From: Vlad Buslov <vladbu@mellanox.com>
Date: Sun, 3 Jun 2018 20:31:47 +0300
Subject: net/mlx5e: Extend encap entry with reference counter
Patch-mainline: v5.4-rc1
Git-commit: 948993f2beebbdc1c9d926cfdad9827cf6bb67c0
References: jsc#SLE-8464
List of flows attached to encap entry is used as implicit reference
counter (encap entry is deallocated when list becomes free) and as a
mechanism to obtain encap entry that flow is attached to (through list
head). This is not safe when concurrent modification of list of flows
attached to encap entry is possible. Proper atomic reference counter is
required to support concurrent access.
As a preparation for extending encap with reference counting, extract code
that lookups and deletes encap entry into standalone put/get helpers. In
order to remove this dependency on external locking, extend encap entry
with reference counter to manage its lifetime and extend flow structure
with direct pointer to encap entry that flow is attached to.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 +
drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 1
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 84 +++++++++++++++--------
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2
4 files changed, 64 insertions(+), 28 deletions(-)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -613,12 +613,17 @@ static void mlx5e_rep_neigh_update(struc
neigh_connected = (nud_state & NUD_VALID) && !dead;
list_for_each_entry(e, &nhe->encap_list, encap_list) {
+ if (!mlx5e_encap_take(e))
+ continue;
+
encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
priv = netdev_priv(e->out_dev);
if (encap_connected != neigh_connected ||
!ether_addr_equal(e->h_dest, ha))
mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
+
+ mlx5e_encap_put(priv, e);
}
mlx5e_rep_neigh_entry_release(nhe);
rtnl_unlock();
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -164,6 +164,7 @@ struct mlx5e_encap_entry {
u8 flags;
char *encap_header;
int encap_size;
+ refcount_t refcnt;
};
struct mlx5e_rep_sq {
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -103,6 +103,7 @@ enum {
* container_of(helper item, containing struct type, helper field[index])
*/
struct encap_flow_item {
+ struct mlx5e_encap_entry *e; /* attached encap instance */
struct list_head list;
int index;
};
@@ -1433,8 +1434,11 @@ void mlx5e_tc_update_neigh_used_value(st
list_for_each_entry(e, &nhe->encap_list, encap_list) {
struct encap_flow_item *efi, *tmp;
- if (!(e->flags & MLX5_ENCAP_ENTRY_VALID))
+
+ if (!(e->flags & MLX5_ENCAP_ENTRY_VALID) ||
+ !mlx5e_encap_take(e))
continue;
+
list_for_each_entry_safe(efi, tmp, &e->flows, list) {
flow = container_of(efi, struct mlx5e_tc_flow,
encaps[efi->index]);
@@ -1453,6 +1457,8 @@ void mlx5e_tc_update_neigh_used_value(st
mlx5e_flow_put(netdev_priv(e->out_dev), flow);
}
+
+ mlx5e_encap_put(netdev_priv(e->out_dev), e);
if (neigh_used)
break;
}
@@ -1472,29 +1478,33 @@ void mlx5e_tc_update_neigh_used_value(st
}
}
+void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
+{
+ if (!refcount_dec_and_test(&e->refcnt))
+ return;
+
+ WARN_ON(!list_empty(&e->flows));
+ mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+
+ if (e->flags & MLX5_ENCAP_ENTRY_VALID)
+ mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+
+ hash_del_rcu(&e->encap_hlist);
+ kfree(e->encap_header);
+ kfree(e);
+}
+
static void mlx5e_detach_encap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow, int out_index)
{
- struct list_head *next = flow->encaps[out_index].list.next;
-
/* flow wasn't fully initialized */
- if (list_empty(&flow->encaps[out_index].list))
+ if (!flow->encaps[out_index].e)
return;
list_del(&flow->encaps[out_index].list);
- if (list_empty(next)) {
- struct mlx5e_encap_entry *e;
-
- e = list_entry(next, struct mlx5e_encap_entry, flows);
- mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-
- if (e->flags & MLX5_ENCAP_ENTRY_VALID)
- mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
- hash_del_rcu(&e->encap_hlist);
- kfree(e->encap_header);
- kfree(e);
- }
+ mlx5e_encap_put(priv, flow->encaps[out_index].e);
+ flow->encaps[out_index].e = NULL;
}
static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
@@ -2826,6 +2836,31 @@ static bool is_merged_eswitch_dev(struct
+bool mlx5e_encap_take(struct mlx5e_encap_entry *e)
+{
+ return refcount_inc_not_zero(&e->refcnt);
+}
+
+static struct mlx5e_encap_entry *
+mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
+ uintptr_t hash_key)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5e_encap_entry *e;
+ struct encap_key e_key;
+
+ hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
+ encap_hlist, hash_key) {
+ e_key.ip_tun_key = &e->tun_info->key;
+ e_key.tc_tunnel = e->tunnel;
+ if (!cmp_encap_info(&e_key, key) &&
+ mlx5e_encap_take(e))
+ return e;
+ }
+
+ return NULL;
+}
+
static int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct net_device *mirred_dev,
@@ -2838,11 +2873,10 @@ static int mlx5e_attach_encap(struct mlx
struct mlx5_esw_flow_attr *attr = flow->esw_attr;
struct mlx5e_tc_flow_parse_attr *parse_attr;
const struct ip_tunnel_info *tun_info;
- struct encap_key key, e_key;
+ struct encap_key key;
struct mlx5e_encap_entry *e;
unsigned short family;
uintptr_t hash_key;
- bool found = false;
int err = 0;
parse_attr = attr->parse_attr;
@@ -2857,24 +2891,17 @@ static int mlx5e_attach_encap(struct mlx
hash_key = hash_encap_info(&key);
- hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
- encap_hlist, hash_key) {
- e_key.ip_tun_key = &e->tun_info->key;
- e_key.tc_tunnel = e->tunnel;
- if (!cmp_encap_info(&e_key, &key)) {
- found = true;
- break;
- }
- }
+ e = mlx5e_encap_get(priv, &key, hash_key);
/* must verify if encap is valid or not */
- if (found)
+ if (e)
goto attach_flow;
e = kzalloc(sizeof(*e), GFP_KERNEL);
if (!e)
return -ENOMEM;
+ refcount_set(&e->refcnt, 1);
e->tun_info = tun_info;
err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
if (err)
@@ -2893,6 +2920,7 @@ static int mlx5e_attach_encap(struct mlx
hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
attach_flow:
+ flow->encaps[out_index].e = e;
list_add(&flow->encaps[out_index].list, &e->flows);
flow->encaps[out_index].index = out_index;
*encap_dev = e->out_dev;
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -75,6 +75,8 @@ void mlx5e_tc_encap_flows_add(struct mlx
struct mlx5e_encap_entry *e);
void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
struct mlx5e_encap_entry *e);
+bool mlx5e_encap_take(struct mlx5e_encap_entry *e);
+void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e);
struct mlx5e_neigh_hash_entry;
void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);