Daniel Xu
Daniel Xu
I think you'll need to add a cmake test to detect the `init_disassemble_info` signature change.
Closing in favor of #2328
Runtime detection sounds reasonable. I originally suggested compile time flag b/c it was faster to iterate with than writing runtime detection code. Since this touches on pretty core parts of...
Getting filesystem paths through bpf is notoriously tricky b/c you need to take locks. IIUC from following the kernel discussions, the main issue is deadlocks b/c the bpf prog could...
@bwplotka It looks like you're using hybrid cgroup1 + cgroup2 setup on your host. I believe under cgroup1, a process may be in multiple cgroups. Under cgroup2, a process may...
Hi, sorry about slow response. > Was there any work already done on this? Not that I'm aware of, but I've been a bit out of the loop lately. >...
I read through most of this PR and it looks quite reasonable.
Hmm, can't seem to reproduce on master: ``` $ sudo ./build/src/bpftrace ~/scratch/bpftrace/bugs/sys_types.h Attaching 1 probe... $ sudo ./build/src/bpftrace ~/scratch/bpftrace/bugs/sys_types.h --btf Attaching 1 probe... $ cat ~/scratch/bpftrace/bugs/sys_types.h #include BEGIN { exit();...
I am open to this as well. I evaluated the same idea ~1 year ago but stopped short of implementing for a few reasons: 1. bpftrace does some tricky things...
To expand, I think vendoring libbpf is really the only sane long term solution. It is more or less inevitable that we will have to carry some out of tree...