All of lore.kernel.org
 help / color / mirror / Atom feed
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
Subject: [patch net-next v3 01/10] net: sched: introduce support for multiple filter chain pointers registration
Date: Wed, 13 Dec 2017 16:10:29 +0100	[thread overview]
Message-ID: <20171213151038.29665-2-jiri@resnulli.us> (raw)
In-Reply-To: <20171213151038.29665-1-jiri@resnulli.us>

From: Jiri Pirko <jiri@mellanox.com>

So far, there was possible only to register a single filter chain
pointer to block->chain[0]. However, when the blocks will get shareable,
we need to allow multiple filter chain pointers registration.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v2->v3:
- rebased on top of the current net-next
---
 include/net/pkt_cls.h     |   3 +
 include/net/sch_generic.h |   5 +-
 net/sched/cls_api.c       | 225 ++++++++++++++++++++++++++++++++++++++++------
 3 files changed, 206 insertions(+), 27 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0105445..c04154f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -29,6 +29,8 @@ struct tcf_block_ext_info {
 	enum tcf_block_binder_type binder_type;
 	tcf_chain_head_change_t *chain_head_change;
 	void *chain_head_change_priv;
+	bool shareable;
+	u32 block_index;
 };
 
 struct tcf_block_cb;
@@ -48,6 +50,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
+	WARN_ON(block->refcnt != 1);
 	return block->q;
 }
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 8f8c0af..9ad1a51 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -269,8 +269,7 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
 
 struct tcf_chain {
 	struct tcf_proto __rcu *filter_chain;
-	tcf_chain_head_change_t *chain_head_change;
-	void *chain_head_change_priv;
+	struct list_head filter_chain_list;
 	struct list_head list;
 	struct tcf_block *block;
 	u32 index; /* chain index */
@@ -279,6 +278,8 @@ struct tcf_chain {
 
 struct tcf_block {
 	struct list_head chain_list;
+	u32 index; /* block index for shared blocks */
+	unsigned int refcnt;
 	struct net *net;
 	struct Qdisc *q;
 	struct list_head cb_list;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5b9b8a6..dce4c3d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -25,6 +25,7 @@
 #include <linux/kmod.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/idr.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -180,6 +181,12 @@ static void tcf_proto_destroy(struct tcf_proto *tp)
 	kfree_rcu(tp, rcu);
 }
 
+struct tcf_filter_chain_list_item {
+	struct list_head list;
+	tcf_chain_head_change_t *chain_head_change;
+	void *chain_head_change_priv;
+};
+
 static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 					  u32 chain_index)
 {
@@ -188,6 +195,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 	if (!chain)
 		return NULL;
+	INIT_LIST_HEAD(&chain->filter_chain_list);
 	list_add_tail(&chain->list, &block->chain_list);
 	chain->block = block;
 	chain->index = chain_index;
@@ -195,12 +203,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	return chain;
 }
 
+static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item,
+				       struct tcf_proto *tp_head)
+{
+	if (item->chain_head_change)
+		item->chain_head_change(tp_head, item->chain_head_change_priv);
+}
 static void tcf_chain_head_change(struct tcf_chain *chain,
 				  struct tcf_proto *tp_head)
 {
-	if (chain->chain_head_change)
-		chain->chain_head_change(tp_head,
-					 chain->chain_head_change_priv);
+	struct tcf_filter_chain_list_item *item;
+
+	list_for_each_entry(item, &chain->filter_chain_list, list)
+		tcf_chain_head_change_item(item, tp_head);
 }
 
 static void tcf_chain_flush(struct tcf_chain *chain)
@@ -281,15 +296,84 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
 }
 
