Merge tag 'mlx5-next-netdev-deadlock' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Saeed Mahameed says:

====================
mlx5-next-netdev-deadlock

This series from Jiri solves a deadlock when removing a network namespace
with mlx5 devlink instance being in it.
The deadlock is between:
1) mlx5_ib->unregister_netdevice_notifier()
AND
2) mlx5_core->devlink_reload->cleanup_net()

To slove this introduced mlx5 netdev added/removed events to track uplink
netdev to be used for register_netdevice_notifier_dev_net() purposes.

* tag 'mlx5-next-netdev-deadlock' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  RDMA/mlx5: Track netdev to avoid deadlock during netdev notifier unregister
  net/mlx5e: Propagate an internal event in case uplink netdev changes
  net/mlx5e: Fix trap event handling
  net/mlx5: Introduce CQE error syndrome
====================

Link: https://lore.kernel.org/r/20230208005626.72930-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 48 insertions, 5 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 70b3eacf2bbb..71b06ebad402 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -362,6 +362,7 @@ enum mlx5_event {
 
 enum mlx5_driver_event {
 	MLX5_DRIVER_EVENT_TYPE_TRAP = 0,
+	MLX5_DRIVER_EVENT_UPLINK_NETDEV,
 };
 
 enum {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 91e8160ed087..e0b104ea49b1 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -49,6 +49,7 @@
 #include <linux/notifier.h>
 #include <linux/refcount.h>
 #include <linux/auxiliary_bus.h>
+#include <linux/mutex.h>
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
@@ -672,6 +673,7 @@ struct mlx5e_resources {
 	} hw_objs;
 	struct devlink_port dl_port;
 	struct net_device *uplink_netdev;
+	struct mutex uplink_netdev_lock;
 	struct mlx5_crypto_dek_priv *dek_priv;
 };
 
@@ -1010,6 +1012,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size);
 bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
 
+void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev);
+void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev);
+
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7cf6a78fea07..1e530a8a2cf5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1521,7 +1521,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         null_mkey[0x1];
 	u8         log_max_klm_list_size[0x6];
 
-	u8         reserved_at_120[0xa];
+	u8         reserved_at_120[0x2];
+	u8	   qpc_extension[0x1];
+	u8	   reserved_at_123[0x7];
 	u8         log_max_ra_req_dc[0x6];
 	u8         reserved_at_130[0x2];
 	u8         eth_wqe_too_small[0x1];
@@ -1687,7 +1689,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_bf_reg_size[0x5];
 
-	u8         reserved_at_270[0x6];
+	u8         reserved_at_270[0x3];
+	u8	   qp_error_syndrome[0x1];
+	u8	   reserved_at_274[0x2];
 	u8         lag_dct[0x2];
 	u8         lag_tx_port_affinity[0x1];
 	u8         lag_native_fdb_selection[0x1];
@@ -5393,6 +5397,37 @@ struct mlx5_ifc_query_rmp_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_cqe_error_syndrome_bits {
+	u8         hw_error_syndrome[0x8];
+	u8         hw_syndrome_type[0x4];
+	u8         reserved_at_c[0x4];
+	u8         vendor_error_syndrome[0x8];
+	u8         syndrome[0x8];
+};
+
+struct mlx5_ifc_qp_context_extension_bits {
+	u8         reserved_at_0[0x60];
+
+	struct mlx5_ifc_cqe_error_syndrome_bits error_syndrome;
+
+	u8         reserved_at_80[0x580];
+};
+
+struct mlx5_ifc_qpc_extension_and_pas_list_in_bits {
+	struct mlx5_ifc_qp_context_extension_bits qpc_data_extension;
+
+	u8         pas[0][0x40];
+};
+
+struct mlx5_ifc_qp_pas_list_in_bits {
+	struct mlx5_ifc_cmd_pas_bits pas[0];
+};
+
+union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits {
+	struct mlx5_ifc_qp_pas_list_in_bits qp_pas_list;
+	struct mlx5_ifc_qpc_extension_and_pas_list_in_bits qpc_ext_and_pas_list;
+};
+
 struct mlx5_ifc_query_qp_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -5409,7 +5444,7 @@ struct mlx5_ifc_query_qp_out_bits {
 
 	u8         reserved_at_800[0x80];
 
-	u8         pas[][0x40];
+	union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits qp_pas_or_qpc_ext_and_pas;
 };
 
 struct mlx5_ifc_query_qp_in_bits {
@@ -5419,7 +5454,8 @@ struct mlx5_ifc_query_qp_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x8];
+	u8         qpc_ext[0x1];
+	u8         reserved_at_41[0x7];
 	u8         qpn[0x18];
 
 	u8         reserved_at_60[0x20];
@@ -8635,7 +8671,8 @@ struct mlx5_ifc_create_qp_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x8];
+	u8         qpc_ext[0x1];
+	u8         reserved_at_41[0x7];
 	u8         input_qpn[0x18];
 
 	u8         reserved_at_60[0x20];