From: Jiri Pirko <jiri@resnulli.us>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, jhs@mojatatu.com, xiyou.wangcong@gmail.com,
mlxsw@mellanox.com, andrew@lunn.ch,
vivien.didelot@savoirfairelinux.com, f.fainelli@gmail.com,
michael.chan@broadcom.com, ganeshgr@chelsio.com,
saeedm@mellanox.com, matanb@mellanox.com, leonro@mellanox.com,
idosch@mellanox.com, jakub.kicinski@netronome.com,
simon.horman@netronome.com, pieter.jansenvanvuuren@netronome.com,
john.hurley@netronome.com, alexander.h.duyck@intel.com,
ogerlitz@mellanox.com, john.fastabend@gmail.com,
daniel@iogearbox.net, dsahern@gmail.com
Subject: [patch net-next v10 07/13] net: sched: use block index as a handle instead of qdisc when block is shared
Date: Tue, 16 Jan 2018 16:33:10 +0100 [thread overview]
Message-ID: <20180116153316.4751-8-jiri@resnulli.us> (raw)
In-Reply-To: <20180116153316.4751-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
As the tcm_ifindex with value TCM_IFINDEX_MAGIC_BLOCK is invalid ifindex,
use it to indicate that we work with block, instead of qdisc.
So if tcm_ifindex is set to TCM_IFINDEX_MAGIC_BLOCK, tcm_parent is used
to carry block_index.
If the block is set to be shared between at least 2 qdiscs, it is
forbidden to use the qdisc handle to add/delete filters. In that case,
userspace has to pass block_index.
Also, for dump of the filters, in case the block is shared in between at
least 2 qdiscs, the each filter is dumped with tcm_ifindex value
TCM_IFINDEX_MAGIC_BLOCK and tcm_parent set to block_index. That gives
the user clear indication, that the filter belongs to a shared block
and not only to one qdisc under which it is dumped.
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v9->10:
- fixed ifindex magic in the patch description
v7->v8:
- added comment to ifindex block magic
v6->v7:
- changed extack message for block index handle as suggested by DaveA
- added extack message when block index does not exist
- the block ifindex magic is in define and change to 0xffffffff
as suggested by Jamal
v5->v6:
- new patch
---
include/uapi/linux/rtnetlink.h | 10 ++
net/sched/cls_api.c | 202 ++++++++++++++++++++++++-----------------
2 files changed, 128 insertions(+), 84 deletions(-)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 843e29a..da878f2 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -541,9 +541,19 @@ struct tcmsg {
int tcm_ifindex;
__u32 tcm_handle;
__u32 tcm_parent;
+/* tcm_block_index is used instead of tcm_parent
+ * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK
+ */
+#define tcm_block_index tcm_parent
__u32 tcm_info;
};
+/* For manipulation of filters in shared block, tcm_ifindex is set to
+ * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index
+ * which is the block index.
