net/mlx5: Cleanup IRQs in case of unload failure

When mlx5_stop_eqs fails to destroy any of the eqs it returns with an error.
In such failure flow the function will return without
releasing all EQs irqs and then pci_free_irq_vectors will fail.
Fix by only warn on destroy EQ failure and continue to release other
EQs and their irqs.

It fixes the following kernel trace:
kernel: kernel BUG at drivers/pci/msi.c:352!
...
...
kernel: Call Trace:
kernel: pci_disable_msix+0xd3/0x100
kernel: pci_free_irq_vectors+0xe/0x20
kernel: mlx5_load_one.isra.17+0x9f5/0xec0 [mlx5_core]

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 0308a2b4823cb847258202ebc42a1dcc75775f48..ab4d1465b7e41e563a44a52ff155e1ca911767c9 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -775,7 +775,7 @@ err1:
        return err;
 }
 
-int mlx5_stop_eqs(struct mlx5_core_dev *dev)
+void mlx5_stop_eqs(struct mlx5_core_dev *dev)
 {
        struct mlx5_eq_table *table = &dev->priv.eq_table;
        int err;
@@ -784,22 +784,28 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev)
        if (MLX5_CAP_GEN(dev, pg)) {
                err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
                if (err)
-                       return err;
+                       mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
+                                     err);
        }
 #endif
 
        err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
        if (err)
-               return err;
+               mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
+                             err);
 
-       mlx5_destroy_unmap_eq(dev, &table->async_eq);
+       err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+       if (err)
+               mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
+                             err);
        mlx5_cmd_use_polling(dev);
 
        err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
-       if (err)
+       if (err) {
+               mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
+                             err);
                mlx5_cmd_use_events(dev);
-
-       return err;
+       }
 }
 
 int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 40a6f33c4cde939310a8ecdf3af7886618109915..57b109c6e422784dd0498c46f9a1a6e96f3ef0ca 100644 (file)
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1049,7 +1049,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
                       enum mlx5_eq_type type);
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
-int mlx5_stop_eqs(struct mlx5_core_dev *dev);
+void mlx5_stop_eqs(struct mlx5_core_dev *dev);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
                    unsigned int *irqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);