-int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
-		      struct tcf_block_ext_info *ei)
+static int
+tcf_chain_head_change_cb_add(struct tcf_chain *chain,
+			     struct tcf_block_ext_info *ei)
+{
+	struct tcf_filter_chain_list_item *item;
+
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item)
+		return -ENOMEM;
+	item->chain_head_change = ei->chain_head_change;
+	item->chain_head_change_priv = ei->chain_head_change_priv;
+	if (chain->filter_chain)
+		tcf_chain_head_change_item(item, chain->filter_chain);
+	list_add(&item->list, &chain->filter_chain_list);
+	return 0;
+}
+
+static void
+tcf_chain_head_change_cb_del(struct tcf_chain *chain,
+			     struct tcf_block_ext_info *ei)
+{
+	struct tcf_filter_chain_list_item *item;
+
+	list_for_each_entry(item, &chain->filter_chain_list, list) {
+		if ((!ei->chain_head_change && !ei->chain_head_change_priv) ||
+		    (item->chain_head_change == ei->chain_head_change &&
+		     item->chain_head_change_priv == ei->chain_head_change_priv)) {
+			tcf_chain_head_change_item(item, NULL);
+			list_del(&item->list);
+			kfree(item);
+			return;
+		}
+	}
+	WARN_ON(1);
+}
+
+struct tcf_net {
+	struct idr idr;
+};
+
+static unsigned int tcf_net_id;
+
+static int tcf_block_insert(struct tcf_block *block, struct net *net,
+			    u32 block_index)
 {
-	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
+	struct tcf_net *tn = net_generic(net, tcf_net_id);
+	int idr_start;
+	int idr_end;
+	int index;
+
+	if (block_index >= INT_MAX)
+		return -EINVAL;
+	idr_start = block_index ? block_index : 1;
+	idr_end = block_index ? block_index + 1 : INT_MAX;
+
+	index = idr_alloc(&tn->idr, block, idr_start, idr_end, GFP_KERNEL);
+	if (index < 0)
+		return index;
+	block->index = index;
+	return 0;
+}
+
+static void tcf_block_remove(struct tcf_block *block, struct net *net)
+{
+	struct tcf_net *tn = net_generic(net, tcf_net_id);
+
+	idr_remove(&tn->idr, block->index);
+}
+
+static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q)
+{
+	struct tcf_block *block;
 	struct tcf_chain *chain;
 	int err;
 
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&block->chain_list);
 	INIT_LIST_HEAD(&block->cb_list);
 
@@ -299,17 +383,72 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 		err = -ENOMEM;
 		goto err_chain_create;
 	}
-	WARN_ON(!ei->chain_head_change);
-	chain->chain_head_change = ei->chain_head_change;
-	chain->chain_head_change_priv = ei->chain_head_change_priv;
 	block->net = qdisc_net(q);
+	block->refcnt = 1;
+	block->net = net;
 	block->q = q;
+	return block;
+
+err_chain_create:
+	kfree(block);
+	return ERR_PTR(err);
+}
+
+static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
+{
+	struct tcf_net *tn = net_generic(net, tcf_net_id);
+
+	return idr_find(&tn->idr, block_index);
+}
+
+static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
+{
+	return list_first_entry(&block->chain_list, struct tcf_chain, list);
+}
+
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
+{
+	struct net *net = qdisc_net(q);
+	struct tcf_block *block = NULL;
+	bool created = false;
+	int err;
+
+	if (ei->shareable) {
+		block = tcf_block_lookup(net, ei->block_index);
+		if (block)
+			block->refcnt++;
+	}
+
+	if (!block) {
+		block = tcf_block_create(net, q);
+		if (IS_ERR(block))
+			return PTR_ERR(block);
+		created = true;
+		if (ei->shareable) {
+			err = tcf_block_insert(block, net, ei->block_index);
+			if (err)
+				goto err_block_insert;
+		}
+	}
+
+	err = tcf_chain_head_change_cb_add(tcf_block_chain_zero(block), ei);
+	if (err)
+		goto err_chain_head_change_cb_add;
+
 	tcf_block_offload_bind(block, q, ei);
 	*p_block = block;
 	return 0;
 
-err_chain_create:
-	kfree(block);
+err_chain_head_change_cb_add:
+	if (created) {
+		if (ei->shareable)
+			tcf_block_remove(block, net);
+err_block_insert:
+		kfree(block);
+	} else {
+		block->refcnt--;
+	}
 	return err;
 }
 EXPORT_SYMBOL(tcf_block_get_ext);
@@ -342,24 +481,32 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 	struct tcf_chain *chain, *tmp;
 
-	/* Hold a refcnt for all chains, so that they don't disappear
-	 * while we are iterating.
-	 */
-	list_for_each_entry(chain, &block->chain_list, list)
-		tcf_chain_hold(chain);
+	tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei);
 
