- 13 Mar, 2020 13 commits
-
-
Jiri Olsa authored
Adding name to 'struct bpf_ksym' object to carry the name of the symbol for bpf_prog, bpf_trampoline, bpf_dispatcher objects. The current benefit is that name is now generated only when the symbol is added to the list, so we don't need to generate it every time it's accessed. The future benefit is that we will have all the bpf objects symbols represented by struct bpf_ksym. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Acked-by:
Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200312195610.346362-5-jolsa@kernel.orgSigned-off-by:
-
Jiri Olsa authored
Adding 'struct bpf_ksym' object that will carry the kallsym information for bpf symbol. Adding the start and end address to begin with. It will be used by bpf_prog, bpf_trampoline, bpf_dispatcher objects. The symbol_start/symbol_end values were originally used to sort bpf_prog objects. For the address displayed in /proc/kallsyms we are using prog->bpf_func value. I'm using the bpf_func value for program symbol start instead of the symbol_start, because it makes no difference for sorting bpf_prog objects and we can use it directly as an address to display it in /proc/kallsyms. Signed-off-by:
-
Björn Töpel authored
Adding bpf_trampoline_ name prefix for DECLARE_BPF_DISPATCHER, so all the dispatchers have the common name prefix. And also a small '_' cleanup for bpf_dispatcher_nopfunc function name. Signed-off-by:
Björn Töpel <bjorn.topel@intel.com> Signed-off-by:
-
Jiri Olsa authored
The kbuild test robot reported compile issue on x86 in one of the following patches that adds <linux/kallsyms.h> include into <linux/bpf.h>, which is picked up by init_32.c object. The problem is that <linux/kallsyms.h> defines global function is_kernel_text which colides with the static function of the same name defined in init_32.c: $ make ARCH=i386 ... >> arch/x86/mm/init_32.c:241:19: error: redefinition of 'is_kernel_text' static inline int is_kernel_text(unsigned long addr) ^~~~~~~~~~~~~~ In file included from include/linux/bpf.h:21:0, from include/linux/bpf-cgroup.h:5, from include/linux/cgroup-defs.h:22, from include/linux/cgroup.h:28, from include/linux/hugetlb.h:9, from arch/x86/mm/init_32.c:18: include/linux/kallsyms.h:31:19: note: previous definition of 'is_kernel_text' was here static inline int is_kernel_text(unsigned long addr) Renaming the init_32.c is_kernel_text function to __is_kernel_text. Reported-by:kbuild test robot <lkp@intel.com> Signed-off-by:
-
Andrii Nakryiko authored
Instead of requiring users to do three steps for cleaning up bpf_link, its anon_inode file, and unused fd, abstract that away into bpf_link_cleanup() helper. bpf_link_defunct() is removed, as it shouldn't be needed as an individual operation anymore. v1->v2: - keep bpf_link_cleanup() static for now (Daniel). Signed-off-by:
Andrii Nakryiko <andriin@fb.com> Signed-off-by:
Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20200313002128.2028680-1-andriin@fb.comSigned-off-by:
-
Andrii Nakryiko authored
Switch to non-blocking accept and wait for server thread to exit before proceeding. I noticed that sometimes tcp_rtt server thread failure would "spill over" into other tests (that would run after tcp_rtt), probably just because server thread exits much later and tcp_rtt doesn't wait for it. v1->v2: - add usleep() while waiting on initial non-blocking accept() (Stanislav); Fixes: 8a03222f ("selftests/bpf: test_progs: fix client/server race in tcp_rtt") Signed-off-by:
Stanislav Fomichev <sdf@google.com> Link: https://lore.kernel.org/bpf/20200311222749.458015-1-andriin@fb.comSigned-off-by:
-
Andrii Nakryiko authored
Some implementations of C runtime library won't call nanosleep() syscall from usleep(). But a bunch of kprobe/tracepoint selftests rely on nanosleep being called to trigger them. To make this more reliable, "override" usleep implementation and call nanosleep explicitly. Signed-off-by:
-
Quentin Monnet authored
