From: Nikolay Aleksandrov <nikolay@nvidia.com>
To: Tobias Waldekranz <tobias@waldekranz.com>,
davem@davemloft.net, kuba@kernel.org
Cc: andrew@lunn.ch, vivien.didelot@gmail.com, f.fainelli@gmail.com,
olteanv@gmail.com, roopa@nvidia.com, jiri@resnulli.us,
idosch@idosch.org, stephen@networkplumber.org,
netdev@vger.kernel.org, bridge@lists.linux-foundation.org
Subject: Re: [RFC net-next 3/9] net: bridge: switchdev: Recycle unused hwdoms
Date: Tue, 27 Apr 2021 13:42:00 +0300 [thread overview]
Message-ID: <26e631b0-f5d0-343e-194d-c15b4a8dc7aa@nvidia.com> (raw)
In-Reply-To: <20210426170411.1789186-4-tobias@waldekranz.com>
On 26/04/2021 20:04, Tobias Waldekranz wrote:
> Since hwdoms has thus far only been used 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.
>
> Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
> ---
> net/bridge/br_if.c | 4 +-
> net/bridge/br_private.h | 29 +++++++++---
> net/bridge/br_switchdev.c | 94 ++++++++++++++++++++++++++-------------
> 3 files changed, 87 insertions(+), 40 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 53248715f631..aba92864d285 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 */
> @@ -54,6 +56,8 @@ typedef struct bridge_id bridge_id;
> typedef struct mac_addr mac_addr;
> typedef __u16 port_id;
>
> +typedef DECLARE_BITMAP(br_hwdom_map_t, BR_HWDOM_MAX);
> +
You can avoid the typedef and DECLARE_BITMAP() and just use an
unsigned long below. In general avoiding new typedefs is a good thing. :)
> struct bridge_id {
> unsigned char prio[2];
> unsigned char addr[ETH_ALEN];
> @@ -472,7 +476,7 @@ struct net_bridge {
> u32 auto_cnt;
>
> #ifdef CONFIG_NET_SWITCHDEV
> - int last_hwdom;
> + br_hwdom_map_t busy_hwdoms;
> #endif
> struct hlist_head fdb_list;
>
> @@ -1593,7 +1597,6 @@ 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,
> @@ -1607,17 +1610,15 @@ void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb,
> 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)
> {
> @@ -1657,6 +1658,20 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
> 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 bc085077ae71..54bd7205bfb5 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);
> +}
>
next prev parent reply other threads:[~2021-04-27 10:42 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-26 17:04 [RFC net-next 0/9] net: bridge: Forward offloading Tobias Waldekranz
2021-04-26 17:04 ` [RFC net-next 1/9] net: dfwd: Constrain existing users to macvlan subordinates Tobias Waldekranz
2021-04-26 17:04 ` [RFC net-next 2/9] net: bridge: Disambiguate offload_fwd_mark Tobias Waldekranz
2021-05-02 15:00 ` Ido Schimmel
2021-05-03 8:49 ` Tobias Waldekranz
2021-05-05 7:39 ` Ido Schimmel
2021-04-26 17:04 ` [RFC net-next 3/9] net: bridge: switchdev: Recycle unused hwdoms Tobias Waldekranz
2021-04-27 10:42 ` Nikolay Aleksandrov [this message]
2021-04-26 17:04 ` [RFC net-next 4/9] net: bridge: switchdev: Forward offloading Tobias Waldekranz
2021-04-27 10:35 ` Nikolay Aleksandrov
2021-04-28 22:47 ` Tobias Waldekranz
2021-04-29 9:16 ` Nikolay Aleksandrov
2021-04-29 14:55 ` Tobias Waldekranz
2021-05-02 15:04 ` Ido Schimmel
2021-05-03 8:53 ` Tobias Waldekranz
2021-05-06 11:01 ` Vladimir Oltean
2021-04-26 17:04 ` [RFC net-next 5/9] net: dsa: Track port PVIDs Tobias Waldekranz
2021-04-26 19:40 ` Vladimir Oltean
2021-04-26 20:05 ` Tobias Waldekranz
2021-04-26 20:28 ` Vladimir Oltean
2021-04-27 9:12 ` Tobias Waldekranz
2021-04-27 9:27 ` Vladimir Oltean
2021-04-27 10:07 ` Vladimir Oltean
2021-04-28 23:10 ` Tobias Waldekranz
2021-04-26 17:04 ` [RFC net-next 6/9] net: dsa: Forward offloading Tobias Waldekranz
2021-04-27 10:17 ` Vladimir Oltean
2021-05-04 14:44 ` Tobias Waldekranz
2021-05-04 15:21 ` Vladimir Oltean
2021-05-04 20:07 ` Tobias Waldekranz
2021-05-04 20:33 ` Andrew Lunn
2021-05-04 21:24 ` Tobias Waldekranz
2021-05-04 20:58 ` Vladimir Oltean
2021-05-04 22:12 ` Tobias Waldekranz
2021-05-04 23:04 ` Vladimir Oltean
2021-05-05 9:01 ` Tobias Waldekranz
2021-05-05 16:12 ` Vladimir Oltean
2021-04-26 17:04 ` [RFC net-next 7/9] net: dsa: mv88e6xxx: Allocate a virtual DSA port for each bridge Tobias Waldekranz
2021-04-26 17:04 ` [RFC net-next 8/9] net: dsa: mv88e6xxx: Map virtual bridge port in PVT Tobias Waldekranz
2021-04-26 17:04 ` [RFC net-next 9/9] net: dsa: mv88e6xxx: Forward offloading Tobias Waldekranz
2021-05-02 14:58 ` [RFC net-next 0/9] net: bridge: " Ido Schimmel
2021-05-03 9:44 ` Tobias Waldekranz
2021-05-06 10:59 ` 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=26e631b0-f5d0-343e-194d-c15b4a8dc7aa@nvidia.com \
--to=nikolay@nvidia.com \
--cc=andrew@lunn.ch \
--cc=bridge@lists.linux-foundation.org \
--cc=davem@davemloft.net \
--cc=f.fainelli@gmail.com \
--cc=idosch@idosch.org \
--cc=jiri@resnulli.us \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=olteanv@gmail.com \
--cc=roopa@nvidia.com \
--cc=stephen@networkplumber.org \
--cc=tobias@waldekranz.com \
--cc=vivien.didelot@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).