Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Vladimir Oltean <vladimir.oltean@nxp.com>
To: netdev@vger.kernel.org, Jakub Kicinski <kuba@kernel.org>,
	"David S. Miller" <davem@davemloft.net>
Cc: Andrew Lunn <andrew@lunn.ch>,
	Florian Fainelli <f.fainelli@gmail.com>,
	Vivien Didelot <vivien.didelot@gmail.com>,
	Jiri Pirko <jiri@resnulli.us>, Ido Schimmel <idosch@idosch.org>,
	Tobias Waldekranz <tobias@waldekranz.com>,
	Roopa Prabhu <roopa@nvidia.com>,
	Nikolay Aleksandrov <nikolay@nvidia.com>,
	Stephen Hemminger <stephen@networkplumber.org>,
	bridge@lists.linux-foundation.org,
	Grygorii Strashko <grygorii.strashko@ti.com>
Subject: [RFC PATCH v3 net-next 08/24] net: bridge: switchdev: recycle unused hwdoms
Date: Mon, 12 Jul 2021 18:21:26 +0300	[thread overview]
Message-ID: <20210712152142.800651-9-vladimir.oltean@nxp.com> (raw)
In-Reply-To: <20210712152142.800651-1-vladimir.oltean@nxp.com>

From: Tobias Waldekranz <tobias@waldekranz.com>

Since hwdoms have only been used thus far for equality comparisons, the
bridge has used the simplest possible assignment policy; using a
counter to keep track of the last value handed out.

With the upcoming transmit offloading, we need to perform set
operations efficiently based on hwdoms, e.g. we want to answer
questions like "has this skb been forwarded to any port within this
hwdom?"

Move to a bitmap-based allocation scheme that recycles hwdoms once all
members leaves the bridge. This means that we can use a single
unsigned long to keep track of the hwdoms that have received an skb.

v1->v2: convert the typedef DECLARE_BITMAP(br_hwdom_map_t, BR_HWDOM_MAX)
        into a plain unsigned long.

Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
 net/bridge/br_if.c        |  4 +-
 net/bridge/br_private.h   | 27 ++++++++---
 net/bridge/br_switchdev.c | 94 ++++++++++++++++++++++++++-------------
 3 files changed, 86 insertions(+), 39 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 73fa703f8df5..adaf78e45c23 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -349,6 +349,7 @@ static void del_nbp(struct net_bridge_port *p)
 	nbp_backup_clear(p);
 
 	nbp_update_port_count(br);
+	nbp_switchdev_del(p);
 
 	netdev_upper_dev_unlink(dev, br->dev);
 
@@ -643,7 +644,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	if (err)
 		goto err5;
 
-	err = nbp_switchdev_hwdom_set(p);
+	err = nbp_switchdev_add(p);
 	if (err)
 		goto err6;
 
@@ -704,6 +705,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	list_del_rcu(&p->list);
 	br_fdb_delete_by_port(br, p, 0, 1);
 	nbp_update_port_count(br);
+	nbp_switchdev_del(p);
 err6:
 	netdev_upper_dev_unlink(dev, br->dev);
 err5:
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 54e29a8576a1..a23c565b8970 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -29,6 +29,8 @@
 
 #define BR_MULTICAST_DEFAULT_HASH_MAX 4096
 
+#define BR_HWDOM_MAX BITS_PER_LONG
+
 #define BR_VERSION	"2.3"
 
 /* Control of forwarding link local multicast */
@@ -483,6 +485,8 @@ struct net_bridge {
 	 * identifiers in case a bridge spans multiple switchdev instances.
 	 */
 	int				last_hwdom;
+	/* Bit mask of hardware domain numbers in use */
+	unsigned long			busy_hwdoms;
 #endif
 	struct hlist_head		fdb_list;
 
@@ -1656,7 +1660,6 @@ static inline void br_sysfs_delbr(struct net_device *dev) { return; }
 
