- 02 Dec, 2021 10 commits
-
-
Alexei Starovoitov authored
Add ability to initialize inner maps in light skeleton. Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
Andrii Nakryiko <andrii@kernel.org> Acked-by:
-
Alexei Starovoitov authored
Without lskel the CO-RE relocations are processed by libbpf before any other work is done. Instead, when lskel is needed, remember relocation as RELO_CORE kind. Then when loader prog is generated for a given bpf program pass CO-RE relos of that program to gen loader via bpf_gen__record_relo_core(). The gen loader will remember them as-is and pass it later as-is into the kernel. The normal libbpf flow is to process CO-RE early before call relos happen. In case of gen_loader the core relos have to be added to other relos to be copied together when bpf static function is appended in different places to other main bpf progs. During the copy the append_subprog_relos() will adjust insn_idx for normal relos and for RELO_CORE kind too. When that is done each struct reloc_desc has good relos for specific main prog. Signed-off-by:
-
Alexei Starovoitov authored
Given BPF program's BTF root type name perform the following steps: . search in vmlinux candidate cache. . if (present in cache and candidate list >= 1) return candidate list. . do a linear search through kernel BTFs for possible candidates. . regardless of number of candidates found populate vmlinux cache. . if (candidate list >= 1) return candidate list. . search in module candidate cache. . if (present in cache) return candidate list (even if list is empty). . do a linear search through BTFs of all kernel modules collecting candidates from all of them. . regardless of number of candidates found populate module cache. . return candidate list. Then wire the result into bpf_core_apply_relo_insn(). When BPF program is trying to CO-RE relocate a type that doesn't exist in either vmlinux BTF or in modules BTFs these steps will perform 2 cache lookups when cache is hit. Note the cache doesn't prevent the abuse by the program that might have lots of relocations that cannot be resolved. Hence cond_resched(). CO-RE in the kernel requires CAP_BPF, since BTF loading requires it. Signed-off-by:
-
Andrii Nakryiko authored
Remove two redundant fields from struct bpf_core_cand. Signed-off-by:
-
Alexei Starovoitov authored
Make BTF log size limit to be the same as the verifier log size limit. Otherwise tools that progressively increase log size and use the same log for BTF loading and program loading will be hitting hard to debug EINVAL. Signed-off-by:
-
Alexei Starovoitov authored
struct bpf_core_relo is generated by llvm and processed by libbpf. It's a de-facto uapi. With CO-RE in the kernel the struct bpf_core_relo becomes uapi de-jure. Add an ability to pass a set of 'struct bpf_core_relo' to prog_load command and let the kernel perform CO-RE relocations. Note the struct bpf_line_info and struct bpf_func_info have the same layout when passed from LLVM to libbpf and from libbpf to the kernel except "insn_off" fields means "byte offset" when LLVM generates it. Then libbpf converts it to "insn index" to pass to the kernel. The struct bpf_core_relo's "insn_off" field is always "byte offset". Signed-off-by:
-
Alexei Starovoitov authored
enum bpf_core_relo_kind is generated by llvm and processed by libbpf. It's a de-facto uapi. With CO-RE in the kernel the bpf_core_relo_kind values become uapi de-jure. Also rename them with BPF_CORE_ prefix to distinguish from conflicting names in bpf_core_read.h. The enums bpf_field_info_kind, bpf_type_id_kind, bpf_type_info_kind, bpf_enum_value_kind are passing different values from bpf program into llvm. Signed-off-by:
-
Alexei Starovoitov authored
Make relo_core.c to be compiled for the kernel and for user space libbpf. Note the patch is reducing BPF_CORE_SPEC_MAX_LEN from 64 to 32. This is the maximum number of nested structs and arrays. For example: struct sample { int a; struct { int b[10]; }; }; struct sample *s = ...; int *y = &s->b[5]; This field access is encoded as "0:1:0:5" and spec len is 4. The follow up patch might bump it back to 64. Signed-off-by: -
Alexei Starovoitov authored