+ */
+#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU)
+
enum {
TCA_UNSPEC,
TCA_KIND,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0ff8ae9..d687e58 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -865,8 +865,9 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
}
static int tcf_fill_node(struct net *net, struct sk_buff *skb,
- struct tcf_proto *tp, struct Qdisc *q, u32 parent,
- void *fh, u32 portid, u32 seq, u16 flags, int event)
+ struct tcf_proto *tp, struct tcf_block *block,
+ struct Qdisc *q, u32 parent, void *fh,
+ u32 portid, u32 seq, u16 flags, int event)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
@@ -879,8 +880,13 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
tcm->tcm_family = AF_UNSPEC;
tcm->tcm__pad1 = 0;
tcm->tcm__pad2 = 0;
- tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
- tcm->tcm_parent = parent;
+ if (q) {
+ tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
+ tcm->tcm_parent = parent;
+ } else {
+ tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
+ tcm->tcm_block_index = block->index;
+ }
tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
if (nla_put_string(skb, TCA_KIND, tp->ops->kind))
goto nla_put_failure;
@@ -903,8 +909,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
static int tfilter_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
- struct Qdisc *q, u32 parent,
- void *fh, int event, bool unicast)
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, void *fh, int event, bool unicast)
{
struct sk_buff *skb;
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
@@ -913,8 +919,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
- n->nlmsg_flags, event) <= 0) {
+ if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
+ n->nlmsg_seq, n->nlmsg_flags, event) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
@@ -928,8 +934,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct tcf_proto *tp,
- struct Qdisc *q, u32 parent,
- void *fh, bool unicast, bool *last)
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, void *fh, bool unicast, bool *last)
{
struct sk_buff *skb;
u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
@@ -939,8 +945,8 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
- n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
+ if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
+ n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
@@ -959,15 +965,16 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
}
static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
- struct Qdisc *q, u32 parent,
- struct nlmsghdr *n,
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, struct nlmsghdr *n,
struct tcf_chain *chain, int event)
{
struct tcf_proto *tp;
for (tp = rtnl_dereference(chain->filter_chain);
tp; tp = rtnl_dereference(tp->next))
- tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false);
+ tfilter_notify(net, oskb, n, tp, block,
+ q, parent, 0, event, false);
}
/* Add/change/delete/get a filter node */
@@ -983,13 +990,11 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
bool prio_allocate;
u32 parent;
u32 chain_index;
- struct net_device *dev;
- struct Qdisc *q;
+ struct Qdisc *q = NULL;
struct tcf_chain_info chain_info;
struct tcf_chain *chain = NULL;
struct tcf_block *block;
struct tcf_proto *tp;
- const struct Qdisc_class_ops *cops;
unsigned long cl;
void *fh;
int err;
@@ -1036,41 +1041,58 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Find head of filter chain. */
- /* Find link */
- dev = __dev_get_by_index(net, t->tcm_ifindex);
- if (dev == NULL)
- return -ENODEV;
-
- /* Find qdisc */
- if (!parent) {
- q = dev->qdisc;
- parent = q->handle;
+ if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+ block = tcf_block_lookup(net, t->tcm_block_index);
+ if (!block) {
+ NL_SET_ERR_MSG(extack, "Block of given index was not found");
+ err = -EINVAL;
+ goto errout;
+ }
} else {
- q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
- if (q == NULL)
- return -EINVAL;
- }
+ const struct Qdisc_class_ops *cops;
+ struct net_device *dev;
- /* Is it classful? */
- cops = q->ops->cl_ops;
- if (!cops)
- return -EINVAL;
+ /* Find link */
+ dev = __dev_get_by_index(net, t->tcm_ifindex);
+ if (!dev)
+ return -ENODEV;
- if (!cops->tcf_block)
- return -EOPNOTSUPP;
+ /* Find qdisc */
+ if (!parent) {
+ q = dev->qdisc;
+ parent = q->handle;
+ } else {
