diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-18 12:34:53 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-18 12:34:53 -0700 |
| commit | 81160dda9a7aad13c04e78bb2cfd3c4630e3afab (patch) | |
| tree | 4bf79ffa9fc7dc5e2915ff978778c3402c491113 /tools | |
| parent | 8b53c76533aa4356602aea98f98a2f3b4051464c (diff) | |
| parent | 1bab8d4c488be22d57f9dd09968c90a0ddc413bf (diff) | |
| download | linux-81160dda9a7aad13c04e78bb2cfd3c4630e3afab.tar.bz2 | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.
2) Use bio_vec in the networking instead of custom skb_frag_t, from
Matthew Wilcox.
3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.
4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.
5) Support all variants of 5750X bnxt_en chips, from Michael Chan.
6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
Buslov.
7) Add TCP syn cookies bpf helper, from Petar Penkov.
8) Add 'nettest' to selftests and use it, from David Ahern.
9) Add extack support to drop_monitor, add packet alert mode and
support for HW drops, from Ido Schimmel.
10) Add VLAN offload to stmmac, from Jose Abreu.
11) Lots of devm_platform_ioremap_resource() conversions, from
YueHaibing.
12) Add IONIC driver, from Shannon Nelson.
13) Several kTLS cleanups, from Jakub Kicinski.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
mlxsw: spectrum: Register CPU port with devlink
mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
net: ena: fix incorrect update of intr_delay_resolution
net: ena: fix retrieval of nonadaptive interrupt moderation intervals
net: ena: fix update of interrupt moderation register
net: ena: remove all old adaptive rx interrupt moderation code from ena_com
net: ena: remove ena_restore_ethtool_params() and relevant fields
net: ena: remove old adaptive interrupt moderation code from ena_netdev
net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
net: ena: enable the interrupt_moderation in driver_supported_features
net: ena: reimplement set/get_coalesce()
net: ena: switch to dim algorithm for rx adaptive interrupt moderation
net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
ethtool: implement Energy Detect Powerdown support via phy-tunable
xen-netfront: do not assume sk_buff_head list is empty in error handling
s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
net: ena: don't wake up tx queue when down
drop_monitor: Better sanitize notified packets
...
Diffstat (limited to 'tools')
170 files changed, 14169 insertions, 1451 deletions
diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore index dfe2bd5a4b95..59024197e71d 100644 --- a/tools/bpf/.gitignore +++ b/tools/bpf/.gitignore @@ -1,4 +1,5 @@ FEATURE-DUMP.bpf +feature bpf_asm bpf_dbg bpf_exp.yacc.* diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 53b60ad452f5..fbf5e4a0cb9c 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -81,10 +81,11 @@ $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c clean: bpftool_clean $(call QUIET_CLEAN, bpf-progs) - $(Q)rm -rf $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ + $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* $(call QUIET_CLEAN, core-gen) - $(Q)rm -f $(OUTPUT)FEATURE-DUMP.bpf + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf + $(Q)$(RM) -r -- $(OUTPUT)feature install: $(PROGS) bpftool_install $(call QUIET_INSTALL, bpf_jit_disasm) diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 8248b8dd89d4..b13926432b84 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -3,3 +3,5 @@ bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool +feature +libbpf diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index 6694a0fc8f99..39615f8e145b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -19,6 +19,7 @@ SYNOPSIS BTF COMMANDS ============= +| **bpftool** **btf** { **show** | **list** } [**id** *BTF_ID*] | **bpftool** **btf dump** *BTF_SRC* [**format** *FORMAT*] | **bpftool** **btf help** | @@ -29,6 +30,12 @@ BTF COMMANDS DESCRIPTION =========== + **bpftool btf { show | list }** [**id** *BTF_ID*] + Show information about loaded BTF objects. If a BTF ID is + specified, show information only about given BTF object, + otherwise list all BTF objects currently loaded on the + system. + **bpftool btf dump** *BTF_SRC* Dump BTF entries from a given *BTF_SRC*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 585f270c2d25..06a28b07787d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -20,8 +20,8 @@ SYNOPSIS CGROUP COMMANDS =============== -| **bpftool** **cgroup { show | list }** *CGROUP* -| **bpftool** **cgroup tree** [*CGROUP_ROOT*] +| **bpftool** **cgroup { show | list }** *CGROUP* [**effective**] +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* | **bpftool** **cgroup help** @@ -35,13 +35,17 @@ CGROUP COMMANDS DESCRIPTION =========== - **bpftool cgroup { show | list }** *CGROUP* + **bpftool cgroup { show | list }** *CGROUP* [**effective**] List all programs attached to the cgroup *CGROUP*. Output will start with program ID followed by attach type, attach flags and program name. - **bpftool cgroup tree** [*CGROUP_ROOT*] + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + + **bpftool cgroup tree** [*CGROUP_ROOT*] [**effective**] Iterate over all cgroups in *CGROUP_ROOT* and list all attached programs. If *CGROUP_ROOT* is not specified, bpftool uses cgroup v2 mountpoint. @@ -50,6 +54,10 @@ DESCRIPTION commands: it starts with absolute cgroup path, followed by program ID, attach type, attach flags and program name. + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* and optional *ATTACH_FLAGS*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 490b4501cb6e..1c0f7146aab0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -36,6 +36,7 @@ MAP COMMANDS | **bpftool** **map pop** *MAP* | **bpftool** **map enqueue** *MAP* **value** *VALUE* | **bpftool** **map dequeue** *MAP* +| **bpftool** **map freeze** *MAP* | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -46,7 +47,7 @@ MAP COMMANDS | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** | | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** -| | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** } @@ -127,6 +128,14 @@ DESCRIPTION **bpftool map dequeue** *MAP* Dequeue and print **value** from the queue. + **bpftool map freeze** *MAP* + Freeze the map as read-only from user space. Entries from a + frozen map can not longer be updated or deleted with the + **bpf\ ()** system call. This operation is not reversible, + and the map remains immutable from user space until its + destruction. However, read and write permissions for BPF + programs to the map remain unchanged. + **bpftool map help** Print short help message. diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index d8e5237a2085..8651b00b81ea 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -15,17 +15,22 @@ SYNOPSIS *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } *COMMANDS* := - { **show** | **list** } [ **dev** name ] | **help** + { **show** | **list** | **attach** | **detach** | **help** } NET COMMANDS ============ -| **bpftool** **net { show | list } [ dev name ]** +| **bpftool** **net { show | list }** [ **dev** *NAME* ] +| **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] +| **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* | **bpftool** **net help** +| +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *ATTACH_TYPE* := { **xdp** | **xdpgeneric** | **xdpdrv** | **xdpoffload** } DESCRIPTION =========== - **bpftool net { show | list } [ dev name ]** + **bpftool net { show | list }** [ **dev** *NAME* ] List bpf program attachments in the kernel networking subsystem. Currently, only device driver xdp attachments and tc filter @@ -47,6 +52,24 @@ DESCRIPTION all bpf programs attached to non clsact qdiscs, and finally all bpf programs attached to root and clsact qdisc. + **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] + Attach bpf program *PROG* to network interface *NAME* with + type specified by *ATTACH_TYPE*. Previously attached bpf program + can be replaced by the command used with **overwrite** option. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + + *ATTACH_TYPE* can be of: + **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; + **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; + **xdpdrv** - Native XDP. runs earliest point in driver's receive path; + **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; + + **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* + Detach bpf program attached to network interface *NAME* with + type specified by *ATTACH_TYPE*. To detach bpf program, same + *ATTACH_TYPE* previously used for attach must be specified. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + **bpftool net help** Print short help message. @@ -137,6 +160,34 @@ EXAMPLES } ] +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 16 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net attach xdpdrv id 20 dev enp6s0np0 overwrite** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 20 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net detach xdpdrv dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + SEE ALSO ======== diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index a7afea4dec47..39bc6f0f4f0b 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -17,27 +17,30 @@ endif BPF_DIR = $(srctree)/tools/lib/bpf/ ifneq ($(OUTPUT),) - BPF_PATH = $(OUTPUT) + LIBBPF_OUTPUT = $(OUTPUT)/libbpf/ + LIBBPF_PATH = $(LIBBPF_OUTPUT) else - BPF_PATH = $(BPF_DIR) + LIBBPF_PATH = $(BPF_DIR) endif -LIBBPF = $(BPF_PATH)libbpf.a +LIBBPF = $(LIBBPF_PATH)libbpf.a -BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion) +BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a + $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT)) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) clean >/dev/null prefix ?= /usr/local bash_compdir ?= /usr/share/bash-completion/completions CFLAGS += -O2 -CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers +CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers +CFLAGS += $(filter-out -Wswitch-enum,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ @@ -52,14 +55,14 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = -lelf $(LIBBPF) +LIBS = $(LIBBPF) -lelf -lz INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib +FEATURE_DISPLAY = libbfd disassembler-four-args zlib check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -111,17 +114,21 @@ OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< +$(OUTPUT)feature.o: | zdep + $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) $(OUTPUT)%.o: %.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< clean: $(LIBBPF)-clean $(call QUIET_CLEAN, bpftool) - $(Q)$(RM) $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -r -- $(OUTPUT)libbpf/ $(call QUIET_CLEAN, core-gen) - $(Q)$(RM) $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -r -- $(OUTPUT)feature/ install: $(OUTPUT)bpftool $(call QUIET_INSTALL, bpftool) @@ -132,8 +139,8 @@ install: $(OUTPUT)bpftool uninstall: $(call QUIET_UNINST, bpftool) - $(Q)$(RM) $(DESTDIR)$(prefix)/sbin/bpftool - $(Q)$(RM) $(DESTDIR)$(bash_compdir)/bpftool + $(Q)$(RM) -- $(DESTDIR)$(prefix)/sbin/bpftool + $(Q)$(RM) -- $(DESTDIR)$(bash_compdir)/bpftool doc: $(call descend,Documentation) @@ -149,6 +156,9 @@ doc-uninstall: FORCE: -.PHONY: all FORCE clean install uninstall +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + +.PHONY: all FORCE clean install uninstall zdep .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index c8f42e1fcbc9..70493a6da206 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -73,8 +73,8 @@ _bpftool_get_prog_tags() _bpftool_get_btf_ids() { - COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ - command sed -n 's/.*"btf_id": \(.*\),\?$/\1/p' )" -- "$cur" ) ) + COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } _bpftool_get_obj_map_names() @@ -201,6 +201,10 @@ _bpftool() _bpftool_get_prog_tags return 0 ;; + dev) + _sysfs_get_netdevs + return 0 + ;; file|pinned) _filedir return 0 @@ -399,10 +403,6 @@ _bpftool() _filedir return 0 ;; - dev) - _sysfs_get_netdevs - return 0 - ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) _bpftool_once_attr 'type' @@ -449,7 +449,7 @@ _bpftool() map) local MAP_TYPE='id pinned' case $command in - show|list|dump|peek|pop|dequeue) + show|list|dump|peek|pop|dequeue|freeze) case $prev in $command) COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) @@ -489,8 +489,8 @@ _bpftool() perf_event_array percpu_hash percpu_array \ stack_trace cgroup_array lru_hash \ lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap sockmap cpumap xskmap \ - sockhash cgroup_storage reuseport_sockarray \ + hash_of_maps devmap devmap_hash sockmap cpumap \ + xskmap sockhash cgroup_storage reuseport_sockarray \ percpu_cgroup_storage queue stack' -- \ "$cur" ) ) return 0 @@ -498,10 +498,6 @@ _bpftool() key|value|flags|name|entries) return 0 ;; - dev) - _sysfs_get_netdevs - return 0 - ;; *) _bpftool_once_attr 'type' _bpftool_once_attr 'key' @@ -642,7 +638,7 @@ _bpftool() [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ lookup pin event_pipe show list update create \ - peek push enqueue pop dequeue' -- \ + peek push enqueue pop dequeue freeze' -- \ "$cur" ) ) ;; esac @@ -674,7 +670,7 @@ _bpftool() map) _bpftool_get_map_ids ;; - dump) + $command) _bpftool_get_btf_ids ;; esac @@ -702,20 +698,35 @@ _bpftool() ;; esac ;; + show|list) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id" -- "$cur" ) ) + ;; + id) + _bpftool_get_btf_ids + ;; + esac + return 0 + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'dump help' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'dump help show list' \ + -- "$cur" ) ) ;; esac ;; cgroup) case $command in - show|list) - _filedir - return 0 - ;; - tree) - _filedir + show|list|tree) + case $cword in + 3) + _filedir + ;; + 4) + COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) ) + ;; + esac return 0 ;; attach|detach) @@ -775,18 +786,67 @@ _bpftool() esac ;; net) + local PROG_TYPE='id pinned tag' + local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + attach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 5) + case $prev in + id) + _bpftool_get_prog_ids + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + 8) + _bpftool_once_attr 'overwrite' + return 0 + ;; + esac + ;; + detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'help \ - show list' -- "$cur" ) ) + show list attach detach' -- "$cur" ) ) ;; esac ;; feature) case $command in probe) - [[ $prev == "dev" ]] && _sysfs_get_netdevs && return 0 [[ $prev == "prefix" ]] && return 0 if _bpftool_search_list 'macros'; then COMPREPLY+=( $( compgen -W 'prefix' -- "$cur" ) ) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 1b8ec91899e6..9a9376d1d3df 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -11,6 +11,7 @@ #include <bpf.h> #include <libbpf.h> #include <linux/btf.h> +#include <linux/hashtable.h> #include "btf.h" #include "json_writer.h" @@ -35,6 +36,16 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = "DATASEC", }; +struct btf_attach_table { + DECLARE_HASHTABLE(table, 16); +}; + +struct btf_attach_point { + __u32 obj_id; + __u32 btf_id; + struct hlist_node hash; +}; + static const char *btf_int_enc_str(__u8 encoding) { switch (encoding) { @@ -449,7 +460,7 @@ static int do_dump(int argc, char **argv) btf_id = strtoul(*argv, &endptr, 0); if (*endptr) { - p_err("can't parse %s as ID", **argv); + p_err("can't parse %s as ID", *argv); return -1; } NEXT_ARG(); @@ -522,6 +533,330 @@ done: return err; } +static int btf_parse_fd(int *argc, char ***argv) +{ + unsigned int id; + char *endptr; + int fd; + + if (!is_prefix(*argv[0], "id")) { + p_err("expected 'id', got: '%s'?", **argv); + return -1; + } + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + + return fd; +} + +static void delete_btf_table(struct btf_attach_table *tab) +{ + struct btf_attach_point *obj; + struct hlist_node *tmp; + + unsigned int bkt; + + hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { + hash_del(&obj->hash); + free(obj); + } +} + +static int +build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, + void *info, __u32 *len) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + }; + struct btf_attach_point *obj_node; + __u32 btf_id, id = 0; + int err; + int fd; + + while (true) { + switch (type) { + case BPF_OBJ_PROG: + err = bpf_prog_get_next_id(id, &id); + break; + case BPF_OBJ_MAP: + err = bpf_map_get_next_id(id, &id); + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next %s: %s%s", names[type], + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + fd = bpf_prog_get_fd_by_id(id); + break; + case BPF_OBJ_MAP: + fd = bpf_map_get_fd_by_id(id); + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get %s by id (%u): %s", names[type], id, + strerror(errno)); + err = -1; + goto err_free; + } + + memset(info, 0, *len); + err = bpf_obj_get_info_by_fd(fd, info, len); + close(fd); + if (err) { + p_err("can't get %s info: %s", names[type], + strerror(errno)); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + btf_id = ((struct bpf_prog_info *)info)->btf_id; + break; + case BPF_OBJ_MAP: + btf_id = ((struct bpf_map_info *)info)->btf_id; + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (!btf_id) + continue; + + obj_node = calloc(1, sizeof(*obj_node)); + if (!obj_node) { + p_err("failed to allocate memory: %s", strerror(errno)); + goto err_free; + } + + obj_node->obj_id = id; + obj_node->btf_id = btf_id; + hash_add(tab->table, &obj_node->hash, obj_node->btf_id); + } + + return 0; + +err_free: + delete_btf_table(tab); + return err; +} + +static int +build_btf_tables(struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct bpf_prog_info prog_info; + __u32 prog_len = sizeof(prog_info); + struct bpf_map_info map_info; + __u32 map_len = sizeof(map_info); + int err = 0; + + err = build_btf_type_table(btf_prog_table, BPF_OBJ_PROG, &prog_info, + &prog_len); + if (err) + return err; + + err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info, + &map_len); + if (err) { + delete_btf_table(btf_prog_table); + return err; + } + + return 0; +} + +static void +show_btf_plain(struct bpf_btf_info *info, int fd, + struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct btf_attach_point *obj; + int n; + + printf("%u: ", info->id); + printf("size %uB", info->btf_size); + + n = 0; + hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) { + if (obj->btf_id == info->id) + printf("%s%u", n++ == 0 ? " prog_ids " : ",", + obj->obj_id); + } + + n = 0; + hash_for_each_possible(btf_map_table->table, obj, hash, info->id) { + if (obj->btf_id == info->id) + printf("%s%u", n++ == 0 ? " map_ids " : ",", + obj->obj_id); + } + + printf("\n"); +} + +static void +show_btf_json(struct bpf_btf_info *info, int fd, + struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct btf_attach_point *obj; + + jsonw_start_object(json_wtr); /* btf object */ + jsonw_uint_field(json_wtr, "id", info->id); + jsonw_uint_field(json_wtr, "size", info->btf_size); + + jsonw_name(json_wtr, "prog_ids"); + jsonw_start_array(json_wtr); /* prog_ids */ + hash_for_each_possible(btf_prog_table->table, obj, hash, + info->id) { + if (obj->btf_id == info->id) + jsonw_uint(json_wtr, obj->obj_id); + } + jsonw_end_array(json_wtr); /* prog_ids */ + + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); /* map_ids */ + hash_for_each_possible(btf_map_table->table, obj, hash, + info->id) { + if (obj->btf_id == info->id) + jsonw_uint(json_wtr, obj->obj_id); + } + jsonw_end_array(json_wtr); /* map_ids */ + jsonw_end_object(json_wtr); /* btf object */ +} + +static int +show_btf(int fd, struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct bpf_btf_info info = {}; + __u32 len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get BTF object info: %s", strerror(errno)); + return -1; + } + + if (json_output) + show_btf_json(&info, fd, btf_prog_table, btf_map_table); + else + show_btf_plain(&info, fd, btf_prog_table, btf_map_table); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + struct btf_attach_table btf_prog_table; + struct btf_attach_table btf_map_table; + int err, fd = -1; + __u32 id = 0; + + if (argc == 2) { + fd = btf_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + } + + if (argc) { + if (fd >= 0) + close(fd); + return BAD_ARG(); + } + + hash_init(btf_prog_table.table); + hash_init(btf_map_table.table); + err = build_btf_tables(&btf_prog_table, &btf_map_table); + if (err) { + if (fd >= 0) + close(fd); + return err; + } + + if (fd >= 0) { + err = show_btf(fd, &btf_prog_table, &btf_map_table); + close(fd); + goto exit_free; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next BTF object: %s%s", + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + err = -1; + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + err = -1; + break; + } + + err = show_btf(fd, &btf_prog_table, &btf_map_table); + close(fd); + if (err) + break; + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + delete_btf_table(&btf_prog_table); + delete_btf_table(&btf_map_table); + + return err; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -530,7 +865,8 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s btf dump BTF_SRC [format FORMAT]\n" + "Usage: %s btf { show | list } [id BTF_ID]\n" + " %s btf dump BTF_SRC [format FORMAT]\n" " %s btf help\n" "\n" " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" @@ -539,12 +875,14 @@ static int do_help(int argc, char **argv) " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name, bin_name); + bin_name, bin_name, bin_name); return 0; } static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, { "help", do_help }, { "dump", do_dump }, { 0 } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 8cafb9b31467..d66131f69689 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -26,9 +26,9 @@ static void btf_dumper_ptr(const void *data, json_writer_t *jw, bool is_plain_text) { if (is_plain_text) - jsonw_printf(jw, "%p", *(unsigned long *)data); + jsonw_printf(jw, "%p", data); else - jsonw_printf(jw, "%u", *(unsigned long *)data); + jsonw_printf(jw, "%lu", *(unsigned long *)data); } static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, @@ -216,7 +216,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, switch (BTF_INT_ENCODING(*int_type)) { case 0: if (BTF_INT_BITS(*int_type) == 64) - jsonw_printf(jw, "%lu", *(__u64 *)data); + jsonw_printf(jw, "%llu", *(__u64 *)data); else if (BTF_INT_BITS(*int_type) == 32) jsonw_printf(jw, "%u", *(__u32 *)data); else if (BTF_INT_BITS(*int_type) == 16) @@ -229,7 +229,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, break; case BTF_INT_SIGNED: if (BTF_INT_BITS(*int_type) == 64) - jsonw_printf(jw, "%ld", *(long long *)data); + jsonw_printf(jw, "%lld", *(long long *)data); else if (BTF_INT_BITS(*int_type) == 32) jsonw_printf(jw, "%d", *(int *)data); else if (BTF_INT_BITS(*int_type) == 16) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index f3c05b08c68c..1ef45e55039e 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -29,6 +29,8 @@ " recvmsg4 | recvmsg6 | sysctl |\n" \ " getsockopt | setsockopt }" +static unsigned int query_flags; + static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", [BPF_CGROUP_INET_EGRESS] = "egress", @@ -107,7 +109,8 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) __u32 prog_cnt = 0; int ret; - ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL, + NULL, &prog_cnt); if (ret) return -1; @@ -117,16 +120,16 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { + const char *attach_flags_str; __u32 prog_ids[1024] = {0}; - char *attach_flags_str; __u32 prog_cnt, iter; __u32 attach_flags; char buf[32]; int ret; prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, 0, &attach_flags, prog_ids, - &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, + prog_ids, &prog_cnt); if (ret) return ret; @@ -158,20 +161,34 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + const char *path; int cgroup_fd; int ret = -1; - if (argc < 1) { - p_err("too few parameters for cgroup show"); - goto exit; - } else if (argc > 1) { - p_err("too many parameters for cgroup show"); - goto exit; + query_flags = 0; + + if (!REQ_ARGS(1)) + return -1; + path = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } } - cgroup_fd = open(argv[0], O_RDONLY); + cgroup_fd = open(path, O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[0]); + p_err("can't open cgroup %s", path); goto exit; } @@ -294,26 +311,37 @@ static char *find_cgroup_root(void) static int do_show_tree(int argc, char **argv) { - char *cgroup_root; + char *cgroup_root, *cgroup_alloced = NULL; int ret; - switch (argc) { - case 0: - cgroup_root = find_cgroup_root(); - if (!cgroup_root) { + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { p_err("cgroup v2 isn't mounted"); return -1; } - break; - case 1: - cgroup_root = argv[0]; - break; - default: - p_err("too many parameters for cgroup tree"); - return -1; + cgroup_root = cgroup_alloced; + } else { + cgroup_root = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } } - if (json_output) jsonw_start_array(json_wtr); else @@ -338,8 +366,7 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - if (argc == 0) - free(cgroup_root); + free(cgroup_alloced); return ret; } @@ -459,8 +486,8 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } CGROUP\n" - " %s %s tree [CGROUP_ROOT]\n" + "Usage: %s %s { show | list } CGROUP [**effective**]\n" + " %s %s tree [CGROUP_ROOT] [**effective**]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 6a71324be628..88264abaa738 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -29,7 +29,7 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif -void __printf(1, 2) p_err(const char *fmt, ...) +void p_err(const char *fmt, ...) { va_list ap; @@ -47,7 +47,7 @@ void __printf(1, 2) p_err(const char *fmt, ...) va_end(ap); } -void __printf(1, 2) p_info(const char *fmt, ...) +void p_info(const char *fmt, ...) { va_list ap; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index d672d9086fff..03bdc5b3ac49 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -14,6 +14,7 @@ #include <bpf.h> #include <libbpf.h> +#include <zlib.h> #include "main.h" @@ -284,34 +285,32 @@ static void probe_jit_limit(void) } } -static char *get_kernel_config_option(FILE *fd, const char *option) +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) { - size_t line_n = 0, optlen = strlen(option); - char *res, *strval, *line = NULL; - ssize_t n; + char *sep; - rewind(fd); - while ((n = getline(&line, &line_n, fd)) > 0) { - if (strncmp(line, option, optlen)) + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) continue; - /* Check we have at least '=', value, and '\n' */ - if (strlen(line) < optlen + 3) - continue; - if (*(line + optlen) != '=') + + sep = strchr(buf, '='); + if (!sep) continue; /* Trim ending '\n' */ - line[strlen(line) - 1] = '\0'; + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; - /* Copy and return config option value */ - strval = line + optlen + 1; - res = strdup(strval); - free(line); - return res; + *value = sep + 1; + return true; } - free(line); - return NULL; + return false; } static void probe_kernel_image_config(void) @@ -386,59 +385,61 @@ static void probe_kernel_image_config(void) /* test_bpf module for BPF tests */ "CONFIG_TEST_BPF", }; - char *value, *buf = NULL; + char *values[ARRAY_SIZE(options)] = { }; struct utsname utsn; char path[PATH_MAX]; - size_t i, n; - ssize_t ret; - FILE *fd; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; - if (uname(&utsn)) - goto no_config; + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); - snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } - fd = fopen(path, "r"); - if (!fd && errno == ENOENT) { - /* Some distributions put the config file at /proc/config, give - * it a try. - * Sometimes it is also at /proc/config.gz but we do not try - * this one for now, it would require linking against libz. + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. */ - fd = fopen("/proc/config", "r"); + file = gzopen("/proc/config.gz", "r"); } - if (!fd) { + if (!file) { p_info("skipping kernel config, can't open file: %s", strerror(errno)); - goto no_config; + goto end_parse; } /* Sanity checks */ - ret = getline(&buf, &n, fd); - ret = getline(&buf, &n, fd); - if (!buf || !ret) { + if (!gzgets(file, buf, sizeof(buf)) || + !gzgets(file, buf, sizeof(buf))) { p_info("skipping kernel config, can't read from file: %s", strerror(errno)); - free(buf); - goto no_config; + goto end_parse; } if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { p_info("skipping kernel config, can't find correct file"); - free(buf); - goto no_config; + goto end_parse; } - free(buf); - for (i = 0; i < ARRAY_SIZE(options); i++) { - value = get_kernel_config_option(fd, options[i]); - print_kernel_option(options[i], value); - free(value); + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (values[i] || strcmp(buf, options[i])) + continue; + + values[i] = strdup(value); + } } - fclose(fd); - return; -no_config: - for (i = 0; i < ARRAY_SIZE(options); i++) - print_kernel_option(options[i], NULL); +end_parse: + if (file) + gzclose(file); + + for (i = 0; i < ARRAY_SIZE(options); i++) { + print_kernel_option(options[i], values[i]); + free(values[i]); + } } static bool probe_bpf_syscall(const char *define_prefix) diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c index 6046dcab51cc..86501cd3c763 100644 --- a/tools/bpf/bpftool/json_writer.c +++ b/tools/bpf/bpftool/json_writer.c @@ -15,7 +15,6 @@ #include <malloc.h> #include <inttypes.h> #include <stdint.h> -#include <linux/compiler.h> #include "json_writer.h" @@ -153,8 +152,7 @@ void jsonw_name(json_writer_t *self, const char *name) putc(' ', self->out); } -void __printf(2, 0) -jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) { jsonw_eor(self); putc('"', self->out); @@ -162,7 +160,7 @@ jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) putc('"', self->out); } -void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...) +void jsonw_printf(json_writer_t *self, const char *fmt, ...) { va_list ap; diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h index cb9a1993681c..35cf1f00f96c 100644 --- a/tools/bpf/bpftool/json_writer.h +++ b/tools/bpf/bpftool/json_writer.h @@ -14,6 +14,7 @@ #include <stdbool.h> #include <stdint.h> #include <stdarg.h> +#include <linux/compiler.h> /* Opaque class structure */ typedef struct json_writer json_writer_t; @@ -30,8 +31,9 @@ void jsonw_pretty(json_writer_t *self, bool on); void jsonw_name(json_writer_t *self, const char *name); /* Add value */ -void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap); -void jsonw_printf(json_writer_t *self, const char *fmt, ...); +void __printf(2, 0) jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, + va_list ap); +void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...); void jsonw_string(json_writer_t *self, const char *value); void jsonw_bool(json_writer_t *self, bool value); void jsonw_float(json_writer_t *self, double number); diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index e916ff25697f..93d008687020 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -139,7 +139,7 @@ int detect_common_prefix(const char *arg, ...) strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); if (count >= 2) { - p_err(msg); + p_err("%s", msg); return -1; } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 7031a4bf87a0..af9ad56c303a 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -98,8 +98,8 @@ extern int bpf_flags; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; -void p_err(const char *fmt, ...); -void p_info(const char *fmt, ...); +void __printf(1, 2) p_err(const char *fmt, ...); +void __printf(1, 2) p_info(const char *fmt, ...); bool is_prefix(const char *pfx, const char *str); int detect_common_prefix(const char *arg, ...); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 5da5a7311f13..de61d73b9030 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -37,6 +37,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", [BPF_MAP_TYPE_XSKMAP] = "xskmap", @@ -480,9 +481,11 @@ static int parse_elem(char **argv, struct bpf_map_info *info, static int show_map_close_json(int fd, struct bpf_map_info *info) { - char *memlock; + char *memlock, *frozen_str; + int frozen = 0; memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); jsonw_start_object(json_wtr); @@ -532,6 +535,12 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) } close(fd); + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + jsonw_int_field(json_wtr, "frozen", frozen); + if (info->btf_id) jsonw_int_field(json_wtr, "btf_id", info->btf_id); @@ -554,9 +563,11 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) static int show_map_close_plain(int fd, struct bpf_map_info *info) { - char *memlock; + char *memlock, *frozen_str; + int frozen = 0; memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) @@ -609,9 +620,23 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("\n\tpinned %s", obj->path); } } + printf("\n"); + + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + + if (!info->btf_id && !frozen) + return 0; + + printf("\t"); if (info->btf_id) - printf("\n\tbtf_id %d", info->btf_id); + printf("btf_id %d", info->btf_id); + + if (frozen) + printf("%sfrozen", info->btf_id ? " " : ""); printf("\n"); return 0; @@ -1237,6 +1262,35 @@ exit_free: return err; } +static int do_freeze(int argc, char **argv) +{ + int err, fd; + + if (!REQ_ARGS(2)) + return -1; + + fd = map_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + if (argc) { + close(fd); + return BAD_ARG(); + } + + err = bpf_map_freeze(fd); + close(fd); + if (err) { + p_err("failed to freeze map: %s", strerror(errno)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1261,6 +1315,7 @@ static int do_help(int argc, char **argv) " %s %s pop MAP\n" " %s %s enqueue MAP value VALUE\n" " %s %s dequeue MAP\n" + " %s %s freeze MAP\n" " %s %s help\n" "\n" " " HELP_SPEC_MAP "\n" @@ -1271,7 +1326,7 @@ static int do_help(int argc, char **argv) " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" " percpu_array | stack_trace | cgroup_array | lru_hash |\n" " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" - " devmap | sockmap | cpumap | xskmap | sockhash |\n" + " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", @@ -1279,7 +1334,8 @@ static int do_help(int argc, char **argv) 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], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -1301,6 +1357,7 @@ static const struct cmd cmds[] = { { "enqueue", do_update }, { "pop", do_pop_dequeue }, { "dequeue", do_pop_dequeue }, + { "freeze", do_freeze }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 3f108ab17797..4c5531d1a450 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -157,7 +157,7 @@ int do_event_pipe(int argc, char **argv) NEXT_ARG(); ctx.cpu = strtoul(*argv, &endptr, 0); if (*endptr) { - p_err("can't parse %s as CPU ID", **argv); + p_err("can't parse %s as CPU ID", *argv); goto err_close_map; } @@ -168,7 +168,7 @@ int do_event_pipe(int argc, char **argv) NEXT_ARG(); ctx.idx = strtoul(*argv, &endptr, 0); if (*endptr) { - p_err("can't parse %s as index", **argv); + p_err("can't parse %s as index", *argv); goto err_close_map; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 67e99c56bc88..4f52d3151616 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -55,6 +55,35 @@ struct bpf_attach_info { __u32 flow_dissector_id; }; +enum net_attach_type { + NET_ATTACH_TYPE_XDP, + NET_ATTACH_TYPE_XDP_GENERIC, + NET_ATTACH_TYPE_XDP_DRIVER, + NET_ATTACH_TYPE_XDP_OFFLOAD, +}; + +static const char * const attach_type_strings[] = { + [NET_ATTACH_TYPE_XDP] = "xdp", + [NET_ATTACH_TYPE_XDP_GENERIC] = "xdpgeneric", + [NET_ATTACH_TYPE_XDP_DRIVER] = "xdpdrv", + [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", +}; + +const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); + +static enum net_attach_type parse_attach_type(const char *str) +{ + enum net_attach_type type; + + for (type = 0; type < net_attach_type_size; type++) { + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return net_attach_type_size; +} + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -197,7 +226,7 @@ static int query_flow_dissector(struct bpf_attach_info *attach_info) fd = open("/proc/self/ns/net", O_RDONLY); if (fd < 0) { - p_err("can't open /proc/self/ns/net: %d", + p_err("can't open /proc/self/ns/net: %s", strerror(errno)); return -1; } @@ -223,6 +252,134 @@ static int query_flow_dissector(struct bpf_attach_info *attach_info) return 0; } +static int net_parse_dev(int *argc, char ***argv) +{ + int ifindex; + + if (is_prefix(**argv, "dev")) { + NEXT_ARGP(); + + ifindex = if_nametoindex(**argv); + if (!ifindex) + p_err("invalid devname %s", **argv); + + NEXT_ARGP(); + } else { + p_err("expected 'dev', got: '%s'?", **argv); + return -1; + } + + return ifindex; +} + +static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, + int ifindex, bool overwrite) +{ + __u32 flags = 0; + + if (!overwrite) + flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (attach_type == NET_ATTACH_TYPE_XDP_GENERIC) + flags |= XDP_FLAGS_SKB_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_DRIVER) + flags |= XDP_FLAGS_DRV_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) + flags |= XDP_FLAGS_HW_MODE; + + return bpf_set_link_xdp_fd(ifindex, progfd, flags); +} + +static int do_attach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + bool overwrite = false; + + /* parse attach args */ + if (!REQ_ARGS(5)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + progfd = prog_parse_fd(&argc, &argv); + if (progfd < 0) + return -EINVAL; + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) { + close(progfd); + return -EINVAL; + } + + if (argc) { + if (is_prefix(*argv, "overwrite")) { + overwrite = true; + } else { + p_err("expected 'overwrite', got: '%s'?", *argv); + close(progfd); + return -EINVAL; + } + } + + /* attach xdp prog */ + if (is_prefix("xdp", attach_type_strings[attach_type])) + err = do_attach_detach_xdp(progfd, attach_type, ifindex, + overwrite); + + if (err < 0) { + p_err("interface %s attach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_detach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + + /* parse detach args */ + if (!REQ_ARGS(3)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) + return -EINVAL; + + /* detach xdp prog */ + progfd = -1; + if (is_prefix("xdp", attach_type_strings[attach_type])) + err = do_attach_detach_xdp(progfd, attach_type, ifindex, NULL); + + if (err < 0) { + p_err("interface %s detach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_show(int argc, char **argv) { struct bpf_attach_info attach_info = {}; @@ -232,13 +389,9 @@ static int do_show(int argc, char **argv) char err_buf[256]; if (argc == 2) { - if (strcmp(argv[0], "dev") != 0) - usage(); - filter_idx = if_nametoindex(argv[1]); - if (filter_idx == 0) { - fprintf(stderr, "invalid dev name %s\n", argv[1]); + filter_idx = net_parse_dev(&argc, &argv); + if (filter_idx < 1) return -1; - } } else if (argc != 0) { usage(); } @@ -305,13 +458,20 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [dev <devname>]\n" + " %s %s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n" + " %s %s detach ATTACH_TYPE dev <devname>\n" " %s %s help\n" + "\n" + " " HELP_SPEC_PROGRAM "\n" + " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" + "\n" "Note: Only xdp and tc attachments are supported now.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" " consult iproute2.