Rename btf_member_bit_offset() and btf_member_bitfield_size() to avoid conflicts with similarly named helpers in libbpf's btf.h. Rename the kernel helpers, since libbpf helpers are part of uapi. Suggested-by:
-
Alexei Starovoitov authored
To prepare relo_core.c to be compiled in the kernel and the user space replace btf__type_by_id with btf_type_by_id. In libbpf btf__type_by_id and btf_type_by_id have different behavior. bpf_core_apply_relo_insn() needs behavior of uapi btf__type_by_id vs internal btf_type_by_id, but type_id range check is already done in bpf_core_apply_relo(), so it's safe to replace it everywhere. The kernel btf_type_by_id() does the check anyway. It doesn't hurt. Suggested-by:
-
- 01 Dec, 2021 2 commits
-
-
Alexander Lobakin authored
Fix the following samples/bpf build error appeared after the introduction of bpf_map_create() in libbpf: CC samples/bpf/fds_example.o samples/bpf/fds_example.c:49:12: error: static declaration of 'bpf_map_create' follows non-static declaration static int bpf_map_create(void) ^ samples/bpf/libbpf/include/bpf/bpf.h:55:16: note: previous declaration is here LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, ^ samples/bpf/fds_example.c:82:23: error: too few arguments to function call, expected 6, have 0 fd = bpf_map_create(); ~~~~~~~~~~~~~~ ^ samples/bpf/libbpf/include/bpf/bpf.h:55:16: note: 'bpf_map_create' declared here LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, ^ 2 errors generated. fds_example by accident has a static function with the same name. It's not worth it to separate a single call into its own function, so just embed it. Fixes: 992c4225 ("libbpf: Unify low-level map creation APIs w/ new bpf_map_create()") Signed-off-by:Alexander Lobakin <alexandr.lobakin@intel.com> Signed-off-by:
Maciej Fijalkowski <maciej.fijalkowski@intel.com> Acked-by:
Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20211201164931.47357-1-alexandr.lobakin@intel.com
-
Hou Tao authored
An extra newline will output for bpf_log() with BPF_LOG_KERNEL level as shown below: [ 52.095704] BPF:The function test_3 has 12 arguments. Too many. [ 52.095704] [ 52.096896] Error in parsing func ptr test_3 in struct bpf_dummy_ops Now all bpf_log() are ended by newline, but not all btf_verifier_log() are ended by newline, so checking whether or not the log message has the trailing newline and adding a newline if not. Also there is no need to calculate the left userspace buffer size for kernel log output and to truncate the output by '\0' which has already been done by vscnprintf(), so only do these for userspace log output. Signed-off-by:
Hou Tao <houtao1@huawei.com> Signed-off-by:
Yonghong Song <yhs@fb.com> Acked-by:
Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20211201073458.2731595-2-houtao1@huawei.com
-
- 30 Nov, 2021 15 commits
-
-
Andrii Nakryiko authored
Kumar Kartikeya says: ==================== Three commits addressing comments for the typeless/weak ksym set. No functional change intended. Hopefully this is simpler to read for kfunc as well. ==================== Signed-off-by: -
Kumar Kartikeya Dwivedi authored
Alexei pointed out that we can use BPF_REG_0 which already contains imm from move_blob2blob computation. Note that we now compare the second insn's imm, but this should not matter, since both will be zeroed out for the error case for the insn populated earlier. Suggested-by:
Kumar Kartikeya Dwivedi <memxor@gmail.com> Signed-off-by:
Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20211122235733.634914-4-memxor@gmail.com
-
Kumar Kartikeya Dwivedi authored
Instead, jump directly to success case stores in case ret >= 0, else do the default 0 value store and jump over the success case. This is better in terms of readability. Readjust the code for kfunc relocation as well to follow a similar pattern, also leads to easier to follow code now. Suggested-by:
-
Kumar Kartikeya Dwivedi authored
Andrii mentioned in [0] that switching to ARG_CONST_SIZE_OR_ZERO lets user avoid having to prove that string size at runtime is not zero and helps with not having to supress clang optimizations. [0]: https://lore.kernel.org/bpf/CAEf4BzZa_vhXB3c8atNcTS6=krQvC25H7K7c3WWZhM=27ro=Wg@mail.gmail.comSuggested-by:
-
Alexei Starovoitov authored
Joanne Koong says: ==================== This patchset add a new helper, bpf_loop. One of the complexities of using for loops in bpf programs is that the verifier needs to ensure that in every possibility of the loop logic, the loop will always terminate. As such, there is a limit on how many iterations the loop can do. The bpf_loop helper moves the loop logic into the kernel and can thereby guarantee that the loop will always terminate. The bpf_loop helper simplifies a lot of the complexity the verifier needs to check, as well as removes the constraint on the number of loops able to be run. From the test results, we see that using bpf_loop in place of the traditional for loop led to a decrease in verification time and number of bpf instructions by ~99%. The benchmark results show that as the number of iterations increases, the overhead per iteration decreases. The high-level overview of the patches - Patch 1 - kernel-side + API changes for adding bpf_loop Patch 2 - tests Patch 3 - use bpf_loop in strobemeta + pyperf600 and measure verifier performance Patch 4 - benchmark for throughput + latency of bpf_loop call v3 -> v4: ~ Address nits: use usleep for triggering bpf programs, fix copyright style v2 -> v3: ~ Rerun benchmarks on physical machine, update results ~ Propagate original error codes in the verifier v1 -> v2: ~ Change helper name to bpf_loop (instead of bpf_for_each) ~ Set max nr_loops (~8 million loops) for bpf_loop call ~ Split tests + strobemeta/pyperf600 changes into two patches ~ Add new ops_report_final helper for outputting throughput and latency ==================== Signed-off-by: -
Joanne Koong authored
Add benchmark to measure the throughput and latency of the bpf_loop call. Testing this on my dev machine on 1 thread, the data is as follows: nr_loops: 10 bpf_loop - throughput: 198.519 ± 0.155 M ops/s, latency: 5.037 ns/op nr_loops: 100 bpf_loop - throughput: 247.448 ± 0.305 M ops/s, latency: 4.041 ns/op nr_loops: 500 bpf_loop - throughput: 260.839 ± 0.380 M ops/s, latency: 3.834 ns/op nr_loops: 1000 bpf_loop - throughput: 262.806 ± 0.629 M ops/s, latency: 3.805 ns/op nr_loops: 5000 bpf_loop - throughput: 264.211 ± 1.508 M ops/s, latency: 3.785 ns/op nr_loops: 10000 bpf_loop - throughput: 265.366 ± 3.054 M ops/s, latency: 3.768 ns/op nr_loops: 50000 bpf_loop - throughput: 235.986 ± 20.205 M ops/s, latency: 4.238 ns/op nr_loops: 100000 bpf_loop - throughput: 264.482 ± 0.279 M ops/s, latency: 3.781 ns/op nr_loops: 500000 bpf_loop - throughput: 309.773 ± 87.713 M ops/s, latency: 3.228 ns/op nr_loops: 1000000 bpf_loop - throughput: 262.818 ± 4.143 M ops/s, latency: 3.805 ns/op >From this data, we can see that the latency per loop decreases as the number of loops increases. On this particular machine, each loop had an overhead of about ~4 ns, and we were able to run ~250 million loops per second. Signed-off-by:Joanne Koong <joannekoong@fb.com> Signed-off-by:
-
Joanne Koong authored
This patch tests bpf_loop in pyperf and strobemeta, and measures the verifier performance of replacing the traditional for loop with bpf_loop. The results are as follows: ~strobemeta~ Baseline verification time 6808200 usec stack depth 496 processed 554252 insns (limit 1000000) max_states_per_insn 16 total_states 15878 peak_states 13489 mark_read 3110 #192 verif_scale_strobemeta:OK (unrolled loop) Using bpf_loop verification time 31589 usec stack depth 96+400 processed 1513 insns (limit 1000000) max_states_per_insn 2 total_states 106 peak_states 106 mark_read 60 #193 verif_scale_strobemeta_bpf_loop:OK ~pyperf600~ Baseline verification time 29702486 usec stack depth 368 processed 626838 insns (limit 1000000) max_states_per_insn 7 total_states 30368 peak_states 30279 mark_read 748 #182 verif_scale_pyperf600:OK (unrolled loop) Using bpf_loop verification time 148488 usec stack depth 320+40 processed 10518 insns (limit 1000000) max_states_per_insn 10 total_states 705 peak_states 517 mark_read 38 #183 verif_scale_pyperf600_bpf_loop:OK Using the bpf_loop helper led to approximately a 99% decrease in the verification time and in the number of instructions. Signed-off-by: -
Joanne Koong authored
Add test for bpf_loop testing a variety of cases: various nr_loops, null callback ctx, invalid flags, nested callbacks. Signed-off-by:
