Re: [RFC PATCH 0/6] fprobe: Introduce fprobe function entry/exit probe

[Masami Hiramatsu]

Hi Alexei,

On Tue, 11 Jan 2022 14:39:44 -0800
Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx> wrote:

> On Wed, Jan 12, 2022 at 12:00:17AM +0900, Masami Hiramatsu wrote:
> > Hi Jiri,
> > 
> > Here is a short series of patches, which shows what I replied
> > to your series.
> > 
> > This introduces the fprobe, the function entry/exit probe with
> > multiple probe point support. This also introduces the rethook
> > for hooking function return, which I cloned from kretprobe.
> > 
> > I also rewrite your [08/13] bpf patch to use this fprobe instead
> > of kprobes. I didn't tested that one, but the sample module seems
> > to work. Please test bpf part with your libbpf updates.
> > 
> > BTW, while implementing the fprobe, I introduced the per-probe
> > point private data, but I'm not sure why you need it. It seems
> > that data is not used from bpf...
> > 
> > If this is good for you, I would like to proceed this with
> > the rethook and rewrite the kretprobe to use the rethook to
> > hook the functions. That should be much cleaner (and easy to
> > prepare for the fgraph tracer integration)
> 
> What is the speed of attach/detach of thousands fprobes?

I've treaked my example module and it shows below result;

/lib/modules/5.16.0-rc4+/kernel/samples/fprobe # time insmod ./fprobe_example.ko
 symbol='btrfs_*'
[  187.095925] fprobe_init: 1028 symbols found
[  188.521694] fprobe_init: Planted fprobe at btrfs_*
real	0m 1.47s
user	0m 0.00s
sys	0m 1.36s

I think using ftrace_set_filter_ips() can make it faster.
(maybe it needs to drop per-probe point private data, that
prevents fprobe to use that interface)

Thank you,

-- 
Masami Hiramatsu <mhiramat@xxxxxxxxxx>