In commit 4a3d6c6a ("libbpf: Reduce log level for custom section names"), log level for messages for libbpf_attach_type_by_name() and libbpf_prog_type_by_name() was downgraded from "info" to "debug". The latter function, in particular, is used by bpftool when attempting to load programs, and this change caused bpftool to exit with no hint or error message when it fails to detect the type of the program to load (unless "-d" option was provided). To help users understand why bpftool fails to load the program, let's do a second run of the function with log level in "debug" mode in case of failure. Before: # bpftool prog load sample_ret0.o /sys/fs/bpf/sample_ret0 # echo $? 255 Or really verbose with -d flag: # bpftool -d prog load sample_ret0.o /sys/fs/bpf/sample_ret0 libbpf: loading sample_ret0.o libbpf: section(1) .strtab, size 134, link 0, flags 0, type=3 libbpf: skip section(1) .strtab libbpf: section(2) .text, size 16, link 0, flags 6, type=1 libbpf: found program .text libbpf: section(3) .debug_abbrev, size 55, link 0, flags 0, type=1 libbpf: skip section(3) .debug_abbrev libbpf: section(4) .debug_info, size 75, link 0, flags 0, type=1 libbpf: skip section(4) .debug_info libbpf: section(5) .rel.debug_info, size 32, link 14, flags 0, type=9 libbpf: skip relo .rel.debug_info(5) for section(4) libbpf: section(6) .debug_str, size 150, link 0, flags 30, type=1 libbpf: skip section(6) .debug_str libbpf: section(7) .BTF, size 155, link 0, flags 0, type=1 libbpf: section(8) .BTF.ext, size 80, link 0, flags 0, type=1 libbpf: section(9) .rel.BTF.ext, size 32, link 14, flags 0, type=9 libbpf: skip relo .rel.BTF.ext(9) for section(8) libbpf: section(10) .debug_frame, size 40, link 0, flags 0, type=1 libbpf: skip section(10) .debug_frame libbpf: section(11) .rel.debug_frame, size 16, link 14, flags 0, type=9 libbpf: skip relo .rel.debug_frame(11) for section(10) libbpf: section(12) .debug_line, size 74, link 0, flags 0, type=1 libbpf: skip section(12) .debug_line libbpf: section(13) .rel.debug_line, size 16, link 14, flags 0, type=9 libbpf: skip relo .rel.debug_line(13) for section(12) libbpf: section(14) .symtab, size 96, link 1, flags 0, type=2 libbpf: looking for externs among 4 symbols... libbpf: collected 0 externs total libbpf: failed to guess program type from ELF section '.text' libbpf: supported section(type) names are: socket sk_reuseport kprobe/ [...] After: # bpftool prog load sample_ret0.o /sys/fs/bpf/sample_ret0 libbpf: failed to guess program type from ELF section '.text' libbpf: supported section(type) names are: socket sk_reuseport kprobe/ [...] Signed-off-by:
Quentin Monnet <quentin@isovalent.com> Signed-off-by:
John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200311021205.9755-1-quentin@isovalent.comSigned-off-by:
-
Eelco Chaudron authored
Introduce new helper that reuses existing xdp perf_event output implementation, but can be called from raw_tracepoint programs that receive 'struct xdp_buff *' as a tracepoint argument. Signed-off-by:
Eelco Chaudron <echaudro@redhat.com> Signed-off-by:
Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/158348514556.2239.11050972434793741444.stgit@xdp-tutorial
-
Alexei Starovoitov authored
Carlos Neira says: ==================== Currently bpf_get_current_pid_tgid(), is used to do pid filtering in bcc's scripts but this helper returns the pid as seen by the root namespace which is fine when a bcc script is not executed inside a container. When the process of interest is inside a container, pid filtering will not work if bpf_get_current_pid_tgid() is used. This helper addresses this limitation returning the pid as it's seen by the current namespace where the script is executing. In the future different pid_ns files may belong to different devices, according to the discussion between Eric Biederman and Yonghong in 2017 Linux plumbers conference. To address that situation the helper requires inum and dev_t from /proc/self/ns/pid. This helper has the same use cases as bpf_get_current_pid_tgid() as it can be used to do pid filtering even inside a container. ==================== Signed-off-by: -
