summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorVladimir Oltean <vladimir.oltean@nxp.com>2021-09-14 16:47:26 +0300
committerJakub Kicinski <kuba@kernel.org>2021-09-16 01:09:46 +0300
commita57d8c217aadac75530b8e7ffb3a3e1b7bfd0330 (patch)
tree939447e3f1734c7111123dfcb619ddb3fd389454 /net
parent301de697d869be6564aebeb5ab811c84c0a7abed (diff)
downloadlinux-a57d8c217aadac75530b8e7ffb3a3e1b7bfd0330.tar.xz
net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports
Sometimes when unbinding the mv88e6xxx driver on Turris MOX, these error messages appear: mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 0 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 100 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 0 from fdb: -2 (and similarly for other ports) What happens is that DSA has a policy "even if there are bugs, let's at least not leak memory" and dsa_port_teardown() clears the dp->fdbs and dp->mdbs lists, which are supposed to be empty. But deleting that cleanup code, the warnings go away. => the FDB and MDB lists (used for refcounting on shared ports, aka CPU and DSA ports) will eventually be empty, but are not empty by the time we tear down those ports. Aka we are deleting them too soon. The addresses that DSA complains about are host-trapped addresses: the local addresses of the ports, and the MAC address of the bridge device. The problem is that offloading those entries happens from a deferred work item scheduled by the SWITCHDEV_FDB_DEL_TO_DEVICE handler, and this races with the teardown of the CPU and DSA ports where the refcounting is kept. In fact, not only it races, but fundamentally speaking, if we iterate through the port list linearly, we might end up tearing down the shared ports even before we delete a DSA user port which has a bridge upper. So as it turns out, we need to first tear down the user ports (and the unused ones, for no better place of doing that), then the shared ports (the CPU and DSA ports). In between, we need to ensure that all work items scheduled by our switchdev handlers (which only run for user ports, hence the reason why we tear them down first) have finished. Fixes: 161ca59d39e9 ("net: dsa: reference count the MDB entries at the cross-chip notifier level") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20210914134726.2305133-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/dsa/dsa.c5
-rw-r--r--net/dsa/dsa2.c46
-rw-r--r--net/dsa/dsa_priv.h1
3 files changed, 37 insertions, 15 deletions
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1dc45e40f961..41f36ad8b0ec 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work)
return queue_work(dsa_owq, work);
}
+void dsa_flush_workqueue(void)
+{
+ flush_workqueue(dsa_owq);
+}
+
int dsa_devlink_param_get(struct devlink *dl, u32 id,
struct devlink_param_gset_ctx *ctx)
{
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 1b2b25d7bd02..eef13cd20f19 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -897,6 +897,33 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
ds->setup = false;
}
+/* First tear down the non-shared, then the shared ports. This ensures that
+ * all work items scheduled by our switchdev handlers for user ports have
+ * completed before we destroy the refcounting kept on the shared ports.
+ */
+static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst)
+{
+ struct dsa_port *dp;
+
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_user(dp) || dsa_port_is_unused(dp))
+ dsa_port_teardown(dp);
+
+ dsa_flush_workqueue();
+
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp))
+ dsa_port_teardown(dp);
+}
+
+static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
+{
+ struct dsa_port *dp;
+
+ list_for_each_entry(dp, &dst->ports, list)
+ dsa_switch_teardown(dp->ds);
+}
+
static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
{
struct dsa_port *dp;
@@ -923,26 +950,13 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
return 0;
teardown:
- list_for_each_entry(dp, &dst->ports, list)
- dsa_port_teardown(dp);
+ dsa_tree_teardown_ports(dst);
- list_for_each_entry(dp, &dst->ports, list)
- dsa_switch_teardown(dp->ds);
+ dsa_tree_teardown_switches(dst);
return err;
}
-static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst)
-{
- struct dsa_port *dp;
-
- list_for_each_entry(dp, &dst->ports, list)
- dsa_port_teardown(dp);
-
- list_for_each_entry(dp, &dst->ports, list)
- dsa_switch_teardown(dp->ds);
-}
-
static int dsa_tree_setup_master(struct dsa_switch_tree *dst)
{
struct dsa_port *dp;
@@ -1052,6 +1066,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
dsa_tree_teardown_master(dst);
+ dsa_tree_teardown_ports(dst);
+
dsa_tree_teardown_switches(dst);
dsa_tree_teardown_cpu_ports(dst);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 33ab7d7af9eb..a5c9bc7b66c6 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -170,6 +170,7 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops);
const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf);
bool dsa_schedule_work(struct work_struct *work);
+void dsa_flush_workqueue(void);
const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops)