms) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + + nr_func_lens = info.nr_jited_func_lens; + if (nr_func_lens) { + func_lens = malloc(nr_func_lens * sizeof(__u32)); + if (!func_lens) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + memset(&info, 0, sizeof(info)); *member_ptr = ptr_to_u64(buf); *member_len = buf_size; + info.jited_ksyms = ptr_to_u64(func_ksyms); + info.nr_jited_ksyms = nr_func_ksyms; + info.jited_func_lens = ptr_to_u64(func_lens); + info.nr_jited_func_lens = nr_func_lens; err = bpf_obj_get_info_by_fd(fd, &info, &len); close(fd); @@ -503,6 +542,16 @@ static int do_dump(int argc, char **argv) goto err_free; } + if (info.nr_jited_ksyms > nr_func_ksyms) { + p_err("too many addresses returned"); + goto err_free; + } + + if (info.nr_jited_func_lens > nr_func_lens) { + p_err("too many values returned"); + goto err_free; + } + if ((member_len == &info.jited_prog_len && info.jited_prog_insns == 0) || (member_len == &info.xlated_prog_len && @@ -540,7 +589,57 @@ static int do_dump(int argc, char **argv) goto err_free; } - disasm_print_insn(buf, *member_len, opcodes, name); + if (info.nr_jited_func_lens && info.jited_func_lens) { + struct kernel_sym *sym = NULL; + char sym_name[SYM_MAX_NAME]; + unsigned char *img = buf; + __u64 *ksyms = NULL; + __u32 *lens; + __u32 i; + + if (info.nr_jited_ksyms) { + kernel_syms_load(&dd); + ksyms = (__u64 *) info.jited_ksyms; + } + + if (json_output) + jsonw_start_array(json_wtr); + + lens = (__u32 *) info.jited_func_lens; + for (i = 0; i < info.nr_jited_func_lens; i++) { + if (ksyms) { + sym = kernel_syms_search(&dd, ksyms[i]); + if (sym) + sprintf(sym_name, "%s", sym->name); + else + sprintf(sym_name, "0x%016llx", ksyms[i]); + } else { + strcpy(sym_name, "unknown"); + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "name"); + jsonw_string(json_wtr, sym_name); + jsonw_name(json_wtr, "insns"); + } else { + printf("%s:\n", sym_name); + } + + disasm_print_insn(img, lens[i], opcodes, name); + img += lens[i]; + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + } + + if (json_output) + jsonw_end_array(json_wtr); + } else { + disasm_print_insn(buf, *member_len, opcodes, name); + } } else if (visual) { if (json_output) jsonw_null(json_wtr); @@ -548,6 +647,9 @@ static int do_dump(int argc, char **argv) dump_xlated_cfg(buf, *member_len); } else { kernel_syms_load(&dd); + dd.nr_jited_ksyms = info.nr_jited_ksyms; + dd.jited_ksyms = (__u64 *) info.jited_ksyms; + if (json_output) dump_xlated_json(&dd, buf, *member_len, opcodes); else @@ -556,10 +658,14 @@ static int do_dump(int argc, char **argv) } free(buf); + free(func_ksyms); + free(func_lens); return 0; err_free: free(buf); + free(func_ksyms); + free(func_lens); return -1; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7a3173b76c16..b97f1da60dd1 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -102,8 +102,8 @@ void kernel_syms_destroy(struct dump_data *dd) free(dd->sym_mapping); } -static struct kernel_sym *kernel_syms_search(struct dump_data *dd, - unsigned long key) +struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) { struct kernel_sym sym = { .address = key, @@ -174,7 +174,11 @@ static const char *print_call_pcrel(struct dump_data *dd, unsigned long address, const struct bpf_insn *insn) { - if (sym) + if (!dd->nr_jited_ksyms) + /* Do not show address for interpreted programs */ + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d", insn->off); + else if (sym) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "%+d#%s", insn->off, sym->name); else @@ -203,6 +207,10 @@ static const char *print_call(void *private_data, unsigned long address = dd->address_call_base + insn->imm; struct kernel_sym *sym; + if (insn->src_reg == BPF_PSEUDO_CALL && + (__u32) insn->imm < dd->nr_jited_ksyms) + address = dd->jited_ksyms[insn->imm]; + sym = kernel_syms_search(dd, address); if (insn->src_reg == BPF_PSEUDO_CALL) return print_call_pcrel(dd, sym, address, insn); diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index b34affa7ef2d..33d86e2b369b 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -49,11 +49,14 @@ struct dump_data { unsigned long address_call_base; struct kernel_sym *sym_mapping; __u32 sym_count; + __u64 *jited_ksyms; + __u32 nr_jited_ksyms; char scratch_buff[SYM_MAX_NAME + 8]; }; void kernel_syms_load(struct dump_data *dd); void kernel_syms_destroy(struct dump_data *dd); +struct kernel_sym *kernel_syms_search(struct dump_data *dd, unsigned long key); void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, bool opcodes); void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index c5e512da8d8a..af55acf73e75 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -263,6 +263,16 @@ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) +/* Relative call */ + +#define BPF_CALL_REL(TGT) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = BPF_PSEUDO_CALL, \ + .off = 0, \ + .imm = TGT }) + /* Program exit */ #define BPF_EXIT_INSN() \ diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..8dd6aefdafa4 --- /dev/null +++ b/tools/include/uapi/asm/bitsperlong.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../arch/x86/include/uapi/asm/bitsperlong.h" +#elif defined(__aarch64__) +#include "../../arch/arm64/include/uapi/asm/bitsperlong.h" +#elif defined(__powerpc__) +#include "../../arch/powerpc/include/uapi/asm/bitsperlong.h" +#elif defined(__s390__) +#include "../../arch/s390/include/uapi/asm/bitsperlong.h" +#elif defined(__sparc__) +#include "../../arch/sparc/include/uapi/asm/bitsperlong.h" +#elif defined(__mips__) +#include "../../arch/mips/include/uapi/asm/bitsperlong.h" +#elif defined(__ia64__) +#include "../../arch/ia64/include/uapi/asm/bitsperlong.h" +#else +#include <asm-generic/bitsperlong.h> +#endif diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h new file mode 100644 index 000000000000..ce3c5945a1c4 --- /dev/null +++ b/tools/include/uapi/asm/errno.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../arch/x86/include/uapi/asm/errno.h" +#elif defined(__powerpc__) +#include "../../arch/powerpc/include/uapi/asm/errno.h" +#elif defined(__sparc__) +#include "../../arch/sparc/include/uapi/asm/errno.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/errno.h" +#elif defined(__mips__) +#include "../../arch/mips/include/uapi/asm/errno.h" +#elif defined(__ia64__) +#include "../../arch/ia64/include/uapi/asm/errno.h" +#elif defined(__xtensa__) +#include "../../arch/xtensa/include/uapi/asm/errno.h" +#else +#include <asm-generic/errno.h> +#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8c317737ba3f..e0b06784f227 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -95,6 +95,9 @@ enum bpf_cmd { BPF_OBJ_GET_INFO_BY_FD, BPF_PROG_QUERY, BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, }; enum bpf_map_type { @@ -115,6 +118,8 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, }; enum bpf_prog_type { @@ -137,6 +142,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_RAW_TRACEPOINT, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, }; enum bpf_attach_type { @@ -154,6 +161,9 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, __MAX_BPF_ATTACH_TYPE }; @@ -279,6 +289,9 @@ union bpf_attr { */ char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -339,6 +352,7 @@ union bpf_attr { __u32 start_id; __u32 prog_id; __u32 map_id; + __u32 btf_id; }; __u32 next_id; __u32 open_flags; @@ -363,398 +377,1704 @@ union bpf_attr { __u64 name; __u32 prog_fd; } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; } __attribute__((aligned(8))); -/* BPF helper function descriptions: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: 32-bit index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. * * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set - * - * int bpf_msg_redirect_map(map, key, flags) - * Redirect msg to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_bind(ctx, addr, addr_len) - * Bind socket to address. Only binding to IP is supported, no port can be - * set in addr. - * @ctx: pointer to context of type bpf_sock_addr - * @addr: pointer to struct sockaddr to bind socket to - * @addr_len: length of sockaddr structure - * Return: 0 on success or negative error code + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** 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. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *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 + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * 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 + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * 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, char *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 + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting 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 + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * 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. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only). + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * Egress device index on success, 0 if packet needs to continue + * up the stack for further processing or a negative error in case + * of failure. + * + * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of param: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of param: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown** () again with the same values, or calling + * **bpf_rc_repeat** (). + * + * 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 + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and 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_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -821,7 +2141,23 @@ union bpf_attr { FN(msg_apply_bytes), \ FN(msg_cork_bytes), \ FN(msg_pull_data), \ - FN(bind), + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -855,11 +2191,14 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) @@ -879,6 +2218,18 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -923,10 +2274,24 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; + __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; }; +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + /* Generic BPF return codes which all BPF program types may support. * The values are binary compatible with their TC_ACT_* counter-part to * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT @@ -999,6 +2364,14 @@ enum sk_action { struct sk_msg_md { void *data; void *data_end; + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; #define BPF_TAG_SIZE 8 @@ -1017,9 +2390,13 @@ struct bpf_prog_info { __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; - __u32 :32; + __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; } __attribute__((aligned(8))); struct bpf_map_info { @@ -1034,6 +2411,15 @@ struct bpf_map_info { __u32 :32; __u64 netns_dev; __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; } __attribute__((aligned(8))); /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed @@ -1054,6 +2440,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -1214,4 +2606,64 @@ struct bpf_raw_tracepoint_args { __u64 args[0]; }; +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +#define BPF_FIB_LOOKUP_DIRECT BIT(0) +#define BPF_FIB_LOOKUP_OUTPUT BIT(1) + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + __u32 ifindex; /* L3 device index for lookup */ + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowlabel; /* AF_INET6 */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h new file mode 100644 index 000000000000..0b5ddbe135a4 --- /dev/null +++ b/tools/include/uapi/linux/btf.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include <linux/types.h> + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x0000ffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x0000ffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-31: unused + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + __u32 offset; /* offset in bits */ +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h new file mode 100644 index 000000000000..841573019ae1 --- /dev/null +++ b/tools/include/uapi/linux/erspan.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ERSPAN Tunnel Metadata + * + * Copyright (c) 2018 VMware + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * Userspace API for metadata mode ERSPAN tunnel + */ +#ifndef _UAPI_ERSPAN_H +#define _UAPI_ERSPAN_H + +#include <linux/types.h> /* For __beXX in userspace */ +#include <asm/byteorder.h> + +/* ERSPAN version 2 metadata header */ +struct erspan_md2 { + __be32 timestamp; + __be16 sgt; /* security group tag */ +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hwid_upper:2, + ft:5, + p:1; + __u8 o:1, + gra:2, + dir:1, + hwid:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 p:1, + ft:5, + hwid_upper:2; + __u8 hwid:4, + dir:1, + gra:2, + o:1; +#else +#error "Please fix <asm/byteorder.h>" +#endif +}; + +struct erspan_metadata { + int version; + union { + __be32 index; /* Version 1 (type II)*/ + struct erspan_md2 md2; /* Version 2 (type III) */ + } u; +}; + +#endif /* _UAPI_ERSPAN_H */ diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h new file mode 100644 index 000000000000..f189931042a7 --- /dev/null +++ b/tools/include/uapi/linux/lirc.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * lirc.h - linux infrared remote control header file + * last modified 2010/07/13 by Jarod Wilson + */ + +#ifndef _LINUX_LIRC_H +#define _LINUX_LIRC_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +#define PULSE_BIT 0x01000000 +#define PULSE_MASK 0x00FFFFFF + +#define LIRC_MODE2_SPACE 0x00000000 +#define LIRC_MODE2_PULSE 0x01000000 +#define LIRC_MODE2_FREQUENCY 0x02000000 +#define LIRC_MODE2_TIMEOUT 0x03000000 + +#define LIRC_VALUE_MASK 0x00FFFFFF +#define LIRC_MODE2_MASK 0xFF000000 + +#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) +#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) +#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) +#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) + +#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) +#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) + +#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE) +#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) +#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) +#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) + +/* used heavily by lirc userspace */ +#define lirc_t int + +/*** lirc compatible hardware features ***/ + +#define LIRC_MODE2SEND(x) (x) +#define LIRC_SEND2MODE(x) (x) +#define LIRC_MODE2REC(x) ((x) << 16) +#define LIRC_REC2MODE(x) ((x) >> 16) + +#define LIRC_MODE_RAW 0x00000001 +#define LIRC_MODE_PULSE 0x00000002 +#define LIRC_MODE_MODE2 0x00000004 +#define LIRC_MODE_SCANCODE 0x00000008 +#define LIRC_MODE_LIRCCODE 0x00000010 + + +#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) +#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) +#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) +#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) + +#define LIRC_CAN_SEND_MASK 0x0000003f + +#define LIRC_CAN_SET_SEND_CARRIER 0x00000100 +#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200 +#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400 + +#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW) +#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE) +#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2) +#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE) +#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE) + +#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) + +#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) +#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) + +#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 +#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 +#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 +#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 +#define LIRC_CAN_SET_REC_FILTER 0x08000000 + +#define LIRC_CAN_MEASURE_CARRIER 0x02000000 +#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 + +#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) +#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) + +#define LIRC_CAN_NOTIFY_DECODE 0x01000000 + +/*** IOCTL commands for lirc driver ***/ + +#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) + +#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) +#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) +#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) + +#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) +#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) + +/* code length in bits, currently only for LIRC_MODE_LIRCCODE */ +#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) + +#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32) +#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32) +/* Note: these can reset the according pulse_width */ +#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) +#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) +#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) +#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) + +/* + * when a timeout != 0 is set the driver will send a + * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is + * never sent, timeout is disabled by default + */ +#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32) + +/* 1 enables, 0 disables timeout reports in MODE2 */ +#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) + +/* + * if enabled from the next key press on the driver will send + * LIRC_MODE2_FREQUENCY packets + */ +#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) + +/* + * to set a range use LIRC_SET_REC_CARRIER_RANGE with the + * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound + */ +#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) + +#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) + +/* + * struct lirc_scancode - decoded scancode with protocol for use with + * LIRC_MODE_SCANCODE + * + * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR + * was decoded. + * @flags: should be 0 for transmit. When receiving scancodes, + * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set + * depending on the protocol + * @rc_proto: see enum rc_proto + * @keycode: the translated keycode. Set to 0 for transmit. + * @scancode: the scancode received or to be sent + */ +struct lirc_scancode { + __u64 timestamp; + __u16 flags; + __u16 rc_proto; + __u32 keycode; + __u64 scancode; +}; + +/* Set if the toggle bit of rc-5 or rc-6 is enabled */ +#define LIRC_SCANCODE_FLAG_TOGGLE 1 +/* Set if this is a nec or sanyo repeat */ +#define LIRC_SCANCODE_FLAG_REPEAT 2 + +/** + * enum rc_proto - the Remote Controller protocol + * + * @RC_PROTO_UNKNOWN: Protocol not known + * @RC_PROTO_OTHER: Protocol known but proprietary + * @RC_PROTO_RC5: Philips RC5 protocol + * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol + * @RC_PROTO_RC5_SZ: StreamZap variant of RC5 + * @RC_PROTO_JVC: JVC protocol + * @RC_PROTO_SONY12: Sony 12 bit protocol + * @RC_PROTO_SONY15: Sony 15 bit protocol + * @RC_PROTO_SONY20: Sony 20 bit protocol + * @RC_PROTO_NEC: NEC protocol + * @RC_PROTO_NECX: Extended NEC protocol + * @RC_PROTO_NEC32: NEC 32 bit protocol + * @RC_PROTO_SANYO: Sanyo protocol + * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard + * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse + * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol + * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol + * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol + * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol + * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol + * @RC_PROTO_SHARP: Sharp protocol + * @RC_PROTO_XMP: XMP protocol + * @RC_PROTO_CEC: CEC protocol + * @RC_PROTO_IMON: iMon Pad protocol + */ +enum rc_proto { + RC_PROTO_UNKNOWN = 0, + RC_PROTO_OTHER = 1, + RC_PROTO_RC5 = 2, + RC_PROTO_RC5X_20 = 3, + RC_PROTO_RC5_SZ = 4, + RC_PROTO_JVC = 5, + RC_PROTO_SONY12 = 6, + RC_PROTO_SONY15 = 7, + RC_PROTO_SONY20 = 8, + RC_PROTO_NEC = 9, + RC_PROTO_NECX = 10, + RC_PROTO_NEC32 = 11, + RC_PROTO_SANYO = 12, + RC_PROTO_MCIR2_KBD = 13, + RC_PROTO_MCIR2_MSE = 14, + RC_PROTO_RC6_0 = 15, + RC_PROTO_RC6_6A_20 = 16, + RC_PROTO_RC6_6A_24 = 17, + RC_PROTO_RC6_6A_32 = 18, + RC_PROTO_RC6_MCE = 19, + RC_PROTO_SHARP = 20, + RC_PROTO_XMP = 21, + RC_PROTO_CEC = 22, + RC_PROTO_IMON = 23, +}; + +#endif diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h new file mode 100644 index 000000000000..286e8d6a8e98 --- /dev/null +++ b/tools/include/uapi/linux/seg6.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_H +#define _UAPI_LINUX_SEG6_H + +#include <linux/types.h> +#include <linux/in6.h> /* For struct in6_addr. */ + +/* + * SRH + */ +struct ipv6_sr_hdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 type; + __u8 segments_left; + __u8 first_segment; /* Represents the last_entry field of SRH */ + __u8 flags; + __u16 tag; + + struct in6_addr segments[0]; +}; + +#define SR6_FLAG1_PROTECTED (1 << 6) +#define SR6_FLAG1_OAM (1 << 5) +#define SR6_FLAG1_ALERT (1 << 4) +#define SR6_FLAG1_HMAC (1 << 3) + +#define SR6_TLV_INGRESS 1 +#define SR6_TLV_EGRESS 2 +#define SR6_TLV_OPAQUE 3 +#define SR6_TLV_PADDING 4 +#define SR6_TLV_HMAC 5 + +#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC) + +struct sr6_tlv { + __u8 type; + __u8 len; + __u8 data[0]; +}; + +#endif diff --git a/tools/include/uapi/linux/seg6_local.h b/tools/include/uapi/linux/seg6_local.h new file mode 100644 index 000000000000..edc138bdc56d --- /dev/null +++ b/tools/include/uapi/linux/seg6_local.h @@ -0,0 +1,80 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_LOCAL_H +#define _UAPI_LINUX_SEG6_LOCAL_H + +#include <linux/seg6.h> + +enum { + SEG6_LOCAL_UNSPEC, + SEG6_LOCAL_ACTION, + SEG6_LOCAL_SRH, + SEG6_LOCAL_TABLE, + SEG6_LOCAL_NH4, + SEG6_LOCAL_NH6, + SEG6_LOCAL_IIF, + SEG6_LOCAL_OIF, + SEG6_LOCAL_BPF, + __SEG6_LOCAL_MAX, +}; +#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) + +enum { + SEG6_LOCAL_ACTION_UNSPEC = 0, + /* node segment */ + SEG6_LOCAL_ACTION_END = 1, + /* adjacency segment (IPv6 cross-connect) */ + SEG6_LOCAL_ACTION_END_X = 2, + /* lookup of next seg NH in table */ + SEG6_LOCAL_ACTION_END_T = 3, + /* decap and L2 cross-connect */ + SEG6_LOCAL_ACTION_END_DX2 = 4, + /* decap and IPv6 cross-connect */ + SEG6_LOCAL_ACTION_END_DX6 = 5, + /* decap and IPv4 cross-connect */ + SEG6_LOCAL_ACTION_END_DX4 = 6, + /* decap and lookup of DA in v6 table */ + SEG6_LOCAL_ACTION_END_DT6 = 7, + /* decap and lookup of DA in v4 table */ + SEG6_LOCAL_ACTION_END_DT4 = 8, + /* binding segment with insertion */ + SEG6_LOCAL_ACTION_END_B6 = 9, + /* binding segment with encapsulation */ + SEG6_LOCAL_ACTION_END_B6_ENCAP = 10, + /* binding segment with MPLS encap */ + SEG6_LOCAL_ACTION_END_BM = 11, + /* lookup last seg in table */ + SEG6_LOCAL_ACTION_END_S = 12, + /* forward to SR-unaware VNF with static proxy */ + SEG6_LOCAL_ACTION_END_AS = 13, + /* forward to SR-unaware VNF with masquerading */ + SEG6_LOCAL_ACTION_END_AM = 14, + /* custom BPF action */ + SEG6_LOCAL_ACTION_END_BPF = 15, + + __SEG6_LOCAL_ACTION_MAX, +}; + +#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1) + +enum { + SEG6_LOCAL_BPF_PROG_UNSPEC, + SEG6_LOCAL_BPF_PROG, + SEG6_LOCAL_BPF_PROG_NAME, + __SEG6_LOCAL_BPF_PROG_MAX, +}; + +#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1) + +#endif diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 64c679d67109..6070e655042d 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e6d5f8d1477f..5390e7725e43 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -69,7 +69,7 @@ FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf FEATURE_DISPLAY = libelf bpf -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) check_feat := 1 @@ -189,6 +189,7 @@ install_headers: $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); + $(call do_install,btf.h,$(prefix)/include/bpf,644); install: install_lib diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index acbb3f8b3bec..9ddc89dae962 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -73,43 +73,77 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags, int node) +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = name ? strlen(name) : 0; + __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.map_type = create_attr->map_type; + attr.key_size = create_attr->key_size; + attr.value_size = create_attr->value_size; + attr.max_entries = create_attr->max_entries; + attr.map_flags = create_attr->map_flags; + memcpy(attr.map_name, create_attr->name, + min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = create_attr->numa_node; + attr.btf_fd = create_attr->btf_fd; + attr.btf_key_type_id = create_attr->btf_key_type_id; + attr.btf_value_type_id = create_attr->btf_value_type_id; + attr.map_ifindex = create_attr->map_ifindex; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + map_attr.numa_node = node; + map_attr.map_flags |= BPF_F_NUMA_NODE; } - return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + return bpf_create_map_xattr(&map_attr); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, NULL, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, name, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, @@ -168,6 +202,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.log_size = 0; attr.log_level = 0; attr.kern_version = load_attr->kern_version; + attr.prog_ifindex = load_attr->prog_ifindex; memcpy(attr.prog_name, load_attr->name, min(name_len, BPF_OBJ_NAME_LEN - 1)); @@ -425,6 +460,16 @@ int bpf_map_get_fd_by_id(__u32 id) return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); } +int bpf_btf_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.btf_id = 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) { union bpf_attr attr; @@ -573,3 +618,51 @@ cleanup: close(sock); return ret; } + +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log) +{ + union bpf_attr attr = {}; + int fd; + + attr.btf = ptr_to_u64(btf); + attr.btf_size = btf_size; + +retry: + if (do_log && log_buf && log_buf_size) { + attr.btf_log_level = 1; + attr.btf_log_size = log_buf_size; + attr.btf_log_buf = ptr_to_u64(log_buf); + } + + fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (fd == -1 && !do_log && log_buf && log_buf_size) { + do_log = true; + goto retry; + } + + return fd; +} + +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) +{ + union bpf_attr attr = {}; + int err; + + attr.task_fd_query.pid = pid; + attr.task_fd_query.fd = fd; + attr.task_fd_query.flags = flags; + attr.task_fd_query.buf = ptr_to_u64(buf); + attr.task_fd_query.buf_len = *buf_len; + + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + *buf_len = attr.task_fd_query.buf_len; + *prog_id = attr.task_fd_query.prog_id; + *fd_type = attr.task_fd_query.fd_type; + *probe_offset = attr.task_fd_query.probe_offset; + *probe_addr = attr.task_fd_query.probe_addr; + + return err; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 39f6a0d64a3b..0639a30a457d 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,8 +24,24 @@ #define __BPF_BPF_H #include <linux/bpf.h> +#include <stdbool.h> #include <stddef.h> +struct bpf_create_map_attr { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 map_ifindex; +}; + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node); @@ -49,6 +65,7 @@ struct bpf_load_program_attr { size_t insns_cnt; const char *license; __u32 kern_version; + __u32 prog_ifindex; }; /* Recommend log buffer size */ @@ -83,8 +100,14 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); int bpf_prog_get_fd_by_id(__u32 id); int bpf_map_get_fd_by_id(__u32 id); +int bpf_btf_get_fd_by_id(__u32 id); int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); int bpf_raw_tracepoint_open(const char *name, int prog_fd); +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log); +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); #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c new file mode 100644 index 000000000000..8c54a4b6f187 --- /dev/null +++ b/tools/lib/bpf/btf.c @@ -0,0 +1,373 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include "btf.h" +#include "bpf.h" + +#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); } +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min(a, b) ((a) < (b) ? (a) : (b)) + +#define BTF_MAX_NR_TYPES 65535 + +static struct btf_type btf_void; + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + const char *strings; + void *nohdr_data; + uint32_t nr_types; + uint32_t types_size; + uint32_t data_size; + int fd; +}; + +static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) +{ + if (offset < btf->hdr->str_len) + return &btf->strings[offset]; + else + return NULL; +} + +static int btf_add_type(struct btf *btf, struct btf_type *t) +{ + if (btf->types_size - btf->nr_types < 2) { + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) + return -E2BIG; + + expand_by = max(btf->types_size >> 2, 16); + new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + + new_types = realloc(btf->types, sizeof(*new_types) * new_size); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + u32 meta_left; + + if (btf->data_size < sizeof(struct btf_header)) { + elog("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + elog("Invalid BTF magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + elog("Unsupported BTF version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + elog("Unsupported BTF flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + elog("BTF has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->type_off) { + elog("Invalid BTF type section offset:%u\n", hdr->type_off); + return -EINVAL; + } + + if (meta_left < hdr->str_off) { + elog("Invalid BTF string section offset:%u\n", hdr->str_off); + return -EINVAL; + } + + if (hdr->type_off >= hdr->str_off) { + elog("BTF type section offset >= string section offset. No type?\n"); + return -EINVAL; + } + + if (hdr->type_off & 0x02) { + elog("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->nohdr_data + hdr->str_off; + const char *end = start + btf->hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + elog("Invalid BTF string section\n"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) +{ + struct btf_header *hdr = btf->hdr; + void *nohdr_data = btf->nohdr_data; + void *next_type = nohdr_data + hdr->type_off; + void *end_type = nohdr_data + hdr->str_off; + + while (next_type < end_type) { + struct btf_type *t = next_type; + uint16_t vlen = BTF_INFO_VLEN(t->info); + int err; + + next_type += sizeof(*t); + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + next_type += sizeof(int); + break; + case BTF_KIND_ARRAY: + next_type += sizeof(struct btf_array); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + next_type += vlen * sizeof(struct btf_member); + break; + case BTF_KIND_ENUM: + next_type += vlen * sizeof(struct btf_enum); + break; + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + break; + default: + elog("Unsupported BTF_KIND:%u\n", + BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + err = btf_add_type(btf, t); + if (err) + return err; + } + + return 0; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, + uint32_t type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +static int64_t btf_type_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return t->size; + case BTF_KIND_PTR: + return sizeof(void *); + default: + return -EINVAL; + } +} + +#define MAX_RESOLVE_DEPTH 32 + +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + uint32_t nelems = 1; + int64_t size = -1; + int i; + + t = btf_type_by_id(btf, type_id); + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); + i++) { + size = btf_type_size(t); + if (size >= 0) + break; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = (const struct btf_array *)(t + 1); + if (nelems && array->nelems > UINT32_MAX / nelems) + return -E2BIG; + nelems *= array->nelems; + type_id = array->type; + break; + default: + return -EINVAL; + } + + t = btf_type_by_id(btf, type_id); + } + + if (size < 0) + return -EINVAL; + + if (nelems && size > UINT32_MAX / nelems) + return -E2BIG; + + return nelems * size; +} + +int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +{ + uint32_t i; + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name = btf_name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +void btf__free(struct btf *btf) +{ + if (!btf) + return; + + if (btf->fd != -1) + close(btf->fd); + + free(btf->data); + free(btf->types); + free(btf); +} + +struct btf *btf__new(uint8_t *data, uint32_t size, + btf_print_fn_t err_log) +{ + uint32_t log_buf_size = 0; + char *log_buf = NULL; + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->fd = -1; + + if (err_log) { + log_buf = malloc(BPF_LOG_BUF_SIZE); + if (!log_buf) { + err = -ENOMEM; + goto done; + } + *log_buf = 0; + log_buf_size = BPF_LOG_BUF_SIZE; + } + + btf->data = malloc(size); + if (!btf->data) { + err = -ENOMEM; + goto done; + } + + memcpy(btf->data, data, size); + btf->data_size = size; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + + if (btf->fd == -1) { + err = -errno; + elog("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (log_buf && *log_buf) + elog("%s\n", log_buf); + goto done; + } + + err = btf_parse_hdr(btf, err_log); + if (err) + goto done; + + err = btf_parse_str_sec(btf, err_log); + if (err) + goto done; + + err = btf_parse_type_sec(btf, err_log); + +done: + free(log_buf); + + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h new file mode 100644 index 000000000000..74bb344035bb --- /dev/null +++ b/tools/lib/bpf/btf.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#ifndef __BPF_BTF_H +#define __BPF_BTF_H + +#include <stdint.h> + +#define BTF_ELF_SEC ".BTF" + +struct btf; + +typedef int (*btf_print_fn_t)(const char *, ...) + __attribute__((format(printf, 1, 2))); + +void btf__free(struct btf *btf); +struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); +int32_t btf__find_by_name(const struct btf *btf, const char *type_name); +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +int btf__fd(const struct btf *btf); + +#endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0f9f06df49bc..a1e96b5de5ff 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -31,6 +31,7 @@ #include <unistd.h> #include <fcntl.h> #include <errno.h> +#include <perf-sys.h> #include <asm/unistd.h> #include <linux/err.h> #include <linux/kernel.h> @@ -45,6 +46,7 @@ #include "libbpf.h" #include "bpf.h" +#include "btf.h" #ifndef EM_BPF #define EM_BPF 247 @@ -176,6 +178,7 @@ struct bpf_program { /* Index in elf obj file, for relocation use. */ int idx; char *name; + int prog_ifindex; char *section_name; struct bpf_insn *insns; size_t insns_cnt, main_prog_cnt; @@ -211,7 +214,10 @@ struct bpf_map { int fd; char *name; size_t offset; + int map_ifindex; struct bpf_map_def def; + uint32_t btf_key_type_id; + uint32_t btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -256,6 +262,8 @@ struct bpf_object { */ struct list_head list; + struct btf *btf; + void *priv; bpf_object_clear_priv_t clear_priv; @@ -819,7 +827,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size); else if (strcmp(name, "maps") == 0) obj->efile.maps_shndx = idx; - else if (sh.sh_type == SHT_SYMTAB) { + else if (strcmp(name, BTF_ELF_SEC) == 0) { + obj->btf = btf__new(data->d_buf, data->d_size, + __pr_debug); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } + } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); @@ -996,33 +1012,127 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } +static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +{ + struct bpf_map_def *def = &map->def; + const size_t max_name = 256; + int64_t key_size, value_size; + int32_t key_id, value_id; + char name[max_name]; + + /* Find key type by name from BTF */ + if (snprintf(name, max_name, "%s_key", map->name) == max_name) { + pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + map->name, map->name); + return -EINVAL; + } + + key_id = btf__find_by_name(btf, name); + if (key_id < 0) { + pr_debug("map:%s key_type:%s cannot be found in BTF\n", + map->name, name); + return key_id; + } + + key_size = btf__resolve_size(btf, key_id); + if (key_size < 0) { + pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", + map->name, name); + return key_size; + } + + if (def->key_size != key_size) { + pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n", + map->name, name, (unsigned int)key_size, def->key_size); + return -EINVAL; + } + + /* Find value type from BTF */ + if (snprintf(name, max_name, "%s_value", map->name) == max_name) { + pr_warning("map:%s length of BTF value_type:%s_value is too long\n", + map->name, map->name); + return -EINVAL; + } + + value_id = btf__find_by_name(btf, name); + if (value_id < 0) { + pr_debug("map:%s value_type:%s cannot be found in BTF\n", + map->name, name); + return value_id; + } + + value_size = btf__resolve_size(btf, value_id); + if (value_size < 0) { + pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", + map->name, name); + return value_size; + } + + if (def->value_size != value_size) { + pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n", + map->name, name, (unsigned int)value_size, def->value_size); + return -EINVAL; + } + + map->btf_key_type_id = key_id; + map->btf_value_type_id = value_id; + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { + struct bpf_create_map_attr create_attr = {}; unsigned int i; + int err; for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map_def *def = &obj->maps[i].def; - int *pfd = &obj->maps[i].fd; - - *pfd = bpf_create_map_name(def->type, - obj->maps[i].name, - def->key_size, - def->value_size, - def->max_entries, - def->map_flags); + struct bpf_map *map = &obj->maps[i]; + struct bpf_map_def *def = &map->def; + int *pfd = &map->fd; + + 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; + 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 (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + 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) { + pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, strerror(errno), errno); + 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); + } + if (*pfd < 0) { size_t j; - int err = *pfd; + err = *pfd; pr_warning("failed to create map (name: '%s'): %s\n", - obj->maps[i].name, + map->name, strerror(errno)); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; } - pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd); + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1166,7 +1276,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) static int load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, const char *name, struct bpf_insn *insns, int insns_cnt, - char *license, u32 kern_version, int *pfd) + char *license, u32 kern_version, int *pfd, int prog_ifindex) { struct bpf_load_program_attr load_attr; char *log_buf; @@ -1180,6 +1290,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, load_attr.insns_cnt = insns_cnt; load_attr.license = license; load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog_ifindex; if (!load_attr.insns || !load_attr.insns_cnt) return -EINVAL; @@ -1261,7 +1372,8 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog->type, prog->expected_attach_type, prog->name, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + license, kern_version, &fd, + prog->prog_ifindex); if (!err) prog->instances.fds[0] = fd; goto out; @@ -1292,7 +1404,8 @@ bpf_program__load(struct bpf_program *prog, err = load_program(prog->type, prog->expected_attach_type, prog->name, result.new_insn_ptr, result.new_insn_cnt, - license, kern_version, &fd); + license, kern_version, &fd, + prog->prog_ifindex); if (err) { pr_warning("Loading the %dth instance of program '%s' failed\n", @@ -1331,9 +1444,39 @@ bpf_object__load_progs(struct bpf_object *obj) return 0; } -static int bpf_object__validate(struct bpf_object *obj) +static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_LIRC_MODE2: + return false; + case BPF_PROG_TYPE_UNSPEC: + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + default: + return true; + } +} + +static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) { - if (obj->kern_version == 0) { + if (needs_kver && obj->kern_version == 0) { pr_warning("%s doesn't provide kernel version\n", obj->path); return -LIBBPF_ERRNO__KVERSION; @@ -1342,7 +1485,8 @@ static int bpf_object__validate(struct bpf_object *obj) } static struct bpf_object * -__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) +__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, + bool needs_kver) { struct bpf_object *obj; int err; @@ -1360,7 +1504,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz) CHECK_ERR(bpf_object__check_endianness(obj), err, out); CHECK_ERR(bpf_object__elf_collect(obj), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); - CHECK_ERR(bpf_object__validate(obj), err, out); + CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); bpf_object__elf_finish(obj); return obj; @@ -1377,7 +1521,7 @@ struct bpf_object *bpf_object__open(const char *path) pr_debug("loading %s\n", path); - return __bpf_object__open(path, NULL, 0); + return __bpf_object__open(path, NULL, 0, true); } struct bpf_object *bpf_object__open_buffer(void *obj_buf, @@ -1400,7 +1544,7 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, pr_debug("loading object '%s' from buffer\n", name); - return __bpf_object__open(name, obj_buf, obj_buf_sz); + return __bpf_object__open(name, obj_buf, obj_buf_sz, true); } int bpf_object__unload(struct bpf_object *obj) @@ -1641,6 +1785,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); + btf__free(obj->btf); for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); @@ -1692,6 +1837,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj) return obj ? obj->kern_version : 0; } +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv) { @@ -1845,11 +1995,12 @@ BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); -static void bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type) +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) { prog->expected_attach_type = type; } @@ -1859,6 +2010,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog, #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0) +#define BPF_S_PROG_SEC(string, ptype) \ + BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype) + #define BPF_SA_PROG_SEC(string, ptype) \ BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype) @@ -1874,6 +2028,7 @@ static const struct { BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), @@ -1889,10 +2044,15 @@ static const struct { BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND), BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT), BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT), + BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG), + BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG), + BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND), + BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND), }; #undef BPF_PROG_SEC #undef BPF_PROG_SEC_FULL +#undef BPF_S_PROG_SEC #undef BPF_SA_PROG_SEC static int bpf_program__identify_section(struct bpf_program *prog) @@ -1929,6 +2089,16 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } +uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map) +{ + return map ? map->btf_key_type_id : 0; +} + +uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map) +{ + return map ? map->btf_value_type_id : 0; +} + int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv) { @@ -2028,13 +2198,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, enum bpf_attach_type expected_attach_type; enum bpf_prog_type prog_type; struct bpf_object *obj; + struct bpf_map *map; int section_idx; int err; if (!attr) return -EINVAL; + if (!attr->file) + return -EINVAL; - obj = bpf_object__open(attr->file); + obj = __bpf_object__open(attr->file, NULL, 0, + bpf_prog_type__needs_kver(attr->prog_type)); if (IS_ERR_OR_NULL(obj)) return -ENOENT; @@ -2044,6 +2218,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, * section name. */ prog_type = attr->prog_type; + prog->prog_ifindex = attr->ifindex; expected_attach_type = attr->expected_attach_type; if (prog_type == BPF_PROG_TYPE_UNSPEC) { section_idx = bpf_program__identify_section(prog); @@ -2064,6 +2239,10 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, first_prog = prog; } + bpf_map__for_each(map, obj) { + map->map_ifindex = attr->ifindex; + } + if (!first_prog) { pr_warning("object file doesn't contain bpf program\n"); bpf_object__close(obj); @@ -2080,3 +2259,63 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, *prog_fd = bpf_program__fd(first_prog); return 0; } + +enum bpf_perf_event_ret +bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv) +{ + volatile struct perf_event_mmap_page *header = mem; + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + void *base, *begin, *end; + int ret; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return LIBBPF_PERF_EVENT_CONT; + + base = ((char *)header) + page_size; + + begin = base + data_tail % size; + end = base + data_head % size; + + while (begin != end) { + struct perf_event_header *ehdr; + + ehdr = begin; + if (begin + ehdr->size > base + size) { + long len = base + size - begin; + + if (*buf_len < ehdr->size) { + free(*buf); + *buf = malloc(ehdr->size); + if (!