+ q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
+ if (!q)
+ return -EINVAL;
+ }
- /* Do we search for filter, attached to class? */
- if (TC_H_MIN(parent)) {
- cl = cops->find(q, parent);
- if (cl == 0)
- return -ENOENT;
- }
+ /* Is it classful? */
+ cops = q->ops->cl_ops;
+ if (!cops)
+ return -EINVAL;
- /* And the last stroke */
- block = cops->tcf_block(q, cl, extack);
- if (!block) {
- err = -EINVAL;
- goto errout;
+ if (!cops->tcf_block)
+ return -EOPNOTSUPP;
+
+ /* Do we search for filter, attached to class? */
+ if (TC_H_MIN(parent)) {
+ cl = cops->find(q, parent);
+ if (cl == 0)
+ return -ENOENT;
+ }
+
+ /* And the last stroke */
+ block = cops->tcf_block(q, cl, extack);
+ if (!block) {
+ err = -EINVAL;
+ goto errout;
+ }
+ if (tcf_block_shared(block)) {
+ NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
+ err = -EOPNOTSUPP;
+ goto errout;
+ }
}
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
@@ -1086,7 +1108,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
}
if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
- tfilter_notify_chain(net, skb, q, parent, n,
+ tfilter_notify_chain(net, skb, block, q, parent, n,
chain, RTM_DELTFILTER);
tcf_chain_flush(chain);
err = 0;
@@ -1134,7 +1156,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (!fh) {
if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
tcf_chain_tp_remove(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, q, parent, fh,
+ tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_DELTFILTER, false);
tcf_proto_destroy(tp);
err = 0;
@@ -1159,8 +1181,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
}
break;
case RTM_DELTFILTER:
- err = tfilter_del_notify(net, skb, n, tp, q, parent,
- fh, false, &last);
+ err = tfilter_del_notify(net, skb, n, tp, block,
+ q, parent, fh, false, &last);
if (err)
goto errout;
if (last) {
@@ -1169,8 +1191,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
}
goto errout;
case RTM_GETTFILTER:
- err = tfilter_notify(net, skb, n, tp, q, parent, fh,
- RTM_NEWTFILTER, true);
+ err = tfilter_notify(net, skb, n, tp, block, q, parent,
+ fh, RTM_NEWTFILTER, true);
goto errout;
default:
err = -EINVAL;
@@ -1183,7 +1205,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (err == 0) {
if (tp_created)
tcf_chain_tp_insert(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, q, parent, fh,
+ tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false);
} else {
if (tp_created)
@@ -1203,6 +1225,7 @@ struct tcf_dump_args {
struct tcf_walker w;
struct sk_buff *skb;
struct netlink_callback *cb;
+ struct tcf_block *block;
struct Qdisc *q;
u32 parent;
};
@@ -1212,7 +1235,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
struct tcf_dump_args *a = (void *)arg;
struct net *net = sock_net(a->skb->sk);
- return tcf_fill_node(net, a->skb, tp, a->q, a->parent,
+ return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
n, NETLINK_CB(a->cb->skb).portid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER);
@@ -1223,6 +1246,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
long index_start, long *p_index)
{
struct net *net = sock_net(skb->sk);
+ struct tcf_block *block = chain->block;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
struct tcf_dump_args arg;
struct tcf_proto *tp;
@@ -1241,7 +1265,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (cb->args[1] == 0) {
- if (tcf_fill_node(net, skb, tp, q, parent, 0,
+ if (tcf_fill_node(net, skb, tp, block, q, parent, 0,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWTFILTER) <= 0)
@@ -1254,6 +1278,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
arg.w.fn = tcf_node_dump;
arg.skb = skb;
arg.cb = cb;
+ arg.block = block;
arg.q = q;
arg.parent = parent;
arg.w.stop = 0;
@@ -1272,13 +1297,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
- struct net_device *dev;
- struct Qdisc *q;
+ struct Qdisc *q = NULL;
struct tcf_block *block;
struct tcf_chain *chain;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
- unsigned long cl = 0;
- const struct Qdisc_class_ops *cops;
long index_start;
long index;
u32 parent;
@@ -1291,32 +1313,44 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if (err)
return err;
- dev = __dev_get_by_index(net, tcm->tcm_ifindex);
- if (!dev)
- return skb->len;
-
- parent = tcm->tcm_parent;
- if (!parent) {
- q = dev->qdisc;
- parent = q->handle;
