- 03 May, 2017 6 commits
-
-
4ast authored
docs: update features list (ThunderX support for XDP)
-
4ast authored
cc: Work around verifier error when reading USDT probe arguments
-
Teng Qin authored
-
Arthur Gautier authored
explicit the type of the nlattr Signed-off-by: Arthur Gautier <baloo@gandi.net>
-
Sasha Goldshtein authored
The code generated by the USDT helpers for reading probe arguments occasionally caused a verifier error due to a construct similar to the following: ``` switch (ctx->ip) { case 0xaaaa: *dest = ctx->cx; break; case 0xbbbb: *dest = ctx->dx; break; } ``` This would generate an instruction sequence that attempts to access ctx through an offset that is not statically known, which confuses the verifier. This was reported in #751, #829, and #1133, and likely seen by others as well. The workaround, suggested by @yonghong-song, is to force memory writes by using the volatile modifier, which precludes this specific optimization. Resolves #751, #829, #1133.
-
Quentin Monnet authored
-
- 02 May, 2017 3 commits
-
-
4ast authored
docs: update features list
-
Quentin Monnet authored
Update of BPF features list, following the release of kernel 4.11. New items include: - Sparc eBPF JIT - ixgbe support for XDP - eBPF benchmarking facility - new helpers `get_socket_*()`
-
4ast authored
Small improvements to symboling availiability
-
- 01 May, 2017 3 commits
-
-
Teng Qin authored
Currently we check if `ProcSyms` needs refresh for every symboling call. However if the `ProcSyms` was loaded, but the Process terminated later, we will see it as a "need refresh" and effectively clear the symbol table and not able to resovle anything anymore. This commit changes so that we only refresh when the PID still exists (but differnt from what loaded).
-
Teng Qin authored
Currently we think the Module's symbol table is not loaed as long as its empty. But some times we were just not able to read the symbols from the binary / perf map, or didn't get symbol from the read. This commit makes so that we don't end up trying to do a read on each lookup.
-
Brenden Blanco authored
Install sudo inside the debian build container
-
- 30 Apr, 2017 1 commit
-
-
Sam Kottler authored
-
- 28 Apr, 2017 1 commit
-
-
4ast authored
frontend/b: fixes for LLVM 4.0 API change
-
- 27 Apr, 2017 5 commits
-
-
Brenden Blanco authored
Upstream LLVM added a new parameter to the AllocaInst constructor, which breaks compilation. Fix it by using the IRBuilder method. Signed-off-by: Brenden Blanco <bblanco@gmail.com>
-
Brenden Blanco authored
Add default -Wno-address-of-packed-membe to Clang loader
-
Teng Qin authored
-
4ast authored
Use uintptr_t for addresses in C++ API
-
Teng Qin authored
-
- 26 Apr, 2017 2 commits
-
-
Brenden Blanco authored
[RFC]: Extend table API with string support
-
Mauricio Vasquez B authored
This commit exposes functions to convert between key and value from/to strings, additionally it implements the BPFTable class that allows accessing tables using strings. Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
-
- 21 Apr, 2017 3 commits
-
-
Brenden Blanco authored
With local LLVM (4.0ish), inline strings in this test case would segfault. Fix the crash by constructing explicitly on the stack. Signed-off-by: Brenden Blanco <bblanco@gmail.com>
-
Brenden Blanco authored
Possibly due to local LLVM differences, this change was needed for sslsniff code to pass the verifier. Signed-off-by: Brenden Blanco <bblanco@gmail.com>
-
Brenden Blanco authored
On my system, the manually unrolled stack walker fails the verifier, due to what seems to me like an incorrect return statement. Setting bp = 0 has no effect, seems that the intent was to return 0 instead. Not sure why others haven't hit this, but the fix contained here seems reasonable. Signed-off-by: Brenden Blanco <bblanco@gmail.com>
-
- 20 Apr, 2017 6 commits
-
-
4ast authored
Disable non-static function calls
-
Brenden Blanco authored
Compiled BPF programs must consist of a single contiguous code block, meaning trying to call other function entry points (besides the kernel-defined helpers) is not possible. The bcc frontend didn't explicitly prohibit this, even though the program would fail to compile/load. Add an explicit check and error message. Fixes: #653 Signed-off-by: Brenden Blanco <bblanco@gmail.com>
-
Colin Ian King authored
Minor sorting of the yaml tool list and sync it to the latest updates in tools Signed-off-by: Colin Ian King <colin.king@canonical.com>
-
Sasha Goldshtein authored
Printing the BPF program after loading it means that if there is a load error, the program isn't printed, which sort of defeats the purpose of the whole thing.
-
Sasha Goldshtein authored
-
Simon Liu authored
-
- 19 Apr, 2017 4 commits
-
-
Nikita V. Shirokov authored
* adding args matching option * fixing typos * fixing merge artefacts * [execsnoop]: adding documentation on -l in man * [execsnoop][man]: fixing typo in commands name
-
Tobias Klauser authored
Add a link to the proposed generic XDP feature to the list of XDP features.
-
4ast authored
Use normal inlining in clang loader
-
Huapeng Zhou authored
-
- 18 Apr, 2017 1 commit
-
-
Brendan Gregg authored
Display pid namespace in summary histogram using a new `--pidnss` option.
-
- 17 Apr, 2017 1 commit
-
-
Simon Liu authored
used the CheckCXXCompilerFlag module of Cmake to check the compiler whether or not supporting c++11. (#1116)
-
- 16 Apr, 2017 1 commit
-
-
4ast authored
bcc: add __attribute__((always_inline)) to helper functions
-
- 15 Apr, 2017 1 commit
-
-
Huapeng Zhou authored
-
- 14 Apr, 2017 2 commits
-
-
Simon Liu authored
When using Clang 3.9(compiled by GCC 6.x), bcc will used -isystem, because the GCC_VERSION(get the version of the Clang) is less 6.0. And then the compiler will compile failed.
-
Paul Chaignon authored
In bcc, ProgArray.__delitem__ defaults to ArrayBase.__delitem__ which uses the bpf_update_elem helper to clear the item (override with a null value). However, eBPF doesn't offer a bpf_update_elem helper for prog arrays. This pull request overrides __delitem__ in ProgArray to use the bpf_delete_item helper.
-