 /* br_switchdev.c */
 #ifdef CONFIG_NET_SWITCHDEV
-int nbp_switchdev_hwdom_set(struct net_bridge_port *p);
 void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
 			      struct sk_buff *skb);
 bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
@@ -1670,17 +1673,15 @@ void br_switchdev_fdb_notify(struct net_bridge *br,
 int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
 			       struct netlink_ext_ack *extack);
 int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid);
+int nbp_switchdev_add(struct net_bridge_port *p);
+void nbp_switchdev_del(struct net_bridge_port *p);
+void br_switchdev_init(struct net_bridge *br);
 
 static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
 {
 	skb->offload_fwd_mark = 0;
 }
 #else
-static inline int nbp_switchdev_hwdom_set(struct net_bridge_port *p)
-{
-	return 0;
-}
-
 static inline void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
 					    struct sk_buff *skb)
 {
@@ -1721,6 +1722,20 @@ br_switchdev_fdb_notify(struct net_bridge *br,
 static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
 {
 }
+
+static inline int nbp_switchdev_add(struct net_bridge_port *p)
+{
+	return 0;
+}
+
+static inline void nbp_switchdev_del(struct net_bridge_port *p)
+{
+}
+
+static inline void br_switchdev_init(struct net_bridge *br)
+{
+}
+
 #endif /* CONFIG_NET_SWITCHDEV */
 
 /* br_arp_nd_proxy.c */
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 833fd30482c2..f3120f13c293 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -8,38 +8,6 @@
 
 #include "br_private.h"
 
-static int br_switchdev_hwdom_get(struct net_bridge *br, struct net_device *dev)
-{
-	struct net_bridge_port *p;
-
-	/* dev is yet to be added to the port list. */
-	list_for_each_entry(p, &br->port_list, list) {
-		if (netdev_port_same_parent_id(dev, p->dev))
-			return p->hwdom;
-	}
-
-	return ++br->last_hwdom;
-}
-
-int nbp_switchdev_hwdom_set(struct net_bridge_port *p)
-{
-	struct netdev_phys_item_id ppid = { };
-	int err;
-
-	ASSERT_RTNL();
-
-	err = dev_get_port_parent_id(p->dev, &ppid, true);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
-	}
-
-	p->hwdom = br_switchdev_hwdom_get(p->br, p->dev);
-
-	return 0;
-}
-
 void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
 			      struct sk_buff *skb)
 {
@@ -156,3 +124,65 @@ int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
 
 	return switchdev_port_obj_del(dev, &v.obj);
 }
+
+static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining)
+{
+	struct net_bridge *br = joining->br;
+	struct net_bridge_port *p;
+	int hwdom;
+
+	/* joining is yet to be added to the port list. */
+	list_for_each_entry(p, &br->port_list, list) {
+		if (netdev_port_same_parent_id(joining->dev, p->dev)) {
+			joining->hwdom = p->hwdom;
+			return 0;
+		}
+	}
+
+	hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1);
+	if (hwdom >= BR_HWDOM_MAX)
+		return -EBUSY;
+
+	set_bit(hwdom, &br->busy_hwdoms);
+	joining->hwdom = hwdom;
+	return 0;
+}
+
+static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving)
+{
+	struct net_bridge *br = leaving->br;
+	struct net_bridge_port *p;
+
+	/* leaving is no longer in the port list. */
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->hwdom == leaving->hwdom)
+			return;
+	}
+
+	clear_bit(leaving->hwdom, &br->busy_hwdoms);
+}
+
+int nbp_switchdev_add(struct net_bridge_port *p)
+{
+	struct netdev_phys_item_id ppid = { };
+	int err;
+
+	ASSERT_RTNL();
+
+	err = dev_get_port_parent_id(p->dev, &ppid, true);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	return nbp_switchdev_hwdom_set(p);
+}
+
+void nbp_switchdev_del(struct net_bridge_port *p)
+{
+	ASSERT_RTNL();
+
+	if (p->hwdom)
+		nbp_switchdev_hwdom_put(p);
+}
-- 
2.25.1


