[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20160809235955.GA28438@ircssh.c.rugged-nimbus-611.internal>
Date: Tue, 9 Aug 2016 16:59:57 -0700
From: Sargun Dhillon <sargun@...gun.me>
To: netdev@...r.kernel.org
Cc: alexei.starovoitov@...il.com, daniel@...earbox.net
Subject: [net-next v2 v2 0/2] Add bpf current_task_in_cgroup helper &
opensnoop example
This patchset includes a helper and an example to determine whether the probe is
currently executing in the context of a specific cgroup based on a cgroup bpf
map / array. The helper checks the cgroupsv2 hierarchy based on the handle in
the map and if the current cgroup is equal to it, or a descendant of it. The
helper was tested with the example program, and it was verified that the correct
behaviour occurs in the interrupt context.
The example on the other hand, "open snoop" is much simplified version of that
in the iovisor/BCC project. In order to run it, you must supply a specific
cgroup in the hierarchy, and it'll print out all files being opened under it.
v1->v2: Add better example code -- OpenSnoop, clean up
Sargun Dhillon (2):
bpf: Add bpf_current_task_in_cgroup helper
samples/bpf: Add opensnoop example that uses current_task_in_cgroup
helper
include/linux/bpf.h | 24 +++++++++++++
include/uapi/linux/bpf.h | 11 ++++++
kernel/bpf/arraymap.c | 2 +-
kernel/bpf/verifier.c | 4 ++-
kernel/trace/bpf_trace.c | 34 ++++++++++++++++++
net/core/filter.c | 11 +++---
samples/bpf/Makefile | 4 +++
samples/bpf/bpf_helpers.h | 2 ++
samples/bpf/trace_opensnoop_kern.c | 35 +++++++++++++++++++
samples/bpf/trace_opensnoop_user.c | 70 ++++++++++++++++++++++++++++++++++++++
10 files changed, 188 insertions(+), 9 deletions(-)
create mode 100644 samples/bpf/trace_opensnoop_kern.c
create mode 100644 samples/bpf/trace_opensnoop_user.c
--
2.7.4
Powered by blists - more mailing lists