\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]); return 0; } @@ -319,6 +479,8 @@ static int do_help(int argc, char **argv) static const struct cmd cmds[] = { { "show", do_show }, { "list", do_show }, + { "attach", do_attach }, + { "detach", do_detach }, { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index f2a545e667c4..b2046f33e23f 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -104,6 +104,8 @@ static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, jsonw_string_field(json_wtr, "filename", buf); jsonw_lluint_field(json_wtr, "offset", probe_offset); break; + default: + break; } jsonw_end_object(json_wtr); } @@ -140,6 +142,8 @@ static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, printf("uretprobe filename %s offset %llu\n", buf, probe_offset); break; + default: + break; } } diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 0d35f18006a1..95c072b70d0e 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -6,9 +6,11 @@ /* * Common definitions for all gcc versions go here. */ +#ifndef GCC_VERSION #define GCC_VERSION (__GNUC__ * 10000 \ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) +#endif #if GCC_VERSION >= 70000 && !defined(__CHECKER__) # define __fallthrough __attribute__ ((fallthrough)) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a5aa7d3ac6a1..77c6be96d676 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -106,6 +106,7 @@ enum bpf_cmd { BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, + BPF_BTF_GET_NEXT_ID, }; enum bpf_map_type { @@ -134,6 +135,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as @@ -283,6 +285,9 @@ enum bpf_attach_type { */ #define BPF_F_TEST_RND_HI32 (1U << 2) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_STATE_FREQ (1U << 3) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@ -336,6 +341,9 @@ enum bpf_attach_type { #define BPF_F_RDONLY_PROG (1U << 7) #define BPF_F_WRONLY_PROG (1U << 8) +/* Clone map from listener for newly accepted socket */ +#define BPF_F_CLONE (1U << 9) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -575,6 +583,8 @@ union bpf_attr { * limited to five). * * Each time the helper is called, it appends a line to the trace. + * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is + * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. * 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 @@ -1013,7 +1023,7 @@ union bpf_attr { * The realm of the route for the packet associated to *skb*, or 0 * if none was found. * - * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * int bpf_perf_event_output(struct pt_regs *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 @@ -1075,7 +1085,7 @@ union bpf_attr { * 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) + * int bpf_get_stackid(struct pt_regs *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 @@ -1724,7 +1734,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_override_return(struct pt_reg *regs, u64 rc) + * int bpf_override_return(struct pt_regs *regs, u64 rc) * Description * Used for error injection, this helper uses kprobes to override * the return value of the probed function, and to set it to *rc*. @@ -2713,6 +2723,33 @@ union bpf_attr { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2824,7 +2861,8 @@ union bpf_attr { FN(strtoul), \ FN(sk_storage_get), \ FN(sk_storage_delete), \ - FN(send_signal), + FN(send_signal), \ + FN(tcp_gen_syncookie), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3507,6 +3545,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3570,8 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; + __be32 flow_label; }; struct bpf_func_info { diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index faaa5ca2a117..be328c59389d 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -16,6 +16,18 @@ #define XDP_SHARED_UMEM (1 << 0) #define XDP_COPY (1 << 1) /* Force copy-mode */ #define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ +/* If this option is set, the driver might go sleep and in that case + * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be + * set. If it is set, the application need to explicitly wake up the + * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are + * running the driver and the application on the same core, you should + * use this option so that the kernel will yield to the user space + * application. + */ +#define XDP_USE_NEED_WAKEUP (1 << 3) + +/* Flags for xsk_umem_config flags */ +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) struct sockaddr_xdp { __u16 sxdp_family; @@ -25,10 +37,14 @@ struct sockaddr_xdp { __u32 sxdp_shared_umem_fd; }; +/* XDP_RING flags */ +#define XDP_RING_NEED_WAKEUP (1 << 0) + struct xdp_ring_offset { __u64 producer; __u64 consumer; __u64 desc; + __u64 flags; }; struct xdp_mmap_offsets { @@ -53,6 +69,7 @@ struct xdp_umem_reg { __u64 len; /* Length of packet data area */ __u32 chunk_size; __u32 headroom; + __u32 flags; }; struct xdp_statistics { @@ -74,6 +91,11 @@ struct xdp_options { #define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL #define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL +/* Masks for unaligned chunks mode */ +#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48 +#define XSK_UNALIGNED_BUF_ADDR_MASK \ + ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) + /* Rx/Tx descriptor */ struct xdp_desc { __u64 addr; diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 9312066a1ae3..c6f94cffe06e 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -1,9 +1,10 @@ # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) # Most of this file is copied from tools/lib/traceevent/Makefile -BPF_VERSION = 0 -BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 4 +LIBBPF_VERSION := $(shell \ + grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \ + sort -rV | head -n1 | cut -d'_' -f2) +LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory @@ -79,15 +80,9 @@ export prefix libdir src obj libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -VERSION = $(BPF_VERSION) -PATCHLEVEL = $(BPF_PATCHLEVEL) -EXTRAVERSION = $(BPF_EXTRAVERSION) - OBJ = $@ N = -LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) - LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) LIB_FILE = libbpf.a libbpf.so* PC_FILE = libbpf.pc @@ -113,6 +108,7 @@ override CFLAGS += -Werror -Wall override CFLAGS += -fPIC override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden +override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 ifeq ($(VERBOSE),1) Q = @@ -138,7 +134,9 @@ LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \ + sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) @@ -178,10 +176,10 @@ $(BPF_IN): force elfdep bpfdep $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) - $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \ + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so - @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION) + @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) $(OUTPUT)libbpf.a: $(BPF_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ @@ -205,6 +203,7 @@ check_abi: $(OUTPUT)libbpf.so "Please make sure all LIBBPF_API symbols are" \ "versioned in $(VERSION_SCRIPT)." >&2; \ readelf -s --wide $(OUTPUT)libbpf-in.o | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -257,7 +256,8 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS + *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ + *.pc LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index c7d7993c44bb..cbb933532981 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -568,7 +568,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) return ret; } -int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) { union bpf_attr attr; int err; @@ -576,26 +576,26 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) memset(&attr, 0, sizeof(attr)); attr.start_id = start_id; - err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr)); + err = sys_bpf(cmd, &attr, sizeof(attr)); if (!err) *next_id = attr.next_id; return err; } -int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) { - union bpf_attr attr; - int err; - - memset(&attr, 0, sizeof(attr)); - attr.start_id = start_id; + return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID); +} - err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr)); - if (!err) - *next_id = attr.next_id; +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID); +} - return err; +int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID); } int bpf_prog_get_fd_by_id(__u32 id) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index ff42ca043dc8..0db01334740f 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -156,6 +156,7 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 *retval, __u32 *duration); LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d821107f55f9..1aa189a9112a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -20,13 +20,6 @@ #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff -#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ - ((k) == BTF_KIND_VOLATILE) || \ - ((k) == BTF_KIND_CONST) || \ - ((k) == BTF_KIND_RESTRICT)) - -#define IS_VAR(k) ((k) == BTF_KIND_VAR) - static struct btf_type btf_void; struct btf { @@ -43,47 +36,6 @@ struct btf { int fd; }; -struct btf_ext_info { - /* - * info points to the individual info section (e.g. func_info and - * line_info) from the .BTF.ext. It does not include the __u32 rec_size. - */ - void *info; - __u32 rec_size; - __u32 len; -}; - -struct btf_ext { - union { - struct btf_ext_header *hdr; - void *data; - }; - struct btf_ext_info func_info; - struct btf_ext_info line_info; - __u32 data_size; -}; - -struct btf_ext_info_sec { - __u32 sec_name_off; - __u32 num_info; - /* Followed by num_info * record_size number of bytes */ - __u8 data[0]; -}; - -/* The minimum bpf_func_info checked by the loader */ -struct bpf_func_info_min { - __u32 insn_off; - __u32 type_id; -}; - -/* The minimum bpf_line_info checked by the loader */ -struct bpf_line_info_min { - __u32 insn_off; - __u32 file_name_off; - __u32 line_off; - __u32 line_col; -}; - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -193,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf) static int btf_type_size(struct btf_type *t) { int base_size = sizeof(struct btf_type); - __u16 vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = btf_vlen(t); - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_FWD: case BTF_KIND_CONST: case BTF_KIND_VOLATILE: @@ -220,7 +172,7 @@ static int btf_type_size(struct btf_type *t) case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); default: - pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; } } @@ -264,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 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; + return t == &btf_void || btf_is_fwd(t); } static bool btf_type_is_void_or_null(const struct btf_type *t) @@ -285,7 +237,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: @@ -304,7 +256,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) type_id = t->type; break; case BTF_KIND_ARRAY: - array = (const struct btf_array *)(t + 1); + array = btf_array(t); if (nelems && array->nelems > UINT32_MAX / nelems) return -E2BIG; nelems *= array->nelems; @@ -335,8 +287,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - (IS_MODIFIER(BTF_INFO_KIND(t->info)) || - IS_VAR(BTF_INFO_KIND(t->info)))) { + (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -555,11 +506,11 @@ static int compare_vsi_off(const void *_a, const void *_b) static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, struct btf_type *t) { - __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + __u32 size = 0, off = 0, i, vars = btf_vlen(t); const char *name = btf__name_by_offset(btf, t->name_off); const struct btf_type *t_var; struct btf_var_secinfo *vsi; - struct btf_var *var; + const struct btf_var *var; int ret; if (!name) { @@ -575,12 +526,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, t->size = size; - for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); - i < vars; i++, vsi++) { + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { t_var = btf__type_by_id(btf, vsi->type); - var = (struct btf_var *)(t_var + 1); + var = btf_var(t_var); - if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + if (!btf_is_var(t_var)) { pr_debug("Non-VAR type seen in section %s\n", name); return -EINVAL; } @@ -596,7 +546,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, ret = bpf_object__variable_offset(obj, name, &off); if (ret) { - pr_debug("No offset found in symbol table for VAR %s\n", name); + pr_debug("No offset found in symbol table for VAR %s\n", + name); return -ENOENT; } @@ -620,7 +571,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) * is section size and global variable offset. We use * the info from the ELF itself for this purpose. */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + if (btf_is_datasec(t)) { err = btf_fixup_datasec(obj, btf, t); if (err) break; @@ -775,14 +726,13 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, return -EINVAL; } - if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(container_type->info) < 2) { + if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { pr_warning("map:%s container_name:%s is an invalid container struct\n", map_name, container_name); return -EINVAL; } - key = (struct btf_member *)(container_type + 1); + key = btf_members(container_type); value = key + 1; key_size = btf__resolve_size(btf, key->type); @@ -832,6 +782,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* The start of the info sec (including the __u32 record_size). */ void *info; + if (ext_sec->len == 0) + return 0; + if (ext_sec->off & 0x03) { pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", ext_sec->desc); @@ -935,11 +888,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } +static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->offset_reloc_off, + .len = btf_ext->hdr->offset_reloc_len, + .min_rec_size = sizeof(struct bpf_offset_reloc), + .ext_info = &btf_ext->offset_reloc_info, + .desc = "offset_reloc", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) { const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - if (data_size < offsetof(struct btf_ext_header, func_info_off) || + if (data_size < offsetofend(struct btf_ext_header, hdr_len) || data_size < hdr->hdr_len) { pr_debug("BTF.ext header not found"); return -EINVAL; @@ -997,6 +963,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, line_info_len)) + goto done; err = btf_ext_setup_func_info(btf_ext); if (err) goto done; @@ -1005,6 +974,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, offset_reloc_len)) + goto done; + err = btf_ext_setup_offset_reloc(btf_ext); + if (err) + goto done; + done: if (err) { btf_ext__free(btf_ext); @@ -1441,10 +1417,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, d->map[0] = 0; for (i = 1; i <= btf->nr_types; i++) { struct btf_type *t = d->btf->types[i]; - __u16 kind = BTF_INFO_KIND(t->info); /* VAR and DATASEC are never deduped and are self-canonical */ - if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + if (btf_is_var(t) || btf_is_datasec(t)) d->map[i] = i; else d->map[i] = BTF_UNPROCESSED_ID; @@ -1485,11 +1460,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) if (r) return r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *m = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1500,8 +1475,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_ENUM: { - struct btf_enum *m = (struct btf_enum *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_enum *m = btf_enum(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1512,8 +1487,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *m = btf_params(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1802,16 +1777,16 @@ static long btf_hash_enum(struct btf_type *t) /* Check structural equality of two ENUMs. */ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) { - struct btf_enum *m1, *m2; + const struct btf_enum *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_enum *)(t1 + 1); - m2 = (struct btf_enum *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_enum(t1); + m2 = btf_enum(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->val != m2->val) return false; @@ -1823,8 +1798,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) static inline bool btf_is_enum_fwd(struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && - BTF_INFO_VLEN(t->info) == 0; + return btf_is_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -1844,8 +1818,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_struct(struct btf_type *t) { - struct btf_member *member = (struct btf_member *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1865,16 +1839,16 @@ static long btf_hash_struct(struct btf_type *t) */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) { - struct btf_member *m1, *m2; + const struct btf_member *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_member *)(t1 + 1); - m2 = (struct btf_member *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->offset != m2->offset) return false; @@ -1891,7 +1865,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_array(struct btf_type *t) { - struct btf_array *info = (struct btf_array *)(t + 1); + const struct btf_array *info = btf_array(t); long h = btf_hash_common(t); h = hash_combine(h, info->type); @@ -1909,13 +1883,13 @@ static long btf_hash_array(struct btf_type *t) */ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; + const struct btf_array *info1, *info2; if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); + info1 = btf_array(t1); + info2 = btf_array(t2); return info1->type == info2->type && info1->index_type == info2->index_type && info1->nelems == info2->nelems; @@ -1928,14 +1902,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; - if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); - return info1->nelems == info2->nelems; + return btf_array(t1)->nelems == btf_array(t2)->nelems; } /* @@ -1945,8 +1915,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_fnproto(struct btf_type *t) { - struct btf_param *member = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1967,16 +1937,16 @@ static long btf_hash_fnproto(struct btf_type *t) */ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->type != m2->type) return false; @@ -1993,7 +1963,7 @@ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; @@ -2001,9 +1971,9 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) if (t1->name_off != t2->name_off || t1->info != t2->info) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off) return false; @@ -2029,7 +1999,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) __u32 cand_id; long h; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2142,13 +2112,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) { __u32 orig_type_id = type_id; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) type_id = d->map[type_id]; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; return orig_type_id; @@ -2157,7 +2127,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) static inline __u16 btf_fwd_kind(struct btf_type *t) { - return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT; + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } /* @@ -2278,8 +2248,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, cand_type = d->btf->types[cand_id]; canon_type = d->btf->types[canon_id]; - cand_kind = BTF_INFO_KIND(cand_type->info); - canon_kind = BTF_INFO_KIND(canon_type->info); + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); if (cand_type->name_off != canon_type->name_off) return 0; @@ -2328,12 +2298,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { - struct btf_array *cand_arr, *canon_arr; + const struct btf_array *cand_arr, *canon_arr; if (!btf_compat_array(cand_type, canon_type)) return 0; - cand_arr = (struct btf_array *)(cand_type + 1); - canon_arr = (struct btf_array *)(canon_type + 1); + cand_arr = btf_array(cand_type); + canon_arr = btf_array(canon_type); eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type); if (eq <= 0) @@ -2343,14 +2313,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *cand_m, *canon_m; + const struct btf_member *cand_m, *canon_m; __u16 vlen; if (!btf_shallow_equal_struct(cand_type, canon_type)) return 0; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_m = (struct btf_member *)(cand_type + 1); - canon_m = (struct btf_member *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_m = btf_members(cand_type); + canon_m = btf_members(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); if (eq <= 0) @@ -2363,7 +2333,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, } case BTF_KIND_FUNC_PROTO: { - struct btf_param *cand_p, *canon_p; + const struct btf_param *cand_p, *canon_p; __u16 vlen; if (!btf_compat_fnproto(cand_type, canon_type)) @@ -2371,9 +2341,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); if (eq <= 0) return eq; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_p = (struct btf_param *)(cand_type + 1); - canon_p = (struct btf_param *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_p = btf_params(cand_type); + canon_p = btf_params(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); if (eq <= 0) @@ -2428,8 +2398,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) targ_type_id = d->hypot_map[cand_type_id]; t_id = resolve_type_id(d, targ_type_id); c_id = resolve_type_id(d, cand_type_id); - t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info); - c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info); + t_kind = btf_kind(d->btf->types[t_id]); + c_kind = btf_kind(d->btf->types[c_id]); /* * Resolve FWD into STRUCT/UNION. * It's ok to resolve FWD into STRUCT/UNION that's not yet @@ -2498,7 +2468,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) return 0; t = d->btf->types[type_id]; - kind = BTF_INFO_KIND(t->info); + kind = btf_kind(t); if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) return 0; @@ -2593,7 +2563,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) t = d->btf->types[type_id]; d->map[type_id] = BTF_IN_PROGRESS_ID; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2617,7 +2587,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *info = (struct btf_array *)(t + 1); + struct btf_array *info = btf_array(t); ref_type_id = btf_dedup_ref_type(d, info->type); if (ref_type_id < 0) @@ -2651,8 +2621,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) return ref_type_id; t->type = ref_type_id; - vlen = BTF_INFO_VLEN(t->info); - param = (struct btf_param *)(t + 1); + vlen = btf_vlen(t); + param = btf_params(t); for (i = 0; i < vlen; i++) { ref_type_id = btf_dedup_ref_type(d, param->type); if (ref_type_id < 0) @@ -2792,7 +2762,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) struct btf_type *t = d->btf->types[type_id]; int i, r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: break; @@ -2812,7 +2782,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *arr_info = (struct btf_array *)(t + 1); + struct btf_array *arr_info = btf_array(t); r = btf_dedup_remap_type_id(d, arr_info->type); if (r < 0) @@ -2827,8 +2797,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *member = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *member = btf_members(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, member->type); @@ -2841,8 +2811,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_FUNC_PROTO: { - struct btf_param *param = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *param = btf_params(t); + __u16 vlen = btf_vlen(t); r = btf_dedup_remap_type_id(d, t->type); if (r < 0) @@ -2860,8 +2830,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_DATASEC: { - struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_var_secinfo *var = btf_var_secinfos(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, var->type); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 88a52ae56fc6..9cb44b4fbf60 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -5,6 +5,7 @@ #define __LIBBPF_BTF_H #include <stdarg.h> +#include <linux/btf.h> #include <linux/types.h> #ifdef __cplusplus @@ -57,6 +58,10 @@ struct btf_ext_header { __u32 func_info_len; __u32 line_info_off; __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 offset_reloc_off; + __u32 offset_reloc_len; }; LIBBPF_API void btf__free(struct btf *btf); @@ -120,6 +125,183 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +/* + * A set of helpers for easier BTF types handling + */ +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline __u16 btf_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_struct(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_STRUCT; +} + +static inline bool btf_is_union(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNION; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +static inline bool btf_is_typedef(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_is_volatile(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VOLATILE; +} + +static inline bool btf_is_const(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_CONST; +} + +static inline bool btf_is_restrict(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_mod(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_VOLATILE || + kind == BTF_KIND_CONST || + kind == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_func(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC; +} + +static inline bool btf_is_func_proto(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC_PROTO; +} + +static inline bool btf_is_var(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VAR; +} + +static inline bool btf_is_datasec(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DATASEC; +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* Get bit offset of a member with specified index. */ +static inline __u32 btf_member_bit_offset(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; +} +/* + * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or + * BTF_KIND_UNION. If member is not a bitfield, zero is returned. + */ +static inline __u32 btf_member_bitfield_size(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; +} + +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + +static inline struct btf_var *btf_var(const struct btf_type *t) +{ + return (struct btf_var *)(t + 1); +} + +static inline struct btf_var_secinfo * +btf_var_secinfos(const struct btf_type *t) +{ + return (struct btf_var_secinfo *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 7065bb5b2752..715967762312 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -100,21 +100,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx) return strcmp(a, b) == 0; } -static __u16 btf_kind_of(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info); -} - -static __u16 btf_vlen_of(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_kflag_of(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) { return btf__name_by_offset(d->btf, name_off); @@ -349,7 +334,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) */ struct btf_dump_type_aux_state *tstate = &d->type_states[id]; const struct btf_type *t; - __u16 kind, vlen; + __u16 vlen; int err, i; /* return true, letting typedefs know that it's ok to be emitted */ @@ -357,18 +342,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); if (tstate->order_state == ORDERING) { /* type loop, but resolvable through fwd declaration */ - if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) && - through_ptr && t->name_off != 0) + if (btf_is_composite(t) && through_ptr && t->name_off != 0) return 0; pr_warning("unsatisfiable type cycle, id:[%u]\n", id); return -ELOOP; } - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_INT: tstate->order_state = ORDERED; return 0; @@ -378,14 +361,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERED; return err; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); - return btf_dump_order_type(d, a->type, through_ptr); - } case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); + const struct btf_member *m = btf_members(t); /* * struct/union is part of strong link, only if it's embedded * (so no ptr in a path) or it's anonymous (so has to be @@ -396,7 +377,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERING; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, m++) { err = btf_dump_order_type(d, m->type, false); if (err < 0) @@ -447,7 +428,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); + const struct btf_param *p = btf_params(t); bool is_strong; err = btf_dump_order_type(d, t->type, through_ptr); @@ -455,7 +436,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err; is_strong = err > 0; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, p++) { err = btf_dump_order_type(d, p->type, through_ptr); if (err < 0) @@ -553,7 +534,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) return; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); if (top_level_def && t->name_off == 0) { pr_warning("unexpected nameless definition, id:[%u]\n", id); @@ -618,12 +599,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_RESTRICT: btf_dump_emit_type(d, t->type, cont_id); break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - btf_dump_emit_type(d, a->type, cont_id); + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); break; - } case BTF_KIND_FWD: btf_dump_emit_fwd_def(d, id, t); btf_dump_printf(d, ";\n\n"); @@ -656,8 +634,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) * applicable */ if (top_level_def || t->name_off == 0) { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, new_cont_id; new_cont_id = t->name_off == 0 ? cont_id : id; @@ -678,8 +656,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } break; case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_type(d, t->type, cont_id); @@ -696,7 +674,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) static int btf_align_of(const struct btf *btf, __u32 id) { const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind_of(t); + __u16 kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -709,15 +687,12 @@ static int btf_align_of(const struct btf *btf, __u32 id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - return btf_align_of(btf, a->type); - } + case BTF_KIND_ARRAY: + return btf_align_of(btf, btf_array(t)->type); case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, align = 1; for (i = 0; i < vlen; i++, m++) @@ -726,7 +701,7 @@ static int btf_align_of(const struct btf *btf, __u32 id) return align; } default: - pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t)); + pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t)); return 1; } } @@ -737,20 +712,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_member *m; int align, i, bit_sz; __u16 vlen; - bool kflag; align = btf_align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ if (t->size % align) return true; - m = (void *)(t + 1); - kflag = btf_kflag_of(t); - vlen = btf_vlen_of(t); + m = btf_members(t); + vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { align = btf_align_of(btf, m->type); - bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; + bit_sz = btf_member_bitfield_size(t, i); if (bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -807,7 +780,7 @@ static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { btf_dump_printf(d, "%s %s", - btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union", + btf_is_struct(t) ? "struct" : "union", btf_dump_type_name(d, id)); } @@ -816,12 +789,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, const struct btf_type *t, int lvl) { - const struct btf_member *m = (void *)(t + 1); - bool kflag = btf_kflag_of(t), is_struct; + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); int align, i, packed, off = 0; - __u16 vlen = btf_vlen_of(t); + __u16 vlen = btf_vlen(t); - is_struct = btf_kind_of(t) == BTF_KIND_STRUCT; packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; align = packed ? 1 : btf_align_of(d->btf, id); @@ -835,8 +807,8 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, int m_off, m_sz; fname = btf_name_of(d, m->name_off); - m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; - m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; + m_sz = btf_member_bitfield_size(t, i); + m_off = btf_member_bit_offset(t, i); align = packed ? 1 : btf_align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); @@ -870,8 +842,8 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, const struct btf_type *t, int lvl) { - const struct btf_enum *v = (void *)(t+1); - __u16 vlen = btf_vlen_of(t); + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); const char *name; size_t dup_cnt; int i; @@ -905,7 +877,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, { const char *name = btf_dump_type_name(d, id); - if (btf_kflag_of(t)) + if (btf_kflag(t)) btf_dump_printf(d, "union %s", name); else btf_dump_printf(d, "struct %s", name); @@ -987,7 +959,6 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, struct id_stack decl_stack; const struct btf_type *t; int err, stack_start; - __u16 kind; stack_start = d->decl_stack_cnt; for (;;) { @@ -1008,8 +979,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, break; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_PTR: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -1017,12 +987,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_FUNC_PROTO: id = t->type; break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - id = a->type; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; break; - } case BTF_KIND_INT: case BTF_KIND_ENUM: case BTF_KIND_FWD: @@ -1032,7 +999,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, goto done; default: pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n", - kind, id); + btf_kind(t), id); goto done; } } @@ -1070,7 +1037,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) id = decl_stack->ids[decl_stack->cnt - 1]; t = btf__type_by_id(d->btf, id); - switch (btf_kind_of(t)) { + switch (btf_kind(t)) { case BTF_KIND_VOLATILE: btf_dump_printf(d, "volatile "); break; @@ -1087,20 +1054,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) } } -static bool btf_is_mod_kind(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - - switch (btf_kind_of(t)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return true; - default: - return false; - } -} - static void btf_dump_emit_name(const struct btf_dump *d, const char *name, bool last_was_ptr) { @@ -1139,7 +1092,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -1185,7 +1138,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_printf(d, " restrict"); break; case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + const struct btf_array *a = btf_array(t); const struct btf_type *next_t; __u32 next_id; bool multidim; @@ -1201,7 +1154,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, */ while (decls->cnt) { next_id = decls->ids[decls->cnt - 1]; - if (btf_is_mod_kind(d->btf, next_id)) + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) decls->cnt--; else break; @@ -1214,7 +1168,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } next_t = btf__type_by_id(d->btf, next_id); - multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY; + multidim = btf_is_array(next_t); /* we need space if we have named non-pointer */ if (fname[0] && !last_was_ptr) btf_dump_printf(d, " "); @@ -1228,8 +1182,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_mods(d, decls); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2b57d7ea7836..e0276520171b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -39,6 +39,7 @@ #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> +#include <sys/utsname.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> @@ -48,6 +49,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" +#include "hashmap.h" #ifndef EM_BPF #define EM_BPF 247 @@ -75,9 +77,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format, static libbpf_print_fn_t __libbpf_pr = __base_pr; -void libbpf_set_print(libbpf_print_fn_t fn) +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { + libbpf_print_fn_t old_print_fn = __libbpf_pr; + __libbpf_pr = fn; + return old_print_fn; } __printf(2, 3) @@ -1010,23 +1015,21 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } -static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, - __u32 id) +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) { const struct btf_type *t = btf__type_by_id(btf, id); - while (true) { - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - case BTF_KIND_TYPEDEF: - t = btf__type_by_id(btf, t->type); - break; - default: - return t; - } + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); } + + return t; } /* @@ -1039,14 +1042,14 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, static bool get_map_field_int(const char *map_name, const struct btf *btf, const struct btf_type *def, const struct btf_member *m, __u32 *res) { - const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); const char *name = btf__name_by_offset(btf, m->name_off); const struct btf_array *arr_info; const struct btf_type *arr_t; - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': attr '%s': expected PTR, got %u.\n", - map_name, name, BTF_INFO_KIND(t->info)); + map_name, name, btf_kind(t)); return false; } @@ -1056,12 +1059,12 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, map_name, name, t->type); return false; } - if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) { + if (!btf_is_array(arr_t)) { pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n", - map_name, name, BTF_INFO_KIND(arr_t->info)); + map_name, name, btf_kind(arr_t)); return false; } - arr_info = (const void *)(arr_t + 1); + arr_info = btf_array(arr_t); *res = arr_info->nelems; return true; } @@ -1079,11 +1082,11 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, struct bpf_map *map; int vlen, i; - vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + vi = btf_var_secinfos(sec) + var_idx; var = btf__type_by_id(obj->btf, vi->type); - var_extra = (const void *)(var + 1); + var_extra = btf_var(var); map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = BTF_INFO_VLEN(var->info); + vlen = btf_vlen(var); if (map_name == NULL || map_name[0] == '\0') { pr_warning("map #%d: empty name.\n", var_idx); @@ -1093,9 +1096,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_warning("map '%s' BTF data is corrupted.\n", map_name); return -EINVAL; } - if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + if (!btf_is_var(var)) { pr_warning("map '%s': unexpected var kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && @@ -1105,10 +1108,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return -EOPNOTSUPP; } - def = skip_mods_and_typedefs(obj->btf, var->type); - if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { pr_warning("map '%s': unexpected def kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (def->size > vi->size) { @@ -1131,8 +1134,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - vlen = BTF_INFO_VLEN(def->info); - m = (const void *)(def + 1); + vlen = btf_vlen(def); + m = btf_members(def); for (i = 0; i < vlen; i++, m++) { const char *name = btf__name_by_offset(obj->btf, m->name_off); @@ -1182,9 +1185,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': key spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1225,9 +1228,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': value spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1288,7 +1291,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) nr_types = btf__get_nr_types(obj->btf); for (i = 1; i <= nr_types; i++) { t = btf__type_by_id(obj->btf, i); - if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + if (!btf_is_datasec(t)) continue; name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { @@ -1302,7 +1305,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) return -ENOENT; } - vlen = BTF_INFO_VLEN(sec->info); + vlen = btf_vlen(sec); for (i = 0; i < vlen; i++) { err = bpf_object__init_user_btf_map(obj, sec, i, obj->efile.btf_maps_shndx, @@ -1363,16 +1366,14 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - __u16 kind; if (!obj->btf || (has_func && has_datasec)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - kind = BTF_INFO_KIND(t->info); - if (!has_datasec && kind == BTF_KIND_VAR) { + if (!has_datasec && btf_is_var(t)) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* @@ -1381,11 +1382,11 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) * original variable took less than 4 bytes */ t->size = 1; - *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); - } else if (!has_datasec && kind == BTF_KIND_DATASEC) { + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { /* replace DATASEC with STRUCT */ - struct btf_var_secinfo *v = (void *)(t + 1); - struct btf_member *m = (void *)(t + 1); + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); struct btf_type *vt; char *name; @@ -1396,7 +1397,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) name++; } - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); for (j = 0; j < vlen; j++, v++, m++) { /* order of field assignments is important */ @@ -1406,12 +1407,12 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) vt = (void *)btf__type_by_id(btf, v->type); m->name_off = vt->name_off; } - } else if (!has_func && kind == BTF_KIND_FUNC_PROTO) { + } else if (!has_func && btf_is_func_proto(t)) { /* replace FUNC_PROTO with ENUM */ - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); t->size = sizeof(__u32); /* kernel enforced */ - } else if (!has_func && kind == BTF_KIND_FUNC) { + } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); } @@ -1769,15 +1770,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, (long long) sym.st_value, sym.st_name, name); shdr_idx = sym.st_shndx; + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n", + insn_idx, shdr_idx); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n", + name, shdr_idx, insn_idx, + insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { pr_warning("incorrect bpf_call opcode\n"); @@ -2288,6 +2296,894 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, return 0; } +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field byte offset represented by spec */ + __u32 offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_offset_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field offset (in bytes), specified by accessor string. Low-level spec + * captures every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset = access_idx * sz; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + if (btf_member_bitfield_size(t, access_idx)) + return -EINVAL; + + offset = btf_member_bit_offset(t, access_idx); + if (offset % 8) + return -EINVAL; + spec->offset += offset / 8; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset += access_idx * sz; + } else { + pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating offset to the compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible; + * - any two PTRs are always compatible; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and bitness should match, signedness is ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_FWD: + case BTF_KIND_PTR: + return 1; + case BTF_KIND_ENUM: + return local_type->size == targ_type->size; + case BTF_KIND_INT: + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0 && + local_type->size == targ_type->size && + btf_int_bits(local_type) == btf_int_bits(targ_type); + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 offset; + + /* bitfield relocations not supported */ + if (btf_member_bitfield_size(targ_type, i)) + continue; + offset = btf_member_bit_offset(targ_type, i); + if (offset % 8) + continue; + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->offset += offset / 8; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->offset -= offset / 8; + spec->raw_len--; + } + + return 0; +} + +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->offset += local_acc->idx * sz; + } + } + + return 1; +} + +/* + * Patch relocatable BPF instruction. + * Expected insn->imm value is provided for validation, as well as the new + * relocated value. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + * 3. *(rX) = <imm> (indirect memory assignment with immediate operand). + * + * If actual insn->imm value is wrong, bail out. + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off, + __u32 orig_off, __u32 new_off) +{ + struct bpf_insn *insn; + int insn_idx; + __u8 class; + + if (insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = insn_off / sizeof(struct bpf_insn); + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (insn->imm != orig_off) + return -EINVAL; + insn->imm = new_off; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n", + bpf_program__title(prog, false), + insn_idx, orig_off, new_off); + } else { + pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warning("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u @ &x", spec->offset); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is not error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_offset_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_offset(struct bpf_program *prog, + const struct bpf_offset_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warning("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.offset != targ_spec.offset) { + /* if there are many candidates, they should all + * resolve to the same offset + */ + pr_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.offset, + targ_spec.offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + cand_ids->len = j; + if (cand_ids->len == 0) { + pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + err = bpf_core_reloc_insn(prog, relo->insn_off, + local_spec.offset, targ_spec.offset); + if (err) { + pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_offset_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warning("failed to get target BTF: %ld\n", + PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->offset_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warning("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_offset(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warning("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->offset_reloc_info.len) + err = bpf_core_reloc_offsets(obj, targ_btf_path); + + return err; +} + static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) @@ -2395,14 +3291,21 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; } - static int -bpf_object__relocate(struct bpf_object *obj) +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i; int err; + if (obj->btf_ext) { + err = bpf_object__relocate_core(obj, targ_btf_path); + if (err) { + pr_warning("failed to perform CO-RE relocations: %d\n", + err); + return err; + } + } for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; @@ -2808,7 +3711,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5cbf459ece0b..e8f70977d137 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -57,7 +57,7 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); -LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; @@ -92,6 +92,7 @@ LIBBPF_API void bpf_object__close(struct bpf_object *object); struct bpf_object_load_attr { struct bpf_object *obj; int log_level; + const char *target_btf_path; }; /* Load/unload object into/from kernel */ diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f9d316e873d8..d04c7cb623ed 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -183,4 +183,10 @@ LIBBPF_0.0.4 { perf_buffer__new; perf_buffer__new_raw; perf_buffer__poll; + xsk_umem__create; } LIBBPF_0.0.3; + +LIBBPF_0.0.5 { + global: + bpf_btf_get_next_id; +} LIBBPF_0.0.4; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2ac29bd36226..2e83a34f8c79 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -29,6 +29,10 @@ #ifndef max # define max(x, y) ((x) < (y) ? (y) : (x)) #endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) @@ -46,4 +50,105 @@ do { \ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +struct btf_ext_info { + /* + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. + */ + void *info; + __u32 rec_size; + __u32 len; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + for (sec = (seg)->info; \ + (void *)sec < (seg)->info + (seg)->len; \ + sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \ + (seg)->rec_size * sec->num_info) + +#define for_each_btf_ext_rec(seg, sec, i, rec) \ + for (i = 0, rec = (void *)&(sec)->data; \ + i < (sec)->num_info; \ + i++, rec = (void *)rec + (seg)->rec_size) + +struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; + struct btf_ext_info func_info; + struct btf_ext_info line_info; + struct btf_ext_info offset_reloc_info; + __u32 data_size; +}; + +struct btf_ext_info_sec { + __u32 sec_name_off; + __u32 num_info; + /* Followed by num_info * record_size number of bytes */ + __u8 data[0]; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_off; + __u32 type_id; +}; + +/* The minimum bpf_line_info checked by the loader */ +struct bpf_line_info_min { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +/* The minimum bpf_offset_reloc checked by the loader + * + * Offset relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual offset; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * offset; + * - access_str_off - offset into corresponding .BTF string section. String + * itself encodes an accessed field using a sequence of field and array + * indicies, separated by colon (:). It's conceptually very close to LLVM's + * getelementptr ([0]) instruction's arguments for identifying offset to + * a field. + * + * Example to provide a better feel. + * + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int x = &s->a; // encoded as "0:0" (a is field #0) + * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit offset relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_offset_reloc { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; +}; + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ace1a0708d99..4b0b0364f5fc 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -244,6 +244,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_XSKMAP: diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 680e63066cf3..842c4fd55859 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -74,23 +74,6 @@ struct xsk_nl_info { int fd; }; -/* For 32-bit systems, we need to use mmap2 as the offsets are 64-bit. - * Unfortunately, it is not part of glibc. - */ -static inline void *xsk_mmap(void *addr, size_t length, int prot, int flags, - int fd, __u64 offset) -{ -#ifdef __NR_mmap2 - unsigned int page_shift = __builtin_ffs(getpagesize()) - 1; - long ret = syscall(__NR_mmap2, addr, length, prot, flags, fd, - (off_t)(offset >> page_shift)); - - return (void *)ret; -#else - return mmap(addr, length, prot, flags, fd, offset); -#endif -} - int xsk_umem__fd(const struct xsk_umem *umem) { return umem ? umem->fd : -EINVAL; @@ -116,6 +99,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + cfg->flags = XSK_UMEM__DEFAULT_FLAGS; return; } @@ -123,6 +107,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->comp_size = usr_cfg->comp_size; cfg->frame_size = usr_cfg->frame_size; cfg->frame_headroom = usr_cfg->frame_headroom; + cfg->flags = usr_cfg->flags; } static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, @@ -149,9 +134,10 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, return 0; } -int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, - struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, - const struct xsk_umem_config *usr_config) +int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) { struct xdp_mmap_offsets off; struct xdp_umem_reg mr; @@ -182,6 +168,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, mr.len = size; mr.chunk_size = umem->config.frame_size; mr.headroom = umem->config.frame_headroom; + mr.flags = umem->config.flags; err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)); if (err) { @@ -210,10 +197,9 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, goto out_socket; } - map = xsk_mmap(NULL, off.fr.desc + - umem->config.fill_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - umem->fd, XDP_UMEM_PGOFF_FILL_RING); + map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_FILL_RING); if (map == MAP_FAILED) { err = -errno; goto out_socket; @@ -224,13 +210,13 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, fill->size = umem->config.fill_size; fill->producer = map + off.fr.producer; fill->consumer = map + off.fr.consumer; + fill->flags = map + off.fr.flags; fill->ring = map + off.fr.desc; fill->cached_cons = umem->config.fill_size; - map = xsk_mmap(NULL, - off.cr.desc + umem->config.comp_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - umem->fd, XDP_UMEM_PGOFF_COMPLETION_RING); + map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_COMPLETION_RING); if (map == MAP_FAILED) { err = -errno; goto out_mmap; @@ -241,6 +227,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, comp->size = umem->config.comp_size; comp->producer = map + off.cr.producer; comp->consumer = map + off.cr.consumer; + comp->flags = map + off.cr.flags; comp->ring = map + off.cr.desc; *umem_ptr = umem; @@ -255,6 +242,29 @@ out_umem_alloc: return err; } +struct xsk_umem_config_v1 { + __u32 fill_size; + __u32 comp_size; + __u32 frame_size; + __u32 frame_headroom; +}; + +int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) +{ + struct xsk_umem_config config; + + memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1)); + config.flags = 0; + + return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, + &config); +} +asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2"); +asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4"); + static int xsk_load_xdp_prog(struct xsk_socket *xsk) { static const int log_buf_size = 16 * 1024; @@ -550,11 +560,10 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } if (rx) { - rx_map = xsk_mmap(NULL, off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_RX_RING); + rx_map = mmap(NULL, off.rx.desc + + xsk->config.rx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_RX_RING); if (rx_map == MAP_FAILED) { err = -errno; goto out_socket; @@ -564,16 +573,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, rx->size = xsk->config.rx_size; rx->producer = rx_map + off.rx.producer; rx->consumer = rx_map + off.rx.consumer; + rx->flags = rx_map + off.rx.flags; rx->ring = rx_map + off.rx.desc; } xsk->rx = rx; if (tx) { - tx_map = xsk_mmap(NULL, off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_TX_RING); + tx_map = mmap(NULL, off.tx.desc + + xsk->config.tx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_TX_RING); if (tx_map == MAP_FAILED) { err = -errno; goto out_mmap_rx; @@ -583,6 +592,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, tx->size = xsk->config.tx_size; tx->producer = tx_map + off.tx.producer; tx->consumer = tx_map + off.tx.consumer; + tx->flags = tx_map + off.tx.flags; tx->ring = tx_map + off.tx.desc; tx->cached_cons = xsk->config.tx_size; } diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 833a6e60d065..584f6820a639 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -32,6 +32,7 @@ struct name { \ __u32 *producer; \ __u32 *consumer; \ void *ring; \ + __u32 *flags; \ } DEFINE_XSK_RING(xsk_ring_prod); @@ -76,6 +77,11 @@ xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx) return &descs[idx & rx->mask]; } +static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r) +{ + return *r->flags & XDP_RING_NEED_WAKEUP; +} + static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) { __u32 free_entries = r->cached_cons - r->cached_prod; @@ -162,6 +168,21 @@ static inline void *xsk_umem__get_data(void *umem_area, __u64 addr) return &((char *)umem_area)[addr]; } +static inline __u64 xsk_umem__extract_addr(__u64 addr) +{ + return addr & XSK_UNALIGNED_BUF_ADDR_MASK; +} + +static inline __u64 xsk_umem__extract_offset(__u64 addr) +{ + return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; +} + +static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) +{ + return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); +} + LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem); LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); @@ -170,12 +191,14 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); #define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */ #define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT) #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0 +#define XSK_UMEM__DEFAULT_FLAGS 0 struct xsk_umem_config { __u32 fill_size; __u32 comp_size; __u32 frame_size; __u32 frame_headroom; + __u32 flags; }; /* Flags for the libbpf_flags field. */ @@ -195,6 +218,16 @@ LIBBPF_API int xsk_umem__create(struct xsk_umem **umem, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk, const char *ifname, __u32 queue_id, struct xsk_umem *umem, diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 90f70d2c7c22..7470327edcfe 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -39,7 +39,3 @@ libbpf.so.* test_hashmap test_btf_dump xdping -test_sockopt -test_sockopt_sk -test_sockopt_multi -test_tcp_rtt diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 96752ebd938f..6889c19a628c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -17,6 +17,7 @@ LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy LLVM_READELF ?= llvm-readelf BTF_PAHOLE ?= pahole +BPF_GCC ?= $(shell command -v bpf-gcc;) CFLAGS += -g -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program @@ -28,8 +29,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage test_select_reuseport test_section_names \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk \ - test_sockopt_multi test_tcp_rtt + test_btf_dump test_cgroup_attach xdping BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) @@ -47,6 +47,10 @@ ifneq ($(SUBREG_CODEGEN),) TEST_GEN_FILES += $(patsubst %.o,alu32/%.o, $(BPF_OBJ_FILES)) endif +ifneq ($(BPF_GCC),) +TEST_GEN_FILES += $(patsubst %.o,bpf_gcc/%.o, $(BPF_OBJ_FILES)) +endif + # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ test_libbpf.sh \ @@ -66,7 +70,8 @@ TEST_PROGS := test_kmod.sh \ test_tcp_check_syncookie.sh \ test_tc_tunnel.sh \ test_tc_edt.sh \ - test_xdping.sh + test_xdping.sh \ + test_bpftool_build.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh \ @@ -105,17 +110,13 @@ $(OUTPUT)/test_socket_cookie: cgroup_helpers.c $(OUTPUT)/test_sockmap: cgroup_helpers.c $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c $(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c -$(OUTPUT)/test_progs: trace_helpers.c +$(OUTPUT)/test_progs: cgroup_helpers.c trace_helpers.c $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c $(OUTPUT)/test_sysctl: cgroup_helpers.c $(OUTPUT)/test_cgroup_attach: cgroup_helpers.c -$(OUTPUT)/test_sockopt: cgroup_helpers.c -$(OUTPUT)/test_sockopt_sk: cgroup_helpers.c -$(OUTPUT)/test_sockopt_multi: cgroup_helpers.c -$(OUTPUT)/test_tcp_rtt: cgroup_helpers.c .PHONY: force @@ -141,16 +142,19 @@ endif # # Use '-idirafter': Don't interfere with include mechanics except where the # build would have failed anyways. -CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ +define get_sys_includes +$(shell $(1) -v -E - </dev/null 2>&1 \ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') +endef +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) +BPF_CFLAGS = -I. -I./include/uapi -I../../../include/uapi \ + -I$(OUTPUT)/../usr/include -D__TARGET_ARCH_$(SRCARCH) -CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ - $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types \ - -D__TARGET_ARCH_$(SRCARCH) +CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ + -Wno-compare-distinct-pointer-types -$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline -$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline +$(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline +$(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline $(OUTPUT)/test_queue_map.o: test_queue_stack_map.h $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h @@ -167,12 +171,12 @@ BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ /bin/rm -f ./llvm_btf_verify.o) ifneq ($(BTF_LLVM_PROBE),) - CLANG_FLAGS += -g + BPF_CFLAGS += -g else ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) ifneq ($(BTF_OBJCOPY_PROBE),) - CLANG_FLAGS += -g + BPF_CFLAGS += -g LLC_FLAGS += -mattr=dwarfris DWARF2BTF = y endif @@ -198,7 +202,7 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ | $(ALU32_BUILD_DIR) $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \ -o $(ALU32_BUILD_DIR)/test_progs_32 \ - test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \ + test_progs.c test_stub.c cgroup_helpers.c trace_helpers.c prog_tests/*.c \ $(OUTPUT)/libbpf.a $(LDLIBS) $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H) @@ -206,8 +210,8 @@ $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c $(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \ | $(ALU32_BUILD_DIR) - ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ - echo "clang failed") | \ + ($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -target bpf -emit-llvm \ + -c $< -o - || echo "clang failed") | \ $(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \ -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) @@ -215,10 +219,37 @@ ifeq ($(DWARF2BTF),y) endif endif +ifneq ($(BPF_GCC),) +GCC_SYS_INCLUDES = $(call get_sys_includes,gcc) +IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ + grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__') +ifeq ($(IS_LITTLE_ENDIAN),) +MENDIAN=-mbig-endian +else +MENDIAN=-mlittle-endian +endif +BPF_GCC_CFLAGS = $(GCC_SYS_INCLUDES) $(MENDIAN) +BPF_GCC_BUILD_DIR = $(OUTPUT)/bpf_gcc +TEST_CUSTOM_PROGS += $(BPF_GCC_BUILD_DIR)/test_progs_bpf_gcc +$(BPF_GCC_BUILD_DIR): + mkdir -p $@ + +$(BPF_GCC_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(BPF_GCC_BUILD_DIR) + cp $< $@ + +$(BPF_GCC_BUILD_DIR)/test_progs_bpf_gcc: $(OUTPUT)/test_progs \ + | $(BPF_GCC_BUILD_DIR) + cp $< $@ + +$(BPF_GCC_BUILD_DIR)/%.o: progs/%.c $(BPF_GCC_BUILD_DIR)/test_progs_bpf_gcc \ + | $(BPF_GCC_BUILD_DIR) + $(BPF_GCC) $(BPF_CFLAGS) $(BPF_GCC_CFLAGS) -O2 -c $< -o $@ +endif + # Have one program compiled without "-target bpf" to test whether libbpf loads # it successfully $(OUTPUT)/test_xdp.o: progs/test_xdp.c - ($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \ + ($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -emit-llvm -c $< -o - || \ echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) @@ -226,8 +257,8 @@ ifeq ($(DWARF2BTF),y) endif $(OUTPUT)/%.o: progs/%.c - ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ - echo "clang failed") | \ + ($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -target bpf -emit-llvm \ + -c $< -o - || echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ @@ -240,18 +271,12 @@ PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) test_progs.c: $(PROG_TESTS_H) $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(PROG_TESTS_H) $(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ - echo '#ifdef DECLARE'; \ - ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \ - echo '#endif'; \ - echo '#ifdef CALL'; \ ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@test_\1();@'; \ - echo '#endif' \ + sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@'; \ ) > $(PROG_TESTS_H)) MAP_TESTS_DIR = $(OUTPUT)/map_tests @@ -261,7 +286,7 @@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h MAP_TESTS_FILES := $(wildcard map_tests/*.c) test_maps.c: $(MAP_TESTS_H) $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) -$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES) +$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_FILES) | $(MAP_TESTS_H) $(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR) $(shell ( cd map_tests/; \ echo '/* Generated header, do not edit */'; \ @@ -282,7 +307,7 @@ VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) -$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: test_verifier.c | $(VERIFIER_TEST_FILES) $(VERIFIER_TESTS_H) $(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ @@ -292,6 +317,6 @@ $(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) echo '#endif' \ ) > $(VERIFIER_TESTS_H)) -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \ +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) $(BPF_GCC_BUILD_DIR) \ $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) \ feature diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h index 05f036df8a4c..fbe28008450f 100644 --- a/tools/testing/selftests/bpf/bpf_endian.h +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ #ifndef __BPF_ENDIAN__ #define __BPF_ENDIAN__ @@ -29,6 +29,10 @@ # define __bpf_htonl(x) __builtin_bswap32(x) # define __bpf_constant_ntohl(x) ___constant_swab32(x) # define __bpf_constant_htonl(x) ___constant_swab32(x) +# define __bpf_be64_to_cpu(x) __builtin_bswap64(x) +# define __bpf_cpu_to_be64(x) __builtin_bswap64(x) +# define __bpf_constant_be64_to_cpu(x) ___constant_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___constant_swab64(x) #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ # define __bpf_ntohs(x) (x) # define __bpf_htons(x) (x) @@ -38,6 +42,10 @@ # define __bpf_htonl(x) (x) # define __bpf_constant_ntohl(x) (x) # define __bpf_constant_htonl(x) (x) +# define __bpf_be64_to_cpu(x) (x) +# define __bpf_cpu_to_be64(x) (x) +# define __bpf_constant_be64_to_cpu(x) (x) +# define __bpf_constant_cpu_to_be64(x) (x) #else # error "Fix your compiler's __BYTE_ORDER__?!" #endif @@ -54,5 +62,11 @@ #define bpf_ntohl(x) \ (__builtin_constant_p(x) ? \ __bpf_constant_ntohl(x) : __bpf_ntohl(x)) +#define bpf_cpu_to_be64(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x)) +#define bpf_be64_to_cpu(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x)) #endif /* __BPF_ENDIAN__ */ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f804f210244e..54a50699bbfd 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -1,12 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __BPF_HELPERS_H -#define __BPF_HELPERS_H - -/* helper macro to place programs, maps, license in - * different sections in elf_bpf file. Section names - * are interpreted by elf_bpf loader - */ -#define SEC(NAME) __attribute__((section(NAME), used)) +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_HELPERS__ +#define __BPF_HELPERS__ #define __uint(name, val) int (*name)[val] #define __type(name, val) val *name @@ -19,6 +13,14 @@ ##__VA_ARGS__); \ }) +#ifdef __clang__ + +/* helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by elf_bpf loader + */ +#define SEC(NAME) __attribute__((section(NAME), used)) + /* helper functions called from eBPF programs written in C */ static void *(*bpf_map_lookup_elem)(void *map, const void *key) = (void *) BPF_FUNC_map_lookup_elem; @@ -228,6 +230,9 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = (void *)BPF_FUNC_sk_storage_delete; static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal; +static long long (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *ip, + int ip_len, void *tcp, int tcp_len) = + (void *) BPF_FUNC_tcp_gen_syncookie; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -253,6 +258,12 @@ struct bpf_map_def { unsigned int numa_node; }; +#else + +#include <bpf-helpers.h> + +#endif + #define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ struct ____btf_map_##name { \ type_key key; \ @@ -501,4 +512,24 @@ struct pt_regs; (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif +/* + * BPF_CORE_READ abstracts away bpf_probe_read() call and captures offset + * relocation for source address using __builtin_preserve_access_index() + * built-in, provided by Clang. + * + * __builtin_preserve_access_index() takes as an argument an expression of + * taking an address of a field within struct/union. It makes compiler emit + * a relocation, which records BTF type ID describing root struct/union and an + * accessor string which describes exact embedded field that was used to take + * an address. See detailed description of this relocation format and + * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h. + * + * This relocation allows libbpf to adjust BPF instruction to use correct + * actual field offset, based on target kernel BTF type that matches original + * (local) BTF, used to record relocation. + */ +#define BPF_CORE_READ(dst, src) \ + bpf_probe_read((dst), sizeof(*(src)), \ + __builtin_preserve_access_index(src)) + #endif diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index cb827383db4d..f10029821e16 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -48,16 +48,17 @@ void test_bpf_obj_id(void) /* test_obj_id.o is a dumb prog. It should never fail * to load. */ - if (err) - error_cnt++; - assert(!err); + if (CHECK_FAIL(err)) + continue; /* Insert a magic value to the map */ map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); - assert(map_fds[i] >= 0); + if (CHECK_FAIL(map_fds[i] < 0)) + goto done; err = bpf_map_update_elem(map_fds[i], &array_key, &array_magic_value, 0); - assert(!err); + if (CHECK_FAIL(err)) + goto done; /* Check getting map info */ info_len = sizeof(struct bpf_map_info) * 2; @@ -96,9 +97,11 @@ void test_bpf_obj_id(void) prog_infos[i].map_ids = ptr_to_u64(map_ids + i); prog_infos[i].nr_map_ids = 2; err = clock_gettime(CLOCK_REALTIME, &real_time_ts); - assert(!err); + if (CHECK_FAIL(err)) + goto done; err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts); - assert(!err); + if (CHECK_FAIL(err)) + goto done; err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i], &info_len); load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) @@ -106,8 +109,8 @@ void test_bpf_obj_id(void) if (CHECK(err || prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || - (jit_enabled && !prog_infos[i].jited_prog_len) || - (jit_enabled && + (env.jit_enabled && !prog_infos[i].jited_prog_len) || + (env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))) || !prog_infos[i].xlated_prog_len || !memcmp(xlated_insns, zeros, sizeof(zeros)) || @@ -121,7 +124,7 @@ void test_bpf_obj_id(void) err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), - jit_enabled, + env.jit_enabled, prog_infos[i].jited_prog_len, prog_infos[i].xlated_prog_len, !!memcmp(jited_insns, zeros, sizeof(zeros)), @@ -224,7 +227,8 @@ void test_bpf_obj_id(void) nr_id_found++; err = bpf_map_lookup_elem(map_fd, &array_key, &array_value); - assert(!err); + if (CHECK_FAIL(err)) + goto done; err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); CHECK(err || info_len != sizeof(struct bpf_map_info) || diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index e1b55261526f..1c01ee2600a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -4,12 +4,15 @@ static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { - if (level != LIBBPF_DEBUG) - return vfprintf(stderr, format, args); + if (level != LIBBPF_DEBUG) { + vprintf(format, args); + return 0; + } if (!strstr(format, "verifier log")) return 0; - return vfprintf(stderr, "%s", args); + vprintf("%s", args); + return 0; } static int check_load(const char *file, enum bpf_prog_type type) @@ -25,19 +28,28 @@ static int check_load(const char *file, enum bpf_prog_type type) attr.prog_flags = BPF_F_TEST_RND_HI32; err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); bpf_object__close(obj); - if (err) - error_cnt++; return err; } +struct scale_test_def { + const char *file; + enum bpf_prog_type attach_type; + bool fails; +}; + void test_bpf_verif_scale(void) { - const char *sched_cls[] = { - "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o", - }; - const char *raw_tp[] = { + struct scale_test_def tests[] = { + { "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ }, + + { "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, + /* full unroll by llvm */ - "./pyperf50.o", "./pyperf100.o", "./pyperf180.o", + { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* partial unroll. llvm will unroll loop ~150 times. * C loop count -> 600. @@ -45,7 +57,7 @@ void test_bpf_verif_scale(void) * 16k insns in loop body. * Total of 5 such loops. Total program size ~82k insns. */ - "./pyperf600.o", + { "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll at all. * C loop count -> 600. @@ -53,48 +65,47 @@ void test_bpf_verif_scale(void) * ~110 insns in loop body. * Total of 5 such loops. Total program size ~1500 insns. */ - "./pyperf600_nounroll.o", + { "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - "./loop1.o", "./loop2.o", + { "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop4.o", BPF_PROG_TYPE_SCHED_CLS }, + { "loop5.o", BPF_PROG_TYPE_SCHED_CLS }, /* partial unroll. 19k insn in a loop. * Total program size 20.8k insn. * ~350k processed_insns */ - "./strobemeta.o", + { "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll, tiny loops */ - "./strobemeta_nounroll1.o", - "./strobemeta_nounroll2.o", - }; - const char *cg_sysctl[] = { - "./test_sysctl_loop1.o", "./test_sysctl_loop2.o", - }; - int err, i; + { "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - if (verifier_stats) - libbpf_set_print(libbpf_debug_print); + { "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, + { "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, - err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL"); + { "test_xdp_loop.o", BPF_PROG_TYPE_XDP }, + { "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL }, + }; + libbpf_print_fn_t old_print_fn = NULL; + int err, i; - for (i = 0; i < ARRAY_SIZE(sched_cls); i++) { - err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS); - printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK"); + if (env.verifier_stats) { + test__force_log(); + old_print_fn = libbpf_set_print(libbpf_debug_print); } - for (i = 0; i < ARRAY_SIZE(raw_tp); i++) { - err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK"); - } + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct scale_test_def *test = &tests[i]; + + if (!test__start_subtest(test->file)) + continue; - for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) { - err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL); - printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK"); + err = check_load(test->file, test->attach_type); + CHECK_FAIL(err && !test->fails); } - err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP); - printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK"); - err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL); - printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK"); + if (env.verifier_stats) + libbpf_set_print(old_print_fn); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c new file mode 100644 index 000000000000..f3863f976a48 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "progs/core_reloc_types.h" + +#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) + +#define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 42, \ + .b = 0xc001, \ + .c = 0xbeef, \ +} + +#define FLAVORS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_flavors.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define FLAVORS_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .input = FLAVORS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = FLAVORS_DATA(core_reloc_flavors), \ + .output_len = sizeof(struct core_reloc_flavors), \ +} + +#define FLAVORS_ERR_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define NESTING_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { .a = { .a = 42 } }, \ + .b = { .b = { .b = 0xc001 } }, \ +} + +#define NESTING_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_nesting.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define NESTING_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .input = NESTING_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = NESTING_DATA(core_reloc_nesting), \ + .output_len = sizeof(struct core_reloc_nesting) \ +} + +#define NESTING_ERR_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .fails = true, \ +} + +#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { [2] = 1 }, \ + .b = { [1] = { [2] = { [3] = 2 } } }, \ + .c = { [1] = { .c = 3 } }, \ + .d = { [0] = { [0] = { .d = 4 } } }, \ +} + +#define ARRAYS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_arrays.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define ARRAYS_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .input = ARRAYS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) { \ + .a2 = 1, \ + .b123 = 2, \ + .c1c = 3, \ + .d00d = 4, \ + }, \ + .output_len = sizeof(struct core_reloc_arrays_output) \ +} + +#define ARRAYS_ERR_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define PRIMITIVES_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 1, \ + .b = 2, \ + .c = 3, \ + .d = (void *)4, \ + .f = (void *)5, \ +} + +#define PRIMITIVES_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_primitives.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define PRIMITIVES_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .input = PRIMITIVES_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = PRIMITIVES_DATA(core_reloc_primitives), \ + .output_len = sizeof(struct core_reloc_primitives), \ +} + +#define PRIMITIVES_ERR_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .fails = true, \ +} + +#define MODS_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_mods.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = STRUCT_TO_CHAR_PTR(core_reloc_##name) { \ + .a = 1, \ + .b = 2, \ + .c = (void *)3, \ + .d = (void *)4, \ + .e = { [2] = 5 }, \ + .f = { [1] = 6 }, \ + .g = { .x = 7 }, \ + .h = { .y = 8 }, \ + }, \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_mods_output) { \ + .a = 1, .b = 2, .c = 3, .d = 4, \ + .e = 5, .f = 6, .g = 7, .h = 8, \ + }, \ + .output_len = sizeof(struct core_reloc_mods_output), \ +} + +#define PTR_AS_ARR_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ptr_as_arr.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = (const char *)&(struct core_reloc_##name []){ \ + { .a = 1 }, \ + { .a = 2 }, \ + { .a = 3 }, \ + }, \ + .input_len = 3 * sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_ptr_as_arr) { \ + .a = 3, \ + }, \ + .output_len = sizeof(struct core_reloc_ptr_as_arr), \ +} + +#define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .u8_field = 1, \ + .s8_field = 2, \ + .u16_field = 3, \ + .s16_field = 4, \ + .u32_field = 5, \ + .s32_field = 6, \ + .u64_field = 7, \ + .s64_field = 8, \ +} + +#define INTS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ints.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define INTS_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .input = INTS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = INTS_DATA(core_reloc_ints), \ + .output_len = sizeof(struct core_reloc_ints), \ +} + +#define INTS_ERR_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .fails = true, \ +} + +struct core_reloc_test_case { + const char *case_name; + const char *bpf_obj_file; + const char *btf_src_file; + const char *input; + int input_len; + const char *output; + int output_len; + bool fails; +}; + +static struct core_reloc_test_case test_cases[] = { + /* validate we can find kernel image and use its BTF for relocs */ + { + .case_name = "kernel", + .bpf_obj_file = "test_core_reloc_kernel.o", + .btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */ + .input = "", + .input_len = 0, + .output = "\1", /* true */ + .output_len = 1, + }, + + /* validate BPF program can use multiple flavors to match against + * single target BTF type + */ + FLAVORS_CASE(flavors), + + FLAVORS_ERR_CASE(flavors__err_wrong_name), + + /* various struct/enum nesting and resolution scenarios */ + NESTING_CASE(nesting), + NESTING_CASE(nesting___anon_embed), + NESTING_CASE(nesting___struct_union_mixup), + NESTING_CASE(nesting___extra_nesting), + NESTING_CASE(nesting___dup_compat_types), + + NESTING_ERR_CASE(nesting___err_missing_field), + NESTING_ERR_CASE(nesting___err_array_field), + NESTING_ERR_CASE(nesting___err_missing_container), + NESTING_ERR_CASE(nesting___err_nonstruct_container), + NESTING_ERR_CASE(nesting___err_array_container), + NESTING_ERR_CASE(nesting___err_dup_incompat_types), + NESTING_ERR_CASE(nesting___err_partial_match_dups), + NESTING_ERR_CASE(nesting___err_too_deep), + + /* various array access relocation scenarios */ + ARRAYS_CASE(arrays), + ARRAYS_CASE(arrays___diff_arr_dim), + ARRAYS_CASE(arrays___diff_arr_val_sz), + + ARRAYS_ERR_CASE(arrays___err_too_small), + ARRAYS_ERR_CASE(arrays___err_too_shallow), + ARRAYS_ERR_CASE(arrays___err_non_array), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + + /* enum/ptr/int handling scenarios */ + PRIMITIVES_CASE(primitives), + PRIMITIVES_CASE(primitives___diff_enum_def), + PRIMITIVES_CASE(primitives___diff_func_proto), + PRIMITIVES_CASE(primitives___diff_ptr_type), + + PRIMITIVES_ERR_CASE(primitives___err_non_enum), + PRIMITIVES_ERR_CASE(primitives___err_non_int), + PRIMITIVES_ERR_CASE(primitives___err_non_ptr), + + /* const/volatile/restrict and typedefs scenarios */ + MODS_CASE(mods), + MODS_CASE(mods___mod_swap), + MODS_CASE(mods___typedefs), + + /* handling "ptr is an array" semantics */ + PTR_AS_ARR_CASE(ptr_as_arr), + PTR_AS_ARR_CASE(ptr_as_arr___diff_sz), + + /* int signedness/sizing/bitfield handling */ + INTS_CASE(ints), + INTS_CASE(ints___bool), + INTS_CASE(ints___reverse_sign), + + INTS_ERR_CASE(ints___err_bitfield), + INTS_ERR_CASE(ints___err_wrong_sz_8), + INTS_ERR_CASE(ints___err_wrong_sz_16), + INTS_ERR_CASE(ints___err_wrong_sz_32), + INTS_ERR_CASE(ints___err_wrong_sz_64), + + /* validate edge cases of capturing relocations */ + { + .case_name = "misc", + .bpf_obj_file = "test_core_reloc_misc.o", + .btf_src_file = "btf__core_reloc_misc.o", + .input = (const char *)&(struct core_reloc_misc_extensible[]){ + { .a = 1 }, + { .a = 2 }, /* not read */ + { .a = 3 }, + }, + .input_len = 4 * sizeof(int), + .output = STRUCT_TO_CHAR_PTR(core_reloc_misc_output) { + .a = 1, + .b = 1, + .c = 0, /* BUG in clang, should be 3 */ + }, + .output_len = sizeof(struct core_reloc_misc_output), + }, +}; + +struct data { + char in[256]; + char out[256]; +}; + +void test_core_reloc(void) +{ + const char *probe_name = "raw_tracepoint/sys_enter"; + struct bpf_object_load_attr load_attr = {}; + struct core_reloc_test_case *test_case; + int err, duration = 0, i, equal; + struct bpf_link *link = NULL; + struct bpf_map *data_map; + struct bpf_program *prog; + struct bpf_object *obj; + const int zero = 0; + struct data data; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + test_case = &test_cases[i]; + + if (!test__start_subtest(test_case->case_name)) + continue; + + obj = bpf_object__open(test_case->bpf_obj_file); + if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", + "failed to open '%s': %ld\n", + test_case->bpf_obj_file, PTR_ERR(obj))) + continue; + + prog = bpf_object__find_program_by_title(obj, probe_name); + if (CHECK(!prog, "find_probe", + "prog '%s' not found\n", probe_name)) + goto cleanup; + bpf_program__set_type(prog, BPF_PROG_TYPE_RAW_TRACEPOINT); + + load_attr.obj = obj; + load_attr.log_level = 0; + load_attr.target_btf_path = test_case->btf_src_file; + err = bpf_object__load_xattr(&load_attr); + if (test_case->fails) { + CHECK(!err, "obj_load_fail", + "should fail to load prog '%s'\n", probe_name); + goto cleanup; + } else { + if (CHECK(err, "obj_load", + "failed to load prog '%s': %d\n", + probe_name, err)) + goto cleanup; + } + + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", + PTR_ERR(link))) + goto cleanup; + + data_map = bpf_object__find_map_by_name(obj, "test_cor.bss"); + if (CHECK(!data_map, "find_data_map", "data map not found\n")) + goto cleanup; + + memset(&data, 0, sizeof(data)); + memcpy(data.in, test_case->input, test_case->input_len); + + err = bpf_map_update_elem(bpf_map__fd(data_map), + &zero, &data, 0); + if (CHECK(err, "update_data_map", + "failed to update .data map: %d\n", err)) + goto cleanup; + + /* trigger test run */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data); + if (CHECK(err, "get_result", + "failed to get output data: %d\n", err)) + goto cleanup; + + equal = memcmp(data.out, test_case->output, + test_case->output_len) == 0; + if (CHECK(!equal, "check_result", + "input/output data don't match\n")) { + int j; + + for (j = 0; j < test_case->input_len; j++) { + printf("input byte #%d: 0x%02hhx\n", + j, test_case->input[j]); + } + for (j = 0; j < test_case->output_len; j++) { + printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n", + j, test_case->output[j], data.out[j]); + } + goto cleanup; + } + +cleanup: + if (!IS_ERR_OR_NULL(link)) { + bpf_link__destroy(link); + link = NULL; + } + bpf_object__close(obj); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index c938283ac232..92563898867c 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -5,6 +5,10 @@ #include <linux/if_tun.h> #include <sys/uio.h> +#ifndef IP_MF +#define IP_MF 0x2000 +#endif + #define CHECK_FLOW_KEYS(desc, got, expected) \ CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ @@ -16,6 +20,7 @@ "is_encap=%u/%u " \ "ip_proto=0x%x/0x%x " \ "n_proto=0x%x/0x%x " \ + "flow_label=0x%x/0x%x " \ "sport=%u/%u " \ "dport=%u/%u\n", \ got.nhoff, expected.nhoff, \ @@ -26,6 +31,7 @@ got.is_encap, expected.is_encap, \ got.ip_proto, expected.ip_proto, \ got.n_proto, expected.n_proto, \ + got.flow_label, expected.flow_label, \ got.sport, expected.sport, \ got.dport, expected.dport) @@ -35,6 +41,13 @@ struct ipv4_pkt { struct tcphdr tcp; } __packed; +struct ipip_pkt { + struct ethhdr eth; + struct iphdr iph; + struct iphdr iph_inner; + struct tcphdr tcp; +} __packed; + struct svlan_ipv4_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -49,6 +62,18 @@ struct ipv6_pkt { struct tcphdr tcp; } __packed; +struct ipv6_frag_pkt { + struct ethhdr eth; + struct ipv6hdr iph; + struct frag_hdr { + __u8 nexthdr; + __u8 reserved; + __be16 frag_off; + __be32 identification; + } ipf; + struct tcphdr tcp; +} __packed; + struct dvlan_ipv6_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -64,10 +89,13 @@ struct test { union { struct ipv4_pkt ipv4; struct svlan_ipv4_pkt svlan_ipv4; + struct ipip_pkt ipip; struct ipv6_pkt ipv6; + struct ipv6_frag_pkt ipv6_frag; struct dvlan_ipv6_pkt dvlan_ipv6; } pkt; struct bpf_flow_keys keys; + __u32 flags; }; #define VLAN_HLEN 4 @@ -81,6 +109,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -88,6 +118,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -97,6 +129,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -104,6 +138,8 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, }, }, { @@ -115,6 +151,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN, @@ -122,6 +160,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -133,6 +173,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN * 2, @@ -141,8 +183,205 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, + }, + }, + { + .name = "ipv4-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv4-no-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv6-no-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, + .flow_label = __bpf_constant_htonl(0xbeeef), }, }, + { + .name = "ipv6-no-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .flow_label = __bpf_constant_htonl(0xbeeef), + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + }, + { + .name = "ipip-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) + + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + .sport = 80, + .dport = 8080, + }, + }, + { + .name = "ipip-no-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_IPIP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + }, }; static int create_tap(const char *ifname) @@ -212,10 +451,8 @@ void test_flow_dissector(void) err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector", "jmp_table", "last_dissection", &prog_fd, &keys_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_flow_keys flow_keys; @@ -225,6 +462,13 @@ void test_flow_dissector(void) .data_size_in = sizeof(tests[i].pkt), .data_out = &flow_keys, }; + static struct bpf_flow_keys ctx = {}; + + if (tests[i].flags) { + tattr.ctx_in = &ctx; + tattr.ctx_size_in = sizeof(ctx); + ctx.flags = tests[i].flags; + } err = bpf_prog_test_run_xattr(&tattr); CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || @@ -251,9 +495,20 @@ void test_flow_dissector(void) CHECK(err, "ifup", "err %d errno %d\n", err, errno); for (i = 0; i < ARRAY_SIZE(tests); i++) { - struct bpf_flow_keys flow_keys = {}; + /* Keep in sync with 'flags' from eth_get_headlen. */ + __u32 eth_get_headlen_flags = + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; struct bpf_prog_test_run_attr tattr = {}; - __u32 key = 0; + struct bpf_flow_keys flow_keys = {}; + __u32 key = (__u32)(tests[i].keys.sport) << 16 | + tests[i].keys.dport; + + /* For skb-less case we can't pass input flags; run + * only the tests that have a matching set of flags. + */ + + if (tests[i].flags != eth_get_headlen_flags) + continue; err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); @@ -263,6 +518,9 @@ void test_flow_dissector(void) CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + + err = bpf_map_delete_elem(keys_fd, &key); + CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); } bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index c2a0a9d5591b..eba9a970703b 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -1,8 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <pthread.h> +#include <sched.h> +#include <sys/socket.h> #include <test_progs.h> #define MAX_CNT_RAWTP 10ull #define MAX_STACK_RAWTP 100 + +static int duration = 0; + struct get_stack_trace_t { int pid; int kern_stack_size; @@ -13,7 +20,7 @@ struct get_stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -static int get_stack_print_output(void *data, int size) +static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) { bool good_kern_stack = false, good_user_stack = false; const char *nonjit_func = "___bpf_prog_run"; @@ -34,7 +41,7 @@ static int get_stack_print_output(void *data, int size) * just assume it is good if the stack is not empty. * This could be improved in the future. */ - if (jit_enabled) { + if (env.jit_enabled) { found = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -51,7 +58,7 @@ static int get_stack_print_output(void *data, int size) } } else { num_stack = e->kern_stack_size / sizeof(__u64); - if (jit_enabled) { + if (env.jit_enabled) { good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -65,75 +72,73 @@ static int get_stack_print_output(void *data, int size) 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; + if (!good_kern_stack) + CHECK(!good_kern_stack, "kern_stack", "corrupted kernel stack\n"); + if (!good_user_stack) + CHECK(!good_user_stack, "user_stack", "corrupted user stack\n"); } 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 = {}; + const char *prog_name = "raw_tracepoint/sys_enter"; + int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP; + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb = NULL; + struct bpf_link *link = NULL; struct timespec tv = {0, 10}; - __u32 key = 0, duration = 0; + struct bpf_program *prog; struct bpf_object *obj; + struct bpf_map *map; + cpu_set_t cpu_set; 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)) + prog = bpf_object__find_program_by_title(obj, prog_name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) 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)) + map = bpf_object__find_map_by_name(obj, "perfmap"); + if (CHECK(!map, "bpf_find_map", "not found\n")) 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)) + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno)) goto 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)) + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) 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)) + pb_opts.sample_cb = get_stack_print_output; + pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts); + if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) 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; + while (exp_cnt > 0) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && CHECK(err < 0, "pb__poll", "err %d\n", err)) + goto close_prog; + exp_cnt -= err; + } - goto close_prog_noerr; close_prog: - error_cnt++; -close_prog_noerr: + if (!IS_ERR_OR_NULL(link)) + bpf_link__destroy(link); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index d011079fb0bf..c680926fce73 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -7,10 +7,8 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) uint64_t num; map_fd = bpf_find_map(__func__, obj, "result_number"); - if (map_fd < 0) { - error_cnt++; + if (CHECK_FAIL(map_fd < 0)) return; - } struct { char *name; @@ -44,10 +42,8 @@ static void test_global_data_string(struct bpf_object *obj, __u32 duration) char str[32]; map_fd = bpf_find_map(__func__, obj, "result_string"); - if (map_fd < 0) { - error_cnt++; + if (CHECK_FAIL(map_fd < 0)) return; - } struct { char *name; @@ -81,10 +77,8 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration) struct foo val; map_fd = bpf_find_map(__func__, obj, "result_struct"); - if (map_fd < 