-
Joanne Koong authored
This patch adds the kernel-side and API changes for a new helper function, bpf_loop: long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags); where long (*callback_fn)(u32 index, void *ctx); bpf_loop invokes the "callback_fn" **nr_loops** times or until the callback_fn returns 1. The callback_fn can only return 0 or 1, and this is enforced by the verifier. The callback_fn index is zero-indexed. A few things to please note: ~ The "u64 flags" parameter is currently unused but is included in case a future use case for it arises. ~ In the kernel-side implementation of bpf_loop (kernel/bpf/bpf_iter.c), bpf_callback_t is used as the callback function cast. ~ A program can have nested bpf_loop calls but the program must still adhere to the verifier constraint of its stack depth (the stack depth cannot exceed MAX_BPF_STACK)) ~ Recursive callback_fns do not pass the verifier, due to the call stack for these being too deep. ~ The next patch will include the tests and benchmark Signed-off-by:
-
Christoph Hellwig authored
filter.rst starts out documenting the classic BPF and then spills into introducing and documentating eBPF. Move the eBPF documentation into rwo new files under Documentation/bpf/ for the instruction set and the verifier and link to the BPF documentation from filter.rst. Signed-off-by:
Christoph Hellwig <hch@lst.de> Signed-off-by:
-
Christoph Hellwig authored
Move the general maps documentation into the maps.rst file from the overall networking filter documentation and add a link instead. Signed-off-by:
-
Christoph Hellwig authored
The eBPF name has completely taken over from eBPF in general usage for the actual eBPF representation, or BPF for any general in-kernel use. Prune all remaining references to "internal BPF". Signed-off-by:
-
Christoph Hellwig authored
The comment telling that the prog_free helper is freeing the program is not exactly useful, so just remove it. Signed-off-by:
-
Christoph Hellwig authored
Don't bother mentioning the file name as it is implied, and remove the reference to internal BPF. Signed-off-by:
-
Mehrdad Arshad Rad authored
There is a same action when load_attr.attach_btf_id is initialized. Signed-off-by:
Mehrdad Arshad Rad <arshad.rad@gmail.com> Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20211128193337.10628-1-arshad.rad@gmail.com
-
- 29 Nov, 2021 4 commits
-
-
Alan Maguire authored
When compiling libbpf with gcc 4.8.5, we see: CC staticobjs/btf_dump.o btf_dump.c: In function ‘btf_dump_dump_type_data.isra.24’: btf_dump.c:2296:5: error: ‘err’ may be used uninitialized in this function [-Werror=maybe-uninitialized] if (err < 0) ^ cc1: all warnings being treated as errors make: *** [staticobjs/btf_dump.o] Error 1 While gcc 4.8.5 is too old to build the upstream kernel, it's possible it could be used to build standalone libbpf which suffers from the same problem. Silence the error by initializing 'err' to 0. The warning/error seems to be a false positive since err is set early in the function. Regardless we shouldn't prevent libbpf from building for this. Fixes: 920d16af ("libbpf: BTF dumper support for typed data") Signed-off-by:Alan Maguire <alan.maguire@oracle.com> Signed-off-by:
-
Andrii Nakryiko authored
Hengqi Chen says: ==================== Make libbpf support static initialization of BPF_MAP_TYPE_PROG_ARRAY with a syntax similar to map-in-map initialization: SEC("socket") int tailcall_1(void *ctx) { return 0; } struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __uint(max_entries, 2); __uint(key_size, sizeof(__u32)); __array(values, int (void *)); } prog_array_init SEC(".maps") = { .values = { [1] = (void *)&tailcall_1, }, }; v1->v2: - Add stricter checks on relos collect, some renamings (Andrii) - Update selftest to check tailcall result (Andrii) ==================== Signed-off-by: -
Hengqi Chen authored
Add testcase for BPF_MAP_TYPE_PROG_ARRAY static initialization. Signed-off-by:
Hengqi Chen <hengqi.chen@gmail.com> Signed-off-by:
-
Hengqi Chen authored