*buf) { + ret = LIBBPF_PERF_EVENT_ERROR; + break; + } + *buf_len = ehdr->size; + } + + memcpy(*buf, begin, len); + memcpy(*buf + len, base, ehdr->size - len); + ehdr = (void *)*buf; + begin = base + ehdr->size - len; + } else if (begin + ehdr->size == base + size) { + begin = base; + } else { + begin += ehdr->size; + } + + ret = fn(ehdr, priv); + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + + data_tail += ehdr->size; + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_tail; + + return ret; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index a3a62a583f27..09976531aa74 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -52,8 +52,8 @@ enum libbpf_errno { int libbpf_strerror(int err, char *buf, size_t size); /* - * In include/linux/compiler-gcc.h, __printf is defined. However - * it should be better if libbpf.h doesn't depend on Linux header file. + * __printf is defined in include/linux/compiler-gcc.h. However, + * it would be better if libbpf.h didn't depend on Linux header files. * So instead of __printf, here we use gcc attribute directly. */ typedef int (*libbpf_print_fn_t)(const char *, ...) @@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj); int bpf_object__unload(struct bpf_object *obj); const char *bpf_object__name(struct bpf_object *obj); unsigned int bpf_object__kversion(struct bpf_object *obj); +int bpf_object__btf_fd(const struct bpf_object *obj); struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -91,7 +92,7 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); void *bpf_object__priv(struct bpf_object *prog); -/* Accessors of bpf_program. */ +/* Accessors of bpf_program */ struct bpf_program; struct bpf_program *bpf_program__next(struct bpf_program *prog, struct bpf_object *obj); @@ -120,28 +121,28 @@ struct bpf_insn; /* * Libbpf allows callers to adjust BPF programs before being loaded - * into kernel. One program in an object file can be transform into - * multiple variants to be attached to different code. + * into kernel. One program in an object file can be transformed into + * multiple variants to be attached to different hooks. * * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd - * are APIs for this propose. + * form an API for this purpose. * * - bpf_program_prep_t: - * It defines 'preprocessor', which is a caller defined function + * Defines a 'preprocessor', which is a caller defined function * passed to libbpf through bpf_program__set_prep(), and will be * called before program is loaded. The processor should adjust - * the program one time for each instances according to the number + * the program one time for each instance according to the instance id * passed to it. * * - bpf_program__set_prep: - * Attachs a preprocessor to a BPF program. The number of instances - * whould be created is also passed through this function. + * Attaches a preprocessor to a BPF program. The number of instances + * that should be created is also passed through this function. * * - bpf_program__nth_fd: - * After the program is loaded, get resuling fds from bpf program for - * each instances. + * After the program is loaded, get resulting FD of a given instance + * of the BPF program. * - * If bpf_program__set_prep() is not used, the program whould be loaded + * If bpf_program__set_prep() is not used, the program would be loaded * without adjustment during bpf_object__load(). The program has only * one instance. In this case bpf_program__fd(prog) is equal to * bpf_program__nth_fd(prog, 0). @@ -155,7 +156,7 @@ struct bpf_prog_prep_result { struct bpf_insn *new_insn_ptr; int new_insn_cnt; - /* If not NULL, result fd is set to it */ + /* If not NULL, result FD is written to it. */ int *pfd; }; @@ -168,8 +169,8 @@ struct bpf_prog_prep_result { * - res: Output parameter, result of transformation. * * Return value: - * - Zero: pre-processing success. - * - Non-zero: pre-processing, stop loading. + * - Zero: pre-processing success. + * - Non-zero: pre-processing error, stop loading. */ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, struct bpf_insn *insns, int insns_cnt, @@ -181,19 +182,23 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, int bpf_program__nth_fd(struct bpf_program *prog, int n); /* - * Adjust type of bpf program. Default is kprobe. + * Adjust type of BPF program. Default is kprobe. */ int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog); +int bpf_program__set_raw_tracepoint(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog); int bpf_program__set_sched_cls(struct bpf_program *prog); int bpf_program__set_sched_act(struct bpf_program *prog); int bpf_program__set_xdp(struct bpf_program *prog); int bpf_program__set_perf_event(struct bpf_program *prog); void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); +bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog); bool bpf_program__is_sched_cls(struct bpf_program *prog); bool bpf_program__is_sched_act(struct bpf_program *prog); @@ -201,10 +206,10 @@ bool bpf_program__is_xdp(struct bpf_program *prog); bool bpf_program__is_perf_event(struct bpf_program *prog); /* - * We don't need __attribute__((packed)) now since it is - * unnecessary for 'bpf_map_def' because they are all aligned. - * In addition, using it will trigger -Wpacked warning message, - * and will be treated as an error due to -Werror. + * No need for __attribute__((packed)), all members of 'bpf_map_def' + * are all aligned. In addition, using __attribute__((packed)) + * would trigger a -Wpacked warning message, and lead to an error + * if -Werror is set. */ struct bpf_map_def { unsigned int type; @@ -215,8 +220,8 @@ struct bpf_map_def { }; /* - * There is another 'struct bpf_map' in include/linux/map.h. However, - * it is not a uapi header so no need to consider name clash. + * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, + * so no need to worry about a name clash. */ struct bpf_map; struct bpf_map * @@ -224,7 +229,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def - * in the bpf object file. + * in the BPF object file. */ struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); @@ -239,6 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); +uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map); +uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, @@ -252,6 +259,7 @@ struct bpf_prog_load_attr { const char *file; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; + int ifindex; }; int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, @@ -260,4 +268,17 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); + +enum bpf_perf_event_ret { + LIBBPF_PERF_EVENT_DONE = 0, + LIBBPF_PERF_EVENT_ERROR = -1, + LIBBPF_PERF_EVENT_CONT = -2, +}; + +typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event, + void *priv); +int bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, + void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv); #endif diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 5e1ab2f0eb79..49938d72cf63 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -15,3 +15,7 @@ test_libbpf_open test_sock test_sock_addr urandom_read +test_btf +test_sockmap +test_lirc_mode2_user +get_cgroup_id_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0a315ddabbf4..607ed8729c06 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -10,7 +10,7 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf -lrt -lpthread TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read @@ -19,19 +19,23 @@ all: $(TEST_CUSTOM_PROGS) $(TEST_CUSTOM_PROGS): urandom_read urandom_read: urandom_read.c - $(CC) -o $(TEST_CUSTOM_PROGS) -static $< + $(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ - test_sock test_sock_addr + test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ - sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o + sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ + test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ + test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ + test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ + get_cgroup_id_kern.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -39,10 +43,13 @@ TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ test_xdp_meta.sh \ test_offload.py \ - test_sock_addr.sh + test_sock_addr.sh \ + test_tunnel.sh \ + test_lwt_seg6local.sh \ + test_lirc_mode2.sh # Compile but not part of 'make run_tests' -TEST_GEN_PROGS_EXTENDED = test_libbpf_open +TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr include ../lib.mk @@ -55,6 +62,9 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c +$(OUTPUT)/test_sockmap: cgroup_helpers.c +$(OUTPUT)/test_progs: trace_helpers.c +$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c .PHONY: force @@ -66,6 +76,8 @@ $(BPFOBJ): force CLANG ?= clang LLC ?= llc +LLVM_OBJCOPY ?= llvm-objcopy +BTF_PAHOLE ?= pahole PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) @@ -77,15 +89,42 @@ else CPU ?= generic endif +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') + CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ + $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) + +ifneq ($(BTF_LLC_PROBE),) +ifneq ($(BTF_PAHOLE_PROBE),) +ifneq ($(BTF_OBJCOPY_PROBE),) + CLANG_FLAGS += -g + LLC_FLAGS += -mattr=dwarfris + DWARF2BTF = y +endif +endif +endif + $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ - $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index d8223d99f96d..f2f28b6c8915 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -75,9 +75,14 @@ static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) = (void *) BPF_FUNC_sock_ops_cb_flags_set; static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; +static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) = + (void *) BPF_FUNC_sk_redirect_hash; static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; +static int (*bpf_sock_hash_update)(void *map, void *key, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_sock_hash_update; static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, void *buf, unsigned int buf_size) = (void *) BPF_FUNC_perf_event_read_value; @@ -88,6 +93,9 @@ static int (*bpf_override_return)(void *ctx, unsigned long rc) = (void *) BPF_FUNC_override_return; static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_msg_redirect_map; +static int (*bpf_msg_redirect_hash)(void *ctx, + void *map, void *key, int flags) = + (void *) BPF_FUNC_msg_redirect_hash; static int (*bpf_msg_apply_bytes)(void *ctx, int len) = (void *) BPF_FUNC_msg_apply_bytes; static int (*bpf_msg_cork_bytes)(void *ctx, int len) = @@ -96,6 +104,35 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) = (void *) BPF_FUNC_msg_pull_data; static int (*bpf_bind)(void *ctx, void *addr, int addr_len) = (void *) BPF_FUNC_bind; +static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_tail; +static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state, + int size, int flags) = + (void *) BPF_FUNC_skb_get_xfrm_state; +static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) = + (void *) BPF_FUNC_get_stack; +static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params, + int plen, __u32 flags) = + (void *) BPF_FUNC_fib_lookup; +static int (*bpf_lwt_push_encap)(void *ctx, unsigned int type, void *hdr, + unsigned int len) = + (void *) BPF_FUNC_lwt_push_encap; +static int (*bpf_lwt_seg6_store_bytes)(void *ctx, unsigned int offset, + void *from, unsigned int len) = + (void *) BPF_FUNC_lwt_seg6_store_bytes; +static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param, + unsigned int param_len) = + (void *) BPF_FUNC_lwt_seg6_action; +static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset, + unsigned int len) = + (void *) BPF_FUNC_lwt_seg6_adjust_srh; +static int (*bpf_rc_repeat)(void *ctx) = + (void *) BPF_FUNC_rc_repeat; +static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol, + unsigned long long scancode, unsigned int toggle) = + (void *) BPF_FUNC_rc_keydown; +static unsigned long long (*bpf_get_current_cgroup_id)(void) = + (void *) BPF_FUNC_get_current_cgroup_id; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -129,6 +166,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag (void *) BPF_FUNC_l3_csum_replace; static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; +static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) = + (void *) BPF_FUNC_csum_diff; static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = (void *) BPF_FUNC_skb_under_cgroup; static int (*bpf_skb_change_head)(void *, int len, int flags) = diff --git a/tools/testing/selftests/bpf/bpf_rand.h b/tools/testing/selftests/bpf/bpf_rand.h new file mode 100644 index 000000000000..59bf3e1a9371 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_rand.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_RAND__ +#define __BPF_RAND__ + +#include <stdint.h> +#include <stdlib.h> +#include <time.h> + +static inline uint64_t bpf_rand_mask(uint64_t mask) +{ + return (((uint64_t)(uint32_t)rand()) | + ((uint64_t)(uint32_t)rand() << 32)) & mask; +} + +#define bpf_rand_ux(x, m) \ +static inline uint64_t bpf_rand_u##x(int shift) \ +{ \ + return bpf_rand_mask((m)) << shift; \ +} + +bpf_rand_ux( 8, 0xffULL) +bpf_rand_ux(16, 0xffffULL) +bpf_rand_ux(24, 0xffffffULL) +bpf_rand_ux(32, 0xffffffffULL) +bpf_rand_ux(40, 0xffffffffffULL) +bpf_rand_ux(48, 0xffffffffffffULL) +bpf_rand_ux(56, 0xffffffffffffffULL) +bpf_rand_ux(64, 0xffffffffffffffffULL) + +static inline void bpf_semi_rand_init(void) +{ + srand(time(NULL)); +} + +static inline uint64_t bpf_semi_rand_get(void) +{ + switch (rand() % 39) { + case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0); + case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0); + case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0); + case 3: return 0x8000000000000000ULL | bpf_rand_u32(0); + case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0); + case 5: return 0x0000000100000000ULL | bpf_rand_u24(0); + case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0); + case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0); + case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24); + case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0); + case 10: return 0x0000000010000000ULL | bpf_rand_u32(0); + case 11: return 0xf000000000000000ULL | bpf_rand_u8(0); + case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8); + case 13: return 0x000000000f000000ULL | bpf_rand_u8(16); + case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32); + case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48); + case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1); + case 17: return 0xffff800000000000ULL | bpf_rand_u8(4); + case 18: return 0xffff800000000000ULL | bpf_rand_u8(20); + case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0); + case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0); + case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20); + case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40); + case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64); + case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64); + case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64); + case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64); + case 27: return 0x0000800000000000ULL; + case 28: return 0x8000000000000000ULL; + case 29: return 0x0000000000000000ULL; + case 30: return 0xffffffffffffffffULL; + case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64); + case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64); + case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64); + case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64); + case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64); + case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64); + case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64); + default: return bpf_rand_u64(0); + } +} + +#endif /* __BPF_RAND__ */ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index f3bca3ade0f3..c87b4e052ce9 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -6,6 +6,7 @@ #include <sys/types.h> #include <linux/limits.h> #include <stdio.h> +#include <stdlib.h> #include <linux/sched.h> #include <fcntl.h> #include <unistd.h> @@ -176,3 +177,59 @@ int create_and_get_cgroup(char *path) return fd; } + +/** + * get_cgroup_id() - Get cgroup id for a particular cgroup path + * @path: The cgroup path, relative to the workdir, to join + * + * On success, it returns the cgroup id. On failure it returns 0, + * which is an invalid cgroup id. + * If there is a failure, it prints the error to stderr. + */ +unsigned long long get_cgroup_id(char *path) +{ + int dirfd, err, flags, mount_id, fhsize; + union { + unsigned long long cgid; + unsigned char raw_bytes[8]; + } id; + char cgroup_workdir[PATH_MAX + 1]; + struct file_handle *fhp, *fhp2; + unsigned long long ret = 0; + + format_cgroup_path(cgroup_workdir, path); + + dirfd = AT_FDCWD; + flags = 0; + fhsize = sizeof(*fhp); + fhp = calloc(1, fhsize); + if (!fhp) { + log_err("calloc"); + return 0; + } + err = name_to_handle_at(dirfd, cgroup_workdir, fhp, &mount_id, flags); + if (err >= 0 || fhp->handle_bytes != 8) { + log_err("name_to_handle_at"); + goto free_mem; + } + + fhsize = sizeof(struct file_handle) + fhp->handle_bytes; + fhp2 = realloc(fhp, fhsize); + if (!fhp2) { + log_err("realloc"); + goto free_mem; + } + err = name_to_handle_at(dirfd, cgroup_workdir, fhp2, &mount_id, flags); + fhp = fhp2; + if (err < 0) { + log_err("name_to_handle_at"); + goto free_mem; + } + + memcpy(id.raw_bytes, fhp->f_handle, 8); + ret = id.cgid; + +free_mem: + free(fhp); + return ret; +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 06485e0002b3..20a4a5dcd469 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -13,5 +13,6 @@ int create_and_get_cgroup(char *path); int join_cgroup(char *path); int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); +unsigned long long get_cgroup_id(char *path); #endif diff --git a/tools/testing/selftests/bpf/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/get_cgroup_id_kern.c new file mode 100644 index 000000000000..2cf8cb23f209 --- /dev/null +++ b/tools/testing/selftests/bpf/get_cgroup_id_kern.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") cg_ids = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int trace(void *ctx) +{ + __u32 key = 0; + __u64 *val; + + val = bpf_map_lookup_elem(&cg_ids, &key); + if (val) + *val = bpf_get_current_cgroup_id(); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c new file mode 100644 index 000000000000..ea19a42e5894 --- /dev/null +++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <syscall.h> +#include <unistd.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "cgroup_helpers.h" +#include "bpf_rlimit.h" + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s:FAIL:%s ", __func__, tag); \ + printf(format); \ + } else { \ + printf("%s:PASS:%s\n", __func__, tag); \ + } \ + __ret; \ +}) + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) + return -1; + return bpf_map__fd(map); +} + +#define TEST_CGROUP "/test-bpf-get-cgroup-id/" + +int main(int argc, char **argv) +{ + const char *probe_name = "syscalls/sys_enter_nanosleep"; + const char *file = "get_cgroup_id_kern.o"; + int err, bytes, efd, prog_fd, pmu_fd; + struct perf_event_attr attr = {}; + int cgroup_fd, cgidmap_fd; + struct bpf_object *obj; + __u64 kcgid = 0, ucgid; + int exit_code = 1; + char buf[256]; + __u32 key = 0; + + err = setup_cgroup_environment(); + if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err, + errno)) + return 1; + + cgroup_fd = create_and_get_cgroup(TEST_CGROUP); + if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n", + cgroup_fd, errno)) + goto cleanup_cgroup_env; + + err = join_cgroup(TEST_CGROUP); + if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno)) + goto cleanup_cgroup_env; + + err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + goto cleanup_cgroup_env; + + cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids"); + if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + cgidmap_fd, errno)) + goto close_prog; + + snprintf(buf, sizeof(buf), + "/sys/kernel/debug/tracing/events/%s/id", probe_name); + efd = open(buf, O_RDONLY, 0); + if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno)) + goto close_prog; + bytes = read(efd, buf, sizeof(buf)); + close(efd); + if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read", + "bytes %d errno %d\n", bytes, errno)) + goto close_prog; + + attr.config = strtol(buf, NULL, 0); + attr.type = PERF_TYPE_TRACEPOINT; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + + /* attach to this pid so the all bpf invocations will be in the + * cgroup associated with this pid. + */ + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + /* trigger some syscalls */ + sleep(1); + + err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid); + if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno)) + goto close_pmu; + + ucgid = get_cgroup_id(TEST_CGROUP); + if (CHECK(kcgid != ucgid, "compare_cgroup_id", + "kern cgid %llx user cgid %llx", kcgid, ucgid)) + goto close_pmu; + + exit_code = 0; + printf("%s:PASS\n", argv[0]); + +close_pmu: + close(pmu_fd); +close_prog: + bpf_object__close(obj); +cleanup_cgroup_env: + cleanup_cgroup_environment(); + return exit_code; +} diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/sendmsg4_prog.c new file mode 100644 index 000000000000..a91536b1c47e --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg4_prog.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ +#define SRC2_IP4 0x00000000U +#define SRC_REWRITE_IP4 0x7f000004U +#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */ +#define DST_REWRITE_IP4 0x7f000001U +#define DST_PORT 4040 +#define DST_REWRITE_PORT4 4444 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg4") +int sendmsg_v4_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) || + ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) { + ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) && + ctx->user_port == bpf_htons(DST_PORT)) { + ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); + ctx->user_port = bpf_htons(DST_REWRITE_PORT4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c new file mode 100644 index 000000000000..5aeaa284fc47 --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg6_prog.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <sys/socket.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC_REWRITE_IP6_0 0 +#define SRC_REWRITE_IP6_1 0 +#define SRC_REWRITE_IP6_2 0 +#define SRC_REWRITE_IP6_3 6 + +#define DST_REWRITE_IP6_0 0 +#define DST_REWRITE_IP6_1 0 +#define DST_REWRITE_IP6_2 0 +#define DST_REWRITE_IP6_3 1 + +#define DST_REWRITE_PORT6 6666 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg6") +int sendmsg_v6_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip6[3] == bpf_htonl(1) || + ctx->msg_src_ip6[3] == bpf_htonl(0)) { + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && + ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + } else { + /* Unexpected destination. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/test_adjust_tail.c new file mode 100644 index 000000000000..4cd5e860c903 --- /dev/null +++ b/tools/testing/selftests/bpf/test_adjust_tail.c @@ -0,0 +1,30 @@ +/* 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 + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +SEC("xdp_adjust_tail") +int _xdp_adjust_tail(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; + else + offset = 20; + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c new file mode 100644 index 000000000000..3619f3023088 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf.c @@ -0,0 +1,2315 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <bpf/bpf.h> +#include <sys/resource.h> +#include <libelf.h> +#include <gelf.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <unistd.h> +#include <fcntl.h> +#include <errno.h> +#include <bpf/libbpf.h> +#include <bpf/btf.h> + +#include "bpf_rlimit.h" + +static uint32_t pass_cnt; +static uint32_t error_cnt; +static uint32_t skip_cnt; + +#define CHECK(condition, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \ + fprintf(stderr, format); \ + } \ + __ret; \ +}) + +static int count_result(int err) +{ + if (err) + error_cnt++; + else + pass_cnt++; + + fprintf(stderr, "\n"); + return err; +} + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define __printf(a, b) __attribute__((format(printf, a, b))) + +__printf(1, 2) +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +#define BTF_INFO_ENC(kind, root, vlen) \ + ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) + +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) + +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ + (type), (index_type), (nr_elems) +#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ + BTF_ARRAY_ENC(type, index_type, nr_elems) + +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) +#define BTF_ENUM_ENC(name, val) (name), (val) + +#define BTF_TYPEDEF_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) + +#define BTF_PTR_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_END_RAW 0xdeadbeef +#define NAME_TBD 0xdeadb33f + +#define MAX_NR_RAW_TYPES 1024 +#define BTF_LOG_BUF_SIZE 65535 + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +static struct args { + unsigned int raw_test_num; + unsigned int file_test_num; + unsigned int get_info_test_num; + bool raw_test; + bool file_test; + bool get_info_test; + bool pprint_test; + bool always_log; +} args; + +static char btf_log_buf[BTF_LOG_BUF_SIZE]; + +static struct btf_header hdr_tmpl = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), +}; + +struct btf_raw_test { + const char *descr; + const char *str_sec; + const char *map_name; + const char *err_str; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 key_type_id; + __u32 value_type_id; + __u32 max_entries; + bool btf_load_err; + bool map_create_err; + int hdr_len_delta; + int type_off_delta; + int str_off_delta; + int str_len_delta; +}; + +static struct btf_raw_test raw_tests[] = { +/* enum E { + * E0, + * E1, + * }; + * + * struct A { + * unsigned long long m; + * int n; + * char o; + * [3 bytes hole] + * int p[8]; + * int q[4][8]; + * enum E r; + * }; + */ +{ + .descr = "struct test #1", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 6), 180), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + BTF_MEMBER_ENC(NAME_TBD, 6, 384),/* int q[4][8] */ + BTF_MEMBER_ENC(NAME_TBD, 7, 1408), /* enum E r */ + /* } */ + /* int[4][8] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), /* [6] */ + /* enum E */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test1_map", + .key_size = sizeof(int), + .value_size = 180, + .key_type_id = 1, + .value_type_id = 5, + .max_entries = 4, +}, + +/* typedef struct b Struct_B; + * + * struct A { + * int m; + * struct b n[4]; + * const Struct_B o[4]; + * }; + * + * struct B { + * int m; + * int n; + * }; + */ +{ + .descr = "struct test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct b [4] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 3), 68), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct B n[4] */ + BTF_MEMBER_ENC(NAME_TBD, 8, 288),/* const Struct_B o[4];*/ + /* } */ + + /* struct B { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */ + /* } */ + + /* const int */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1), + /* typedef struct b Struct_B */ /* [6] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 4), + /* const Struct_B */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 6), + /* const Struct_B [4] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(7, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0B\0m\0n\0Struct_B", + .str_sec_size = sizeof("\0A\0m\0n\0o\0B\0m\0n\0Struct_B"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test2_map", + .key_size = sizeof(int), + .value_size = 68, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, +}, + +/* Test member exceeds the size of struct. + * + * struct A { + * int m; + * int n; + * }; + */ +{ + .descr = "size check test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check1_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * int n[2]; + * }; + */ +{ + .descr = "size check test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* int[2] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 3 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n[2]; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check2_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * void *n; + * }; + */ +{ + .descr = "size check test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* void* */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) + sizeof(void *) - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* void *n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check3_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* Test member exceeds the size of struct + * + * enum E { + * E0, + * E1, + * }; + * + * struct A { + * int m; + * enum E n; + * }; + */ +{ + .descr = "size check test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* enum E { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + /* } */ + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* enum E n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0E\0E0\0E1\0A\0m\0n", + .str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check4_map", + .key_size = sizeof(int), + .value_size = 1, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Member exceeds struct_size", +}, + +/* typedef const void * const_void_ptr; + * struct A { + * const_void_ptr m; + * }; + */ +{ + .descr = "void test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* struct A { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const_void_ptr m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr\0A\0m", + .str_sec_size = sizeof("\0const_void_ptr\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 4, + .max_entries = 4, +}, + +/* struct A { + * const void m; + * }; + */ +{ + .descr = "void test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 8), + /* const void m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid member", +}, + +/* typedef const void * const_void_ptr; + * const_void_ptr[4] + */ +{ + .descr = "void test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* const_void_ptr[4] */ /* [5] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr", + .str_sec_size = sizeof("\0const_void_ptr"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_type_id = 1, + .value_type_id = 4, + .max_entries = 4, +}, + +/* const void[4] */ +{ + .descr = "void test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void[4] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid elem", +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array A --+ + */ +{ + .descr = "loop test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef is _before_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #2", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* typedef Array_B int_array */ + BTF_TYPEDEF_ENC(1, 4), /* [2] */ + /* Array_A */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), /* [3] */ + /* Array_B */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef is _between_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* typedef Array_B int_array */ /* [3] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* Array_B */ /* [4] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* typedef struct B Struct_B + * + * struct A { + * int x; + * Struct_B y; + * }; + * + * struct B { + * int x; + * struct A y; + * }; + */ +{ + .descr = "loop test #5", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct A */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* Struct_B y; */ + /* typedef struct B Struct_B */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + /* struct B */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A y; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y\0Struct_B\0B\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y\0Struct_B\0B\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test5_map", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +/* struct A { + * int x; + * struct A array_a[4]; + * }; + */ +{ + .descr = "loop test #6", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */ + /* struct A */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A array_a[4]; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test6_map", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "loop test #7", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* CONST type_id=3 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* PTR type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test7_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "loop test #8", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 0), + /* struct B { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *n; */ + BTF_MEMBER_ENC(NAME_TBD, 6, 0), + /* CONST type_id=5 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 5), + /* PTR type_id=6 */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 6), + /* CONST type_id=7 */ /* [6] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 7), + /* PTR type_id=4 */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0B\0n", + .str_sec_size = sizeof("\0A\0m\0B\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test8_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Loop detected", +}, + +{ + .descr = "string section does not end with null", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int") - 1, + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid string section", +}, + +{ + .descr = "empty string section", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = 0, + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid string section", +}, + +{ + .descr = "empty type section", + .raw_types = { + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "No type found", +}, + +{ + .descr = "btf_header test. Longer hdr_len", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .hdr_len_delta = 4, + .err_str = "Unsupported btf_header", +}, + +{ + .descr = "btf_header test. Gap between hdr and type", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .type_off_delta = 4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Gap between type and str", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_off_delta = 4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Overlap between type and str", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_off_delta = -4, + .err_str = "Section overlap found", +}, + +{ + .descr = "btf_header test. Larger BTF size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = -4, + .err_str = "Unsupported section found", +}, + +{ + .descr = "btf_header test. Smaller BTF size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = 4, + .err_str = "Total section length too long", +}, + +{ + .descr = "array test. index_type/elem_type \"int\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 1, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type/elem_type \"const int\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 3, 16), + /* CONST type_id=1 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type \"const int:31\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int:31 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4), + /* int[16] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(1, 4, 16), + /* CONST type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. elem_type \"const int:31\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int:31 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4), + /* int[16] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(4, 1, 16), + /* CONST type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid array of int", +}, + +{ + .descr = "array test. index_type \"void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 0, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. index_type \"const void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 3, 16), + /* CONST type_id=0 (void) */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. elem_type \"const void\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 16), + /* CONST type_id=0 (void) */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid elem", +}, + +{ + .descr = "array test. elem_type \"const void *\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void *[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 16), + /* CONST type_id=4 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* void* */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "array test. index_type \"const void *\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void *[16] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 3, 16), + /* CONST type_id=4 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* void* */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid index", +}, + +{ + .descr = "array test. t->size != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 1), + BTF_ARRAY_ENC(1, 1, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "size != 0", +}, + +{ + .descr = "int test. invalid int_data", + .raw_types = { + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), 4), + 0x10000000, + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid int_data", +}, + +{ + .descr = "invalid BTF_INFO", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_ENC(0, 0x10000000, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid btf_info", +}, + +{ + .descr = "fwd test. t->type != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* fwd type */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FWD, 0, 0), 1), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "fwd_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "type != 0", +}, + +}; /* struct btf_raw_test raw_tests[] */ + +static const char *get_next_str(const char *start, const char *end) +{ + return start < end - 1 ? start + 1 : NULL; +} + +static int get_type_sec_size(const __u32 *raw_types) +{ + int i; + + for (i = MAX_NR_RAW_TYPES - 1; + i >= 0 && raw_types[i] != BTF_END_RAW; + i--) + ; + + return i < 0 ? i : i * sizeof(raw_types[0]); +} + +static void *btf_raw_create(const struct btf_header *hdr, + const __u32 *raw_types, + const char *str, + unsigned int str_sec_size, + unsigned int *btf_size) +{ + const char *next_str = str, *end_str = str + str_sec_size; + unsigned int size_needed, offset; + struct btf_header *ret_hdr; + int i, type_sec_size; + uint32_t *ret_types; + void *raw_btf; + + type_sec_size = get_type_sec_size(raw_types); + if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types")) + return NULL; + + size_needed = sizeof(*hdr) + type_sec_size + str_sec_size; + raw_btf = malloc(size_needed); + if (CHECK(!raw_btf, "Cannot allocate memory for raw_btf")) + return NULL; + + /* Copy header */ + memcpy(raw_btf, hdr, sizeof(*hdr)); + offset = sizeof(*hdr); + + /* Copy type section */ + ret_types = raw_btf + offset; + for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) { + if (raw_types[i] == NAME_TBD) { + next_str = get_next_str(next_str, end_str); + if (CHECK(!next_str, "Error in getting next_str")) { + free(raw_btf); + return NULL; + } + ret_types[i] = next_str - str; + next_str += strlen(next_str); + } else { + ret_types[i] = raw_types[i]; + } + } + offset += type_sec_size; + + /* Copy string section */ + memcpy(raw_btf + offset, str, str_sec_size); + + ret_hdr = (struct btf_header *)raw_btf; + ret_hdr->type_len = type_sec_size; + ret_hdr->str_off = type_sec_size; + ret_hdr->str_len = str_sec_size; + + *btf_size = size_needed; + + return raw_btf; +} + +static int do_test_raw(unsigned int test_num) +{ + struct btf_raw_test *test = &raw_tests[test_num - 1]; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + unsigned int raw_btf_size; + struct btf_header *hdr; + void *raw_btf; + int err; + + fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + hdr = raw_btf; + + hdr->hdr_len = (int)hdr->hdr_len + test->hdr_len_delta; + hdr->type_off = (int)hdr->type_off + test->type_off_delta; + hdr->str_off = (int)hdr->str_off + test->str_off_delta; + hdr->str_len = (int)hdr->str_len + test->str_len_delta; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + err = ((btf_fd == -1) != test->btf_load_err); + if (CHECK(err, "btf_fd:%d test->btf_load_err:%u", + btf_fd, test->btf_load_err) || + CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), + "expected err_str:%s", test->err_str)) { + err = -1; + goto done; + } + + if (err || btf_fd == -1) + goto done; + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_type_id = test->key_type_id; + create_attr.btf_value_type_id = test->value_type_id; + + map_fd = bpf_create_map_xattr(&create_attr); + + err = ((map_fd == -1) != test->map_create_err); + CHECK(err, "map_fd:%d test->map_create_err:%u", + map_fd, test->map_create_err); + +done: + if (!err) + fprintf(stderr, "OK"); + + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + + return err; +} + +static int test_raw(void) +{ + unsigned int i; + int err = 0; + + if (args.raw_test_num) + return count_result(do_test_raw(args.raw_test_num)); + + for (i = 1; i <= ARRAY_SIZE(raw_tests); i++) + err |= count_result(do_test_raw(i)); + + return err; +} + +struct btf_get_info_test { + const char *descr; + const char *str_sec; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + int btf_size_delta; + int (*special_test)(unsigned int test_num); +}; + +static int test_big_btf_info(unsigned int test_num); +static int test_btf_id(unsigned int test_num); + +const struct btf_get_info_test get_info_tests[] = { +{ + .descr = "== raw_btf_size+1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .btf_size_delta = 1, +}, +{ + .descr = "== raw_btf_size-3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .btf_size_delta = -3, +}, +{ + .descr = "Large bpf_btf_info", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .special_test = test_big_btf_info, +}, +{ + .descr = "BTF ID", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* unsigned int */ /* [2] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .special_test = test_btf_id, +}, +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static int test_big_btf_info(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + uint8_t *raw_btf = NULL, *user_btf = NULL; + unsigned int raw_btf_size; + struct { + struct bpf_btf_info info; + uint64_t garbage; + } info_garbage; + struct bpf_btf_info *info; + int btf_fd = -1, err; + uint32_t info_len; + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + user_btf = malloc(raw_btf_size); + if (CHECK(!user_btf, "!user_btf")) { + err = -1; + goto done; + } + + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + /* + * GET_INFO should error out if the userspace info + * has non zero tailing bytes. + */ + info = &info_garbage.info; + memset(info, 0, sizeof(*info)); + info_garbage.garbage = 0xdeadbeef; + info_len = sizeof(info_garbage); + info->btf = ptr_to_u64(user_btf); + info->btf_size = raw_btf_size; + + err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + if (CHECK(!err, "!err")) { + err = -1; + goto done; + } + + /* + * GET_INFO should succeed even info_len is larger than + * the kernel supported as long as tailing bytes are zero. + * The kernel supported info len should also be returned + * to userspace. + */ + info_garbage.garbage = 0; + err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + if (CHECK(err || info_len != sizeof(*info), + "err:%d errno:%d info_len:%u sizeof(*info):%lu", + err, errno, info_len, sizeof(*info))) { + err = -1; + goto done; + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + free(user_btf); + + if (btf_fd != -1) + close(btf_fd); + + return err; +} + +static int test_btf_id(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + struct bpf_create_map_attr create_attr = {}; + uint8_t *raw_btf = NULL, *user_btf[2] = {}; + int btf_fd[2] = {-1, -1}, map_fd = -1; + struct bpf_map_info map_info = {}; + struct bpf_btf_info info[2] = {}; + unsigned int raw_btf_size; + uint32_t info_len; + int err, i, ret; + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + for (i = 0; i < 2; i++) { + user_btf[i] = malloc(raw_btf_size); + if (CHECK(!user_btf[i], "!user_btf[%d]", i)) { + err = -1; + goto done; + } + info[i].btf = ptr_to_u64(user_btf[i]); + info[i].btf_size = raw_btf_size; + } + + btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + /* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */ + info_len = sizeof(info[0]); + err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len); + if (CHECK(err, "errno:%d", errno)) { + err = -1; + goto done; + } + + btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id); + if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + ret = 0; + err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len); + if (CHECK(err || info[0].id != info[1].id || + info[0].btf_size != info[1].btf_size || + (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)), + "err:%d errno:%d id0:%u id1:%u btf_size0:%u btf_size1:%u memcmp:%d", + err, errno, info[0].id, info[1].id, + info[0].btf_size, info[1].btf_size, ret)) { + err = -1; + goto done; + } + + /* Test btf members in struct bpf_map_info */ + create_attr.name = "test_btf_id"; + create_attr.map_type = BPF_MAP_TYPE_ARRAY; + create_attr.key_size = sizeof(int); + create_attr.value_size = sizeof(unsigned int); + create_attr.max_entries = 4; + create_attr.btf_fd = btf_fd[0]; + create_attr.btf_key_type_id = 1; + create_attr.btf_value_type_id = 2; + + map_fd = bpf_create_map_xattr(&create_attr); + if (CHECK(map_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + info_len = sizeof(map_info); + err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + if (CHECK(err || map_info.btf_id != info[0].id || + map_info.btf_key_type_id != 1 || map_info.btf_value_type_id != 2, + "err:%d errno:%d info.id:%u btf_id:%u btf_key_type_id:%u btf_value_type_id:%u", + err, errno, info[0].id, map_info.btf_id, map_info.btf_key_type_id, + map_info.btf_value_type_id)) { + err = -1; + goto done; + } + + for (i = 0; i < 2; i++) { + close(btf_fd[i]); + btf_fd[i] = -1; + } + + /* Test BTF ID is removed from the kernel */ + btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); + if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + close(btf_fd[0]); + btf_fd[0] = -1; + + /* The map holds the last ref to BTF and its btf_id */ + close(map_fd); + map_fd = -1; + btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); + if (CHECK(btf_fd[0] != -1, "BTF lingers")) { + err = -1; + goto done; + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + if (map_fd != -1) + close(map_fd); + for (i = 0; i < 2; i++) { + free(user_btf[i]); + if (btf_fd[i] != -1) + close(btf_fd[i]); + } + + return err; +} + +static int do_test_get_info(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + unsigned int raw_btf_size, user_btf_size, expected_nbytes; + uint8_t *raw_btf = NULL, *user_btf = NULL; + struct bpf_btf_info info = {}; + int btf_fd = -1, err, ret; + uint32_t info_len; + + fprintf(stderr, "BTF GET_INFO test[%u] (%s): ", + test_num, test->descr); + + if (test->special_test) + return test->special_test(test_num); + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + user_btf = malloc(raw_btf_size); + if (CHECK(!user_btf, "!user_btf")) { + err = -1; + goto done; + } + + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + user_btf_size = (int)raw_btf_size + test->btf_size_delta; + expected_nbytes = min(raw_btf_size, user_btf_size); + if (raw_btf_size > expected_nbytes) + memset(user_btf + expected_nbytes, 0xff, + raw_btf_size - expected_nbytes); + + info_len = sizeof(info); + info.btf = ptr_to_u64(user_btf); + info.btf_size = user_btf_size; + + ret = 0; + err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len); + if (CHECK(err || !info.id || info_len != sizeof(info) || + info.btf_size != raw_btf_size || + (ret = memcmp(raw_btf, user_btf, expected_nbytes)), + "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", + err, errno, info.id, info_len, sizeof(info), + raw_btf_size, info.btf_size, expected_nbytes, ret)) { + err = -1; + goto done; + } + + while (expected_nbytes < raw_btf_size) { + fprintf(stderr, "%u...", expected_nbytes); + if (CHECK(user_btf[expected_nbytes++] != 0xff, + "user_btf[%u]:%x != 0xff", expected_nbytes - 1, + user_btf[expected_nbytes - 1])) { + err = -1; + goto done; + } + } + + fprintf(stderr, "OK"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + free(raw_btf); + free(user_btf); + + if (btf_fd != -1) + close(btf_fd); + + return err; +} + +static int test_get_info(void) +{ + unsigned int i; + int err = 0; + + if (args.get_info_test_num) + return count_result(do_test_get_info(args.get_info_test_num)); + + for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++) + err |= count_result(do_test_get_info(i)); + + return err; +} + +struct btf_file_test { + const char *file; + bool btf_kv_notfound; +}; + +static struct btf_file_test file_tests[] = { +{ + .file = "test_btf_haskv.o", +}, +{ + .file = "test_btf_nokv.o", + .btf_kv_notfound = true, +}, +}; + +static int file_has_btf_elf(const char *fn) +{ + Elf_Scn *scn = NULL; + GElf_Ehdr ehdr; + int elf_fd; + Elf *elf; + int ret; + + if (CHECK(elf_version(EV_CURRENT) == EV_NONE, + "elf_version(EV_CURRENT) == EV_NONE")) + return -1; + + elf_fd = open(fn, O_RDONLY); + if (CHECK(elf_fd == -1, "open(%s): errno:%d", fn, errno)) + return -1; + + elf = elf_begin(elf_fd, ELF_C_READ, NULL); + if (CHECK(!elf, "elf_begin(%s): %s", fn, elf_errmsg(elf_errno()))) { + ret = -1; + goto done; + } + + if (CHECK(!gelf_getehdr(elf, &ehdr), "!gelf_getehdr(%s)", fn)) { + ret = -1; + goto done; + } + + while ((scn = elf_nextscn(elf, scn))) { + const char *sh_name; + GElf_Shdr sh; + + if (CHECK(gelf_getshdr(scn, &sh) != &sh, + "file:%s gelf_getshdr != &sh", fn)) { + ret = -1; + goto done; + } + + sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!strcmp(sh_name, BTF_ELF_SEC)) { + ret = 1; + goto done; + } + } + + ret = 0; + +done: + close(elf_fd); + elf_end(elf); + return ret; +} + +static int do_test_file(unsigned int test_num) +{ + const struct btf_file_test *test = &file_tests[test_num - 1]; + struct bpf_object *obj = NULL; + struct bpf_program *prog; + struct bpf_map *map; + int err; + + fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num, + test->file); + + err = file_has_btf_elf(test->file); + if (err == -1) + return err; + + if (err == 0) { + fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC); + skip_cnt++; + return 0; + } + + obj = bpf_object__open(test->file); + if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj))) + return PTR_ERR(obj); + + err = bpf_object__btf_fd(obj); + if (CHECK(err == -1, "bpf_object__btf_fd: -1")) + goto done; + + prog = bpf_program__next(NULL, obj); + if (CHECK(!prog, "Cannot find bpf_prog")) { + err = -1; + goto done; + } + + bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); + err = bpf_object__load(obj); + if (CHECK(err < 0, "bpf_object__load: %d", err)) + goto done; + + map = bpf_object__find_map_by_name(obj, "btf_map"); + if (CHECK(!map, "btf_map not found")) { + err = -1; + goto done; + } + + err = (bpf_map__btf_key_type_id(map) == 0 || bpf_map__btf_value_type_id(map) == 0) + != test->btf_kv_notfound; + if (CHECK(err, "btf_key_type_id:%u btf_value_type_id:%u test->btf_kv_notfound:%u", + bpf_map__btf_key_type_id(map), bpf_map__btf_value_type_id(map), + test->btf_kv_notfound)) + goto done; + + fprintf(stderr, "OK"); + +done: + bpf_object__close(obj); + return err; +} + +static int test_file(void) +{ + unsigned int i; + int err = 0; + + if (args.file_test_num) + return count_result(do_test_file(args.file_test_num)); + + for (i = 1; i <= ARRAY_SIZE(file_tests); i++) + err |= count_result(do_test_file(i)); + + return err; +} + +const char *pprint_enum_str[] = { + "ENUM_ZERO", + "ENUM_ONE", + "ENUM_TWO", + "ENUM_THREE", +}; + +struct pprint_mapv { + uint32_t ui32; + uint16_t ui16; + /* 2 bytes hole */ + int32_t si32; + uint32_t unused_bits2a:2, + bits28:28, + unused_bits2b:2; + union { + uint64_t ui64; + uint8_t ui8a[8]; + }; + enum { + ENUM_ZERO, + ENUM_ONE, + ENUM_TWO, + ENUM_THREE, + } aenum; +}; + +static struct btf_raw_test pprint_test = { + .descr = "BTF pretty print test #1", + .raw_types = { + /* unsighed char */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1), + /* unsigned short */ /* [2] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2), + /* unsigned int */ /* [3] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), + /* int */ /* [4] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + /* unsigned long long */ /* [5] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8), + /* 2 bits */ /* [6] */ + BTF_TYPE_INT_ENC(0, 0, 0, 2, 2), + /* 28 bits */ /* [7] */ + BTF_TYPE_INT_ENC(0, 0, 0, 28, 4), + /* uint8_t[8] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(9, 1, 8), + /* typedef unsigned char uint8_t */ /* [9] */ + BTF_TYPEDEF_ENC(NAME_TBD, 1), + /* typedef unsigned short uint16_t */ /* [10] */ + BTF_TYPEDEF_ENC(NAME_TBD, 2), + /* typedef unsigned int uint32_t */ /* [11] */ + BTF_TYPEDEF_ENC(NAME_TBD, 3), + /* typedef int int32_t */ /* [12] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* typedef unsigned long long uint64_t *//* [13] */ + BTF_TYPEDEF_ENC(NAME_TBD, 5), + /* union (anon) */ /* [14] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */ + BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */ + /* enum (anon) */ /* [15] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_ENUM_ENC(NAME_TBD, 2), + BTF_ENUM_ENC(NAME_TBD, 3), + /* struct pprint_mapv */ /* [16] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ + BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ + BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 96), /* unused_bits2a */ + BTF_MEMBER_ENC(NAME_TBD, 7, 98), /* bits28 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 126), /* unused_bits2b */ + BTF_MEMBER_ENC(0, 14, 128), /* union (anon) */ + BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */ + BTF_END_RAW, + }, + .