Vladimir Oltean
2021-Feb-09 15:19 UTC
[Bridge] [PATCH v2 net-next 02/11] net: bridge: offload all port flags at once in br_setport
From: Vladimir Oltean <vladimir.oltean at nxp.com>
The br_switchdev_set_port_flag function uses the atomic notifier call
chain because br_setport runs in an atomic section (under br->lock).
This is because port flag changes need to be synchronized with the data
path. But actually the switchdev notifier doesn't need that, only
br_set_port_flag does. So we can collect all the port flag changes and
only emit the notification at the end, then revert the changes if the
switchdev notification failed.
There's also the other aspect: if for example this command:
ip link set swp0 type bridge_slave flood off mcast_flood off learning off
succeeded at configuring BR_FLOOD and BR_MCAST_FLOOD but not at
BR_LEARNING, there would be no attempt to revert the partial state in
any way. Arguably, if the user changes more than one flag through the
same netlink command, this one _should_ be all or nothing, which means
it should be passed through switchdev as all or nothing.
Signed-off-by: Vladimir Oltean <vladimir.oltean at nxp.com>
---
Changes in v2:
Patch is new.
net/bridge/br_netlink.c | 155 +++++++++++++++-----------------------
net/bridge/br_switchdev.c | 7 +-
2 files changed, 66 insertions(+), 96 deletions(-)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index bd3962da345a..2c110bcbc6d0 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -853,103 +853,82 @@ static int br_set_port_state(struct net_bridge_port *p,
u8 state)
}
/* Set/clear or port flags based on attribute */
-static int br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
- int attrtype, unsigned long mask)
+static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
+ int attrtype, unsigned long mask)
{
- unsigned long flags;
- int err;
-
if (!tb[attrtype])
- return 0;
+ return;
if (nla_get_u8(tb[attrtype]))
- flags = p->flags | mask;
+ p->flags |= mask;
else
- flags = p->flags & ~mask;
-
- err = br_switchdev_set_port_flag(p, flags, mask);
- if (err)
- return err;
-
- p->flags = flags;
- return 0;
+ p->flags &= ~mask;
}
/* Process bridge protocol info on port */
static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
{
- unsigned long old_flags = p->flags;
- bool br_vlan_tunnel_old = false;
+ unsigned long old_flags, changed_mask;
+ bool br_vlan_tunnel_old;
int err;
- err = br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE,
BR_MULTICAST_FAST_LEAVE);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST,
BR_MULTICAST_TO_UNICAST);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI);
- if (err)
+ spin_lock_bh(&p->br->lock);
+
+ old_flags = p->flags;
+ br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false;
+
+ br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+ br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
+ br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE,
+ BR_MULTICAST_FAST_LEAVE);
+ br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
+ br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
+ br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
+ br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD);
+ br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST,
+ BR_MULTICAST_TO_UNICAST);
+ br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD);
+ br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
+ br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI);
+ br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL);
+ br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS);
+ br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED);
+
+ changed_mask = old_flags ^ p->flags;
+
+ spin_unlock_bh(&p->br->lock);
+
+ err = br_switchdev_set_port_flag(p, p->flags, changed_mask);
+ if (err) {
+ spin_lock_bh(&p->br->lock);
+ p->flags = old_flags;
+ spin_unlock_bh(&p->br->lock);
return err;
+ }
- br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false;
- err = br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL);
- if (err)
- return err;
+ spin_lock_bh(&p->br->lock);
if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL))
nbp_vlan_tunnel_info_flush(p);
+ br_port_flags_change(p, changed_mask);
+
if (tb[IFLA_BRPORT_COST]) {
err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
if (err)
- return err;
+ goto out;
}
if (tb[IFLA_BRPORT_PRIORITY]) {
err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY]));
if (err)
- return err;
+ goto out;
}
if (tb[IFLA_BRPORT_STATE]) {
err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE]));
if (err)
- return err;
+ goto out;
}
if (tb[IFLA_BRPORT_FLUSH])