-	list_for_each_entry(chain, &block->chain_list, list)
-		tcf_chain_flush(chain);
+	if (--block->refcnt == 0) {
+		if (ei->shareable)
+			tcf_block_remove(block, block->net);
+
+		/* Hold a refcnt for all chains, except 0, so that they
+		 * don't disappear while we are iterating.
+		 */
+		list_for_each_entry(chain, &block->chain_list, list)
+			tcf_chain_hold(chain);
+
+		list_for_each_entry(chain, &block->chain_list, list)
+			tcf_chain_flush(chain);
+	}
 
 	tcf_block_offload_unbind(block, q, ei);
 
-	/* At this point, all the chains should have refcnt >= 1. */
-	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
-		tcf_chain_put(chain);
+	if (block->refcnt == 0) {
+		/* At this point, all the chains should have refcnt >= 1. */
+		list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+			tcf_chain_put(chain);
 
-	/* Finally, put chain 0 and allow block to be freed. */
-	chain = list_first_entry(&block->chain_list, struct tcf_chain, list);
-	tcf_chain_put(chain);
+		/* Finally, put chain 0 and allow block to be freed. */
+		tcf_chain_put(tcf_block_chain_zero(block));
+	}
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
 
@@ -1246,12 +1393,40 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
 }
 EXPORT_SYMBOL(tc_setup_cb_call);
 
+static __net_init int tcf_net_init(struct net *net)
+{
+	struct tcf_net *tn = net_generic(net, tcf_net_id);
+
+	idr_init(&tn->idr);
+	return 0;
+}
+
+static void __net_exit tcf_net_exit(struct net *net)
+{
+	struct tcf_net *tn = net_generic(net, tcf_net_id);
+
+	idr_destroy(&tn->idr);
+}
+
+static struct pernet_operations tcf_net_ops = {
+	.init = tcf_net_init,
+	.exit = tcf_net_exit,
+	.id   = &tcf_net_id,
+	.size = sizeof(struct tcf_net),
+};
+
 static int __init tc_filter_init(void)
 {
+	int err;
+
 	tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
 	if (!tc_filter_wq)
 		return -ENOMEM;
 
+	err = register_pernet_subsys(&tcf_net_ops);
+	if (err)
+		return err;
+
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
-- 
2.9.5

  reply	other threads:[~2017-12-13 15:10 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-13 15:10 [patch net-next v3 00/10] net: sched: allow qdiscs to share filter block instances Jiri Pirko
2017-12-13 15:10 ` Jiri Pirko [this message]
2017-12-13 15:10 ` [patch net-next v3 02/10] net: sched: avoid usage of tp->q in tcf_classify Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 03/10] net: sched: introduce block mechanism to handle netif_keep_dst calls Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 04/10] net: sched: remove classid and q fields from tcf_proto Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 05/10] net: sched: keep track of offloaded filters and check tc offload feature Jiri Pirko
2017-12-14  1:05   ` Jakub Kicinski
2017-12-14  9:47     ` Jiri Pirko
2017-12-14 13:10       ` Jiri Pirko
2017-12-14 18:49         ` Jakub Kicinski
2017-12-15  9:09           ` Jiri Pirko
2017-12-14 19:22   ` Jakub Kicinski
2017-12-15  9:09     ` Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 06/10] net: sched: allow ingress and clsact qdiscs to share filter blocks Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 07/10] mlxsw: spectrum_acl: Reshuffle code around mlxsw_sp_acl_ruleset_create/destroy Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 08/10] mlxsw: spectrum_acl: Don't store netdev and ingress for ruleset unbind Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 09/10] mlxsw: spectrum_acl: Implement TC block sharing Jiri Pirko
2017-12-13 15:10 ` [patch net-next v3 10/10] mlxsw: spectrum_acl: Pass mlxsw_sp_port down to ruleset bind/unbind ops Jiri Pirko
2017-12-13 15:13 ` [patch iproute2] tc: implement filter block sharing to ingress and clsact qdiscs Jiri Pirko
2017-12-16 18:12   ` Stephen Hemminger
2017-12-17 16:05     ` Jiri Pirko
2017-12-13 16:54 ` [patch net-next v3 00/10] net: sched: allow qdiscs to share filter block instances David Ahern
2017-12-13 17:07   ` Jiri Pirko
2017-12-13 17:18     ` David Ahern
2017-12-13 17:39       ` Jiri Pirko
2017-12-13 18:28         ` David Ahern
2017-12-13 18:42           ` Jiri Pirko
2017-12-14  0:46             ` Jakub Kicinski
2017-12-15 17:08               ` David Ahern
2017-12-15 17:10                 ` Jiri Pirko

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=20171213151038.29665-2-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=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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.