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum", + .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "pprint_test", + .key_size = sizeof(unsigned int), + .value_size = sizeof(struct pprint_mapv), + .key_type_id = 3, /* unsigned int */ + .value_type_id = 16, /* struct pprint_mapv */ + .max_entries = 128 * 1024, +}; + +static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i) +{ + v->ui32 = i; + v->si32 = -i; + v->unused_bits2a = 3; + v->bits28 = i; + v->unused_bits2b = 3; + v->ui64 = i; + v->aenum = i & 0x03; +} + +static int test_pprint(void) +{ + const struct btf_raw_test *test = &pprint_test; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + struct pprint_mapv mapv = {}; + unsigned int raw_btf_size; + char expected_line[255]; + FILE *pin_file = NULL; + char pin_path[255]; + size_t line_len = 0; + char *line = NULL; + unsigned int key; + uint8_t *raw_btf; + ssize_t nread; + int err, ret; + + fprintf(stderr, "%s......", test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, + test->str_sec, test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + if (CHECK(btf_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_type_id = test->key_type_id; + create_attr.btf_value_type_id = test->value_type_id; + + map_fd = bpf_create_map_xattr(&create_attr); + if (CHECK(map_fd == -1, "errno:%d", errno)) { + err = -1; + goto done; + } + + ret = snprintf(pin_path, sizeof(pin_path), "%s/%s", + "/sys/fs/bpf", test->map_name); + + if (CHECK(ret == sizeof(pin_path), "pin_path %s/%s is too long", + "/sys/fs/bpf", test->map_name)) { + err = -1; + goto done; + } + + err = bpf_obj_pin(map_fd, pin_path); + if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno)) + goto done; + + for (key = 0; key < test->max_entries; key++) { + set_pprint_mapv(&mapv, key); + bpf_map_update_elem(map_fd, &key, &mapv, 0); + } + + pin_file = fopen(pin_path, "r"); + if (CHECK(!pin_file, "fopen(%s): errno:%d", pin_path, errno)) { + err = -1; + goto done; + } + + /* Skip lines start with '#' */ + while ((nread = getline(&line, &line_len, pin_file)) > 0 && + *line == '#') + ; + + if (CHECK(nread <= 0, "Unexpected EOF")) { + err = -1; + goto done; + } + + key = 0; + do { + ssize_t nexpected_line; + + set_pprint_mapv(&mapv, key); + nexpected_line = snprintf(expected_line, sizeof(expected_line), + "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", + key, + mapv.ui32, mapv.si32, + mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b, + mapv.ui64, + mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3], + mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7], + pprint_enum_str[mapv.aenum]); + + if (CHECK(nexpected_line == sizeof(expected_line), + "expected_line is too long")) { + err = -1; + goto done; + } + + if (strcmp(expected_line, line)) { + err = -1; + fprintf(stderr, "unexpected pprint output\n"); + fprintf(stderr, "expected: %s", expected_line); + fprintf(stderr, " read: %s", line); + goto done; + } + + nread = getline(&line, &line_len, pin_file); + } while (++key < test->max_entries && nread > 0); + + if (CHECK(key < test->max_entries, + "Unexpected EOF. key:%u test->max_entries:%u", + key, test->max_entries)) { + err = -1; + goto done; + } + + if (CHECK(nread > 0, "Unexpected extra pprint output: %s", line)) { + err = -1; + goto done; + } + + err = 0; + +done: + if (!err) + fprintf(stderr, "OK"); + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + if (pin_file) + fclose(pin_file); + unlink(pin_path); + free(line); + + return err; +} + +static void usage(const char *cmd) +{ + fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n", + cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests), + ARRAY_SIZE(file_tests)); +} + +static int parse_args(int argc, char **argv) +{ + const char *optstr = "lpf:r:g:"; + int opt; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'l': + args.always_log = true; + break; + case 'f': + args.file_test_num = atoi(optarg); + args.file_test = true; + break; + case 'r': + args.raw_test_num = atoi(optarg); + args.raw_test = true; + break; + case 'g': + args.get_info_test_num = atoi(optarg); + args.get_info_test = true; + break; + case 'p': + args.pprint_test = true; + break; + case 'h': + usage(argv[0]); + exit(0); + default: + usage(argv[0]); + return -1; + } + } + + if (args.raw_test_num && + (args.raw_test_num < 1 || + args.raw_test_num > ARRAY_SIZE(raw_tests))) { + fprintf(stderr, "BTF raw test number must be [1 - %zu]\n", + ARRAY_SIZE(raw_tests)); + return -1; + } + + if (args.file_test_num && + (args.file_test_num < 1 || + args.file_test_num > ARRAY_SIZE(file_tests))) { + fprintf(stderr, "BTF file test number must be [1 - %zu]\n", + ARRAY_SIZE(file_tests)); + return -1; + } + + if (args.get_info_test_num && + (args.get_info_test_num < 1 || + args.get_info_test_num > ARRAY_SIZE(get_info_tests))) { + fprintf(stderr, "BTF get info test number must be [1 - %zu]\n", + ARRAY_SIZE(get_info_tests)); + return -1; + } + + return 0; +} + +static void print_summary(void) +{ + fprintf(stderr, "PASS:%u SKIP:%u FAIL:%u\n", + pass_cnt - skip_cnt, skip_cnt, error_cnt); +} + +int main(int argc, char **argv) +{ + int err = 0; + + err = parse_args(argc, argv); + if (err) + return err; + + if (args.always_log) + libbpf_set_print(__base_pr, __base_pr, __base_pr); + + if (args.raw_test) + err |= test_raw(); + + if (args.get_info_test) + err |= test_get_info(); + + if (args.file_test) + err |= test_file(); + + if (args.pprint_test) + err |= count_result(test_pprint()); + + if (args.raw_test || args.get_info_test || args.file_test || + args.pprint_test) + goto done; + + err |= test_raw(); + err |= test_get_info(); + err |= test_file(); + +done: + print_summary(); + return err; +} diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c new file mode 100644 index 000000000000..8c7ca096ecf2 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +typedef int btf_map_key; +typedef struct ipv_counts btf_map_value; +btf_map_key dumm_key; +btf_map_value dummy_value; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c new file mode 100644 index 000000000000..0ed8e088eebf --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_nokv.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/test_get_stack_rawtp.c new file mode 100644 index 000000000000..f6d9f238e00a --- /dev/null +++ b/tools/testing/selftests/bpf/test_get_stack_rawtp.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +/* Permit pretty deep stack traces */ +#define MAX_STACK_RAWTP 100 +struct stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +struct bpf_map_def SEC("maps") perfmap = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(__u32), + .max_entries = 2, +}; + +struct bpf_map_def SEC("maps") stackdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct stack_trace_t), + .max_entries = 1, +}; + +/* Allocate per-cpu space twice the needed. For the code below + * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + * if (usize < 0) + * return 0; + * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + * + * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64), + * verifier will complain that access "raw_data + usize" + * with size "max_len - usize" may be out of bound. + * The maximum "raw_data + usize" is "raw_data + max_len" + * and the maximum "max_len - usize" is "max_len", verifier + * concludes that the maximum buffer access range is + * "raw_data[0...max_len * 2 - 1]" and hence reject the program. + * + * Doubling the to-be-used max buffer size can fix this verifier + * issue and avoid complicated C programming massaging. + * This is an acceptable workaround since there is one entry here. + */ +struct bpf_map_def SEC("maps") rawdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, + .max_entries = 1, +}; + +SEC("tracepoint/raw_syscalls/sys_enter") +int bpf_prog1(void *ctx) +{ + int max_len, max_buildid_len, usize, ksize, total_size; + struct stack_trace_t *data; + void *raw_data; + __u32 key = 0; + + data = bpf_map_lookup_elem(&stackdata_map, &key); + if (!data) + return 0; + + max_len = MAX_STACK_RAWTP * sizeof(__u64); + max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id); + data->pid = bpf_get_current_pid_tgid(); + data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack, + max_len, 0); + data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len, + BPF_F_USER_STACK); + data->user_stack_buildid_size = bpf_get_stack( + ctx, data->user_stack_buildid, max_buildid_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data)); + + /* write both kernel and user stacks to the same buffer */ + raw_data = bpf_map_lookup_elem(&rawdata_map, &key); + if (!raw_data) + return 0; + + usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + if (usize < 0) + return 0; + + ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + if (ksize < 0) + return 0; + + total_size = usize + ksize; + if (total_size > 0 && total_size <= max_len) + bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh new file mode 100755 index 000000000000..ce2e15e4f976 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -0,0 +1,28 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +modprobe rc-loopback + +for i in /sys/class/rc/rc* +do + if grep -q DRV_NAME=rc-loopback $i/uevent + then + LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q) + fi +done + +if [ -n $LIRCDEV ]; +then + TYPE=lirc_mode2 + ./test_lirc_mode2_user $LIRCDEV + ret=$? + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + else + echo -e ${GREEN}"PASS: $TYPE"${NC} + fi +fi diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c new file mode 100644 index 000000000000..ba26855563a5 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// test ir decoder +// +// Copyright (C) 2018 Sean Young <sean@mess.org> + +#include <linux/bpf.h> +#include <linux/lirc.h> +#include "bpf_helpers.h" + +SEC("lirc_mode2") +int bpf_decoder(unsigned int *sample) +{ + if (LIRC_IS_PULSE(*sample)) { + unsigned int duration = LIRC_VALUE(*sample); + + if (duration & 0x10000) + bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c new file mode 100644 index 000000000000..d470d63c33db --- /dev/null +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +// test ir decoder +// +// Copyright (C) 2018 Sean Young <sean@mess.org> + +// A lirc chardev is a device representing a consumer IR (cir) device which +// can receive infrared signals from remote control and/or transmit IR. +// +// IR is sent as a series of pulses and space somewhat like morse code. The +// BPF program can decode this into scancodes so that rc-core can translate +// this into input key codes using the rc keymap. +// +// This test works by sending IR over rc-loopback, so the IR is processed by +// BPF and then decoded into scancodes. The lirc chardev must be the one +// associated with rc-loopback, see the output of ir-keytable(1). +// +// The following CONFIG options must be enabled for the test to succeed: +// CONFIG_RC_CORE=y +// CONFIG_BPF_RAWIR_EVENT=y +// CONFIG_RC_LOOPBACK=y + +// Steps: +// 1. Open the /dev/lircN device for rc-loopback (given on command line) +// 2. Attach bpf_lirc_mode2 program which decodes some IR. +// 3. Send some IR to the same IR device; since it is loopback, this will +// end up in the bpf program +// 4. bpf program should decode IR and report keycode +// 5. We can read keycode from same /dev/lirc device + +#include <linux/bpf.h> +#include <linux/lirc.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <poll.h> +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <fcntl.h> + +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +int main(int argc, char **argv) +{ + struct bpf_object *obj; + int ret, lircfd, progfd, mode; + int testir = 0x1dead; + u32 prog_ids[10], prog_flags[10], prog_cnt; + + if (argc != 2) { + printf("Usage: %s /dev/lircN\n", argv[0]); + return 2; + } + + ret = bpf_prog_load("test_lirc_mode2_kern.o", + BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd); + if (ret) { + printf("Failed to load bpf program\n"); + return 1; + } + + lircfd = open(argv[1], O_RDWR | O_NONBLOCK); + if (lircfd == -1) { + printf("failed to open lirc device %s: %m\n", argv[1]); + return 1; + } + + /* Let's try detach it before it was ever attached */ + ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); + if (ret != -1 || errno != ENOENT) { + printf("bpf_prog_detach2 not attached should fail: %m\n"); + return 1; + } + + mode = LIRC_MODE_SCANCODE; + if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) { + printf("failed to set rec mode: %m\n"); + return 1; + } + + prog_cnt = 10; + ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids, + &prog_cnt); + if (ret) { + printf("Failed to query bpf programs on lirc device: %m\n"); + return 1; + } + + if (prog_cnt != 0) { + printf("Expected nothing to be attached\n"); + return 1; + } + + ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0); + if (ret) { + printf("Failed to attach bpf to lirc device: %m\n"); + return 1; + } + + /* Write raw IR */ + ret = write(lircfd, &testir, sizeof(testir)); + if (ret != sizeof(testir)) { + printf("Failed to send test IR message: %m\n"); + return 1; + } + + struct pollfd pfd = { .fd = lircfd, .events = POLLIN }; + struct lirc_scancode lsc; + + poll(&pfd, 1, 100); + + /* Read decoded IR */ + ret = read(lircfd, &lsc, sizeof(lsc)); + if (ret != sizeof(lsc)) { + printf("Failed to read decoded IR: %m\n"); + return 1; + } + + if (lsc.scancode != 0xdead || lsc.rc_proto != 64) { + printf("Incorrect scancode decoded\n"); + return 1; + } + + prog_cnt = 10; + ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids, + &prog_cnt); + if (ret) { + printf("Failed to query bpf programs on lirc device: %m\n"); + return 1; + } + + if (prog_cnt != 1) { + printf("Expected one program to be attached\n"); + return 1; + } + + /* Let's try detaching it now it is actually attached */ + ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); + if (ret) { + printf("bpf_prog_detach2: returned %m\n"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/test_lwt_seg6local.c new file mode 100644 index 000000000000..0575751bc1bc --- /dev/null +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.c @@ -0,0 +1,437 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \ + 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32)) +#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \ + 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32)) +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +__attribute__((always_inline)) +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +__attribute__((always_inline)) +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(full) + for (int i = 0; i < 10; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +__attribute__((always_inline)) +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +__attribute__((always_inline)) +int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t tlv_off) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t partial_srh_len; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + struct sr6_tlv_t tlv; + int err; + + tlv_off += srh_off; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_skb_load_bytes(skb, tlv_off, &tlv, sizeof(tlv)); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, -(sizeof(tlv) + tlv.len)); + if (err) + return err; + + pad_off -= sizeof(tlv) + tlv.len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +__attribute__((always_inline)) +int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh) +{ + int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) + + ((srh->first_segment + 1) << 4); + struct sr6_tlv_t tlv; + + if (bpf_skb_load_bytes(skb, tlv_offset, &tlv, sizeof(struct sr6_tlv_t))) + return 0; + + if (tlv.type == SR6_TLV_EGRESS && tlv.len == 18) { + struct ip6_addr_t egr_addr; + + if (bpf_skb_load_bytes(skb, tlv_offset + 4, &egr_addr, 16)) + return 0; + + // check if egress TLV value is correct + if (ntohll(egr_addr.hi) == 0xfd00000000000000 && + ntohll(egr_addr.lo) == 0x4) + return 1; + } + + return 0; +} + +// This function will push a SRH with segments fd00::1, fd00::2, fd00::3, +// fd00::4 +SEC("encap_srh") +int __encap_srh(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfd00000000000000; + struct ip6_addr_t *seg; + struct ip6_srh_t *srh; + char srh_buf[72]; // room for 4 segments + int err; + + srh = (struct ip6_srh_t *)srh_buf; + srh->nexthdr = 0; + srh->hdrlen = 8; + srh->type = 4; + srh->segments_left = 3; + srh->first_segment = 3; + srh->flags = 0; + srh->tag = 0; + + seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh)); + + #pragma clang loop unroll(full) + for (unsigned long long lo = 0; lo < 4; lo++) { + seg->lo = htonll(4 - lo); + seg->hi = htonll(hi); + seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg)); + } + + err = bpf_lwt_push_encap(skb, 0, (void *)srh, sizeof(srh_buf)); + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("add_egr_x") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = htonll(lo); + addr.hi = htonll(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} + +// Pop the Egress TLV, reset the flags, change the tag 2442 and finally do a +// simple End action +SEC("pop_egr") +int __pop_egr(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + uint16_t new_tag = bpf_htons(2442); + uint8_t new_flags = 0; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != SR6_FLAG_ALERT) + return BPF_DROP; + + if (srh->hdrlen != 11) // 4 segments + Egress TLV + Padding TLV + return BPF_DROP; + + if (!has_egr_tlv(skb, srh)) + return BPF_DROP; + + err = delete_tlv(skb, srh, 8 + (srh->first_segment + 1) * 16); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_flags, + sizeof(new_flags))) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, tag); + if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_tag, + sizeof(new_tag))) + return BPF_DROP; + + return BPF_OK; +} + +// Inspect if the Egress TLV and flag have been removed, if the tag is correct, +// then apply a End.T action to reach the last segment +SEC("inspect_t") +int __inspect_t(struct __sk_buff *skb) +{ + struct ip6_srh_t *srh = get_srh(skb); + int table = 117; + int err; + + if (srh == NULL) + return BPF_DROP; + + if (srh->flags != 0) + return BPF_DROP; + + if (srh->tag != bpf_htons(2442)) + return BPF_DROP; + + if (srh->hdrlen != 8) // 4 segments + return BPF_DROP; + + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_T, + (void *)&table, sizeof(table)); + + if (err) + return BPF_DROP; + + return BPF_REDIRECT; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh new file mode 100755 index 000000000000..1c77994b5e71 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -0,0 +1,140 @@ +#!/bin/bash +# Connects 6 network namespaces through veths. +# Each NS may have different IPv6 global scope addresses : +# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6 +# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6 +# fc42::1 fd00::4 +# +# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a +# IPv6 header with a Segment Routing Header, with segments : +# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4 +# +# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions : +# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1 +# - fd00::2 : remove the TLV, change the flags, add a tag +# - fd00::3 : apply an End.T action to fd00::4, through routing table 117 +# +# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet. +# Each End.BPF action will validate the operations applied on the SRH by the +# previous BPF program in the chain, otherwise the packet is dropped. +# +# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this +# datagram can be read on NS6 when binding to fb00::6. + +TMP_FILE="/tmp/selftest_lwt_seg6local.txt" + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_lwt_seg6local [PASS]"; + else + echo "selftests: test_lwt_seg6local [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null + ip netns del ns3 2> /dev/null + ip netns del ns4 2> /dev/null + ip netns del ns5 2> /dev/null + ip netns del ns6 2> /dev/null + rm -f $TMP_FILE +} + +set -e + +ip netns add ns1 +ip netns add ns2 +ip netns add ns3 +ip netns add ns4 +ip netns add ns5 +ip netns add ns6 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 type veth peer name veth2 +ip link add veth3 type veth peer name veth4 +ip link add veth5 type veth peer name veth6 +ip link add veth7 type veth peer name veth8 +ip link add veth9 type veth peer name veth10 + +ip link set veth1 netns ns1 +ip link set veth2 netns ns2 +ip link set veth3 netns ns2 +ip link set veth4 netns ns3 +ip link set veth5 netns ns3 +ip link set veth6 netns ns4 +ip link set veth7 netns ns4 +ip link set veth8 netns ns5 +ip link set veth9 netns ns5 +ip link set veth10 netns ns6 + +ip netns exec ns1 ip link set dev veth1 up +ip netns exec ns2 ip link set dev veth2 up +ip netns exec ns2 ip link set dev veth3 up +ip netns exec ns3 ip link set dev veth4 up +ip netns exec ns3 ip link set dev veth5 up +ip netns exec ns4 ip link set dev veth6 up +ip netns exec ns4 ip link set dev veth7 up +ip netns exec ns5 ip link set dev veth8 up +ip netns exec ns5 ip link set dev veth9 up +ip netns exec ns6 ip link set dev veth10 up +ip netns exec ns6 ip link set dev lo up + +# All link scope addresses and routes required between veths +ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link +ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link +ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link +ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link +ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link +ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link +ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link +ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link +ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link +ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link +ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link +ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link +ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link +ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link +ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link +ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link + +ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo +ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21 + +ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 +ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link + +ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 +ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4 + +ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ns4 ip -6 addr add fc42::1 dev lo +ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 + +ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 +ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8 + +ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo +ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo + +ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + +ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null +ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null +ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null + +ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & +ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" +sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment +kill -INT $! + +if [[ $(< $TMP_FILE) != "foobar" ]]; then + exit 1 +fi + +exit 0 diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 4123d0ab90ba..0ef68204c84b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -38,8 +38,10 @@ typedef __u16 __sum16; #include "bpf_util.h" #include "bpf_endian.h" #include "bpf_rlimit.h" +#include "trace_helpers.h" static int error_cnt, pass_cnt; +static bool jit_enabled; #define MAGIC_BYTES 123 @@ -166,6 +168,37 @@ out: bpf_object__close(obj); } +static void test_xdp_adjust_tail(void) +{ + const char *file = "./test_adjust_tail.o"; + struct bpf_object *obj; + char buf[128]; + __u32 duration, retval, size; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + CHECK(err || errno || retval != XDP_DROP, + "ipv4", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != XDP_TX || size != 54, + "ipv6", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + bpf_object__close(obj); +} + + + #define MAGIC_VAL 0x1234 #define NUM_ITER 100000 #define VIP_NUM 5 @@ -360,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} + static 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 *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; @@ -383,20 +433,11 @@ static void test_bpf_obj_id(void) char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; - int sysctl_fd, jit_enabled = 0, err = 0; + int err = 0; __u64 array_value; uid_t my_uid = getuid(); time_t now, load_time; - sysctl_fd = open(jit_sysctl, 0, O_RDONLY); - if (sysctl_fd != -1) { - char tmpc; - - if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) - jit_enabled = (tmpc != '0'); - close(sysctl_fd); - } - err = bpf_prog_get_fd_by_id(0); CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); @@ -865,11 +906,47 @@ static int compare_map_keys(int map1_fd, int map2_fd) return 0; } +static int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len) +{ + __u32 key, next_key, *cur_key_p, *next_key_p; + char *val_buf1, *val_buf2; + int i, err = 0; + + val_buf1 = malloc(stack_trace_len); + val_buf2 = malloc(stack_trace_len); + cur_key_p = NULL; + next_key_p = &key; + while (bpf_map_get_next_key(smap_fd, cur_key_p, next_key_p) == 0) { + err = bpf_map_lookup_elem(smap_fd, next_key_p, val_buf1); + if (err) + goto out; + err = bpf_map_lookup_elem(amap_fd, next_key_p, val_buf2); + if (err) + goto out; + for (i = 0; i < stack_trace_len; i++) { + if (val_buf1[i] != val_buf2[i]) { + err = -1; + goto out; + } + } + key = *next_key_p; + cur_key_p = &key; + next_key_p = &next_key; + } + if (errno != ENOENT) + err = -1; + +out: + free(val_buf1); + free(val_buf2); + return err; +} + static void test_stacktrace_map() { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_map.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, val, duration = 0; struct bpf_object *obj; @@ -925,6 +1002,10 @@ static void test_stacktrace_map() if (stackmap_fd < 0) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (stack_amap_fd < 0) + goto disable_pmu; + /* give some time for bpf program run */ sleep(1); @@ -946,6 +1027,12 @@ static void test_stacktrace_map() "err %d errno %d\n", err, errno)) goto disable_pmu_noerr; + stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu_noerr; + goto disable_pmu_noerr; disable_pmu: error_cnt++; @@ -1039,9 +1126,9 @@ err: static void test_stacktrace_build_id(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_build_id.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, previous_key, val, duration = 0; struct bpf_object *obj; @@ -1106,6 +1193,11 @@ static void test_stacktrace_build_id(void) err, errno)) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0); assert(system("./urandom_read") == 0); @@ -1157,8 +1249,15 @@ static void test_stacktrace_build_id(void) previous_key = key; } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); - CHECK(build_id_matches < 1, "build id match", - "Didn't find expected build ID from the map\n"); + if (CHECK(build_id_matches < 1, "build id match", + "Didn't find expected build ID from the map\n")) + goto disable_pmu; + + stack_trace_len = PERF_MAX_STACK_DEPTH + * sizeof(struct bpf_stack_build_id); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno); disable_pmu: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); @@ -1173,10 +1272,439 @@ out: return; } +static void test_stacktrace_build_id_nmi(void) +{ + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; + const char *file = "./test_stacktrace_build_id.o"; + int err, pmu_fd, prog_fd; + struct perf_event_attr attr = { + .sample_freq = 5000, + .freq = 1, + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + __u32 key, previous_key, val, duration = 0; + struct bpf_object *obj; + char buf[256]; + int i, j; + struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; + int build_id_matches = 0; + + err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd); + if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + return; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (CHECK(pmu_fd < 0, "perf_event_open", + "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n", + pmu_fd, errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", + err, errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", + err, errno)) + goto disable_pmu; + + /* find map fds */ + control_map_fd = bpf_find_map(__func__, obj, "control_map"); + if (CHECK(control_map_fd < 0, "bpf_find_map control_map", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); + if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); + if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", + err, errno)) + goto disable_pmu; + + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") + == 0); + assert(system("taskset 0x1 ./urandom_read 100000") == 0); + /* disable stack trace collection */ + key = 0; + val = 1; + bpf_map_update_elem(control_map_fd, &key, &val, 0); + + /* for every element in stackid_hmap, we can find a corresponding one + * in stackmap, and vise versa. + */ + err = compare_map_keys(stackid_hmap_fd, stackmap_fd); + if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = compare_map_keys(stackmap_fd, stackid_hmap_fd); + if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = extract_build_id(buf, 256); + + if (CHECK(err, "get build_id with readelf", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + + err = bpf_map_get_next_key(stackmap_fd, NULL, &key); + if (CHECK(err, "get_next_key from stackmap", + "err %d, errno %d\n", err, errno)) + goto disable_pmu; + + do { + char build_id[64]; + + err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); + if (CHECK(err, "lookup_elem from stackmap", + "err %d, errno %d\n", err, errno)) + goto disable_pmu; + for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) + if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && + id_offs[i].offset != 0) { + for (j = 0; j < 20; ++j) + sprintf(build_id + 2 * j, "%02x", + id_offs[i].build_id[j] & 0xff); + if (strstr(buf, build_id) != NULL) + build_id_matches = 1; + } + previous_key = key; + } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); + + if (CHECK(build_id_matches < 1, "build id match", + "Didn't find expected build ID from the map\n")) + goto disable_pmu; + + /* + * We intentionally skip compare_stack_ips(). This is because we + * only support one in_nmi() ips-to-build_id translation per cpu + * at any time, thus stack_amap here will always fallback to + * BPF_STACK_BUILD_ID_IP; + */ + +disable_pmu: + ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); + +close_pmu: + close(pmu_fd); + +close_prog: + bpf_object__close(obj); +} + +#define MAX_CNT_RAWTP 10ull +#define MAX_STACK_RAWTP 100 +struct get_stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +static int get_stack_print_output(void *data, int size) +{ + bool good_kern_stack = false, good_user_stack = false; + const char *nonjit_func = "___bpf_prog_run"; + struct get_stack_trace_t *e = data; + int i, num_stack; + static __u64 cnt; + struct ksym *ks; + + cnt++; + + if (size < sizeof(struct get_stack_trace_t)) { + __u64 *raw_data = data; + bool found = false; + + num_stack = size / sizeof(__u64); + /* If jit is enabled, we do not have a good way to + * verify the sanity of the kernel stack. So we + * just assume it is good if the stack is not empty. + * This could be improved in the future. + */ + if (jit_enabled) { + found = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(raw_data[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + found = true; + break; + } + } + } + if (found) { + good_kern_stack = true; + good_user_stack = true; + } + } else { + num_stack = e->kern_stack_size / sizeof(__u64); + if (jit_enabled) { + good_kern_stack = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(e->kern_stack[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + good_kern_stack = true; + break; + } + } + } + if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + good_user_stack = true; + } + if (!good_kern_stack || !good_user_stack) + return LIBBPF_PERF_EVENT_ERROR; + + if (cnt == MAX_CNT_RAWTP) + return LIBBPF_PERF_EVENT_DONE; + + return LIBBPF_PERF_EVENT_CONT; +} + +static void test_get_stack_raw_tp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + int i, efd, err, prog_fd, pmu_fd, perfmap_fd; + struct perf_event_attr attr = {}; + struct timespec tv = {0, 10}; + __u32 key = 0, duration = 0; + struct bpf_object *obj; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); + if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + perfmap_fd, errno)) + goto close_prog; + + err = load_kallsyms(); + if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) + goto close_prog; + + attr.sample_type = PERF_SAMPLE_RAW; + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_BPF_OUTPUT; + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, + -1/*group_fd*/, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); + if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", + err, errno)) + goto close_prog; + + err = perf_event_mmap(pmu_fd); + if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + goto close_prog; + + /* trigger some syscall action */ + for (i = 0; i < MAX_CNT_RAWTP; i++) + nanosleep(&tv, NULL); + + err = perf_event_poller(pmu_fd, get_stack_print_output); + if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_rawtp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + struct bpf_object *obj; + int efd, err, prog_fd; + __u32 duration = 0; + char buf[256]; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + /* query (getpid(), efd) */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + strcmp(buf, "sys_enter") == 0; + if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n", + fd_type, buf)) + goto close_prog; + + /* test zero len */ + len = 0; + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query (len = 0)", "err %d errno %d\n", + err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter"); + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + /* test empty buffer */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), efd, 0, 0, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query (buf = 0)", "err %d errno %d\n", + err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter"); + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + /* test smaller buffer */ + len = 3; + err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err >= 0 || errno != ENOSPC, "bpf_task_fd_query (len = 3)", + "err %d errno %d\n", err, errno)) + goto close_prog; + err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT && + len == strlen("sys_enter") && + strcmp(buf, "sy") == 0; + if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_tp_core(const char *probe_name, + const char *tp_name) +{ + const char *file = "./test_tracepoint.o"; + int err, bytes, efd, prog_fd, pmu_fd; + struct perf_event_attr attr = {}; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + struct bpf_object *obj; + __u32 duration = 0; + char buf[256]; + + err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) + goto close_prog; + + snprintf(buf, sizeof(buf), + "/sys/kernel/debug/tracing/events/%s/id", probe_name); + efd = open(buf, O_RDONLY, 0); + if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno)) + goto close_prog; + bytes = read(efd, buf, sizeof(buf)); + close(efd); + if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read", + "bytes %d errno %d\n", bytes, errno)) + goto close_prog; + + attr.config = strtol(buf, NULL, 0); + attr.type = PERF_TYPE_TRACEPOINT; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (CHECK(err, "perf_event_open", "err %d errno %d\n", err, errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + /* query (getpid(), pmu_fd) */ + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), pmu_fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err, + errno)) + goto close_pmu; + + err = (fd_type == BPF_FD_TYPE_TRACEPOINT) && !strcmp(buf, tp_name); + if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n", + fd_type, buf)) + goto close_pmu; + + close(pmu_fd); + goto close_prog_noerr; + +close_pmu: + close(pmu_fd); +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void test_task_fd_query_tp(void) +{ + test_task_fd_query_tp_core("sched/sched_switch", + "sched_switch"); + test_task_fd_query_tp_core("syscalls/sys_enter_read", + "sys_enter_read"); +} + int main(void) { + jit_enabled = is_jit_enabled(); + test_pkt_access(); test_xdp(); + test_xdp_adjust_tail(); test_l4lb_all(); test_xdp_noinline(); test_tcp_estats(); @@ -1186,7 +1714,11 @@ int main(void) test_tp_attach_query(); test_stacktrace_map(); test_stacktrace_build_id(); + test_stacktrace_build_id_nmi(); test_stacktrace_map_raw_tp(); + test_get_stack_raw_tp(); + test_task_fd_query_rawtp(); + test_task_fd_query_tp(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 2950f80ba7fb..a5e76b9219b9 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1,12 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook +#define _GNU_SOURCE + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <arpa/inet.h> +#include <netinet/in.h> #include <sys/types.h> +#include <sys/select.h> #include <sys/socket.h> #include <linux/filter.h> @@ -17,34 +21,465 @@ #include "cgroup_helpers.h" #include "bpf_rlimit.h" +#ifndef ENOTSUPP +# define ENOTSUPP 524 +#endif + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + #define CG_PATH "/foo" #define CONNECT4_PROG_PATH "./connect4_prog.o" #define CONNECT6_PROG_PATH "./connect6_prog.o" +#define SENDMSG4_PROG_PATH "./sendmsg4_prog.o" +#define SENDMSG6_PROG_PATH "./sendmsg6_prog.o" #define SERV4_IP "192.168.1.254" #define SERV4_REWRITE_IP "127.0.0.1" +#define SRC4_IP "172.16.0.1" +#define SRC4_REWRITE_IP "127.0.0.4" #define SERV4_PORT 4040 #define SERV4_REWRITE_PORT 4444 #define SERV6_IP "face:b00c:1234:5678::abcd" #define SERV6_REWRITE_IP "::1" +#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" +#define SRC6_IP "::1" +#define SRC6_REWRITE_IP "::6" #define SERV6_PORT 6060 #define SERV6_REWRITE_PORT 6666 #define INET_NTOP_BUF 40 -typedef int (*load_fn)(enum bpf_attach_type, const char *comment); +struct sock_addr_test; + +typedef int (*load_fn)(const struct sock_addr_test *test); typedef int (*info_fn)(int, struct sockaddr *, socklen_t *); -struct program { - enum bpf_attach_type type; - load_fn loadfn; - int fd; - const char *name; - enum bpf_attach_type invalid_type; +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +struct sock_addr_test { + const char *descr; + /* BPF prog properties */ + load_fn loadfn; + enum bpf_attach_type expected_attach_type; + enum bpf_attach_type attach_type; + /* Socket properties */ + int domain; + int type; + /* IP:port pairs for BPF prog to override */ + const char *requested_ip; + unsigned short requested_port; + const char *expected_ip; + unsigned short expected_port; + const char *expected_src_ip; + /* Expected test result */ + enum { + LOAD_REJECT, + ATTACH_REJECT, + SYSCALL_EPERM, + SYSCALL_ENOTSUPP, + SUCCESS, + } expected_result; }; -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static int bind4_prog_load(const struct sock_addr_test *test); +static int bind6_prog_load(const struct sock_addr_test *test); +static int connect4_prog_load(const struct sock_addr_test *test); +static int connect6_prog_load(const struct sock_addr_test *test); +static int sendmsg_deny_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test); + +static struct sock_addr_test tests[] = { + /* bind */ + { + "bind4: load prog with wrong expected attach type", + bind4_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind4: attach prog with wrong attach type", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind4: rewrite IP & TCP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind4: rewrite IP & UDP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: load prog with wrong expected attach type", + bind6_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind6: attach prog with wrong attach type", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind6: rewrite IP & TCP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: rewrite IP & UDP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + + /* connect */ + { + "connect4: load prog with wrong expected attach type", + connect4_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect4: attach prog with wrong attach type", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect4: rewrite IP & TCP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect4: rewrite IP & UDP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect6: load prog with wrong expected attach type", + connect6_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect6: attach prog with wrong attach type", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect6: rewrite IP & TCP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "connect6: rewrite IP & UDP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + + /* sendmsg */ + { + "sendmsg4: load prog with wrong expected attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg4: attach prog with wrong attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg4: rewrite IP & port (asm)", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: rewrite IP & port (C)", + sendmsg4_rw_c_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + "sendmsg6: load prog with wrong expected attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg6: attach prog with wrong attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg6: rewrite IP & port (asm)", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: rewrite IP & port (C)", + sendmsg6_rw_c_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: IPv4-mapped IPv6", + sendmsg6_rw_v4mapped_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_ENOTSUPP, + }, + { + "sendmsg6: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, +}; static int mk_sockaddr(int domain, const char *ip, unsigned short port, struct sockaddr *addr, socklen_t addr_len) @@ -84,25 +519,23 @@ static int mk_sockaddr(int domain, const char *ip, unsigned short port, return 0; } -static int load_insns(enum bpf_attach_type attach_type, - const struct bpf_insn *insns, size_t insns_cnt, - const char *comment) +static int load_insns(const struct sock_addr_test *test, + const struct bpf_insn *insns, size_t insns_cnt) { struct bpf_load_program_attr load_attr; int ret; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - load_attr.expected_attach_type = attach_type; + load_attr.expected_attach_type = test->expected_attach_type; load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = "GPL"; ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE); - if (ret < 0 && comment) { - log_err(">>> Loading %s program error.