From babd6134a54d70efe875fa5661a20eaecb63f278 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Sun, 18 Sep 2016 18:20:27 +0300 Subject: [PATCH 1/3] net/mlx5: Fix flow counter bulk command out mailbox allocation The FW command output length should be only the length of struct mlx5_cmd_fc_bulk out field. Failing to do so will cause the memcpy call which is invoked later in the driver to write over wrong memory address and corrupt kernel memory which results in random crashes. This bug was found using the kernel address sanitizer (kasan). Fixes: a351a1b03bf1 ('net/mlx5: Introduce bulk reading of flow counters') Signed-off-by: Roi Dayan Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 9134010e2921..287ade151ec8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -425,11 +425,11 @@ struct mlx5_cmd_fc_bulk * mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u16 id, int num) { struct mlx5_cmd_fc_bulk *b; - int outlen = sizeof(*b) + + int outlen = MLX5_ST_SZ_BYTES(query_flow_counter_out) + MLX5_ST_SZ_BYTES(traffic_counter) * num; - b = kzalloc(outlen, GFP_KERNEL); + b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); if (!b) return NULL; From 4eea37d7b92076fdeac2a21e5f4dbd92d286719d Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 18 Sep 2016 18:20:28 +0300 Subject: [PATCH 2/3] net/mlx5: E-Switch, Fix error flow in the SRIOV e-switch init code When enablement of the SRIOV e-switch in certain mode (switchdev or legacy) fails, we must set the mode to none. Otherwise, we'll run into double free based crashes when further attempting to deal with the e-switch (such as when disabling sriov or unloading the driver). Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8b78f156214e..b247949df135 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1554,6 +1554,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) abort: esw_enable_vport(esw, 0, UC_ADDR_CHANGE); + esw->mode = SRIOV_NONE; return err; } From 6c419ba8e2580ab17c164db6e918e163d3537ec1 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 18 Sep 2016 18:20:29 +0300 Subject: [PATCH 3/3] net/mlx5: E-Switch, Handle mode change failures E-switch mode changes involve creating HW tables, potentially allocating netdevices, etc, and things can fail. Add an attempt to rollback to the existing mode when changing to the new mode fails. Only if rollback fails, getting proper SRIOV functionality requires module unload or sriov disablement/enablement. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- .../mellanox/mlx5/core/eswitch_offloads.c | 20 +++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3dc83a9459a4..7de40e6b0c25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -446,7 +446,7 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn) static int esw_offloads_start(struct mlx5_eswitch *esw) { - int err, num_vfs = esw->dev->priv.sriov.num_vfs; + int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; if (esw->mode != SRIOV_LEGACY) { esw_warn(esw->dev, "Can't set offloads mode, SRIOV legacy not enabled\n"); @@ -455,8 +455,12 @@ static int esw_offloads_start(struct mlx5_eswitch *esw) mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); - if (err) - esw_warn(esw->dev, "Failed set eswitch to offloads, err %d\n", err); + if (err) { + esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err); + err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); + if (err1) + esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err); + } return err; } @@ -508,12 +512,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) static int esw_offloads_stop(struct mlx5_eswitch *esw) { - int err, num_vfs = esw->dev->priv.sriov.num_vfs; + int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); - if (err) - esw_warn(esw->dev, "Failed set eswitch legacy mode. err %d\n", err); + if (err) { + esw_warn(esw->dev, "Failed setting eswitch to legacy, err %d\n", err); + err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); + if (err1) + esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err); + } return err; }