Break up the first 10 kLoC of test verifier test cases
out into smaller files. Looks like git line counting
gets a little flismy above 16 bit integers, so we need
two commits to break up test_verifier.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
test_verifier.c has grown to be very long (almost 16 kLoC),
and it is very conflict prone since we always add tests at
the end.
Try to break it apart a little bit. Allow test snippets
to be defined in separate files and include them automatically
into the huge test array.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Jiong Wang says:
====================
v3 -> v4:
- Fixed rebase issue. JMP32 checks were missing in two new functions:
+ kernel/bpf/verifier.c:insn_is_cond_jump
+ drivers/net/ethernet/netronome/nfp/bpf/main.h:is_mbpf_cond_jump
(Daniel)
- Further rebased on top of latest llvm-readelf change.
v2 -> v3:
- Added missed check on JMP32 inside bpf_jit_build_body. (Sandipan)
- Wrap ?: statements in s390 port with brace. They are used by macros
which doesn't guard the operand with brace.
- Fixed the ',' issues test_verifier change.
- Reorder two selftests patches to be near each other.
- Rebased on top of latest bpf-next.
v1 -> v2:
- Updated encoding. Use reserved insn class 0x6 instead of packing with
existing BPF_JMP. (Alexei)
- Updated code comments in s390 port. (Martin)
- Separate JIT function for jeq32_imm in NFP port. (Jakub)
- Re-implemented auto-testing support. (Jakub)
- Moved testcases to test_verifer.c, plus more unit tests. (Jakub)
- Fixed JEQ/JNE range deduction. (Jakub)
- Also supported JSET in this patch set.
- Fixed/Improved range deduction for all the other operations. All C
programs under bpf selftest passed verification now.
- Improved min/max code implementation.
- Fixed bpftool/disassembler.
Current eBPF ISA has 32-bit sub-register and has defined a set of ALU32
instructions.
However, there is no JMP32 instructions, the consequence is code-gen for
32-bit sub-registers is not efficient. For example, explicit sign-extension
from 32-bit to 64-bit is needed for signed comparison.
Adding JMP32 instruction therefore could complete eBPF ISA on 32-bit
sub-register support. This also match those JMP32 instructions in most JIT
backends, for example x64-64 and AArch64. These new eBPF JMP32 instructions
could have one-to-one map on them.
A few verifier ALU32 related bugs has been fixed recently, and JMP32
introduced by this set further improves BPF sub-register ecosystem. Once
this is landed, BPF programs using 32-bit sub-register ISA could get
reasonably good support from verifier and JIT compilers. Users then could
compare the runtime efficiency of one BPF program under both modes, and
could use the one shown better from benchmark result.
From benchmark results on some Cilium BPF programs, for 64-bit arches,
after JMP32 introduced, programs compiled with -mattr=+alu32 (meaning
enable sub-register usage) are smaller in code size and generally smaller
in verifier processed insn number.
Benchmark results
===
Text size in bytes (generated by "size")
---
LLVM code-gen option default alu32 alu32/jmp32 change Vs. change Vs.
alu32 default
bpf_lb-DLB_L3.o: 6456 6280 6160 -1.91% -4.58%
bpf_lb-DLB_L4.o: 7848 7664 7136 -6.89% -9.07%
bpf_lb-DUNKNOWN.o: 2680 2664 2568 -3.60% -4.18%
bpf_lxc.o: 104824 104744 97360 -7.05% -7.12%
bpf_netdev.o: 23456 23576 21632 -8.25% -7.78%
bpf_overlay.o: 16184 16304 14648 -10.16% -9.49%
Processed instruction number
---
LLVM code-gen option default alu32 alu32/jmp32 change Vs. change Vs.
alu32 default
bpf_lb-DLB_L3.o: 1579 1281 1295 +1.09% -17.99%
bpf_lb-DLB_L4.o: 2045 1663 1556 -6.43% -23.91%
bpf_lb-DUNKNOWN.o: 606 513 501 -2.34% -17.33%
bpf_lxc.o: 85381 103218 94435 -8.51% +10.60%
bpf_netdev.o: 5246 5809 5200 -10.48% -0.08%
bpf_overlay.o: 2443 2705 2456 -9.02% -0.53%
It is even better for 32-bit arches like x32, arm32 and nfp etc, as now
some conditional jump will become JMP32 which doesn't require code-gen for
high 32-bit comparison.