Support static initialization of BPF_MAP_TYPE_PROG_ARRAY with a syntax similar to map-in-map initialization ([0]): SEC("socket") int tailcall_1(void *ctx) { return 0; } struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __uint(max_entries, 2); __uint(key_size, sizeof(__u32)); __array(values, int (void *)); } prog_array_init SEC(".maps") = { .values = { [1] = (void *)&tailcall_1, }, }; Here's the relevant part of libbpf debug log showing what's going on with prog-array initialization: libbpf: sec '.relsocket': collecting relocation for section(3) 'socket' libbpf: sec '.relsocket': relo #0: insn #2 against 'prog_array_init' libbpf: prog 'entry': found map 0 (prog_array_init, sec 4, off 0) for insn #0 libbpf: .maps relo #0: for 3 value 0 rel->r_offset 32 name 53 ('tailcall_1') libbpf: .maps relo #0: map 'prog_array_init' slot [1] points to prog 'tailcall_1' libbpf: map 'prog_array_init': created successfully, fd=5 libbpf: map 'prog_array_init': slot [1] set to prog 'tailcall_1' fd=6 [0] Closes: https://github.com/libbpf/libbpf/issues/354Signed-off-by:
-
- 26 Nov, 2021 1 commit
-
-
Tiezhu Yang authored
Add the __NR_bpf definitions to fix the following build errors for mips: $ cd tools/bpf/bpftool $ make [...] bpf.c:54:4: error: #error __NR_bpf not defined. libbpf does not support your arch. # error __NR_bpf not defined. libbpf does not support your arch. ^~~~~ bpf.c: In function ‘sys_bpf’: bpf.c:66:17: error: ‘__NR_bpf’ undeclared (first use in this function); did you mean ‘__NR_brk’? return syscall(__NR_bpf, cmd, attr, size); ^~~~~~~~ __NR_brk [...] In file included from gen_loader.c:15:0: skel_internal.h: In function ‘skel_sys_bpf’: skel_internal.h:53:17: error: ‘__NR_bpf’ undeclared (first use in this function); did you mean ‘__NR_brk’? return syscall(__NR_bpf, cmd, attr, size); ^~~~~~~~ __NR_brk We can see the following generated definitions: $ grep -r "#define __NR_bpf" arch/mips arch/mips/include/generated/uapi/asm/unistd_o32.h:#define __NR_bpf (__NR_Linux + 355) arch/mips/include/generated/uapi/asm/unistd_n64.h:#define __NR_bpf (__NR_Linux + 315) arch/mips/include/generated/uapi/asm/unistd_n32.h:#define __NR_bpf (__NR_Linux + 319) The __NR_Linux is defined in arch/mips/include/uapi/asm/unistd.h: $ grep -r "#define __NR_Linux" arch/mips arch/mips/include/uapi/asm/unistd.h:#define __NR_Linux 4000 arch/mips/include/uapi/asm/unistd.h:#define __NR_Linux 5000 arch/mips/include/uapi/asm/unistd.h:#define __NR_Linux 6000 That is to say, __NR_bpf is: 4000 + 355 = 4355 for mips o32, 6000 + 319 = 6319 for mips n32, 5000 + 315 = 5315 for mips n64. So use the GCC pre-defined macro _ABIO32, _ABIN32 and _ABI64 [1] to define the corresponding __NR_bpf. This patch is similar with commit bad1926d ("bpf, s390: fix build for libbpf and selftest suite"). [1] https://gcc.gnu.org/git/?p=gcc.git;a=blob;f=gcc/config/mips/mips.h#l549Signed-off-by:Tiezhu Yang <yangtiezhu@loongson.cn> Signed-off-by:
-
- 25 Nov, 2021 8 commits
-
-
Andrii Nakryiko authored
Similar to previous patch, just copy over necessary struct into local stack variable before checking its fields. Signed-off-by:
-
Andrii Nakryiko authored
Construct packet buffer explicitly for each packet to avoid unaligned memory accesses. Signed-off-by:
-
Andrii Nakryiko authored
Buf can be not zero-terminated leading to strstr() to access data beyond the intended buf[] array. Fix by forcing zero termination. Signed-off-by:
-
Andrii Nakryiko authored
Copy over iphdr into a local variable before accessing its fields. Signed-off-by:
-
Andrii Nakryiko authored
Perfbuf doesn't guarantee 8-byte alignment of the data like BPF ringbuf does, so struct get_stack_trace_t can arrive not properly aligned for subsequent u64 accesses. Easiest fix is to just copy data locally. Signed-off-by:
-
Andrii Nakryiko authored
Prevent sanitizer from complaining about passing NULL into memcpy(), even if it happens with zero size. Signed-off-by:
-
Andrii Nakryiko authored
Test is using __int128 variable as unsigned and highest order bit can be set to 1 after bit shift. Use unsigned __int128 explicitly and prevent UBSan from complaining. Signed-off-by:
-
Andrii Nakryiko authored
add_dst_sec() can invalidate bpf_linker's section index making dst_symtab pointer pointing into unallocated memory. Reinitialize dst_symtab pointer on each iteration to make sure it's always valid. Fixes: faf6ed32 ("libbpf: Add BPF static linker APIs") Signed-off-by:
-