\n" - ">>> Output from verifier:\n%s\n-------\n", - comment, bpf_log_buf); + if (ret < 0 && test->expected_result != LOAD_REJECT) { + log_err(">>> Loading program error.\n" + ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); } return ret; @@ -119,8 +552,7 @@ static int load_insns(enum bpf_attach_type attach_type, * to count jumps properly. */ -static int bind4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind4_prog_load(const struct sock_addr_test *test) { union { uint8_t u4_addr8[4]; @@ -186,12 +618,10 @@ static int bind4_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int bind6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind6_prog_load(const struct sock_addr_test *test) { struct sockaddr_in6 addr6_rw; struct in6_addr ip6; @@ -254,13 +684,10 @@ static int bind6_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int connect_prog_load_path(const char *path, - enum bpf_attach_type attach_type, - const char *comment) +static int load_path(const struct sock_addr_test *test, const char *path) { struct bpf_prog_load_attr attr; struct bpf_object *obj; @@ -269,75 +696,218 @@ static int connect_prog_load_path(const char *path, memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); attr.file = path; attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - attr.expected_attach_type = attach_type; + attr.expected_attach_type = test->expected_attach_type; if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { - if (comment) - log_err(">>> Loading %s program at %s error.\n", - comment, path); + if (test->expected_result != LOAD_REJECT) + log_err(">>> Loading program (%s) error.\n", path); return -1; } return prog_fd; } -static int connect4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect4_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT4_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT4_PROG_PATH); } -static int connect6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect6_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT6_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT6_PROG_PATH); } -static void print_ip_port(int sockfd, info_fn fn, const char *fmt) +static int sendmsg_deny_prog_load(const struct sock_addr_test *test) { - char addr_buf[INET_NTOP_BUF]; - struct sockaddr_storage addr; - struct sockaddr_in6 *addr6; - struct sockaddr_in *addr4; - socklen_t addr_len; - unsigned short port; - void *nip; - - addr_len = sizeof(struct sockaddr_storage); - memset(&addr, 0, addr_len); - - if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) { - if (addr.ss_family == AF_INET) { - addr4 = (struct sockaddr_in *)&addr; - nip = (void *)&addr4->sin_addr; - port = ntohs(addr4->sin_port); - } else if (addr.ss_family == AF_INET6) { - addr6 = (struct sockaddr_in6 *)&addr; - nip = (void *)&addr6->sin6_addr; - port = ntohs(addr6->sin6_port); - } else { - return; - } - const char *addr_str = - inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF); - printf(fmt, addr_str ? addr_str : "??", port); + struct bpf_insn insns[] = { + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) +{ + struct sockaddr_in dst4_rw_addr; + struct in_addr src4_rw_ip; + + if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) { + log_err("Invalid IPv4: %s", SRC4_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, + (struct sockaddr *)&dst4_rw_addr, + sizeof(dst4_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* 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, 8), + + /* sk.type == SOCK_DGRAM) { */ + 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, 6), + + /* msg_src_ip4 = src4_rw_ip */ + BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, msg_src_ip4)), + + /* user_ip4 = dst4_rw_addr.sin_addr */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_ip4)), + + /* user_port = dst4_rw_addr.sin_port */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG4_PROG_PATH); +} + +static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, + const char *rw_dst_ip) +{ + struct sockaddr_in6 dst6_rw_addr; + struct in6_addr src6_rw_ip; + + if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) { + log_err("Invalid IPv6: %s", SRC6_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT, + (struct sockaddr *)&dst6_rw_addr, + sizeof(dst6_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (sk.family == AF_INET6) { */ + 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_INET6, 18), + +#define STORE_IPV6_WORD_N(DST, SRC, N) \ + BPF_MOV32_IMM(BPF_REG_7, SRC[N]), \ + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \ + offsetof(struct bpf_sock_addr, DST[N])) + +#define STORE_IPV6(DST, SRC) \ + STORE_IPV6_WORD_N(DST, SRC, 0), \ + STORE_IPV6_WORD_N(DST, SRC, 1), \ + STORE_IPV6_WORD_N(DST, SRC, 2), \ + STORE_IPV6_WORD_N(DST, SRC, 3) + + STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32), + STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32), + + /* user_port = dst6_rw_addr.sin6_port */ + BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.sin6_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP); +} + +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP); +} + +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG6_PROG_PATH); +} + +static int cmp_addr(const struct sockaddr_storage *addr1, + const struct sockaddr_storage *addr2, int cmp_port) +{ + const struct sockaddr_in *four1, *four2; + const struct sockaddr_in6 *six1, *six2; + + if (addr1->ss_family != addr2->ss_family) + return -1; + + if (addr1->ss_family == AF_INET) { + four1 = (const struct sockaddr_in *)addr1; + four2 = (const struct sockaddr_in *)addr2; + return !((four1->sin_port == four2->sin_port || !cmp_port) && + four1->sin_addr.s_addr == four2->sin_addr.s_addr); + } else if (addr1->ss_family == AF_INET6) { + six1 = (const struct sockaddr_in6 *)addr1; + six2 = (const struct sockaddr_in6 *)addr2; + return !((six1->sin6_port == six2->sin6_port || !cmp_port) && + !memcmp(&six1->sin6_addr, &six2->sin6_addr, + sizeof(struct in6_addr))); } + + return -1; } -static void print_local_ip_port(int sockfd, const char *fmt) +static int cmp_sock_addr(info_fn fn, int sock1, + const struct sockaddr_storage *addr2, int cmp_port) { - print_ip_port(sockfd, getsockname, fmt); + struct sockaddr_storage addr1; + socklen_t len1 = sizeof(addr1); + + memset(&addr1, 0, len1); + if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0) + return -1; + + return cmp_addr(&addr1, addr2, cmp_port); +} + +static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0); } -static void print_remote_ip_port(int sockfd, const char *fmt) +static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2) { - print_ip_port(sockfd, getpeername, fmt); + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1); +} + +static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1); } static int start_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { - int fd; fd = socket(addr->ss_family, type, 0); @@ -358,8 +928,6 @@ static int start_server(int type, const struct sockaddr_storage *addr, } } - print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n"); - goto out; close_out: close(fd); @@ -372,19 +940,19 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { int domain; - int fd; + int fd = -1; domain = addr->ss_family; if (domain != AF_INET && domain != AF_INET6) { log_err("Unsupported address family"); - return -1; + goto err; } fd = socket(domain, type, 0); if (fd == -1) { - log_err("Failed to creating client socket"); - return -1; + log_err("Failed to create client socket"); + goto err; } if (connect(fd, (const struct sockaddr *)addr, addr_len) == -1) { @@ -392,162 +960,394 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, goto err; } - print_remote_ip_port(fd, "\t Actual: connect(%s, %d)"); - print_local_ip_port(fd, " from (%s, %d)\n"); + goto out; +err: + close(fd); + fd = -1; +out: + return fd; +} + +int init_pktinfo(int domain, struct cmsghdr *cmsg) +{ + struct in6_pktinfo *pktinfo6; + struct in_pktinfo *pktinfo4; + + if (domain == AF_INET) { + cmsg->cmsg_level = SOL_IP; + cmsg->cmsg_type = IP_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo4, 0, sizeof(struct in_pktinfo)); + if (inet_pton(domain, SRC4_IP, + (void *)&pktinfo4->ipi_spec_dst) != 1) + return -1; + } else if (domain == AF_INET6) { + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = IPV6_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo6, 0, sizeof(struct in6_pktinfo)); + if (inet_pton(domain, SRC6_IP, + (void *)&pktinfo6->ipi6_addr) != 1) + return -1; + } else { + return -1; + } return 0; +} + +static int sendmsg_to_server(const struct sockaddr_storage *addr, + socklen_t addr_len, int set_cmsg, int *syscall_err) +{ + union { + char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))]; + struct cmsghdr align; + } control6; + union { + char buf[CMSG_SPACE(sizeof(struct in_pktinfo))]; + struct cmsghdr align; + } control4; + struct msghdr hdr; + struct iovec iov; + char data = 'a'; + int domain; + int fd = -1; + + domain = addr->ss_family; + + if (domain != AF_INET && domain != AF_INET6) { + log_err("Unsupported address family"); + goto err; + } + + fd = socket(domain, SOCK_DGRAM, 0); + if (fd == -1) { + log_err("Failed to create client socket"); + goto err; + } + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = (void *)addr; + hdr.msg_namelen = addr_len; + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + if (set_cmsg) { + if (domain == AF_INET) { + hdr.msg_control = &control4; + hdr.msg_controllen = sizeof(control4.buf); + } else if (domain == AF_INET6) { + hdr.msg_control = &control6; + hdr.msg_controllen = sizeof(control6.buf); + } + if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) { + log_err("Fail to init pktinfo"); + goto err; + } + } + + if (sendmsg(fd, &hdr, 0) != sizeof(data)) { + log_err("Fail to send message to server"); + *syscall_err = errno; + goto err; + } + + goto out; err: close(fd); - return -1; + fd = -1; +out: + return fd; } -static void print_test_case_num(int domain, int type) +static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr) { - static int test_num; - - printf("Test case #%d (%s/%s):\n", ++test_num, - (domain == AF_INET ? "IPv4" : - domain == AF_INET6 ? "IPv6" : - "unknown_domain"), - (type == SOCK_STREAM ? "TCP" : - type == SOCK_DGRAM ? "UDP" : - "unknown_type")); + struct timeval tv; + struct msghdr hdr; + struct iovec iov; + char data[64]; + fd_set rfds; + + FD_ZERO(&rfds); + FD_SET(sockfd, &rfds); + + tv.tv_sec = 2; + tv.tv_usec = 0; + + if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 || + !FD_ISSET(sockfd, &rfds)) + return -1; + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = src_addr; + hdr.msg_namelen = sizeof(struct sockaddr_storage); + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + return recvmsg(sockfd, &hdr, 0); } -static int run_test_case(int domain, int type, const char *ip, - unsigned short port) +static int init_addrs(const struct sock_addr_test *test, + struct sockaddr_storage *requested_addr, + struct sockaddr_storage *expected_addr, + struct sockaddr_storage *expected_src_addr) { - struct sockaddr_storage addr; - socklen_t addr_len = sizeof(addr); + socklen_t addr_len = sizeof(struct sockaddr_storage); + + if (mk_sockaddr(test->domain, test->expected_ip, test->expected_port, + (struct sockaddr *)expected_addr, addr_len) == -1) + goto err; + + if (mk_sockaddr(test->domain, test->requested_ip, test->requested_port, + (struct sockaddr *)requested_addr, addr_len) == -1) + goto err; + + if (test->expected_src_ip && + mk_sockaddr(test->domain, test->expected_src_ip, 0, + (struct sockaddr *)expected_src_addr, addr_len) == -1) + goto err; + + return 0; +err: + return -1; +} + +static int run_bind_test_case(const struct sock_addr_test *test) +{ + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; int servfd = -1; int err = 0; - print_test_case_num(domain, type); - - if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr, - addr_len) == -1) - return -1; + if (init_addrs(test, &requested_addr, &expected_addr, NULL)) + goto err; - printf("\tRequested: bind(%s, %d) ..\n", ip, port); - servfd = start_server(type, &addr, addr_len); + servfd = start_server(test->type, &requested_addr, addr_len); if (servfd == -1) goto err; - printf("\tRequested: connect(%s, %d) from (*, *) ..\n", ip, port); - if (connect_to_server(type, &addr, addr_len)) + if (cmp_local_addr(servfd, &expected_addr)) + goto err; + + /* Try to connect to server just in case */ + clientfd = connect_to_server(test->type, &expected_addr, addr_len); + if (clientfd == -1) goto err; goto out; err: err = -1; out: + close(clientfd); close(servfd); return err; } -static void close_progs_fds(struct program *progs, size_t prog_cnt) +static int run_connect_test_case(const struct sock_addr_test *test) { - size_t i; + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; + int servfd = -1; + int err = 0; - for (i = 0; i < prog_cnt; ++i) { - close(progs[i].fd); - progs[i].fd = -1; - } + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to connect to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + clientfd = connect_to_server(test->type, &requested_addr, addr_len); + if (clientfd == -1) + goto err; + + /* Make sure src and dst addrs were overridden properly */ + if (cmp_peer_addr(clientfd, &expected_addr)) + goto err; + + if (cmp_local_ip(clientfd, &expected_src_addr)) + goto err; + + goto out; +err: + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int load_and_attach_progs(int cgfd, struct program *progs, - size_t prog_cnt) +static int run_sendmsg_test_case(const struct sock_addr_test *test) { - size_t i; - - for (i = 0; i < prog_cnt; ++i) { - printf("Load %s with invalid type (can pollute stderr) ", - progs[i].name); - fflush(stdout); - progs[i].fd = progs[i].loadfn(progs[i].invalid_type, NULL); - if (progs[i].fd != -1) { - log_err("Load with invalid type accepted for %s", - progs[i].name); - goto err; - } - printf("... REJECTED\n"); + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + struct sockaddr_storage real_src_addr; + int clientfd = -1; + int servfd = -1; + int set_cmsg; + int err = 0; + + if (test->type != SOCK_DGRAM) + goto err; - printf("Load %s with valid type", progs[i].name); - progs[i].fd = progs[i].loadfn(progs[i].type, progs[i].name); - if (progs[i].fd == -1) { - log_err("Failed to load program %s", progs[i].name); + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to sendmsg to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + for (set_cmsg = 0; set_cmsg <= 1; ++set_cmsg) { + if (clientfd >= 0) + close(clientfd); + + clientfd = sendmsg_to_server(&requested_addr, addr_len, + set_cmsg, &err); + if (err) + goto out; + else if (clientfd == -1) goto err; - } - printf(" ... OK\n"); - printf("Attach %s with invalid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].invalid_type, - BPF_F_ALLOW_OVERRIDE) != -1) { - log_err("Attach with invalid type accepted for %s", - progs[i].name); + /* Try to receive message on server instead of using + * getpeername(2) on client socket, to check that client's + * destination address was rewritten properly, since + * getpeername(2) doesn't work with unconnected datagram + * sockets. + * + * Get source address from recvmsg(2) as well to make sure + * source was rewritten properly: getsockname(2) can't be used + * since socket is unconnected and source defined for one + * specific packet may differ from the one used by default and + * returned by getsockname(2). + */ + if (recvmsg_from_client(servfd, &real_src_addr) == -1) goto err; - } - printf(" ... REJECTED\n"); - printf("Attach %s with valid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type, - BPF_F_ALLOW_OVERRIDE) == -1) { - log_err("Failed to attach program %s", progs[i].name); + if (cmp_addr(&real_src_addr, &expected_src_addr, /*cmp_port*/0)) goto err; - } - printf(" ... OK\n"); } - return 0; + goto out; err: - close_progs_fds(progs, prog_cnt); - return -1; + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int run_domain_test(int domain, int cgfd, struct program *progs, - size_t prog_cnt, const char *ip, unsigned short port) +static int run_test_case(int cgfd, const struct sock_addr_test *test) { + int progfd = -1; int err = 0; - if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1) + printf("Test case: %s .. ", test->descr); + + progfd = test->loadfn(test); + if (test->expected_result == LOAD_REJECT && progfd < 0) + goto out; + else if (test->expected_result == LOAD_REJECT || progfd < 0) + goto err; + + err = bpf_prog_attach(progfd, cgfd, test->attach_type, + BPF_F_ALLOW_OVERRIDE); + if (test->expected_result == ATTACH_REJECT && err) { + err = 0; /* error was expected, reset it */ + goto out; + } else if (test->expected_result == ATTACH_REJECT || err) { goto err; + } - if (run_test_case(domain, SOCK_STREAM, ip, port) == -1) + switch (test->attach_type) { + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: + err = run_bind_test_case(test); + break; + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + err = run_connect_test_case(test); + break; + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + err = run_sendmsg_test_case(test); + break; + default: goto err; + } + + if (test->expected_result == SYSCALL_EPERM && err == EPERM) { + err = 0; /* error was expected, reset it */ + goto out; + } + + if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) { + err = 0; /* error was expected, reset it */ + goto out; + } - if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1) + if (err || test->expected_result != SUCCESS) goto err; goto out; err: err = -1; out: - close_progs_fds(progs, prog_cnt); + /* Detaching w/o checking return code: best effort attempt. */ + if (progfd != -1) + bpf_prog_detach(cgfd, test->attach_type); + close(progfd); + printf("[%s]\n", err ? "FAIL" : "PASS"); return err; } -static int run_test(void) +static int run_tests(int cgfd) +{ + int passes = 0; + int fails = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + if (run_test_case(cgfd, &tests[i])) + ++fails; + else + ++passes; + } + printf("Summary: %d PASSED, %d FAILED\n", passes, fails); + return fails ? -1 : 0; +} + +int main(int argc, char **argv) { - size_t inet6_prog_cnt; - size_t inet_prog_cnt; int cgfd = -1; int err = 0; - struct program inet6_progs[] = { - {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6", - BPF_CGROUP_INET4_BIND}, - {BPF_CGROUP_INET6_CONNECT, connect6_prog_load, -1, "connect6", - BPF_CGROUP_INET4_CONNECT}, - }; - inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program); - - struct program inet_progs[] = { - {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4", - BPF_CGROUP_INET6_BIND}, - {BPF_CGROUP_INET4_CONNECT, connect4_prog_load, -1, "connect4", - BPF_CGROUP_INET6_CONNECT}, - }; - inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program); + if (argc < 2) { + fprintf(stderr, + "%s has to be run via %s.sh. Skip direct run.\n", + argv[0], argv[0]); + exit(err); + } if (setup_cgroup_environment()) goto err; @@ -559,12 +1359,7 @@ static int run_test(void) if (join_cgroup(CG_PATH)) goto err; - if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP, - SERV4_PORT) == -1) - goto err; - - if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt, - SERV6_IP, SERV6_PORT) == -1) + if (run_tests(cgfd)) goto err; goto out; @@ -573,17 +1368,5 @@ err: out: close(cgfd); cleanup_cgroup_environment(); - printf(err ? "### FAIL\n" : "### SUCCESS\n"); return err; } - -int main(int argc, char **argv) -{ - if (argc < 2) { - fprintf(stderr, - "%s has to be run via %s.sh. Skip direct run.\n", - argv[0], argv[0]); - exit(0); - } - return run_test(); -} diff --git a/tools/testing/selftests/bpf/test_sockhash_kern.c b/tools/testing/selftests/bpf/test_sockhash_kern.c new file mode 100644 index 000000000000..e6755916442a --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockhash_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#undef SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c new file mode 100644 index 000000000000..05c8cb71724a --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -0,0 +1,1524 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <sys/select.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <stdbool.h> +#include <signal.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <time.h> +#include <sched.h> + +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/types.h> +#include <sys/sendfile.h> + +#include <linux/netlink.h> +#include <linux/socket.h> +#include <linux/sock_diag.h> +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <libgen.h> + +#include <getopt.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" + +int running; +static void running_handler(int a); + +/* randomly selected ports for testing on lo */ +#define S1_PORT 10000 +#define S2_PORT 10001 + +#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o" +#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o" +#define CG_PATH "/sockmap" + +/* global sockets */ +int s1, s2, c1, c2, p1, p2; +int test_cnt; +int passed; +int failed; +int map_fd[8]; +struct bpf_map *maps[8]; +int prog_fd[11]; + +int txmsg_pass; +int txmsg_noisy; +int txmsg_redir; +int txmsg_redir_noisy; +int txmsg_drop; +int txmsg_apply; +int txmsg_cork; +int txmsg_start; +int txmsg_end; +int txmsg_ingress; +int txmsg_skb; + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"cgroup", required_argument, NULL, 'c' }, + {"rate", required_argument, NULL, 'r' }, + {"verbose", no_argument, NULL, 'v' }, + {"iov_count", required_argument, NULL, 'i' }, + {"length", required_argument, NULL, 'l' }, + {"test", required_argument, NULL, 't' }, + {"data_test", no_argument, NULL, 'd' }, + {"txmsg", no_argument, &txmsg_pass, 1 }, + {"txmsg_noisy", no_argument, &txmsg_noisy, 1 }, + {"txmsg_redir", no_argument, &txmsg_redir, 1 }, + {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1}, + {"txmsg_drop", no_argument, &txmsg_drop, 1 }, + {"txmsg_apply", required_argument, NULL, 'a'}, + {"txmsg_cork", required_argument, NULL, 'k'}, + {"txmsg_start", required_argument, NULL, 's'}, + {"txmsg_end", required_argument, NULL, 'e'}, + {"txmsg_ingress", no_argument, &txmsg_ingress, 1 }, + {"txmsg_skb", no_argument, &txmsg_skb, 1 }, + {0, 0, NULL, 0 } +}; + +static void usage(char *argv[]) +{ + int i; + + printf(" Usage: %s --cgroup <cgroup_path>\n", argv[0]); + printf(" options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)\n", + *long_options[i].flag); + else + printf(" -%c\n", long_options[i].val); + } + printf("\n"); +} + +static int sockmap_init_sockets(int verbose) +{ + int i, err, one = 1; + struct sockaddr_in addr; + int *fds[4] = {&s1, &s2, &c1, &c2}; + + s1 = s2 = p1 = p2 = c1 = c2 = 0; + + /* Init sockets */ + for (i = 0; i < 4; i++) { + *fds[i] = socket(AF_INET, SOCK_STREAM, 0); + if (*fds[i] < 0) { + perror("socket s1 failed()"); + return errno; + } + } + + /* Allow reuse */ + for (i = 0; i < 2; i++) { + err = setsockopt(*fds[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + perror("setsockopt failed()"); + return errno; + } + } + + /* Non-blocking sockets */ + for (i = 0; i < 2; i++) { + err = ioctl(*fds[i], FIONBIO, (char *)&one); + if (err < 0) { + perror("ioctl s1 failed()"); + return errno; + } + } + + /* Bind server sockets */ + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + + addr.sin_port = htons(S1_PORT); + err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s2 failed()\n"); + return errno; + } + + /* Listen server sockets */ + addr.sin_port = htons(S1_PORT); + err = listen(s1, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = listen(s2, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + /* Initiate Connect */ + addr.sin_port = htons(S1_PORT); + err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c2 failed()\n"); + return errno; + } else if (err < 0) { + err = 0; + } + + /* Accept Connecrtions */ + p1 = accept(s1, NULL, NULL); + if (p1 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + p2 = accept(s2, NULL, NULL); + if (p2 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + if (verbose) { + printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); + printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", + c1, s1, c2, s2); + } + return 0; +} + +struct msg_stats { + size_t bytes_sent; + size_t bytes_recvd; + struct timespec start; + struct timespec end; +}; + +struct sockmap_options { + int verbose; + bool base; + bool sendpage; + bool data_test; + bool drop_expected; + int iov_count; + int iov_length; + int rate; +}; + +static int msg_loop_sendpage(int fd, int iov_length, int cnt, + struct msg_stats *s, + struct sockmap_options *opt) +{ + bool drop = opt->drop_expected; + unsigned char k = 0; + FILE *file; + int i, fp; + + file = fopen(".sendpage_tst.tmp", "w+"); + for (i = 0; i < iov_length * cnt; i++, k++) + fwrite(&k, sizeof(char), 1, file); + fflush(file); + fseek(file, 0, SEEK_SET); + fclose(file); + + fp = open(".sendpage_tst.tmp", O_RDONLY); + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendfile(fd, fp, NULL, iov_length); + + if (!drop && sent < 0) { + perror("send loop error:"); + close(fp); + return sent; + } else if (drop && sent >= 0) { + printf("sendpage loop error expected: %i\n", sent); + close(fp); + return -EIO; + } + + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + close(fp); + return 0; +} + +static int msg_loop(int fd, int iov_count, int iov_length, int cnt, + struct msg_stats *s, bool tx, + struct sockmap_options *opt) +{ + struct msghdr msg = {0}; + int err, i, flags = MSG_NOSIGNAL; + struct iovec *iov; + unsigned char k; + bool data_test = opt->data_test; + bool drop = opt->drop_expected; + + iov = calloc(iov_count, sizeof(struct iovec)); + if (!iov) + return errno; + + k = 0; + for (i = 0; i < iov_count; i++) { + unsigned char *d = calloc(iov_length, sizeof(char)); + + if (!d) { + fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count); + goto out_errno; + } + iov[i].iov_base = d; + iov[i].iov_len = iov_length; + + if (data_test && tx) { + int j; + + for (j = 0; j < iov_length; j++) + d[j] = k++; + } + } + + msg.msg_iov = iov; + msg.msg_iovlen = iov_count; + k = 0; + + if (tx) { + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendmsg(fd, &msg, flags); + + if (!drop && sent < 0) { + perror("send loop error:"); + goto out_errno; + } else if (drop && sent >= 0) { + printf("send loop error expected: %i\n", sent); + errno = -EIO; + goto out_errno; + } + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } else { + int slct, recv, max_fd = fd; + int fd_flags = O_NONBLOCK; + struct timeval timeout; + float total_bytes; + int bytes_cnt = 0; + int chunk_sz; + fd_set w; + + if (opt->sendpage) + chunk_sz = iov_length * cnt; + else + chunk_sz = iov_length * iov_count; + + fcntl(fd, fd_flags); + total_bytes = (float)iov_count * (float)iov_length * (float)cnt; + err = clock_gettime(CLOCK_MONOTONIC, &s->start); + if (err < 0) + perror("recv start time: "); + while (s->bytes_recvd < total_bytes) { + if (txmsg_cork) { + timeout.tv_sec = 0; + timeout.tv_usec = 1000; + } else { + timeout.tv_sec = 1; + timeout.tv_usec = 0; + } + + /* FD sets */ + FD_ZERO(&w); + FD_SET(fd, &w); + + slct = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (slct == -1) { + perror("select()"); + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } else if (!slct) { + if (opt->verbose) + fprintf(stderr, "unexpected timeout\n"); + errno = -EIO; + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } + + recv = recvmsg(fd, &msg, flags); + if (recv < 0) { + if (errno != EWOULDBLOCK) { + clock_gettime(CLOCK_MONOTONIC, &s->end); + perror("recv failed()\n"); + goto out_errno; + } + } + + s->bytes_recvd += recv; + + if (data_test) { + int j; + + for (i = 0; i < msg.msg_iovlen; i++) { + unsigned char *d = iov[i].iov_base; + + for (j = 0; + j < iov[i].iov_len && recv; j++) { + if (d[j] != k++) { + errno = -EIO; + fprintf(stderr, + "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", + i, j, d[j], k - 1, d[j+1], k); + goto out_errno; + } + bytes_cnt++; + if (bytes_cnt == chunk_sz) { + k = 0; + bytes_cnt = 0; + } + recv--; + } + } + } + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } + + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return 0; +out_errno: + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return errno; +} + +static float giga = 1000000000; + +static inline float sentBps(struct msg_stats s) +{ + return s.bytes_sent / (s.end.tv_sec - s.start.tv_sec); +} + +static inline float recvdBps(struct msg_stats s) +{ + return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec); +} + +static int sendmsg_test(struct sockmap_options *opt) +{ + float sent_Bps = 0, recvd_Bps = 0; + int rx_fd, txpid, rxpid, err = 0; + struct msg_stats s = {0}; + int iov_count = opt->iov_count; + int iov_buf = opt->iov_length; + int rx_status, tx_status; + int cnt = opt->rate; + + errno = 0; + + if (opt->base) + rx_fd = p1; + else + rx_fd = p2; + + rxpid = fork(); + if (rxpid == 0) { + if (opt->drop_expected) + exit(0); + + if (opt->sendpage) + iov_count = 1; + err = msg_loop(rx_fd, iov_count, iov_buf, + cnt, &s, false, opt); + if (err && opt->verbose) + fprintf(stderr, + "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(p2, SHUT_RDWR); + shutdown(p1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + if (err && txmsg_cork) + err = 0; + exit(err ? 1 : 0); + } else if (rxpid == -1) { + perror("msg_loop_rx: "); + return errno; + } + + txpid = fork(); + if (txpid == 0) { + if (opt->sendpage) + err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt); + else + err = msg_loop(c1, iov_count, iov_buf, + cnt, &s, true, opt); + + if (err) + fprintf(stderr, + "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(c1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + exit(err ? 1 : 0); + } else if (txpid == -1) { + perror("msg_loop_tx: "); + return errno; + } + + assert(waitpid(rxpid, &rx_status, 0) == rxpid); + assert(waitpid(txpid, &tx_status, 0) == txpid); + if (WIFEXITED(rx_status)) { + err = WEXITSTATUS(rx_status); + if (err) { + fprintf(stderr, "rx thread exited with err %d. ", err); + goto out; + } + } + if (WIFEXITED(tx_status)) { + err = WEXITSTATUS(tx_status); + if (err) + fprintf(stderr, "tx thread exited with err %d. ", err); + } +out: + return err; +} + +static int forever_ping_pong(int rate, struct sockmap_options *opt) +{ + struct timeval timeout; + char buf[1024] = {0}; + int sc; + + timeout.tv_sec = 10; + timeout.tv_usec = 0; + + /* Ping/Pong data from client to server */ + sc = send(c1, buf, sizeof(buf), 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + + do { + int s, rc, i, max_fd = p2; + fd_set w; + + /* FD sets */ + FD_ZERO(&w); + FD_SET(c1, &w); + FD_SET(c2, &w); + FD_SET(p1, &w); + FD_SET(p2, &w); + + s = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (s == -1) { + perror("select()"); + break; + } else if (!s) { + fprintf(stderr, "unexpected timeout\n"); + break; + } + + for (i = 0; i <= max_fd && s > 0; ++i) { + if (!FD_ISSET(i, &w)) + continue; + + s--; + + rc = recv(i, buf, sizeof(buf), 0); + if (rc < 0) { + if (errno != EWOULDBLOCK) { + perror("recv failed()\n"); + return rc; + } + } + + if (rc == 0) { + close(i); + break; + } + + sc = send(i, buf, rc, 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + } + + if (rate) + sleep(rate); + + if (opt->verbose) { + printf("."); + fflush(stdout); + + } + } while (running); + + return 0; +} + +enum { + PING_PONG, + SENDMSG, + BASE, + BASE_SENDPAGE, + SENDPAGE, +}; + +static int run_options(struct sockmap_options *options, int cg_fd, int test) +{ + int i, key, next_key, err, tx_prog_fd = -1, zero = 0; + + /* If base test skip BPF setup */ + if (test == BASE || test == BASE_SENDPAGE) + goto run; + + /* Attach programs to sockmap */ + err = bpf_prog_attach(prog_fd[0], map_fd[0], + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n", + prog_fd[0], map_fd[0], err, strerror(errno)); + return err; + } + + err = bpf_prog_attach(prog_fd[1], map_fd[0], + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + + /* Attach to cgroups */ + err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", + err, strerror(errno)); + return err; + } + +run: + err = sockmap_init_sockets(options->verbose); + if (err) { + fprintf(stderr, "ERROR: test socket failed: %d\n", err); + goto out; + } + + /* Attach txmsg program to sockmap */ + if (txmsg_pass) + tx_prog_fd = prog_fd[3]; + else if (txmsg_noisy) + tx_prog_fd = prog_fd[4]; + else if (txmsg_redir) + tx_prog_fd = prog_fd[5]; + else if (txmsg_redir_noisy) + tx_prog_fd = prog_fd[6]; + else if (txmsg_drop) + tx_prog_fd = prog_fd[9]; + /* apply and cork must be last */ + else if (txmsg_apply) + tx_prog_fd = prog_fd[7]; + else if (txmsg_cork) + tx_prog_fd = prog_fd[8]; + else + tx_prog_fd = 0; + + if (tx_prog_fd) { + int redir_fd, i = 0; + + err = bpf_prog_attach(tx_prog_fd, + map_fd[1], BPF_SK_MSG_VERDICT, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", + err, strerror(errno)); + goto out; + } + + err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_redir || txmsg_redir_noisy) + redir_fd = c2; + else + redir_fd = c1; + + err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_apply) { + err = bpf_map_update_elem(map_fd[3], + &i, &txmsg_apply, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_cork) { + err = bpf_map_update_elem(map_fd[4], + &i, &txmsg_cork, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_start) { + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_start, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_end) { + i = 1; + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_end, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_ingress) { + int in = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + i = 1; + err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n", + err, strerror(errno)); + } + err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n", + err, strerror(errno)); + } + + i = 2; + err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n", + err, strerror(errno)); + } + } + + if (txmsg_skb) { + int skb_fd = (test == SENDMSG || test == SENDPAGE) ? + p2 : p1; + int ingress = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[7], + &i, &ingress, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + + i = 3; + err = bpf_map_update_elem(map_fd[0], + &i, &skb_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", + err, strerror(errno)); + } + } + } + + if (txmsg_drop) + options->drop_expected = true; + + if (test == PING_PONG) + err = forever_ping_pong(options->rate, options); + else if (test == SENDMSG) { + options->base = false; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == SENDPAGE) { + options->base = false; + options->sendpage = true; + err = sendmsg_test(options); + } else if (test == BASE) { + options->base = true; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == BASE_SENDPAGE) { + options->base = true; + options->sendpage = true; + err = sendmsg_test(options); + } else + fprintf(stderr, "unknown test\n"); +out: + /* Detatch and zero all the maps */ + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); + bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); + bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); + if (tx_prog_fd >= 0) + bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); + + for (i = 0; i < 8; i++) { + key = next_key = 0; + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) { + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + key = next_key; + } + } + + close(s1); + close(s2); + close(p1); + close(p2); + close(c1); + close(c2); + return err; +} + +static char *test_to_str(int test) +{ + switch (test) { + case SENDMSG: + return "sendmsg"; + case SENDPAGE: + return "sendpage"; + } + return "unknown"; +} + +#define OPTSTRING 60 +static void test_options(char *options) +{ + char tstr[OPTSTRING]; + + memset(options, 0, OPTSTRING); + + if (txmsg_pass) + strncat(options, "pass,", OPTSTRING); + if (txmsg_noisy) + strncat(options, "pass_noisy,", OPTSTRING); + if (txmsg_redir) + strncat(options, "redir,", OPTSTRING); + if (txmsg_redir_noisy) + strncat(options, "redir_noisy,", OPTSTRING); + if (txmsg_drop) + strncat(options, "drop,", OPTSTRING); + if (txmsg_apply) { + snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_cork) { + snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_start) { + snprintf(tstr, OPTSTRING, "start %d,", txmsg_start); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_end) { + snprintf(tstr, OPTSTRING, "end %d,", txmsg_end); + strncat(options, tstr, OPTSTRING); + } + if (txmsg_ingress) + strncat(options, "ingress,", OPTSTRING); + if (txmsg_skb) + strncat(options, "skb,", OPTSTRING); +} + +static int __test_exec(int cgrp, int test, struct sockmap_options *opt) +{ + char *options = calloc(OPTSTRING, sizeof(char)); + int err; + + if (test == SENDPAGE) + opt->sendpage = true; + else + opt->sendpage = false; + + if (txmsg_drop) + opt->drop_expected = true; + else + opt->drop_expected = false; + + test_options(options); + + fprintf(stdout, + "[TEST %i]: (%i, %i, %i, %s, %s): ", + test_cnt, opt->rate, opt->iov_count, opt->iov_length, + test_to_str(test), options); + fflush(stdout); + err = run_options(opt, cgrp, test); + fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED"); + test_cnt++; + !err ? passed++ : failed++; + free(options); + return err; +} + +static int test_exec(int cgrp, struct sockmap_options *opt) +{ + int err = __test_exec(cgrp, SENDMSG, opt); + + if (err) + goto out; + + err = __test_exec(cgrp, SENDPAGE, opt); +out: + return err; +} + +static int test_loop(int cgrp) +{ + struct sockmap_options opt; + + int err, i, l, r; + + opt.verbose = 0; + opt.base = false; + opt.sendpage = false; + opt.data_test = false; + opt.drop_expected = false; + opt.iov_count = 0; + opt.iov_length = 0; + opt.rate = 0; + + r = 1; + for (i = 1; i < 100; i += 33) { + for (l = 1; l < 100; l += 33) { + opt.rate = r; + opt.iov_count = i; + opt.iov_length = l; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + } + sched_yield(); +out: + return err; +} + +static int test_txmsg(int cgrp) +{ + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_ingress = txmsg_skb = 0; + + txmsg_pass = 1; + err = test_loop(cgrp); + txmsg_pass = 0; + if (err) + goto out; + + txmsg_redir = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + if (err) + goto out; + + txmsg_drop = 1; + err = test_loop(cgrp); + txmsg_drop = 0; + if (err) + goto out; + + txmsg_redir = 1; + txmsg_ingress = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + txmsg_ingress = 0; + if (err) + goto out; +out: + txmsg_pass = 0; + txmsg_redir = 0; + txmsg_drop = 0; + return err; +} + +static int test_send(struct sockmap_options *opt, int cgrp) +{ + int err; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1024; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1024; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 512; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 256; + opt->iov_count = 1024; + opt->rate = 2; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->rate = 100; + opt->iov_count = 1; + opt->iov_length = 5; + err = test_exec(cgrp, opt); + if (err) + goto out; +out: + sched_yield(); + return err; +} + +static int test_mixed(int cgrp) +{ + struct sockmap_options opt = {0}; + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_start = txmsg_end = 0; + /* Test small and large iov_count values with pass/redir/apply/cork */ + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; +out: + return err; +} + +static int test_start_end(int cgrp) +{ + struct sockmap_options opt = {0}; + int err, i; + + /* Test basic start/end with lots of iov_count and iov_lengths */ + txmsg_start = 1; + txmsg_end = 2; + err = test_txmsg(cgrp); + if (err) + goto out; + + /* Test start/end with cork */ + opt.rate = 16; + opt.iov_count = 1; + opt.iov_length = 100; + txmsg_cork = 1600; + + for (i = 99; i <= 1600; i += 500) { + txmsg_start = 0; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork but pull data in middle */ + for (i = 199; i <= 1600; i += 500) { + txmsg_start = 100; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork pulling last sg entry */ + txmsg_start = 1500; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end pull of single byte in last page */ + txmsg_start = 1111; + txmsg_end = 1112; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end < start */ + txmsg_start = 1111; + txmsg_end = 0; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end > data */ + txmsg_start = 0; + txmsg_end = 1601; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with start > data */ + txmsg_start = 1601; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + +out: + txmsg_start = 0; + txmsg_end = 0; + sched_yield(); + return err; +} + +char *map_names[] = { + "sock_map", + "sock_map_txmsg", + "sock_map_redir", + "sock_apply_bytes", + "sock_cork_bytes", + "sock_pull_bytes", + "sock_redir_flags", + "sock_skb_opts", +}; + +int prog_attach_type[] = { + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_SOCK_OPS, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, +}; + +int prog_type[] = { + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, +}; + +static int populate_progs(char *bpf_file) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0; + long err; + + obj = bpf_object__open(bpf_file); + err = libbpf_get_error(obj); + if (err) { + char err_buf[256]; + + libbpf_strerror(err, err_buf, sizeof(err_buf)); + printf("Unable to load eBPF objects in file '%s' : %s\n", + bpf_file, err_buf); + return -1; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_type(prog, prog_type[i]); + bpf_program__set_expected_attach_type(prog, + prog_attach_type[i]); + i++; + } + + i = bpf_object__load(obj); + i = 0; + bpf_object__for_each_program(prog, obj) { + prog_fd[i] = bpf_program__fd(prog); + i++; + } + + for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); + map_fd[i] = bpf_map__fd(maps[i]); + if (map_fd[i] < 0) { + fprintf(stderr, "load_bpf_file: (%i) %s\n", + map_fd[i], strerror(errno)); + return -1; + } + } + + return 0; +} + +static int __test_suite(char *bpf_file) +{ + int cg_fd, err; + + err = populate_progs(bpf_file); + if (err < 0) { + fprintf(stderr, "ERROR: (%i) load bpf failed\n", err); + return err; + } + + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + + if (join_cgroup(CG_PATH)) { + fprintf(stderr, "ERROR: failed to join cgroup\n"); + return -EINVAL; + } + + /* Tests basic commands and APIs with range of iov values */ + txmsg_start = txmsg_end = 0; + err = test_txmsg(cg_fd); + if (err) + goto out; + + /* Tests interesting combinations of APIs used together */ + err = test_mixed(cg_fd); + if (err) + goto out; + + /* Tests pull_data API using start/end API */ + err = test_start_end(cg_fd); + if (err) + goto out; + +out: + printf("Summary: %i PASSED %i FAILED\n", passed, failed); + cleanup_cgroup_environment(); + close(cg_fd); + return err; +} + +static int test_suite(void) +{ + int err; + + err = __test_suite(BPF_SOCKMAP_FILENAME); + if (err) + goto out; + err = __test_suite(BPF_SOCKHASH_FILENAME); +out: + return err; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + int iov_count = 1, length = 1024, rate = 1; + struct sockmap_options options = {0}; + int opt, longindex, err, cg_fd = 0; + char *bpf_file = BPF_SOCKMAP_FILENAME; + int test = PING_PONG; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (argc < 2) + return test_suite(); + + while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", + long_options, &longindex)) != -1) { + switch (opt) { + case 's': + txmsg_start = atoi(optarg); + break; + case 'e': + txmsg_end = atoi(optarg); + break; + case 'a': + txmsg_apply = atoi(optarg); + break; + case 'k': + txmsg_cork = atoi(optarg); + break; + case 'c': + cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + break; + case 'r': + rate = atoi(optarg); + break; + case 'v': + options.verbose = 1; + break; + case 'i': + iov_count = atoi(optarg); + break; + case 'l': + length = atoi(optarg); + break; + case 'd': + options.data_test = true; + break; + case 't': + if (strcmp(optarg, "ping") == 0) { + test = PING_PONG; + } else if (strcmp(optarg, "sendmsg") == 0) { + test = SENDMSG; + } else if (strcmp(optarg, "base") == 0) { + test = BASE; + } else if (strcmp(optarg, "base_sendpage") == 0) { + test = BASE_SENDPAGE; + } else if (strcmp(optarg, "sendpage") == 0) { + test = SENDPAGE; + } else { + usage(argv); + return -1; + } + break; + case 0: + break; + case 'h': + default: + usage(argv); + return -1; + } + } + + if (!cg_fd) { + fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", + argv[0]); + return -1; + } + + err = populate_progs(bpf_file); + if (err) { + fprintf(stderr, "populate program: (%s) %s\n", + bpf_file, strerror(errno)); + return 1; + } + running = 1; + + /* catch SIGINT */ + signal(SIGINT, running_handler); + + options.iov_count = iov_count; + options.iov_length = length; + options.rate = rate; + + err = run_options(&options, cg_fd, test); + close(cg_fd); + return err; +} + +void running_handler(int a) +{ + running = 0; +} diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/test_sockmap_kern.c new file mode 100644 index 000000000000..677b2ed1cc1e --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap_kern.