On Wed, 12 Jan 2022 16:33:53 +0900
Masami Hiramatsu [off-list ref] wrote:
Hi Alexei,
On Tue, 11 Jan 2022 14:39:44 -0800
Alexei Starovoitov [off-list ref] wrote:
quoted
On Wed, Jan 12, 2022 at 12:00:17AM +0900, Masami Hiramatsu wrote:
quoted
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)
OK, I've updated fprobes to use the ftrace_set_filter_ips()
and got below result.
/lib/modules/5.16.0-rc4+/kernel/samples/fprobe # time insmod fprobe_example.ko s
ymbol='btrfs_*'
[ 36.130947] fprobe_init: 1028 symbols found
[ 36.177901] fprobe_init: Planted fprobe at btrfs_*
real 0m 0.08s
user 0m 0.00s
sys 0m 0.07s
Let me update the series :)
Thank you,
--
Masami Hiramatsu [off-list ref]