Carlos Neira authored
Self tests added for new helper bpf_get_ns_current_pid_tgid Signed-off-by:
Carlos Neira <cneirabustos@gmail.com> Signed-off-by:
-
Carlos Neira authored
New bpf helper bpf_get_ns_current_pid_tgid, This helper will return pid and tgid from current task which namespace matches dev_t and inode number provided, this will allows us to instrument a process inside a container. Signed-off-by:
Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200304204157.58695-3-cneirabustos@gmail.com
-
Carlos Neira authored
ns_match returns true if the namespace inode and dev_t matches the ones provided by the caller. Signed-off-by:
-
- 12 Mar, 2020 7 commits
-
-
Quentin Monnet authored
Minor fixes for bash completion: addition of program name completion for two subcommands, and correction for program test-runs and map pinning. The completion for the following commands is fixed or improved: # bpftool prog run [TAB] # bpftool prog pin [TAB] # bpftool map pin [TAB] # bpftool net attach xdp name [TAB] Signed-off-by:Daniel Borkmann <daniel@iogearbox.net> Acked-by:
-
Quentin Monnet authored
Documentation and interactive help for bpftool have always explained that the regular handles for programs (id|name|tag|pinned) and maps (id|name|pinned) can be passed to the utility when attempting to pin objects (bpftool prog pin PROG / bpftool map pin MAP). THIS IS A LIE!! The tool actually accepts only ids, as the parsing is done in do_pin_any() in common.c instead of reusing the parsing functions that have long been generic for program and map handles. Instead of fixing the doc, fix the code. It is trivial to reuse the generic parsing, and to simplify do_pin_any() in the process. Do not accept to pin multiple objects at the same time with prog_parse_fds() or map_parse_fds() (this would require a more complex syntax for passing multiple sysfs paths and validating that they correspond to the number of e.g. programs we find for a given name or tag). Signed-off-by:
-
Andrii Nakryiko authored
Needs for application BTF being present differs between user-space libbpf needs and kernel needs. Currently, BTF is mandatory only in kernel only when BPF application is using STRUCT_OPS. While libbpf itself relies more heavily on presense of BTF: - for BTF-defined maps; - for Kconfig externs; - for STRUCT_OPS as well. Thus, checks for presence and validness of bpf_object's BPF needs to be performed separately, which is patch does. Fixes: 53276446 ("libbpf: Relax check whether BTF is mandatory") Reported-by:
Michal Rostecki <mrostecki@opensuse.org> Signed-off-by:
-
Song Liu authored
These files are generated, so ignore them. Signed-off-by:
-
Song Liu authored
Add the dependency to libbpf, to fix build errors like: In file included from skeleton/profiler.bpf.c:5: .../bpf_helpers.h:5:10: fatal error: 'bpf_helper_defs.h' file not found #include "bpf_helper_defs.h" ^~~~~~~~~~~~~~~~~~~ 1 error generated. make: *** [skeleton/profiler.bpf.o] Error 1 make: *** Waiting for unfinished jobs.... Fixes: 47c09d6a ("bpftool: Introduce "prog profile" command") Suggested-by: -
Song Liu authored
bpftool-prog-profile requires clang to generate BTF for global variables. When compared with older clang, skip this command. This is achieved by adding a new feature, clang-bpf-global-var, to tools/build/feature. Signed-off-by:
-
Tobias Klauser authored
When compiling bpftool on a system where the /usr/include/asm symlink doesn't exist (e.g. on an Ubuntu system without gcc-multilib installed), the build fails with: CLANG skeleton/profiler.bpf.o In file included from skeleton/profiler.bpf.c:4: In file included from /usr/include/linux/bpf.h:11: /usr/include/linux/types.h:5:10: fatal error: 'asm/types.h' file not found #include <asm/types.h> ^~~~~~~~~~~~~ 1 error generated. make: *** [Makefile:123: skeleton/profiler.bpf.o] Error 1 This indicates that the build is using linux/types.h from system headers instead of source tree headers. To fix this, adjust the clang search path to include the necessary headers from tools/testing/selftests/bpf/include/uapi and tools/include/uapi. Also use __bitwise__ instead of __bitwise in skeleton/profiler.h to avoid clashing with the definition in tools/testing/selftests/bpf/include/uapi/linux/types.h. Signed-off-by:Tobias Klauser <tklauser@distanz.ch> Signed-off-by:
