diff mbox series

[RFC,net-next,4/8] net: dsa: introduce locking for the address lists on CPU and DSA ports

Message ID 20210824114049.3814660-5-vladimir.oltean@nxp.com (mailing list archive)
State RFC
Delegated to: Netdev Maintainers
Headers show
Series Drop rtnl_lock from DSA .port_fdb_{add,del} | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 5 maintainers not CCed: davem@davemloft.net linux-mediatek@lists.infradead.org kuba@kernel.org linux-arm-kernel@lists.infradead.org matthias.bgg@gmail.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 8 this patch: 8
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 190 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 8 this patch: 8
netdev/header_inline success Link

Commit Message

Vladimir Oltean Aug. 24, 2021, 11:40 a.m. UTC
Now that the rtnl_mutex is going away for dsa_port_{host_,}fdb_{add,del},
no one is serializing access to the address lists that DSA keeps for the
purpose of reference counting on shared ports (CPU and cascade ports).

It can happen for one dsa_switch_do_fdb_del to do list_del on a dp->fdbs
element while another dsa_switch_do_fdb_{add,del} is traversing dp->fdbs.
We need to avoid that.

Currently dp->mdbs is not at risk, because dsa_switch_do_mdb_{add,del}
still runs under the rtnl_mutex. But it would be nice if it would not
depend on that being the case. So let's introduce a mutex per port (the
address lists are per port too) and share it between dp->mdbs and
dp->fdbs.

The place where we put the locking is interesting. It could be tempting
to put a DSA-level lock which still serializes calls to
.port_fdb_{add,del}, but it would still not avoid concurrency with other
driver code paths that are currently under rtnl_mutex (.port_fdb_dump,
.port_fast_age). So it would add a very false sense of security (and
adding a global switch-wide lock in DSA to resynchronize with the
rtnl_lock is also counterproductive and hard).

So the locking is intentionally done only where the dp->fdbs and dp->mdbs
lists are traversed. That means, from a driver perspective, that
.port_fdb_add will be called with the dp->addr_lists_lock mutex held on
the CPU port, but not held on user ports. This is done so that driver
writers are not encouraged to rely on any guarantee offered by
dp->addr_lists_lock.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
 include/net/dsa.h |  1 +
 net/dsa/dsa2.c    |  1 +
 net/dsa/switch.c  | 76 ++++++++++++++++++++++++++++++++---------------
 3 files changed, 54 insertions(+), 24 deletions(-)
diff mbox series

Patch

diff --git a/include/net/dsa.h b/include/net/dsa.h
index f9a17145255a..bed1fbc0215c 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -285,6 +285,7 @@  struct dsa_port {
 	/* List of MAC addresses that must be forwarded on this port.
 	 * These are only valid on CPU ports and DSA links.
 	 */
+	struct mutex		addr_lists_lock;
 	struct list_head	fdbs;
 	struct list_head	mdbs;
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 1b2b25d7bd02..8ddf10e27d85 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -435,6 +435,7 @@  static int dsa_port_setup(struct dsa_port *dp)
 	if (dp->setup)
 		return 0;
 
+	mutex_init(&dp->addr_lists_lock);
 	INIT_LIST_HEAD(&dp->fdbs);
 	INIT_LIST_HEAD(&dp->mdbs);
 
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 1c797ec8e2c2..40e28eedac59 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -214,26 +214,30 @@  static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_mdb_add(ds, port, mdb);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
 	if (a) {
 		refcount_inc(&a->refcount);
-		return 0;
+		goto out;
 	}
 
 	a = kzalloc(sizeof(*a), GFP_KERNEL);
-	if (!a)
-		return -ENOMEM;
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = ds->ops->port_mdb_add(ds, port, mdb);
 	if (err) {
 		kfree(a);
-		return err;
+		goto out;
 	}
 
 	ether_addr_copy(a->addr, mdb->addr);
@@ -241,7 +245,10 @@  static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port,
 	refcount_set(&a->refcount, 1);
 	list_add_tail(&a->list, &dp->mdbs);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port,
@@ -249,29 +256,36 @@  static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_mdb_del(ds, port, mdb);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
-	if (!a)
-		return -ENOENT;
+	if (!a) {
+		err = -ENOENT;
+		goto out;
+	}
 
 	if (!refcount_dec_and_test(&a->refcount))
-		return 0;
+		goto out;
 
 	err = ds->ops->port_mdb_del(ds, port, mdb);
 	if (err) {
 		refcount_inc(&a->refcount);
-		return err;
+		goto out;
 	}
 
 	list_del(&a->list);
 	kfree(a);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
@@ -279,26 +293,30 @@  static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_fdb_add(ds, port, addr, vid);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
 	if (a) {
 		refcount_inc(&a->refcount);
-		return 0;
+		goto out;
 	}
 
 	a = kzalloc(sizeof(*a), GFP_KERNEL);
-	if (!a)
-		return -ENOMEM;
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = ds->ops->port_fdb_add(ds, port, addr, vid);
 	if (err) {
 		kfree(a);
-		return err;
+		goto out;
 	}
 
 	ether_addr_copy(a->addr, addr);
@@ -306,7 +324,10 @@  static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
 	refcount_set(&a->refcount, 1);
 	list_add_tail(&a->list, &dp->fdbs);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port,
@@ -314,29 +335,36 @@  static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_fdb_del(ds, port, addr, vid);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
-	if (!a)
-		return -ENOENT;
+	if (!a) {
+		err = -ENOENT;
+		goto out;
+	}
 
 	if (!refcount_dec_and_test(&a->refcount))
-		return 0;
+		goto out;
 
 	err = ds->ops->port_fdb_del(ds, port, addr, vid);
 	if (err) {
 		refcount_inc(&a->refcount);
-		return err;
+		goto out;
 	}
 
 	list_del(&a->list);
 	kfree(a);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_host_fdb_add(struct dsa_switch *ds,