Encoding
===
The new JMP32 instructions are using new BPF_JMP32 class which is using
the reserved eBPF class number 0x6. And BPF_JA/CALL/EXIT only exist for
BPF_JMP, they are reserved opcode for BPF_JMP32.
LLVM support
===
A couple of unit tests has been added and included in this set. Also LLVM
code-gen for JMP32 has been added, so you could just compile any BPF C
program with both -mcpu=probe and -mattr=+alu32 specified. If you are
compiling on a machine with kernel patched by this set, LLVM will select
the ISA automatically based on host probe results. Otherwise specify
-mcpu=v3 and -mattr=+alu32 could also force use JMP32 ISA.
LLVM support could be found at:
https://github.com/Netronome/llvm/tree/jmp32-v2
(clang driver also taught about the new "v3" processor, will send out
merge request for both clang and llvm once kernel set landed.)
JIT backends support
===
A couple of JIT backends has been supported in this set except SPARC and
MIPS. It shouldn't be a big issue for these two ports as LLVM default won't
generate JMP32 insns, it will only generate them when host machine is
probed to be with the support.
Thanks.
====================
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch enables testing some eBPF programs under sub-register
compilation mode.
Only enable this when there is BPF_JMP32 support on both LLVM and kernel.
This is because only after BPF_JMP32 added, code-gen for complex program
under sub-register mode will be clean enough to pass verification.
This patch splits TEST_GEN_FILES into BPF_OBJ_FILES and
BPF_OBJ_FILES_DUAL_COMPILE. The latter are those objects we would like to
compile for both default and sub-register mode. They are also objects used
by "test_progs".
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch adds unit tests for new JMP32 instructions.
This patch also added the new BPF_JMP32_REG and BPF_JMP32_IMM macros to
samples/bpf/bpf_insn.h so that JMP32 insn builders are available to tests
under 'samples' directory.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on NFP.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on s390.
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on ppc.
For JMP32 | JSET, instruction encoding for PPC_RLWINM_DOT is added to check
the result of ANDing low 32-bit of operands.
Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on arm.
For JSET, "ands" (AND with flags updated) is used, so corresponding
encoding helper is added.
Cc: Shubham Bansal <illusionist.neo@gmail.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on arm64.
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Zi Shen Lim <zlim.lnx@gmail.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on x32.
Also fixed several reverse xmas tree coding style issues as I am there.
Cc: Wang YanQing <udknight@gmail.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements code-gen for new JMP32 instructions on x86_64.
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch adds JIT blinds support for JMP32.
Like BPF_JMP_REG/IMM, JMP32 version are needed for building raw bpf insn.
They are added to both include/linux/filter.h and
tools/include/linux/filter.h.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch implements interpreting new JMP32 instructions.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The cfg code need to be aware of the new JMP32 instruction class so it
could partition functions correctly.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch teaches disassembler about JMP32. There are two places to
update:
- Class 0x6 now used by BPF_JMP32, not "unused".
- BPF_JMP32 need to show comparison operands properly.
The disassemble format is to add an extra "(32)" before the operands if
it is a sub-register. A better disassemble format for both JMP32 and
ALU32 just show the register prefix as "w" instead of "r", this is the
format using by LLVM assembler.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch teach verifier about the new BPF_JMP32 instruction class.
Verifier need to treat it similar as the existing BPF_JMP class.
A BPF_JMP32 insn needs to go through all checks that have been done on
BPF_JMP.
Also, verifier is doing runtime optimizations based on the extra info
conditional jump instruction could offer, especially when the comparison is
between constant and register that the value range of the register could be
improved based on the comparison results. These code are updated
accordingly.
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The current min/max code does both signed and unsigned comparisons against
the input argument "val" which is "u64" and there is explicit type casting
when the comparison is signed.
As we will need slightly more complexer type casting when JMP32 introduced,
it is better to host the signed type casting. This makes the code more
clean with ignorable runtime overhead.
Also, code for J*GE/GT/LT/LE and JEQ/JNE are very similar, this patch
combine them.
The main purpose for this refactor is to make sure the min/max code will
still be readable and with minimum code duplication after JMP32 introduced.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The new eBPF instruction class JMP32 uses the reserved class number 0x6.
Kernel BPF ISA documentation updated accordingly.
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Björn Töpel says:
====================
This series adds an AF_XDP sock_diag interface for querying sockets
from user-space. Tools like iproute2 ss(8) can use this interface to
list open AF_XDP sockets.
The diagnostic provides information about the Rx/Tx/fill/completetion
rings, umem, memory usage and such. For a complete list, please refer
to the xsk_diag.c file.
The AF_XDP sock_diag interface is optional, and can be built as a
module. A separate patch series, adding ss(8) iproute2 support, will
follow.
v1->v2:
* Removed extra newline
* Zero-out all user-space facing structures prior setting the
members
* Added explicit "pad" member in _msg struct
* Removed unused variable "req" in xsk_diag_handler_dump()
Thanks to Daniel for reviewing the series!
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This patch adds the sock_diag interface for querying sockets from user
space. Tools like iproute2 ss(8) can use this interface to list open
AF_XDP sockets.
The user-space ABI is defined in linux/xdp_diag.h and includes netlink
request and response structs. The request can query sockets and the
response contains socket information about the rings, umems, inode and
more.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit adds an id to the umem structure. The id uniquely
identifies a umem instance, and will be exposed to user-space via the
socket monitoring interface.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Track each AF_XDP socket in a per-netns list. This will be used later
by the sock_diag interface for querying sockets from userspace.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Before:
$ make -s -C tools/testing/selftests/bpf
readelf: Error: Missing knowledge of 32-bit reloc types used in DWARF
sections of machine number 247
readelf: Warning: unable to apply unsupported reloc type 10 to section
.debug_info
readelf: Warning: unable to apply unsupported reloc type 1 to section
.debug_info
readelf: Warning: unable to apply unsupported reloc type 10 to section
.debug_info
After:
$ make -s -C tools/testing/selftests/bpf
v2:
* use llvm-readelf instead of redirecting binutils' readelf stderr to
/dev/null
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This adds the ability to read gso_segs from a BPF program.
v3: Use BPF_REG_AX instead of BPF_REG_TMP for the temporary register,
as suggested by Martin.
v2: refined Eddie Hao patch to address Alexei feedback.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eddie Hao <eddieh@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
When 'bpftool feature' is executed it shows incorrect help string.
test# bpftool feature
Usage: bpftool bpftool probe [COMPONENT] [macros [prefix PREFIX]]
bpftool bpftool help
COMPONENT := { kernel | dev NAME }
Instead of fixing the help text by tweaking argv[] indices, this
patch changes the default action to 'probe'. It makes the behavior
consistent with other subcommands, where first subcommand without
extra parameter results in 'show' action.
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Jakub Kicinski says:
====================
This set adds support for complete removal of dead code.
Patch 3 contains all the code removal logic, patches 2 and 4
additionally optimize branches around and to dead code.
Patches 6 and 7 allow offload JITs to take advantage of the
optimization. After a few small clean ups (8, 9, 10) nfp
support is added (11, 12).
Removing code directly in the verifier makes it easy to adjust
the relevant metadata (line info, subprogram info). JITs for
code store constrained architectures would have hard time
performing such adjustments at JIT level. Removing subprograms
or line info is very hard once BPF core finished the verification.
For user space to perform dead code removal it would have to perform
the execution simulation/analysis similar to what the verifier does.
v3:
- fix uninitilized var warning in GCC 6 (buildbot).
v4:
- simplify the linfo-keeping logic (Yonghong). Instead of
trying to figure out that we are removing first instruction
of a subprogram, just always keep last dead line info, if
first live instruction doesn't have one.
v5:
- improve comments (Martin Lau).
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add a verifier callback to the nfp JIT to remove the instructions
the verifier deemed to be dead.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Verifier will now optimize out branches to dead code, implement
the replace_insn callback to take advantage of that optimization.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Instead of passing env->prog->len around, and trying to adjust
for optimized out instructions just save the initial number
of instructions in struct nfp_prog.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
We fail program loading if jump lands on a skipped instruction.