-
- 11 Mar, 2020 3 commits
-
-
Andrii Nakryiko authored
Libbpf compiles and runs subset of selftests on each PR in its Github mirror repository. To allow still building up-to-date selftests against outdated kernel images, add back BPF_F_CURRENT_CPU definitions back. N.B. BCC's runqslower version ([0]) doesn't need BPF_F_CURRENT_CPU due to use of locally checked in vmlinux.h, generated against kernel with 1aae4bdd ("bpf: Switch BPF UAPI #define constants used from BPF program side to enums") applied. [0] https://github.com/iovisor/bcc/pull/2809 Fixes: 367d82f1 (" tools/runqslower: Drop copy/pasted BPF_F_CURRENT_CPU definiton") Signed-off-by:
-
Alexei Starovoitov authored
fmod_ret progs are emitted as: start = __bpf_prog_enter(); call fmod_ret *(u64 *)(rbp - 8) = rax __bpf_prog_exit(, start); test eax, eax jne do_fexit That 'test eax, eax' is working by accident. The compiler is free to use rax inside __bpf_prog_exit() or inside functions that __bpf_prog_exit() is calling. Which caused "test_progs -t modify_return" to sporadically fail depending on compiler version and kconfig. Fix it by using 'cmp [rbp - 8], 0' instead of 'test eax, eax'. Fixes: ae240823 ("bpf: Introduce BPF_MODIFY_RETURN") Reported-by:
KP Singh <kpsingh@google.com> Link: https://lore.kernel.org/bpf/20200311003906.3643037-1-ast@kernel.org
-
Andrii Nakryiko authored
Add bpf_link_new_file() API for cases when we need to ensure anon_inode is successfully created before we proceed with expensive BPF program attachment procedure, which will require equally (if not more so) expensive and potentially failing compensation detachment procedure just because anon_inode creation failed. This API allows to simplify code by ensuring first that anon_inode is created and after BPF program is attached proceed with fd_install() that can't fail. After anon_inode file is created, link can't be just kfree()'d anymore, because its destruction will be performed by deferred file_operations->release call. For this, bpf_link API required specifying two separate operations: release() and dealloc(), former performing detachment only, while the latter frees memory used by bpf_link itself. dealloc() needs to be specified, because struct bpf_link is frequently embedded into link type-specific container struct (e.g., struct bpf_raw_tp_link), so bpf_link itself doesn't know how to properly free the memory. In case when anon_inode file was successfully created, but subsequent BPF attachment failed, bpf_link needs to be marked as "defunct", so that file's release() callback will perform only memory deallocation, but no detachment. Convert raw tracepoint and tracing attachment to new API and eliminate detachment from error handling path. Signed-off-by:
-
- 09 Mar, 2020 16 commits
-
-
Song Liu authored
_bpftool_get_map_names => _bpftool_get_prog_names for prog-attach|detach. Fixes: 99f9863a ("bpftool: Match maps by name") Signed-off-by:
-
Song Liu authored
Add bash completion for "bpftool prog profile" command. Signed-off-by:
-
Song Liu authored
Add documentation for the new bpftool prog profile command. Signed-off-by:
-
Song Liu authored