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io +#define SOCKMAP +#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP +#include "./test_sockmap_kern.h" diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h new file mode 100644 index 000000000000..8e8e41780bb9 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap_kern.h @@ -0,0 +1,363 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Sockmap sample program connects a client and a backend together + * using cgroups. + * + * client:X <---> frontend:80 client:X <---> backend:80 + * + * For simplicity we hard code values here and bind 1:1. The hard + * coded values are part of the setup in sockmap.sh script that + * is associated with this BPF program. + * + * The bpf_printk is verbose and prints information as connections + * are established and verdicts are decided. + */ + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_txmsg = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_redir = { + .type = TEST_MAP_TYPE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_apply_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_cork_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_pull_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 2 +}; + +struct bpf_map_def SEC("maps") sock_redir_flags = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_skb_opts = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + int len, *f, ret, zero = 0; + __u64 flags = 0; + + if (lport == 10000) + ret = 10; + else + ret = 1; + + len = (__u32)skb->data_end - (__u32)skb->data; + f = bpf_map_lookup_elem(&sock_skb_opts, &zero); + if (f && *f) { + ret = 3; + flags = *f; + } + + bpf_printk("sk_skb2: redirect(%iB) flags=%i\n", + len, flags); +#ifdef SOCKMAP + return bpf_sk_redirect_map(skb, &sock_map, ret, flags); +#else + return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags); +#endif + +} + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 lport, rport; + int op, err = 0, index, key, ret; + + + op = (int) skops->op; + + switch (op) { + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (lport == 10000) { + ret = 1; +#ifdef SOCKMAP + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + err = bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + bpf_printk("passive(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (bpf_ntohl(rport) == 10001) { + ret = 10; +#ifdef SOCKMAP + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#else + err = bpf_sock_hash_update(skops, &sock_map, &ret, + BPF_NOEXIST); +#endif + bpf_printk("active(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + default: + break; + } + + return 0; +} + +SEC("sk_msg1") +int bpf_prog4(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + return SK_PASS; +} + +SEC("sk_msg2") +int bpf_prog5(struct sk_msg_md *msg) +{ + int err1 = -1, err2 = -1, zero = 0, one = 1; + int *bytes, *start, *end, len1, len2; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + int err; + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n", + len1, err1, err2); + return SK_PASS; +} + +SEC("sk_msg3") +int bpf_prog6(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1, key = 0; + int *start, *end, *f; + __u64 flags = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } +#ifdef SOCKMAP + return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +#else + return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags); +#endif +} + +SEC("sk_msg4") +int bpf_prog7(struct sk_msg_md *msg) +{ + int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0; + int *f, *bytes, *start, *end, len1, len2; + __u64 flags = 0; + + int err; + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n", + len1, flags, err1 ? err1 : err2); +#ifdef SOCKMAP + err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +#else + err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags); +#endif + bpf_printk("sk_msg3: err %i\n", err); + return err; +} + +SEC("sk_msg5") +int bpf_prog8(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) { + ret = bpf_msg_apply_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } else { + return SK_DROP; + } + return SK_PASS; +} +SEC("sk_msg6") +int bpf_prog9(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) { + if (((__u64)data_end - (__u64)data) >= *bytes) + return SK_PASS; + ret = bpf_msg_cork_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } + return SK_PASS; +} + +SEC("sk_msg7") +int bpf_prog10(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + + return SK_DROP; +} + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/test_stacktrace_build_id.c index b755bd783ce5..d86c281e957f 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/test_stacktrace_build_id.c @@ -19,7 +19,7 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { @@ -31,6 +31,14 @@ struct bpf_map_def SEC("maps") stackmap = { .map_flags = BPF_F_STACK_BUILD_ID, }; +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH, + .max_entries = 128, +}; + /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */ struct random_urandom_args { unsigned long long pad; @@ -42,7 +50,10 @@ struct random_urandom_args { SEC("tracepoint/random/urandom_read") int oncpu(struct random_urandom_args *args) { + __u32 max_len = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH; __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -50,8 +61,13 @@ int oncpu(struct random_urandom_args *args) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(args, stack_p, max_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/test_stacktrace_map.c index 76d85c5d08bd..af111af7ca1a 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/test_stacktrace_map.c @@ -19,14 +19,21 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { .type = BPF_MAP_TYPE_STACK_TRACE, .key_size = sizeof(__u32), .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, - .max_entries = 10000, + .max_entries = 16384, +}; + +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, + .max_entries = 16384, }; /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ @@ -44,7 +51,9 @@ struct sched_switch_args { SEC("tracepoint/sched/sched_switch") int oncpu(struct sched_switch_args *ctx) { + __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -52,8 +61,12 @@ int oncpu(struct sched_switch_args *ctx) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(ctx, &stackmap, 0); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(ctx, stack_p, max_len, 0); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh new file mode 100755 index 000000000000..aeb2901f21f4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -0,0 +1,729 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# End-to-end eBPF tunnel test suite +# The script tests BPF network tunnel implementation. +# +# Topology: +# --------- +# root namespace | at_ns0 namespace +# | +# ----------- | ----------- +# | tnl dev | | | tnl dev | (overlay network) +# ----------- | ----------- +# metadata-mode | native-mode +# with bpf | +# | +# ---------- | ---------- +# | veth1 | --------- | veth0 | (underlay network) +# ---------- peer ---------- +# +# +# Device Configuration +# -------------------- +# Root namespace with metadata-mode tunnel + BPF +# Device names and addresses: +# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay) +# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay) +# +# Namespace at_ns0 with native tunnel +# Device names and addresses: +# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay) +# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay) +# +# +# End-to-end ping packet flow +# --------------------------- +# Most of the tests start by namespace creation, device configuration, +# then ping the underlay and overlay network. When doing 'ping 10.1.1.100' +# from root namespace, the following operations happen: +# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. +# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, +# with remote_ip=172.16.1.200 and others. +# 3) Outer tunnel header is prepended and route the packet to veth1's egress +# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 +# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet +# 6) Forward the packet to the overlay tnl dev + +PING_ARG="-c 3 -w 10 -q" +ret=0 +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +config_device() +{ + ip netns add at_ns0 + ip link add veth0 type veth peer name veth1 + ip link set veth0 netns at_ns0 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip link set dev veth1 up mtu 1500 + ip addr add dev veth1 172.16.1.200/24 +} + +add_gre_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE key 2 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6gretap_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ + local ::11 remote ::22 + + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip addr add dev $DEV fc80::200/24 + ip link set dev $DEV up +} + +add_erspan_tunnel() +{ + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 2 erspan_dir egress erspan_hwid 3 + fi + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6erspan_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 2 erspan_dir egress erspan_hwid 7 + fi + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_vxlan_tunnel() +{ + # Set static ARP entry here because iptables set-mark works + # on L3 packet, as a result not applying to ARP packets, + # causing errors at get_tunnel_{key/opt}. + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 4789 gbp remote 172.16.1.200 + ip netns exec at_ns0 \ + ip link set dev $DEV_NS address 52:54:00:d9:01:00 up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF + + # root namespace + ip link add dev $DEV type $TYPE external gbp dstport 4789 + ip link set dev $DEV address 52:54:00:d9:02:00 up + ip addr add dev $DEV 10.1.1.200/24 + arp -s 10.1.1.100 52:54:00:d9:01:00 +} + +add_ip6vxlan_tunnel() +{ + #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0 + ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + #ip -4 addr del 172.16.1.200 dev veth1 + ip -6 addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external dstport 4789 + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_geneve_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 6081 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE dstport 6081 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6geneve_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 \ + remote ::22 # geneve has no local option + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_ipip_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ipip6tnl_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +test_gre() +{ + TYPE=gretap + DEV_NS=gretap00 + DEV=gretap11 + ret=0 + + check $TYPE + config_device + add_gre_tunnel + attach_bpf $DEV gre_set_tunnel gre_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gre() +{ + TYPE=ip6gre + DEV_NS=ip6gre00 + DEV=ip6gre11 + ret=0 + + check $TYPE + config_device + # reuse the ip6gretap function + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gretap() +{ + TYPE=ip6gretap + DEV_NS=ip6gretap00 + DEV=ip6gretap11 + ret=0 + + check $TYPE + config_device + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_erspan() +{ + TYPE=erspan + DEV_NS=erspan00 + DEV=erspan11 + ret=0 + + check $TYPE + config_device + add_erspan_tunnel $1 + attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6erspan() +{ + TYPE=ip6erspan + DEV_NS=ip6erspan00 + DEV=ip6erspan11 + ret=0 + + check $TYPE + config_device + add_ip6erspan_tunnel $1 + attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel + ping6 $PING_ARG ::11 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_vxlan() +{ + TYPE=vxlan + DEV_NS=vxlan00 + DEV=vxlan11 + ret=0 + + check $TYPE + config_device + add_vxlan_tunnel + attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6vxlan() +{ + TYPE=vxlan + DEV_NS=ip6vxlan00 + DEV=ip6vxlan11 + ret=0 + + check $TYPE + config_device + add_ip6vxlan_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_geneve() +{ + TYPE=geneve + DEV_NS=geneve00 + DEV=geneve11 + ret=0 + + check $TYPE + config_device + add_geneve_tunnel + attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6geneve() +{ + TYPE=geneve + DEV_NS=ip6geneve00 + DEV=ip6geneve11 + ret=0 + + check $TYPE + config_device + add_ip6geneve_tunnel + attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_ipip() +{ + TYPE=ipip + DEV_NS=ipip00 + DEV=ipip11 + ret=0 + + check $TYPE + config_device + add_ipip_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ipip6() +{ + TYPE=ip6tnl + DEV_NS=ipip6tnl00 + DEV=ipip6tnl11 + ret=0 + + check $TYPE + config_device + add_ipip6tnl_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +setup_xfrm_tunnel() +{ + auth=0x$(printf '1%.0s' {1..40}) + enc=0x$(printf '2%.0s' {1..32}) + spi_in_to_out=0x1 + spi_out_to_in=0x2 + # at_ns0 namespace + # at_ns0 -> root + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip netns exec at_ns0 \ + ip addr add dev veth0 10.1.1.100/32 + ip netns exec at_ns0 \ + ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ + src 10.1.1.100 + + # root namespace + # at_ns0 -> root + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip addr add dev veth1 10.1.1.200/32 + ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 +} + +test_xfrm_tunnel() +{ + config_device + #tcpdump -nei veth1 ip & + output=$(mktemp) + cat /sys/kernel/debug/tracing/trace_pipe | tee $output & + setup_xfrm_tunnel + tc qdisc add dev veth1 clsact + tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \ + sec xfrm_get_state + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + sleep 1 + grep "reqid 1" $output + check_err $? + grep "spi 0x1" $output + check_err $? + grep "remote ip 0xac100164" $output + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: xfrm tunnel"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: xfrm tunnel"${NC} +} + +attach_bpf() +{ + DEV=$1 + SET=$2 + GET=$3 + tc qdisc add dev $DEV clsact + tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET + tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET +} + +cleanup() +{ + ip netns delete at_ns0 2> /dev/null + ip link del veth1 2> /dev/null + ip link del ipip11 2> /dev/null + ip link del ipip6tnl11 2> /dev/null + ip link del gretap11 2> /dev/null + ip link del ip6gre11 2> /dev/null + ip link del ip6gretap11 2> /dev/null + ip link del vxlan11 2> /dev/null + ip link del ip6vxlan11 2> /dev/null + ip link del geneve11 2> /dev/null + ip link del ip6geneve11 2> /dev/null + ip link del erspan11 2> /dev/null + ip link del ip6erspan11 2> /dev/null +} + +cleanup_exit() +{ + echo "CATCH SIGKILL or SIGINT, cleanup and exit" + cleanup + exit 0 +} + +check() +{ + ip link help $1 2>&1 | grep -q "^Usage:" + if [ $? -ne 0 ];then + echo "SKIP $1: iproute2 not support" + cleanup + return 1 + fi +} + +enable_debug() +{ + echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control +} + +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +bpf_tunnel_test() +{ + echo "Testing GRE tunnel..." + test_gre + echo "Testing IP6GRE tunnel..." + test_ip6gre + echo "Testing IP6GRETAP tunnel..." + test_ip6gretap + echo "Testing ERSPAN tunnel..." + test_erspan v2 + echo "Testing IP6ERSPAN tunnel..." + test_ip6erspan v2 + echo "Testing VXLAN tunnel..." + test_vxlan + echo "Testing IP6VXLAN tunnel..." + test_ip6vxlan + echo "Testing GENEVE tunnel..." + test_geneve + echo "Testing IP6GENEVE tunnel..." + test_ip6geneve + echo "Testing IPIP tunnel..." + test_ipip + echo "Testing IPIP6 tunnel..." + test_ipip6 + echo "Testing IPSec tunnel..." + test_xfrm_tunnel +} + +trap cleanup 0 3 6 +trap cleanup_exit 2 9 + +cleanup +bpf_tunnel_test + +exit 0 diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/test_tunnel_kern.c new file mode 100644 index 000000000000..504df69c83df --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel_kern.c @@ -0,0 +1,713 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016 VMware + * Copyright (c) 2016 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 + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/pkt_cls.h> +#include <linux/erspan.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define ERROR(ret) do {\ + char fmt[] = "ERROR line:%d ret:%d\n";\ + bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \ + } while (0) + +int _version SEC("version") = 1; + +struct geneve_opt { + __be16 opt_class; + __u8 type; + __u8 length:5; + __u8 r3:1; + __u8 r2:1; + __u8 r1:1; + __u8 opt_data[8]; /* hard-coded to 8 byte */ +}; + +struct vxlan_metadata { + __u32 gbp; +}; + +SEC("gre_set_tunnel") +int _gre_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("gre_get_tunnel") +int _gre_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "key %d remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ip6gretap_set_tunnel") +int _ip6gretap_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + key.tunnel_label = 0xabcde; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6gretap_get_tunnel") +int _ip6gretap_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("erspan_set_tunnel") +int _erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); +#ifdef ERSPAN_V1 + md.version = 1; + md.u.index = bpf_htonl(123); +#else + __u8 direction = 1; + __u8 hwid = 7; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("erspan_get_tunnel") +int _erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_set_tunnel") +int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); + +#ifdef ERSPAN_V1 + md.u.index = bpf_htonl(123); + md.version = 1; +#else + __u8 direction = 0; + __u8 hwid = 17; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_get_tunnel") +int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("vxlan_set_tunnel") +int _vxlan_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */ + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("vxlan_get_tunnel") +int _vxlan_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.gbp); + + return TC_ACT_OK; +} + +SEC("ip6vxlan_set_tunnel") +int _ip6vxlan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6vxlan_get_tunnel") +int _ip6vxlan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("geneve_set_tunnel") +int _geneve_set_tunnel(struct __sk_buff *skb) +{ + int ret, ret2; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("geneve_get_tunnel") +int _geneve_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + return TC_ACT_OK; +} + +SEC("ip6geneve_set_tunnel") +int _ip6geneve_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6geneve_get_tunnel") +int _ip6geneve_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + + return TC_ACT_OK; +} + +SEC("ipip_set_tunnel") +int _ipip_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) { + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + } else { + if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) + return TC_ACT_SHOT; + + if (tcp->dest == bpf_htons(5200)) + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + else if (tcp->dest == bpf_htons(5201)) + key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */ + else + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip_get_tunnel") +int _ipip_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ipip6_set_tunnel") +int _ipip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip6_get_tunnel") +int _ipip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("ip6ip6_set_tunnel") +int _ip6ip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct ipv6hdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.remote_ipv6[0] = bpf_htonl(0x2401db00); + key.tunnel_ttl = 64; + + if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) { + key.remote_ipv6[3] = bpf_htonl(1); + } else { + if (iph->nexthdr != 6 /* NEXTHDR_TCP */) { + ERROR(iph->nexthdr); + return TC_ACT_SHOT; + } + + if (tcp->dest == bpf_htons(5200)) { + key.remote_ipv6[3] = bpf_htonl(1); + } else if (tcp->dest == bpf_htons(5201)) { + key.remote_ipv6[3] = bpf_htonl(2); + } else { + ERROR(tcp->dest); + return TC_ACT_SHOT; + } + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6ip6_get_tunnel") +int _ip6ip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("xfrm_get_state") +int _xfrm_get_state(struct __sk_buff *skb) +{ + struct bpf_xfrm_state x; + char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n"; + int ret; + + ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0); + if (ret < 0) + return TC_ACT_OK; + + bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi), + bpf_ntohl(x.remote_ipv4)); + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index fd7de7eb329e..7cb1d74057ce 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -41,15 +41,16 @@ # endif #endif #include "bpf_rlimit.h" +#include "bpf_rand.h" #include "../../../include/linux/filter.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif -#define MAX_INSNS 512 +#define MAX_INSNS BPF_MAXINSNS #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 4 +#define MAX_NR_MAPS 7 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -64,7 +65,10 @@ struct bpf_test { struct bpf_insn insns[MAX_INSNS]; int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; - int fixup_prog[MAX_FIXUPS]; + int fixup_map3[MAX_FIXUPS]; + int fixup_map4[MAX_FIXUPS]; + int fixup_prog1[MAX_FIXUPS]; + int fixup_prog2[MAX_FIXUPS]; int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; @@ -76,6 +80,8 @@ struct bpf_test { } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; + __u8 data[TEST_DATA_LEN]; + void (*fill_helper)(struct bpf_test *self); }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -88,6 +94,91 @@ struct test_val { int foo[MAX_ENTRIES]; }; +struct other_val { + long long foo; + long long bar; +}; + +static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) +{ + /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ +#define PUSH_CNT 51 + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn = self->insns; + int i = 0, j, k = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); +loop: + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); + insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_pop), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + if (++k < 5) + goto loop; + + for (; i < len - 1; i++) + insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef); + insn[len - 1] = BPF_EXIT_INSN(); +} + +static void bpf_fill_jump_around_ld_abs(struct bpf_test *self) +{ + struct bpf_insn *insn = self->insns; + unsigned int len = BPF_MAXINSNS; + int i = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2); + i++; + while (i < len - 1) + insn[i++] = BPF_LD_ABS(BPF_B, 1); + insn[i] = BPF_EXIT_INSN(); +} + +static void bpf_fill_rand_ld_dw(struct bpf_test *self) +{ + struct bpf_insn *insn = self->insns; + uint64_t res = 0; + int i = 0; + + insn[i++] = BPF_MOV32_IMM(BPF_REG_0, 0); + while (i < self->retval) { + uint64_t val = bpf_semi_rand_get(); + struct bpf_insn tmp[2] = { BPF_LD_IMM64(BPF_REG_1, val) }; + + res ^= val; + insn[i++] = tmp[0]; + insn[i++] = tmp[1]; + insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1); + } + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); + insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32); + insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1); + insn[i] = BPF_EXIT_INSN(); + res ^= (res >> 32); + self->retval = (uint32_t)res; +} + static struct bpf_test tests[] = { { "add+sub+mul", @@ -1597,6 +1688,121 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SK_SKB, }, { + "valid access family in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, family)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_ip4 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access local_ip4 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_port in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access local_port in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "valid access remote_ip6 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, remote_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access local_ip6 in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct sk_msg_md, local_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "invalid 64B read of family in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, family)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "invalid read past end of SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, local_port) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { + "invalid read offset in SK_MSG", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct sk_msg_md, family) + 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_MSG, + }, + { "direct packet read for SK_MSG", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, @@ -2565,7 +2771,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .errstr_unpriv = "R3 leaks addr into helper", .result_unpriv = REJECT, .result = ACCEPT, @@ -2652,7 +2858,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 42, }, @@ -2666,7 +2872,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 41, }, @@ -2680,7 +2886,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 1, }, @@ -2694,7 +2900,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 2, }, @@ -2708,7 +2914,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 1 }, + .fixup_prog1 = { 1 }, .result = ACCEPT, .retval = 2, }, @@ -2722,7 +2928,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .fixup_prog = { 2 }, + .fixup_prog1 = { 2 }, .result = ACCEPT, .retval = 42, }, @@ -5594,6 +5800,257 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map lookup helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 8 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map: wrong size", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .fixup_map3 = { 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=0 size=16", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + offsetof(struct other_val, bar)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + sizeof(struct other_val) - 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + 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_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct other_val, bar)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + sizeof(struct other_val) - 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, -4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): wrong max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar) + 1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=9 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -11227,6 +11684,112 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "calls: two calls returning different map pointers for lookup (hash, array)", + .insns = { + /* main prog */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_CALL_REL(11), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_CALL_REL(12), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + 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_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + /* subprog 1 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* subprog 2 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map2 = { 13 }, + .fixup_map4 = { 16 }, + .result = ACCEPT, + .retval = 1, + }, + { + "calls: two calls returning different map pointers for lookup (hash, map in map)", + .insns = { + /* main prog */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_CALL_REL(11), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_CALL_REL(12), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + 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_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + /* subprog 1 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* subprog 2 */ + BPF_LD_MAP_FD(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_in_map = { 16 }, + .fixup_map4 = { 13 }, + .result = REJECT, + .errstr = "R0 invalid mem access 'map_ptr'", + }, + { + "cond: two branches returning different map pointers for lookup (tail, tail)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 2 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, + .retval = 42, + }, + { + "cond: two branches returning same map pointers for lookup (tail, tail)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog2 = { 2, 5 }, + .result_unpriv = ACCEPT, + .result = ACCEPT, + .retval = 42, + }, + { "search pruning: all branches should be verified (nop operation)", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -11423,6 +11986,278 @@ static struct bpf_test tests[] = { .errstr = "BPF_XADD stores into R2 packet", .prog_type = BPF_PROG_TYPE_XDP, }, + { + "bpf_get_stack return R0 within range", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_4, 256), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32), + BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16), + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_9), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 4 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "ld_abs: invalid op 1", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_DW, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: invalid op 2", + .insns = { + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_IND(BPF_DW, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: nmap reduced", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26), + BPF_MOV32_IMM(BPF_REG_0, 18), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64), + BPF_LD_IND(BPF_W, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60), + BPF_MOV32_IMM(BPF_REG_0, 280971478), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13), + BPF_MOV32_IMM(BPF_REG_0, 22), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LD_IND(BPF_H, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52), + BPF_MOV32_IMM(BPF_REG_0, 17366), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .data = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 256, + }, + { + "ld_abs: div + abs, test 1", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, + { + "ld_abs: div + abs, test 2", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 128), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 3", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 4", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 256), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: vlan + abs, test 1", + .insns = { }, + .data = { + 0x34, + }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0xbef, + }, + { + "ld_abs: vlan + abs, test 2", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .data = { + 0x34, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 42, + }, + { + "ld_abs: jump around ld_abs", + .insns = { }, + .data = { + 10, 11, + }, + .fill_helper = bpf_fill_jump_around_ld_abs, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 1", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 4090, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 2", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 2047, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 3", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 511, + }, + { + "ld_dw: xor semi-random 64 bit imms, test 4", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 5, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -11435,12 +12270,13 @@ static int probe_filter_length(const struct bpf_insn *fp) return len + 1; } -static int create_map(uint32_t size_value, uint32_t max_elem) +static int create_map(uint32_t type, uint32_t size_key, + uint32_t size_value, uint32_t max_elem) { int fd; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(long long), - size_value, max_elem, BPF_F_NO_PREALLOC); + fd = bpf_create_map(type, size_key, size_value, max_elem, + type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0); if (fd < 0) printf("Failed to create hash map '%s'!\n", strerror(errno)); @@ -11473,13 +12309,13 @@ static int create_prog_dummy2(int mfd, int idx) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_array(void) +static int create_prog_array(uint32_t max_elem, int p1key) { - int p1key = 0, p2key = 1; + int p2key = 1; int mfd, p1fd, p2fd; mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), - sizeof(int), 4, 0); + sizeof(int), max_elem, 0); if (mfd < 0) { printf("Failed to create prog array '%s'!\n", strerror(errno)); return -1; @@ -11526,22 +12362,29 @@ static int create_map_in_map(void) return outer_map_fd; } -static char bpf_vlog[32768]; +static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; - int *fixup_prog = test->fixup_prog; + int *fixup_map3 = test->fixup_map3; + int *fixup_map4 = test->fixup_map4; + int *fixup_prog1 = test->fixup_prog1; + int *fixup_prog2 = test->fixup_prog2; int *fixup_map_in_map = test->fixup_map_in_map; + if (test->fill_helper) + test->fill_helper(test); + /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing * that really matters is value size in this case. */ if (*fixup_map1) { - map_fds[0] = create_map(sizeof(long long), 1); + map_fds[0] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(long long), 1); do { prog[*fixup_map1].imm = map_fds[0]; fixup_map1++; @@ -11549,25 +12392,52 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } if (*fixup_map2) { - map_fds[1] = create_map(sizeof(struct test_val), 1); + map_fds[1] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(struct test_val), 1); do { prog[*fixup_map2].imm = map_fds[1]; fixup_map2++; } while (*fixup_map2); } - if (*fixup_prog) { - map_fds[2] = create_prog_array(); + if (*fixup_map3) { + map_fds[2] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long), + sizeof(struct other_val), 1); + do { + prog[*fixup_map3].imm = map_fds[2]; + fixup_map3++; + } while (*fixup_map3); + } + + if (*fixup_map4) { + map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(struct test_val), 1); + do { + prog[*fixup_map4].imm = map_fds[3]; + fixup_map4++; + } while (*fixup_map4); + } + + if (*fixup_prog1) { + map_fds[4] = create_prog_array(4, 0); + do { + prog[*fixup_prog1].imm = map_fds[4]; + fixup_prog1++; + } while (*fixup_prog1); + } + + if (*fixup_prog2) { + map_fds[5] = create_prog_array(8, 7); do { - prog[*fixup_prog].imm = map_fds[2]; - fixup_prog++; - } while (*fixup_prog); + prog[*fixup_prog2].imm = map_fds[5]; + fixup_prog2++; + } while (*fixup_prog2); } if (*fixup_map_in_map) { - map_fds[3] = create_map_in_map(); + map_fds[6] = create_map_in_map(); do { - prog[*fixup_map_in_map].imm = map_fds[3]; + prog[*fixup_map_in_map].imm = map_fds[6]; fixup_map_in_map++; } while (*fixup_map_in_map); } @@ -11577,10 +12447,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { int fd_prog, expected_ret, reject_from_alignment; + int prog_len, prog_type = test->prog_type; struct bpf_insn *prog = test->insns; - int prog_len = probe_filter_length(prog); - char data_in[TEST_DATA_LEN] = {}; - int prog_type = test->prog_type; int map_fds[MAX_NR_MAPS]; const char *expected_err; uint32_t retval; @@ -11590,6 +12458,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, map_fds[i] = -1; do_test_fixup(test, prog, map_fds); + prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, @@ -11629,8 +12498,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } if (fd_prog >= 0) { - err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run(fd_prog, 1, test->data, + sizeof(test->data), NULL, NULL, + &retval, NULL); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); goto fail_log; @@ -11788,5 +12658,6 @@ int main(int argc, char **argv) return EXIT_FAILURE; } + bpf_semi_rand_init(); return do_test(unpriv, from, to); } diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c new file mode 100644 index 000000000000..3868dcb63420 --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <assert.h> +#include <errno.h> +#include <poll.h> +#include <unistd.h> +#include <linux/perf_event.h> +#include <sys/mman.h> +#include "trace_helpers.h" + +#define MAX_SYMS 300000 +static struct ksym syms[MAX_SYMS]; +static int sym_cnt; + +static int ksym_cmp(const void *p1, const void *p2) +{ + return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; +} + +int load_kallsyms(void) +{ + FILE *f = fopen("/proc/kallsyms", "r"); + char func[256], buf[256]; + char symbol; + void *addr; + int i = 0; + + if (!f) + return -ENOENT; + + while (!feof(f)) { + if (!fgets(buf, sizeof(buf), f)) + break; + if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) + break; + if (!addr) + continue; + syms[i].addr = (long) addr; + syms[i].name = strdup(func); + i++; + } + sym_cnt = i; + qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); + return 0; +} + +struct ksym *ksym_search(long key) +{ + int start = 0, end = sym_cnt; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = key - syms[mid].addr; + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return &syms[mid]; + } + + if (start >= 1 && syms[start - 1].addr < key && + key < syms[start].addr) + /* valid ksym */ + return &syms[start - 1]; + + /* out of range. return _stext */ + return &syms[0]; +} + +long ksym_get_addr(const char *name) +{ + int i; + + for (i = 0; i < sym_cnt; i++) { + if (strcmp(syms[i].name, name) == 0) + return syms[i].addr; + } + + return 0; +} + +static int page_size; +static int page_cnt = 8; +static struct perf_event_mmap_page *header; + +int perf_event_mmap(int fd) +{ + void *base; + int mmap_size; + + page_size = getpagesize(); + mmap_size = page_size * (page_cnt + 1); + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + printf("mmap err\n"); + return -1; + } + + header = base; + return 0; +} + +static int perf_event_poll(int fd) +{ + struct pollfd pfd = { .fd = fd, .events = POLLIN }; + + return poll(&pfd, 1, 1000); +} + +struct perf_event_sample { + struct perf_event_header header; + __u32 size; + char data[]; +}; + +static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv) +{ + struct perf_event_sample *e = event; + perf_event_print_fn fn = priv; + int ret; + + if (e->header.type == PERF_RECORD_SAMPLE) { + ret = fn(e->data, e->size); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + } else if (e->header.type == PERF_RECORD_LOST) { + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = (void *) e; + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + + return LIBBPF_PERF_EVENT_CONT; +} + +int perf_event_poller(int fd, perf_event_print_fn output_fn) +{ + enum bpf_perf_event_ret ret; + void *buf = NULL; + size_t len = 0; + + for (;;) { + perf_event_poll(fd); + ret = bpf_perf_event_read_simple(header, page_cnt * page_size, + page_size, &buf, &len, + bpf_perf_event_print, + output_fn); + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + } + free(buf); + + return ret; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h new file mode 100644 index 000000000000..3b4bcf7f5084 --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TRACE_HELPER_H +#define __TRACE_HELPER_H + +#include <libbpf.h> + +struct ksym { + long addr; + char *name; +}; + +int load_kallsyms(void); +struct ksym *ksym_search(long key); +long ksym_get_addr(const char *name); + +typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size); + +int perf_event_mmap(int fd); +/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */ +int perf_event_poller(int fd, perf_event_print_fn output_fn); +#endif diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c index 4acfdebf36fa..9de8b7cb4e6d 100644 --- a/tools/testing/selftests/bpf/urandom_read.c +++ b/tools/testing/selftests/bpf/urandom_read.c @@ -6,15 +6,21 @@ #include <stdlib.h> #define BUF_SIZE 256 -int main(void) + +int main(int argc, char *argv[]) { int fd = open("/dev/urandom", O_RDONLY); int i; char buf[BUF_SIZE]; + int count = 4; if (fd < 0) return 1; - for (i = 0; i < 4; ++i) + + if (argc == 2) + count = atoi(argv[1]); + + for (i = 0; i < count; ++i) read(fd, buf, BUF_SIZE); close(fd); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c612d6e38c62..128e548aa377 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,9 +1,14 @@ msg_zerocopy socket psock_fanout +psock_snd psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack reuseaddr_conflict +tcp_mmap +udpgso +udpgso_bench_rx +udpgso_bench_tx diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3ff81a478dbe..663e11e85727 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,13 +5,18 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh +TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd +TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread +$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh new file mode 100755 index 000000000000..d4cfb6a7a086 --- /dev/null +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -0,0 +1,248 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking IPv4 and IPv6 FIB rules API + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} +IP="ip -netns testns" + +RTABLE=100 +GW_IP4=192.51.100.2 +SRC_IP=192.51.100.3 +GW_IP6=2001:db8:1::2 +SRC_IP6=2001:db8:1::3 + +DEV_ADDR=192.51.100.1 +DEV=dummy0 + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-50s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "\n TEST: %-50s [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 +} + +log_section() +{ + echo + echo "######################################################################" + echo "TEST SECTION: $*" + echo "######################################################################" +} + +setup() +{ + set -e + ip netns add testns + $IP link set dev lo up + + $IP link add dummy0 type dummy + $IP link set dev dummy0 up + $IP address add 198.51.100.1/24 dev dummy0 + $IP -6 address add 2001:db8:1::1/64 dev dummy0 + + set +e +} + +cleanup() +{ + $IP link del dev dummy0 &> /dev/null + ip netns del testns +} + +fib_check_iproute_support() +{ + ip rule help 2>&1 | grep -q $1 + if [ $? -ne 0 ]; then + echo "SKIP: iproute2 iprule too old, missing $1 match" + return 1 + fi + + ip route get help 2>&1 | grep -q $2 + if [ $? -ne 0 ]; then + echo "SKIP: iproute2 get route too old, missing $2 match" + return 1 + fi + + return 0 +} + +fib_rule6_del() +{ + $IP -6 rule del $1 + log_test $? 0 "rule6 del $1" +} + +fib_rule6_del_by_pref() +{ + pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + $IP -6 rule del pref $pref +} + +fib_rule6_test_match_n_redirect() +{ + local match="$1" + local getmatch="$2" + + $IP -6 rule add $match table $RTABLE + $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" + log_test $? 0 "rule6 check: $1" + + fib_rule6_del_by_pref "$match" + log_test $? 0 "rule6 del by pref: $match" +} + +fib_rule6_test() +{ + # setup the fib rule redirect route + $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink + + match="oif $DEV" + fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table" + + match="from $SRC_IP6 iif $DEV" + fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + + match="tos 0x10" + fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + + match="fwmark 0x64" + getmatch="mark 0x64" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + + fib_check_iproute_support "uidrange" "uid" + if [ $? -eq 0 ]; then + match="uidrange 100-100" + getmatch="uid 100" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + fi + + fib_check_iproute_support "sport" "sport" + if [ $? -eq 0 ]; then + match="sport 666 dport 777" + fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto tcp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto icmp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match" + fi +} + +fib_rule4_del() +{ + $IP rule del $1 + log_test $? 0 "del $1" +} + +fib_rule4_del_by_pref() +{ + pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + $IP rule del pref $pref +} + +fib_rule4_test_match_n_redirect() +{ + local match="$1" + local getmatch="$2" + + $IP rule add $match table $RTABLE + $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" + log_test $? 0 "rule4 check: $1" + + fib_rule4_del_by_pref "$match" + log_test $? 