This is for historical reasons, it used to be that we only skipped
instructions optimized out based on prior context, and therefore
the optimization would be buggy if we jumped directly to such
instruction (because the context would be skipped by the jump).
There are cases where instructions can be skipped without any
context, for example there is no point in generating code for:
r0 |= 0
We will also soon support dropping dead code, so make the skip
logic differentiate between "optimized with preceding context"
vs other skip types.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Instruction number is meaningless at code gen phase. The target
of the instruction is overwritten by nfp_fixup_branches(). The
convention is to put the raw offset in target address as a place
holder. See cmp_* functions.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Let offload JITs know when instructions are replaced and optimized
out, so they can update their state appropriately. The optimizations
are best effort, if JIT returns an error from any callback verifier
will stop notifying it as state may now be out of sync, but the
verifier continues making progress.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The communication between the verifier and advanced JITs is based
on instruction indexes. We have to keep them stable throughout
the optimizations otherwise referring to a particular instruction
gets messy quickly.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add tests for newly added dead code elimination. Both verifier
and BTF tests are added. BTF test infrastructure has to be
extended to be able to account for line info which is eliminated
during dead code removal.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Unconditional branches by 0 instructions are basically noops
but they can result from earlier optimizations, e.g. a conditional
jumps which would never be taken or a conditional jump around
dead code.
Remove those branches.
v0.2:
- s/opt_remove_dead_branches/opt_remove_nops/ (Jiong).
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Instead of overwriting dead code with jmp -1 instructions
remove it completely for root. Adjust verifier state and
line info appropriately.
v2:
- adjust func_info (Alexei);
- make sure first instruction retains line info (Alexei).
v4: (Yonghong)
- remove unnecessary if (!insn to remove) checks;
- always keep last line info if first live instruction lacks one.
v5: (Martin Lau)
- improve and clarify comments.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Loading programs with dead code becomes more and more
common, as people begin to patch constants at load time.
Turn conditional jumps to unconditional ones, to avoid
potential branch misprediction penalty.
This optimization is enabled for privileged users only.
For branches which just fall through we could just mark
them as not seen and have dead code removal take care of
them, but that seems less clean.
v0.2:
- don't call capable(CAP_SYS_ADMIN) twice (Jiong).
v3:
- fix GCC warning;
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In preparation for code removal change parameters to branch
and call adjustment functions to be more universal. The
current parameters assume we are patching a single instruction
with a longer set.
A diagram may help reading the change, this is for the patch
single case, patching instruction 1 with a replacement of 4:
____
0 |____|
1 |____| <-- pos ^
2 | | <-- end old ^ |
3 | | | delta | len
4 |____| | | (patch region)
5 | | <-- end new v v
6 |____|
end_old = pos + 1
end_new = pos + delta + 1
If we are before the patch region - curr variable and the target
are fully in old coordinates (hence comparing against end_old).
If we are after the region curr is in new coordinates (hence
the comparison to end_new) but target is in mixed coordinates,
so we just check if it falls before end_new, and if so it needs
the adjustment.
Note that we will not fix up branches which land in removed region
in case of removal, which should be okay, as we are only going to
remove dead code.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
system() is calling shell which should find the appropriate full path
via $PATH. On some systems, full path to iptables and/or nc might be
different that we one we have hardcoded.
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
We need to let users check their wrong ELF section name with proper
ELF section names when they fail to get a prog/attach type from it.
Because users can't realize libbpf guess prog/attach types from given
ELF section names. For example, when a 'cgroup' section name of a
BPF program is used, show available ELF section names(types).