0) { - error_cnt++; + if (CHECK_FAIL(map_fd < 0)) return; - } struct { char *name; @@ -112,16 +106,12 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) __u8 *buff; map = bpf_object__find_map_by_name(obj, "test_glo.rodata"); - if (!map || !bpf_map__is_internal(map)) { - error_cnt++; + if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) return; - } map_fd = bpf_map__fd(map); - if (map_fd < 0) { - error_cnt++; + if (CHECK_FAIL(map_fd < 0)) return; - } buff = malloc(bpf_map__def(map)->value_size); if (buff) diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index 20ddca830e68..eaf64595be88 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -30,10 +30,8 @@ static void test_l4lb(const char *file) u32 *magic = (u32 *)buf; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } map_fd = bpf_find_map(__func__, obj, "vip_map"); if (map_fd < 0) @@ -72,10 +70,9 @@ static void test_l4lb(const char *file) bytes += stats[i].bytes; pkts += stats[i].pkts; } - if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { - error_cnt++; + if (CHECK_FAIL(bytes != MAGIC_BYTES * NUM_ITER * 2 || + pkts != NUM_ITER * 2)) printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts); - } out: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index ee99368c595c..8f91f1881d11 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -8,14 +8,12 @@ static void *parallel_map_access(void *arg) for (i = 0; i < 10000; i++) { err = bpf_map_lookup_elem_flags(map_fd, &key, vars, BPF_F_LOCK); - if (err) { + if (CHECK_FAIL(err)) { printf("lookup failed\n"); - error_cnt++; goto out; } - if (vars[0] != 0) { + if (CHECK_FAIL(vars[0] != 0)) { printf("lookup #%d var[0]=%d\n", i, vars[0]); - error_cnt++; goto out; } rnd = vars[1]; @@ -24,7 +22,7 @@ static void *parallel_map_access(void *arg) continue; printf("lookup #%d var[1]=%d var[%d]=%d\n", i, rnd, j, vars[j]); - error_cnt++; + CHECK_FAIL(vars[j] != rnd); goto out; } } @@ -42,34 +40,36 @@ void test_map_lock(void) void *ret; err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); - if (err) { + if (CHECK_FAIL(err)) { printf("test_map_lock:bpf_prog_load errno %d\n", errno); goto close_prog; } map_fd[0] = bpf_find_map(__func__, obj, "hash_map"); - if (map_fd[0] < 0) + if (CHECK_FAIL(map_fd[0] < 0)) goto close_prog; map_fd[1] = bpf_find_map(__func__, obj, "array_map"); - if (map_fd[1] < 0) + if (CHECK_FAIL(map_fd[1] < 0)) goto close_prog; bpf_map_update_elem(map_fd[0], &key, vars, BPF_F_LOCK); for (i = 0; i < 4; i++) - assert(pthread_create(&thread_id[i], NULL, - &spin_lock_thread, &prog_fd) == 0); + if (CHECK_FAIL(pthread_create(&thread_id[i], NULL, + &spin_lock_thread, &prog_fd))) + goto close_prog; for (i = 4; i < 6; i++) - assert(pthread_create(&thread_id[i], NULL, - ¶llel_map_access, &map_fd[i - 4]) == 0); + if (CHECK_FAIL(pthread_create(&thread_id[i], NULL, + ¶llel_map_access, + &map_fd[i - 4]))) + goto close_prog; for (i = 0; i < 4; i++) - assert(pthread_join(thread_id[i], &ret) == 0 && - ret == (void *)&prog_fd); + if (CHECK_FAIL(pthread_join(thread_id[i], &ret) || + ret != (void *)&prog_fd)) + goto close_prog; for (i = 4; i < 6; i++) - assert(pthread_join(thread_id[i], &ret) == 0 && - ret == (void *)&map_fd[i - 4]); - goto close_prog_noerr; + if (CHECK_FAIL(pthread_join(thread_id[i], &ret) || + ret != (void *)&map_fd[i - 4])) + goto close_prog; close_prog: - error_cnt++; -close_prog_noerr: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index 4ecfd721a044..a2537dfa899c 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -9,10 +9,8 @@ void test_pkt_access(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), NULL, NULL, &retval, &duration); diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index ac0d43435806..5f7aea605019 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -9,10 +9,8 @@ void test_pkt_md_access(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), NULL, NULL, &retval, &duration); diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index e60cd5ff1f55..faccc66f4e39 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -27,10 +27,8 @@ static void test_queue_stack_map_by_type(int type) return; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } map_in_fd = bpf_find_map(__func__, obj, "map_in"); if (map_in_fd < 0) @@ -43,10 +41,8 @@ static void test_queue_stack_map_by_type(int type) /* Push 32 elements to the input map */ for (i = 0; i < MAP_SIZE; i++) { err = bpf_map_update_elem(map_in_fd, NULL, &vals[i], 0); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) goto out; - } } /* The eBPF program pushes iph.saddr in the output map, diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 5633be43828f..5c78e2b5a917 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,15 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> -static int libbpf_debug_print(enum libbpf_print_level level, - const char *format, va_list args) -{ - if (level == LIBBPF_DEBUG) - return 0; - - return vfprintf(stderr, format, args); -} - void test_reference_tracking(void) { const char *file = "./test_sk_lookup_kern.o"; @@ -19,10 +10,8 @@ void test_reference_tracking(void) int err = 0; obj = bpf_object__open(file); - if (IS_ERR(obj)) { - error_cnt++; + if (CHECK_FAIL(IS_ERR(obj))) return; - } bpf_object__for_each_program(prog, obj) { const char *title; @@ -36,9 +25,11 @@ void test_reference_tracking(void) /* Expect verifier failure if test name has 'fail' */ if (strstr(title, "fail") != NULL) { - libbpf_set_print(NULL); + libbpf_print_fn_t old_print_fn; + + old_print_fn = libbpf_set_print(NULL); err = !bpf_program__load(prog, "GPL", 0); - libbpf_set_print(libbpf_debug_print); + libbpf_set_print(old_print_fn); } else { err = bpf_program__load(prog, "GPL", 0); } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 54218ee3c004..b607112c64e7 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -8,7 +8,7 @@ static void sigusr1_handler(int signum) sigusr1_received++; } -static int test_send_signal_common(struct perf_event_attr *attr, +static void test_send_signal_common(struct perf_event_attr *attr, int prog_type, const char *test_name) { @@ -23,13 +23,13 @@ static int test_send_signal_common(struct perf_event_attr *attr, if (CHECK(pipe(pipe_c2p), test_name, "pipe pipe_c2p error: %s\n", strerror(errno))) - goto no_fork_done; + return; if (CHECK(pipe(pipe_p2c), test_name, "pipe pipe_p2c error: %s\n", strerror(errno))) { close(pipe_c2p[0]); close(pipe_c2p[1]); - goto no_fork_done; + return; } pid = fork(); @@ -38,7 +38,7 @@ static int test_send_signal_common(struct perf_event_attr *attr, close(pipe_c2p[1]); close(pipe_p2c[0]); close(pipe_p2c[1]); - goto no_fork_done; + return; } if (pid == 0) { @@ -125,7 +125,7 @@ static int test_send_signal_common(struct perf_event_attr *attr, goto disable_pmu; } - err = CHECK(buf[0] != '2', test_name, "incorrect result\n"); + CHECK(buf[0] != '2', test_name, "incorrect result\n"); /* notify child safe to exit */ write(pipe_p2c[1], buf, 1); @@ -138,11 +138,9 @@ prog_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); wait(NULL); -no_fork_done: - return err; } -static int test_send_signal_tracepoint(void) +static void test_send_signal_tracepoint(void) { const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id"; struct perf_event_attr attr = { @@ -159,21 +157,21 @@ static int test_send_signal_tracepoint(void) if (CHECK(efd < 0, "tracepoint", "open syscalls/sys_enter_nanosleep/id failure: %s\n", strerror(errno))) - return -1; + return; bytes = read(efd, buf, sizeof(buf)); close(efd); if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint", "read syscalls/sys_enter_nanosleep/id failure: %s\n", strerror(errno))) - return -1; + return; attr.config = strtol(buf, NULL, 0); - return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); + test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); } -static int test_send_signal_perf(void) +static void test_send_signal_perf(void) { struct perf_event_attr attr = { .sample_period = 1, @@ -181,11 +179,11 @@ static int test_send_signal_perf(void) .config = PERF_COUNT_SW_CPU_CLOCK, }; - return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_sw_event"); + test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_sw_event"); } -static int test_send_signal_nmi(void) +static void test_send_signal_nmi(void) { struct perf_event_attr attr = { .sample_freq = 50, @@ -203,27 +201,25 @@ static int test_send_signal_nmi(void) if (pmu_fd == -1) { if (errno == ENOENT) { printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", - __func__); - return 0; + __func__); + test__skip(); + return; } /* Let the test fail with a more informative message */ } else { close(pmu_fd); } - return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_hw_event"); + test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_hw_event"); } void test_send_signal(void) { - int ret = 0; - - ret |= test_send_signal_tracepoint(); - ret |= test_send_signal_perf(); - ret |= test_send_signal_nmi(); - if (!ret) - printf("test_send_signal:OK\n"); - else - printf("test_send_signal:FAIL\n"); + if (test__start_subtest("send_signal_tracepoint")) + test_send_signal_tracepoint(); + if (test__start_subtest("send_signal_perf")) + test_send_signal_perf(); + if (test__start_subtest("send_signal_nmi")) + test_send_signal_nmi(); } diff --git a/tools/testing/selftests/bpf/test_sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index 23bd0819382d..3e8517a8395a 100644 --- a/tools/testing/selftests/bpf/test_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -1,22 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 - -#include <errno.h> -#include <stdio.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/socket.h> -#include <netinet/in.h> - -#include <linux/filter.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "bpf_rlimit.h" -#include "bpf_util.h" +#include <test_progs.h> #include "cgroup_helpers.h" -#define CG_PATH "/sockopt" - static char bpf_log_buf[4096]; static bool verbose; @@ -983,39 +968,18 @@ close_prog_fd: return ret; } -int main(int args, char **argv) +void test_sockopt(void) { - int err = EXIT_FAILURE, error_cnt = 0; int cgroup_fd, i; - if (setup_cgroup_environment()) - goto cleanup_obj; - - cgroup_fd = create_and_get_cgroup(CG_PATH); - if (cgroup_fd < 0) - goto cleanup_cgroup_env; - - if (join_cgroup(CG_PATH)) - goto cleanup_cgroup; + cgroup_fd = test__join_cgroup("/sockopt"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; for (i = 0; i < ARRAY_SIZE(tests); i++) { - int err = run_test(cgroup_fd, &tests[i]); - - if (err) - error_cnt++; - - printf("#%d %s: %s\n", i, err ? "FAIL" : "PASS", - tests[i].descr); + test__start_subtest(tests[i].descr); + CHECK_FAIL(run_test(cgroup_fd, &tests[i])); } - printf("Summary: %ld PASSED, %d FAILED\n", - ARRAY_SIZE(tests) - error_cnt, error_cnt); - err = error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; - -cleanup_cgroup: close(cgroup_fd); -cleanup_cgroup_env: - cleanup_cgroup_environment(); -cleanup_obj: - return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c new file mode 100644 index 000000000000..6cbeea7b4bf1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "cgroup_helpers.h" + +#define SOL_CUSTOM 0xdeadbeef +#define CUSTOM_INHERIT1 0 +#define CUSTOM_INHERIT2 1 +#define CUSTOM_LISTENER 2 + +static int connect_to_server(int server_fd) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + goto out; + } + + if (connect(fd, (const struct sockaddr *)&addr, len) < 0) { + log_err("Fail to connect to server"); + goto out; + } + + return fd; + +out: + close(fd); + return -1; +} + +static int verify_sockopt(int fd, int optname, const char *msg, char expected) +{ + socklen_t optlen = 1; + char buf = 0; + int err; + + err = getsockopt(fd, SOL_CUSTOM, optname, &buf, &optlen); + if (err) { + log_err("%s: failed to call getsockopt", msg); + return 1; + } + + printf("%s %d: got=0x%x ? expected=0x%x\n", msg, optname, buf, expected); + + if (buf != expected) { + log_err("%s: unexpected getsockopt value %d != %d", msg, + buf, expected); + return 1; + } + + return 0; +} + +static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER; + +static void *server_thread(void *arg) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd = *(int *)arg; + int client_fd; + int err = 0; + + err = listen(fd, 1); + + pthread_mutex_lock(&server_started_mtx); + pthread_cond_signal(&server_started); + pthread_mutex_unlock(&server_started_mtx); + + if (CHECK_FAIL(err < 0)) { + perror("Failed to listed on socket"); + return NULL; + } + + err += verify_sockopt(fd, CUSTOM_INHERIT1, "listen", 1); + err += verify_sockopt(fd, CUSTOM_INHERIT2, "listen", 1); + err += verify_sockopt(fd, CUSTOM_LISTENER, "listen", 1); + + client_fd = accept(fd, (struct sockaddr *)&addr, &len); + if (CHECK_FAIL(client_fd < 0)) { + perror("Failed to accept client"); + return NULL; + } + + err += verify_sockopt(client_fd, CUSTOM_INHERIT1, "accept", 1); + err += verify_sockopt(client_fd, CUSTOM_INHERIT2, "accept", 1); + err += verify_sockopt(client_fd, CUSTOM_LISTENER, "accept", 0); + + close(client_fd); + + return (void *)(long)err; +} + +static int start_server(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + }; + char buf; + int err; + int fd; + int i; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create server socket"); + return -1; + } + + for (i = CUSTOM_INHERIT1; i <= CUSTOM_LISTENER; i++) { + buf = 0x01; + err = setsockopt(fd, SOL_CUSTOM, i, &buf, 1); + if (err) { + log_err("Failed to call setsockopt(%d)", i); + close(fd); + return -1; + } + } + + if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { + log_err("Failed to bind socket"); + close(fd); + return -1; + } + + return fd; +} + +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +{ + enum bpf_attach_type attach_type; + enum bpf_prog_type prog_type; + struct bpf_program *prog; + int err; + + err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); + if (err) { + log_err("Failed to deduct types for %s BPF program", title); + return -1; + } + + prog = bpf_object__find_program_by_title(obj, title); + if (!prog) { + log_err("Failed to find %s BPF program", title); + return -1; + } + + err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, + attach_type, 0); + if (err) { + log_err("Failed to attach %s BPF program", title); + return -1; + } + + return 0; +} + +static void run_test(int cgroup_fd) +{ + struct bpf_prog_load_attr attr = { + .file = "./sockopt_inherit.o", + }; + int server_fd = -1, client_fd; + struct bpf_object *obj; + void *server_err; + pthread_t tid; + int ignored; + int err; + + err = bpf_prog_load_xattr(&attr, &obj, &ignored); + if (CHECK_FAIL(err)) + return; + + err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt"); + if (CHECK_FAIL(err)) + goto close_bpf_object; + + err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt"); + if (CHECK_FAIL(err)) + goto close_bpf_object; + + server_fd = start_server(); + if (CHECK_FAIL(server_fd < 0)) + goto close_bpf_object; + + if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, + (void *)&server_fd))) + goto close_bpf_object; + + pthread_mutex_lock(&server_started_mtx); + pthread_cond_wait(&server_started, &server_started_mtx); + pthread_mutex_unlock(&server_started_mtx); + + client_fd = connect_to_server(server_fd); + if (CHECK_FAIL(client_fd < 0)) + goto close_server_fd; + + CHECK_FAIL(verify_sockopt(client_fd, CUSTOM_INHERIT1, "connect", 0)); + CHECK_FAIL(verify_sockopt(client_fd, CUSTOM_INHERIT2, "connect", 0)); + CHECK_FAIL(verify_sockopt(client_fd, CUSTOM_LISTENER, "connect", 0)); + + pthread_join(tid, &server_err); + + err = (int)(long)server_err; + CHECK_FAIL(err); + + close(client_fd); + +close_server_fd: + close(server_fd); +close_bpf_object: + bpf_object__close(obj); +} + +void test_sockopt_inherit(void) +{ + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/sockopt_inherit"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; + + run_test(cgroup_fd); + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/test_sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 4be3441db867..29188d6f5c8d 100644 --- a/tools/testing/selftests/bpf/test_sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -1,19 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 - -#include <error.h> -#include <errno.h> -#include <stdio.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/socket.h> -#include <netinet/in.h> - -#include <linux/filter.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "bpf_rlimit.h" -#include "bpf_util.h" +#include <test_progs.h> #include "cgroup_helpers.h" static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) @@ -308,7 +294,7 @@ detach: return err; } -int main(int argc, char **argv) +void test_sockopt_multi(void) { struct bpf_prog_load_attr attr = { .file = "./sockopt_multi.o", @@ -319,56 +305,28 @@ int main(int argc, char **argv) int err = -1; int ignored; - if (setup_cgroup_environment()) { - log_err("Failed to setup cgroup environment\n"); - goto out; - } - - cg_parent = create_and_get_cgroup("/parent"); - if (cg_parent < 0) { - log_err("Failed to create cgroup /parent\n"); - goto out; - } - - cg_child = create_and_get_cgroup("/parent/child"); - if (cg_child < 0) { - log_err("Failed to create cgroup /parent/child\n"); + cg_parent = test__join_cgroup("/parent"); + if (CHECK_FAIL(cg_parent < 0)) goto out; - } - if (join_cgroup("/parent/child")) { - log_err("Failed to join cgroup /parent/child\n"); + cg_child = test__join_cgroup("/parent/child"); + if (CHECK_FAIL(cg_child < 0)) goto out; - } err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (err) { - log_err("Failed to load BPF object"); + if (CHECK_FAIL(err)) goto out; - } sock_fd = socket(AF_INET, SOCK_STREAM, 0); - if (sock_fd < 0) { - log_err("Failed to create socket"); + if (CHECK_FAIL(sock_fd < 0)) goto out; - } - if (run_getsockopt_test(obj, cg_parent, cg_child, sock_fd)) - err = -1; - printf("test_sockopt_multi: getsockopt %s\n", - err ? "FAILED" : "PASSED"); - - if (run_setsockopt_test(obj, cg_parent, cg_child, sock_fd)) - err = -1; - printf("test_sockopt_multi: setsockopt %s\n", - err ? "FAILED" : "PASSED"); + CHECK_FAIL(run_getsockopt_test(obj, cg_parent, cg_child, sock_fd)); + CHECK_FAIL(run_setsockopt_test(obj, cg_parent, cg_child, sock_fd)); out: close(sock_fd); bpf_object__close(obj); close(cg_child); close(cg_parent); - - printf("test_sockopt_multi: %s\n", err ? "FAILED" : "PASSED"); - return err ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 036b652e5ca9..2061a6beac0f 100644 --- a/tools/testing/selftests/bpf/test_sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -1,22 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 - -#include <errno.h> -#include <stdio.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/socket.h> -#include <netinet/in.h> - -#include <linux/filter.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "bpf_rlimit.h" -#include "bpf_util.h" +#include <test_progs.h> #include "cgroup_helpers.h" -#define CG_PATH "/sockopt" - #define SOL_CUSTOM 0xdeadbeef static int getsetsockopt(void) @@ -25,6 +10,7 @@ static int getsetsockopt(void) union { char u8[4]; __u32 u32; + char cc[16]; /* TCP_CA_NAME_MAX */ } buf = {}; socklen_t optlen; @@ -115,6 +101,29 @@ static int getsetsockopt(void) goto err; } + /* TCP_CONGESTION can extend the string */ + + strcpy(buf.cc, "nv"); + err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv")); + if (err) { + log_err("Failed to call setsockopt(TCP_CONGESTION)"); + goto err; + } + + + optlen = sizeof(buf.cc); + err = getsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(TCP_CONGESTION)"); + goto err; + } + + if (strcmp(buf.cc, "cubic") != 0) { + log_err("Unexpected getsockopt(TCP_CONGESTION) %s != %s", + buf.cc, "cubic"); + goto err; + } + close(fd); return 0; err: @@ -151,7 +160,7 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) return 0; } -static int run_test(int cgroup_fd) +static void run_test(int cgroup_fd) { struct bpf_prog_load_attr attr = { .file = "./sockopt_sk.o", @@ -161,51 +170,31 @@ static int run_test(int cgroup_fd) int err; err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (err) { - log_err("Failed to load BPF object"); - return -1; - } + if (CHECK_FAIL(err)) + return; err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt"); - if (err) + if (CHECK_FAIL(err)) goto close_bpf_object; err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt"); - if (err) + if (CHECK_FAIL(err)) goto close_bpf_object; - err = getsetsockopt(); + CHECK_FAIL(getsetsockopt()); close_bpf_object: bpf_object__close(obj); - return err; } -int main(int args, char **argv) +void test_sockopt_sk(void) { int cgroup_fd; - int err = EXIT_SUCCESS; - - if (setup_cgroup_environment()) - goto cleanup_obj; - - cgroup_fd = create_and_get_cgroup(CG_PATH); - if (cgroup_fd < 0) - goto cleanup_cgroup_env; - - if (join_cgroup(CG_PATH)) - goto cleanup_cgroup; - - if (run_test(cgroup_fd)) - err = EXIT_FAILURE; - printf("test_sockopt_sk: %s\n", - err == EXIT_SUCCESS ? "PASSED" : "FAILED"); + cgroup_fd = test__join_cgroup("/sockopt_sk"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; -cleanup_cgroup: + run_test(cgroup_fd); close(cgroup_fd); -cleanup_cgroup_env: - cleanup_cgroup_environment(); -cleanup_obj: - return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 114ebe6a438e..1ae00cd3174e 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -11,19 +11,19 @@ void test_spinlock(void) void *ret; err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); - if (err) { + if (CHECK_FAIL(err)) { printf("test_spin_lock:bpf_prog_load errno %d\n", errno); goto close_prog; } for (i = 0; i < 4; i++) - assert(pthread_create(&thread_id[i], NULL, - &spin_lock_thread, &prog_fd) == 0); + if (CHECK_FAIL(pthread_create(&thread_id[i], NULL, + &spin_lock_thread, &prog_fd))) + goto close_prog; + for (i = 0; i < 4; i++) - assert(pthread_join(thread_id[i], &ret) == 0 && - ret == (void *)&prog_fd); - goto close_prog_noerr; + if (CHECK_FAIL(pthread_join(thread_id[i], &ret) || + ret != (void *)&prog_fd)) + goto close_prog; close_prog: - error_cnt++; -close_prog_noerr: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c index ac44fda84833..d841dced971f 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c @@ -51,9 +51,10 @@ retry: "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); + if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) + goto disable_pmu; + if (CHECK_FAIL(system("./urandom_read"))) + goto disable_pmu; /* disable stack trace collection */ key = 0; val = 1; diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 9557b7dfb782..f62aa0eb959b 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -82,9 +82,10 @@ retry: "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); + if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) + goto disable_pmu; + if (CHECK_FAIL(system("taskset 0x1 ./urandom_read 100000"))) + goto disable_pmu; /* disable stack trace collection */ key = 0; val = 1; diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c index fc539335c5b3..37269d23df93 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c @@ -26,19 +26,19 @@ void test_stacktrace_map(void) /* find map fds */ control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (control_map_fd < 0) + if (CHECK_FAIL(control_map_fd < 0)) goto disable_pmu; stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (stackid_hmap_fd < 0) + if (CHECK_FAIL(stackid_hmap_fd < 0)) goto disable_pmu; stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (stackmap_fd < 0) + if (CHECK_FAIL(stackmap_fd < 0)) goto disable_pmu; stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (stack_amap_fd < 0) + if (CHECK_FAIL(stack_amap_fd < 0)) goto disable_pmu; /* give some time for bpf program run */ @@ -55,23 +55,20 @@ void test_stacktrace_map(void) 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_noerr; + 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_noerr; + goto disable_pmu; 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; - goto disable_pmu_noerr; disable_pmu: - error_cnt++; -disable_pmu_noerr: bpf_link__destroy(link); close_prog: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c index fbfa8e76cf63..404a5498e1a3 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c @@ -26,15 +26,15 @@ void test_stacktrace_map_raw_tp(void) /* find map fds */ control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (control_map_fd < 0) + if (CHECK_FAIL(control_map_fd < 0)) goto close_prog; stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (stackid_hmap_fd < 0) + if (CHECK_FAIL(stackid_hmap_fd < 0)) goto close_prog; stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (stackmap_fd < 0) + if (CHECK_FAIL(stackmap_fd < 0)) goto close_prog; /* give some time for bpf program run */ @@ -58,10 +58,7 @@ void test_stacktrace_map_raw_tp(void) "err %d errno %d\n", err, errno)) goto close_prog; - goto close_prog_noerr; close_prog: - error_cnt++; -close_prog_noerr: if (!IS_ERR_OR_NULL(link)) bpf_link__destroy(link); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c b/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c index 958a3d88de99..1bdc1d86a50c 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c +++ b/tools/testing/selftests/bpf/prog_tests/task_fd_query_rawtp.c @@ -70,9 +70,6 @@ void test_task_fd_query_rawtp(void) 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); } diff --git a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c index f9b70e81682b..3f131b8fe328 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c @@ -62,14 +62,9 @@ static void test_task_fd_query_tp_core(const char *probe_name, 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); } diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_estats.c b/tools/testing/selftests/bpf/prog_tests/tcp_estats.c index bb8759d69099..594307dffd13 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_estats.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_estats.c @@ -10,10 +10,8 @@ void test_tcp_estats(void) err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); CHECK(err, "", "err %d errno %d\n", err, errno); - if (err) { - error_cnt++; + if (err) return; - } bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/test_tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index 90c3862f74a8..fdc0b3614a9e 100644 --- a/tools/testing/selftests/bpf/test_tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -1,23 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include <error.h> -#include <errno.h> -#include <stdio.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/socket.h> -#include <netinet/in.h> -#include <pthread.h> - -#include <linux/filter.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "bpf_rlimit.h" -#include "bpf_util.h" +#include <test_progs.h> #include "cgroup_helpers.h" -#define CG_PATH "/tcp_rtt" - struct tcp_rtt_storage { __u32 invoked; __u32 dsack_dups; @@ -30,8 +14,32 @@ static void send_byte(int fd) { char b = 0x55; - if (write(fd, &b, sizeof(b)) != 1) - error(1, errno, "Failed to send single byte"); + if (CHECK_FAIL(write(fd, &b, sizeof(b)) != 1)) + perror("Failed to send single byte"); +} + +static int wait_for_ack(int fd, int retries) +{ + struct tcp_info info; + socklen_t optlen; + int i, err; + + for (i = 0; i < retries; i++) { + optlen = sizeof(info); + err = getsockopt(fd, SOL_TCP, TCP_INFO, &info, &optlen); + if (err < 0) { + log_err("Failed to lookup TCP stats"); + return err; + } + + if (info.tcpi_unacked == 0) + return 0; + + usleep(10); + } + + log_err("Did not receive ACK"); + return -1; } static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, @@ -41,8 +49,10 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, int err = 0; struct tcp_rtt_storage val; - if (bpf_map_lookup_elem(map_fd, &client_fd, &val) < 0) - error(1, errno, "Failed to read socket storage"); + if (CHECK_FAIL(bpf_map_lookup_elem(map_fd, &client_fd, &val) < 0)) { + perror("Failed to read socket storage"); + return -1; + } if (val.invoked != invoked) { log_err("%s: unexpected bpf_tcp_sock.invoked %d != %d", @@ -149,6 +159,11 @@ static int run_test(int cgroup_fd, int server_fd) /*icsk_retransmits=*/0); send_byte(client_fd); + if (wait_for_ack(client_fd, 100) < 0) { + err = -1; + goto close_client_fd; + } + err += verify_sk(map_fd, client_fd, "first payload byte", /*invoked=*/2, @@ -157,6 +172,7 @@ static int run_test(int cgroup_fd, int server_fd) /*delivered_ce=*/0, /*icsk_retransmits=*/0); +close_client_fd: close(client_fd); close_bpf_object: @@ -194,61 +210,47 @@ static void *server_thread(void *arg) int fd = *(int *)arg; int client_fd; - if (listen(fd, 1) < 0) - error(1, errno, "Failed to listed on socket"); + if (CHECK_FAIL(listen(fd, 1)) < 0) { + perror("Failed to listed on socket"); + return NULL; + } client_fd = accept(fd, (struct sockaddr *)&addr, &len); - if (client_fd < 0) - error(1, errno, "Failed to accept client"); + if (CHECK_FAIL(client_fd < 0)) { + perror("Failed to accept client"); + return NULL; + } /* Wait for the next connection (that never arrives) * to keep this thread alive to prevent calling * close() on client_fd. */ - if (accept(fd, (struct sockaddr *)&addr, &len) >= 0) - error(1, errno, "Unexpected success in second accept"); + if (CHECK_FAIL(accept(fd, (struct sockaddr *)&addr, &len) >= 0)) { + perror("Unexpected success in second accept"); + return NULL; + } close(client_fd); return NULL; } -int main(int args, char **argv) +void test_tcp_rtt(void) { int server_fd, cgroup_fd; - int err = EXIT_SUCCESS; pthread_t tid; - if (setup_cgroup_environment()) - goto cleanup_obj; - - cgroup_fd = create_and_get_cgroup(CG_PATH); - if (cgroup_fd < 0) - goto cleanup_cgroup_env; - - if (join_cgroup(CG_PATH)) - goto cleanup_cgroup; + cgroup_fd = test__join_cgroup("/tcp_rtt"); + if (CHECK_FAIL(cgroup_fd < 0)) + return; server_fd = start_server(); - if (server_fd < 0) { - err = EXIT_FAILURE; - goto cleanup_cgroup; - } + if (CHECK_FAIL(server_fd < 0)) + goto close_cgroup_fd; pthread_create(&tid, NULL, server_thread, (void *)&server_fd); - - if (run_test(cgroup_fd, server_fd)) - err = EXIT_FAILURE; - + CHECK_FAIL(run_test(cgroup_fd, server_fd)); close(server_fd); - - printf("test_sockopt_sk: %s\n", - err == EXIT_SUCCESS ? "PASSED" : "FAILED"); - -cleanup_cgroup: +close_cgroup_fd: close(cgroup_fd); -cleanup_cgroup_env: - cleanup_cgroup_environment(); -cleanup_obj: - return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index a74167289545..dcb5ecac778e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -16,10 +16,8 @@ void test_xdp(void) int err, prog_fd, map_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } map_fd = bpf_find_map(__func__, obj, "vip2tnl"); if (map_fd < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 922aa0a19764..3744196d7cba 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -10,10 +10,8 @@ void test_xdp_adjust_tail(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 09e6b46f5515..c9404e6b226e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -31,10 +31,8 @@ void test_xdp_noinline(void) u32 *magic = (u32 *)buf; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (err) { - error_cnt++; + if (CHECK_FAIL(err)) return; - } map_fd = bpf_find_map(__func__, obj, "vip_map"); if (map_fd < 0) @@ -73,9 +71,10 @@ void test_xdp_noinline(void) bytes += stats[i].bytes; pkts += stats[i].pkts; } - if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { - error_cnt++; - printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts); + if (CHECK_FAIL(bytes != MAGIC_BYTES * NUM_ITER * 2 || + pkts != NUM_ITER * 2)) { + printf("test_xdp_noinline:FAIL:stats %lld %lld\n", + bytes, pkts); } out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 5ae485a6af3f..040a44206f29 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -65,8 +65,8 @@ struct { } jmp_table SEC(".maps"); struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); __type(key, __u32); __type(value, struct bpf_flow_keys); } last_dissection SEC(".maps"); @@ -74,15 +74,20 @@ struct { static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, int ret) { - struct bpf_flow_keys *val; - __u32 key = 0; + __u32 key = (__u32)(keys->sport) << 16 | keys->dport; + struct bpf_flow_keys val; - val = bpf_map_lookup_elem(&last_dissection, &key); - if (val) - memcpy(val, keys, sizeof(*val)); + memcpy(&val, keys, sizeof(val)); + bpf_map_update_elem(&last_dissection, &key, &val, BPF_ANY); return ret; } +#define IPV6_FLOWLABEL_MASK __bpf_constant_htonl(0x000FFFFF) +static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) +{ + return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; +} + static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, __u16 hdr_size, void *buffer) @@ -153,7 +158,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) struct tcphdr *tcp, _tcp; struct udphdr *udp, _udp; - keys->ip_proto = proto; switch (proto) { case IPPROTO_ICMP: icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); @@ -162,9 +166,15 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) return export_flow_keys(keys, BPF_OK); case IPPROTO_IPIP: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); case IPPROTO_IPV6: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6)); case IPPROTO_GRE: gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); @@ -184,6 +194,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) keys->thoff += 4; /* Step over sequence number */ keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); if (gre->proto == bpf_htons(ETH_P_TEB)) { eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), @@ -231,7 +243,6 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->ip_proto = nexthdr; switch (nexthdr) { case IPPROTO_HOPOPTS: case IPPROTO_DSTOPTS: @@ -266,6 +277,7 @@ PROG(IP)(struct __sk_buff *skb) keys->addr_proto = ETH_P_IP; keys->ipv4_src = iph->saddr; keys->ipv4_dst = iph->daddr; + keys->ip_proto = iph->protocol; keys->thoff += iph->ihl << 2; if (data + keys->thoff > data_end) @@ -273,13 +285,20 @@ PROG(IP)(struct __sk_buff *skb) if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { keys->is_frag = true; - if (iph->frag_off & bpf_htons(IP_OFFSET)) + if (iph->frag_off & bpf_htons(IP_OFFSET)) { /* From second fragment on, packets do not have headers * we can parse. */ done = true; - else + } else { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + done = true; + } } if (done) @@ -301,6 +320,11 @@ PROG(IPV6)(struct __sk_buff *skb) memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); keys->thoff += sizeof(struct ipv6hdr); + keys->ip_proto = ip6h->nexthdr; + keys->flow_label = ip6_flowlabel(ip6h); + + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) + return export_flow_keys(keys, BPF_OK); return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -317,7 +341,8 @@ PROG(IPV6OP)(struct __sk_buff *skb) /* hlen is in 8-octets and does not include the first 8 bytes * of the header */ - skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->ip_proto = ip6h->nexthdr; return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -333,9 +358,18 @@ PROG(IPV6FR)(struct __sk_buff *skb) keys->thoff += sizeof(*fragh); keys->is_frag = true; - if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) + keys->ip_proto = fragh->nexthdr; + + if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + return export_flow_keys(keys, BPF_OK); + } + return parse_ipv6_proto(skb, fragh->nexthdr); } diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c new file mode 100644 index 000000000000..018ed7fbba3a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c new file mode 100644 index 000000000000..13d662c57014 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_dim x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c new file mode 100644 index 000000000000..a351f418c85d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_val_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c new file mode 100644 index 000000000000..a8735009becc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_non_array x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c new file mode 100644 index 000000000000..2a67c28b1e75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_shallow x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c new file mode 100644 index 000000000000..1142c08c925f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_small x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c new file mode 100644 index 000000000000..795a5b729176 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type1 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c new file mode 100644 index 000000000000..3af74b837c4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c new file mode 100644 index 000000000000..b74455b91227 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c new file mode 100644 index 000000000000..7b6035f86ee6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors__err_wrong_name x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c new file mode 100644 index 000000000000..7d0f041042c5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c new file mode 100644 index 000000000000..f9359450186e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___bool x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c new file mode 100644 index 000000000000..50369e8320a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_bitfield x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c new file mode 100644 index 000000000000..823bac13d641 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_16 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c new file mode 100644 index 000000000000..b44f3be18535 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_32 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c new file mode 100644 index 000000000000..9a3dd2099c0f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_64 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c new file mode 100644 index 000000000000..9f11ef5f6e88 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_8 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c new file mode 100644 index 000000000000..aafb1c5819d7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___reverse_sign x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c new file mode 100644 index 000000000000..ed9ad8b5b4f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_misc___a x) {} +void f2(struct core_reloc_misc___b x) {} +void f3(struct core_reloc_misc_extensible x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c new file mode 100644 index 000000000000..124197a2e813 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c new file mode 100644 index 000000000000..f8a6592ca75f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___mod_swap x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c new file mode 100644 index 000000000000..5c0d73687247 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___typedefs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c new file mode 100644 index 000000000000..4480fcc0f183 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c new file mode 100644 index 000000000000..13e108f76ece --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___anon_embed x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c new file mode 100644 index 000000000000..76b54fda5fbb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___dup_compat_types x) {} +void f2(struct core_reloc_nesting___dup_compat_types__2 x) {} +void f3(struct core_reloc_nesting___dup_compat_types__3 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c new file mode 100644 index 000000000000..975fb95db810 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c new file mode 100644 index 000000000000..ad66c67e7980 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c new file mode 100644 index 000000000000..35c5f8da6812 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_dup_incompat_types__1 x) {} +void f2(struct core_reloc_nesting___err_dup_incompat_types__2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c new file mode 100644 index 000000000000..142e332041db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c new file mode 100644 index 000000000000..efcae167fab9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c new file mode 100644 index 000000000000..97aaaedd8ada --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_nonstruct_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c new file mode 100644 index 000000000000..ffde35086e90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_partial_match_dups__a x) {} +void f2(struct core_reloc_nesting___err_partial_match_dups__b x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c new file mode 100644 index 000000000000..39a2fadd8e95 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_too_deep x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c new file mode 100644 index 000000000000..a09d9dfb20df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___extra_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c new file mode 100644 index 000000000000..3d8a1a74012f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___struct_union_mixup x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c new file mode 100644 index 000000000000..96b90e39242a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c new file mode 100644 index 000000000000..6e87233a3ed0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_enum_def x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c new file mode 100644 index 000000000000..d9f48e80b9d9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_func_proto x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c new file mode 100644 index 000000000000..c718f75f8f3b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_ptr_type x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c new file mode 100644 index 000000000000..b8a120830891 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_enum x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c new file mode 100644 index 000000000000..ad8b3c9aa76f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_int x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c new file mode 100644 index 000000000000..e20bc1d42d0a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_ptr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..8da52432ba17 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c new file mode 100644 index 000000000000..003acfc9a3e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h new file mode 100644 index 000000000000..f686a8138d90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -0,0 +1,667 @@ +#include <stdint.h> +#include <stdbool.h> + +/* + * FLAVORS + */ +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* this is not a flavor, as it doesn't have triple underscore */ +struct core_reloc_flavors__err_wrong_name { + int a; + int b; + int c; +}; + +/* + * NESTING + */ +/* original set up, used to record relocations in BPF program */ +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +/* inlined anonymous struct/union instead of named structs in original */ +struct core_reloc_nesting___anon_embed { + int __just_for_padding; + union { + struct { + int a; + } a; + } a; + struct { + union { + int b; + } b; + } b; +}; + +/* different mix of nested structs/unions than in original */ +struct core_reloc_nesting___struct_union_mixup { + int __a; + struct { + int __a; + union { + char __a; + int a; + } a; + } a; + int __b; + union { + int __b; + union { + char __b; + int b; + } b; + } b; +}; + +/* extra anon structs/unions, but still valid a.a.a and b.b.b accessors */ +struct core_reloc_nesting___extra_nesting { + int __padding; + struct { + struct { + struct { + struct { + union { + int a; + } a; + }; + }; + } a; + int __some_more; + struct { + union { + union { + union { + struct { + int b; + }; + } b; + }; + } b; + }; + }; +}; + +/* three flavors of same struct with different structure but same layout for + * a.a.a and b.b.b, thus successfully resolved and relocatable */ +struct core_reloc_nesting___dup_compat_types { + char __just_for_padding; + /* 3 more bytes of padding */ + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + long long __more_padding; + struct { + struct { + int b; /* offset 16 */ + } b; + } b; +}; + +struct core_reloc_nesting___dup_compat_types__2 { + int __aligned_padding; + struct { + int __trickier_noop[0]; + struct { + char __some_more_noops[0]; + int a; /* offset 4 */ + } a; + } a; + int __more_padding; + struct { + struct { + struct { + int __critical_padding; + int b; /* offset 16 */ + } b; + int __does_not_matter; + }; + } b; + int __more_irrelevant_stuff; +}; + +struct core_reloc_nesting___dup_compat_types__3 { + char __correct_padding[4]; + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + /* 8 byte padding due to next struct's alignment */ + struct { + struct { + int b; + } b; + } b __attribute__((aligned(16))); +}; + +/* b.b.b field is missing */ +struct core_reloc_nesting___err_missing_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int x; + } b; + } b; +}; + +/* b.b.b field is an array of integers instead of plain int */ +struct core_reloc_nesting___err_array_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b[1]; + } b; + } b; +}; + +/* middle b container is missing */ +struct core_reloc_nesting___err_missing_container { + struct { + struct { + int a; + } a; + } a; + struct { + int x; + } b; +}; + +/* middle b container is referenced through pointer instead of being embedded */ +struct core_reloc_nesting___err_nonstruct_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } *b; + } b; +}; + +/* middle b container is an array of structs instead of plain struct */ +struct core_reloc_nesting___err_array_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } b[1]; + } b; +}; + +/* two flavors of same struct with incompatible layout for b.b.b */ +struct core_reloc_nesting___err_dup_incompat_types__1 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + struct { + struct { + int b; /* offset 4 */ + } b; + } b; +}; + +struct core_reloc_nesting___err_dup_incompat_types__2 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + int __extra_padding; + struct { + struct { + int b; /* offset 8 (!) */ + } b; + } b; +}; + +/* two flavors of same struct having one of a.a.a and b.b.b, but not both */ +struct core_reloc_nesting___err_partial_match_dups__a { + struct { + struct { + int a; + } a; + } a; +}; + +struct core_reloc_nesting___err_partial_match_dups__b { + struct { + struct { + int b; + } b; + } b; +}; + +struct core_reloc_nesting___err_too_deep { + struct { + struct { + int a; + } a; + } a; + /* 65 levels of nestedness for b.b.b */ + struct { + struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + /* this one is one too much */ + struct { + int b; + }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + } b; + } b; +}; + +/* + * ARRAYS + */ +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* bigger array dimensions */ +struct core_reloc_arrays___diff_arr_dim { + int a[7]; + char b[3][4][5]; + struct core_reloc_arrays_substruct c[4]; + struct core_reloc_arrays_substruct d[2][3]; +}; + +/* different size of array's value (struct) */ +struct core_reloc_arrays___diff_arr_val_sz { + int a[5]; + char b[2][3][4]; + struct { + int __padding1; + int c; + int __padding2; + } c[3]; + struct { + int __padding1; + int d; + int __padding2; + } d[1][2]; +}; + +struct core_reloc_arrays___err_too_small { + int a[2]; /* this one is too small */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_too_shallow { + int a[5]; + char b[2][3]; /* this one lacks one dimension */ + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_non_array { + int a; /* not an array */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type1 { + char a[5]; /* char instead of int */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type2 { + int a[5]; + char b[2][3][4]; + int c[3]; /* value is not a struct */ + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* + * PRIMITIVES + */ +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___diff_enum_def { + char a; + int b; + void *d; + int (*f)(const char *); + enum { + X = 100, + Y = 200, + } c; /* inline enum def with differing set of values */ +}; + +struct core_reloc_primitives___diff_func_proto { + void (*f)(int); /* incompatible function prototype */ + void *d; + enum core_reloc_primitives_enum c; + int b; + char a; +}; + +struct core_reloc_primitives___diff_ptr_type { + const char * const d; /* different pointee type + modifiers */ + char a; + int b; + enum core_reloc_primitives_enum c; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_enum { + char a[1]; + int b; + int c; /* int instead of enum */ + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_int { + char a[1]; + int *b; /* ptr instead of int */ + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_ptr { + char a[1]; + int b; + enum core_reloc_primitives_enum c; + int d; /* int instead of ptr */ + int (*f)(const char *); +}; + +/* + * MODS + */ +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +/* a/b, c/d, e/f, and g/h pairs are swapped */ +struct core_reloc_mods___mod_swap { + int b; + int_t a; + char *d; + char_ptr_t c; + int f[3]; + arr_t e; + struct { + int y; + int x; + } h; + core_reloc_mods_substruct_t g; +}; + +typedef int int1_t; +typedef int1_t int2_t; +typedef int2_t int3_t; + +typedef int arr1_t[5]; +typedef arr1_t arr2_t; +typedef arr2_t arr3_t; +typedef arr3_t arr4_t; + +typedef const char * const volatile fancy_char_ptr_t; + +typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; + +/* we need more typedefs */ +struct core_reloc_mods___typedefs { + core_reloc_mods_substruct_tt g; + core_reloc_mods_substruct_tt h; + arr4_t f; + arr4_t e; + fancy_char_ptr_t d; + fancy_char_ptr_t c; + int3_t b; + int3_t a; +}; + +/* + * PTR_AS_ARR + */ +struct core_reloc_ptr_as_arr { + int a; +}; + +struct core_reloc_ptr_as_arr___diff_sz { + int :32; /* padding */ + char __some_more_padding; + int a; +}; + +/* + * INTS + */ +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +/* signed/unsigned types swap */ +struct core_reloc_ints___reverse_sign { + int8_t u8_field; + uint8_t s8_field; + int16_t u16_field; + uint16_t s16_field; + int32_t u32_field; + uint32_t s32_field; + int64_t u64_field; + uint64_t s64_field; +}; + +struct core_reloc_ints___bool { + bool u8_field; /* bool instead of uint8 */ + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_bitfield { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field: 32; /* bitfields are not supported */ + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_8 { + uint16_t u8_field; /* not 8-bit anymore */ + int16_t s8_field; /* not 8-bit anymore */ + + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_16 { + uint8_t u8_field; + int8_t s8_field; + + uint32_t u16_field; /* not 16-bit anymore */ + int32_t s16_field; /* not 16-bit anymore */ + + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_32 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + + uint64_t u32_field; /* not 32-bit anymore */ + int64_t s32_field; /* not 32-bit anymore */ + + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_64 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + + uint32_t u64_field; /* not 64-bit anymore */ + int32_t s64_field; /* not 64-bit anymore */ +}; + +/* + * MISC + */ +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* this one extends core_reloc_misc_extensible struct from BPF prog */ +struct core_reloc_misc_extensible { + int a; + int b; + int c; + int d; +}; diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c new file mode 100644 index 000000000000..650859022771 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int combinations(volatile struct __sk_buff* skb) +{ + int ret = 0, i; + +#pragma nounroll + for (i = 0; i < 20; i++) + if (skb->len) + ret |= 1 << i; + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c new file mode 100644 index 000000000000..28d1d668f07c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define barrier() __asm__ __volatile__("": : :"memory") + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int while_true(volatile struct __sk_buff* skb) +{ + int i = 0; + + while (1) { + if (skb->len) + i += 3; + else + i += 7; + if (i == 9) + break; + barrier(); + if (i == 10) + break; + barrier(); + if (i == 13) + break; + barrier(); + if (i == 14) + break; + } + return i; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c new file mode 100644 index 000000000000..dede0fcd6102 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; + +#define SOL_CUSTOM 0xdeadbeef +#define CUSTOM_INHERIT1 0 +#define CUSTOM_INHERIT2 1 +#define CUSTOM_LISTENER 2 + +struct sockopt_inherit { + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct sockopt_inherit); +} cloned1_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct sockopt_inherit); +} cloned2_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct sockopt_inherit); +} listener_only_map SEC(".maps"); + +static __inline struct sockopt_inherit *get_storage(struct bpf_sockopt *ctx) +{ + if (ctx->optname == CUSTOM_INHERIT1) + return bpf_sk_storage_get(&cloned1_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + else if (ctx->optname == CUSTOM_INHERIT2) + return bpf_sk_storage_get(&cloned2_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + else + return bpf_sk_storage_get(&listener_only_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); +} + +SEC("cgroup/getsockopt") +int _getsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + struct sockopt_inherit *storage; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_CUSTOM) + return 1; /* only interested in SOL_CUSTOM */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = get_storage(ctx); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = storage->val; + ctx->optlen = 1; + + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + struct sockopt_inherit *storage; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_CUSTOM) + return 1; /* only interested in SOL_CUSTOM */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = get_storage(ctx); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + storage->val = optval[0]; + ctx->optlen = -1; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 076122c898e9..9a3d1c79e6fe 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include <string.h> #include <netinet/in.h> +#include <netinet/tcp.h> #include <linux/bpf.h> #include "bpf_helpers.h" @@ -42,6 +44,14 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Not interested in SOL_TCP:TCP_CONGESTION; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ @@ -91,6 +101,18 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Always use cubic */ + + if (optval + 5 > optval_end) + return 0; /* EPERM, bounds check */ + + memcpy(optval, "cubic", 5); + ctx->optlen = 5; + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c new file mode 100644 index 000000000000..bf67f0fdf743 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_arrays(void *ctx) +{ + struct core_reloc_arrays *in = (void *)&data.in; + struct core_reloc_arrays_output *out = (void *)&data.out; + + /* in->a[2] */ + if (BPF_CORE_READ(&out->a2, &in->a[2])) + return 1; + /* in->b[1][2][3] */ + if (BPF_CORE_READ(&out->b123, &in->b[1][2][3])) + return 1; + /* in->c[1].c */ + if (BPF_CORE_READ(&out->c1c, &in->c[1].c)) + return 1; + /* in->d[0][0].d */ + if (BPF_CORE_READ(&out->d00d, &in->d[0][0].d)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c new file mode 100644 index 000000000000..9fda73e87972 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* local flavor with reversed layout */ +struct core_reloc_flavors___reversed { + int c; + int b; + int a; +}; + +/* local flavor with nested/overlapping layout */ +struct core_reloc_flavors___weird { + struct { + int b; + }; + /* a and c overlap in local flavor, but this should still work + * correctly with target original flavor + */ + union { + int a; + int c; + }; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_flavors(void *ctx) +{ + struct core_reloc_flavors *in_orig = (void *)&data.in; + struct core_reloc_flavors___reversed *in_rev = (void *)&data.in; + struct core_reloc_flavors___weird *in_weird = (void *)&data.in; + struct core_reloc_flavors *out = (void *)&data.out; + + /* read a using weird layout */ + if (BPF_CORE_READ(&out->a, &in_weird->a)) + return 1; + /* read b using reversed layout */ + if (BPF_CORE_READ(&out->b, &in_rev->b)) + return 1; + /* read c using original layout */ + if (BPF_CORE_READ(&out->c, &in_orig->c)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c new file mode 100644 index 000000000000..d99233c8008a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ints(void *ctx) +{ + struct core_reloc_ints *in = (void *)&data.in; + struct core_reloc_ints *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->u8_field, &in->u8_field) || + BPF_CORE_READ(&out->s8_field, &in->s8_field) || + BPF_CORE_READ(&out->u16_field, &in->u16_field) || + BPF_CORE_READ(&out->s16_field, &in->s16_field) || + BPF_CORE_READ(&out->u32_field, &in->u32_field) || + BPF_CORE_READ(&out->s32_field, &in->s32_field) || + BPF_CORE_READ(&out->u64_field, &in->u64_field) || + BPF_CORE_READ(&out->s64_field, &in->s64_field)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c new file mode 100644 index 000000000000..37e02aa3f0c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct task_struct { + int pid; + int tgid; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_kernel(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + int pid, tgid; + + if (BPF_CORE_READ(&pid, &task->pid) || + BPF_CORE_READ(&tgid, &task->tgid)) + return 1; + + /* validate pid + tgid matches */ + data.out[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c new file mode 100644 index 000000000000..c59984bd3e23 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* fixed two first members, can be extended with new fields */ +struct core_reloc_misc_extensible { + int a; + int b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_misc(void *ctx) +{ + struct core_reloc_misc___a *in_a = (void *)&data.in; + struct core_reloc_misc___b *in_b = (void *)&data.in; + struct core_reloc_misc_extensible *in_ext = (void *)&data.in; + struct core_reloc_misc_output *out = (void *)&data.out; + + /* record two different relocations with the same accessor string */ + if (BPF_CORE_READ(&out->a, &in_a->a1) || /* accessor: 0:0 */ + BPF_CORE_READ(&out->b, &in_b->b1)) /* accessor: 0:0 */ + return 1; + + /* Validate relocations capture array-only accesses for structs with + * fixed header, but with potentially extendable tail. This will read + * first 4 bytes of 2nd element of in_ext array of potentially + * variably sized struct core_reloc_misc_extensible. */ + if (BPF_CORE_READ(&out->c, &in_ext[2])) /* accessor: 2 */ + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c new file mode 100644 index 000000000000..f98b942c062b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_mods(void *ctx) +{ + struct core_reloc_mods *in = (void *)&data.in; + struct core_reloc_mods_output *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->e, &in->e[2]) || + BPF_CORE_READ(&out->f, &in->f[1]) || + BPF_CORE_READ(&out->g, &in->g.x) || + BPF_CORE_READ(&out->h, &in->h.y)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c new file mode 100644 index 000000000000..3ca30cec2b39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +/* int a.a.a and b.b.b accesses */ +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_nesting(void *ctx) +{ + struct core_reloc_nesting *in = (void *)&data.in; + struct core_reloc_nesting *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a.a.a, &in->a.a.a)) + return 1; + if (BPF_CORE_READ(&out->b.b.b, &in->b.b.b)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c new file mode 100644 index 000000000000..add52f23ab35 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_primitives(void *ctx) +{ + struct core_reloc_primitives *in = (void *)&data.in; + struct core_reloc_primitives *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->f, &in->f)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..526b7ddc7ea1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ptr_as_arr { + int a; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ptr_as_arr(void *ctx) +{ + struct core_reloc_ptr_as_arr *in = (void *)&data.in; + struct core_reloc_ptr_as_arr *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in[2].a)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 33254b771384..f8ffa3f3d44b 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -55,7 +55,7 @@ struct { __type(value, raw_stack_trace_t); } rawdata_map SEC(".maps"); -SEC("tracepoint/raw_syscalls/sys_enter") +SEC("raw_tracepoint/sys_enter") int bpf_prog1(void *ctx) { int max_len, max_buildid_len, usize, ksize, total_size; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index a334a0e882e4..41a3ebcd593d 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -12,10 +12,6 @@ #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 { @@ -276,8 +272,8 @@ int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh) return 0; // check if egress TLV value is correct - if (ntohll(egr_addr.hi) == 0xfd00000000000000 && - ntohll(egr_addr.lo) == 0x4) + if (bpf_be64_to_cpu(egr_addr.hi) == 0xfd00000000000000 && + bpf_be64_to_cpu(egr_addr.lo) == 0x4) return 1; } @@ -308,8 +304,8 @@ int __encap_srh(struct __sk_buff *skb) #pragma clang loop unroll(full) for (unsigned long long lo = 0; lo < 4; lo++) { - seg->lo = htonll(4 - lo); - seg->hi = htonll(hi); + seg->lo = bpf_cpu_to_be64(4 - lo); + seg->hi = bpf_cpu_to_be64(hi); seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg)); } @@ -349,8 +345,8 @@ int __add_egr_x(struct __sk_buff *skb) if (err) return BPF_DROP; - addr.lo = htonll(lo); - addr.hi = htonll(hi); + addr.lo = bpf_cpu_to_be64(lo); + addr.hi = bpf_cpu_to_be64(hi); err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, (void *)&addr, sizeof(addr)); if (err) diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index 1dbe1d4d467e..c4d104428643 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -12,10 +12,6 @@ #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 { @@ -251,8 +247,8 @@ int __add_egr_x(struct __sk_buff *skb) if (err) return BPF_DROP; - addr.lo = htonll(lo); - addr.hi = htonll(hi); + addr.lo = bpf_cpu_to_be64(lo); + addr.hi = bpf_cpu_to_be64(hi); err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, (void *)&addr, sizeof(addr)); if (err) diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index 3af64c470d64..0961415ba477 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -2,6 +2,7 @@ #include <stdint.h> #include <linux/bpf.h> #include <linux/if_ether.h> +#include <linux/stddef.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/pkt_cls.h> diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 1ab095bcacd8..d8803dfa8d32 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -19,10 +19,29 @@ struct bpf_map_def SEC("maps") results = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = 1, + .value_size = sizeof(__u32), + .max_entries = 3, }; +static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, + void *iph, __u32 ip_size, + struct tcphdr *tcph) +{ + __u32 thlen = tcph->doff * 4; + + if (tcph->syn && !tcph->ack) { + // packet should only have an MSS option + if (thlen != 24) + return 0; + + if ((void *)tcph + thlen > data_end) + return 0; + + return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen); + } + return 0; +} + static __always_inline void check_syncookie(void *ctx, void *data, void *data_end) { @@ -33,8 +52,10 @@ static __always_inline void check_syncookie(void *ctx, void *data, struct ipv6hdr *ipv6h; struct tcphdr *tcph; int ret; + __u32 key_mss = 2; + __u32 key_gen = 1; __u32 key = 0; - __u64 value = 1; + __s64 seq_mss; ethh = data; if (ethh + 1 > data_end) @@ -66,6 +87,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h), tcph, sizeof(*tcph)); break; @@ -95,6 +119,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h), tcph, sizeof(*tcph)); break; @@ -103,8 +130,19 @@ static __always_inline void check_syncookie(void *ctx, void *data, return; } - if (ret == 0) - bpf_map_update_elem(&results, &key, &value, 0); + if (seq_mss > 0) { + __u32 cookie = (__u32)seq_mss; + __u32 mss = seq_mss >> 32; + + bpf_map_update_elem(&results, &key_gen, &cookie, 0); + bpf_map_update_elem(&results, &key_mss, &mss, 0); + } + + if (ret == 0) { + __u32 cookie = bpf_ntohl(tcph->ack_seq) - 1; + + bpf_map_update_elem(&results, &key, &cookie, 0); + } release: bpf_sk_release(sk); diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh new file mode 100755 index 000000000000..4ba5a34bff56 --- /dev/null +++ b/tools/testing/selftests/bpf/test_bpftool_build.sh @@ -0,0 +1,143 @@ +#!/bin/bash +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +ERROR=0 +TMPDIR= + +# If one build fails, continue but return non-0 on exit. +return_value() { + if [ -d "$TMPDIR" ] ; then + rm -rf -- $TMPDIR + fi + exit $ERROR +} +trap return_value EXIT + +case $1 in + -h|--help) + echo -e "$0 [-j <n>]" + echo -e "\tTest the different ways of building bpftool." + echo -e "" + echo -e "\tOptions:" + echo -e "\t\t-j <n>:\tPass -j flag to 'make'." + exit + ;; +esac + +J=$* + +# Assume script is located under tools/testing/selftests/bpf/. We want to start +# build attempts from the top of kernel repository. +SCRIPT_REL_PATH=$(realpath --relative-to=$PWD $0) +SCRIPT_REL_DIR=$(dirname $SCRIPT_REL_PATH) +KDIR_ROOT_DIR=$(realpath $PWD/$SCRIPT_REL_DIR/../../../../) +cd $KDIR_ROOT_DIR + +check() { + local dir=$(realpath $1) + + echo -n "binary: " + # Returns non-null if file is found (and "false" is run) + find $dir -type f -executable -name bpftool -print -exec false {} + && \ + ERROR=1 && printf "FAILURE: Did not find bpftool\n" +} + +make_and_clean() { + echo -e "\$PWD: $PWD" + echo -e "command: make -s $* >/dev/null" + make $J -s $* >/dev/null + if [ $? -ne 0 ] ; then + ERROR=1 + fi + if [ $# -ge 1 ] ; then + check ${@: -1} + else + check . + fi + ( + if [ $# -ge 1 ] ; then + cd ${@: -1} + fi + make -s clean + ) + echo +} + +make_with_tmpdir() { + local ARGS + + TMPDIR=$(mktemp -d) + if [ $# -ge 2 ] ; then + ARGS=${@:1:(($# - 1))} + fi + echo -e "\$PWD: $PWD" + echo -e "command: make -s $ARGS ${@: -1}=$TMPDIR/ >/dev/null" + make $J -s $ARGS ${@: -1}=$TMPDIR/ >/dev/null + if [ $? -ne 0 ] ; then + ERROR=1 + fi + check $TMPDIR + rm -rf -- $TMPDIR + echo +} + +echo "Trying to build bpftool" +echo -e "... through kbuild\n" + +if [ -f ".config" ] ; then + make_and_clean tools/bpf + + ## $OUTPUT is overwritten in kbuild Makefile, and thus cannot be passed + ## down from toplevel Makefile to bpftool's Makefile. + + # make_with_tmpdir tools/bpf OUTPUT + echo -e "skip: make tools/bpf OUTPUT=<dir> (not supported)\n" + + make_with_tmpdir tools/bpf O +else + echo -e "skip: make tools/bpf (no .config found)\n" + echo -e "skip: make tools/bpf OUTPUT=<dir> (not supported)\n" + echo -e "skip: make tools/bpf O=<dir> (no .config found)\n" +fi + +echo -e "... from kernel source tree\n" + +make_and_clean -C tools/bpf/bpftool + +make_with_tmpdir -C tools/bpf/bpftool OUTPUT + +make_with_tmpdir -C tools/bpf/bpftool O + +echo -e "... from tools/\n" +cd tools/ + +make_and_clean bpf + +## In tools/bpf/Makefile, function "descend" is called and passes $(O) and +## $(OUTPUT). We would like $(OUTPUT) to have "bpf/bpftool/" appended before +## calling bpftool's Makefile, but this is not the case as the "descend" +## function focuses on $(O)/$(subdir). However, in the present case, updating +## $(O) to have $(OUTPUT) recomputed from it in bpftool's Makefile does not +## work, because $(O) is not defined from command line and $(OUTPUT) is not +## updated in tools/scripts/Makefile.include. +## +## Workarounds would require to a) edit "descend" or use an alternative way to +## call bpftool's Makefile, b) modify the conditions to update $(OUTPUT) and +## other variables in tools/scripts/Makefile.include (at the risk of breaking +## the build of other tools), or c) append manually the "bpf/bpftool" suffix to +## $(OUTPUT) in bpf's Makefile, which may break if targets for other directories +## use "descend" in the future. + +# make_with_tmpdir bpf OUTPUT +echo -e "skip: make bpf OUTPUT=<dir> (not supported)\n" + +make_with_tmpdir bpf O + +echo -e "... from bpftool's dir\n" +cd bpf/bpftool + +make_and_clean + +make_with_tmpdir OUTPUT + +make_with_tmpdir O diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 5443b9bd75ed..e1f1becda529 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -508,6 +508,21 @@ static void test_devmap(unsigned int task, void *data) close(fd); } +static void test_devmap_hash(unsigned int task, void *data) +{ + int fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create devmap_hash '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + static void test_queuemap(unsigned int task, void *data) { const int MAP_SIZE = 32; @@ -1684,6 +1699,7 @@ static void run_all_tests(void) test_arraymap_percpu_many_keys(); test_devmap(0, NULL); + test_devmap_hash(0, NULL); test_sockmap(0, NULL); test_map_large(); diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 425f9ed27c3b..15a666329a34 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -1353,7 +1353,7 @@ try: bpftool_prog_list_wait(expected=1) ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"] - fail(ifnameB != simB1['ifname'], "program not bound to originial device") + fail(ifnameB != simB1['ifname'], "program not bound to original device") simB1.remove() bpftool_prog_list_wait(expected=1) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index dae0819b1141..af75a1c7a458 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -2,11 +2,160 @@ /* Copyright (c) 2017 Facebook */ #include "test_progs.h" +#include "cgroup_helpers.h" #include "bpf_rlimit.h" +#include <argp.h> +#include <string.h> -int error_cnt, pass_cnt; -bool jit_enabled; -bool verifier_stats = false; +/* defined in test_progs.h */ +struct test_env env; + +struct prog_test_def { + const char *test_name; + int test_num; + void (*run_test)(void); + bool force_log; + int error_cnt; + int skip_cnt; + bool tested; + bool need_cgroup_cleanup; + + const char *subtest_name; + int subtest_num; + + /* store counts before subtest started */ + int old_error_cnt; +}; + +static bool should_run(struct test_selector *sel, int num, const char *name) +{ + if (sel->name && sel->name[0] && !strstr(name, sel->name)) + return false; + + if (!sel->num_set) + return true; + + return num < sel->num_set_len && sel->num_set[num]; +} + +static void dump_test_log(const struct prog_test_def *test, bool failed) +{ + if (stdout == env.stdout) + return; + + fflush(stdout); /* exports env.log_buf & env.log_cnt */ + + if (env.verbose || test->force_log || failed) { + if (env.log_cnt) { + env.log_buf[env.log_cnt] = '\0'; + fprintf(env.stdout, "%s", env.log_buf); + if (env.log_buf[env.log_cnt - 1] != '\n') + fprintf(env.stdout, "\n"); + } + } + + fseeko(stdout, 0, SEEK_SET); /* rewind */ +} + +static void skip_account(void) +{ + if (env.test->skip_cnt) { + env.skip_cnt++; + env.test->skip_cnt = 0; + } +} + +void test__end_subtest() +{ + struct prog_test_def *test = env.test; + int sub_error_cnt = test->error_cnt - test->old_error_cnt; + + if (sub_error_cnt) + env.fail_cnt++; + else + env.sub_succ_cnt++; + skip_account(); + + dump_test_log(test, sub_error_cnt); + + fprintf(env.stdout, "#%d/%d %s:%s\n", + test->test_num, test->subtest_num, + test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); +} + +bool test__start_subtest(const char *name) +{ + struct prog_test_def *test = env.test; + + if (test->subtest_name) { + test__end_subtest(); + test->subtest_name = NULL; + } + + test->subtest_num++; + + if (!name || !name[0]) { + fprintf(env.stderr, + "Subtest #%d didn't provide sub-test name!\n", + test->subtest_num); + return false; + } + + if (!should_run(&env.subtest_selector, test->subtest_num, name)) + return false; + + test->subtest_name = name; + env.test->old_error_cnt = env.test->error_cnt; + + return true; +} + +void test__force_log() { + env.test->force_log = true; +} + +void test__skip(void) +{ + env.test->skip_cnt++; +} + +void test__fail(void) +{ + env.test->error_cnt++; +} + +int test__join_cgroup(const char *path) +{ + int fd; + + if (!env.test->need_cgroup_cleanup) { + if (setup_cgroup_environment()) { + fprintf(stderr, + "#%d %s: Failed to setup cgroup environment\n", + env.test->test_num, env.test->test_name); + return -1; + } + + env.test->need_cgroup_cleanup = true; + } + + fd = create_and_get_cgroup(path); + if (fd < 0) { + fprintf(stderr, + "#%d %s: Failed to create cgroup '%s' (errno=%d)\n", + env.test->test_num, env.test->test_name, path, errno); + return fd; + } + + if (join_cgroup(path)) { + fprintf(stderr, + "#%d %s: Failed to join cgroup '%s' (errno=%d)\n", + env.test->test_num, env.test->test_name, path, errno); + return -1; + } + + return fd; +} struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -32,7 +181,7 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) map = bpf_object__find_map_by_name(obj, name); if (!map) { printf("%s:FAIL:map '%s' not found\n", test, name); - error_cnt++; + test__fail(); return -1; } return bpf_map__fd(map); @@ -156,23 +305,276 @@ void *spin_lock_thread(void *arg) pthread_exit(arg); } -#define DECLARE +/* extern declarations for test funcs */ +#define DEFINE_TEST(name) extern void test_##name(); #include <prog_tests/tests.h> -#undef DECLARE +#undef DEFINE_TEST + +static struct prog_test_def prog_test_defs[] = { +#define DEFINE_TEST(name) { \ + .test_name = #name, \ + .run_test = &test_##name, \ +}, +#include <prog_tests/tests.h> +#undef DEFINE_TEST +}; +const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); + +const char *argp_program_version = "test_progs 0.1"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = "BPF selftests test runner"; + +enum ARG_KEYS { + ARG_TEST_NUM = 'n', + ARG_TEST_NAME = 't', + ARG_VERIFIER_STATS = 's', + ARG_VERBOSE = 'v', +}; + +static const struct argp_option opts[] = { + { "num", ARG_TEST_NUM, "NUM", 0, + "Run test number NUM only " }, + { "name", ARG_TEST_NAME, "NAME", 0, + "Run tests with names containing NAME" }, + { "verifier-stats", ARG_VERIFIER_STATS, NULL, 0, + "Output verifier statistics", }, + { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, + "Verbose output (use -vv for extra verbose output)" }, + {}, +}; -int main(int ac, char **av) +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) { + if (!env.very_verbose && level == LIBBPF_DEBUG) + return 0; + vprintf(format, args); + return 0; +} + +int parse_num_list(const char *s, struct test_selector *sel) +{ + int i, set_len = 0, num, start = 0, end = -1; + bool *set = NULL, *tmp, parsing_end = false; + char *next; + + while (s[0]) { + errno = 0; + num = strtol(s, &next, 10); + if (errno) + return -errno; + + if (parsing_end) + end = num; + else + start = num; + + if (!parsing_end && *next == '-') { + s = next + 1; + parsing_end = true; + continue; + } else if (*next == ',') { + parsing_end = false; + s = next + 1; + end = num; + } else if (*next == '\0') { + parsing_end = false; + s = next; + end = num; + } else { + return -EINVAL; + } + + if (start > end) + return -EINVAL; + + if (end + 1 > set_len) { + set_len = end + 1; + tmp = realloc(set, set_len); + if (!tmp) { + free(set); + return -ENOMEM; + } + set = tmp; + } + for (i = start; i <= end; i++) { + set[i] = true; + } + + } + + if (!set) + return -EINVAL; + + sel->num_set = set; + sel->num_set_len = set_len; + + return 0; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + struct test_env *env = state->input; + + switch (key) { + case ARG_TEST_NUM: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + if (parse_num_list(subtest_str + 1, + &env->subtest_selector)) { + fprintf(stderr, + "Failed to parse subtest numbers.\n"); + return -EINVAL; + } + } + if (parse_num_list(arg, &env->test_selector)) { + fprintf(stderr, "Failed to parse test numbers.\n"); + return -EINVAL; + } + break; + } + case ARG_TEST_NAME: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + env->subtest_selector.name = strdup(subtest_str + 1); + if (!env->subtest_selector.name) + return -ENOMEM; + } + env->test_selector.name = strdup(arg); + if (!env->test_selector.name) + return -ENOMEM; + break; + } + case ARG_VERIFIER_STATS: + env->verifier_stats = true; + break; + case ARG_VERBOSE: + if (arg) { + if (strcmp(arg, "v") == 0) { + env->very_verbose = true; + } else { + fprintf(stderr, + "Unrecognized verbosity setting ('%s'), only -v and -vv are supported\n", + arg); + return -EINVAL; + } + } + env->verbose = true; + break; + case ARGP_KEY_ARG: + argp_usage(state); + break; + case ARGP_KEY_END: + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +static void stdio_hijack(void) +{ +#ifdef __GLIBC__ + env.stdout = stdout; + env.stderr = stderr; + + if (env.verbose) { + /* nothing to do, output to stdout by default */ + return; + } + + /* stdout and stderr -> buffer */ + fflush(stdout); + + stdout = open_memstream(&env.log_buf, &env.log_cnt); + if (!stdout) { + stdout = env.stdout; + perror("open_memstream"); + return; + } + + stderr = stdout; +#endif +} + +static void stdio_restore(void) +{ +#ifdef __GLIBC__ + if (stdout == env.stdout) + return; + + fclose(stdout); + free(env.log_buf); + + env.log_buf = NULL; + env.log_cnt = 0; + + stdout = env.stdout; + stderr = env.stderr; +#endif +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + int err, i; + + err = argp_parse(&argp, argc, argv, 0, NULL, &env); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + srand(time(NULL)); - jit_enabled = is_jit_enabled(); + env.jit_enabled = is_jit_enabled(); - if (ac == 2 && strcmp(av[1], "-s") == 0) - verifier_stats = true; + stdio_hijack(); + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test = &prog_test_defs[i]; -#define CALL -#include <prog_tests/tests.h> -#undef CALL + env.test = test; + test->test_num = i + 1; + + if (!should_run(&env.test_selector, + test->test_num, test->test_name)) + continue; + + test->run_test(); + /* ensure last sub-test is finalized properly */ + if (test->subtest_name) + test__end_subtest(); + + test->tested = true; + if (test->error_cnt) + env.fail_cnt++; + else + env.succ_cnt++; + skip_account(); + + dump_test_log(test, test->error_cnt); + + fprintf(env.stdout, "#%d %s:%s\n", + test->test_num, test->test_name, + test->error_cnt ? "FAIL" : "OK"); + + if (test->need_cgroup_cleanup) + cleanup_cgroup_environment(); + } + stdio_restore(); + printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", + env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + + free(env.test_selector.num_set); + free(env.subtest_selector.num_set); - printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); - return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; + return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 49e0f7d85643..0c48f64f732b 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -16,9 +16,10 @@ typedef __u16 __sum16; #include <linux/if_packet.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/tcp.h> +#include <netinet/tcp.h> #include <linux/filter.h> #include <linux/perf_event.h> +#include <linux/socket.h> #include <linux/unistd.h> #include <sys/ioctl.h> @@ -38,9 +39,40 @@ typedef __u16 __sum16; #include "trace_helpers.h" #include "flow_dissector_load.h" -extern int error_cnt, pass_cnt; -extern bool jit_enabled; -extern bool verifier_stats; +struct test_selector { + const char *name; + bool *num_set; + int num_set_len; +}; + +struct test_env { + struct test_selector test_selector; + struct test_selector subtest_selector; + bool verifier_stats; + bool verbose; + bool very_verbose; + + bool jit_enabled; + + struct prog_test_def *test; + FILE *stdout; + FILE *stderr; + char *log_buf; + size_t log_cnt; + + int succ_cnt; /* successful tests */ + int sub_succ_cnt; /* successful sub-tests */ + int fail_cnt; /* total failed tests + sub-tests */ + int skip_cnt; /* skipped tests */ +}; + +extern struct test_env env; + +extern void test__force_log(); +extern bool test__start_subtest(const char *name); +extern void test__skip(void); +extern void test__fail(void); +extern int test__join_cgroup(const char *path); #define MAGIC_BYTES 123 @@ -63,12 +95,21 @@ extern struct ipv6_packet pkt_v6; #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ if (__ret) { \ - error_cnt++; \ + test__fail(); \ printf("%s:FAIL:%s ", __func__, tag); \ printf(format); \ } else { \ - pass_cnt++; \ - printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ + printf("%s:PASS:%s %d nsec\n", \ + __func__, tag, duration); \ + } \ + __ret; \ +}) + +#define CHECK_FAIL(condition) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + test__fail(); \ + printf("%s:FAIL:%d\n", __func__, __LINE__); \ } \ __ret; \ }) diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index a3bebd7c68dd..4f8ec1f10a80 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -13,6 +13,7 @@ #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include "bpf_endian.h" #include "bpf_rlimit.h" #include "bpf_util.h" #include "cgroup_helpers.h" @@ -31,6 +32,7 @@ struct sysctl_test { enum bpf_attach_type attach_type; const char *sysctl; int open_flags; + int seek; const char *newval; const char *oldval; enum { @@ -100,7 +102,7 @@ static struct sysctl_test tests[] = { .descr = "ctx:write sysctl:write read ok", .insns = { /* If (write) */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, write)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2), @@ -139,7 +141,7 @@ static struct sysctl_test tests[] = { /* If (file_pos == X) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 3, 2), /* return ALLOW; */ BPF_MOV64_IMM(BPF_REG_0, 1), @@ -152,6 +154,7 @@ static struct sysctl_test tests[] = { .attach_type = BPF_CGROUP_SYSCTL, .sysctl = "kernel/ostype", .open_flags = O_RDONLY, + .seek = 3, .result = SUCCESS, }, { @@ -214,7 +217,8 @@ static struct sysctl_test tests[] = { /* if (ret == expected && */ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, sizeof("tcp_mem") - 1, 6), /* buf == "tcp_mem\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x006d656d5f706374ULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x7463705f6d656d00ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -255,7 +259,8 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), /* buf[0:7] == "tcp_me\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x00656d5f706374ULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x7463705f6d650000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -298,12 +303,14 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 16, 14), /* buf[0:8] == "net/ipv4" && */ - BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x6e65742f69707634ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10), /* buf[8:16] == "/tcp_mem" && */ - BPF_LD_IMM64(BPF_REG_8, 0x6d656d5f7063742fULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x2f7463705f6d656dULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), @@ -350,12 +357,14 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 10), /* buf[0:8] == "net/ipv4" && */ - BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x6e65742f69707634ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), /* buf[8:16] == "/tcp_me\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x00656d5f7063742fULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x2f7463705f6d6500ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -396,7 +405,8 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), /* buf[0:8] == "net/ip\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x000070692f74656eULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x6e65742f69700000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -431,7 +441,8 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6), /* buf[0:6] == "Linux\n\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x4c696e75780a0000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -469,7 +480,8 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6), /* buf[0:6] == "Linux\n\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x4c696e75780a0000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -507,7 +519,8 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), /* buf[0:6] == "Linux\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x000078756e694cULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x4c696e7578000000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -650,7 +663,8 @@ static struct sysctl_test tests[] = { /* buf[0:4] == "606\0") */ BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0), - BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x00363036, 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, + bpf_ntohl(0x36303600), 2), /* return DENY; */ BPF_MOV64_IMM(BPF_REG_0, 0), @@ -685,17 +699,20 @@ static struct sysctl_test tests[] = { BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 23, 14), /* buf[0:8] == "3000000 " && */ - BPF_LD_IMM64(BPF_REG_8, 0x2030303030303033ULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x3330303030303020ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10), /* buf[8:16] == "4000000 " && */ - BPF_LD_IMM64(BPF_REG_8, 0x2030303030303034ULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x3430303030303020ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), /* buf[16:24] == "6000000\0") */ - BPF_LD_IMM64(BPF_REG_8, 0x0030303030303036ULL), + BPF_LD_IMM64(BPF_REG_8, + bpf_be64_to_cpu(0x3630303030303000ULL)), BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16), BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), @@ -735,7 +752,8 @@ static struct sysctl_test tests[] = { /* buf[0:3] == "60\0") */ BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0), - BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x003036, 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, + bpf_ntohl(0x36300000), 2), /* return DENY; */ BPF_MOV64_IMM(BPF_REG_0, 0), @@ -757,7 +775,8 @@ static struct sysctl_test tests[] = { /* sysctl_set_new_value arg2 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x36303000)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), @@ -791,7 +810,7 @@ static struct sysctl_test tests[] = { /* sysctl_set_new_value arg2 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, FIXUP_SYSCTL_VALUE), + BPF_LD_IMM64(BPF_REG_0, FIXUP_SYSCTL_VALUE), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), @@ -825,8 +844,9 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00303036), - BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x36303000)), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -869,7 +889,8 @@ static struct sysctl_test tests[] = { BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), /* "600 602\0" */ - BPF_LD_IMM64(BPF_REG_0, 0x0032303620303036ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3630302036303200ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -937,7 +958,8 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x36303000)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -969,8 +991,9 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00373730), - BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x30373700)), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1012,7 +1035,8 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x36303000)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1052,7 +1076,8 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x090a0c0d), + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x0d0c0a09)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1092,7 +1117,9 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */ + /* " -6\0" */ + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x0a2d3600)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1132,8 +1159,10 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */ - BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + /* " -6\0" */ + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x0a2d3600)), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1175,8 +1204,10 @@ static struct sysctl_test tests[] = { /* arg1 (buf) */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), - BPF_MOV64_IMM(BPF_REG_0, 0x65667830), /* "0xfe" */ - BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + /* "0xfe" */ + BPF_MOV64_IMM(BPF_REG_0, + bpf_ntohl(0x30786665)), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1218,11 +1249,14 @@ static struct sysctl_test