From: Jianbo Liu <jianbol@nvidia.com>
Previously, a unique tunnel id was added for the matching on TC
non-zero chains, to support inner header rewrite with goto action.
Later, it was used to support VF tunnel offload for vxlan, then for
Geneve and GRE. To support VF tunnel, a temporary mlx5_flow_spec is
used to parse tunnel options. For Geneve, if there is TLV option, a
object is created, or refcnt is added if already exists. But the
temporary mlx5_flow_spec is directly freed after parsing, which causes
the leak because no information regarding the object is saved in
flow's mlx5_flow_spec, which is used to free the object when deleting
the flow.
To fix the leak, call mlx5_geneve_tlv_option_del() before free the
temporary spec if it has TLV object.
Fixes: 521933cdc4aa ("net/mlx5e: Support Geneve and GRE with VF tunnel offload")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f1d908f61134..b9c1d7f8f05c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2028,9 +2028,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
return err;
}
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
{
- struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
void *headers_v = MLX5_ADDR_OF(fte_match_param,
spec->match_value,
misc_parameters_3);
@@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
}
complete_all(&flow->del_hw_done);
- if (mlx5_flow_has_geneve_opt(flow))
+ if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
mlx5_geneve_tlv_option_del(priv->mdev->geneve);
if (flow->decap_route)
@@ -2580,6 +2579,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
return err;
}
err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+ if (mlx5_flow_has_geneve_opt(tmp_spec))
+ mlx5_geneve_tlv_option_del(priv->mdev->geneve);
kvfree(tmp_spec);
if (err)
return err;
--
2.31.1On Thu, May 22, 2025 at 09:28:06AM +0300, Tariq Toukan wrote:
> From: Jianbo Liu <jianbol@nvidia.com>
>
> Previously, a unique tunnel id was added for the matching on TC
> non-zero chains, to support inner header rewrite with goto action.
> Later, it was used to support VF tunnel offload for vxlan, then for
> Geneve and GRE. To support VF tunnel, a temporary mlx5_flow_spec is
> used to parse tunnel options. For Geneve, if there is TLV option, a
> object is created, or refcnt is added if already exists. But the
> temporary mlx5_flow_spec is directly freed after parsing, which causes
> the leak because no information regarding the object is saved in
> flow's mlx5_flow_spec, which is used to free the object when deleting
> the flow.
>
> To fix the leak, call mlx5_geneve_tlv_option_del() before free the
> temporary spec if it has TLV object.
>
> Fixes: 521933cdc4aa ("net/mlx5e: Support Geneve and GRE with VF tunnel offload")
> Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
> Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
> Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 7 ++++---
> 1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> index f1d908f61134..b9c1d7f8f05c 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> @@ -2028,9 +2028,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
> return err;
> }
>
> -static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
> +static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
> {
> - struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
> void *headers_v = MLX5_ADDR_OF(fte_match_param,
> spec->match_value,
> misc_parameters_3);
> @@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
> }
> complete_all(&flow->del_hw_done);
>
> - if (mlx5_flow_has_geneve_opt(flow))
> + if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
> mlx5_geneve_tlv_option_del(priv->mdev->geneve);
>
> if (flow->decap_route)
Hi,
The lines leading up to the hung below are:
err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
if (err) {
kvfree(tmp_spec);
NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
I am wondering if the same resource leak described in the patch description
can occur if mlx5e_tc_tun_parse() fails after it successfully calls
tunnel->parse_tunnel().
> @@ -2580,6 +2579,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
> return err;
> }
> err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
> + if (mlx5_flow_has_geneve_opt(tmp_spec))
> + mlx5_geneve_tlv_option_del(priv->mdev->geneve);
> kvfree(tmp_spec);
> if (err)
> return err;
> --
> 2.31.1
>
>
On 5/23/2025 3:16 AM, Simon Horman wrote:
> On Thu, May 22, 2025 at 09:28:06AM +0300, Tariq Toukan wrote:
>> From: Jianbo Liu <jianbol@nvidia.com>
>>
>> Previously, a unique tunnel id was added for the matching on TC
>> non-zero chains, to support inner header rewrite with goto action.
>> Later, it was used to support VF tunnel offload for vxlan, then for
>> Geneve and GRE. To support VF tunnel, a temporary mlx5_flow_spec is
>> used to parse tunnel options. For Geneve, if there is TLV option, a
>> object is created, or refcnt is added if already exists. But the
>> temporary mlx5_flow_spec is directly freed after parsing, which causes
>> the leak because no information regarding the object is saved in
>> flow's mlx5_flow_spec, which is used to free the object when deleting
>> the flow.