0 "rule4 del by pref: $match" +} + +fib_rule4_test() +{ + # setup the fib rule redirect route + $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink + + match="oif $DEV" + fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table" + + match="from $SRC_IP iif $DEV" + fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" + + match="tos 0x10" + fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + + match="fwmark 0x64" + getmatch="mark 0x64" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + + fib_check_iproute_support "uidrange" "uid" + if [ $? -eq 0 ]; then + match="uidrange 100-100" + getmatch="uid 100" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + fi + + fib_check_iproute_support "sport" "sport" + if [ $? -eq 0 ]; then + match="sport 666 dport 777" + fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto tcp" + fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match" + fi + + fib_check_iproute_support "ipproto" "ipproto" + if [ $? -eq 0 ]; then + match="ipproto icmp" + fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match" + fi +} + +run_fibrule_tests() +{ + log_section "IPv4 fib rule" + fib_rule4_test + log_section "IPv6 fib rule" + fib_rule6_test +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +# start clean +cleanup &> /dev/null +setup +run_fibrule_tests +cleanup + +exit $ret diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5baac82b9287..78245d60d8bc 100755..100644 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -8,8 +8,11 @@ ret=0 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -VERBOSE=${VERBOSE:=0} -PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} +# all tests in this script. Can be overridden with -t option +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no IP="ip -netns testns" log_test() @@ -20,8 +23,10 @@ log_test() 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 @@ -30,6 +35,13 @@ log_test() [ "$a" = "q" ] && exit 1 fi fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi } setup() @@ -565,20 +577,825 @@ fib_nexthop_test() } ################################################################################ -# +# Tests on route add and replace + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route6() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP -6 ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP -6 ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP -6 ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route6() +{ + add_route6 "2001:db8:104::/64" "$1" +} + +check_route6() +{ + local pfx="2001:db8:104::/64" + local expected="$1" + local out + local rc=0 + + out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + +route_cleanup() +{ + $IP li del red 2>/dev/null + $IP li del dummy1 2>/dev/null + $IP li del veth1 2>/dev/null + $IP li del veth3 2>/dev/null + + cleanup &> /dev/null +} + +route_setup() +{ + route_cleanup + setup + + [ "${VERBOSE}" = "1" ] && set -x + set -e + + $IP li add red up type vrf table 101 + $IP li add veth1 type veth peer name veth2 + $IP li add veth3 type veth peer name veth4 + + $IP li set veth1 up + $IP li set veth3 up + $IP li set veth2 vrf red up + $IP li set veth4 vrf red up + $IP li add dummy1 type dummy + $IP li set dummy1 vrf red up + + $IP -6 addr add 2001:db8:101::1/64 dev veth1 + $IP -6 addr add 2001:db8:101::2/64 dev veth2 + $IP -6 addr add 2001:db8:103::1/64 dev veth3 + $IP -6 addr add 2001:db8:103::2/64 dev veth4 + $IP -6 addr add 2001:db8:104::1/64 dev dummy1 + + $IP addr add 172.16.101.1/24 dev veth1 + $IP addr add 172.16.101.2/24 dev veth2 + $IP addr add 172.16.103.1/24 dev veth3 + $IP addr add 172.16.103.2/24 dev veth4 + $IP addr add 172.16.104.1/24 dev dummy1 + + set +ex +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv6_rt_add() +{ + local rc + + echo + echo "IPv6 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # iproute2 prepend only sets NLM_F_CREATE + # - adds a new route; does NOT convert existing route to ECMP + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Append nexthop to existing route - gw" + + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1" + log_test $? 0 "Append nexthop to existing route - dev only" + + # multipath route can not have a nexthop that is a reject route + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64" + log_test $? 2 "Append nexthop to existing route - reject route" + + # reject route can not be converted to multipath route + run_cmd "$IP -6 ro flush 2001:db8:104::/64" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" + log_test $? 2 "Append nexthop to existing reject route - gw" + + run_cmd "$IP -6 ro flush 2001:db8:104::/64" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" + log_test $? 2 "Append nexthop to existing reject route - dev only" + + # insert mpath directly + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Add multipath route" + + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP -6 ro del 2001:db8:104::/64 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 via 2001:db8:103::3 dev veth3 metric 256 2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} -fib_test() +ipv6_rt_replace_single() { - if [ -n "$TEST" ]; then - eval $TEST + # single path with single path + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route6 "nexthop via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with reject + # + add_initial_route6 "nexthop via 2001:db8:101::2" + run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" + check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" + log_test $? 0 "Single path with reject route" + + # single path with single path using MULTIPATH attribute + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" else - fib_unreg_test - fib_down_test - fib_carrier_test - fib_nexthop_test + check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + log_test $? 0 "Invalid nexthop" fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 via 2001:db8:101::2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv6_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with reject + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" + check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" + log_test $? 0 "Multipath with reject route" + + # route replace fails - invalid nexthop 1 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:113::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv6_rt_replace() +{ + echo + echo "IPv6 route replace tests" + + ipv6_rt_replace_single + ipv6_rt_replace_mpath +} + +ipv6_route_test() +{ + route_setup + + ipv6_rt_add + ipv6_rt_replace + + route_cleanup } +ip_addr_metric_check() +{ + ip addr help 2>&1 | grep -q metric + if [ $? -ne 0 ]; then + echo "iproute2 command does not support metric for addresses. Skipping test" + return 1 + fi + + return 0 +} + +ipv6_addr_metric_test() +{ + local rc + + echo + echo "IPv6 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP -6 addr flush dev dummy1" + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257" + set +e + + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route() +{ + add_route "172.16.104.0/24" "$1" +} + +check_route() +{ + local pfx="172.16.104.0/24" + local expected="$1" + local out + local rc=0 + + out=$($IP ro ls match ${pfx}) + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv4_rt_add() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # iproute2 prepend only sets NLM_F_CREATE + # - adds a new route; does NOT convert existing route to ECMP + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro prepend 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3 172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Add new nexthop for existing prefix" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing route - gw" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing route - dev only" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append unreachable 172.16.104.0/24" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 unreachable 172.16.104.0/24" + log_test $? 0 "Append nexthop to existing route - reject route" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing reject route - gw" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing reject route - dev only" + + # insert mpath directly + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "add multipath route" + + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP ro del 172.16.104.0/24 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.3 dev veth3 metric 256" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} + +ipv4_rt_replace_single() +{ + # single path with single path + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with reject + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Single path with reject route" + + # single path with single path using MULTIPATH attribute + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" + else + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Invalid nexthop" + fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro change 172.16.105.0/24 via 172.16.101.2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv4_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with reject + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Multipath with reject route" + + # route replace fails - invalid nexthop 1 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.111.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.113.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro change 172.16.105.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv4_rt_replace() +{ + echo + echo "IPv4 route replace tests" + + ipv4_rt_replace_single + ipv4_rt_replace_mpath +} + +ipv4_route_test() +{ + route_setup + + ipv4_rt_add + ipv4_rt_replace + + route_cleanup +} + +ipv4_addr_metric_test() +{ + local rc + + echo + echo "IPv4 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP addr add dev dummy1 172.16.104.1/24" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP addr flush dev dummy1" + run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257" + set +e + + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + check_route "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v verbose mode (show commands and output) +EOF +} + +################################################################################ +# main + +while getopts :t:pPhv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +PEER_CMD="ip netns exec ${PEER_NS}" + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" exit $ksft_skip; @@ -598,6 +1415,25 @@ fi # start clean cleanup &> /dev/null -fib_test +for t in $TESTS +do + case $t in + fib_unreg_test|unregister) fib_unreg_test;; + fib_down_test|down) fib_down_test;; + fib_carrier_test|carrier) fib_carrier_test;; + fib_nexthop_test|nexthop) fib_nexthop_test;; + ipv6_route_test|ipv6_rt) ipv6_route_test;; + ipv4_route_test|ipv4_rt) ipv4_route_test;; + ipv6_addr_metric) ipv6_addr_metric_test;; + ipv4_addr_metric) ipv4_addr_metric_test;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi exit $ret diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index 75d922438bc9..d8313d0438b7 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -75,14 +76,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index 1cddf06f691d..c15c6c85c984 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 source lib.sh @@ -73,14 +74,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1ac6c62271f3..7b18a53aa556 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -321,6 +321,50 @@ simple_if_fini() vrf_destroy $vrf_name } +tunnel_create() +{ + local name=$1; shift + local type=$1; shift + local local=$1; shift + local remote=$1; shift + + ip link add name $name type $type \ + local $local remote $remote "$@" + ip link set dev $name up +} + +tunnel_destroy() +{ + local name=$1; shift + + ip link del dev $name +} + +vlan_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf=$1; shift + local ips=("${@}") + local name=$if_name.$vid + + ip link add name $name link $if_name type vlan id $vid + if [ "$vrf" != "" ]; then + ip link set dev $name master $vrf + fi + ip link set dev $name up + __addr_add_del $name add "${ips[@]}" +} + +vlan_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local name=$if_name.$vid + + ip link del dev $name +} + master_name_get() { local if_name=$1 @@ -335,6 +379,15 @@ link_stats_tx_packets_get() ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]' } +tc_rule_stats_get() +{ + local dev=$1; shift + local pref=$1; shift + + tc -j -s filter show dev $dev ingress pref $pref | + jq '.[1].options.actions[].stats.packets' +} + mac_get() { local if_name=$1 @@ -353,19 +406,33 @@ bridge_ageing_time_get() echo $((ageing_time / 100)) } -forwarding_enable() +declare -A SYSCTL_ORIG +sysctl_set() +{ + local key=$1; shift + local value=$1; shift + + SYSCTL_ORIG[$key]=$(sysctl -n $key) + sysctl -qw $key=$value +} + +sysctl_restore() { - ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding) - ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding) + local key=$1; shift - sysctl -q -w net.ipv4.conf.all.forwarding=1 - sysctl -q -w net.ipv6.conf.all.forwarding=1 + sysctl -qw $key=${SYSCTL_ORIG["$key"]} +} + +forwarding_enable() +{ + sysctl_set net.ipv4.conf.all.forwarding 1 + sysctl_set net.ipv6.conf.all.forwarding 1 } forwarding_restore() { - sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd - sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd + sysctl_restore net.ipv6.conf.all.forwarding + sysctl_restore net.ipv4.conf.all.forwarding } tc_offload_check() @@ -381,6 +448,115 @@ tc_offload_check() return 0 } +trap_install() +{ + local dev=$1; shift + local direction=$1; shift + + # For slow-path testing, we need to install a trap to get to + # slow path the packets that would otherwise be switched in HW. + tc filter add dev $dev $direction pref 1 flower skip_sw action trap +} + +trap_uninstall() +{ + local dev=$1; shift + local direction=$1; shift + + tc filter del dev $dev $direction pref 1 flower skip_sw +} + +slow_path_trap_install() +{ + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + trap_install "$@" + fi +} + +slow_path_trap_uninstall() +{ + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + trap_uninstall "$@" + fi +} + +__icmp_capture_add_del() +{ + local add_del=$1; shift + local pref=$1; shift + local vsuf=$1; shift + local tundev=$1; shift + local filter=$1; shift + + tc filter $add_del dev "$tundev" ingress \ + proto ip$vsuf pref $pref \ + flower ip_proto icmp$vsuf $filter \ + action pass +} + +icmp_capture_install() +{ + __icmp_capture_add_del add 100 "" "$@" +} + +icmp_capture_uninstall() +{ + __icmp_capture_add_del del 100 "" "$@" +} + +icmp6_capture_install() +{ + __icmp_capture_add_del add 100 v6 "$@" +} + +icmp6_capture_uninstall() +{ + __icmp_capture_add_del del 100 v6 "$@" +} + +__vlan_capture_add_del() +{ + local add_del=$1; shift + local pref=$1; shift + local dev=$1; shift + local filter=$1; shift + + tc filter $add_del dev "$dev" ingress \ + proto 802.1q pref $pref \ + flower $filter \ + action pass +} + +vlan_capture_install() +{ + __vlan_capture_add_del add 100 "$@" +} + +vlan_capture_uninstall() +{ + __vlan_capture_add_del del 100 "$@" +} + +matchall_sink_create() +{ + local dev=$1; shift + + tc qdisc add dev $dev clsact + tc filter add dev $dev ingress \ + pref 10000 \ + matchall \ + action drop +} + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + $current_test + done +} + ############################################################################## # Tests diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh new file mode 100755 index 000000000000..e6fd7a18c655 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -0,0 +1,159 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the device to mirror to is a +# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated, +# and another gretap / ip6gretap netdevice is then capable of decapsulating the +# traffic. Test that the payload is what is expected (ICMP ping request or +# reply, depending on test). + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_mac + test_ip6gretap_mac + test_two_spans +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_mac() +{ + local tundev=$1; shift + local direction=$1; shift + local prot=$1; shift + local what=$1; shift + + local swp3mac=$(mac_get $swp3) + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ + action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + tc filter del dev $h3 ingress pref 77 + mirror_uninstall $swp1 $direction + + log_test "$direction $what: envelope MAC ($tcflags)" +} + +test_two_spans() +{ + RET=0 + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_install $swp1 egress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + fail_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_uninstall $swp1 egress + quick_test_span_gre_dir gt4 ingress + fail_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + log_test "two simultaneously configured mirrors ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" +} + +test_gretap_mac() +{ + test_span_gre_mac gt4 ingress ip "mirror to gretap" + test_span_gre_mac gt4 egress ip "mirror to gretap" +} + +test_ip6gretap_mac() +{ + test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh new file mode 100755 index 000000000000..360ca133bead --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh @@ -0,0 +1,226 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | +---------------------------------------------------------------------+ | +# | | OL + gt6 (ip6gretap) + gt4 (gretap) | | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | | +# | | : ttl=100 : ttl=100 | | +# | | : tos=inherit : tos=inherit | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | : | : | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | | UL : |,---------------------' | | +# | | + $swp3 : || : | | +# | | | 192.0.2.129/28 : vv : | | +# | | | 2001:db8:2::1/64 : + ul (dummy) : | | +# | +---|---------------------:----------------------:--------------------+ | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 | +# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ +# +# This tests mirroring to gretap and ip6gretap configured in an overlay / +# underlay manner, i.e. with a bound dummy device that marks underlay VRF where +# the encapsulated packed should be routed. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64 + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64 +} + +switch_create() +{ + # Bridge between H1 and H2. + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + + # Underlay. + + simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link add name ul type dummy + ip link set dev ul master v$swp3 + ip link set dev ul up + + # Overlay. + + vrf_create vrf-ol + ip link set dev vrf-ol up + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit dev ul + ip link set dev gt4 master vrf-ol + ip link set dev gt4 up + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit dev ul allow-localremote + ip link set dev gt6 master vrf-ol + ip link set dev gt6 up +} + +switch_destroy() +{ + vrf_destroy vrf-ol + + tunnel_destroy gt6 + tunnel_destroy gt4 + + simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link del dev ul + + tc qdisc del dev $swp1 clsact + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap w/ UL" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap w/ UL" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh new file mode 100755 index 000000000000..3bb4c2ba7b14 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device without vlan filtering (802.1d). The device attached to that +# bridge is a VLAN. + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_stp + test_ip6gretap_stp +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link add name br2 type bridge vlan_filtering 0 + ip link set dev br2 up + + vlan_create $swp3 555 + + ip link set dev $swp3.555 master br2 + ip route add 192.0.2.130/32 dev br2 + ip -6 route add 2001:db8:2::2/128 dev br2 + + ip address add dev br2 192.0.2.129/32 + ip address add dev br2 2001:db8:2::1/128 + + vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + vlan_destroy $h3 555 + ip link del dev br2 + vlan_destroy $swp3 555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_vlan_match() +{ + local tundev=$1; shift + local vlan_match=$1; shift + local what=$1; shift + + full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what" + full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what" +} + +test_gretap() +{ + test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" +} + +test_ip6gretap() +{ + test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" +} + +test_gretap_stp() +{ + full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap" +} + +test_ip6gretap_stp() +{ + full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh new file mode 100755 index 000000000000..aa29d46186a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -0,0 +1,278 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test how mirrors to gretap and ip6gretap react to changes to relevant +# configuration. + +ALL_TESTS=" + test_ttl + test_tun_up + test_egress_up + test_remote_ip + test_tun_del + test_route_del +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + # This test downs $swp3, which deletes the configured IPv6 address + # unless this sysctl is set. + sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1 + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_ttl() +{ + local tundev=$1; shift + local type=$1; shift + local prot=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_ttl 50 action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 + + ip link set dev $tundev type $type ttl 50 + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + ip link set dev $tundev type $type ttl 100 + tc filter del dev $h3 ingress pref 77 + mirror_uninstall $swp1 ingress + + log_test "$what: TTL change ($tcflags)" +} + +test_span_gre_tun_up() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev up + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: tunnel down/up ($tcflags)" +} + +test_span_gre_egress_up() +{ + local tundev=$1; shift + local remote_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $swp3 down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + # After setting the device up, wait for neighbor to get resolved so that + # we can expect mirroring to work. + ip link set dev $swp3 up + while true; do + ip neigh sh dev $swp3 $remote_ip nud reachable | + grep -q ^ + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: egress down/up ($tcflags)" +} + +test_span_gre_remote_ip() +{ + local tundev=$1; shift + local type=$1; shift + local correct_ip=$1; shift + local wrong_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev type $type remote $wrong_ip + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev type $type remote $correct_ip + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: remote address change ($tcflags)" +} + +test_span_gre_tun_del() +{ + local tundev=$1; shift + local type=$1; shift + local flags=$1; shift + local local_ip=$1; shift + local remote_ip=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + ip link del dev $tundev + fail_test_span_gre_dir $tundev ingress + + tunnel_create $tundev $type $local_ip $remote_ip \ + ttl 100 tos inherit $flags + + # Recreating the tunnel doesn't reestablish mirroring, so reinstall it + # and verify it works for the follow-up tests. + mirror_uninstall $swp1 ingress + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: tunnel deleted ($tcflags)" +} + +test_span_gre_route_del() +{ + local tundev=$1; shift + local edev=$1; shift + local route=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + ip route del $route dev $edev + fail_test_span_gre_dir $tundev ingress + + ip route add $route dev $edev + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: underlay route removal ($tcflags)" +} + +test_ttl() +{ + test_span_gre_ttl gt4 gretap ip "mirror to gretap" + test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap" +} + +test_tun_up() +{ + test_span_gre_tun_up gt4 "mirror to gretap" + test_span_gre_tun_up gt6 "mirror to ip6gretap" +} + +test_egress_up() +{ + test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap" + test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap" +} + +test_remote_ip() +{ + test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap" + test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap" +} + +test_tun_del() +{ + test_span_gre_tun_del gt4 gretap "" \ + 192.0.2.129 192.0.2.130 "mirror to gretap" + test_span_gre_tun_del gt6 ip6gretap allow-localremote \ + 2001:db8:2::1 2001:db8:2::2 "mirror to ip6gretap" +} + +test_route_del() +{ + test_span_gre_route_del gt4 $swp3 192.0.2.128/28 "mirror to gretap" + test_span_gre_route_del gt6 $swp3 2001:db8:2::/64 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh new file mode 100755 index 000000000000..12914f40612d --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh @@ -0,0 +1,137 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The +# interfaces on H1 and H2 have two addresses each. Flower match on one of the +# addresses is configured with mirror action. It is expected that when pinging +# this address, mirroring takes place, whereas when pinging the other one, +# there's no mirroring. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 + + ip address add dev $h1 192.0.2.3/28 + ip address add dev $h2 192.0.2.4/28 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h2 192.0.2.4/28 + ip address del dev $h1 192.0.2.3/28 + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_dir_acl() +{ + test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4 +} + +fail_test_span_gre_dir_acl() +{ + fail_test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4 +} + +full_test_span_gre_dir_acl() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local match_dip=$1; shift + local what=$1; shift + + mirror_install $swp1 $direction $tundev \ + "protocol ip flower $tcflags dst_ip $match_dip" + fail_test_span_gre_dir $tundev $direction + test_span_gre_dir_acl "$tundev" "$direction" \ + "$forward_type" "$backward_type" + mirror_uninstall $swp1 $direction + + # Test lack of mirroring after ACL mirror is uninstalled. + fail_test_span_gre_dir_acl "$tundev" "$direction" + + log_test "$direction $what ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap" + full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap" + full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh new file mode 100644 index 000000000000..619b469365be --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -0,0 +1,130 @@ +# SPDX-License-Identifier: GPL-2.0 + +source mirror_lib.sh + +quick_test_span_gre_dir_ips() +{ + local tundev=$1; shift + + do_test_span_dir_ips 10 h3-$tundev "$@" +} + +fail_test_span_gre_dir_ips() +{ + local tundev=$1; shift + + do_test_span_dir_ips 0 h3-$tundev "$@" +} + +test_span_gre_dir_ips() +{ + local tundev=$1; shift + + test_span_dir_ips h3-$tundev "$@" +} + +full_test_span_gre_dir_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \ + "$backward_type" "$ip1" "$ip2" + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +full_test_span_gre_dir_vlan_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local vlan_match=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + + test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \ + "$backward_type" "$ip1" "$ip2" + + tc filter add dev $h3 ingress pref 77 prot 802.1q \ + flower $vlan_match ip_proto 0x2f \ + action pass + mirror_test v$h1 $ip1 $ip2 $h3 77 10 + tc filter del dev $h3 ingress pref 77 + + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +quick_test_span_gre_dir() +{ + quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +fail_test_span_gre_dir() +{ + fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +test_span_gre_dir() +{ + test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_dir() +{ + full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_dir_vlan() +{ + full_test_span_gre_dir_vlan_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_stp_ips() +{ + local tundev=$1; shift + local nbpdev=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + bridge link set dev $nbpdev state disabled + sleep 1 + fail_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + bridge link set dev $nbpdev state forwarding + sleep 1 + quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2 + + mirror_uninstall $swp1 ingress + + log_test "$what: STP state ($tcflags)" +} + +full_test_span_gre_stp() +{ + full_test_span_gre_stp_ips "$@" 192.0.2.1 192.0.2.2 +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh new file mode 100755 index 000000000000..fc0508e40fca --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh @@ -0,0 +1,115 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for +# the tunnel remote address has invalid address at the time that the mirroring +# is set up. Later on, the neighbor is deleted and it is expected to be +# reinitialized using the usual ARP process, and the mirroring offload updated. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_neigh() +{ + local addr=$1; shift + local tundev=$1; shift + local direction=$1; shift + local what=$1; shift + + RET=0 + + ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55 + mirror_install $swp1 $direction $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + ip neigh del dev $swp3 $addr + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 $direction + + log_test "$direction $what: neighbor change ($tcflags)" +} + +test_gretap() +{ + test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap" + test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap" +} + +test_ip6gretap() +{ + test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap" + test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh new file mode 100755 index 000000000000..8fa681eb90e7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh @@ -0,0 +1,127 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint +# is reachable through a next-hop route (as opposed to directly-attached route). + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$h3.rp_filter 0 + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.161/28 + ip address add dev $h3 192.0.2.162/28 + ip address add dev gt4 192.0.2.129/32 + ip address add dev h3-gt4 192.0.2.130/32 + + # IPv6 route can't be added after address. Such routes are rejected due + # to the gateway address having been configured on the local system. It + # works the other way around though. + ip address add dev $swp3 2001:db8:4::1/64 + ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2 + ip address add dev $h3 2001:db8:4::2/64 + ip address add dev gt6 2001:db8:2::1 + ip address add dev h3-gt6 2001:db8:2::2 +} + +cleanup() +{ + pre_cleanup + + ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2 + ip address del dev $h3 2001:db8:4::2/64 + ip address del dev $swp3 2001:db8:4::1/64 + + ip address del dev $h3 192.0.2.162/28 + ip address del dev $swp3 192.0.2.161/28 + + mirror_gre_topo_destroy + vrf_cleanup + + sysctl_restore net.ipv4.conf.$h3.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +test_gretap() +{ + RET=0 + mirror_install $swp1 ingress gt4 "matchall $tcflags" + + # For IPv4, test that there's no mirroring without the route directing + # the traffic to tunnel remote address. Then add it and test that + # mirroring starts. For IPv6 we can't test this due to the limitation + # that routes for locally-specified IPv6 addresses can't be added. + fail_test_span_gre_dir gt4 ingress + + ip route add 192.0.2.130/32 via 192.0.2.162 + quick_test_span_gre_dir gt4 ingress + ip route del 192.0.2.130/32 via 192.0.2.162 + + mirror_uninstall $swp1 ingress + log_test "mirror to gre with next-hop remote ($tcflags)" +} + +test_ip6gretap() +{ + RET=0 + + mirror_install $swp1 ingress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt6 ingress + mirror_uninstall $swp1 ingress + + log_test "mirror to ip6gre with next-hop remote ($tcflags)" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh new file mode 100644 index 000000000000..253419564708 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh @@ -0,0 +1,94 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is the standard topology for testing mirroring to gretap and ip6gretap +# netdevices. The tests that use it tweak it in one way or another--importantly, +# $swp3 and $h3 need to have addresses set up. +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 + gt6 (ip6gretap) + gt4 (gretap) | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# | | : : | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | loc=2001:db8:2::2 loc=192.0.2.130 | +# | rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ + +source mirror_topo_lib.sh + +mirror_gre_topo_h3_create() +{ + mirror_topo_h3_create + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +mirror_gre_topo_h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + mirror_topo_h3_destroy +} + +mirror_gre_topo_switch_create() +{ + mirror_topo_switch_create + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit allow-localremote +} + +mirror_gre_topo_switch_destroy() +{ + tunnel_destroy gt6 + tunnel_destroy gt4 + + mirror_topo_switch_destroy +} + +mirror_gre_topo_create() +{ + mirror_topo_h1_create + mirror_topo_h2_create + mirror_gre_topo_h3_create + + mirror_gre_topo_switch_create +} + +mirror_gre_topo_destroy() +{ + mirror_gre_topo_switch_destroy + + mirror_gre_topo_h3_destroy + mirror_topo_h2_destroy + mirror_topo_h1_destroy +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh new file mode 100755 index 000000000000..88cecdb9a861 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh @@ -0,0 +1,92 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" that mirrors to a gretap netdevice +# whose underlay route points at a vlan device. + +ALL_TESTS=" + test_gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip link add name $swp3.555 link $swp3 type vlan id 555 + ip address add dev $swp3.555 192.0.2.129/32 + ip address add dev $swp3.555 2001:db8:2::1/128 + ip link set dev $swp3.555 up + + ip route add 192.0.2.130/32 dev $swp3.555 + ip -6 route add 2001:db8:2::2/128 dev $swp3.555 + + ip link add name $h3.555 link $h3 type vlan id 555 + ip link set dev $h3.555 master v$h3 + ip address add dev $h3.555 192.0.2.130/28 + ip address add dev $h3.555 2001:db8:2::2/64 + ip link set dev $h3.555 up +} + +cleanup() +{ + pre_cleanup + + ip link del dev $h3.555 + ip link del dev $swp3.555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh new file mode 100755 index 000000000000..5dbc7a08f4bd --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -0,0 +1,270 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the underlay route points at a +# vlan device on top of a bridge device with vlan filtering (802.1q). + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_forbidden_cpu + test_ip6gretap_forbidden_cpu + test_gretap_forbidden_egress + test_ip6gretap_forbidden_egress + test_gretap_untagged_egress + test_ip6gretap_untagged_egress + test_gretap_fdb_roaming + test_ip6gretap_fdb_roaming + test_gretap_stp + test_ip6gretap_stp +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + vlan_create br1 555 "" 192.0.2.129/32 2001:db8:2::1/128 + bridge vlan add dev br1 vid 555 self + ip route rep 192.0.2.130/32 dev br1.555 + ip -6 route rep 2001:db8:2::2/128 dev br1.555 + + vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 + + ip link set dev $swp3 master br1 + bridge vlan add dev $swp3 vid 555 + bridge vlan add dev $swp2 vid 555 +} + +cleanup() +{ + pre_cleanup + + ip link set dev $swp2 nomaster + ip link set dev $swp3 nomaster + vlan_destroy $h3 555 + vlan_destroy br1 555 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_vlan_match() +{ + local tundev=$1; shift + local vlan_match=$1; shift + local what=$1; shift + + full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what" + full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what" +} + +test_gretap() +{ + test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" +} + +test_ip6gretap() +{ + test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" +} + +test_span_gre_forbidden_cpu() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + # Run the pass-test first, to prime neighbor table. + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + # Now forbid the VLAN at the bridge and see it fail. + bridge vlan del dev br1 vid 555 self + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge vlan add dev br1 vid 555 self + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan forbidden at a bridge ($tcflags)" +} + +test_gretap_forbidden_cpu() +{ + test_span_gre_forbidden_cpu gt4 "mirror to gretap" +} + +test_ip6gretap_forbidden_cpu() +{ + test_span_gre_forbidden_cpu gt6 "mirror to ip6gretap" +} + +test_span_gre_forbidden_egress() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + bridge vlan del dev $swp3 vid 555 + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge vlan add dev $swp3 vid 555 + # Re-prime FDB + arping -I br1.555 192.0.2.130 -fqc 1 + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan forbidden at a bridge egress ($tcflags)" +} + +test_gretap_forbidden_egress() +{ + test_span_gre_forbidden_egress gt4 "mirror to gretap" +} + +test_ip6gretap_forbidden_egress() +{ + test_span_gre_forbidden_egress gt6 "mirror to ip6gretap" +} + +test_span_gre_untagged_egress() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + + quick_test_span_gre_dir $tundev ingress + quick_test_span_vlan_dir $h3 555 ingress + + bridge vlan add dev $swp3 vid 555 pvid untagged + sleep 1 + quick_test_span_gre_dir $tundev ingress + fail_test_span_vlan_dir $h3 555 ingress + + bridge vlan add dev $swp3 vid 555 + sleep 1 + quick_test_span_gre_dir $tundev ingress + quick_test_span_vlan_dir $h3 555 ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: vlan untagged at a bridge egress ($tcflags)" +} + +test_gretap_untagged_egress() +{ + test_span_gre_untagged_egress gt4 "mirror to gretap" +} + +test_ip6gretap_untagged_egress() +{ + test_span_gre_untagged_egress gt6 "mirror to ip6gretap" +} + +test_span_gre_fdb_roaming() +{ + local tundev=$1; shift + local what=$1; shift + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + quick_test_span_gre_dir $tundev ingress + + bridge fdb del dev $swp3 $h3mac vlan 555 master + bridge fdb add dev $swp2 $h3mac vlan 555 master + sleep 1 + fail_test_span_gre_dir $tundev ingress + + bridge fdb del dev $swp2 $h3mac vlan 555 master + # Re-prime FDB + arping -I br1.555 192.0.2.130 -fqc 1 + sleep 1 + quick_test_span_gre_dir $tundev ingress + + mirror_uninstall $swp1 ingress + + log_test "$what: MAC roaming ($tcflags)" +} + +test_gretap_fdb_roaming() +{ + test_span_gre_fdb_roaming gt4 "mirror to gretap" +} + +test_ip6gretap_fdb_roaming() +{ + test_span_gre_fdb_roaming gt6 "mirror to ip6gretap" +} + +test_gretap_stp() +{ + full_test_span_gre_stp gt4 $swp3 "mirror to gretap" +} + +test_ip6gretap_stp() +{ + full_test_span_gre_stp gt6 $swp3 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh new file mode 100644 index 000000000000..d36dc26c6c51 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -0,0 +1,132 @@ +# SPDX-License-Identifier: GPL-2.0 + +mirror_install() +{ + local from_dev=$1; shift + local direction=$1; shift + local to_dev=$1; shift + local filter=$1; shift + + tc filter add dev $from_dev $direction \ + pref 1000 $filter \ + action mirred egress mirror dev $to_dev +} + +mirror_uninstall() +{ + local from_dev=$1; shift + local direction=$1; shift + + tc filter del dev $swp1 $direction pref 1000 +} + +mirror_test() +{ + local vrf_name=$1; shift + local sip=$1; shift + local dip=$1; shift + local dev=$1; shift + local pref=$1; shift + local expect=$1; shift + + local t0=$(tc_rule_stats_get $dev $pref) + ip vrf exec $vrf_name \ + ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null + local t1=$(tc_rule_stats_get $dev $pref) + local delta=$((t1 - t0)) + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "Expected to capture $expect packets, got $delta." +} + +do_test_span_dir_ips() +{ + local expect=$1; shift + local dev=$1; shift + local direction=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + icmp_capture_install $dev + mirror_test v$h1 $ip1 $ip2 $dev 100 $expect + mirror_test v$h2 $ip2 $ip1 $dev 100 $expect + icmp_capture_uninstall $dev +} + +quick_test_span_dir_ips() +{ + do_test_span_dir_ips 10 "$@" +} + +fail_test_span_dir_ips() +{ + do_test_span_dir_ips 0 "$@" +} + +test_span_dir_ips() +{ + local dev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + quick_test_span_dir_ips "$dev" "$direction" "$ip1" "$ip2" + + icmp_capture_install $dev "type $forward_type" + mirror_test v$h1 $ip1 $ip2 $dev 100 10 + icmp_capture_uninstall $dev + + icmp_capture_install $dev "type $backward_type" + mirror_test v$h2 $ip2 $ip1 $dev 100 10 + icmp_capture_uninstall $dev +} + +fail_test_span_dir() +{ + fail_test_span_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +test_span_dir() +{ + test_span_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +do_test_span_vlan_dir_ips() +{ + local expect=$1; shift + local dev=$1; shift + local vid=$1; shift + local direction=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + # Install the capture as skip_hw to avoid double-counting of packets. + # The traffic is meant for local box anyway, so will be trapped to + # kernel. + vlan_capture_install $dev "skip_hw vlan_id $vid" + mirror_test v$h1 $ip1 $ip2 $dev 100 $expect + mirror_test v$h2 $ip2 $ip1 $dev 100 $expect + vlan_capture_uninstall $dev +} + +quick_test_span_vlan_dir_ips() +{ + do_test_span_vlan_dir_ips 10 "$@" +} + +fail_test_span_vlan_dir_ips() +{ + do_test_span_vlan_dir_ips 0 "$@" +} + +quick_test_span_vlan_dir() +{ + quick_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +fail_test_span_vlan_dir() +{ + fail_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2 +} diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh new file mode 100644 index 000000000000..04979e5962e7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh @@ -0,0 +1,101 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is the standard topology for testing mirroring. The tests that use it +# tweak it in one way or another--typically add more devices to the topology. +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 | +# +-----|-------------------------------------------------------------------+ +# | +# +-----|-------------------------------------------------------------------+ +# | H3 + $h3 | +# | | +# +-------------------------------------------------------------------------+ + +mirror_topo_h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +mirror_topo_h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +mirror_topo_h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +mirror_topo_h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +mirror_topo_h3_create() +{ + simple_if_init $h3 + tc qdisc add dev $h3 clsact +} + +mirror_topo_h3_destroy() +{ + tc qdisc del dev $h3 clsact + simple_if_fini $h3 +} + +mirror_topo_switch_create() +{ + ip link set dev $swp3 up + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact +} + +mirror_topo_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 + + ip link set dev $swp3 down +} + +mirror_topo_create() +{ + mirror_topo_h1_create + mirror_topo_h2_create + mirror_topo_h3_create + + mirror_topo_switch_create +} + +mirror_topo_destroy() +{ + mirror_topo_switch_destroy + + mirror_topo_h3_destroy + mirror_topo_h2_destroy + mirror_topo_h1_destroy +} diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh new file mode 100755 index 000000000000..9ab2ce77b332 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh @@ -0,0 +1,131 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing mirroring. See mirror_topo_lib.sh +# for more details. +# +# Test for "tc action mirred egress mirror" that mirrors to a vlan device. + +ALL_TESTS=" + test_vlan + test_tagged_vlan +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_topo_create + + vlan_create $swp3 555 + + vlan_create $h3 555 v$h3 + matchall_sink_create $h3.555 + + vlan_create $h1 111 v$h1 192.0.2.17/28 + bridge vlan add dev $swp1 vid 111 + + vlan_create $h2 111 v$h2 192.0.2.18/28 + bridge vlan add dev $swp2 vid 111 +} + +cleanup() +{ + pre_cleanup + + vlan_destroy $h2 111 + vlan_destroy $h1 111 + vlan_destroy $h3 555 + vlan_destroy $swp3 555 + + mirror_topo_destroy + vrf_cleanup +} + +test_vlan_dir() +{ + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + + RET=0 + + mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" + test_span_dir "$h3.555" "$direction" "$forward_type" "$backward_type" + mirror_uninstall $swp1 $direction + + log_test "$direction mirror to vlan ($tcflags)" +} + +test_vlan() +{ + test_vlan_dir ingress 8 0 + test_vlan_dir egress 0 8 +} + +test_tagged_vlan_dir() +{ + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + + RET=0 + + mirror_install $swp1 $direction $swp3.555 "matchall $tcflags" + do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \ + 192.0.2.17 192.0.2.18 + do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" \ + 192.0.2.17 192.0.2.18 + mirror_uninstall $swp1 $direction + + log_test "$direction mirror tagged to vlan ($tcflags)" +} + +test_tagged_vlan() +{ + test_tagged_vlan_dir ingress 8 0 + test_tagged_vlan_dir egress 0 8 +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + trap_install $h3 ingress + + tests_run + + trap_uninstall $h3 ingress + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index cc6a14abfa87..a75cb51cc5bd 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6" NUM_NETIFS=4 source lib.sh @@ -114,12 +115,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 3bc351008db6..8b6d0fb6d604 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test" NUM_NETIFS=8 source lib.sh @@ -191,7 +192,7 @@ multipath_eval() diff=$(echo $weights_ratio - $packets_ratio | bc -l) diff=${diff#-} - test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0 + test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 check_err $? "Too large discrepancy between expected and measured ratios" log_test "$desc" log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" @@ -204,13 +205,11 @@ multipath4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) - sysctl -q -w net.ipv4.fib_multipath_hash_policy=1 + sysctl_set net.ipv4.fib_multipath_hash_policy 1 ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \ nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13 @@ -232,7 +231,7 @@ multipath4_test() ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 \ nexthop via 169.254.3.23 dev $rp13 - sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv4.fib_multipath_hash_policy } multipath6_l4_test() @@ -242,13 +241,11 @@ multipath6_l4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy) - sysctl -q -w net.ipv6.fib_multipath_hash_policy=1 + sysctl_set net.ipv6.fib_multipath_hash_policy 1 ip route replace 2001:db8:2::/64 vrf vrf-r1 \ nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ @@ -271,7 +268,7 @@ multipath6_l4_test() nexthop via fe80:2::22 dev $rp12 \ nexthop via fe80:3::23 dev $rp13 - sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv6.fib_multipath_hash_policy } multipath6_test() @@ -364,13 +361,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 -multipath_test +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 3a6385ebd5d0..813d02d1939d 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ + mirred_egress_mirror_test gact_trap_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -111,6 +113,10 @@ gact_trap_test() { RET=0 + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ skip_hw dst_ip 192.0.2.2 action drop tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \ @@ -179,24 +185,29 @@ cleanup() ip link set $swp1 address $swp1origmac } +mirred_egress_redirect_test() +{ + mirred_egress_test "redirect" +} + +mirred_egress_mirror_test() +{ + mirred_egress_test "mirror" +} + trap cleanup EXIT setup_prepare setup_wait -gact_drop_and_ok_test -mirred_egress_test "redirect" -mirred_egress_test "mirror" +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - gact_drop_and_ok_test - mirred_egress_test "redirect" - mirred_egress_test "mirror" - gact_trap_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh index 2fd15226974b..d2c783e94df3 100755 --- a/tools/testing/selftests/net/forwarding/tc_chains.sh +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="unreachable_chain_test gact_goto_chain_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -107,16 +108,14 @@ trap cleanup EXIT setup_prepare setup_wait -unreachable_chain_test -gact_goto_chain_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - unreachable_chain_test - gact_goto_chain_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 032b882adfc0..20d1077e5a3d 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ + match_src_ip_test match_ip_flags_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -149,6 +151,74 @@ match_src_ip_test() log_test "src_ip match ($tcflags)" } +match_ip_flags_test() +{ + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags ip_flags frag action continue + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags ip_flags firstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags ip_flags nofirstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 4 handle 104 flower \ + $tcflags ip_flags nofrag action drop + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on wrong frag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_fail $? "Matched on wrong firstfrag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on nofirstfrag filter (nofrag) " + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Did not match on nofrag filter (nofrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0,mf" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on frag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match fistfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Matched on wrong nofirstfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Match on wrong nofrag filter (1stfrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256,mf" -q + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256" -q + + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "Did not match on frag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Matched on wrong firstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 3 + check_err $? "Did not match on nofirstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Matched on nofrag filter (no1stfrag)" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + tc filter del dev $h2 ingress protocol ip pref 4 handle 104 flower + + log_test "ip_flags match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} @@ -177,20 +247,14 @@ trap cleanup EXIT setup_prepare setup_wait -match_dst_mac_test -match_src_mac_test -match_dst_ip_test -match_src_ip_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - match_dst_mac_test - match_src_mac_test - match_dst_ip_test - match_src_ip_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh index 077b98048ef4..b5b917203815 100755 --- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh +++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="shared_block_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -109,14 +110,14 @@ trap cleanup EXIT setup_prepare setup_wait -shared_block_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - shared_block_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index d571d213418d..c43c6debda06 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -21,6 +21,14 @@ readonly DADDR6='fd::2' readonly path_sysctl_mem="net.core.optmem_max" +# No arguments: automated test +if [[ "$#" -eq "0" ]]; then + $0 4 tcp -t 1 + $0 6 tcp -t 1 + echo "OK. All tests passed" + exit 0 +fi + # Argument parsing if [[ "$#" -lt "2" ]]; then echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 7514f93e1624..f8cc38afffa2 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -371,7 +371,7 @@ test_pmtu_vti6_link_add_mtu() { fail=0 - min=1280 + min=68 # vti6 can carry IPv4 packets too max=$((65535 - 40)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do @@ -387,7 +387,7 @@ test_pmtu_vti6_link_add_mtu() { done # Now check valid values - for v in 1280 1300 $((65535 - 40)); do + for v in 68 1280 1300 $((65535 - 40)); do ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 mtu="$(link_get_mtu "${ns_a}" vti6_a)" ${ns_a} ip link del vti6_a diff --git a/tools/testing/selftests/net/psock_snd.c b/tools/testing/selftests/net/psock_snd.c new file mode 100644 index 000000000000..7d15e10a9fb6 --- /dev/null +++ b/tools/testing/selftests/net/psock_snd.