Before:
$ bpftool prog load bpf-prog.o /sys/fs/bpf/prog1
Error: failed to guess program type based on ELF section name cgroup
After:
libbpf: failed to guess program type based on ELF section name 'cgroup'
libbpf: supported section(type) names are: socket kprobe/ kretprobe/ classifier action tracepoint/ raw_tracepoint/ xdp perf_event lwt_in lwt_out lwt_xmit lwt_seg6local cgroup_skb/ingress cgroup_skb/egress cgroup/skb cgroup/sock cgroup/post_bind4 cgroup/post_bind6 cgroup/dev sockops sk_skb/stream_parser sk_skb/stream_verdict sk_skb sk_msg lirc_mode2 flow_dissector cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Quentin Monnet <quentin.monnet@netronome.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Andrey Ignatov <rdna@fb.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This patch added documentation for BTF (BPF Debug Format).
The document is placed under linux:Documentation/bpf directory.
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Quentin Monnet says:
====================
Hi,
This set adds a new command to bpftool in order to dump a list of
eBPF-related parameters for the system (or for a specific network
device) to the console. Once again, this is based on a suggestion from
Daniel.
At this time, output includes:
- Availability of bpf() system call
- Availability of bpf() system call for unprivileged users
- JIT status (enabled or not, with or without debugging traces)
- JIT hardening status
- JIT kallsyms exports status
- Global memory limit for JIT compiler for unprivileged users
- Status of kernel compilation options related to BPF features
- Availability of known eBPF program types
- Availability of known eBPF map types
- Availability of known eBPF helper functions
There are three different ways to dump this information at this time:
- Plain output dumps probe results in plain text. It is the most
flexible options for providing descriptive output to the user, but
should not be relied upon for parsing the output.
- JSON output is supported.
- A third mode, available through the "macros" keyword appended to the
command line, dumps some of those parameters (not all) as a series of
"#define" directives, that can be included into a C header file for
example.
Probes for supported program and map types, and supported helpers, are
directly added to libbpf, so that other applications (or selftests) can
reuse them as necessary.
If the user does not have root privileges (or more precisely, the
CAP_SYS_ADMIN capability) detection will be erroneous for most
parameters. Therefore, forbid non-root users to run the command.
v5:
- Move exported symbols to a new LIBBPF_0.0.2 section in libbpf.map
(patches 4 to 6).
- Minor fixes on patches 3 and 4.
v4:
- Probe bpf_jit_limit parameter (patch 2).
- Probe some additional kernel config options (patch 3).
- Minor fixes on patch 6.
v3:
- Do not probe kernel version in bpftool (just retrieve it to probe support
for kprobes in libbpf).
- Change the way results for helper support is displayed: now one list of
compatible helpers for each program type (and C-style output gets a
HAVE_PROG_TYPE_HELPER(prog_type, helper) macro to help with tests. See
patches 6, 7.
- Address other comments from feedback from v2 (please refer to individual
patches' history).
v2 (please also refer to individual patches' history):
- Move probes for prog/map types, helpers, from bpftool to libbpf.
- Move C-style output as a separate patch, and restrict it to a subset of
collected information (bpf() availability, prog/map types, helpers).
- Now probe helpers with all supported program types, and display a list of
compatible program types (as supported on the system) for each helper.
- NOT addressed: grouping compilation options for kernel into subsections
(patch 3) (I don't see an easy way of grouping them at the moment, please
see also the discussion on v1 thread).
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add the bash completion related to the newly introduced "bpftool feature
probe" command.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
bpftool gained support for probing the current system in order to see
what program and map types, and what helpers are available on that
system. This patch adds the possibility to pass an interface index to
libbpf (and hence to the kernel) when trying to load the programs or to
create the maps, in order to see what items a given network device can
support.
A new keyword "dev <ifname>" can be used as an alternative to "kernel"
to indicate that the given device should be tested. If no target ("dev"
or "kernel") is specified bpftool defaults to probing the kernel.
Sample output:
# bpftool -p feature probe dev lo
{
"syscall_config": {
"have_bpf_syscall": true
},
"program_types": {
"have_sched_cls_prog_type": false,
"have_xdp_prog_type": false
},
...
}
As the target is a network device, /proc/ parameters and kernel
configuration are NOT dumped. Availability of the bpf() syscall is
still probed, so we can return early if that syscall is not usable
(since there is no point in attempting the remaining probes in this
case).
Among the program types, only the ones that can be offloaded are probed.
All map types are probed, as there is no specific rule telling which one
could or could not be supported by a device in the future. All helpers
are probed (but only for offload-able program types).