>>
>> To fix the leak, call mlx5_geneve_tlv_option_del() before free the
>> temporary spec if it has TLV object.
>>
>> Fixes: 521933cdc4aa ("net/mlx5e: Support Geneve and GRE with VF tunnel offload")
>> Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
>> Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
>> Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
>> ---
>> drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 7 ++++---
>> 1 file changed, 4 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
>> index f1d908f61134..b9c1d7f8f05c 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
>> @@ -2028,9 +2028,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
>> return err;
>> }
>>
>> -static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
>> +static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
>> {
>> - struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
>> void *headers_v = MLX5_ADDR_OF(fte_match_param,
>> spec->match_value,
>> misc_parameters_3);
>> @@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
>> }
>> complete_all(&flow->del_hw_done);
>>
>> - if (mlx5_flow_has_geneve_opt(flow))
>> + if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
>> mlx5_geneve_tlv_option_del(priv->mdev->geneve);
>>
>> if (flow->decap_route)
>
> Hi,
>
> The lines leading up to the hung below are:
>
> err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
> if (err) {
> kvfree(tmp_spec);
> NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
> netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
>
> I am wondering if the same resource leak described in the patch description
> can occur if mlx5e_tc_tun_parse() fails after it successfully calls
> tunnel->parse_tunnel().
>
Yes, I missed that. I will fix in next version.
Thanks!
Jianbo
>> @@ -2580,6 +2579,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
>> return err;
>> }
>> err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
>> + if (mlx5_flow_has_geneve_opt(tmp_spec))
>> + mlx5_geneve_tlv_option_del(priv->mdev->geneve);
>> kvfree(tmp_spec);
>> if (err)
>> return err;
>> --
>> 2.31.1
>>
>>
On Fri, May 23, 2025 at 09:58:57AM +0800, Jianbo Liu wrote:
>
>
> On 5/23/2025 3:16 AM, Simon Horman wrote:
> > On Thu, May 22, 2025 at 09:28:06AM +0300, Tariq Toukan wrote:
> > > From: Jianbo Liu <jianbol@nvidia.com>
> > >
> > > Previously, a unique tunnel id was added for the matching on TC
> > > non-zero chains, to support inner header rewrite with goto action.
> > > Later, it was used to support VF tunnel offload for vxlan, then for
> > > Geneve and GRE. To support VF tunnel, a temporary mlx5_flow_spec is
> > > used to parse tunnel options. For Geneve, if there is TLV option, a
> > > object is created, or refcnt is added if already exists. But the
> > > temporary mlx5_flow_spec is directly freed after parsing, which causes
> > > the leak because no information regarding the object is saved in
> > > flow's mlx5_flow_spec, which is used to free the object when deleting
> > > the flow.
> > >
> > > To fix the leak, call mlx5_geneve_tlv_option_del() before free the
> > > temporary spec if it has TLV object.
> > >
> > > Fixes: 521933cdc4aa ("net/mlx5e: Support Geneve and GRE with VF tunnel offload")
> > > Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
> > > Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
> > > Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
> > > ---
> > > drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 7 ++++---
> > > 1 file changed, 4 insertions(+), 3 deletions(-)
> > >
> > > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> > > index f1d908f61134..b9c1d7f8f05c 100644
> > > --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> > > +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
> > > @@ -2028,9 +2028,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
> > > return err;
> > > }
> > > -static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
> > > +static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
> > > {
> > > - struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
> > > void *headers_v = MLX5_ADDR_OF(fte_match_param,
> > > spec->match_value,
> > > misc_parameters_3);
> > > @@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
> > > }
> > > complete_all(&flow->del_hw_done);
> > > - if (mlx5_flow_has_geneve_opt(flow))
> > > + if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
> > > mlx5_geneve_tlv_option_del(priv->mdev->geneve);
> > > if (flow->decap_route)
> >
> > Hi,
> >
> > The lines leading up to the hung below are:
> >
> > err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
> > if (err) {
> > kvfree(tmp_spec);
> > NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
> > netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
> >
> > I am wondering if the same resource leak described in the patch description
> > can occur if mlx5e_tc_tun_parse() fails after it successfully calls
> > tunnel->parse_tunnel().
> >
>
> Yes, I missed that. I will fix in next version.
Thanks, much appreciated.
© 2016 - 2025 Red Hat, Inc.