tests[] = { /* arg1 (buf) 9223372036854775807 */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), - BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3932323333373230ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), - BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3336383534373735ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), - BPF_LD_IMM64(BPF_REG_0, 0x0000000000373038ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3830370000000000ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1266,11 +1300,14 @@ static struct sysctl_test tests[] = { /* arg1 (buf) 9223372036854775808 */ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), - BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3932323333373230ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), - BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3336383534373735ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), - BPF_LD_IMM64(BPF_REG_0, 0x0000000000383038ULL), + BPF_LD_IMM64(BPF_REG_0, + bpf_be64_to_cpu(0x3830380000000000ULL)), BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), @@ -1344,20 +1381,24 @@ static size_t probe_prog_length(const struct bpf_insn *fp) static int fixup_sysctl_value(const char *buf, size_t buf_len, struct bpf_insn *prog, size_t insn_num) { - uint32_t value_num = 0; + union { + uint8_t raw[sizeof(uint64_t)]; + uint64_t num; + } value = {}; uint8_t c, i; - if (buf_len > sizeof(value_num)) { + if (buf_len > sizeof(value)) { log_err("Value is too big (%zd) to use in fixup", buf_len); return -1; } - - for (i = 0; i < buf_len; ++i) { - c = buf[i]; - value_num |= (c << i * 8); + if (prog[insn_num].code != (BPF_LD | BPF_DW | BPF_IMM)) { + log_err("Can fixup only BPF_LD_IMM64 insns"); + return -1; } - prog[insn_num].imm = value_num; + memcpy(value.raw, buf, buf_len); + prog[insn_num].imm = (uint32_t)value.num; + prog[insn_num + 1].imm = (uint32_t)(value.num >> 32); return 0; } @@ -1442,6 +1483,11 @@ static int access_sysctl(const char *sysctl_path, if (fd < 0) return fd; + if (test->seek && lseek(fd, test->seek, SEEK_SET) == -1) { + log_err("lseek(%d) failed", test->seek); + goto err; + } + if (test->open_flags == O_RDONLY) { char buf[128]; @@ -1499,6 +1545,7 @@ static int run_test_case(int cgfd, struct sysctl_test *test) goto err; } + errno = 0; if (access_sysctl(sysctl_path, test) == -1) { if (test->result == OP_EPERM && errno == EPERM) goto out; @@ -1507,7 +1554,7 @@ static int run_test_case(int cgfd, struct sysctl_test *test) } if (test->result != SUCCESS) { - log_err("Unexpected failure"); + log_err("Unexpected success"); goto err; } diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index d48e51716d19..9b3617d770a5 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -37,6 +37,9 @@ setup() ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 + ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0 + ns1_exec sysctl -w net.ipv4.tcp_timestamps=0 + ns1_exec sysctl -w net.ipv4.tcp_sack=0 wait_for_ip 127.0.0.1 wait_for_ip ::1 diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 87829c86c746..b9e991d43155 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -2,6 +2,7 @@ // Copyright (c) 2018 Facebook // Copyright (c) 2019 Cloudflare +#include <limits.h> #include <string.h> #include <stdlib.h> #include <unistd.h> @@ -77,7 +78,7 @@ out: return fd; } -static int get_map_fd_by_prog_id(int prog_id) +static int get_map_fd_by_prog_id(int prog_id, bool *xdp) { struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); @@ -104,6 +105,8 @@ static int get_map_fd_by_prog_id(int prog_id) goto err; } + *xdp = info.type == BPF_PROG_TYPE_XDP; + map_fd = bpf_map_get_fd_by_id(map_ids[0]); if (map_fd < 0) log_err("Failed to get fd by map id %d", map_ids[0]); @@ -113,18 +116,32 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd) +static int run_test(int server_fd, int results_fd, bool xdp) { int client = -1, srv_client = -1; int ret = 0; __u32 key = 0; - __u64 value = 0; + __u32 key_gen = 1; + __u32 key_mss = 2; + __u32 value = 0; + __u32 value_gen = 0; + __u32 value_mss = 0; if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) { log_err("Can't clear results"); goto err; } + if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + + if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + client = connect_to_server(server_fd); if (client == -1) goto err; @@ -140,8 +157,35 @@ static int run_test(int server_fd, int results_fd) goto err; } - if (value != 1) { - log_err("Didn't match syncookie: %llu", value); + if (value == 0) { + log_err("Didn't match syncookie: %u", value); + goto err; + } + + if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (xdp && value_gen == 0) { + // SYN packets do not get passed through generic XDP, skip the + // rest of the test. + printf("Skipping XDP cookie check\n"); + goto out; + } + + if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (value != value_gen) { + log_err("BPF generated cookie does not match kernel one"); + goto err; + } + + if (value_mss < 536 || value_mss > USHRT_MAX) { + log_err("Unexpected MSS retrieved"); goto err; } @@ -163,13 +207,14 @@ int main(int argc, char **argv) int server_v6 = -1; int results = -1; int err = 0; + bool xdp; if (argc < 2) { fprintf(stderr, "Usage: %s prog_id\n", argv[0]); exit(1); } - results = get_map_fd_by_prog_id(atoi(argv[1])); + results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp); if (results < 0) { log_err("Can't get map"); goto err; @@ -194,10 +239,10 @@ int main(int argc, char **argv) if (server_v6 == -1) goto err; - if (run_test(server, results)) + if (run_test(server, results, xdp)) goto err; - if (run_test(server_v6, results)) + if (run_test(server_v6, results, xdp)) goto err; printf("ok\n"); diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 86152d9ae95b..f9765ddf0761 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -17,6 +17,7 @@ #include <linux/rtnetlink.h> #include <signal.h> #include <linux/perf_event.h> +#include <linux/err.h> #include "bpf_rlimit.h" #include "bpf_util.h" @@ -30,28 +31,34 @@ pthread_t tid; int rx_callbacks; -static int dummyfn(void *data, int size) +static void dummyfn(void *ctx, int cpu, void *data, __u32 size) { struct tcp_notifier *t = data; if (t->type != 0xde || t->subtype != 0xad || t->source != 0xbe || t->hash != 0xef) - return 1; + return; rx_callbacks++; - return 0; } -void tcp_notifier_poller(int fd) +void tcp_notifier_poller(struct perf_buffer *pb) { - while (1) - perf_event_poller(fd, dummyfn); + int err; + + while (1) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && err != -EINTR) { + printf("failed perf_buffer__poll: %d\n", err); + return; + } + } } static void *poller_thread(void *arg) { - int fd = *(int *)arg; + struct perf_buffer *pb = arg; - tcp_notifier_poller(fd); + tcp_notifier_poller(pb); return arg; } @@ -60,52 +67,20 @@ int verify_result(const struct tcpnotify_globals *result) return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1); } -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) { - printf("%s:FAIL:map '%s' not found\n", test, name); - return -1; - } - return bpf_map__fd(map); -} - -static int setup_bpf_perf_event(int mapfd) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - int pmu_fd; - - pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0); - if (pmu_fd < 0) - return pmu_fd; - bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY); - - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - return pmu_fd; -} - int main(int argc, char **argv) { const char *file = "test_tcpnotify_kern.o"; - int prog_fd, map_fd, perf_event_fd; + struct bpf_map *perf_map, *global_map; + struct perf_buffer_opts pb_opts = {}; struct tcpnotify_globals g = {0}; + struct perf_buffer *pb = NULL; const char *cg_path = "/foo"; + int prog_fd, rv, cg_fd = -1; int error = EXIT_FAILURE; struct bpf_object *obj; - int cg_fd = -1; - __u32 key = 0; - int rv; char test_script[80]; - int pmu_fd; cpu_set_t cpuset; + __u32 key = 0; CPU_ZERO(&cpuset); CPU_SET(0, &cpuset); @@ -133,19 +108,24 @@ int main(int argc, char **argv) goto err; } - perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map"); - if (perf_event_fd < 0) + perf_map = bpf_object__find_map_by_name(obj, "perf_event_map"); + if (!perf_map) { + printf("FAIL:map '%s' not found\n", "perf_event_map"); goto err; + } - map_fd = bpf_find_map(__func__, obj, "global_map"); - if (map_fd < 0) - goto err; + global_map = bpf_object__find_map_by_name(obj, "global_map"); + if (!global_map) { + printf("FAIL:map '%s' not found\n", "global_map"); + return -1; + } - pmu_fd = setup_bpf_perf_event(perf_event_fd); - if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = dummyfn; + pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts); + if (IS_ERR(pb)) goto err; - pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd); + pthread_create(&tid, NULL, poller_thread, pb); sprintf(test_script, "iptables -A INPUT -p tcp --dport %d -j DROP", @@ -162,7 +142,7 @@ int main(int argc, char **argv) TESTPORT); system(test_script); - rv = bpf_map_lookup_elem(map_fd, &key, &g); + rv = bpf_map_lookup_elem(bpf_map__fd(global_map), &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); goto err; @@ -182,5 +162,7 @@ err: bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); close(cg_fd); cleanup_cgroup_environment(); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); return error; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 84135d5f4b35..d27fd929abb9 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 18 +#define MAX_NR_MAPS 19 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -61,6 +61,7 @@ #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; static int skips; +static bool verbose = false; struct bpf_test { const char *descr; @@ -84,6 +85,7 @@ struct bpf_test { int fixup_map_array_wo[MAX_FIXUPS]; int fixup_map_array_small[MAX_FIXUPS]; int fixup_sk_storage_map[MAX_FIXUPS]; + int fixup_map_event_output[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -91,7 +93,8 @@ struct bpf_test { enum { UNDEF, ACCEPT, - REJECT + REJECT, + VERBOSE_ACCEPT, } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; @@ -632,6 +635,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_wo = test->fixup_map_array_wo; int *fixup_map_array_small = test->fixup_map_array_small; int *fixup_sk_storage_map = test->fixup_sk_storage_map; + int *fixup_map_event_output = test->fixup_map_event_output; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -793,6 +797,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_sk_storage_map++; } while (*fixup_sk_storage_map); } + if (*fixup_map_event_output) { + map_fds[18] = __create_map(BPF_MAP_TYPE_PERF_EVENT_ARRAY, + sizeof(int), sizeof(int), 1, 0); + do { + prog[*fixup_map_event_output].imm = map_fds[18]; + fixup_map_event_output++; + } while (*fixup_map_event_output); + } } static int set_admin(bool admin) @@ -849,6 +861,36 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, return 0; } +static bool cmp_str_seq(const char *log, const char *exp) +{ + char needle[80]; + const char *p, *q; + int len; + + do { + p = strchr(exp, '\t'); + if (!p) + p = exp + strlen(exp); + + len = p - exp; + if (len >= sizeof(needle) || !len) { + printf("FAIL\nTestcase bug\n"); + return false; + } + strncpy(needle, exp, len); + needle[len] = 0; + q = strstr(log, needle); + if (!q) { + printf("FAIL\nUnexpected verifier log in successful load!\n" + "EXP: %s\nRES:\n", needle); + return false; + } + log = q + len; + exp = p + 1; + } while (*p); + return true; +} + static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { @@ -887,14 +929,20 @@ static void do_test_single(struct bpf_test *test, bool unpriv, pflags |= BPF_F_STRICT_ALIGNMENT; if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) pflags |= BPF_F_ANY_ALIGNMENT; + if (test->flags & ~3) + pflags |= test->flags; + expected_ret = unpriv && test->result_unpriv != UNDEF ? + test->result_unpriv : test->result; + expected_err = unpriv && test->errstr_unpriv ? + test->errstr_unpriv : test->errstr; memset(&attr, 0, sizeof(attr)); attr.prog_type = prog_type; attr.expected_attach_type = test->expected_attach_type; attr.insns = prog; attr.insns_cnt = prog_len; attr.license = "GPL"; - attr.log_level = 4; + attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4; attr.prog_flags = pflags; fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); @@ -904,14 +952,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, goto close_fds; } - expected_ret = unpriv && test->result_unpriv != UNDEF ? - test->result_unpriv : test->result; - expected_err = unpriv && test->errstr_unpriv ? - test->errstr_unpriv : test->errstr; - alignment_prevented_execution = 0; - if (expected_ret == ACCEPT) { + if (expected_ret == ACCEPT || expected_ret == VERBOSE_ACCEPT) { if (fd_prog < 0) { printf("FAIL\nFailed to load prog '%s'!\n", strerror(errno)); @@ -922,6 +965,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)) alignment_prevented_execution = 1; #endif + if (expected_ret == VERBOSE_ACCEPT && !cmp_str_seq(bpf_vlog, expected_err)) { + goto fail_log; + } } else { if (fd_prog >= 0) { printf("FAIL\nUnexpected success to load!\n"); @@ -947,6 +993,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } } + if (verbose) + printf(", verifier log:\n%s", bpf_vlog); + run_errs = 0; run_successes = 0; if (!alignment_prevented_execution && fd_prog >= 0) { @@ -1087,17 +1136,24 @@ int main(int argc, char **argv) { unsigned int from = 0, to = ARRAY_SIZE(tests); bool unpriv = !is_admin(); + int arg = 1; + + if (argc > 1 && strcmp(argv[1], "-v") == 0) { + arg++; + verbose = true; + argc--; + } if (argc == 3) { - unsigned int l = atoi(argv[argc - 2]); - unsigned int u = atoi(argv[argc - 1]); + unsigned int l = atoi(argv[arg]); + unsigned int u = atoi(argv[arg + 1]); if (l < to && u < to) { from = l; to = u + 1; } } else if (argc == 2) { - unsigned int t = atoi(argv[argc - 1]); + unsigned int t = atoi(argv[arg]); if (t < to) { from = t; diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index b47f205f0310..7f989b3e4e22 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -86,128 +86,3 @@ long ksym_get_addr(const char *name) return 0; } - -static int page_size; -static int page_cnt = 8; -static struct perf_event_mmap_page *header; - -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header) -{ - 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; -} - -int perf_event_mmap(int fd) -{ - return perf_event_mmap_header(fd, &header); -} - -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(struct perf_event_header *hdr, void *private_data) -{ - struct perf_event_sample *e = (struct perf_event_sample *)hdr; - perf_event_print_fn fn = private_data; - 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; -} - -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn) -{ - enum bpf_perf_event_ret ret; - struct pollfd *pfds; - void *buf = NULL; - size_t len = 0; - int i; - - pfds = calloc(num_fds, sizeof(*pfds)); - if (!pfds) - return LIBBPF_PERF_EVENT_ERROR; - - for (i = 0; i < num_fds; i++) { - pfds[i].fd = fds[i]; - pfds[i].events = POLLIN; - } - - for (;;) { - poll(pfds, num_fds, 1000); - for (i = 0; i < num_fds; i++) { - if (!pfds[i].revents) - continue; - - ret = bpf_perf_event_read_simple(headers[i], - page_cnt * page_size, - page_size, &buf, &len, - bpf_perf_event_print, - output_fn); - if (ret != LIBBPF_PERF_EVENT_CONT) - break; - } - } - free(buf); - free(pfds); - - return ret; -} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 18924f23db1b..aa4dcfe18050 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -3,7 +3,6 @@ #define __TRACE_HELPER_H #include <libbpf.h> -#include <linux/perf_event.h> struct ksym { long addr; @@ -14,12 +13,4 @@ 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); -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header); -/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */ -int perf_event_poller(int fd, perf_event_print_fn output_fn); -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn); #endif diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c new file mode 100644 index 000000000000..130553e19eca --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -0,0 +1,94 @@ +/* instructions used to output a skb based software event, produced + * from code snippet: + * struct TMP { + * uint64_t tmp; + * } tt; + * tt.tmp = 5; + * bpf_perf_event_output(skb, &connection_tracking_event_map, 0, + * &tt, sizeof(tt)); + * return 1; + * + * the bpf assembly from llvm is: + * 0: b7 02 00 00 05 00 00 00 r2 = 5 + * 1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2 + * 2: bf a4 00 00 00 00 00 00 r4 = r10 + * 3: 07 04 00 00 f8 ff ff ff r4 += -8 + * 4: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0ll + * 6: b7 03 00 00 00 00 00 00 r3 = 0 + * 7: b7 05 00 00 08 00 00 00 r5 = 8 + * 8: 85 00 00 00 19 00 00 00 call 25 + * 9: b7 00 00 00 01 00 00 00 r0 = 1 + * 10: 95 00 00 00 00 00 00 00 exit + * + * The reason I put the code here instead of fill_helpers is that map fixup + * is against the insns, instead of filled prog. + */ + +#define __PERF_EVENT_INSNS__ \ + BPF_MOV64_IMM(BPF_REG_2, 5), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), \ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), \ + BPF_LD_MAP_FD(BPF_REG_2, 0), \ + BPF_MOV64_IMM(BPF_REG_3, 0), \ + BPF_MOV64_IMM(BPF_REG_5, 8), \ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, \ + BPF_FUNC_perf_event_output), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), +{ + "perfevent for sockops", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCK_OPS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for tc", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for lwt out", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_LWT_OUT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for xdp", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for socket filter", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for sk_skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c new file mode 100644 index 000000000000..02151f8c940f --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -0,0 +1,194 @@ +{ + "precise: test 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_FD(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), /* map_value_ptr -= map_value_ptr */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_9), + BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), + BPF_EXIT_INSN(), + + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_array_48b = { 1 }, + .result = VERBOSE_ACCEPT, + .errstr = + "26: (85) call bpf_probe_read#4\ + last_idx 26 first_idx 20\ + regs=4 stack=0 before 25\ + regs=4 stack=0 before 24\ + regs=4 stack=0 before 23\ + regs=4 stack=0 before 22\ + regs=4 stack=0 before 20\ + parent didn't have regs=4 stack=0 marks\ + last_idx 19 first_idx 10\ + regs=4 stack=0 before 19\ + regs=200 stack=0 before 18\ + regs=300 stack=0 before 17\ + regs=201 stack=0 before 15\ + regs=201 stack=0 before 14\ + regs=200 stack=0 before 13\ + regs=200 stack=0 before 12\ + regs=200 stack=0 before 11\ + regs=200 stack=0 before 10\ + parent already had regs=0 stack=0 marks", +}, +{ + "precise: test 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_FD(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), /* map_value_ptr -= map_value_ptr */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_9), + BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), + BPF_EXIT_INSN(), + + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_array_48b = { 1 }, + .result = VERBOSE_ACCEPT, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = + "26: (85) call bpf_probe_read#4\ + last_idx 26 first_idx 22\ + regs=4 stack=0 before 25\ + regs=4 stack=0 before 24\ + regs=4 stack=0 before 23\ + regs=4 stack=0 before 22\ + parent didn't have regs=4 stack=0 marks\ + last_idx 20 first_idx 20\ + regs=4 stack=0 before 20\ + parent didn't have regs=4 stack=0 marks\ + last_idx 19 first_idx 17\ + regs=4 stack=0 before 19\ + regs=200 stack=0 before 18\ + regs=300 stack=0 before 17\ + parent already had regs=0 stack=0 marks", +}, +{ + "precise: cross frame pruning", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_9, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "!read_ok", + .result = REJECT, +}, +{ + "precise: ST insn causing spi > allocated_stack", + .insns = { + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "5: (2d) if r4 > r0 goto pc+0\ + last_idx 5 first_idx 5\ + parent didn't have regs=10 stack=0 marks\ + last_idx 4 first_idx 2\ + regs=10 stack=0 before 4\ + regs=10 stack=0 before 3\ + regs=0 stack=1 before 2\ + last_idx 5 first_idx 5\ + parent didn't have regs=1 stack=0 marks", + .result = VERBOSE_ACCEPT, + .retval = -1, +}, +{ + "precise: STX insn causing spi > allocated_stack", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "last_idx 6 first_idx 6\ + parent didn't have regs=10 stack=0 marks\ + last_idx 5 first_idx 3\ + regs=10 stack=0 before 5\ + regs=10 stack=0 before 4\ + regs=0 stack=1 before 3\ + last_idx 6 first_idx 6\ + parent didn't have regs=1 stack=0 marks\ + last_idx 5 first_idx 3\ + regs=1 stack=0 before 5", + .result = VERBOSE_ACCEPT, + .retval = -1, +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh new file mode 100755 index 000000000000..89b55e946eed --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh @@ -0,0 +1,129 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test generic devlink-trap functionality over mlxsw. These tests are not +# specific to a single trap, but do not check the devlink-trap common +# infrastructure either. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + dev_del_test +" +NUM_NETIFS=4 +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 +} + +h2_destroy() +{ + simple_if_fini $h2 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +dev_del_test() +{ + local trap_name="source_mac_is_multicast" + local smac=01:02:03:04:05:06 + local num_iter=5 + local mz_pid + local i + + $MZ $h1 -c 0 -p 100 -a $smac -b bcast -t ip -q & + mz_pid=$! + + # The purpose of this test is to make sure we correctly dismantle a + # port while packets are trapped from it. This is done by reloading the + # the driver while the 'ingress_smac_mc_drop' trap is triggered. + RET=0 + + for i in $(seq 1 $num_iter); do + log_info "Iteration $i / $num_iter" + + devlink_trap_action_set $trap_name "trap" + sleep 1 + + devlink_reload + # Allow netdevices to be re-created following the reload + sleep 20 + + cleanup + setup_prepare + setup_wait + done + + log_test "Device delete" + + kill $mz_pid && wait $mz_pid &> /dev/null +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh new file mode 100755 index 000000000000..5dcdfa20fc6c --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh @@ -0,0 +1,484 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap L2 drops functionality over mlxsw. Each registered L2 drop +# packet trap is tested to make sure it is triggered under the right +# conditions. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + source_mac_is_multicast_test + vlan_tag_mismatch_test + ingress_vlan_filter_test + ingress_stp_filter_test + port_list_is_empty_test + port_loopback_filter_test +" +NUM_NETIFS=4 +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 +} + +h2_destroy() +{ + simple_if_fini $h2 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +l2_drops_test() +{ + local trap_name=$1; shift + local group_name=$1; shift + + # This is the common part of all the tests. It checks that stats are + # initially idle, then non-idle after changing the trap action and + # finally idle again. It also makes sure the packets are dropped and + # never forwarded. + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle with initial drop action" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with initial drop action" + + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_fail $? "Trap stats idle after setting action to trap" + devlink_trap_group_stats_idle_test $group_name + check_fail $? "Trap group stats idle after setting action to trap" + + devlink_trap_action_set $trap_name "drop" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle after setting action to drop" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle after setting action to drop" + + tc_check_packets "dev $swp2 egress" 101 0 + check_err $? "Packets were not dropped" +} + +l2_drops_cleanup() +{ + local mz_pid=$1; shift + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower +} + +source_mac_is_multicast_test() +{ + local trap_name="source_mac_is_multicast" + local smac=01:02:03:04:05:06 + local group_name="l2_drops" + local mz_pid + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower src_mac $smac action drop + + $MZ $h1 -c 0 -p 100 -a $smac -b bcast -t ip -d 1msec -q & + mz_pid=$! + + RET=0 + + l2_drops_test $trap_name $group_name + + log_test "Source MAC is multicast" + + l2_drops_cleanup $mz_pid +} + +__vlan_tag_mismatch_test() +{ + local trap_name="vlan_tag_mismatch" + local dmac=de:ad:be:ef:13:37 + local group_name="l2_drops" + local opt=$1; shift + local mz_pid + + # Remove PVID flag. This should prevent untagged and prio-tagged + # packets from entering the bridge. + bridge vlan add vid 1 dev $swp1 untagged master + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 "$opt" -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Add PVID and make sure packets are no longer dropped. + bridge vlan add vid 1 dev $swp1 pvid untagged master + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + l2_drops_cleanup $mz_pid +} + +vlan_tag_mismatch_untagged_test() +{ + RET=0 + + __vlan_tag_mismatch_test + + log_test "VLAN tag mismatch - untagged packets" +} + +vlan_tag_mismatch_vid_0_test() +{ + RET=0 + + __vlan_tag_mismatch_test "-Q 0" + + log_test "VLAN tag mismatch - prio-tagged packets" +} + +vlan_tag_mismatch_test() +{ + vlan_tag_mismatch_untagged_test + vlan_tag_mismatch_vid_0_test +} + +ingress_vlan_filter_test() +{ + local trap_name="ingress_vlan_filter" + local dmac=de:ad:be:ef:13:37 + local group_name="l2_drops" + local mz_pid + local vid=10 + + bridge vlan add vid $vid dev $swp2 master + # During initialization the firmware enables all the VLAN filters and + # the driver does not turn them off since the traffic will be discarded + # by the STP filter whose default is DISCARD state. Add the VID on the + # ingress bridge port and then remove it to make sure it is not member + # in the VLAN. + bridge vlan add vid $vid dev $swp1 master + bridge vlan del vid $vid dev $swp1 master + + RET=0 + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Add the VLAN on the bridge port and make sure packets are no longer + # dropped. + bridge vlan add vid $vid dev $swp1 master + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + log_test "Ingress VLAN filter" + + l2_drops_cleanup $mz_pid + + bridge vlan del vid $vid dev $swp1 master + bridge vlan del vid $vid dev $swp2 master +} + +__ingress_stp_filter_test() +{ + local trap_name="ingress_spanning_tree_filter" + local dmac=de:ad:be:ef:13:37 + local group_name="l2_drops" + local state=$1; shift + local mz_pid + local vid=20 + + bridge vlan add vid $vid dev $swp2 master + bridge vlan add vid $vid dev $swp1 master + ip link set dev $swp1 type bridge_slave state $state + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Change STP state to forwarding and make sure packets are no longer + # dropped. + ip link set dev $swp1 type bridge_slave state 3 + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + l2_drops_cleanup $mz_pid + + bridge vlan del vid $vid dev $swp1 master + bridge vlan del vid $vid dev $swp2 master +} + +ingress_stp_filter_listening_test() +{ + local state=$1; shift + + RET=0 + + __ingress_stp_filter_test $state + + log_test "Ingress STP filter - listening state" +} + +ingress_stp_filter_learning_test() +{ + local state=$1; shift + + RET=0 + + __ingress_stp_filter_test $state + + log_test "Ingress STP filter - learning state" +} + +ingress_stp_filter_test() +{ + ingress_stp_filter_listening_test 1 + ingress_stp_filter_learning_test 2 +} + +port_list_is_empty_uc_test() +{ + local trap_name="port_list_is_empty" + local dmac=de:ad:be:ef:13:37 + local group_name="l2_drops" + local mz_pid + + # Disable unicast flooding on both ports, so that packets cannot egress + # any port. + ip link set dev $swp1 type bridge_slave flood off + ip link set dev $swp2 type bridge_slave flood off + + RET=0 + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Allow packets to be flooded to one port. + ip link set dev $swp2 type bridge_slave flood on + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + log_test "Port list is empty - unicast" + + l2_drops_cleanup $mz_pid + + ip link set dev $swp1 type bridge_slave flood on +} + +port_list_is_empty_mc_test() +{ + local trap_name="port_list_is_empty" + local dmac=01:00:5e:00:00:01 + local group_name="l2_drops" + local dip=239.0.0.1 + local mz_pid + + # Disable multicast flooding on both ports, so that packets cannot + # egress any port. We also need to flush IP addresses from the bridge + # in order to prevent packets from being flooded to the router port. + ip link set dev $swp1 type bridge_slave mcast_flood off + ip link set dev $swp2 type bridge_slave mcast_flood off + ip address flush dev br0 + + RET=0 + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -B $dip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Allow packets to be flooded to one port. + ip link set dev $swp2 type bridge_slave mcast_flood on + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + log_test "Port list is empty - multicast" + + l2_drops_cleanup $mz_pid + + ip link set dev $swp1 type bridge_slave mcast_flood on +} + +port_list_is_empty_test() +{ + port_list_is_empty_uc_test + port_list_is_empty_mc_test +} + +port_loopback_filter_uc_test() +{ + local trap_name="port_loopback_filter" + local dmac=de:ad:be:ef:13:37 + local group_name="l2_drops" + local mz_pid + + # Make sure packets can only egress the input port. + ip link set dev $swp2 type bridge_slave flood off + + RET=0 + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_mac $dmac action drop + + $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & + mz_pid=$! + + l2_drops_test $trap_name $group_name + + # Allow packets to be flooded. + ip link set dev $swp2 type bridge_slave flood on + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_idle_test $trap_name + check_err $? "Trap stats not idle when packets should not be dropped" + devlink_trap_group_stats_idle_test $group_name + check_err $? "Trap group stats not idle with when packets should not be dropped" + + tc_check_packets "dev $swp2 egress" 101 0 + check_fail $? "Packets not forwarded when should" + + devlink_trap_action_set $trap_name "drop" + + log_test "Port loopback filter - unicast" + + l2_drops_cleanup $mz_pid +} + +port_loopback_filter_test() +{ + port_loopback_filter_uc_test +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 40f16f2a3afd..5cbff8038f84 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -36,8 +36,6 @@ source $lib_dir/lib.sh h1_create() { - local dscp; - simple_if_init $h1 192.0.2.1/28 tc qdisc add dev $h1 clsact dscp_capture_install $h1 10 @@ -67,6 +65,7 @@ h2_destroy() dscp_map() { local base=$1; shift + local prio for prio in {0..7}; do echo app=$prio,5,$((base + prio)) @@ -138,6 +137,7 @@ dscp_ping_test() local prio=$1; shift local dev_10=$1; shift local dev_20=$1; shift + local key local dscp_10=$(((prio + 10) << 2)) local dscp_20=$(((prio + 20) << 2)) @@ -175,6 +175,8 @@ dscp_ping_test() test_dscp() { + local prio + for prio in {0..7}; do dscp_ping_test v$h1 192.0.2.1 192.0.2.2 $prio $h1 $h2 done diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh index 9faf02e32627..c745ce3befee 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -31,6 +31,7 @@ ALL_TESTS=" ping_ipv4 test_update test_no_update + test_dscp_leftover " lib_dir=$(dirname $0)/../../../net/forwarding @@ -50,10 +51,13 @@ reprioritize() echo ${reprio[$in]} } -h1_create() +zero() { - local dscp; + echo 0 +} +h1_create() +{ simple_if_init $h1 192.0.2.1/28 tc qdisc add dev $h1 clsact dscp_capture_install $h1 0 @@ -87,6 +91,7 @@ h2_destroy() dscp_map() { local base=$1; shift + local prio for prio in {0..7}; do echo app=$prio,5,$((base + prio)) @@ -156,6 +161,7 @@ dscp_ping_test() local reprio=$1; shift local dev1=$1; shift local dev2=$1; shift + local i local prio2=$($reprio $prio) # ICMP Request egress prio local prio3=$($reprio $prio2) # ICMP Response egress prio @@ -205,6 +211,7 @@ __test_update() { local update=$1; shift local reprio=$1; shift + local prio sysctl_restore net.ipv4.ip_forward_update_priority sysctl_set net.ipv4.ip_forward_update_priority $update @@ -224,6 +231,19 @@ test_no_update() __test_update 0 echo } +# Test that when the last APP rule is removed, the prio->DSCP map is properly +# set to zeroes, and that the last APP rule does not stay active in the ASIC. +test_dscp_leftover() +{ + lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null + lldpad_app_wait_del + + __test_update 0 zero + + lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null + lldpad_app_wait_set $swp2 +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 9d8baf5d14b3..115837355eaf 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -3,7 +3,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding -ALL_TESTS="fw_flash_test" +ALL_TESTS="fw_flash_test params_test regions_test" NUM_NETIFS=0 source $lib_dir/lib.sh @@ -30,6 +30,118 @@ fw_flash_test() log_test "fw flash test" } +param_get() +{ + local name=$1 + + cmd_jq "devlink dev param show $DL_HANDLE name $name -j" \ + '.[][][].values[] | select(.cmode == "driverinit").value' +} + +param_set() +{ + local name=$1 + local value=$2 + + devlink dev param set $DL_HANDLE name $name cmode driverinit value $value +} + +check_value() +{ + local name=$1 + local phase_name=$2 + local expected_param_value=$3 + local expected_debugfs_value=$4 + local value + + value=$(param_get $name) + check_err $? "Failed to get $name param value" + [ "$value" == "$expected_param_value" ] + check_err $? "Unexpected $phase_name $name param value" + value=$(<$DEBUGFS_DIR/$name) + check_err $? "Failed to get $name debugfs value" + [ "$value" == "$expected_debugfs_value" ] + check_err $? "Unexpected $phase_name $name debugfs value" +} + +params_test() +{ + RET=0 + + local max_macs + local test1 + + check_value max_macs initial 32 32 + check_value test1 initial true Y + + param_set max_macs 16 + check_err $? "Failed to set max_macs param value" + param_set test1 false + check_err $? "Failed to set test1 param value" + + check_value max_macs post-set 16 32 + check_value test1 post-set false Y + + devlink dev reload $DL_HANDLE + + check_value max_macs post-reload 16 16 + check_value test1 post-reload false N + + log_test "params test" +} + +check_region_size() +{ + local name=$1 + local size + + size=$(devlink region show $DL_HANDLE/$name -j | jq -e -r '.[][].size') + check_err $? "Failed to get $name region size" + [ $size -eq 32768 ] + check_err $? "Invalid $name region size" +} + +check_region_snapshot_count() +{ + local name=$1 + local phase_name=$2 + local expected_count=$3 + local count + + count=$(devlink region show $DL_HANDLE/$name -j | jq -e -r '.[][].snapshot | length') + [ $count -eq $expected_count ] + check_err $? "Unexpected $phase_name snapshot count" +} + +regions_test() +{ + RET=0 + + local count + + check_region_size dummy + check_region_snapshot_count dummy initial 0 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take first dummy region snapshot" + check_region_snapshot_count dummy post-first-snapshot 1 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take second dummy region snapshot" + check_region_snapshot_count dummy post-second-snapshot 2 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take third dummy region snapshot" + check_region_snapshot_count dummy post-third-snapshot 3 + + devlink region del $DL_HANDLE/dummy snapshot 1 + check_err $? "Failed to delete first dummy region snapshot" + + check_region_snapshot_count dummy post-first-delete 2 + + log_test "regions test" +} + setup_prepare() { modprobe netdevsim diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh new file mode 100755 index 000000000000..f101ab9441e2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh @@ -0,0 +1,364 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking devlink-trap functionality. It makes use of +# netdevsim which implements the required callbacks. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + init_test + trap_action_test + trap_metadata_test + bad_trap_test + bad_trap_action_test + trap_stats_test + trap_group_action_test + bad_trap_group_test + trap_group_stats_test + port_del_test + dev_del_test +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SLEEP_TIME=1 +NETDEV="" +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +require_command udevadm + +modprobe netdevsim &> /dev/null +if [ ! -d "$NETDEVSIM_PATH" ]; then + echo "SKIP: No netdevsim support" + exit 1 +fi + +if [ -d "${NETDEVSIM_PATH}/devices/netdevsim${DEV_ADDR}" ]; then + echo "SKIP: Device netdevsim${DEV_ADDR} already exists" + exit 1 +fi + +init_test() +{ + RET=0 + + test $(devlink_traps_num_get) -ne 0 + check_err $? "No traps were registered" + + log_test "Initialization" +} + +trap_action_test() +{ + local orig_action + local trap_name + local action + + RET=0 + + for trap_name in $(devlink_traps_get); do + # The action of non-drop traps cannot be changed. + if [ $(devlink_trap_type_get $trap_name) = "drop" ]; then + devlink_trap_action_set $trap_name "trap" + action=$(devlink_trap_action_get $trap_name) + if [ $action != "trap" ]; then + check_err 1 "Trap $trap_name did not change action to trap" + fi + + devlink_trap_action_set $trap_name "drop" + action=$(devlink_trap_action_get $trap_name) + if [ $action != "drop" ]; then + check_err 1 "Trap $trap_name did not change action to drop" + fi + else + orig_action=$(devlink_trap_action_get $trap_name) + + devlink_trap_action_set $trap_name "trap" + action=$(devlink_trap_action_get $trap_name) + if [ $action != $orig_action ]; then + check_err 1 "Trap $trap_name changed action when should not" + fi + + devlink_trap_action_set $trap_name "drop" + action=$(devlink_trap_action_get $trap_name) + if [ $action != $orig_action ]; then + check_err 1 "Trap $trap_name changed action when should not" + fi + fi + done + + log_test "Trap action" +} + +trap_metadata_test() +{ + local trap_name + + RET=0 + + for trap_name in $(devlink_traps_get); do + devlink_trap_metadata_test $trap_name "input_port" + check_err $? "Input port not reported as metadata of trap $trap_name" + done + + log_test "Trap metadata" +} + +bad_trap_test() +{ + RET=0 + + devlink_trap_action_set "made_up_trap" "drop" + check_fail $? "Did not get an error for non-existing trap" + + log_test "Non-existing trap" +} + +bad_trap_action_test() +{ + local traps_arr + local trap_name + + RET=0 + + # Pick first trap. + traps_arr=($(devlink_traps_get)) + trap_name=${traps_arr[0]} + + devlink_trap_action_set $trap_name "made_up_action" + check_fail $? "Did not get an error for non-existing trap action" + + log_test "Non-existing trap action" +} + +trap_stats_test() +{ + local trap_name + + RET=0 + + for trap_name in $(devlink_traps_get); do + devlink_trap_stats_idle_test $trap_name + check_err $? "Stats of trap $trap_name not idle when netdev down" + + ip link set dev $NETDEV up + + if [ $(devlink_trap_type_get $trap_name) = "drop" ]; then + devlink_trap_action_set $trap_name "trap" + devlink_trap_stats_idle_test $trap_name + check_fail $? "Stats of trap $trap_name idle when action is trap" + + devlink_trap_action_set $trap_name "drop" + devlink_trap_stats_idle_test $trap_name + check_err $? "Stats of trap $trap_name not idle when action is drop" + else + devlink_trap_stats_idle_test $trap_name + check_fail $? "Stats of non-drop trap $trap_name idle when should not" + fi + + ip link set dev $NETDEV down + done + + log_test "Trap statistics" +} + +trap_group_action_test() +{ + local curr_group group_name + local trap_name + local trap_type + local action + + RET=0 + + for group_name in $(devlink_trap_groups_get); do + devlink_trap_group_action_set $group_name "trap" + + for trap_name in $(devlink_traps_get); do + curr_group=$(devlink_trap_group_get $trap_name) + if [ $curr_group != $group_name ]; then + continue + fi + + trap_type=$(devlink_trap_type_get $trap_name) + if [ $trap_type != "drop" ]; then + continue + fi + + action=$(devlink_trap_action_get $trap_name) + if [ $action != "trap" ]; then + check_err 1 "Trap $trap_name did not change action to trap" + fi + done + + devlink_trap_group_action_set $group_name "drop" + + for trap_name in $(devlink_traps_get); do + curr_group=$(devlink_trap_group_get $trap_name) + if [ $curr_group != $group_name ]; then + continue + fi + + trap_type=$(devlink_trap_type_get $trap_name) + if [ $trap_type != "drop" ]; then + continue + fi + + action=$(devlink_trap_action_get $trap_name) + if [ $action != "drop" ]; then + check_err 1 "Trap $trap_name did not change action to drop" + fi + done + done + + log_test "Trap group action" +} + +bad_trap_group_test() +{ + RET=0 + + devlink_trap_group_action_set "made_up_trap_group" "drop" + check_fail $? "Did not get an error for non-existing trap group" + + log_test "Non-existing trap group" +} + +trap_group_stats_test() +{ + local group_name + + RET=0 + + for group_name in $(devlink_trap_groups_get); do + devlink_trap_group_stats_idle_test $group_name + check_err $? "Stats of trap group $group_name not idle when netdev down" + + ip link set dev $NETDEV up + + devlink_trap_group_action_set $group_name "trap" + devlink_trap_group_stats_idle_test $group_name + check_fail $? "Stats of trap group $group_name idle when action is trap" + + devlink_trap_group_action_set $group_name "drop" + ip link set dev $NETDEV down + done + + log_test "Trap group statistics" +} + +port_del_test() +{ + local group_name + local i + + # The test never fails. It is meant to exercise different code paths + # and make sure we properly dismantle a port while packets are + # in-flight. + RET=0 + + devlink_traps_enable_all + + for i in $(seq 1 10); do + ip link set dev $NETDEV up + + sleep $SLEEP_TIME + + netdevsim_port_destroy + netdevsim_port_create + udevadm settle + done + + devlink_traps_disable_all + + log_test "Port delete" +} + +dev_del_test() +{ + local group_name + local i + + # The test never fails. It is meant to exercise different code paths + # and make sure we properly unregister traps while packets are + # in-flight. + RET=0 + + devlink_traps_enable_all + + for i in $(seq 1 10); do + ip link set dev $NETDEV up + + sleep $SLEEP_TIME + + cleanup + setup_prepare + done + + devlink_traps_disable_all + + log_test "Device delete" +} + +netdevsim_dev_create() +{ + echo "$DEV_ADDR 0" > ${NETDEVSIM_PATH}/new_device +} + +netdevsim_dev_destroy() +{ + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device +} + +netdevsim_port_create() +{ + echo 1 > ${NETDEVSIM_PATH}/devices/${DEV}/new_port +} + +netdevsim_port_destroy() +{ + echo 1 > ${NETDEVSIM_PATH}/devices/${DEV}/del_port +} + +setup_prepare() +{ + local netdev + + netdevsim_dev_create + + if [ ! -d "${NETDEVSIM_PATH}/devices/${DEV}" ]; then + echo "Failed to create netdevsim device" + exit 1 + fi + + netdevsim_port_create + + if [ ! -d "${NETDEVSIM_PATH}/devices/${DEV}/net/" ]; then + echo "Failed to create netdevsim port" + exit 1 + fi + + # Wait for udev to rename newly created netdev. + udevadm settle + + NETDEV=$(ls ${NETDEVSIM_PATH}/devices/${DEV}/net/) +} + +cleanup() +{ + pre_cleanup + netdevsim_port_destroy + netdevsim_dev_destroy +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1b24e36b4047..0bd6b23c97ef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -10,9 +10,9 @@ TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh -TEST_PROGS += tcp_fastopen_backup_key.sh +TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh TEST_PROGS_EXTENDED := in_netns.sh -TEST_GEN_FILES = socket +TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh new file mode 100755 index 000000000000..9fd3a0b97f0d --- /dev/null +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -0,0 +1,3432 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 David Ahern <dsahern@gmail.com>. All rights reserved. +# +# IPv4 and IPv6 functional tests focusing on VRF and routing lookups +# for various permutations: +# 1. icmp, tcp, udp and netfilter +# 2. client, server, no-server +# 3. global address on interface +# 4. global address on 'lo' +# 5. remote and local traffic +# 6. VRF and non-VRF permutations +# +# Setup: +# ns-A | ns-B +# No VRF case: +# [ lo ] [ eth1 ]---|---[ eth1 ] [ lo ] +# remote address +# VRF case: +# [ red ]---[ eth1 ]---|---[ eth1 ] [ lo ] +# +# ns-A: +# eth1: 172.16.1.1/24, 2001:db8:1::1/64 +# lo: 127.0.0.1/8, ::1/128 +# 172.16.2.1/32, 2001:db8:2::1/128 +# red: 127.0.0.1/8, ::1/128 +# 172.16.3.1/32, 2001:db8:3::1/128 +# +# ns-B: +# eth1: 172.16.1.2/24, 2001:db8:1::2/64 +# lo2: 127.0.0.1/8, ::1/128 +# 172.16.2.2/32, 2001:db8:2::2/128 +# +# server / client nomenclature relative to ns-A + +VERBOSE=0 + +NSA_DEV=eth1 +NSB_DEV=eth1 +VRF=red +VRF_TABLE=1101 + +# IPv4 config +NSA_IP=172.16.1.1 +NSB_IP=172.16.1.2 +VRF_IP=172.16.3.1 + +# IPv6 config +NSA_IP6=2001:db8:1::1 +NSB_IP6=2001:db8:1::2 +VRF_IP6=2001:db8:3::1 + +NSA_LO_IP=172.16.2.1 +NSB_LO_IP=172.16.2.2 +NSA_LO_IP6=2001:db8:2::1 +NSB_LO_IP6=2001:db8:2::2 + +MCAST=ff02::1 +# set after namespace create +NSA_LINKIP6= +NSB_LINKIP6= + +NSA=ns-A +NSB=ns-B + +NSA_CMD="ip netns exec ${NSA}" +NSB_CMD="ip netns exec ${NSB}" + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + [ "${VERBOSE}" = "1" ] && echo + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "TEST: %-70s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "TEST: %-70s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + kill_procs +} + +log_test_addr() +{ + local addr=$1 + local rc=$2 + local expected=$3 + local msg="$4" + local astr + + astr=$(addr2str ${addr}) + log_test $rc $expected "$msg - ${astr}" +} + +log_section() +{ + echo + echo "###########################################################################" + echo "$*" + echo "###########################################################################" + echo +} + +log_subsection() +{ + echo + echo "#################################################################" + echo "$*" + echo +} + +log_start() +{ + # make sure we have no test instances running + kill_procs + + if [ "${VERBOSE}" = "1" ]; then + echo + echo "#######################################################" + fi +} + +log_debug() +{ + if [ "${VERBOSE}" = "1" ]; then + echo + echo "$*" + echo + fi +} + +show_hint() +{ + if [ "${VERBOSE}" = "1" ]; then + echo "HINT: $*" + echo + fi +} + +kill_procs() +{ + killall nettest ping ping6 >/dev/null 2>&1 + sleep 1 +} + +do_run_cmd() +{ + local cmd="$*" + local out + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: ${cmd}" + fi + + out=$($cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo "$out" + fi + + return $rc +} + +run_cmd() +{ + do_run_cmd ${NSA_CMD} $* +} + +run_cmd_nsb() +{ + do_run_cmd ${NSB_CMD} $* +} + +setup_cmd() +{ + local cmd="$*" + local rc + + run_cmd ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +setup_cmd_nsb() +{ + local cmd="$*" + local rc + + run_cmd_nsb ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +# set sysctl values in NS-A +set_sysctl() +{ + echo "SYSCTL: $*" + echo + run_cmd sysctl -q -w $* +} + +################################################################################ +# Setup for tests + +addr2str() +{ + case "$1" in + 127.0.0.1) echo "loopback";; + ::1) echo "IPv6 loopback";; + + ${NSA_IP}) echo "ns-A IP";; + ${NSA_IP6}) echo "ns-A IPv6";; + ${NSA_LO_IP}) echo "ns-A loopback IP";; + ${NSA_LO_IP6}) echo "ns-A loopback IPv6";; + ${NSA_LINKIP6}|${NSA_LINKIP6}%*) echo "ns-A IPv6 LLA";; + + ${NSB_IP}) echo "ns-B IP";; + ${NSB_IP6}) echo "ns-B IPv6";; + ${NSB_LO_IP}) echo "ns-B loopback IP";; + ${NSB_LO_IP6}) echo "ns-B loopback IPv6";; + ${NSB_LINKIP6}|${NSB_LINKIP6}%*) echo "ns-B IPv6 LLA";; + + ${VRF_IP}) echo "VRF IP";; + ${VRF_IP6}) echo "VRF IPv6";; + + ${MCAST}%*) echo "multicast IP";; + + *) echo "unknown";; + esac +} + +get_linklocal() +{ + local ns=$1 + local dev=$2 + local addr + + addr=$(ip -netns ${ns} -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +################################################################################ +# create namespaces and vrf + +create_vrf() +{ + local ns=$1 + local vrf=$2 + local table=$3 + local addr=$4 + local addr6=$5 + + ip -netns ${ns} link add ${vrf} type vrf table ${table} + ip -netns ${ns} link set ${vrf} up + ip -netns ${ns} route add vrf ${vrf} unreachable default metric 8192 + ip -netns ${ns} -6 route add vrf ${vrf} unreachable default metric 8192 + + ip -netns ${ns} addr add 127.0.0.1/8 dev ${vrf} + ip -netns ${ns} -6 addr add ::1 dev ${vrf} nodad + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev ${vrf} ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev ${vrf} ${addr6} + fi + + ip -netns ${ns} ru del pref 0 + ip -netns ${ns} ru add pref 32765 from all lookup local + ip -netns ${ns} -6 ru del pref 0 + ip -netns ${ns} -6 ru add pref 32765 from all lookup local +} + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +cleanup() +{ + # explicit cleanups to check those code paths + ip netns | grep -q ${NSA} + if [ $? -eq 0 ]; then + ip -netns ${NSA} link delete ${VRF} + ip -netns ${NSA} ro flush table ${VRF_TABLE} + + ip -netns ${NSA} addr flush dev ${NSA_DEV} + ip -netns ${NSA} -6 addr flush dev ${NSA_DEV} + ip -netns ${NSA} link set dev ${NSA_DEV} down + ip -netns ${NSA} link del dev ${NSA_DEV} + + ip netns del ${NSA} + fi + + ip netns del ${NSB} +} + +setup() +{ + local with_vrf=${1} + + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} ${NSA_LO_IP}/32 ${NSA_LO_IP6}/128 + create_ns ${NSB} ${NSB_LO_IP}/32 ${NSB_LO_IP6}/128 + connect_ns ${NSA} ${NSA_DEV} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSB} ${NSB_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + + # tell ns-A how to get to remote addresses of ns-B + if [ "${with_vrf}" = "yes" ]; then + create_vrf ${NSA} ${VRF} ${VRF_TABLE} ${VRF_IP} ${VRF_IP6} + + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} ro add vrf ${VRF} ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} -6 ro add vrf ${VRF} ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + + ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + else + ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + fi + + + # tell ns-B how to get to remote addresses of ns-A + ip -netns ${NSB} ro add ${NSA_LO_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} ro add ${NSA_LO_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + set +e + + sleep 1 +} + +################################################################################ +# IPv4 + +ipv4_ping_novrf() +{ + local a + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_LO_IP} ${a} + log_test_addr ${a} $? 0 "ping out, address bind" + done + + # + # in + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # loopback addresses not reachable from device bind + # fails in a really weird way though because ipv4 special cases + # route lookups with oif set. + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on loopback device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks reachability to remote address + # + log_start + setup_cmd ip rule add pref 32765 from all lookup local + setup_cmd ip rule del pref 0 from all lookup local + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite the rule + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response generates ICMP (or arp request is ignored) due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 32765 from all lookup local + setup_cmd ip rule add pref 0 from all lookup local + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip route replace unreachable ${NSB_LO_IP} + setup_cmd ip route replace unreachable ${NSB_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response is dropped (or arp request is ignored) due to ip route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable default route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} +} + +ipv4_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${NSA_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + dev address bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${VRF_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + vrf address bind" + done + + # + # in + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # vrf device is out of scope + for a in ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on vrf device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, blocked by rule" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del vrf ${VRF} ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, unreachable route" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost by unreachable route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, unreachable route" +} + +ipv4_ping() +{ + log_section "IPv4 ping" + + log_subsection "No VRF" + setup + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + ipv4_ping_novrf + setup + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + ipv4_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_ping_vrf +} + +################################################################################ +# IPv4 TCP + +ipv4_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset sent and received + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" +} + +ipv4_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + # (${VRF_IP} and 127.0.0.1 both timeout) + a=${NSA_IP} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + show_hint "client socket should be bound to device" + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # local address tests + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'No route to host' since client is not bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since client is out of VRF scope" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" +} + +ipv4_tcp() +{ + log_section "IPv4/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv4_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv4_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_tcp_vrf +} + +################################################################################ +# IPv4 UDP + +ipv4_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind via IP_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IP_UNICAST_IF, local connection" + + # IPv4 with device bind has really weird behavior - it overrides the + # fib lookup, generates an rtable and tries to send the packet. This + # causes failures for local traffic at different places + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 2 "Global server, device client, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 2 "No server, device client, local conn" +} + +ipv4_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Fails because ingress is in a VRF and global server is disabled" + run_cmd nettest -D -s & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + + log_start + show_hint "Should fail 'Connection refused' since global server is out of scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, enslaved device client, local connection" + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # enable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${VRF} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "VRF client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${NSB_IP} + log_test $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${NSA_DEV} -r ${NSB_IP} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP} + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + done + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + # negative test - should fail + # verifies ECONNREFUSED + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done +} + +ipv4_udp() +{ + log_section "IPv4/UDP" + log_subsection "No VRF" + + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv4_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv4_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_udp_vrf +} + +################################################################################ +# IPv4 address bind +# +# verifies ability or inability to bind to an address / device + +ipv4_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP} + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not + #a=${NSA_LO_IP} + #log_start + #show_hint "Should fail with 'Cannot assign requested address'" + #run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + #log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv4_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after VRF bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind" + + # + # tcp sockets + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" +} + +ipv4_addr_bind() +{ + log_section "IPv4 address binds" + + log_subsection "No VRF" + setup + ipv4_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_addr_bind_vrf +} + +################################################################################ +# IPv4 runtime tests + +ipv4_rt() +{ + local desc="$1" + local varg="$2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + # + # local address tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client, local" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client, local" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server and client, local" +} + +ipv4_ping_rt() +{ + local with_vrf="yes" + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + done + + a=${NSB_IP} + log_start + run_cmd ping -f -I ${VRF} ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv4_runtime() +{ + log_section "Run time tests - ipv4" + + setup "yes" + ipv4_ping_rt + + setup "yes" + ipv4_rt "TCP active socket" "-n -1" + + setup "yes" + ipv4_rt "TCP passive socket" "-i" +} + +################################################################################ +# IPv6 + +ipv6_ping_novrf() +{ + local a + + # should not have an impact, but make a known state + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_LO_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, loopback address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local, no bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Fails since address on loopback is out of device scope" + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 0 from all lookup local + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + setup_cmd ip -6 rule add pref 0 from all lookup local + setup_cmd ip -6 rule del pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip -6 route del ${NSB_LO_IP6} + setup_cmd ip -6 route add unreachable ${NSB_LO_IP6} metric 10 + setup_cmd ip -6 route add unreachable ${NSB_IP6} metric 10 + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by route" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip route" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del unreachable ${NSB_LO_IP6} + setup_cmd ip -6 ro del unreachable ${NSB_IP6} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" +} + +ipv6_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + done + + for a in ${NSB_LINKIP6}%${VRF} ${MCAST}%${VRF} + do + log_start + show_hint "Fails since VRF device does not support linklocal or multicast" + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, VRF bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd ip vrf exec ${VRF} ${ping6} -c1 -w1 -I ${VRF_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device+address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Fails since loopback address is out of VRF scope" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in" + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + # LLA to GUA - remove ipv6 global addresses from ns-B + setup_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr del ${NSB_LO_IP6}/128 dev lo + setup_cmd_nsb ip -6 ro add ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test_addr ${a} $? 0 "ping in, LLA to GUA" + done + + setup_cmd_nsb ip -6 ro del ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_LO_IP6}/128 dev lo + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + log_start + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del ${NSB_LO_IP6} vrf ${VRF} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + ip -netns ${NSB} -6 ro del ${NSA_LO_IP6} + a=${NSA_LO_IP6} + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping in, unreachable route" +} + +ipv6_ping() +{ + log_section "IPv6 ping" + + log_subsection "No VRF" + setup + ipv6_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_ping_vrf +} + +################################################################################ +# IPv6 TCP + +ipv6_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + done +} + +ipv6_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # link local is always bound to ingress device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # For LLA, child socket is bound to device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Fails 'No route to host' since client is not in VRF" + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + done + + a=${NSB_LINKIP6} + log_start + show_hint "Fails since VRF device does not allow linklocal addresses" + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "Client, VRF bind" + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + a=${NSA_IP6} + log_start + show_hint "Should fail since unbound client is out of VRF scope" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + done +} + +ipv6_tcp() +{ + log_section "IPv6/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv6_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv6_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_tcp_vrf +} + +################################################################################ +# IPv6 UDP + +ipv6_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + a=${NSA_LO_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + # should fail since loopback address is out of scope for a device + # bound server, but it does not - hence this is more documenting + # behavior. + #log_start + #show_hint "Should fail since loopback address is out of scope" + #run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + #sleep 1 + #run_cmd_nsb nettest -6 -D -r ${a} + #log_test_addr ${a} $? 1 "Device server" + + # negative test - should fail + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind via IPV6_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -6 -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Device server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IPV6_UNICAST_IF, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local conn" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # disable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 0 "VRF client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 1 "No server, VRF client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + #log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done + + # device to global IP + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + + # link local addresses + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Global server, linklocal IP" + + log_start + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, linklocal IP" + + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 0 "Enslaved device client, linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 1 "No server, device client, peer linklocal IP" + + + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Enslaved device client, local conn - linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, device client, local conn - linklocal IP" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp() +{ + # should not matter, but set to known state + set_sysctl net.ipv4.udp_early_demux=1 + + log_section "IPv6/UDP" + log_subsection "No VRF" + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv6_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv6_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_udp_vrf +} + +################################################################################ +# IPv6 address bind + +ipv6_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${NSA_LO_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Should fail with 'Cannot assign requested address'" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv6_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after vrf bind" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to invalid local address after vrf bind" + + # + # tcp sockets + # + # address on enslaved device is valid for the VRF or device in a VRF + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with VRF bind" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" + +} + +ipv6_addr_bind() +{ + log_section "IPv6 address binds" + + log_subsection "No VRF" + setup + ipv6_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_addr_bind_vrf +} + +################################################################################ +# IPv6 runtime tests + +ipv6_rt() +{ + local desc="$1" + local varg="-6 $2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + done + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client" + + setup ${with_vrf} + done + + a=${NSA_IP6} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, device server, device client" +} + +ipv6_ping_rt() +{ + local with_vrf="yes" + local a + + a=${NSA_IP6} + log_start + run_cmd_nsb ${ping6} -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + + log_start + run_cmd ${ping6} -f ${NSB_IP6} -I ${VRF} & + sleep 1 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv6_runtime() +{ + log_section "Run time tests - ipv6" + + setup "yes" + ipv6_ping_rt + + setup "yes" + ipv6_rt "TCP active socket" "-n -1" + + setup "yes" + ipv6_rt "TCP passive socket" "-i" + + setup "yes" + ipv6_rt "UDP active socket" "-D -n -1" +} + +################################################################################ +# netfilter blocking connections + +netfilter_tcp_reset() +{ + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="-D" + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${arg} -s & + sleep 1 + run_cmd_nsb nettest ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv4_netfilter() +{ + log_section "IPv4 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp_reset + + log_start + log_subsection "ICMP unreachable" + + log_start + run_cmd iptables -F + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + run_cmd iptables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + + netfilter_icmp "TCP" + netfilter_icmp "UDP" + + log_start + iptables -F +} + +netfilter_tcp6_reset() +{ + local a + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp6() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="$arg -D" + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s ${arg} & + sleep 1 + run_cmd_nsb nettest -6 ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv6_netfilter() +{ + log_section "IPv6 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp6_reset + + log_subsection "ICMP unreachable" + + log_start + run_cmd ip6tables -F + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + run_cmd ip6tables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + + netfilter_icmp6 "TCP" + netfilter_icmp6 "UDP" + + log_start + ip6tables -F +} + +################################################################################ +# specific use cases + +# VRF only. +# ns-A device enslaved to bridge. Verify traffic with and without +# br_netfilter module loaded. Repeat with SVI on bridge. +use_case_br() +{ + setup "yes" + + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip addr del dev ${NSA_DEV} ${NSA_IP}/24 + setup_cmd ip -6 addr del dev ${NSA_DEV} ${NSA_IP6}/64 + + setup_cmd ip link add br0 type bridge + setup_cmd ip addr add dev br0 ${NSA_IP}/24 + setup_cmd ip -6 addr add dev br0 ${NSA_IP6}/64 nodad + + setup_cmd ip li set ${NSA_DEV} master br0 + setup_cmd ip li set ${NSA_DEV} up + setup_cmd ip li set br0 up + setup_cmd ip li set br0 vrf ${VRF} + + rmmod br_netfilter 2>/dev/null + sleep 5 # DAD + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping in" + fi + + setup_cmd ip li set br0 nomaster + setup_cmd ip li add br0.100 link br0 type vlan id 100 + setup_cmd ip li set br0.100 vrf ${VRF} up + setup_cmd ip addr add dev br0.100 172.16.101.1/24 + setup_cmd ip -6 addr add dev br0.100 2001:db8:101::1/64 nodad + + setup_cmd_nsb ip li add vlan100 link ${NSB_DEV} type vlan id 100 + setup_cmd_nsb ip addr add dev vlan100 172.16.101.2/24 + setup_cmd_nsb ip -6 addr add dev vlan100 2001:db8:101::2/64 nodad + setup_cmd_nsb ip li set vlan100 up + sleep 1 + + rmmod br_netfilter 2>/dev/null + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + fi + + setup_cmd ip li del br0 2>/dev/null + setup_cmd_nsb ip li del vlan100 2>/dev/null +} + +use_cases() +{ + log_section "Use cases" + use_case_br +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -4 IPv4 tests only + -6 IPv6 tests only + -t <test> Test name/set to run + -p Pause on fail + -P Pause after each test + -v Be verbose +EOF +} + +################################################################################ +# main + +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_OTHER="use_cases" + +PAUSE_ON_FAIL=no +PAUSE=no + +while getopts :46t:pPvh o +do + case $o in + 4) TESTS=ipv4;; + 6) TESTS=ipv6;; + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=1;; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +# +# show user test config +# +if [ -z "$TESTS" ]; then + TESTS="$TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER" +elif [ "$TESTS" = "ipv4" ]; then + TESTS="$TESTS_IPV4" +elif [ "$TESTS" = "ipv6" ]; then + TESTS="$TESTS_IPV6" +fi + +which nettest >/dev/null +if [ $? -ne 0 ]; then + echo "'nettest' command not found; skipping tests" + exit 0 +fi + +declare -i nfail=0 +declare -i nsuccess=0 + +for t in $TESTS +do + case $t in + ipv4_ping|ping) ipv4_ping;; + ipv4_tcp|tcp) ipv4_tcp;; + ipv4_udp|udp) ipv4_udp;; + ipv4_bind|bind) ipv4_addr_bind;; + ipv4_runtime) ipv4_runtime;; + ipv4_netfilter) ipv4_netfilter;; + + ipv6_ping|ping6) ipv6_ping;; + ipv6_tcp|tcp6) ipv6_tcp;; + ipv6_udp|udp6) ipv6_udp;; + ipv6_bind|bind6) ipv6_addr_bind;; + ipv6_runtime) ipv6_runtime;; + ipv6_netfilter) ipv6_netfilter;; + + use_cases) use_cases;; + + # setup namespaces and config, but do not run any tests + setup) setup; exit 0;; + vrf_setup) setup "yes"; exit 0;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +cleanup 2>/dev/null + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 8553a67a2322..13d03a6d85ba 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -4,19 +4,21 @@ ############################################################################## # Defines -DEVLINK_DEV=$(devlink port show "${NETIFS[p1]}" -j \ - | jq -r '.port | keys[]' | cut -d/ -f-2) -if [ -z "$DEVLINK_DEV" ]; then - echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" - exit 1 -fi -if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then - echo "SKIP: devlink device's bus is not PCI" - exit 1 -fi +if [[ ! -v DEVLINK_DEV ]]; then + DEVLINK_DEV=$(devlink port show "${NETIFS[p1]}" -j \ + | jq -r '.port | keys[]' | cut -d/ -f-2) + if [ -z "$DEVLINK_DEV" ]; then + echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" + exit 1 + fi + if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then + echo "SKIP: devlink device's bus is not PCI" + exit 1 + fi -DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ - -n | cut -d" " -f3) + DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ + -n | cut -d" " -f3) +fi ############################################################################## # Sanity checks @@ -27,6 +29,12 @@ if [ $? -ne 0 ]; then exit 1 fi +devlink help 2>&1 | grep trap &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink trap support" + exit 1 +fi + ############################################################################## # Devlink helpers @@ -190,3 +198,160 @@ devlink_tc_bind_pool_th_restore() devlink sb tc bind set $port tc $tc type $dir \ pool ${orig[0]} th ${orig[1]} } + +devlink_traps_num_get() +{ + devlink -j trap | jq '.[]["'$DEVLINK_DEV'"] | length' +} + +devlink_traps_get() +{ + devlink -j trap | jq -r '.[]["'$DEVLINK_DEV'"][].name' +} + +devlink_trap_type_get() +{ + local trap_name=$1; shift + + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].type' +} + +devlink_trap_action_set() +{ + local trap_name=$1; shift + local action=$1; shift + + # Pipe output to /dev/null to avoid expected warnings. + devlink trap set $DEVLINK_DEV trap $trap_name \ + action $action &> /dev/null +} + +devlink_trap_action_get() +{ + local trap_name=$1; shift + + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].action' +} + +devlink_trap_group_get() +{ + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].group' +} + +devlink_trap_metadata_test() +{ + local trap_name=$1; shift + local metadata=$1; shift + + devlink -jv trap show $DEVLINK_DEV trap $trap_name \ + | jq -e '.[][][].metadata | contains(["'$metadata'"])' \ + &> /dev/null +} + +devlink_trap_rx_packets_get() +{ + local trap_name=$1; shift + + devlink -js trap show $DEVLINK_DEV trap $trap_name \ + | jq '.[][][]["stats"]["rx"]["packets"]' +} + +devlink_trap_rx_bytes_get() +{ + local trap_name=$1; shift + + devlink -js trap show $DEVLINK_DEV trap $trap_name \ + | jq '.[][][]["stats"]["rx"]["bytes"]' +} + +devlink_trap_stats_idle_test() +{ + local trap_name=$1; shift + local t0_packets t0_bytes + local t1_packets t1_bytes + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + sleep 1 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + return 0 + else + return 1 + fi +} + +devlink_traps_enable_all() +{ + local trap_name + + for trap_name in $(devlink_traps_get); do + devlink_trap_action_set $trap_name "trap" + done +} + +devlink_traps_disable_all() +{ + for trap_name in $(devlink_traps_get); do + devlink_trap_action_set $trap_name "drop" + done +} + +devlink_trap_groups_get() +{ + devlink -j trap group | jq -r '.[]["'$DEVLINK_DEV'"][].name' +} + +devlink_trap_group_action_set() +{ + local group_name=$1; shift + local action=$1; shift + + # Pipe output to /dev/null to avoid expected warnings. + devlink trap group set $DEVLINK_DEV group $group_name action $action \ + &> /dev/null +} + +devlink_trap_group_rx_packets_get() +{ + local group_name=$1; shift + + devlink -js trap group show $DEVLINK_DEV group $group_name \ + | jq '.[][][]["stats"]["rx"]["packets"]' +} + +devlink_trap_group_rx_bytes_get() +{ + local group_name=$1; shift + + devlink -js trap group show $DEVLINK_DEV group $group_name \ + | jq '.[][][]["stats"]["rx"]["bytes"]' +} + +devlink_trap_group_stats_idle_test() +{ + local group_name=$1; shift + local t0_packets t0_bytes + local t1_packets t1_bytes + + t0_packets=$(devlink_trap_group_rx_packets_get $group_name) + t0_bytes=$(devlink_trap_group_rx_bytes_get $group_name) + + sleep 1 + + t1_packets=$(devlink_trap_group_rx_packets_get $group_name) + t1_bytes=$(devlink_trap_group_rx_bytes_get $group_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + return 0 + else + return 1 + fi +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9385dc971269..85c587a03c8a 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -250,6 +250,25 @@ setup_wait() sleep $WAIT_TIME } +cmd_jq() +{ + local cmd=$1 + local jq_exp=$2 + local ret + local output + + output="$($cmd)" + # it the command fails, return error right away + ret=$? + if [[ $ret -ne 0 ]]; then + return $ret + fi + output=$(echo $output | jq -r "$jq_exp") + echo $output + # return success only in case of non-empty output + [ ! -z "$output" ] +} + lldpad_app_wait_set() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 9d3b64a2a264..315e934358d4 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -8,18 +8,9 @@ tc_check_packets() local id=$1 local handle=$2 local count=$3 - local ret - output="$(tc -j -s filter show $id)" - # workaround the jq bug which causes jq to return 0 in case input is "" - ret=$? - if [[ $ret -ne 0 ]]; then - return $ret - fi - echo $output | \ - jq -e ".[] \ - | select(.options.handle == $handle) \ - | select(.options.actions[0].stats.packets == $count)" \ - &> /dev/null - return $? + cmd_jq "tc -j -s filter show $id" \ + ".[] | select(.options.handle == $handle) | \ + select(.options.actions[0].stats.packets == $count)" \ + &> /dev/null } diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh new file mode 100644 index 000000000000..5782433886fc --- /dev/null +++ b/tools/testing/selftests/net/l2tp.sh @@ -0,0 +1,382 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# L2TPv3 tunnel between 2 hosts +# +# host-1 | router | host-2 +# | | +# lo l2tp | | l2tp lo +# 172.16.101.1 172.16.1.1 | | 172.16.1.2 172.16.101.2 +# fc00:101::1 fc00:1::1 | | fc00:1::2 fc00:101::2 +# | | +# eth0 | | eth0 +# 10.1.1.1 | | 10.1.2.1 +# 2001:db8:1::1 | | 2001:db8:2::1 + +VERBOSE=0 +PAUSE_ON_FAIL=no + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +run_cmd() +{ + local ns + local cmd + local out + local rc + + ns="$1" + shift + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out=$(eval ip netns exec ${ns} ${cmd} 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +################################################################################ +# create namespaces and interconnects + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + [ -z "${addr}" ] && addr="-" + [ -z "${addr6}" ] && addr6="-" + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +################################################################################ +# test setup + +cleanup() +{ + local ns + + for ns in host-1 host-2 router + do + ip netns del ${ns} 2>/dev/null + done +} + +setup_l2tp_ipv4() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1041 peer_tunnel_id 1042 \ + encap ip local 10.1.1.1 remote 10.1.2.1 + ip -netns host-1 l2tp add session name l2tp4 tunnel_id 1041 \ + session_id 1041 peer_session_id 1042 + ip -netns host-1 link set dev l2tp4 up + ip -netns host-1 addr add dev l2tp4 172.16.1.1 peer 172.16.1.2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1042 peer_tunnel_id 1041 \ + encap ip local 10.1.2.1 remote 10.1.1.1 + ip -netns host-2 l2tp add session name l2tp4 tunnel_id 1042 \ + session_id 1042 peer_session_id 1041 + ip -netns host-2 link set dev l2tp4 up + ip -netns host-2 addr add dev l2tp4 172.16.1.2 peer 172.16.1.1 + + # + # add routes to loopback addresses + # + ip -netns host-1 ro add 172.16.101.2/32 via 172.16.1.2 + ip -netns host-2 ro add 172.16.101.1/32 via 172.16.1.1 +} + +setup_l2tp_ipv6() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1061 peer_tunnel_id 1062 \ + encap ip local 2001:db8:1::1 remote 2001:db8:2::1 + ip -netns host-1 l2tp add session name l2tp6 tunnel_id 1061 \ + session_id 1061 peer_session_id 1062 + ip -netns host-1 link set dev l2tp6 up + ip -netns host-1 addr add dev l2tp6 fc00:1::1 peer fc00:1::2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1062 peer_tunnel_id 1061 \ + encap ip local 2001:db8:2::1 remote 2001:db8:1::1 + ip -netns host-2 l2tp add session name l2tp6 tunnel_id 1062 \ + session_id 1062 peer_session_id 1061 + ip -netns host-2 link set dev l2tp6 up + ip -netns host-2 addr add dev l2tp6 fc00:1::2 peer fc00:1::1 + + # + # add routes to loopback addresses + # + ip -netns host-1 -6 ro add fc00:101::2/128 via fc00:1::2 + ip -netns host-2 -6 ro add fc00:101::1/128 via fc00:1::1 +} + +setup() +{ + # start clean + cleanup + + set -e + create_ns host-1 172.16.101.1/32 fc00:101::1/128 + create_ns host-2 172.16.101.2/32 fc00:101::2/128 + create_ns router + + connect_ns host-1 eth0 10.1.1.1/24 2001:db8:1::1/64 \ + router eth1 10.1.1.2/24 2001:db8:1::2/64 + + connect_ns host-2 eth0 10.1.2.1/24 2001:db8:2::1/64 \ + router eth2 10.1.2.2/24 2001:db8:2::2/64 + + ip -netns host-1 ro add 10.1.2.0/24 via 10.1.1.2 + ip -netns host-1 -6 ro add 2001:db8:2::/64 via 2001:db8:1::2 + + ip -netns host-2 ro add 10.1.1.0/24 via 10.1.2.2 + ip -netns host-2 -6 ro add 2001:db8:1::/64 via 2001:db8:2::2 + + setup_l2tp_ipv4 + setup_l2tp_ipv6 + set +e +} + +setup_ipsec() +{ + # + # IPv4 + # + run_cmd host-1 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + # + # IPV6 + # + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport +} + +teardown_ipsec() +{ + run_cmd host-1 ip xfrm state flush + run_cmd host-1 ip xfrm policy flush + run_cmd host-2 ip xfrm state flush + run_cmd host-2 ip xfrm policy flush +} + +################################################################################ +# generate traffic through tunnel for various cases + +run_ping() +{ + local desc="$1" + + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel ${desc}" +} + +run_tests() +{ + local desc + + setup + run_ping + + setup_ipsec + run_ping "- with IPsec" + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel - with IPsec" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel - with IPsec" + + teardown_ipsec + run_ping "- after IPsec teardown" +} + +################################################################################ +# main + +declare -i nfail=0 +declare -i nsuccess=0 + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + *) exit 1;; + esac +done + +run_tests +cleanup + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c new file mode 100644 index 000000000000..c08f4db8330d --- /dev/null +++ b/tools/testing/selftests/net/nettest.c @@ -0,0 +1,1757 @@ +// SPDX-License-Identifier: GPL-2.0 +/* nettest - used for functional tests of networking APIs + * + * Copyright (c) 2013-2019 David Ahern <dsahern@gmail.com>. All rights reserved. + */ + +#define _GNU_SOURCE +#include <features.h> +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <linux/tcp.h> +#include <arpa/inet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netdb.h> +#include <fcntl.h> +#include <libgen.h> +#include <limits.