Caveat: as bpftool does not attempt to attach programs to the device at
the moment, probes do not entirely reflect what the device accepts:
typically, for Netronome's nfp, results will announce that TC cls
offload is available even if support has been deactivated (with e.g.
ethtool -K eth1 hw-tc-offload off).
v2:
- All helpers are probed, whereas previous version would only probe the
ones compatible with an offload-able program type. This is because we
do not keep a default compatible program type for each helper anymore.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Make bpftool able to dump a subset of the parameters collected by
probing the system as a listing of C-style #define macros, so that
external projects can reuse the result of this probing and build
BPF-based project in accordance with the features available on the
system.
The new "macros" keyword is used to select this output. An additional
"prefix" keyword is added so that users can select a custom prefix for
macro names, in order to avoid any namespace conflict.
Sample output:
# bpftool feature probe kernel macros prefix FOO_
/*** System call availability ***/
#define FOO_HAVE_BPF_SYSCALL
/*** eBPF program types ***/
#define FOO_HAVE_SOCKET_FILTER_PROG_TYPE
#define FOO_HAVE_KPROBE_PROG_TYPE
#define FOO_HAVE_SCHED_CLS_PROG_TYPE
...
/*** eBPF map types ***/
#define FOO_HAVE_HASH_MAP_TYPE
#define FOO_HAVE_ARRAY_MAP_TYPE
#define FOO_HAVE_PROG_ARRAY_MAP_TYPE
...
/*** eBPF helper functions ***/
/*
* Use FOO_HAVE_PROG_TYPE_HELPER(prog_type_name, helper_name)
* to determine if <helper_name> is available for <prog_type_name>,
* e.g.
* #if FOO_HAVE_PROG_TYPE_HELPER(xdp, bpf_redirect)
* // do stuff with this helper
* #elif
* // use a workaround
* #endif
*/
#define FOO_HAVE_PROG_TYPE_HELPER(prog_type, helper) \
FOO_BPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper
...
#define FOO_BPF__PROG_TYPE_socket_filter__HELPER_bpf_probe_read 0
#define FOO_BPF__PROG_TYPE_socket_filter__HELPER_bpf_ktime_get_ns 1
#define FOO_BPF__PROG_TYPE_socket_filter__HELPER_bpf_trace_printk 1
...
v3:
- Change output for helpers again: add a
HAVE_PROG_TYPE_HELPER(type, helper) macro that can be used to tell
if <helper> is available for program <type>.
v2:
- #define-based output added as a distinct patch.
- "HAVE_" prefix appended to macro names.
- Output limited to bpf() syscall availability, BPF prog and map types,
helper functions. In this version kernel config options, procfs
parameter or kernel version are intentionally left aside.
- Following the change on helper probes, format for helper probes in
this output style has changed (now a list of compatible program
types).
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Similarly to what was done for program types and map types, add a set of
probes to test the availability of the different eBPF helper functions
on the current system.
For each known program type, all known helpers are tested, in order to
establish a compatibility matrix. Output is provided as a set of lists
of available helpers, one per program type.
Sample output:
# bpftool feature probe kernel
...
Scanning eBPF helper functions...
eBPF helpers supported for program type socket_filter:
- bpf_map_lookup_elem
- bpf_map_update_elem
- bpf_map_delete_elem
...
eBPF helpers supported for program type kprobe:
- bpf_map_lookup_elem
- bpf_map_update_elem
- bpf_map_delete_elem
...
# bpftool --json --pretty feature probe kernel
{
...
"helpers": {
"socket_filter_available_helpers": ["bpf_map_lookup_elem", \
"bpf_map_update_elem","bpf_map_delete_elem", ...
],
"kprobe_available_helpers": ["bpf_map_lookup_elem", \
"bpf_map_update_elem","bpf_map_delete_elem", ...
],
...
}
}
v5:
- In libbpf.map, move global symbol to the new LIBBPF_0.0.2 section.
v4:
- Use "enum bpf_func_id" instead of "__u32" in bpf_probe_helper()
declaration for the type of the argument used to pass the id of
the helper to probe.