+ if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+ block = tcf_block_lookup(net, tcm->tcm_block_index);
+ if (!block)
+ goto out;
} else {
- q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
- }
- if (!q)
- goto out;
- cops = q->ops->cl_ops;
- if (!cops)
- goto out;
- if (!cops->tcf_block)
- goto out;
- if (TC_H_MIN(tcm->tcm_parent)) {
- cl = cops->find(q, tcm->tcm_parent);
- if (cl == 0)
+ const struct Qdisc_class_ops *cops;
+ struct net_device *dev;
+ unsigned long cl = 0;
+
+ dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
+ return skb->len;
+
+ parent = tcm->tcm_parent;
+ if (!parent) {
+ q = dev->qdisc;
+ parent = q->handle;
+ } else {
+ q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
+ }
+ if (!q)
goto out;
+ cops = q->ops->cl_ops;
+ if (!cops)
+ goto out;
+ if (!cops->tcf_block)
+ goto out;
+ if (TC_H_MIN(tcm->tcm_parent)) {
+ cl = cops->find(q, tcm->tcm_parent);
+ if (cl == 0)
+ goto out;
+ }
+ block = cops->tcf_block(q, cl, NULL);
+ if (!block)
+ goto out;
+ if (tcf_block_shared(block))
+ q = NULL;
}
- block = cops->tcf_block(q, cl, NULL);
- if (!block)
- goto out;
index_start = cb->args[0];
index = 0;
--
2.9.5
next prev parent reply other threads:[~2018-01-16 15:33 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-16 15:33 [patch net-next v10 00/13] net: sched: allow qdiscs to share filter block instances Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 01/13] net: sched: introduce support for multiple filter chain pointers registration Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 02/13] net: sched: introduce shared filter blocks infrastructure Jiri Pirko
2018-01-17 0:03 ` Cong Wang
2018-01-17 8:59 ` Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 03/13] net: sched: avoid usage of tp->q in tcf_classify Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 04/13] net: sched: introduce block mechanism to handle netif_keep_dst calls Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 05/13] net: sched: remove classid and q fields from tcf_proto Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 06/13] net: sched: keep track of offloaded filters and check tc offload feature Jiri Pirko
2018-01-16 15:33 ` Jiri Pirko [this message]
2018-01-16 15:33 ` [patch net-next v10 08/13] net: sched: introduce ingress/egress block index attributes for qdisc Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 09/13] net: sched: allow ingress and clsact qdiscs to share filter blocks Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 10/13] mlxsw: spectrum_acl: Reshuffle code around mlxsw_sp_acl_ruleset_create/destroy Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 11/13] mlxsw: spectrum_acl: Don't store netdev and ingress for ruleset unbind Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 12/13] mlxsw: spectrum_acl: Implement TC block sharing Jiri Pirko
2018-01-16 15:33 ` [patch net-next v10 13/13] mlxsw: spectrum_acl: Pass mlxsw_sp_port down to ruleset bind/unbind ops Jiri Pirko
2018-01-16 15:34 ` [patch iproute2 net-next v10 1/4] include: update rtnetlink header according to kernel Jiri Pirko
2018-01-16 15:34 ` [patch iproute2 net-next v10 2/4] tc: introduce tc_qdisc_block_exists helper Jiri Pirko
2018-01-16 15:34 ` [patch iproute2 net-next v10 3/4] tc: introduce support for block-handle for filter operations Jiri Pirko
2018-01-16 15:34 ` [patch iproute2 net-next v10 4/4] tc: implement ingress/egress block index attributes for qdiscs Jiri Pirko
2018-01-16 23:33 ` [patch net-next v10 00/13] net: sched: allow qdiscs to share filter block instances Jamal Hadi Salim
2018-01-16 23:37 ` David Ahern
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=20180116153316.4751-8-jiri@resnulli.us \
--to=jiri@resnulli.us \
--cc=alexander.h.duyck@intel.com \
--cc=andrew@lunn.ch \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=f.fainelli@gmail.com \
--cc=ganeshgr@chelsio.com \
--cc=idosch@mellanox.com \
--cc=jakub.kicinski@netronome.com \
--cc=jhs@mojatatu.com \
--cc=john.fastabend@gmail.com \
--cc=john.hurley@netronome.com \
--cc=leonro@mellanox.com \
--cc=matanb@mellanox.com \
--cc=michael.chan@broadcom.com \
--cc=mlxsw@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=pieter.jansenvanvuuren@netronome.com \
--cc=saeedm@mellanox.com \
--cc=simon.horman@netronome.com \
--cc=vivien.didelot@savoirfairelinux.com \
--cc=xiyou.wangcong@gmail.com \
/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).