  parent reply	other threads:[~2021-07-12 15:22 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-12 15:21 [RFC PATCH v3 net-next 00/24] Allow forwarding for the software bridge data path to be offloaded to capable devices Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 01/24] net: dpaa2-switch: use extack in dpaa2_switch_port_bridge_join Vladimir Oltean
2021-07-13  2:20   ` Florian Fainelli
2021-07-12 15:21 ` [RFC PATCH v3 net-next 02/24] net: dpaa2-switch: refactor prechangeupper sanity checks Vladimir Oltean
2021-07-13  2:21   ` Florian Fainelli
2021-07-12 15:21 ` [RFC PATCH v3 net-next 03/24] net: mlxsw: " Vladimir Oltean
2021-07-13  2:21   ` Florian Fainelli
2021-07-12 15:21 ` [RFC PATCH v3 net-next 04/24] net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 05/24] net: prestera: if the LAG that we're joining is under a bridge, join it Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 06/24] net: prestera: refactor prechangeupper sanity checks Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 07/24] net: bridge: disambiguate offload_fwd_mark Vladimir Oltean
2021-07-12 15:21 ` Vladimir Oltean [this message]
2021-07-12 15:21 ` [RFC PATCH v3 net-next 09/24] net: bridge: switchdev: let drivers inform which bridge ports are offloaded Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 10/24] net: prestera: guard against multiple switchdev obj replays on same bridge port Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 11/24] net: mlxsw: " Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 12/24] net: bridge: drop context pointer from br_fdb_replay Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 13/24] net: bridge: use the public notifier chain for br_fdb_replay Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 14/24] net: bridge: unexport call_switchdev_blocking_notifiers Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 15/24] net: bridge: propagate ctx to switchdev_port_obj_{add,del} Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 16/24] net: bridge: propagate ctx to br_switchdev_port_vlan_{add,del} Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 17/24] net: bridge: replay mdb entries on the public switchdev notifier chain Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 18/24] net: bridge: replay vlan entries on the public switchdev notifier Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 19/24] net: bridge: switchdev object replay helpers for everybody Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 20/24] net: bridge: switchdev: allow the TX data plane forwarding to be offloaded Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 21/24] net: dsa: track the number of switches in a tree Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 22/24] net: dsa: add support for bridge TX forwarding offload Vladimir Oltean
2021-07-15 14:49   ` Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 23/24] net: dsa: mv88e6xxx: map virtual bridges with forwarding offload in the PVT Vladimir Oltean
2021-07-12 15:21 ` [RFC PATCH v3 net-next 24/24] net: dsa: tag_dsa: offload the bridge forwarding process Vladimir Oltean
2021-07-12 15:40 ` [RFC PATCH v3 net-next 00/24] Allow forwarding for the software bridge data path to be offloaded to capable devices Marek Behun
2021-07-12 17:01   ` Vladimir Oltean
2021-07-12 17:27     ` Marek Behun
2021-07-22  9:50       ` Vladimir Oltean

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=20210712152142.800651-9-vladimir.oltean@nxp.com \
    --to=vladimir.oltean@nxp.com \
    --cc=andrew@lunn.ch \
    --cc=bridge@lists.linux-foundation.org \
    --cc=davem@davemloft.net \
    --cc=f.fainelli@gmail.com \
    --cc=grygorii.strashko@ti.com \
    --cc=idosch@idosch.org \
    --cc=jiri@resnulli.us \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=nikolay@nvidia.com \
    --cc=roopa@nvidia.com \
    --cc=stephen@networkplumber.org \
    --cc=tobias@waldekranz.com \
    --cc=vivien.didelot@gmail.com \
    --subject='Re: [RFC PATCH v3 net-next 08/24] net: bridge: switchdev: recycle unused hwdoms' \
    /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

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).