- Undef BPF_HELPER_MAKE_ENTRY after using it.
v3:
- Do not pass kernel version from bpftool to libbpf probes (kernel
version for testing program with kprobes is retrieved directly from
libbpf).
- Dump one list of available helpers per program type (instead of one
list of compatible program types per helper).
v2:
- Move probes from bpftool to libbpf.
- Test all program types for each helper, print a list of working prog
types for each helper.
- Fall back on include/uapi/linux/bpf.h for names and ids of helpers.
- Remove C-style macros output from this patch.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add new probes for eBPF map types, to detect what are the ones available
on the system. Try creating one map of each type, and see if the kernel
complains.
Sample output:
# bpftool feature probe kernel
...
Scanning eBPF map types...
eBPF map_type hash is available
eBPF map_type array is available
eBPF map_type prog_array is available
...
# bpftool --json --pretty feature probe kernel
{
...
"map_types": {
"have_hash_map_type": true,
"have_array_map_type": true,
"have_prog_array_map_type": true,
...
}
}
v5:
- In libbpf.map, move global symbol to the new LIBBPF_0.0.2 section.
v3:
- Use a switch with all enum values for setting specific map parameters,
so that gcc complains at compile time (-Wswitch-enum) if new map types
were added to the kernel but libbpf was not updated.
v2:
- Move probes from bpftool to libbpf.
- Remove C-style macros output from this patch.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Introduce probes for supported BPF program types in libbpf, and call it
from bpftool to test what types are available on the system. The probe
simply consists in loading a very basic program of that type and see if
the verifier complains or not.
Sample output:
# bpftool feature probe kernel
...
Scanning eBPF program types...
eBPF program_type socket_filter is available
eBPF program_type kprobe is available
eBPF program_type sched_cls is available
...
# bpftool --json --pretty feature probe kernel
{
...
"program_types": {
"have_socket_filter_prog_type": true,
"have_kprobe_prog_type": true,
"have_sched_cls_prog_type": true,
...
}
}
v5:
- In libbpf.map, move global symbol to a new LIBBPF_0.0.2 section.
- Rename (non-API function) prog_load() as probe_load().
v3:
- Get kernel version for checking kprobes availability from libbpf
instead of from bpftool. Do not pass kernel_version as an argument
when calling libbpf probes.
- Use a switch with all enum values for setting specific program
parameters just before probing, so that gcc complains at compile time
(-Wswitch-enum) if new prog types were added to the kernel but libbpf
was not updated.
- Add a comment in libbpf.h about setrlimit() usage to allow many
consecutive probe attempts.
v2:
- Move probes from bpftool to libbpf.
- Remove C-style macros output from this patch.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add probes to dump a number of options set (or not set) for compiling
the kernel image. These parameters provide information about what BPF
components should be available on the system. A number of them are not
directly related to eBPF, but are in fact used in the kernel as
conditions on which to compile, or not to compile, some of the eBPF
helper functions.
Sample output:
# bpftool feature probe kernel
Scanning system configuration...
...
CONFIG_BPF is set to y
CONFIG_BPF_SYSCALL is set to y
CONFIG_HAVE_EBPF_JIT is set to y
...
# bpftool --pretty --json feature probe kernel
{
"system_config": {
...
"CONFIG_BPF": "y",
"CONFIG_BPF_SYSCALL": "y",
"CONFIG_HAVE_EBPF_JIT": "y",
...
}
}
v5:
- Declare options[] array in probe_kernel_image_config() as static.
v4:
- Add some options to the list:
- CONFIG_TRACING
- CONFIG_KPROBE_EVENTS
- CONFIG_UPROBE_EVENTS
- CONFIG_FTRACE_SYSCALLS
- Add comments about those options in the source code.
v3:
- Add a comment about /proc/config.gz not being supported as a path for
the config file at this time.
- Use p_info() instead of p_err() on failure to get options from config
file, as bpftool keeps probing other parameters and that would
possibly create duplicate "error" entries for JSON.
v2:
- Remove C-style macros output from this patch.
- NOT addressed: grouping of those config options into subsections
(I don't see an easy way of grouping them at the moment, please see
also the discussion on v1 thread).
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