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <time.h> +#include <errno.h> + +#ifndef IPV6_UNICAST_IF +#define IPV6_UNICAST_IF 76 +#endif +#ifndef IPV6_MULTICAST_IF +#define IPV6_MULTICAST_IF 17 +#endif + +#define DEFAULT_PORT 12345 + +#ifndef MAX +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +#endif +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + +struct sock_args { + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } local_addr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } remote_addr; + int scope_id; /* remote scope; v6 send only */ + + struct in_addr grp; /* multicast group */ + + unsigned int has_local_ip:1, + has_remote_ip:1, + has_grp:1, + has_expected_laddr:1, + has_expected_raddr:1, + bind_test_only:1; + + unsigned short port; + + int type; /* DGRAM, STREAM, RAW */ + int protocol; + int version; /* AF_INET/AF_INET6 */ + + int use_setsockopt; + int use_cmsg; + const char *dev; + int ifindex; + const char *password; + + /* expected addresses and device index for connection */ + int expected_ifindex; + + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_laddr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_raddr; +}; + +static int server_mode; +static unsigned int prog_timeout = 5; +static unsigned int interactive; +static int iter = 1; +static char *msg = "Hello world!"; +static int msglen; +static int quiet; +static int try_broadcast = 1; + +static char *timestamp(char *timebuf, int buflen) +{ + time_t now; + + now = time(NULL); + if (strftime(timebuf, buflen, "%T", localtime(&now)) == 0) { + memset(timebuf, 0, buflen); + strncpy(timebuf, "00:00:00", buflen-1); + } + + return timebuf; +} + +static void log_msg(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stdout, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stdout, format, args); + va_end(args); + + fflush(stdout); +} + +static void log_error(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stderr, format, args); + va_end(args); + + fflush(stderr); +} + +static void log_err_errno(const char *fmt, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s: ", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, fmt); + vfprintf(stderr, fmt, args); + va_end(args); + + fprintf(stderr, ": %d: %s\n", errno, strerror(errno)); + fflush(stderr); +} + +static void log_address(const char *desc, struct sockaddr *sa) +{ + char addrstr[64]; + + if (quiet) + return; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + + log_msg("%s %s:%d", + desc, + inet_ntop(AF_INET, &s->sin_addr, addrstr, + sizeof(addrstr)), + ntohs(s->sin_port)); + + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + log_msg("%s [%s]:%d", + desc, + inet_ntop(AF_INET6, &s6->sin6_addr, addrstr, + sizeof(addrstr)), + ntohs(s6->sin6_port)); + } + + printf("\n"); + + fflush(stdout); +} + +static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +{ + struct tcp_md5sig md5sig; + int keylen = password ? strlen(password) : 0; + int rc; + + memset(&md5sig, 0, sizeof(md5sig)); + memcpy(&md5sig.tcpm_addr, addr, alen); + md5sig.tcpm_keylen = keylen; + + if (keylen) + memcpy(md5sig.tcpm_key, password, keylen); + + rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + if (rc < 0) { + /* ENOENT is harmless. Returned when a password is cleared */ + if (errno == ENOENT) + rc = 0; + else + log_err_errno("setsockopt(TCP_MD5SIG)"); + } + + return rc; +} + +static int tcp_md5_remote(int sd, struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + addr = &sin6; + alen = sizeof(sin6); + break; + default: + log_error("unknown address family\n"); + exit(1); + } + + if (tcp_md5sig(sd, addr, alen, args->password)) + return -1; + + return 0; +} + +static int get_ifidx(const char *ifname) +{ + struct ifreq ifdata; + int sd, rc; + + if (!ifname || *ifname == '\0') + return -1; + + memset(&ifdata, 0, sizeof(ifdata)); + + strcpy(ifdata.ifr_name, ifname); + + sd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); + if (sd < 0) { + log_err_errno("socket failed"); + return -1; + } + + rc = ioctl(sd, SIOCGIFINDEX, (char *)&ifdata); + close(sd); + if (rc != 0) { + log_err_errno("ioctl(SIOCGIFINDEX) failed"); + return -1; + } + + return ifdata.ifr_ifindex; +} + +static int bind_to_device(int sd, const char *name) +{ + int rc; + + rc = setsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, strlen(name)+1); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int get_bind_to_device(int sd, char *name, size_t len) +{ + int rc; + socklen_t optlen = len; + + name[0] = '\0'; + rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int check_device(int sd, struct sock_args *args) +{ + int ifindex = 0; + char name[32]; + + if (get_bind_to_device(sd, name, sizeof(name))) + *name = '\0'; + else + ifindex = get_ifidx(name); + + log_msg(" bound to device %s/%d\n", + *name ? name : "<none>", ifindex); + + if (!args->expected_ifindex) + return 0; + + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return 1; + } + + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + + return 0; +} + +static int set_pktinfo_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_PKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_PKTINFO)"); + + return rc; +} + +static int set_recvpktinfo_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVPKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVPKTINFO)"); + + return rc; +} + +static int set_recverr_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_RECVERR)"); + + return rc; +} + +static int set_recverr_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVERR)"); + + return rc; +} + +static int set_unicast_if(int sd, int ifindex, int version) +{ + int opt = IP_UNICAST_IF; + int level = SOL_IP; + int rc; + + ifindex = htonl(ifindex); + + if (version == AF_INET6) { + opt = IPV6_UNICAST_IF; + level = SOL_IPV6; + } + rc = setsockopt(sd, level, opt, &ifindex, sizeof(ifindex)); + if (rc < 0) + log_err_errno("setsockopt(IP_UNICAST_IF)"); + + return rc; +} + +static int set_multicast_if(int sd, int ifindex) +{ + struct ip_mreqn mreq = { .imr_ifindex = ifindex }; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_MULTICAST_IF, &mreq, sizeof(mreq)); + if (rc < 0) + log_err_errno("setsockopt(IP_MULTICAST_IF)"); + + return rc; +} + +static int set_membership(int sd, uint32_t grp, uint32_t addr, int ifindex) +{ + uint32_t if_addr = addr; + struct ip_mreqn mreq; + int rc; + + if (addr == htonl(INADDR_ANY) && !ifindex) { + log_error("Either local address or device needs to be given for multicast membership\n"); + return -1; + } + + mreq.imr_multiaddr.s_addr = grp; + mreq.imr_address.s_addr = if_addr; + mreq.imr_ifindex = ifindex; + + rc = setsockopt(sd, IPPROTO_IP, IP_ADD_MEMBERSHIP, &mreq, sizeof(mreq)); + if (rc < 0) { + log_err_errno("setsockopt(IP_ADD_MEMBERSHIP)"); + return -1; + } + + return 0; +} + +static int set_broadcast(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_BROADCAST)"); + rc = -1; + } + + return rc; +} + +static int set_reuseport(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEPORT)"); + rc = -1; + } + + return rc; +} + +static int set_reuseaddr(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEADDR)"); + rc = -1; + } + + return rc; +} + +static int str_to_uint(const char *str, int min, int max, unsigned int *value) +{ + int number; + char *end; + + errno = 0; + number = (unsigned int) strtoul(str, &end, 0); + + /* entire string should be consumed by conversion + * and value should be between min and max + */ + if (((*end == '\0') || (*end == '\n')) && (end != str) && + (errno != ERANGE) && (min <= number) && (number <= max)) { + *value = number; + return 0; + } + + return -1; +} + +static int expected_addr_match(struct sockaddr *sa, void *expected, + const char *desc) +{ + char addrstr[64]; + int rc = 0; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + struct in_addr *exp_in = (struct in_addr *) expected; + + if (s->sin_addr.s_addr != exp_in->s_addr) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *exp_in = (struct in6_addr *) expected; + + if (memcmp(&s6->sin6_addr, exp_in, sizeof(*exp_in))) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET6, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else { + log_error("%s address does not match expected - unknown family", + desc); + rc = 1; + } + + if (!rc) + log_msg("%s address matches expected\n", desc); + + return rc; +} + +static int show_sockstat(int sd, struct sock_args *args) +{ + struct sockaddr_in6 local_addr, remote_addr; + socklen_t alen = sizeof(local_addr); + struct sockaddr *sa; + const char *desc; + int rc = 0; + + desc = server_mode ? "server local:" : "client local:"; + sa = (struct sockaddr *) &local_addr; + if (getsockname(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_laddr) { + rc = expected_addr_match(sa, &args->expected_laddr, + "local"); + } + } else { + log_err_errno("getsockname failed"); + } + + sa = (struct sockaddr *) &remote_addr; + desc = server_mode ? "server peer:" : "client peer:"; + if (getpeername(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_raddr) { + rc |= expected_addr_match(sa, &args->expected_raddr, + "remote"); + } + } else { + log_err_errno("getpeername failed"); + } + + return rc; +} + +static int get_index_from_cmsg(struct msghdr *m) +{ + struct cmsghdr *cm; + int ifindex = 0; + char buf[64]; + + for (cm = (struct cmsghdr *)CMSG_FIRSTHDR(m); + m->msg_controllen != 0 && cm; + cm = (struct cmsghdr *)CMSG_NXTHDR(m, cm)) { + + if (cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_PKTINFO) { + struct in_pktinfo *pi; + + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET, &pi->ipi_addr, buf, sizeof(buf)); + ifindex = pi->ipi_ifindex; + } else if (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *pi6; + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET6, &pi6->ipi6_addr, buf, sizeof(buf)); + ifindex = pi6->ipi6_ifindex; + } + } + + if (ifindex) { + log_msg(" pktinfo: ifindex %d dest addr %s\n", + ifindex, buf); + } + return ifindex; +} + +static int send_msg_no_cmsg(int sd, void *addr, socklen_t alen) +{ + int err; + +again: + err = sendto(sd, msg, msglen, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendto failed"); + return 1; + } + + return 0; +} + +static int send_msg_cmsg(int sd, void *addr, socklen_t alen, + int ifindex, int version) +{ + unsigned char cmsgbuf[64]; + struct iovec iov[2]; + struct cmsghdr *cm; + struct msghdr m; + int err; + + iov[0].iov_base = msg; + iov[0].iov_len = msglen; + m.msg_iov = iov; + m.msg_iovlen = 1; + m.msg_name = (caddr_t)addr; + m.msg_namelen = alen; + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + cm = (struct cmsghdr *)cmsgbuf; + m.msg_control = (caddr_t)cm; + + if (version == AF_INET) { + struct in_pktinfo *pi; + + cm->cmsg_level = SOL_IP; + cm->cmsg_type = IP_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + pi->ipi_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + + } else if (version == AF_INET6) { + struct in6_pktinfo *pi6; + + cm->cmsg_level = SOL_IPV6; + cm->cmsg_type = IPV6_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + pi6->ipi6_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + } + +again: + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendmsg failed"); + return 1; + } + + return 0; +} + + +static int send_msg(int sd, void *addr, socklen_t alen, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) { + if (write(sd, msg, msglen) < 0) { + log_err_errno("write failed sending msg to peer"); + return 1; + } + } else if (args->ifindex && args->use_cmsg) { + if (send_msg_cmsg(sd, addr, alen, args->ifindex, args->version)) + return 1; + } else { + if (send_msg_no_cmsg(sd, addr, alen)) + return 1; + } + + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", msg, msglen > 24 ? " ..." : ""); + + return 0; +} + +static int socket_read_dgram(int sd, struct sock_args *args) +{ + unsigned char addr[sizeof(struct sockaddr_in6)]; + struct sockaddr *sa = (struct sockaddr *) addr; + socklen_t alen = sizeof(addr); + struct iovec iov[2]; + struct msghdr m = { + .msg_name = (caddr_t)addr, + .msg_namelen = alen, + .msg_iov = iov, + .msg_iovlen = 1, + }; + unsigned char cmsgbuf[256]; + struct cmsghdr *cm = (struct cmsghdr *)cmsgbuf; + char buf[16*1024]; + int ifindex; + int len; + + iov[0].iov_base = (caddr_t)buf; + iov[0].iov_len = sizeof(buf); + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + m.msg_control = (caddr_t)cm; + m.msg_controllen = sizeof(cmsgbuf); + + len = recvmsg(sd, &m, 0); + if (len == 0) { + log_msg("peer closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message: %d: %s\n", + errno, strerror(errno)); + return -1; + } + + buf[len] = '\0'; + + log_address("Message from:", sa); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + ifindex = get_index_from_cmsg(&m); + if (args->expected_ifindex) { + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return -1; + } + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + } + + if (!interactive && server_mode) { + if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *in6 = &s6->sin6_addr; + + if (IN6_IS_ADDR_V4MAPPED(in6)) { + const uint32_t *pa = (uint32_t *) &in6->s6_addr; + struct in_addr in4; + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *) addr; + pa += 3; + in4.s_addr = *pa; + sin->sin_addr = in4; + sin->sin_family = AF_INET; + if (send_msg_cmsg(sd, addr, alen, + ifindex, AF_INET) < 0) + goto out_err; + } + } +again: + iov[0].iov_len = len; + + if (args->version == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + if (args->dev) { + /* avoid PKTINFO conflicts with bindtodev */ + if (sendto(sd, buf, len, 0, + (void *) addr, alen) < 0) + goto out_err; + } else { + /* kernel is allowing scope_id to be set to VRF + * index for LLA. for sends to global address + * reset scope id + */ + s6->sin6_scope_id = ifindex; + if (sendmsg(sd, &m, 0) < 0) + goto out_err; + } + } else { + int err; + + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + goto out_err; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +out_err: + log_err_errno("failed to send msg to peer"); + return -1; +} + +static int socket_read_stream(int sd) +{ + char buf[1024]; + int len; + + len = read(sd, buf, sizeof(buf)-1); + if (len == 0) { + log_msg("client closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message\n"); + return -1; + } + + buf[len] = '\0'; + log_msg("Incoming message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + if (!interactive && server_mode) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +} + +static int socket_read(int sd, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) + return socket_read_stream(sd); + + return socket_read_dgram(sd, args); +} + +static int stdin_to_socket(int sd, int type, void *addr, socklen_t alen) +{ + char buf[1024]; + int len; + + if (fgets(buf, sizeof(buf), stdin) == NULL) + return 0; + + len = strlen(buf); + if (type == SOCK_STREAM) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + } else { + int err; + +again: + err = sendto(sd, buf, len, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + log_err_errno("failed to send msg to peer"); + return -1; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + return 1; +} + +static void set_recv_attr(int sd, int version) +{ + if (version == AF_INET6) { + set_recvpktinfo_v6(sd); + set_recverr_v6(sd); + } else { + set_pktinfo_v4(sd); + set_recverr_v4(sd); + } +} + +static int msg_loop(int client, int sd, void *addr, socklen_t alen, + struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + fd_set rfds; + int nfds; + int rc; + + if (args->type != SOCK_STREAM) + set_recv_attr(sd, args->version); + + if (msg) { + msglen = strlen(msg); + + /* client sends first message */ + if (client) { + if (send_msg(sd, addr, alen, args)) + return 1; + } + if (!interactive) { + ptval = &timeout; + if (!prog_timeout) + timeout.tv_sec = 5; + } + } + + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + while (1) { + FD_ZERO(&rfds); + FD_SET(sd, &rfds); + if (interactive) + FD_SET(fileno(stdin), &rfds); + + rc = select(nfds, &rfds, NULL, NULL, ptval); + if (rc < 0) { + if (errno == EINTR) + continue; + + rc = 1; + log_err_errno("select failed"); + break; + } else if (rc == 0) { + log_error("Timed out waiting for response\n"); + rc = 2; + break; + } + + if (FD_ISSET(sd, &rfds)) { + rc = socket_read(sd, args); + if (rc < 0) { + rc = 1; + break; + } + if (rc == 0) + break; + } + + rc = 0; + + if (FD_ISSET(fileno(stdin), &rfds)) { + if (stdin_to_socket(sd, args->type, addr, alen) <= 0) + break; + } + + if (interactive) + continue; + + if (iter != -1) { + --iter; + if (iter == 0) + break; + } + + log_msg("Going into quiet mode\n"); + quiet = 1; + + if (client) { + if (send_msg(sd, addr, alen, args)) { + rc = 1; + break; + } + } + } + + return rc; +} + +static int msock_init(struct sock_args *args, int server) +{ + uint32_t if_addr = htonl(INADDR_ANY); + struct sockaddr_in laddr = { + .sin_family = AF_INET, + .sin_port = htons(args->port), + }; + int one = 1; + int sd; + + if (!server && args->has_local_ip) + if_addr = args->local_addr.in.s_addr; + + sd = socket(PF_INET, SOCK_DGRAM, 0); + if (sd < 0) { + log_err_errno("socket"); + return -1; + } + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)) < 0) { + log_err_errno("Setting SO_REUSEADDR error"); + goto out_err; + } + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, + (char *)&one, sizeof(one)) < 0) + log_err_errno("Setting SO_BROADCAST error"); + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto out_err; + else if (args->use_setsockopt && + set_multicast_if(sd, args->ifindex)) + goto out_err; + + laddr.sin_addr.s_addr = if_addr; + + if (bind(sd, (struct sockaddr *) &laddr, sizeof(laddr)) < 0) { + log_err_errno("bind failed"); + goto out_err; + } + + if (server && + set_membership(sd, args->grp.s_addr, + args->local_addr.in.s_addr, args->ifindex)) + goto out_err; + + return sd; +out_err: + close(sd); + return -1; +} + +static int msock_server(struct sock_args *args) +{ + return msock_init(args, 1); +} + +static int msock_client(struct sock_args *args) +{ + return msock_init(args, 0); +} + +static int bind_socket(int sd, struct sock_args *args) +{ + struct sockaddr_in serv_addr = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 serv6_addr = { + .sin6_family = AF_INET6, + }; + void *addr; + socklen_t alen; + + if (!args->has_local_ip && args->type == SOCK_RAW) + return 0; + + switch (args->version) { + case AF_INET: + serv_addr.sin_port = htons(args->port); + serv_addr.sin_addr = args->local_addr.in; + addr = &serv_addr; + alen = sizeof(serv_addr); + break; + + case AF_INET6: + serv6_addr.sin6_port = htons(args->port); + serv6_addr.sin6_addr = args->local_addr.in6; + addr = &serv6_addr; + alen = sizeof(serv6_addr); + break; + + default: + log_error("Invalid address family\n"); + return -1; + } + + if (bind(sd, addr, alen) < 0) { + log_err_errno("error binding socket"); + return -1; + } + + return 0; +} + +static int lsock_init(struct sock_args *args) +{ + long flags; + int sd; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Error opening socket"); + return -1; + } + + if (set_reuseaddr(sd) != 0) + goto err; + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (bind_socket(sd, args)) + goto err; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM && listen(sd, 1) < 0) { + log_err_errno("listen failed"); + goto err; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0) + log_err_errno("Failed to set close-on-exec flag"); + +out: + return sd; + +err: + close(sd); + return -1; +} + +static int do_server(struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + unsigned char addr[sizeof(struct sockaddr_in6)] = {}; + socklen_t alen = sizeof(addr); + int lsd, csd = -1; + + fd_set rfds; + int rc; + + if (prog_timeout) + ptval = &timeout; + + if (args->has_grp) + lsd = msock_server(args); + else + lsd = lsock_init(args); + + if (lsd < 0) + return 1; + + if (args->bind_test_only) { + close(lsd); + return 0; + } + + if (args->type != SOCK_STREAM) { + rc = msg_loop(0, lsd, (void *) addr, alen, args); + close(lsd); + return rc; + } + + if (args->password && tcp_md5_remote(lsd, args)) { + close(lsd); + return -1; + } + + while (1) { + log_msg("\n"); + log_msg("waiting for client connection.\n"); + FD_ZERO(&rfds); + FD_SET(lsd, &rfds); + + rc = select(lsd+1, &rfds, NULL, NULL, ptval); + if (rc == 0) { + rc = 2; + break; + } + + if (rc < 0) { + if (errno == EINTR) + continue; + + log_err_errno("select failed"); + break; + } + + if (FD_ISSET(lsd, &rfds)) { + + csd = accept(lsd, (void *) addr, &alen); + if (csd < 0) { + log_err_errno("accept failed"); + break; + } + + rc = show_sockstat(csd, args); + if (rc) + break; + + rc = check_device(csd, args); + if (rc) + break; + } + + rc = msg_loop(0, csd, (void *) addr, alen, args); + close(csd); + + if (!interactive) + break; + } + + close(lsd); + + return rc; +} + +static int wait_for_connect(int sd) +{ + struct timeval _tv = { .tv_sec = prog_timeout }, *tv = NULL; + fd_set wfd; + int val = 0, sz = sizeof(val); + int rc; + + FD_ZERO(&wfd); + FD_SET(sd, &wfd); + + if (prog_timeout) + tv = &_tv; + + rc = select(FD_SETSIZE, NULL, &wfd, NULL, tv); + if (rc == 0) { + log_error("connect timed out\n"); + return -2; + } else if (rc < 0) { + log_err_errno("select failed"); + return -3; + } + + if (getsockopt(sd, SOL_SOCKET, SO_ERROR, &val, (socklen_t *)&sz) < 0) { + log_err_errno("getsockopt(SO_ERROR) failed"); + return -4; + } + + if (val != 0) { + log_error("connect failed: %d: %s\n", val, strerror(val)); + return -1; + } + + return 0; +} + +static int connectsock(void *addr, socklen_t alen, struct sock_args *args) +{ + int sd, rc = -1; + long flags; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Failed to create socket"); + return -1; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (args->has_local_ip && bind_socket(sd, args)) + goto err; + + if (args->type != SOCK_STREAM) + goto out; + + if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + goto err; + + if (args->bind_test_only) + goto out; + + if (connect(sd, addr, alen) < 0) { + if (errno != EINPROGRESS) { + log_err_errno("Failed to connect to remote host"); + rc = -1; + goto err; + } + rc = wait_for_connect(sd); + if (rc < 0) + goto err; + } +out: + return sd; + +err: + close(sd); + return rc; +} + +static int do_client(struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + int rc = 0; + int sd; + + if (!args->has_remote_ip && !args->has_grp) { + fprintf(stderr, "remote IP or multicast group not given\n"); + return 1; + } + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + if (args->has_grp) + sin.sin_addr = args->grp; + else + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + sin6.sin6_scope_id = args->scope_id; + addr = &sin6; + alen = sizeof(sin6); + break; + } + + if (args->has_grp) + sd = msock_client(args); + else + sd = connectsock(addr, alen, args); + + if (sd < 0) + return -sd; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM) { + rc = show_sockstat(sd, args); + if (rc != 0) + goto out; + } + + rc = msg_loop(1, sd, addr, alen, args); + +out: + close(sd); + + return rc; +} + +enum addr_type { + ADDR_TYPE_LOCAL, + ADDR_TYPE_REMOTE, + ADDR_TYPE_MCAST, + ADDR_TYPE_EXPECTED_LOCAL, + ADDR_TYPE_EXPECTED_REMOTE, +}; + +static int convert_addr(struct sock_args *args, const char *_str, + enum addr_type atype) +{ + int family = args->version; + struct in6_addr *in6; + struct in_addr *in; + const char *desc; + char *str, *dev; + void *addr; + int rc = 0; + + str = strdup(_str); + if (!str) + return -ENOMEM; + + switch (atype) { + case ADDR_TYPE_LOCAL: + desc = "local"; + addr = &args->local_addr; + break; + case ADDR_TYPE_REMOTE: + desc = "remote"; + addr = &args->remote_addr; + break; + case ADDR_TYPE_MCAST: + desc = "mcast grp"; + addr = &args->grp; + break; + case ADDR_TYPE_EXPECTED_LOCAL: + desc = "expected local"; + addr = &args->expected_laddr; + break; + case ADDR_TYPE_EXPECTED_REMOTE: + desc = "expected remote"; + addr = &args->expected_raddr; + break; + default: + log_error("unknown address type"); + exit(1); + } + + switch (family) { + case AF_INET: + in = (struct in_addr *) addr; + if (str) { + if (inet_pton(AF_INET, str, in) == 0) { + log_error("Invalid %s IP address\n", desc); + rc = -1; + goto out; + } + } else { + in->s_addr = htonl(INADDR_ANY); + } + break; + + case AF_INET6: + dev = strchr(str, '%'); + if (dev) { + *dev = '\0'; + dev++; + } + + in6 = (struct in6_addr *) addr; + if (str) { + if (inet_pton(AF_INET6, str, in6) == 0) { + log_error("Invalid %s IPv6 address\n", desc); + rc = -1; + goto out; + } + } else { + *in6 = in6addr_any; + } + if (dev) { + args->scope_id = get_ifidx(dev); + if (args->scope_id < 0) { + log_error("Invalid scope on %s IPv6 address\n", + desc); + rc = -1; + goto out; + } + } + break; + + default: + log_error("Invalid address family\n"); + } + +out: + free(str); + return rc; +} + +static char *random_msg(int len) +{ + int i, n = 0, olen = len + 1; + char *m; + + if (len <= 0) + return NULL; + + m = malloc(olen); + if (!m) + return NULL; + + while (len > 26) { + i = snprintf(m + n, olen - n, "%.26s", + "abcdefghijklmnopqrstuvwxyz"); + n += i; + len -= i; + } + i = snprintf(m + n, olen - n, "%.*s", len, + "abcdefghijklmnopqrstuvwxyz"); + return m; +} + +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" + +static void print_usage(char *prog) +{ + printf( + "usage: %s OPTS\n" + "Required:\n" + " -r addr remote address to connect to (client mode only)\n" + " -p port port to connect to (client mode)/listen on (server mode)\n" + " (default: %d)\n" + " -s server mode (default: client mode)\n" + " -t timeout seconds (default: none)\n" + "\n" + "Optional:\n" + " -F Restart server loop\n" + " -6 IPv6 (default is IPv4)\n" + " -P proto protocol for socket: icmp, ospf (default: none)\n" + " -D|R datagram (D) / raw (R) socket (default stream)\n" + " -l addr local address to bind to\n" + "\n" + " -d dev bind socket to given device name\n" + " -S use setsockopt (IP_UNICAST_IF or IP_MULTICAST_IF)\n" + " to set device binding\n" + " -C use cmsg and IP_PKTINFO to specify device binding\n" + "\n" + " -L len send random message of given length\n" + " -n num number of times to send message\n" + "\n" + " -M password use MD5 sum protection\n" + " -g grp multicast group (e.g., 239.1.1.1)\n" + " -i interactive mode (default is echo and terminate)\n" + "\n" + " -0 addr Expected local address\n" + " -1 addr Expected remote address\n" + " -2 dev Expected device name (or index) to receive packet\n" + "\n" + " -b Bind test only.\n" + " -q Be quiet. Run test without printing anything.\n" + , prog, DEFAULT_PORT); +} + +int main(int argc, char *argv[]) +{ + struct sock_args args = { + .version = AF_INET, + .type = SOCK_STREAM, + .port = DEFAULT_PORT, + }; + struct protoent *pe; + unsigned int tmp; + int forever = 0; + + /* process inputs */ + extern char *optarg; + int rc = 0; + + /* + * process input args + */ + + while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + switch (rc) { + case 's': + server_mode = 1; + break; + case 'F': + forever = 1; + break; + case 'l': + args.has_local_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_LOCAL) < 0) + return 1; + break; + case 'r': + args.has_remote_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_REMOTE) < 0) + return 1; + break; + case 'p': + if (str_to_uint(optarg, 1, 65535, &tmp) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + args.port = (unsigned short) tmp; + break; + case 't': + if (str_to_uint(optarg, 0, INT_MAX, + &prog_timeout) != 0) { + fprintf(stderr, "Invalid timeout\n"); + return 1; + } + break; + case 'D': + args.type = SOCK_DGRAM; + break; + case 'R': + args.type = SOCK_RAW; + args.port = 0; + break; + case 'P': + pe = getprotobyname(optarg); + if (pe) { + args.protocol = pe->p_proto; + } else { + if (str_to_uint(optarg, 0, 0xffff, &tmp) != 0) { + fprintf(stderr, "Invalid protocol\n"); + return 1; + } + args.protocol = tmp; + } + break; + case 'n': + iter = atoi(optarg); + break; + case 'L': + msg = random_msg(atoi(optarg)); + break; + case 'M': + args.password = optarg; + break; + case 'S': + args.use_setsockopt = 1; + break; + case 'C': + args.use_cmsg = 1; + break; + case 'd': + args.dev = optarg; + args.ifindex = get_ifidx(optarg); + if (args.ifindex < 0) { + fprintf(stderr, "Invalid device name\n"); + return 1; + } + break; + case 'i': + interactive = 1; + break; + case 'g': + args.has_grp = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_MCAST) < 0) + return 1; + args.type = SOCK_DGRAM; + break; + case '6': + args.version = AF_INET6; + break; + case 'b': + args.bind_test_only = 1; + break; + case '0': + args.has_expected_laddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_LOCAL)) + return 1; + break; + case '1': + args.has_expected_raddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_REMOTE)) + return 1; + + break; + case '2': + if (str_to_uint(optarg, 0, INT_MAX, &tmp) == 0) { + args.expected_ifindex = (int)tmp; + } else { + args.expected_ifindex = get_ifidx(optarg); + if (args.expected_ifindex < 0) { + fprintf(stderr, + "Invalid expected device\n"); + return 1; + } + } + break; + case 'q': + quiet = 1; + break; + default: + print_usage(argv[0]); + return 1; + } + } + + if (args.password && + (!args.has_remote_ip || args.type != SOCK_STREAM)) { + log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); + return 1; + } + + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { + fprintf(stderr, "Device binding not specified\n"); + return 1; + } + if (args.use_setsockopt || args.use_cmsg) + args.dev = NULL; + + if (iter == 0) { + fprintf(stderr, "Invalid number of messages to send\n"); + return 1; + } + + if (args.type == SOCK_STREAM && !args.protocol) + args.protocol = IPPROTO_TCP; + if (args.type == SOCK_DGRAM && !args.protocol) + args.protocol = IPPROTO_UDP; + + if ((args.type == SOCK_STREAM || args.type == SOCK_DGRAM) && + args.port == 0) { + fprintf(stderr, "Invalid port number\n"); + return 1; + } + + if (!server_mode && !args.has_grp && + !args.has_remote_ip && !args.has_local_ip) { + fprintf(stderr, + "Local (server mode) or remote IP (client IP) required\n"); + return 1; + } + + if (interactive) { + prog_timeout = 0; + msg = NULL; + } + + if (server_mode) { + do { + rc = do_server(&args); + } while (forever); + + return rc; + } + return do_client(&args); +} diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index 22e5da9008fd..b0954c873e2f 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -128,7 +128,9 @@ optional arguments: -v, --verbose Show the commands that are being run -N, --notap Suppress tap results for command under test -d DEVICE, --device DEVICE - Execute the test case in flower category + Execute test cases that use a physical device, where + DEVICE is its name. (If not defined, tests that require + a physical device will be skipped) -P, --pause Pause execution just before post-suite stage selection: diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json b/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json index 9002714b1851..c2a433a4737e 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/concurrency.json @@ -12,7 +12,7 @@ "$TC qdisc add dev $DEV2 ingress", "./tdc_multibatch.py $DEV2 $BATCH_DIR 100000 10 add" ], - "cmdUnderTest": "find $BATCH_DIR/add* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/add* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -37,7 +37,7 @@ "$TC -b $BATCH_DIR/add_0", "./tdc_multibatch.py $DEV2 $BATCH_DIR 100000 10 del" ], - "cmdUnderTest": "find $BATCH_DIR/del* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/del* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -62,7 +62,7 @@ "$TC -b $BATCH_DIR/add_0", "./tdc_multibatch.py $DEV2 $BATCH_DIR 100000 10 replace" ], - "cmdUnderTest": "find $BATCH_DIR/replace* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/replace* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -87,7 +87,7 @@ "$TC -b $BATCH_DIR/add_0", "./tdc_multibatch.py -d $DEV2 $BATCH_DIR 100000 10 replace" ], - "cmdUnderTest": "find $BATCH_DIR/replace* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/replace* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -112,7 +112,7 @@ "$TC -b $BATCH_DIR/add_0", "./tdc_multibatch.py -d $DEV2 $BATCH_DIR 100000 10 del" ], - "cmdUnderTest": "find $BATCH_DIR/del* -print | xargs -n 1 -P 10 $TC -f -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/del* -print | xargs -n 1 -P 10 $TC -f -b\"", "expExitCode": "123", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -134,11 +134,11 @@ "/bin/mkdir $BATCH_DIR", "$TC qdisc add dev $DEV2 ingress", "./tdc_multibatch.py -x init_ $DEV2 $BATCH_DIR 100000 5 add", - "find $BATCH_DIR/init_* -print | xargs -n 1 -P 5 $TC -b", + "bash -c \"find $BATCH_DIR/init_* -print | xargs -n 1 -P 5 $TC -b\"", "./tdc_multibatch.py -x par_ -a 500001 -m 5 $DEV2 $BATCH_DIR 100000 5 add", "./tdc_multibatch.py -x par_ $DEV2 $BATCH_DIR 100000 5 del" ], - "cmdUnderTest": "find $BATCH_DIR/par_* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/par_* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", @@ -160,11 +160,11 @@ "/bin/mkdir $BATCH_DIR", "$TC qdisc add dev $DEV2 ingress", "./tdc_multibatch.py -x init_ $DEV2 $BATCH_DIR 100000 10 add", - "find $BATCH_DIR/init_* -print | xargs -n 1 -P 5 $TC -b", + "bash -c \"find $BATCH_DIR/init_* -print | xargs -n 1 -P 5 $TC -b\"", "./tdc_multibatch.py -x par_ -a 500001 -m 5 $DEV2 $BATCH_DIR 100000 5 replace", "./tdc_multibatch.py -x par_ $DEV2 $BATCH_DIR 100000 5 del" ], - "cmdUnderTest": "find $BATCH_DIR/par_* -print | xargs -n 1 -P 10 $TC -b", + "cmdUnderTest": "bash -c \"find $BATCH_DIR/par_* -print | xargs -n 1 -P 10 $TC -b\"", "expExitCode": "0", "verifyCmd": "$TC -s filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json new file mode 100644 index 000000000000..51799874a972 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json @@ -0,0 +1,391 @@ +[ + { + "id": "f62b", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f09", + "name": "Add egress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent 1: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0596", + "name": "Add ingress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "41df", + "name": "Add egress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent 1: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e1da", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "3de5", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "72d7", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "41d3", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f755", + "name": "Add ingress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2c33", + "name": "Add egress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0e4a", + "name": "Add ingress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f60", + "name": "Add egress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent 1: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: prio", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8bd2", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:1 action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2a4a", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with invalid classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 6789defg action pass", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 6789defg.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "eaf8", + "name": "Delete single ingress matchall filter", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress", + "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:2 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:2.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "76ad", + "name": "Delete all ingress matchall filters", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress", + "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DUMMY parent ffff:", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DUMMY parent ffff:", + "matchPattern": "^filter protocol all pref.*matchall.*handle.*flowid.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "1eb9", + "name": "Delete single ingress matchall filter out of multiple", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress", + "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DUMMY parent ffff: protocol all handle 0x2 prio 2 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DUMMY parent ffff:", + "matchPattern": "^filter protocol all pref 2 matchall.*handle 0x2 flowid 1:2.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "6d63", + "name": "Delete ingress matchall filter by chain ID", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress", + "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all chain 1 matchall classid 1:1 action pass", + "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv4 chain 2 matchall classid 1:3 action continue" + ], + "cmdUnderTest": "$TC filter del dev $DUMMY parent ffff: chain 2", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DUMMY parent ffff:", + "matchPattern": "^filter protocol all pref 1 matchall chain 1 handle 0x1 flowid 1:1.*gact action pass", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json new file mode 100644 index 000000000000..5ecd93b4c473 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json @@ -0,0 +1,304 @@ +[ + { + "id": "a519", + "name": "Add bfifo qdisc with system default parameters on egress", + "__comment": "When omitted, queue size in bfifo is calculated as: txqueuelen * (MTU + LinkLayerHdrSize), where LinkLayerHdrSize=14 for Ethernet", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root.*limit [0-9]+b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root bfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "585c", + "name": "Add pfifo qdisc with system default parameters on egress", + "__comment": "When omitted, queue size in pfifo is defaulted to the interface's txqueuelen value.", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc pfifo 1: root.*limit [0-9]+p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root pfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "a86e", + "name": "Add bfifo qdisc with system default parameters on egress with handle of maximum value", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle ffff: bfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo ffff: root.*limit [0-9]+b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle ffff: root bfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9ac8", + "name": "Add bfifo qdisc on egress with queue size of 3000 bytes", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo limit 3000b", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root.*limit 3000b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root bfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f4e6", + "name": "Add pfifo qdisc on egress with queue size of 3000 packets", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY txqueuelen 3000 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo limit 3000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc pfifo 1: root.*limit 3000p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root pfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b1b1", + "name": "Add bfifo qdisc with system default parameters on egress with invalid handle exceeding maximum value", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 10000: bfifo", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 10000: root.*limit [0-9]+b", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8d5e", + "name": "Add bfifo qdisc on egress with unsupported argument", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo foorbar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7787", + "name": "Add pfifo qdisc on egress with unsupported argument", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo foorbar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc pfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c4b6", + "name": "Replace bfifo qdisc on egress with new queue size", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link del dev $DUMMY type dummy || /bin/true", + "$IP link add dev $DUMMY txqueuelen 1000 type dummy", + "$TC qdisc add dev $DUMMY handle 1: root bfifo" + ], + "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root bfifo limit 3000b", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root.*limit 3000b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root bfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "3df6", + "name": "Replace pfifo qdisc on egress with new queue size", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link del dev $DUMMY type dummy || /bin/true", + "$IP link add dev $DUMMY txqueuelen 1000 type dummy", + "$TC qdisc add dev $DUMMY handle 1: root pfifo" + ], + "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root pfifo limit 30", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc pfifo 1: root.*limit 30p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root pfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7a67", + "name": "Add bfifo qdisc on egress with queue size in invalid format", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo limit foo-bar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root.*limit foo-bar", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "1298", + "name": "Add duplicate bfifo qdisc on egress", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root bfifo" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root bfifo", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "45a0", + "name": "Delete nonexistent bfifo qdisc", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY root handle 1: bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "972b", + "name": "Add prio qdisc on egress with invalid format for handles", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 123^ bfifo limit 100b", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 123 root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4d39", + "name": "Delete bfifo qdisc twice", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: bfifo", + "$TC qdisc del dev $DUMMY root handle 1: bfifo" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json index f518c55f468b..d99dba6e2b1a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json @@ -7,16 +7,16 @@ "ingress" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress", + "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress", "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 ingress", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -27,15 +27,15 @@ "ingress" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress foorbar", + "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress foorbar", "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -46,17 +46,17 @@ "ingress" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true", - "$TC qdisc add dev $DEV1 ingress" + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress", + "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 ingress", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY ingress", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -67,15 +67,15 @@ "ingress" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc del dev $DEV1 ingress", + "cmdUnderTest": "$TC qdisc del dev $DUMMY ingress", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -86,17 +86,17 @@ "ingress" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true", - "$TC qdisc add dev $DEV1 ingress", - "$TC qdisc del dev $DEV1 ingress" + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY ingress", + "$TC qdisc del dev $DUMMY ingress" ], - "cmdUnderTest": "$TC qdisc del dev $DEV1 ingress", + "cmdUnderTest": "$TC qdisc del dev $DUMMY ingress", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json index 9c792fa8ca23..3076c02d08d6 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json @@ -7,16 +7,16 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio", "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 handle 1: root prio", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY handle 1: root prio", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -27,15 +27,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle ffff: prio", + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle ffff: prio", "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio ffff: root", "matchCount": "1", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -46,15 +46,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle 10000: prio", + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 10000: prio", "expExitCode": "255", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 10000: root", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -65,15 +65,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio foorbar", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio foorbar", "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -84,16 +84,16 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0", "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 handle 1: root prio", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY handle 1: root prio", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -104,15 +104,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0 1 1", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0 1 1", "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0 1 1", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -123,15 +123,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio bands 4 priomap 1 1 2 2 7 5 0 0 1 2 3 0 0 0 0 0", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 7 5 0 0 1 2 3 0 0 0 0 0", "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 7 5 0 0 1 2 3 0 0 0 0 0", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -142,15 +142,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio bands 1 priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 1 priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 1 priomap.*0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -161,15 +161,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio bands 1024 priomap 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 1024 priomap 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 1024 priomap.*1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -180,17 +180,17 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true", - "$TC qdisc add dev $DEV1 handle 1: root prio" + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root prio" ], - "cmdUnderTest": "$TC qdisc replace dev $DEV1 handle 1: root prio bands 8 priomap 1 1 2 2 3 3 4 4 5 5 6 6 7 7 0 0", + "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root prio bands 8 priomap 1 1 2 2 3 3 4 4 5 5 6 6 7 7 0 0", "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root.*bands 8 priomap.*1 1 2 2 3 3 4 4 5 5 6 6 7 7 0 0", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 handle 1: root prio", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY handle 1: root prio", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -201,17 +201,17 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true", - "$TC qdisc add dev $DEV1 handle 1: root prio" + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root prio" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root prio", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root", "matchCount": "1", "teardown": [ - "$TC qdisc del dev $DEV1 handle 1: root prio", - "$IP link del dev $DEV1 type dummy" + "$TC qdisc del dev $DUMMY handle 1: root prio", + "$IP link del dev $DUMMY type dummy" ] }, { @@ -222,15 +222,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc del dev $DEV1 root handle 1: prio", + "cmdUnderTest": "$TC qdisc del dev $DUMMY root handle 1: prio", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 1: root", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -241,15 +241,15 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true" + "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle 123^ prio", + "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 123^ prio", "expExitCode": "255", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc prio 123 root", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] }, { @@ -260,17 +260,17 @@ "prio" ], "setup": [ - "$IP link add dev $DEV1 type dummy || /bin/true", - "$TC qdisc add dev $DEV1 root handle 1: prio", - "$TC qdisc del dev $DEV1 root handle 1: prio" + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: prio", + "$TC qdisc del dev $DUMMY root handle 1: prio" ], - "cmdUnderTest": "$TC qdisc del dev $DEV1 handle 1: root prio", + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root prio", "expExitCode": "2", - "verifyCmd": "$TC qdisc show dev $DEV1", + "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc ingress ffff:", "matchCount": "0", "teardown": [ - "$IP link del dev $DEV1 type dummy" + "$IP link del dev $DUMMY type dummy" ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index f04321ace9fb..e566c70e64a1 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -356,12 +356,14 @@ def test_runner(pm, args, filtered_tests): time.sleep(2) for tidx in testlist: if "flower" in tidx["category"] and args.device == None: + errmsg = "Tests using the DEV2 variable must define the name of a " + errmsg += "physical NIC with the -d option when running tdc.\n" + errmsg += "Test has been skipped." if args.verbose > 1: - print('Not executing test {} {} because DEV2 not defined'. - format(tidx['id'], tidx['name'])) + print(errmsg) res = TestResult(tidx['id'], tidx['name']) res.set_result(ResultState.skip) - res.set_errormsg('Not executed because DEV2 is not defined') + res.set_errormsg(errmsg) tsr.add_resultdata(res) continue try: @@ -499,7 +501,9 @@ def set_args(parser): choices=['none', 'xunit', 'tap'], help='Specify the format for test results. (Default: TAP)') parser.add_argument('-d', '--device', - help='Execute the test case in flower category') + help='Execute test cases that use a physical device, ' + + 'where DEVICE is its name. (If not defined, tests ' + + 'that require a physical device will be skipped)') parser.add_argument( '-P', '--pause', action='store_true', help='Pause execution just before post-suite stage') diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index b771d4c89621..080709cc4297 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -16,6 +16,7 @@ NAMES = { 'DEV0': 'v0p0', 'DEV1': 'v0p1', 'DEV2': '', + 'DUMMY': 'dummy1', 'BATCH_FILE': './batch.txt', 'BATCH_DIR': 'tmp', # Length of time in seconds to wait before terminating a command |