From: Jakub Kicinski <jakub.kicinski@netronome.com>
To: netdev@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net,
Jakub Kicinski <jakub.kicinski@netronome.com>
Subject: [PATCHv7 net-next 03/15] net: cls_bpf: add support for marking filters as hardware-only
Date: Wed, 21 Sep 2016 11:43:55 +0100 [thread overview]
Message-ID: <1474454647-20137-4-git-send-email-jakub.kicinski@netronome.com> (raw)
In-Reply-To: <1474454647-20137-1-git-send-email-jakub.kicinski@netronome.com>
Add cls_bpf support for the TCA_CLS_FLAGS_SKIP_SW flag.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
---
net/sched/cls_bpf.c | 34 +++++++++++++++++++++++++---------
1 file changed, 25 insertions(+), 9 deletions(-)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index ebf01f7c1470..1becc2fe1bc5 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -28,7 +28,7 @@ MODULE_DESCRIPTION("TC BPF based classifier");
#define CLS_BPF_NAME_LEN 256
#define CLS_BPF_SUPPORTED_GEN_FLAGS \
- TCA_CLS_FLAGS_SKIP_HW
+ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW)
struct cls_bpf_head {
struct list_head plist;
@@ -96,7 +96,9 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
qdisc_skb_cb(skb)->tc_classid = prog->res.classid;
- if (at_ingress) {
+ if (tc_skip_sw(prog->gen_flags)) {
+ filter_res = prog->exts_integrated ? TC_ACT_UNSPEC : 0;
+ } else if (at_ingress) {
/* It is safe to push/pull even if skb_shared() */
__skb_push(skb, skb->mac_len);
bpf_compute_data_end(skb);
@@ -164,32 +166,42 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
tp->protocol, &offload);
}
-static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
- struct cls_bpf_prog *oldprog)
+static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+ struct cls_bpf_prog *oldprog)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct cls_bpf_prog *obj = prog;
enum tc_clsbpf_command cmd;
+ bool skip_sw;
+ int ret;
+
+ skip_sw = tc_skip_sw(prog->gen_flags) ||
+ (oldprog && tc_skip_sw(oldprog->gen_flags));
if (oldprog && oldprog->offloaded) {
if (tc_should_offload(dev, tp, prog->gen_flags)) {
cmd = TC_CLSBPF_REPLACE;
- } else {
+ } else if (!tc_skip_sw(prog->gen_flags)) {
obj = oldprog;
cmd = TC_CLSBPF_DESTROY;
+ } else {
+ return -EINVAL;
}
} else {
if (!tc_should_offload(dev, tp, prog->gen_flags))
- return;
+ return skip_sw ? -EINVAL : 0;
cmd = TC_CLSBPF_ADD;
}
- if (cls_bpf_offload_cmd(tp, obj, cmd))
- return;
+ ret = cls_bpf_offload_cmd(tp, obj, cmd);
+ if (ret)
+ return skip_sw ? ret : 0;
obj->offloaded = true;
if (oldprog)
oldprog->offloaded = false;
+
+ return 0;
}
static void cls_bpf_stop_offload(struct tcf_proto *tp,
@@ -498,7 +510,11 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
if (ret < 0)
goto errout;
- cls_bpf_offload(tp, prog, oldprog);
+ ret = cls_bpf_offload(tp, prog, oldprog);
+ if (ret) {
+ cls_bpf_delete_prog(tp, prog);
+ return ret;
+ }
if (oldprog) {
list_replace_rcu(&oldprog->link, &prog->link);
--
1.9.1
next prev parent reply other threads:[~2016-09-21 10:44 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-21 10:43 [PATCHv7 net-next 00/15] BPF hardware offload (cls_bpf for now) Jakub Kicinski
2016-09-21 10:43 ` [PATCHv7 net-next 01/15] net: cls_bpf: add hardware offload Jakub Kicinski
2016-09-21 10:43 ` [PATCHv7 net-next 02/15] net: cls_bpf: limit hardware offload by software-only flag Jakub Kicinski
2016-09-21 10:43 ` Jakub Kicinski [this message]
2016-09-21 10:43 ` [PATCHv7 net-next 04/15] bpf: don't (ab)use instructions to store state Jakub Kicinski
2016-09-21 10:43 ` [PATCHv7 net-next 05/15] bpf: expose internal verfier structures Jakub Kicinski
2016-09-21 10:43 ` [PATCHv7 net-next 06/15] bpf: enable non-core use of the verfier Jakub Kicinski
2016-09-21 10:43 ` [PATCHv7 net-next 07/15] bpf: recognize 64bit immediate loads as consts Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 08/15] nfp: add BPF to NFP code translator Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 09/15] nfp: bpf: add hardware bpf offload Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 10/15] net: cls_bpf: allow offloaded filters to update stats Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 11/15] nfp: bpf: " Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 12/15] nfp: bpf: add packet marking support Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 13/15] net: act_mirred: allow statistic updates from offloaded actions Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 14/15] nfp: bpf: add support for legacy redirect action Jakub Kicinski
2016-09-21 10:44 ` [PATCHv7 net-next 15/15] nfp: bpf: add offload of TC direct action mode Jakub Kicinski
2016-09-21 10:48 ` [PATCHv7 net-next 00/15] BPF hardware offload (cls_bpf for now) Jakub Kicinski
2016-09-21 13:35 ` Daniel Borkmann
2016-09-21 23:56 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1474454647-20137-4-git-send-email-jakub.kicinski@netronome.com \
--to=jakub.kicinski@netronome.com \
--cc=ast@kernel.org \
--cc=daniel@iogearbox.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).