With fentry/fexit programs, it is possible to profile BPF program with hardware counters. Introduce bpftool "prog profile", which measures key metrics of a BPF program. bpftool prog profile command creates per-cpu perf events. Then it attaches fentry/fexit programs to the target BPF program. The fentry program saves perf event value to a map. The fexit program reads the perf event again, and calculates the difference, which is the instructions/cycles used by the target program. Example input and output: ./bpftool prog profile id 337 duration 3 cycles instructions llc_misses 4228 run_cnt 3403698 cycles (84.08%) 3525294 instructions # 1.04 insn per cycle (84.05%) 13 llc_misses # 3.69 LLC misses per million isns (83.50%) This command measures cycles and instructions for BPF program with id 337 for 3 seconds. The program has triggered 4228 times. The rest of the output is similar to perf-stat. In this example, the counters were only counting ~84% of the time because of time multiplexing of perf counters. Note that, this approach measures cycles and instructions in very small increments. So the fentry/fexit programs introduce noticeable errors to the measurement results. The fentry/fexit programs are generated with BPF skeletons. Therefore, we build bpftool twice. The first time _bpftool is built without skeletons. Then, _bpftool is used to generate the skeletons. The second time, bpftool is built with skeletons. Signed-off-by: -
Lorenz Bauer authored
Add Jakub and myself as maintainers for sockmap related code. Signed-off-by:
Lorenz Bauer <lmb@cloudflare.com> Signed-off-by:
Jakub Sitnicki <jakub@cloudflare.com> Acked-by:
-
Lorenz Bauer authored
Remove the guard that disables UDP tests now that sockmap has support for them. Signed-off-by:
-
Lorenz Bauer authored
Expand the TCP sockmap test suite to also check UDP sockets. Signed-off-by:
-
Lorenz Bauer authored
Most tests for TCP sockmap can be adapted to UDP sockmap if the listen call is skipped. Rename listen_loopback, etc. to socket_loopback and skip listen() for SOCK_DGRAM. Signed-off-by:
-
Lorenz Bauer authored
Allow adding hashed UDP sockets to sockmaps. Signed-off-by:
-
Lorenz Bauer authored
Add basic psock hooks for UDP sockets. This allows adding and removing sockets, as well as automatic removal on unhash and close. Signed-off-by:
-
Lorenz Bauer authored
We can take advantage of the fact that both callers of sock_map_init_proto are holding a RCU read lock, and have verified that psock is valid. Signed-off-by:
-
Lorenz Bauer authored
The init, close and unhash handlers from TCP sockmap are generic, and can be reused by UDP sockmap. Move the helpers into the sockmap code base and expose them. This requires tcp_bpf_get_proto and tcp_bpf_clone to be conditional on BPF_STREAM_PARSER. The moved functions are unmodified, except that sk_psock_unlink is renamed to sock_map_unlink to better match its behaviour. Signed-off-by:
-
Lorenz Bauer authored
tcp_bpf.c is only included in the build if CONFIG_NET_SOCK_MSG is selected. The declaration should therefore be guarded as such. Signed-off-by:
-
Lorenz Bauer authored
We need to ensure that sk->sk_prot uses certain callbacks, so that code that directly calls e.g. tcp_sendmsg in certain corner cases works. To avoid spurious asserts, we must to do this only if sk_psock_update_proto has not yet been called. The same invariants apply for tcp_bpf_check_v6_needs_rebuild, so move the call as well. Doing so allows us to merge tcp_bpf_init and tcp_bpf_reinit. Signed-off-by:
-
Lorenz Bauer authored
Only update psock->saved_* if psock->sk_proto has not been initialized yet. This allows us to get rid of tcp_bpf_reinit_sk_prot. Signed-off-by:
-
Lorenz Bauer authored
The sock map code checks that a socket does not have an active upper layer protocol before inserting it into the map. This requires casting via inet_csk, which isn't valid for UDP sockets. Guard checks for ULP by checking inet_sk(sk)->is_icsk first. Signed-off-by:
-
- 05 Mar, 2020 1 commit
-
-
KP Singh authored
test_run.o is not built when CONFIG_NET is not set and bpf_prog_test_run_tracing being referenced in bpf_trace.o causes the linker error: ld: kernel/trace/bpf_trace.o:(.rodata+0x38): undefined reference to `bpf_prog_test_run_tracing' Add a __weak function in bpf_trace.c to handle this. Fixes: da00d2f1 ("bpf: Add test ops for BPF_PROG_TYPE_TRACING") Signed-off-by:
Randy Dunlap <rdunlap@infradead.org> Acked-by:
-