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/virtio_net.h> +#include <net/if.h> +#include <net/ethernet.h> +#include <netinet/ip.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "psock_lib.h" + +static bool cfg_use_bind; +static bool cfg_use_csum_off; +static bool cfg_use_csum_off_bad; +static bool cfg_use_dgram; +static bool cfg_use_gso; +static bool cfg_use_qdisc_bypass; +static bool cfg_use_vlan; +static bool cfg_use_vnet; + +static char *cfg_ifname = "lo"; +static int cfg_mtu = 1500; +static int cfg_payload_len = DATA_LEN; +static int cfg_truncate_len = INT_MAX; +static uint16_t cfg_port = 8000; + +/* test sending up to max mtu + 1 */ +#define TEST_SZ (sizeof(struct virtio_net_hdr) + ETH_HLEN + ETH_MAX_MTU + 1) + +static char tbuf[TEST_SZ], rbuf[TEST_SZ]; + +static unsigned long add_csum_hword(const uint16_t *start, int num_u16) +{ + unsigned long sum = 0; + int i; + + for (i = 0; i < num_u16; i++) + sum += start[i]; + + return sum; +} + +static uint16_t build_ip_csum(const uint16_t *start, int num_u16, + unsigned long sum) +{ + sum += add_csum_hword(start, num_u16); + + while (sum >> 16) + sum = (sum & 0xffff) + (sum >> 16); + + return ~sum; +} + +static int build_vnet_header(void *header) +{ + struct virtio_net_hdr *vh = header; + + vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr); + + if (cfg_use_csum_off) { + vh->flags |= VIRTIO_NET_HDR_F_NEEDS_CSUM; + vh->csum_start = ETH_HLEN + sizeof(struct iphdr); + vh->csum_offset = __builtin_offsetof(struct udphdr, check); + + /* position check field exactly one byte beyond end of packet */ + if (cfg_use_csum_off_bad) + vh->csum_start += sizeof(struct udphdr) + cfg_payload_len - + vh->csum_offset - 1; + } + + if (cfg_use_gso) { + vh->gso_type = VIRTIO_NET_HDR_GSO_UDP; + vh->gso_size = cfg_mtu - sizeof(struct iphdr); + } + + return sizeof(*vh); +} + +static int build_eth_header(void *header) +{ + struct ethhdr *eth = header; + + if (cfg_use_vlan) { + uint16_t *tag = header + ETH_HLEN; + + eth->h_proto = htons(ETH_P_8021Q); + tag[1] = htons(ETH_P_IP); + return ETH_HLEN + 4; + } + + eth->h_proto = htons(ETH_P_IP); + return ETH_HLEN; +} + +static int build_ipv4_header(void *header, int payload_len) +{ + struct iphdr *iph = header; + + iph->ihl = 5; + iph->version = 4; + iph->ttl = 8; + iph->tot_len = htons(sizeof(*iph) + sizeof(struct udphdr) + payload_len); + iph->id = htons(1337); + iph->protocol = IPPROTO_UDP; + iph->saddr = htonl((172 << 24) | (17 << 16) | 2); + iph->daddr = htonl((172 << 24) | (17 << 16) | 1); + iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0); + + return iph->ihl << 2; +} + +static int build_udp_header(void *header, int payload_len) +{ + const int alen = sizeof(uint32_t); + struct udphdr *udph = header; + int len = sizeof(*udph) + payload_len; + + udph->source = htons(9); + udph->dest = htons(cfg_port); + udph->len = htons(len); + + if (cfg_use_csum_off) + udph->check = build_ip_csum(header - (2 * alen), alen, + htons(IPPROTO_UDP) + udph->len); + else + udph->check = 0; + + return sizeof(*udph); +} + +static int build_packet(int payload_len) +{ + int off = 0; + + off += build_vnet_header(tbuf); + off += build_eth_header(tbuf + off); + off += build_ipv4_header(tbuf + off, payload_len); + off += build_udp_header(tbuf + off, payload_len); + + if (off + payload_len > sizeof(tbuf)) + error(1, 0, "payload length exceeds max"); + + memset(tbuf + off, DATA_CHAR, payload_len); + + return off + payload_len; +} + +static void do_bind(int fd) +{ + struct sockaddr_ll laddr = {0}; + + laddr.sll_family = AF_PACKET; + laddr.sll_protocol = htons(ETH_P_IP); + laddr.sll_ifindex = if_nametoindex(cfg_ifname); + if (!laddr.sll_ifindex) + error(1, errno, "if_nametoindex"); + + if (bind(fd, (void *)&laddr, sizeof(laddr))) + error(1, errno, "bind"); +} + +static void do_send(int fd, char *buf, int len) +{ + int ret; + + if (!cfg_use_vnet) { + buf += sizeof(struct virtio_net_hdr); + len -= sizeof(struct virtio_net_hdr); + } + if (cfg_use_dgram) { + buf += ETH_HLEN; + len -= ETH_HLEN; + } + + if (cfg_use_bind) { + ret = write(fd, buf, len); + } else { + struct sockaddr_ll laddr = {0}; + + laddr.sll_protocol = htons(ETH_P_IP); + laddr.sll_ifindex = if_nametoindex(cfg_ifname); + if (!laddr.sll_ifindex) + error(1, errno, "if_nametoindex"); + + ret = sendto(fd, buf, len, 0, (void *)&laddr, sizeof(laddr)); + } + + if (ret == -1) + error(1, errno, "write"); + if (ret != len) + error(1, 0, "write: %u %u", ret, len); + + fprintf(stderr, "tx: %u\n", ret); +} + +static int do_tx(void) +{ + const int one = 1; + int fd, len; + + fd = socket(PF_PACKET, cfg_use_dgram ? SOCK_DGRAM : SOCK_RAW, 0); + if (fd == -1) + error(1, errno, "socket t"); + + if (cfg_use_bind) + do_bind(fd); + + if (cfg_use_qdisc_bypass && + setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one))) + error(1, errno, "setsockopt qdisc bypass"); + + if (cfg_use_vnet && + setsockopt(fd, SOL_PACKET, PACKET_VNET_HDR, &one, sizeof(one))) + error(1, errno, "setsockopt vnet"); + + len = build_packet(cfg_payload_len); + + if (cfg_truncate_len < len) + len = cfg_truncate_len; + + do_send(fd, tbuf, len); + + if (close(fd)) + error(1, errno, "close t"); + + return len; +} + +static int setup_rx(void) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + struct sockaddr_in raddr = {0}; + int fd; + + fd = socket(PF_INET, SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket r"); + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + raddr.sin_family = AF_INET; + raddr.sin_port = htons(cfg_port); + raddr.sin_addr.s_addr = htonl(INADDR_ANY); + + if (bind(fd, (void *)&raddr, sizeof(raddr))) + error(1, errno, "bind r"); + + return fd; +} + +static void do_rx(int fd, int expected_len, char *expected) +{ + int ret; + + ret = recv(fd, rbuf, sizeof(rbuf), 0); + if (ret == -1) + error(1, errno, "recv"); + if (ret != expected_len) + error(1, 0, "recv: %u != %u", ret, expected_len); + + if (memcmp(rbuf, expected, ret)) + error(1, 0, "recv: data mismatch"); + + fprintf(stderr, "rx: %u\n", ret); +} + +static int setup_sniffer(void) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + int fd; + + fd = socket(PF_PACKET, SOCK_RAW, 0); + if (fd == -1) + error(1, errno, "socket p"); + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + pair_udp_setfilter(fd); + do_bind(fd); + + return fd; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "bcCdgl:qt:vV")) != -1) { + switch (c) { + case 'b': + cfg_use_bind = true; + break; + case 'c': + cfg_use_csum_off = true; + break; + case 'C': + cfg_use_csum_off_bad = true; + break; + case 'd': + cfg_use_dgram = true; + break; + case 'g': + cfg_use_gso = true; + break; + case 'l': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'q': + cfg_use_qdisc_bypass = true; + break; + case 't': + cfg_truncate_len = strtoul(optarg, NULL, 0); + break; + case 'v': + cfg_use_vnet = true; + break; + case 'V': + cfg_use_vlan = true; + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } + + if (cfg_use_vlan && cfg_use_dgram) + error(1, 0, "option vlan (-V) conflicts with dgram (-d)"); + + if (cfg_use_csum_off && !cfg_use_vnet) + error(1, 0, "option csum offload (-c) requires vnet (-v)"); + + if (cfg_use_csum_off_bad && !cfg_use_csum_off) + error(1, 0, "option csum bad (-C) requires csum offload (-c)"); + + if (cfg_use_gso && !cfg_use_csum_off) + error(1, 0, "option gso (-g) requires csum offload (-c)"); +} + +static void run_test(void) +{ + int fdr, fds, total_len; + + fdr = setup_rx(); + fds = setup_sniffer(); + + total_len = do_tx(); + + /* BPF filter accepts only this length, vlan changes MAC */ + if (cfg_payload_len == DATA_LEN && !cfg_use_vlan) + do_rx(fds, total_len - sizeof(struct virtio_net_hdr), + tbuf + sizeof(struct virtio_net_hdr)); + + do_rx(fdr, cfg_payload_len, tbuf + total_len - cfg_payload_len); + + if (close(fds)) + error(1, errno, "close s"); + if (close(fdr)) + error(1, errno, "close r"); +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (system("ip link set dev lo mtu 1500")) + error(1, errno, "ip link set mtu"); + if (system("ip addr add dev lo 172.17.0.1/24")) + error(1, errno, "ip addr add"); + + run_test(); + + fprintf(stderr, "OK\n\n"); + return 0; +} diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh new file mode 100755 index 000000000000..6331d91b86a6 --- /dev/null +++ b/tools/testing/selftests/net/psock_snd.sh @@ -0,0 +1,98 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of packet socket send regression tests + +set -e + +readonly mtu=1500 +readonly iphlen=20 +readonly udphlen=8 + +readonly vnet_hlen=10 +readonly eth_hlen=14 + +readonly mss="$((${mtu} - ${iphlen} - ${udphlen}))" +readonly mss_exceeds="$((${mss} + 1))" + +readonly max_mtu=65535 +readonly max_mss="$((${max_mtu} - ${iphlen} - ${udphlen}))" +readonly max_mss_exceeds="$((${max_mss} + 1))" + +# functional checks (not a full cross-product) + +echo "dgram" +./in_netns.sh ./psock_snd -d + +echo "dgram bind" +./in_netns.sh ./psock_snd -d -b + +echo "raw" +./in_netns.sh ./psock_snd + +echo "raw bind" +./in_netns.sh ./psock_snd -b + +echo "raw qdisc bypass" +./in_netns.sh ./psock_snd -q + +echo "raw vlan" +./in_netns.sh ./psock_snd -V + +echo "raw vnet hdr" +./in_netns.sh ./psock_snd -v + +echo "raw csum_off" +./in_netns.sh ./psock_snd -v -c + +echo "raw csum_off with bad offset (fails)" +(! ./in_netns.sh ./psock_snd -v -c -C) + + +# bounds check: send {max, max + 1, min, min - 1} lengths + +echo "raw min size" +./in_netns.sh ./psock_snd -l 0 + +echo "raw mtu size" +./in_netns.sh ./psock_snd -l "${mss}" + +echo "raw mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -l "${mss_exceeds}") + +# fails due to ARPHRD_ETHER check in packet_extra_vlan_len_allowed +# +# echo "raw vlan mtu size" +# ./in_netns.sh ./psock_snd -V -l "${mss}" + +echo "raw vlan mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -V -l "${mss_exceeds}") + +echo "dgram mtu size" +./in_netns.sh ./psock_snd -d -l "${mss}" + +echo "dgram mtu size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -d -l "${mss_exceeds}") + +echo "raw truncate hlen (fails: does not arrive)" +(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen}))") + +echo "raw truncate hlen - 1 (fails: EINVAL)" +(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen} - 1))") + + +# gso checks: implies -l, because with gso len must exceed gso_size + +echo "raw gso min size" +./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}" + +echo "raw gso min size - 1 (fails)" +(! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}") + +echo "raw gso max size" +./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}" + +echo "raw gso max size + 1 (fails)" +(! ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss_exceeds}") + +echo "OK. All tests passed" diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index fb3767844e42..0d7a44fa30af 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -505,6 +505,108 @@ kci_test_macsec() echo "PASS: macsec" } +#------------------------------------------------------------------- +# Example commands +# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 replay-window 32 \ +# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \ +# sel src 14.0.0.52/24 dst 14.0.0.70/24 +# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \ +# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 +# +# Subcommands not tested +# ip x s update +# ip x s allocspi +# ip x s deleteall +# ip x p update +# ip x p deleteall +# ip x p set +#------------------------------------------------------------------- +kci_test_ipsec() +{ + srcip="14.0.0.52" + dstip="14.0.0.70" + algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + + # flush to be sure there's nothing configured + ip x s flush ; ip x p flush + check_err $? + + # start the monitor in the background + tmpfile=`mktemp ipsectestXXX` + ip x m > $tmpfile & + mpid=$! + sleep 0.2 + + ipsecid="proto esp src $srcip dst $dstip spi 0x07" + ip x s add $ipsecid \ + mode transport reqid 0x07 replay-window 32 \ + $algo sel src $srcip/24 dst $dstip/24 + check_err $? + + lines=`ip x s list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s count | grep -q "SAD count 1" + check_err $? + + lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s delete $ipsecid + check_err $? + + lines=`ip x s list | wc -l` + test $lines -eq 0 + check_err $? + + ipsecsel="dir out src $srcip/24 dst $dstip/24" + ip x p add $ipsecsel \ + tmpl proto esp src $srcip dst $dstip \ + spi 0x07 mode transport reqid 0x07 + check_err $? + + lines=`ip x p list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p count | grep -q "SPD IN 0 OUT 1 FWD 0" + check_err $? + + lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p delete $ipsecsel + check_err $? + + lines=`ip x p list | wc -l` + test $lines -eq 0 + check_err $? + + # check the monitor results + kill $mpid + lines=`wc -l $tmpfile | cut "-d " -f1` + test $lines -eq 20 + check_err $? + rm -rf $tmpfile + + # clean up any leftovers + ip x s flush + check_err $? + ip x p flush + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec" + return 1 + fi + echo "PASS: ipsec" +} + kci_test_gretap() { testns="testns" @@ -758,6 +860,7 @@ kci_test_rtnl() kci_test_vrf kci_test_encap kci_test_macsec + kci_test_ipsec kci_del_dummy } diff --git a/tools/testing/selftests/net/tcp_inq.c b/tools/testing/selftests/net/tcp_inq.c new file mode 100644 index 000000000000..d044b29ddabc --- /dev/null +++ b/tools/testing/selftests/net/tcp_inq.c @@ -0,0 +1,189 @@ +/* + * Copyright 2018 Google Inc. + * Author: Soheil Hassas Yeganeh (soheil@google.com) + * + * Simple example on how to use TCP_INQ and TCP_CM_INQ. + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + */ +#define _GNU_SOURCE + +#include <error.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <pthread.h> +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> + +#ifndef TCP_INQ +#define TCP_INQ 36 +#endif + +#ifndef TCP_CM_INQ +#define TCP_CM_INQ TCP_INQ +#endif + +#define BUF_SIZE 8192 +#define CMSG_SIZE 32 + +static int family = AF_INET6; +static socklen_t addr_len = sizeof(struct sockaddr_in6); +static int port = 4974; + +static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (family) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr4->sin_port = htons(port); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_addr = in6addr_loopback; + addr6->sin6_port = htons(port); + break; + default: + error(1, 0, "illegal family"); + } +} + +void *start_server(void *arg) +{ + int server_fd = (int)(unsigned long)arg; + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + char *buf; + int fd; + int r; + + buf = malloc(BUF_SIZE); + + for (;;) { + fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + break; + } + do { + r = send(fd, buf, BUF_SIZE, 0); + } while (r < 0 && errno == EINTR); + if (r < 0) + perror("send"); + if (r != BUF_SIZE) + fprintf(stderr, "can only send %d bytes\n", r); + /* TCP_INQ can overestimate in-queue by one byte if we send + * the FIN packet. Sleep for 1 second, so that the client + * likely invoked recvmsg(). + */ + sleep(1); + close(fd); + } + + free(buf); + close(server_fd); + pthread_exit(0); +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listen_addr, addr; + int c, one = 1, inq = -1; + pthread_t server_thread; + char cmsgbuf[CMSG_SIZE]; + struct iovec iov[1]; + struct cmsghdr *cm; + struct msghdr msg; + int server_fd, fd; + char *buf; + + while ((c = getopt(argc, argv, "46p:")) != -1) { + switch (c) { + case '4': + family = PF_INET; + addr_len = sizeof(struct sockaddr_in); + break; + case '6': + family = PF_INET6; + addr_len = sizeof(struct sockaddr_in6); + break; + case 'p': + port = atoi(optarg); + break; + } + } + + server_fd = socket(family, SOCK_STREAM, 0); + if (server_fd < 0) + error(1, errno, "server socket"); + setup_loopback_addr(family, &listen_addr); + if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR, + &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(SO_REUSEADDR)"); + if (bind(server_fd, (const struct sockaddr *)&listen_addr, + addr_len) == -1) + error(1, errno, "bind"); + if (listen(server_fd, 128) == -1) + error(1, errno, "listen"); + if (pthread_create(&server_thread, NULL, start_server, + (void *)(unsigned long)server_fd) != 0) + error(1, errno, "pthread_create"); + + fd = socket(family, SOCK_STREAM, 0); + if (fd < 0) + error(1, errno, "client socket"); + setup_loopback_addr(family, &addr); + if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1) + error(1, errno, "connect"); + if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(TCP_INQ)"); + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsgbuf; + msg.msg_controllen = sizeof(cmsgbuf); + msg.msg_flags = 0; + + buf = malloc(BUF_SIZE); + iov[0].iov_base = buf; + iov[0].iov_len = BUF_SIZE / 2; + + if (recvmsg(fd, &msg, 0) != iov[0].iov_len) + error(1, errno, "recvmsg"); + if (msg.msg_flags & MSG_CTRUNC) + error(1, 0, "control message is truncated"); + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) + if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ) + inq = *((int *) CMSG_DATA(cm)); + + if (inq != BUF_SIZE - iov[0].iov_len) { + fprintf(stderr, "unexpected inq: %d\n", inq); + exit(1); + } + + printf("PASSED\n"); + free(buf); + close(fd); + return 0; +} diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c new file mode 100644 index 000000000000..77f762780199 --- /dev/null +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -0,0 +1,447 @@ +/* + * Copyright 2018 Google Inc. + * Author: Eric Dumazet (edumazet@google.com) + * + * Reference program demonstrating tcp mmap() usage, + * and SO_RCVLOWAT hints for receiver. + * + * Note : NIC with header split is needed to use mmap() on TCP : + * Each incoming frame must be a multiple of PAGE_SIZE bytes of TCP payload. + * + * How to use on loopback interface : + * + * ifconfig lo mtu 61512 # 15*4096 + 40 (ipv6 header) + 32 (TCP with TS option header) + * tcp_mmap -s -z & + * tcp_mmap -H ::1 -z + * + * Or leave default lo mtu, but use -M option to set TCP_MAXSEG option to (4096 + 12) + * (4096 : page size on x86, 12: TCP TS option length) + * tcp_mmap -s -z -M $((4096+12)) & + * tcp_mmap -H ::1 -z -M $((4096+12)) + * + * Note: -z option on sender uses MSG_ZEROCOPY, which forces a copy when packets go through loopback interface. + * We might use sendfile() instead, but really this test program is about mmap(), for receivers ;) + * + * $ ./tcp_mmap -s & # Without mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (0 % mmap'ed) in 14.1157 s, 19.4732 Gbit + * cpu usage user:0.057 sys:7.815, 240.234 usec per MB, 65531 c-switches + * received 32768 MB (0 % mmap'ed) in 14.6833 s, 18.7204 Gbit + * cpu usage user:0.043 sys:8.103, 248.596 usec per MB, 65524 c-switches + * received 32768 MB (0 % mmap'ed) in 11.143 s, 24.6682 Gbit + * cpu usage user:0.044 sys:6.576, 202.026 usec per MB, 65519 c-switches + * received 32768 MB (0 % mmap'ed) in 14.9056 s, 18.4413 Gbit + * cpu usage user:0.036 sys:8.193, 251.129 usec per MB, 65530 c-switches + * $ kill %1 # kill tcp_mmap server + * + * $ ./tcp_mmap -s -z & # With mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (99.9939 % mmap'ed) in 6.73792 s, 40.7956 Gbit + * cpu usage user:0.045 sys:2.827, 87.6465 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.26732 s, 37.8238 Gbit + * cpu usage user:0.037 sys:3.087, 95.3369 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.61661 s, 36.0893 Gbit + * cpu usage user:0.046 sys:3.559, 110.016 usec per MB, 65529 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.43764 s, 36.9577 Gbit + * cpu usage user:0.035 sys:3.467, 106.873 usec per MB, 65530 c-switches + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ +#define _GNU_SOURCE +#include <pthread.h> +#include <sys/types.h> +#include <fcntl.h> +#include <error.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <time.h> +#include <sys/time.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <poll.h> +#include <linux/tcp.h> +#include <assert.h> + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define FILE_SZ (1UL << 35) +static int cfg_family = AF_INET6; +static socklen_t cfg_alen = sizeof(struct sockaddr_in6); +static int cfg_port = 8787; + +static int rcvbuf; /* Default: autotuning. Can be set with -r <integer> option */ +static int sndbuf; /* Default: autotuning. Can be set with -w <integer> option */ +static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for receiver */ +static int xflg; /* hash received data (simple xor) (-h option) */ +static int keepflag; /* -k option: receiver shall keep all received file in memory (no munmap() calls) */ + +static int chunk_size = 512*1024; + +unsigned long htotal; + +static inline void prefetch(const void *x) +{ +#if defined(__x86_64__) + asm volatile("prefetcht0 %P0" : : "m" (*(const char *)x)); +#endif +} + +void hash_zone(void *zone, unsigned int length) +{ + unsigned long temp = htotal; + + while (length >= 8*sizeof(long)) { + prefetch(zone + 384); + temp ^= *(unsigned long *)zone; + temp ^= *(unsigned long *)(zone + sizeof(long)); + temp ^= *(unsigned long *)(zone + 2*sizeof(long)); + temp ^= *(unsigned long *)(zone + 3*sizeof(long)); + temp ^= *(unsigned long *)(zone + 4*sizeof(long)); + temp ^= *(unsigned long *)(zone + 5*sizeof(long)); + temp ^= *(unsigned long *)(zone + 6*sizeof(long)); + temp ^= *(unsigned long *)(zone + 7*sizeof(long)); + zone += 8*sizeof(long); + length -= 8*sizeof(long); + } + while (length >= 1) { + temp ^= *(unsigned char *)zone; + zone += 1; + length--; + } + htotal = temp; +} + +void *child_thread(void *arg) +{ + unsigned long total_mmap = 0, total = 0; + struct tcp_zerocopy_receive zc; + unsigned long delta_usec; + int flags = MAP_SHARED; + struct timeval t0, t1; + char *buffer = NULL; + void *addr = NULL; + double throughput; + struct rusage ru; + int lu, fd; + + fd = (int)(unsigned long)arg; + + gettimeofday(&t0, NULL); + + fcntl(fd, F_SETFL, O_NDELAY); + buffer = malloc(chunk_size); + if (!buffer) { + perror("malloc"); + goto error; + } + if (zflg) { + addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0); + if (addr == (void *)-1) + zflg = 0; + } + while (1) { + struct pollfd pfd = { .fd = fd, .events = POLLIN, }; + int sub; + + poll(&pfd, 1, 10000); + if (zflg) { + socklen_t zc_len = sizeof(zc); + int res; + + zc.address = (__u64)addr; + zc.length = chunk_size; + zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, + &zc, &zc_len); + if (res == -1) + break; + + if (zc.length) { + assert(zc.length <= chunk_size); + total_mmap += zc.length; + if (xflg) + hash_zone(addr, zc.length); + total += zc.length; + } + if (zc.recv_skip_hint) { + assert(zc.recv_skip_hint <= chunk_size); + lu = read(fd, buffer, zc.recv_skip_hint); + if (lu > 0) { + if (xflg) + hash_zone(buffer, lu); + total += lu; + } + } + continue; + } + sub = 0; + while (sub < chunk_size) { + lu = read(fd, buffer + sub, chunk_size - sub); + if (lu == 0) + goto end; + if (lu < 0) + break; + if (xflg) + hash_zone(buffer + sub, lu); + total += lu; + sub += lu; + } + } +end: + gettimeofday(&t1, NULL); + delta_usec = (t1.tv_sec - t0.tv_sec) * 1000000 + t1.tv_usec - t0.tv_usec; + + throughput = 0; + if (delta_usec) + throughput = total * 8.0 / (double)delta_usec / 1000.0; + getrusage(RUSAGE_THREAD, &ru); + if (total > 1024*1024) { + unsigned long total_usec; + unsigned long mb = total >> 20; + total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec + + 1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec; + printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n" + " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n", + total / (1024.0 * 1024.0), + 100.0*total_mmap/total, + (double)delta_usec / 1000000.0, + throughput, + (double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0, + (double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0, + (double)total_usec/mb, + ru.ru_nvcsw); + } +error: + free(buffer); + close(fd); + if (zflg) + munmap(addr, chunk_size); + pthread_exit(0); +} + +static void apply_rcvsnd_buf(int fd) +{ + if (rcvbuf && setsockopt(fd, SOL_SOCKET, + SO_RCVBUF, &rcvbuf, sizeof(rcvbuf)) == -1) { + perror("setsockopt SO_RCVBUF"); + } + + if (sndbuf && setsockopt(fd, SOL_SOCKET, + SO_SNDBUF, &sndbuf, sizeof(sndbuf)) == -1) { + perror("setsockopt SO_SNDBUF"); + } +} + + +static void setup_sockaddr(int domain, const char *str_addr, + struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void do_accept(int fdlisten) +{ + if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, + &chunk_size, sizeof(chunk_size)) == -1) { + perror("setsockopt SO_RCVLOWAT"); + } + + apply_rcvsnd_buf(fdlisten); + + while (1) { + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + pthread_t th; + int fd, res; + + fd = accept(fdlisten, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + continue; + } + res = pthread_create(&th, NULL, child_thread, + (void *)(unsigned long)fd); + if (res) { + errno = res; + perror("pthread_create"); + close(fd); + } + } +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listenaddr, addr; + unsigned int max_pacing_rate = 0; + unsigned long total = 0; + char *host = NULL; + int fd, c, on = 1; + char *buffer; + int sflg = 0; + int mss = 0; + + while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) { + switch (c) { + case '4': + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'p': + cfg_port = atoi(optarg); + break; + case 'H': + host = optarg; + break; + case 's': /* server : listen for incoming connections */ + sflg++; + break; + case 'r': + rcvbuf = atoi(optarg); + break; + case 'w': + sndbuf = atoi(optarg); + break; + case 'z': + zflg = 1; + break; + case 'M': + mss = atoi(optarg); + break; + case 'x': + xflg = 1; + break; + case 'k': + keepflag = 1; + break; + case 'P': + max_pacing_rate = atoi(optarg) ; + break; + default: + exit(1); + } + } + if (sflg) { + int fdlisten = socket(cfg_family, SOCK_STREAM, 0); + + if (fdlisten == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fdlisten); + setsockopt(fdlisten, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)); + + setup_sockaddr(cfg_family, host, &listenaddr); + + if (mss && + setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG, + &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (bind(fdlisten, (const struct sockaddr *)&listenaddr, cfg_alen) == -1) { + perror("bind"); + exit(1); + } + if (listen(fdlisten, 128) == -1) { + perror("listen"); + exit(1); + } + do_accept(fdlisten); + } + buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buffer == (char *)-1) { + perror("mmap"); + exit(1); + } + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fd); + + setup_sockaddr(cfg_family, host, &addr); + + if (mss && + setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (connect(fd, (const struct sockaddr *)&addr, cfg_alen) == -1) { + perror("connect"); + exit(1); + } + if (max_pacing_rate && + setsockopt(fd, SOL_SOCKET, SO_MAX_PACING_RATE, + &max_pacing_rate, sizeof(max_pacing_rate)) == -1) + perror("setsockopt SO_MAX_PACING_RATE"); + + if (zflg && setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, + &on, sizeof(on)) == -1) { + perror("setsockopt SO_ZEROCOPY, (-z option disabled)"); + zflg = 0; + } + while (total < FILE_SZ) { + long wr = FILE_SZ - total; + + if (wr > chunk_size) + wr = chunk_size; + /* Note : we just want to fill the pipe with 0 bytes */ + wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + if (wr <= 0) + break; + total += wr; + } + close(fd); + munmap(buffer, chunk_size); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c new file mode 100644 index 000000000000..e279051bc631 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.c @@ -0,0 +1,693 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <stddef.h> +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <net/if.h> +#include <linux/in.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <netinet/if_ether.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#ifndef UDP_MAX_SEGMENTS +#define UDP_MAX_SEGMENTS (1 << 6UL) +#endif + +#define CONST_MTU_TEST 1500 + +#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr)) +#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr)) + +#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4) +#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6) + +#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4) +#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6) + +static bool cfg_do_ipv4; +static bool cfg_do_ipv6; +static bool cfg_do_connected; +static bool cfg_do_connectionless; +static bool cfg_do_msgmore; +static bool cfg_do_setsockopt; +static int cfg_specific_test_id = -1; + +static const char cfg_ifname[] = "lo"; +static unsigned short cfg_port = 9000; + +static char buf[ETH_MAX_MTU]; + +struct testcase { + int tlen; /* send() buffer size, may exceed mss */ + bool tfail; /* send() call is expected to fail */ + int gso_len; /* mss after applying gso */ + int r_num_mss; /* recv(): number of calls of full mss */ + int r_len_last; /* recv(): size of last non-mss dgram, if any */ +}; + +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; +const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; + +struct testcase testcases_v4[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V4, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V4 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V4 * 2, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V4 * 2) + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4), + }, + + { + /* send MAX bytes */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = CONST_MAX_SEGS_V4, + .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 - + (CONST_MAX_SEGS_V4 * CONST_MSS_V4), + }, + { + /* send MAX + 1: fail */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1, + .gso_len = CONST_MSS_V4, + .tfail = true, + }, + { + /* send a single 1B MSS: will fail, see single MSS above */ + .tlen = 1, + .gso_len = 1, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send 2 1B segments */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + }, + { + /* send 2B + 2B + 1B segments */ + .tlen = 5, + .gso_len = 2, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send max number of min sized segments */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4, + .gso_len = 1, + .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4, + }, + { + /* send max number + 1 of min sized segments: fail */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1, + .gso_len = 1, + .tfail = true, + }, + { + /* EOL */ + } +}; + +#ifndef IP6_MAX_MTU +#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr)) +#endif + +struct testcase testcases_v6[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V6, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V6 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V6 * 2, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V6 * 2) + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6), + }, + + { + /* send MAX bytes */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = CONST_MAX_SEGS_V6, + .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 - + (CONST_MAX_SEGS_V6 * CONST_MSS_V6), + }, + { + /* send MAX + 1: fail */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1, + .gso_len = CONST_MSS_V6, + .tfail = true, + }, + { + /* send a single 1B MSS: will fail, see single MSS above */ + .tlen = 1, + .gso_len = 1, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send 2 1B segments */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + }, + { + /* send 2B + 2B + 1B segments */ + .tlen = 5, + .gso_len = 2, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send max number of min sized segments */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6, + .gso_len = 1, + .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6, + }, + { + /* send max number + 1 of min sized segments: fail */ + .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1, + .gso_len = 1, + .tfail = true, + }, + { + /* EOL */ + } +}; + +static unsigned int get_device_mtu(int fd, const char *ifname) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFMTU, &ifr)) + error(1, errno, "ioctl get mtu"); + + return ifr.ifr_mtu; +} + +static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_mtu = mtu; + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCSIFMTU, &ifr)) + error(1, errno, "ioctl set mtu"); +} + +static void set_device_mtu(int fd, int mtu) +{ + int val; + + val = get_device_mtu(fd, cfg_ifname); + fprintf(stderr, "device mtu (orig): %u\n", val); + + __set_device_mtu(fd, cfg_ifname, mtu); + val = get_device_mtu(fd, cfg_ifname); + if (val != mtu) + error(1, 0, "unable to set device mtu to %u\n", val); + + fprintf(stderr, "device mtu (test): %u\n", val); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +static unsigned int get_path_mtu(int fd, bool is_ipv4) +{ + socklen_t vallen; + unsigned int mtu; + int ret; + + vallen = sizeof(mtu); + if (is_ipv4) + ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen); + else + ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen); + + if (ret) + error(1, errno, "getsockopt mtu"); + + + fprintf(stderr, "path mtu (read): %u\n", mtu); + return mtu; +} + +/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */ +static void set_route_mtu(int mtu, bool is_ipv4) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + struct nlmsghdr *nh; + struct rtattr *rta; + struct rtmsg *rt; + char data[NLMSG_ALIGN(sizeof(*nh)) + + NLMSG_ALIGN(sizeof(*rt)) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) + + NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))]; + int fd, ret, alen, off = 0; + + alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6); + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (fd == -1) + error(1, errno, "socket netlink"); + + memset(data, 0, sizeof(data)); + + nh = (void *)data; + nh->nlmsg_type = RTM_NEWROUTE; + nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE; + off += NLMSG_ALIGN(sizeof(*nh)); + + rt = (void *)(data + off); + rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6; + rt->rtm_table = RT_TABLE_MAIN; + rt->rtm_dst_len = alen << 3; + rt->rtm_protocol = RTPROT_BOOT; + rt->rtm_scope = RT_SCOPE_UNIVERSE; + rt->rtm_type = RTN_UNICAST; + off += NLMSG_ALIGN(sizeof(*rt)); + + rta = (void *)(data + off); + rta->rta_type = RTA_DST; + rta->rta_len = RTA_LENGTH(alen); + if (is_ipv4) + memcpy(RTA_DATA(rta), &addr4, alen); + else + memcpy(RTA_DATA(rta), &addr6, alen); + off += NLMSG_ALIGN(rta->rta_len); + + rta = (void *)(data + off); + rta->rta_type = RTA_OIF; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo"); + off += NLMSG_ALIGN(rta->rta_len); + + /* MTU is a subtype in a metrics type */ + rta = (void *)(data + off); + rta->rta_type = RTA_METRICS; + rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)); + off += NLMSG_ALIGN(rta->rta_len); + + /* now fill MTU subtype. Note that it fits within above rta_len */ + rta = (void *)(((char *) rta) + RTA_LENGTH(0)); + rta->rta_type = RTAX_MTU; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = mtu; + + nh->nlmsg_len = off; + + ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr)); + if (ret != off) + error(1, errno, "send netlink: %uB != %uB\n", ret, off); + + if (close(fd)) + error(1, errno, "close netlink"); + + fprintf(stderr, "route mtu (test): %u\n", mtu); +} + +static bool __send_one(int fd, struct msghdr *msg, int flags) +{ + int ret; + + ret = sendmsg(fd, msg, flags); + if (ret == -1 && + (errno == EMSGSIZE || errno == ENOMEM || errno == EINVAL)) + return false; + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != msg->msg_iov->iov_len) + error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len); + if (msg->msg_flags) + error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags); + + return true; +} + +static bool send_one(int fd, int len, int gso_len, + struct sockaddr *addr, socklen_t alen) +{ + char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + + iov.iov_base = buf; + iov.iov_len = len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_name = addr; + msg.msg_namelen = alen; + + if (gso_len && !cfg_do_setsockopt) { + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + cm = CMSG_FIRSTHDR(&msg); + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(uint16_t)); + *((uint16_t *) CMSG_DATA(cm)) = gso_len; + } + + /* If MSG_MORE, send 1 byte followed by remainder */ + if (cfg_do_msgmore && len > 1) { + iov.iov_len = 1; + if (!__send_one(fd, &msg, MSG_MORE)) + error(1, 0, "send 1B failed"); + + iov.iov_base++; + iov.iov_len = len - 1; + } + + return __send_one(fd, &msg, 0); +} + +static int recv_one(int fd, int flags) +{ + int ret; + + ret = recv(fd, buf, sizeof(buf), flags); + if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT)) + return 0; + if (ret == -1) + error(1, errno, "recv"); + + return ret; +} + +static void run_one(struct testcase *test, int fdt, int fdr, + struct sockaddr *addr, socklen_t alen) +{ + int i, ret, val, mss; + bool sent; + + fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + addr->sa_family == AF_INET ? 4 : 6, + test->tlen, test->gso_len, + test->tfail ? "(fail)" : ""); + + val = test->gso_len; + if (cfg_do_setsockopt) { + if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) + error(1, errno, "setsockopt udp segment"); + } + + sent = send_one(fdt, test->tlen, test->gso_len, addr, alen); + if (sent && test->tfail) + error(1, 0, "send succeeded while expecting failure"); + if (!sent && !test->tfail) + error(1, 0, "send failed while expecting success"); + if (!sent) + return; + + if (test->gso_len) + mss = test->gso_len; + else + mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6; + + + /* Recv all full MSS datagrams */ + for (i = 0; i < test->r_num_mss; i++) { + ret = recv_one(fdr, 0); + if (ret != mss) + error(1, 0, "recv.%d: %d != %d", i, ret, mss); + } + + /* Recv the non-full last datagram, if tlen was not a multiple of mss */ + if (test->r_len_last) { + ret = recv_one(fdr, 0); + if (ret != test->r_len_last) + error(1, 0, "recv.%d: %d != %d (last)", + i, ret, test->r_len_last); + } + + /* Verify received all data */ + ret = recv_one(fdr, MSG_DONTWAIT); + if (ret) + error(1, 0, "recv: unexpected datagram"); +} + +static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen) +{ + struct testcase *tests, *test; + + tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6; + + for (test = tests; test->tlen; test++) { + /* if a specific test is given, then skip all others */ + if (cfg_specific_test_id == -1 || + cfg_specific_test_id == test - tests) + run_one(test, fdt, fdr, addr, alen); + } +} + +static void run_test(struct sockaddr *addr, socklen_t alen) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + int fdr, fdt, val; + + fdr = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdr == -1) + error(1, errno, "socket r"); + + if (bind(fdr, addr, alen)) + error(1, errno, "bind"); + + /* Have tests fail quickly instead of hang */ + if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + fdt = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdt == -1) + error(1, errno, "socket t"); + + /* Do not fragment these datagrams: only succeed if GSO works */ + set_pmtu_discover(fdt, addr->sa_family == AF_INET); + + if (cfg_do_connectionless) { + set_device_mtu(fdt, CONST_MTU_TEST); + run_all(fdt, fdr, addr, alen); + } + + if (cfg_do_connected) { + set_device_mtu(fdt, CONST_MTU_TEST + 100); + set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET); + + if (connect(fdt, addr, alen)) + error(1, errno, "connect"); + + val = get_path_mtu(fdt, addr->sa_family == AF_INET); + if (val != CONST_MTU_TEST) + error(1, 0, "bad path mtu %u\n", val); + + run_all(fdt, fdr, addr, 0 /* use connected addr */); + } + + if (close(fdt)) + error(1, errno, "close t"); + if (close(fdr)) + error(1, errno, "close r"); +} + +static void run_test_v4(void) +{ + struct sockaddr_in addr = {0}; + + addr.sin_family = AF_INET; + addr.sin_port = htons(cfg_port); + addr.sin_addr = addr4; + + run_test((void *)&addr, sizeof(addr)); +} + +static void run_test_v6(void) +{ + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr)); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "46cCmst:")) != -1) { + switch (c) { + case '4': + cfg_do_ipv4 = true; + break; + case '6': + cfg_do_ipv6 = true; + break; + case 'c': + cfg_do_connected = true; + break; + case 'C': + cfg_do_connectionless = true; + break; + case 'm': + cfg_do_msgmore = true; + break; + case 's': + cfg_do_setsockopt = true; + break; + case 't': + cfg_specific_test_id = strtoul(optarg, NULL, 0); + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (cfg_do_ipv4) + run_test_v4(); + if (cfg_do_ipv6) + run_test_v6(); + + fprintf(stderr, "OK\n"); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh new file mode 100755 index 000000000000..fec24f584fe9 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.sh @@ -0,0 +1,29 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso regression tests + +echo "ipv4 cmsg" +./in_netns.sh ./udpgso -4 -C + +echo "ipv4 setsockopt" +./in_netns.sh ./udpgso -4 -C -s + +echo "ipv6 cmsg" +./in_netns.sh ./udpgso -6 -C + +echo "ipv6 setsockopt" +./in_netns.sh ./udpgso -6 -C -s + +echo "ipv4 connected" +./in_netns.sh ./udpgso -4 -c + +# blocked on 2nd loopback address +# echo "ipv6 connected" +# ./in_netns.sh ./udpgso -6 -c + +echo "ipv4 msg_more" +./in_netns.sh ./udpgso -4 -C -m + +echo "ipv6 msg_more" +./in_netns.sh ./udpgso -6 -C -m diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh new file mode 100755 index 000000000000..792fa4d0285e --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso benchmarks + +wake_children() { + local -r jobs="$(jobs -p)" + + if [[ "${jobs}" != "" ]]; then + kill -1 ${jobs} 2>/dev/null + fi +} +trap wake_children EXIT + +run_one() { + local -r args=$@ + + ./udpgso_bench_rx & + ./udpgso_bench_rx -t & + + ./udpgso_bench_tx ${args} +} + +run_in_netns() { + local -r args=$@ + + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp" + run_in_netns ${args} + + echo "udp gso" + run_in_netns ${args} -S + + echo "udp gso zerocopy" + run_in_netns ${args} -S -z +} + +run_tcp() { + local -r args=$@ + + echo "tcp" + run_in_netns ${args} -t + + echo "tcp zerocopy" + run_in_netns ${args} -t -z +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 127.0.0.1" + local -r ipv6_args="${core_args} -6 -D ::1" + + echo "ipv4" + run_tcp "${ipv4_args}" + run_udp "${ipv4_args}" + + echo "ipv6" + run_tcp "${ipv4_args}" + run_udp "${ipv6_args}" +} + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c new file mode 100644 index 000000000000..727cf67a3f75 --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <limits.h> +#include <linux/errqueue.h> +#include <linux/if_packet.