@@ -961,7 +940,7 @@ static int br_setport(struct net_bridge_port *p, struct
nlattr *tb[])
err = br_multicast_set_port_router(p, mcast_router);
if (err)
- return err;
+ goto out;
}
if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) {
@@ -970,27 +949,20 @@ static int br_setport(struct net_bridge_port *p, struct
nlattr *tb[])
hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]);
err = br_multicast_eht_set_hosts_limit(p, hlimit);
if (err)
- return err;
+ goto out;
}
#endif
if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) {
u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]);
- if (fwd_mask & BR_GROUPFWD_MACPAUSE)
- return -EINVAL;
+ if (fwd_mask & BR_GROUPFWD_MACPAUSE) {
+ err = -EINVAL;
+ goto out;
+ }
p->group_fwd_mask = fwd_mask;
}
- err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS,
- BR_NEIGH_SUPPRESS);
- if (err)
- return err;
-
- err = br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED);
- if (err)
- return err;
-
if (tb[IFLA_BRPORT_BACKUP_PORT]) {
struct net_device *backup_dev = NULL;
u32 backup_ifindex;
@@ -999,17 +971,21 @@ static int br_setport(struct net_bridge_port *p, struct
nlattr *tb[])
if (backup_ifindex) {
backup_dev = __dev_get_by_index(dev_net(p->dev),
backup_ifindex);
- if (!backup_dev)
- return -ENOENT;
+ if (!backup_dev) {
+ err = -ENOENT;
+ goto out;
+ }
}
err = nbp_backup_change(p, backup_dev);
if (err)
- return err;
+ goto out;
}
- br_port_flags_change(p, old_flags ^ p->flags);
- return 0;
+out:
+ spin_unlock_bh(&p->br->lock);
+
+ return err;
}
/* Change state and parameters on port. */
@@ -1045,9 +1021,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr
*nlh, u16 flags,
if (err)
return err;
- spin_lock_bh(&p->br->lock);
err = br_setport(p, tb);
- spin_unlock_bh(&p->br->lock);
} else {
/* Binary compatibility with old RSTP */
if (nla_len(protinfo) < sizeof(u8))
@@ -1134,17 +1108,10 @@ static int br_port_slave_changelink(struct net_device
*brdev,
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
- struct net_bridge *br = netdev_priv(brdev);
- int ret;
-
if (!data)
return 0;
- spin_lock_bh(&br->lock);
- ret = br_setport(br_port_get_rtnl(dev), data);
- spin_unlock_bh(&br->lock);
-
- return ret;
+ return br_setport(br_port_get_rtnl(dev), data);
}
static int br_port_fill_slave_info(struct sk_buff *skb,
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index a9c23ef83443..c004ade25ac0 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -65,16 +65,19 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
struct switchdev_attr attr = {
.orig_dev = p->dev,
.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS,
- .u.brport_flags = mask,
};
struct switchdev_notifier_port_attr_info info = {
.attr = &attr,
};
int err;
- if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD)
+ flags &= BR_PORT_FLAGS_HW_OFFLOAD;
+ mask &= BR_PORT_FLAGS_HW_OFFLOAD;
+ if (!mask)
return 0;
+ attr.u.brport_flags = mask;
+
/* We run from atomic context here */
err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev,
&info.info, NULL);
--
2.25.1
Vladimir Oltean
2021-Feb-09 18:27 UTC
[Bridge] [PATCH v2 net-next 02/11] net: bridge: offload all port flags at once in br_setport
On Tue, Feb 09, 2021 at 05:19:27PM +0200, Vladimir Oltean wrote:> From: Vladimir Oltean <vladimir.oltean at nxp.com> > > The br_switchdev_set_port_flag function uses the atomic notifier call > chain because br_setport runs in an atomic section (under br->lock). > This is because port flag changes need to be synchronized with the data > path. But actually the switchdev notifier doesn't need that, only > br_set_port_flag does. So we can collect all the port flag changes and > only emit the notification at the end, then revert the changes if the > switchdev notification failed. > > There's also the other aspect: if for example this command: > > ip link set swp0 type bridge_slave flood off mcast_flood off learning off > > succeeded at configuring BR_FLOOD and BR_MCAST_FLOOD but not at > BR_LEARNING, there would be no attempt to revert the partial state in > any way. Arguably, if the user changes more than one flag through the > same netlink command, this one _should_ be all or nothing, which means > it should be passed through switchdev as all or nothing. > > Signed-off-by: Vladimir Oltean <vladimir.oltean at nxp.com> > ---(...)> + spin_lock_bh(&p->br->lock); > + > + old_flags = p->flags; > + br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; > + > + br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); > + br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); > + br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, > + BR_MULTICAST_FAST_LEAVE); > + br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); > + br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); > + br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); > + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); > + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, > + BR_MULTICAST_TO_UNICAST); > + br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); > + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); > + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); > + br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); > + br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); > + br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); > + > + changed_mask = old_flags ^ p->flags; > + > + spin_unlock_bh(&p->br->lock); > + > + err = br_switchdev_set_port_flag(p, p->flags, changed_mask); > + if (err) { > + spin_lock_bh(&p->br->lock); > + p->flags = old_flags; > + spin_unlock_bh(&p->br->lock); > return err; > + } >I know it's a bit strange to insert this in the middle of review, but bear with me. While I was reworking the patch series to also make sysfs non-atomic, like this: -----------------------------[cut here]----------------------------->From 6ff6714b6686e4f9406425edf15db6c92e944954 Mon Sep 17 00:00:00 2001From: Vladimir Oltean <vladimir.oltean at nxp.com> Date: Tue, 9 Feb 2021 19:43:40 +0200 Subject: [PATCH] net: bridge: temporarily drop br->lock for br_switchdev_set_port_flag in sysfs Since we would like br_switchdev_set_port_flag to not use an atomic notifier, it should be called from outside spinlock context. Dropping the lock creates some concurrency complications: - There might be an "echo 1 > multicast_flood" simultaneous with an "echo 0 > multicast_flood". The result of this is nondeterministic either way, so I'm not too concerned as long as the result is consistent (no other flags have changed). - There might be an "echo 1 > multicast_flood" simultaneous with an "echo 0 > learning". My expectation is that none of the two writes are "eaten", and the final flags contain BR_MCAST_FLOOD=1 and BR_LEARNING=0 regardless of the order of execution. That is actually possible if, on the commit path, we don't do a trivial "p->flags = flags" which might overwrite bits outside of our mask, but instead we just change the flags corresponding to our mask. Signed-off-by: Vladimir Oltean <vladimir.oltean at nxp.com> --- net/bridge/br_sysfs_if.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 62540b31e356..b419d9aad548 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -68,17 +68,23 @@ static int store_flag(struct net_bridge_port *p, unsigned long v, else flags &= ~mask; - if (flags != p->flags) { - err = br_switchdev_set_port_flag(p, flags, mask, &extack); - if (err) { - if (extack._msg) - netdev_err(p->dev, "%s\n", extack._msg); - return err; - } + if (flags == p->flags) + return 0; - p->flags = flags; - br_port_flags_change(p, mask); + spin_unlock_bh(&p->br->lock); + err = br_switchdev_set_port_flag(p, flags, mask, &extack); + spin_lock_bh(&p->br->lock); + if (err) { + if (extack._msg) + netdev_err(p->dev, "%s\n", extack._msg); + return err; } + + p->flags &= ~mask; + p->flags |= (flags & mask); + + br_port_flags_change(p, mask); + return 0; } -----------------------------[cut here]----------------------------- I figured there's a similar problem in this patch, which I had missed. The code now looks like this: changed_mask = old_flags ^ p->flags; flags = p->flags; spin_unlock_bh(&p->br->lock); err = br_switchdev_set_port_flag(p, flags, changed_mask, extack); if (err) { spin_lock_bh(&p->br->lock); p->flags &= ~changed_mask; p->flags |= (old_flags & changed_mask); spin_unlock_bh(&p->br->lock); return err; } spin_lock_bh(&p->br->lock); where I no longer access p->flags directly when calling br_switchdev_set_port_flag (because I'm not protected by br->lock) but a copy of it saved on stack. Also, I restore just the mask portion of p->flags. But there's an interesting side effect of allowing br_switchdev_set_port_flag to run concurrently (notifier call chains use a rw_semaphore and only take the read side). Basically now drivers that cache the brport flags in their entirety are broken, because there isn't any guarantee that bits outside the mask are valid any longer (we can even enforce that by masking the flags with the mask when notifying them). They would need to do the same trick of updating just the masked part of their cached flags. Except for the fact that they would need some sort of spinlock too, I don't think that the basic bitwise operations are atomic or anything like that. I'm a bit reluctant to add a spinlock in prestera, rocker, mlxsw just for this purpose. What do you think?