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +static int cfg_port = 8000; +static bool cfg_tcp; +static bool cfg_verify; + +static bool interrupted; +static unsigned long packets, bytes; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void do_poll(int fd) +{ + struct pollfd pfd; + int ret; + + pfd.events = POLLIN; + pfd.revents = 0; + pfd.fd = fd; + + do { + ret = poll(&pfd, 1, 10); + if (ret == -1) + error(1, errno, "poll"); + if (ret == 0) + continue; + if (pfd.revents != POLLIN) + error(1, errno, "poll: 0x%x expected 0x%x\n", + pfd.revents, POLLIN); + } while (!ret && !interrupted); +} + +static int do_socket(bool do_tcp) +{ + struct sockaddr_in6 addr = {0}; + int fd, val; + + fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + val = 1 << 21; + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val))) + error(1, errno, "setsockopt rcvbuf"); + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val))) + error(1, errno, "setsockopt reuseport"); + + addr.sin6_family = PF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = in6addr_any; + if (bind(fd, (void *) &addr, sizeof(addr))) + error(1, errno, "bind"); + + if (do_tcp) { + int accept_fd = fd; + + if (listen(accept_fd, 1)) + error(1, errno, "listen"); + + do_poll(accept_fd); + + fd = accept(accept_fd, NULL, NULL); + if (fd == -1) + error(1, errno, "accept"); + if (close(accept_fd)) + error(1, errno, "close accept fd"); + } + + return fd; +} + +/* Flush all outstanding bytes for the tcp receive queue */ +static void do_flush_tcp(int fd) +{ + int ret; + + while (true) { + /* MSG_TRUNC flushes up to len bytes */ + ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "flush"); + if (ret == 0) { + /* client detached */ + exit(0); + } + + packets++; + bytes += ret; + } + +} + +static char sanitized_char(char val) +{ + return (val >= 'a' && val <= 'z') ? val : '.'; +} + +static void do_verify_udp(const char *data, int len) +{ + char cur = data[0]; + int i; + + /* verify contents */ + if (cur < 'a' || cur > 'z') + error(1, 0, "data initial byte out of range"); + + for (i = 1; i < len; i++) { + if (cur == 'z') + cur = 'a'; + else + cur++; + + if (data[i] != cur) + error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n", + i, len, + sanitized_char(data[i]), data[i], + sanitized_char(cur), cur); + } +} + +/* Flush all outstanding datagrams. Verify first few bytes of each. */ +static void do_flush_udp(int fd) +{ + static char rbuf[ETH_DATA_LEN]; + int ret, len, budget = 256; + + len = cfg_verify ? sizeof(rbuf) : 0; + while (budget--) { + /* MSG_TRUNC will make return value full datagram length */ + ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "recv"); + if (len) { + if (ret == 0) + error(1, errno, "recv: 0 byte datagram\n"); + + do_verify_udp(rbuf, ret); + } + + packets++; + bytes += ret; + } +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-tv] [-p port]", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "ptv")) != -1) { + switch (c) { + case 'p': + cfg_port = htons(strtoul(optarg, NULL, 0)); + break; + case 't': + cfg_tcp = true; + break; + case 'v': + cfg_verify = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_tcp && cfg_verify) + error(1, 0, "TODO: implement verify mode for tcp"); +} + +static void do_recv(void) +{ + unsigned long tnow, treport; + int fd; + + fd = do_socket(cfg_tcp); + + treport = gettimeofday_ms() + 1000; + do { + do_poll(fd); + + if (cfg_tcp) + do_flush_tcp(fd); + else + do_flush_udp(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + if (packets) + fprintf(stderr, + "%s rx: %6lu MB/s %8lu calls/s\n", + cfg_tcp ? "tcp" : "udp", + bytes >> 20, packets); + bytes = packets = 0; + treport = tnow + 1000; + } + + } while (!interrupted); + + if (close(fd)) + error(1, errno, "close"); +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + signal(SIGINT, sigint_handler); + + do_recv(); + + return 0; +} diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c new file mode 100644 index 000000000000..e821564053cf --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -0,0 +1,420 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <netinet/if_ether.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#ifndef SO_ZEROCOPY +#define SO_ZEROCOPY 60 +#endif + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define NUM_PKT 100 + +static bool cfg_cache_trash; +static int cfg_cpu = -1; +static int cfg_connected = true; +static int cfg_family = PF_UNSPEC; +static uint16_t cfg_mss; +static int cfg_payload_len = (1472 * 42); +static int cfg_port = 8000; +static int cfg_runtime_ms = -1; +static bool cfg_segment; +static bool cfg_sendmmsg; +static bool cfg_tcp; +static bool cfg_zerocopy; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; + +static bool interrupted; +static char buf[NUM_PKT][ETH_MAX_MTU]; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static int set_cpu(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + error(1, 0, "setaffinity %d", cpu); + + return 0; +} + +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void flush_zerocopy(int fd) +{ + struct msghdr msg = {0}; /* flush */ + int ret; + + while (1) { + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC)) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + msg.msg_flags = 0; + } +} + +static int send_tcp(int fd, char *data) +{ + int ret, done = 0, count = 0; + + while (done < cfg_payload_len) { + ret = send(fd, data + done, cfg_payload_len - done, + cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "write"); + + done += ret; + count++; + } + + return count; +} + +static int send_udp(int fd, char *data) +{ + int ret, total_len, len, count = 0; + + total_len = cfg_payload_len; + + while (total_len) { + len = total_len < cfg_mss ? total_len : cfg_mss; + + ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0, + cfg_connected ? NULL : (void *)&cfg_dst_addr, + cfg_connected ? 0 : cfg_alen); + if (ret == -1) + error(1, errno, "write"); + if (ret != len) + error(1, errno, "write: %uB != %uB\n", ret, len); + + total_len -= len; + count++; + } + + return count; +} + +static int send_udp_sendmmsg(int fd, char *data) +{ + const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN; + struct mmsghdr mmsgs[max_nr_msg]; + struct iovec iov[max_nr_msg]; + unsigned int off = 0, left; + int i = 0, ret; + + memset(mmsgs, 0, sizeof(mmsgs)); + + left = cfg_payload_len; + while (left) { + if (i == max_nr_msg) + error(1, 0, "sendmmsg: exceeds max_nr_msg"); + + iov[i].iov_base = data + off; + iov[i].iov_len = cfg_mss < left ? cfg_mss : left; + + mmsgs[i].msg_hdr.msg_iov = iov + i; + mmsgs[i].msg_hdr.msg_iovlen = 1; + + off += iov[i].iov_len; + left -= iov[i].iov_len; + i++; + } + + ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmmsg"); + + return ret; +} + +static void send_udp_segment_cmsg(struct cmsghdr *cm) +{ + uint16_t *valp; + + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss)); + valp = (void *)CMSG_DATA(cm); + *valp = cfg_mss; +} + +static int send_udp_segment(int fd, char *data) +{ + char control[CMSG_SPACE(sizeof(cfg_mss))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + int ret; + + iov.iov_base = data; + iov.iov_len = cfg_payload_len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg)); + + msg.msg_name = (void *)&cfg_dst_addr; + msg.msg_namelen = cfg_alen; + + ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != iov.iov_len) + error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len); + + return 1; +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]", + filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int max_len, hdrlen; + int c; + + while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) { + switch (c) { + case '4': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'c': + cfg_cache_trash = true; + break; + case 'C': + cfg_cpu = strtol(optarg, NULL, 0); + break; + case 'D': + setup_sockaddr(cfg_family, optarg, &cfg_dst_addr); + break; + case 'l': + cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; + break; + case 'm': + cfg_sendmmsg = true; + break; + case 'p': + cfg_port = strtoul(optarg, NULL, 0); + break; + case 's': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'S': + cfg_segment = true; + break; + case 't': + cfg_tcp = true; + break; + case 'u': + cfg_connected = false; + break; + case 'z': + cfg_zerocopy = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_family == PF_UNSPEC) + error(1, 0, "must pass one of -4 or -6"); + if (cfg_tcp && !cfg_connected) + error(1, 0, "connectionless tcp makes no sense"); + if (cfg_segment && cfg_sendmmsg) + error(1, 0, "cannot combine segment offload and sendmmsg"); + + if (cfg_family == PF_INET) + hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr); + else + hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr); + + cfg_mss = ETH_DATA_LEN - hdrlen; + max_len = ETH_MAX_MTU - hdrlen; + + if (cfg_payload_len > max_len) + error(1, 0, "payload length %u exceeds max %u", + cfg_payload_len, max_len); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +int main(int argc, char **argv) +{ + unsigned long num_msgs, num_sends; + unsigned long tnow, treport, tstop; + int fd, i, val; + + parse_opts(argc, argv); + + if (cfg_cpu > 0) + set_cpu(cfg_cpu); + + for (i = 0; i < sizeof(buf[0]); i++) + buf[0][i] = 'a' + (i % 26); + for (i = 1; i < NUM_PKT; i++) + memcpy(buf[i], buf[0], sizeof(buf[0])); + + signal(SIGINT, sigint_handler); + + fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + if (cfg_zerocopy) { + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) + error(1, errno, "setsockopt zerocopy"); + } + + if (cfg_connected && + connect(fd, (void *)&cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + + if (cfg_segment) + set_pmtu_discover(fd, cfg_family == PF_INET); + + num_msgs = num_sends = 0; + tnow = gettimeofday_ms(); + tstop = tnow + cfg_runtime_ms; + treport = tnow + 1000; + + i = 0; + do { + if (cfg_tcp) + num_sends += send_tcp(fd, buf[i]); + else if (cfg_segment) + num_sends += send_udp_segment(fd, buf[i]); + else if (cfg_sendmmsg) + num_sends += send_udp_sendmmsg(fd, buf[i]); + else + num_sends += send_udp(fd, buf[i]); + num_msgs++; + + if (cfg_zerocopy && ((num_msgs & 0xF) == 0)) + flush_zerocopy(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + fprintf(stderr, + "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n", + cfg_tcp ? "tcp" : "udp", + (num_msgs * cfg_payload_len) >> 20, + num_sends, num_msgs); + num_msgs = num_sends = 0; + treport = tnow + 1000; + } + + /* cold cache when writing buffer */ + if (cfg_cache_trash) + i = ++i < NUM_PKT ? i : 0; + + } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); + + if (close(fd)) + error(1, errno, "close"); + + return 0; +} diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index 93cf8fea8ae7..3a2f51fc7fd4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -398,13 +398,83 @@ 255 ] ], - "cmdUnderTest": "for i in `seq 1 32`; do cmd=\"action csum tcp continue index $i \"; args=\"$args$cmd\"; done && $TC actions add $args", - "expExitCode": "255", + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", "verifyCmd": "$TC actions ls action csum", "matchPattern": "^[ \t]+index [0-9]* ref", "matchCount": "32", "teardown": [ "$TC actions flush action csum" ] + }, + { + "id": "b4e9", + "name": "Delete batch of 32 csum actions", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0015", + "name": "Add batch of 32 csum tcp actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action csum", + "matchPattern": "^[ \t]+index [0-9]* ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action csum" + ] + }, + { + "id": "989e", + "name": "Delete batch of 32 csum actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index 9f34f0753969..de97e4ff705c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1,7 +1,7 @@ [ { - "id": "a568", - "name": "Add action with ife type", + "id": "7682", + "name": "Create valid ife encode action with mark and pass control", "category": [ "actions", "ife" @@ -12,21 +12,782 @@ 0, 1, 255 - ], - "$TC actions add action ife encode type 0xDEAD index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ef47", + "name": "Create valid ife encode action with mark and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 10 pipe index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "df43", + "name": "Create valid ife encode action with mark and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "e4cf", + "name": "Create valid ife encode action with mark and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 789 drop index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*use mark 789.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ccba", + "name": "Create valid ife encode action with mark and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 656768 reclassify index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 656768.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "a1cf", + "name": "Create valid ife encode action with mark and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 65 jump 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action jump 1.*type 0xED3E.*use mark 65.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "cb3d", + "name": "Create valid ife encode action with mark value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295 reclassify index 90", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 4294967295.*index 90", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "1efb", + "name": "Create ife encode action with mark value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295999 pipe index 90", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark 4294967295999.*index 90", + "matchCount": "0", + "teardown": [] + }, + { + "id": "95ed", + "name": "Create valid ife encode action with prio and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pass index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "aa17", + "name": "Create valid ife encode action with prio and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 7 pipe index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 7.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "74c7", + "name": "Create valid ife encode action with prio and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 3 continue index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use prio 3.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7a97", + "name": "Create valid ife encode action with prio and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio drop index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "f66b", + "name": "Create valid ife encode action with prio and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 reclassify index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "3056", + "name": "Create valid ife encode action with prio and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 jump 10 index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action jump 10.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7dd3", + "name": "Create valid ife encode action with prio value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967295 reclassify index 99", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 4294967295.*index 99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "2ca1", + "name": "Create ife encode action with prio value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967298 pipe index 99", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 4294967298.*index 99", + "matchCount": "0", + "teardown": [] + }, + { + "id": "05bb", + "name": "Create valid ife encode action with tcindex and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ce65", + "name": "Create valid ife encode action with tcindex and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 111 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 111.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "09cd", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8eb5", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "451a", + "name": "Create valid ife encode action with tcindex and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex drop index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d76c", + "name": "Create valid ife encode action with tcindex and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex reclassify index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "e731", + "name": "Create valid ife encode action with tcindex and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex jump 999 index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action jump 999.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b7b8", + "name": "Create valid ife encode action with tcindex value at 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65535 pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*use tcindex 65535.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d0d8", + "name": "Create ife encode action with tcindex value exceeding 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65539 pipe index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 65539.*index 1", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2a9c", + "name": "Create valid ife encode action with mac src parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark src 00:11:22:33:44:55 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow mark src 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "cf5c", + "name": "Create valid ife encode action with mac dst parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 9876 dst 00:11:22:33:44:55 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 9876 dst 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "2353", + "name": "Create valid ife encode action with mac src and mac dst parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex src 00:aa:bb:cc:dd:ee dst 00:11:22:33:44:55 pass index 11", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 11", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex dst 00:11:22:33:44:55 src 00:aa:bb:cc:dd:ee .*index 11", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "552c", + "name": "Create valid ife encode action with mark and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 7 type 0xfefe pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xFEFE.*use mark 7.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "0421", + "name": "Create valid ife encode action with prio and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 444 type 0xabba pipe index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xABBA.*use prio 444.*index 21", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "4017", + "name": "Create valid ife encode action with tcindex and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 5000 type 0xabcd reclassify index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xABCD.*use tcindex 5000.*index 21", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "fac3", + "name": "Create valid ife encode action with index at 32-bit maximnum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4294967295", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7c25", + "name": "Create valid ife decode action with pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode pass index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xDEAD", + "matchPattern": "action order [0-9]*: ife decode action pass.*type 0x0.*allow mark allow tcindex allow prio.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] }, { - "id": "b983", - "name": "Add action without ife type", + "id": "dccb", + "name": "Create valid ife decode action with pipe control", "category": [ "actions", "ife" @@ -37,16 +798,267 @@ 0, 1, 255 - ], - "$TC actions add action ife encode index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife decode pipe index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xED3E", + "matchPattern": "action order [0-9]*: ife decode action pipe.*type 0x0.*allow mark allow tcindex allow prio.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "7bb9", + "name": "Create valid ife decode action with continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action continue.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d9ad", + "name": "Create valid ife decode action with drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action drop.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "219f", + "name": "Create valid ife decode action with reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action reclassify.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8f44", + "name": "Create valid ife decode action with jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode jump 10 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action jump 10.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "56cf", + "name": "Create ife encode action with index exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295999", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4294967295999", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295999", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ee94", + "name": "Create ife encode action with invalid control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark kuka index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action kuka.*type 0xED3E.*allow mark.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "b330", + "name": "Create ife encode action with cookie", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pipe index 4 cookie aabbccddeeff112233445566778800a1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow prio.*index 4.*cookie aabbccddeeff112233445566778800a1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "bbc0", + "name": "Create ife encode action with invalid argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow foo pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow foo.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "d54a", + "name": "Create ife encode action with invalid type argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio type 70000 pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0x11170.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "7ee0", + "name": "Create ife encode action with invalid mac src argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio src 00:11:22:33:44:pp pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0a7d", + "name": "Create ife encode action with invalid mac dst argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio dst 00.111-22:33:44:aa pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index 443c9b3c8664..6e4edfae1799 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -340,7 +340,7 @@ }, { "id": "8b69", - "name": "Add mirred mirror action with maximum index", + "name": "Add mirred mirror action with index at 32-bit maximum", "category": [ "actions", "mirred" @@ -363,6 +363,28 @@ ] }, { + "id": "3f66", + "name": "Add mirred mirror action with index exceeding 32-bit maximum", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred ingress mirror dev lo pipe index 429496729555", + "expExitCode": "255", + "verifyCmd": "$TC actions get action mirred index 429496729555", + "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) pipe.*index 429496729555", + "matchCount": "0", + "teardown": [] + }, + { "id": "a70e", "name": "Delete mirred mirror action", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index 38d85a1d7492..f03763d81617 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -401,11 +401,11 @@ ], "cmdUnderTest": "$TC actions add action police rate 10mbit burst 10k index 4294967295", "expExitCode": "0", - "verifyCmd": "$TC actions get action mirred index 4294967295", + "verifyCmd": "$TC actions get action police index 4294967295", "matchPattern": "action order [0-9]*: police 0xffffffff rate 10Mbit burst 10Kb mtu 2Kb", "matchCount": "1", "teardown": [ - "$TC actions flush action mirred" + "$TC actions flush action police" ] }, { diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json new file mode 100644 index 000000000000..3aca33c00039 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -0,0 +1,588 @@ +[ + { + "id": "9784", + "name": "Add valid sample action with mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10 group 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/10 group 1.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "5c91", + "name": "Add valid sample action with mandatory arguments and continue control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 2 continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 2 continue.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "334b", + "name": "Add valid sample action with mandatory arguments and drop control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10000 group 11 drop index 22", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/10000 group 11 drop.*index 22 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "da69", + "name": "Add valid sample action with mandatory arguments and reclassify control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20000 group 72 reclassify index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20000 group 72 reclassify.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "13ce", + "name": "Add valid sample action with mandatory arguments and pipe control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20 group 2 pipe index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20 group 2 pipe.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "1886", + "name": "Add valid sample action with mandatory arguments and jump control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 25 jump 4 index 200", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 200", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 25 jump 4.*index 200 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "b6d4", + "name": "Add sample action with mandatory arguments and invalid control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 200000 group 52 foo index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/200000 group 52 foo.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "a874", + "name": "Add invalid sample action without mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ac01", + "name": "Add invalid sample action without mandatory argument rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample group 10 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*group 10.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "4203", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "14a7", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "8f2e", + "name": "Add valid sample action with trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 1024 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 1024 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "45f8", + "name": "Add sample action with maximum rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967295 group 4 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967295 group 4 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ad0c", + "name": "Add sample action with maximum trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 16000 group 4 trunc 4294967295 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/16000 group 4 trunc_size 4294967295 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "83a9", + "name": "Add sample action with maximum group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294 group 4294967295 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4294 group 4294967295 pipe.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ed27", + "name": "Add sample action with invalid rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967296 group 4 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967296 group 4 pipe.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2eae", + "name": "Add sample action with invalid group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4098 group 5294967299 continue index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4098 group 5294967299 continue.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "6ff3", + "name": "Add sample action with invalid trunc size", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 112233445566 index 11", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 11", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 112233445566.*index 11 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2b2a", + "name": "Add sample action with invalid index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 5294967299", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 5294967299", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 5294967299 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "dee2", + "name": "Add sample action with maximum allowed index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 4294967295", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "560e", + "name": "Add sample action with cookie", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 45 cookie aabbccdd", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 45", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 45.*cookie aabbccdd", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "704a", + "name": "Replace existing sample action with new rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 2048 group 4 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/2048 group 4 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "60eb", + "name": "Replace existing sample action with new group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "2cce", + "name": "Replace existing sample action with new trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 trunc 48 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 trunc 64 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 trunc_size 64 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "59d1", + "name": "Replace existing sample action with new control argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 reclassify index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 pipe index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index 4510ddfa6e54..69ea09eefffc 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -1,7 +1,7 @@ [ { "id": "6f5a", - "name": "Add vlan pop action", + "name": "Add vlan pop action with pipe opcode", "category": [ "actions", "vlan" @@ -14,18 +14,18 @@ 255 ] ], - "cmdUnderTest": "$TC actions add action vlan pop index 8", + "cmdUnderTest": "$TC actions add action vlan pop pipe index 8", "expExitCode": "0", "verifyCmd": "$TC actions list action vlan", - "matchPattern": "action order [0-9]+: vlan.*pop.*index 8 ref", + "matchPattern": "action order [0-9]+: vlan.*pop.*pipe.*index 8 ref", "matchCount": "1", "teardown": [ "$TC actions flush action vlan" ] }, { - "id": "ee6f", - "name": "Add vlan pop action with large index", + "id": "df35", + "name": "Add vlan pop action with pass opcode", "category": [ "actions", "vlan" @@ -38,10 +38,82 @@ 255 ] ], - "cmdUnderTest": "$TC actions add action vlan pop index 4294967295", + "cmdUnderTest": "$TC actions add action vlan pop pass index 8", "expExitCode": "0", - "verifyCmd": "$TC actions list action vlan", - "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*pass.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "b0d4", + "name": "Add vlan pop action with drop opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop drop index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*drop.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "95ee", + "name": "Add vlan pop action with reclassify opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop reclassify index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*reclassify.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "0283", + "name": "Add vlan pop action with continue opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop continue index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 8", + "matchPattern": "action order [0-9]+: vlan.*pop.*continue.*index 8 ref", "matchCount": "1", "teardown": [ "$TC actions flush action vlan" @@ -96,6 +168,74 @@ ] }, { + "id": "a178", + "name": "Add vlan pop action with invalid opcode", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop foo index 8", + "expExitCode": "255", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "action order [0-9]+: vlan.*pop.*foo.*index 8 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ee6f", + "name": "Add vlan pop action with index at 32-bit maximum", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "0dfa", + "name": "Add vlan pop action with index exceeding 32-bit maximum", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan pop reclassify index 429496729599", + "expExitCode": "255", + "verifyCmd": "$TC actions get action vlan index 429496729599", + "matchPattern": "action order [0-9]+: vlan.*pop.reclassify.*index 429496729599", + "matchCount": "0", + "teardown": [] + }, + { "id": "2b91", "name": "Add vlan invalid action", "category": [ @@ -115,13 +255,11 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*bad_mode", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "57fc", - "name": "Add vlan action with invalid protocol type", + "name": "Add vlan push action with invalid protocol type", "category": [ "actions", "vlan" @@ -139,9 +277,7 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*push", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "3989", @@ -216,6 +352,30 @@ ] }, { + "id": "1f4b", + "name": "Add vlan push action with maximum 12-bit vlan ID", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan push id 4094 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 4094.*protocol 802.1Q.*priority 0.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "1f7b", "name": "Add vlan push action with invalid vlan ID", "category": [ @@ -240,6 +400,30 @@ ] }, { + "id": "fe40", + "name": "Add vlan push action with maximum 3-bit IEEE 802.1p priority", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan push id 4 priority 7 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 4.*protocol 802.1Q.*priority 7.*reclassify.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "5d02", "name": "Add vlan push action with invalid IEEE 802.1p priority", "category": [ @@ -259,9 +443,7 @@ "verifyCmd": "$TC actions list action vlan", "matchPattern": "action order [0-9]+: vlan.*push id 5.*index 1 ref", "matchCount": "0", - "teardown": [ - "$TC actions flush action vlan" - ] + "teardown": [] }, { "id": "6812", @@ -312,6 +494,106 @@ ] }, { + "id": "3deb", + "name": "Replace existing vlan push action with new ID", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 500 pipe index 12" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 700 pipe index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 12", + "matchPattern": "action order [0-9]+: vlan.*push id 700 protocol 802.1Q priority 0 pipe.*index 12 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "9e76", + "name": "Replace existing vlan push action with new protocol", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 1 protocol 802.1Q pipe index 1" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 1 protocol 802.1ad pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1ad priority 0 pipe.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "ede4", + "name": "Replace existing vlan push action with new priority", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 1 protocol 802.1Q priority 3 reclassify index 1" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 1 priority 4 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1Q priority 4 reclassify.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "d413", + "name": "Replace existing vlan pop action with new cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan pop continue index 1 cookie 22334455" + ], + "cmdUnderTest": "$TC actions replace action vlan pop continue index 1 cookie a1b1c2d1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 1", + "matchPattern": "action order [0-9]+: vlan.*pop continue.*index 1 ref.*cookie a1b1c2d1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { "id": "83a4", "name": "Delete vlan pop action", "category": [ @@ -385,7 +667,7 @@ }, { "id": "1d78", - "name": "Add vlan action with cookie", + "name": "Add vlan push action with cookie", "category": [ "actions", "vlan" diff --git a/tools/testing/selftests/uevent/Makefile b/tools/testing/selftests/uevent/Makefile new file mode 100644 index 000000000000..f7baa9aa2932 --- /dev/null +++ b/tools/testing/selftests/uevent/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +all: + +include ../lib.mk + +.PHONY: all clean + +BINARIES := uevent_filtering +CFLAGS += -Wl,-no-as-needed -Wall + +uevent_filtering: uevent_filtering.c ../kselftest.h ../kselftest_harness.h + $(CC) $(CFLAGS) $< -o $@ + +TEST_PROGS += $(BINARIES) +EXTRA_CLEAN := $(BINARIES) + +all: $(BINARIES) diff --git a/tools/testing/selftests/uevent/config b/tools/testing/selftests/uevent/config new file mode 100644 index 000000000000..1038f4515be8 --- /dev/null +++ b/tools/testing/selftests/uevent/config @@ -0,0 +1,2 @@ +CONFIG_USER_NS=y +CONFIG_NET=y diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c new file mode 100644 index 000000000000..f83391aa42cf --- /dev/null +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -0,0 +1,486 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/netlink.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/prctl.h> +#include <sys/socket.h> +#include <sched.h> +#include <sys/eventfd.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../kselftest.h" +#include "../kselftest_harness.h" + +#define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" +#define __UEVENT_BUFFER_SIZE (2048 * 2) +#define __UEVENT_HEADER "add@/devices/virtual/mem/full" +#define __UEVENT_HEADER_LEN sizeof("add@/devices/virtual/mem/full") +#define __UEVENT_LISTEN_ALL -1 + +ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + +again: + ret = read(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (ret != pid) + goto again; + + if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) + return -1; + + return 0; +} + +static int uevent_listener(unsigned long post_flags, bool expect_uevent, + int sync_fd) +{ + int sk_fd, ret; + socklen_t sk_addr_len; + int fret = -1, rcv_buf_sz = __UEVENT_BUFFER_SIZE; + uint64_t sync_add = 1; + struct sockaddr_nl sk_addr = { 0 }, rcv_addr = { 0 }; + char buf[__UEVENT_BUFFER_SIZE] = { 0 }; + struct iovec iov = { buf, __UEVENT_BUFFER_SIZE }; + char control[CMSG_SPACE(sizeof(struct ucred))]; + struct msghdr hdr = { + &rcv_addr, sizeof(rcv_addr), &iov, 1, + control, sizeof(control), 0, + }; + + sk_fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, + NETLINK_KOBJECT_UEVENT); + if (sk_fd < 0) { + fprintf(stderr, "%s - Failed to open uevent socket\n", strerror(errno)); + return -1; + } + + ret = setsockopt(sk_fd, SOL_SOCKET, SO_RCVBUF, &rcv_buf_sz, + sizeof(rcv_buf_sz)); + if (ret < 0) { + fprintf(stderr, "%s - Failed to set socket options\n", strerror(errno)); + goto on_error; + } + + sk_addr.nl_family = AF_NETLINK; + sk_addr.nl_groups = __UEVENT_LISTEN_ALL; + + sk_addr_len = sizeof(sk_addr); + ret = bind(sk_fd, (struct sockaddr *)&sk_addr, sk_addr_len); + if (ret < 0) { + fprintf(stderr, "%s - Failed to bind socket\n", strerror(errno)); + goto on_error; + } + + ret = getsockname(sk_fd, (struct sockaddr *)&sk_addr, &sk_addr_len); + if (ret < 0) { + fprintf(stderr, "%s - Failed to retrieve socket name\n", strerror(errno)); + goto on_error; + } + + if ((size_t)sk_addr_len != sizeof(sk_addr)) { + fprintf(stderr, "Invalid socket address size\n"); + goto on_error; + } + + if (post_flags & CLONE_NEWUSER) { + ret = unshare(CLONE_NEWUSER); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare user namespace\n", + strerror(errno)); + goto on_error; + } + } + + if (post_flags & CLONE_NEWNET) { + ret = unshare(CLONE_NEWNET); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare network namespace\n", + strerror(errno)); + goto on_error; + } + } + + ret = write_nointr(sync_fd, &sync_add, sizeof(sync_add)); + close(sync_fd); + if (ret != sizeof(sync_add)) { + fprintf(stderr, "Failed to synchronize with parent process\n"); + goto on_error; + } + + fret = 0; + for (;;) { + ssize_t r; + + r = recvmsg(sk_fd, &hdr, 0); + if (r <= 0) { + fprintf(stderr, "%s - Failed to receive uevent\n", strerror(errno)); + ret = -1; + break; + } + + /* ignore libudev messages */ + if (memcmp(buf, "libudev", 8) == 0) + continue; + + /* ignore uevents we didn't trigger */ + if (memcmp(buf, __UEVENT_HEADER, __UEVENT_HEADER_LEN) != 0) + continue; + + if (!expect_uevent) { + fprintf(stderr, "Received unexpected uevent:\n"); + ret = -1; + } + + if (TH_LOG_ENABLED) { + /* If logging is enabled dump the received uevent. */ + (void)write_nointr(STDERR_FILENO, buf, r); + (void)write_nointr(STDERR_FILENO, "\n", 1); + } + + break; + } + +on_error: + close(sk_fd); + + return fret; +} + +int trigger_uevent(unsigned int times) +{ + int fd, ret; + unsigned int i; + + fd = open(__DEV_FULL, O_RDWR | O_CLOEXEC); + if (fd < 0) { + if (errno != ENOENT) + return -EINVAL; + + return -1; + } + + for (i = 0; i < times; i++) { + ret = write_nointr(fd, "add\n", sizeof("add\n") - 1); + if (ret < 0) { + fprintf(stderr, "Failed to trigger uevent\n"); + break; + } + } + close(fd); + + return ret; +} + +int set_death_signal(void) +{ + int ret; + pid_t ppid; + + ret = prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); + + /* Check whether we have been orphaned. */ + ppid = getppid(); + if (ppid == 1) { + pid_t self; + + self = getpid(); + ret = kill(self, SIGKILL); + } + + if (ret < 0) + return -1; + + return 0; +} + +static int do_test(unsigned long pre_flags, unsigned long post_flags, + bool expect_uevent, int sync_fd) +{ + int ret; + uint64_t wait_val; + pid_t pid; + sigset_t mask; + sigset_t orig_mask; + struct timespec timeout; + + sigemptyset(&mask); + sigaddset(&mask, SIGCHLD); + + ret = sigprocmask(SIG_BLOCK, &mask, &orig_mask); + if (ret < 0) { + fprintf(stderr, "%s- Failed to block SIGCHLD\n", strerror(errno)); + return -1; + } + + pid = fork(); + if (pid < 0) { + fprintf(stderr, "%s - Failed to fork() new process\n", strerror(errno)); + return -1; + } + + if (pid == 0) { + /* Make sure that we go away when our parent dies. */ + ret = set_death_signal(); + if (ret < 0) { + fprintf(stderr, "Failed to set PR_SET_PDEATHSIG to SIGKILL\n"); + _exit(EXIT_FAILURE); + } + + if (pre_flags & CLONE_NEWUSER) { + ret = unshare(CLONE_NEWUSER); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare user namespace\n", + strerror(errno)); + _exit(EXIT_FAILURE); + } + } + + if (pre_flags & CLONE_NEWNET) { + ret = unshare(CLONE_NEWNET); + if (ret < 0) { + fprintf(stderr, + "%s - Failed to unshare network namespace\n", + strerror(errno)); + _exit(EXIT_FAILURE); + } + } + + if (uevent_listener(post_flags, expect_uevent, sync_fd) < 0) + _exit(EXIT_FAILURE); + + _exit(EXIT_SUCCESS); + } + + ret = read_nointr(sync_fd, &wait_val, sizeof(wait_val)); + if (ret != sizeof(wait_val)) { + fprintf(stderr, "Failed to synchronize with child process\n"); + _exit(EXIT_FAILURE); + } + + /* Trigger 10 uevents to account for the case where the kernel might + * drop some. + */ + ret = trigger_uevent(10); + if (ret < 0) + fprintf(stderr, "Failed triggering uevents\n"); + + /* Wait for 2 seconds before considering this failed. This should be + * plenty of time for the kernel to deliver the uevent even under heavy + * load. + */ + timeout.tv_sec = 2; + timeout.tv_nsec = 0; + +again: + ret = sigtimedwait(&mask, NULL, &timeout); + if (ret < 0) { + if (errno == EINTR) + goto again; + + if (!expect_uevent) + ret = kill(pid, SIGTERM); /* success */ + else + ret = kill(pid, SIGUSR1); /* error */ + if (ret < 0) + return -1; + } + + ret = wait_for_pid(pid); + if (ret < 0) + return -1; + + return ret; +} + +static void signal_handler(int sig) +{ + if (sig == SIGTERM) + _exit(EXIT_SUCCESS); + + _exit(EXIT_FAILURE); +} + +TEST(uevent_filtering) +{ + int ret, sync_fd; + struct sigaction act; + + if (geteuid()) { + TH_LOG("Uevent filtering tests require root privileges. Skipping test"); + _exit(KSFT_SKIP); + } + + ret = access(__DEV_FULL, F_OK); + EXPECT_EQ(0, ret) { + if (errno == ENOENT) { + TH_LOG(__DEV_FULL " does not exist. Skipping test"); + _exit(KSFT_SKIP); + } + + _exit(KSFT_FAIL); + } + + act.sa_handler = signal_handler; + act.sa_flags = 0; + sigemptyset(&act.sa_mask); + + ret = sigaction(SIGTERM, &act, NULL); + ASSERT_EQ(0, ret); + + sync_fd = eventfd(0, EFD_CLOEXEC); + ASSERT_GE(sync_fd, 0); + + /* + * Setup: + * - Open uevent listening socket in initial network namespace owned by + * initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in non-initial network namespace + * owned by initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(CLONE_NEWNET, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - unshare user namespace + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(CLONE_NEWUSER, 0, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in non-initial network namespace + * owned by non-initial user namespace. + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives no uevent + */ + ret = do_test(CLONE_NEWUSER | CLONE_NEWNET, 0, false, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare network namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWNET, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare user namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWUSER, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + + /* + * Setup: + * - Open uevent listening socket in initial network namespace + * owned by initial user namespace. + * - unshare user namespace + * - unshare network namespace + * - Trigger uevent in initial network namespace owned by initial user + * namespace. + * Expected Result: + * - uevent listening socket receives uevent + */ + ret = do_test(0, CLONE_NEWUSER | CLONE_NEWNET, true, sync_fd); + ASSERT_EQ(0, ret) { + goto do_cleanup; + } + +do_cleanup: + close(sync_fd); +} + +TEST_HARNESS_MAIN |