Merge branch 'mlx4-next'

Or Gerlitz says:

====================
mlx4: Fix and enhance the device reset flow

This series from Yishai Hadas fixes the device reset flow and adds SRIOV support.

Reset flows are required whenever a device experiences errors, is unresponsive,
or is not in a deterministic state. In such cases, the driver is expected to
reset the HW and continue operation. When SRIOV is enabled, these requirements
apply both to PF and VF devices.

Currently, the mlx4 reset flow doesn't work properly: when a fatal error is
detected on the FW internal buffer the chip is not reset and stays in its
bad state. There are cases that assumed to be fatal such as non-responsive FW,
errors via closing commands but are not handled today.

The AER mechanism should also be fixed:
- It should use mlx4_load_one instead of __mlx4_init_one which is done
  upon HCA probing.
- It must be aligned with concurrent catas flow, mark device to be in
  an error state, reset chip, etc.
- Port types should be restored to their original values before error occurred.

In addition, there the SRIOV use-case isn't supported.

In above cases when the device state becomes fatal we must act as follows:
1) Reset the chip and mark the HW device state as in fatal error.
2) Wake up any pending commands, preventing new ones to come in.
3) Restart the software stack.

We also address the SRIOV mode as follows: In case the PF detects a fatal error,
it lets VFs know about that, then both itself and VFs are restarted asynchronously.
However, in case only the VF encountered a fatal case or forced to be reset, they
reset the VF stuff and then restart software.

changes from V0:

No need to call pci_disable_device upon permanent PCI error. This will
be done as part of mlx4_remove_one which is called later once we
return PCI_ERS_RESULT_DISCONNECT from the pci error handler.

Initial toggle value should use only the T bit and not the whole byte value.
Not doing so sometimes broke SRIOV as of junky value seen by the VF as a
non-ready comm channel
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 34 insertions, 3 deletions

diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 64d25941b329..c989442ffc6a 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -279,6 +279,8 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in
 int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
 int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
 			      struct mlx4_config_dev_params *params);
+void mlx4_cmd_wake_completions(struct mlx4_dev *dev);
+void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev);
 /*
  * mlx4_get_slave_default_vlan -
  * return true if VST ( default vlan)
@@ -288,5 +290,6 @@ bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
 				 u16 *vlan, u8 *qos);
 
 #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
+#define COMM_CHAN_EVENT_INTERNAL_ERR (1 << 17)
 
 #endif /* MLX4_CMD_H */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f1e41b33462f..5ef54e145e4d 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -208,6 +208,10 @@ enum {
 	MLX4_QUERY_FUNC_FLAGS_A0_RES_QP		= 1LL << 1
 };
 
+enum {
+	MLX4_VF_CAP_FLAG_RESET			= 1 << 0
+};
+
 /* bit enums for an 8-bit flags field indicating special use
  * QPs which require special handling in qp_reserve_range.
  * Currently, this only includes QPs used by the ETH interface,
@@ -411,6 +415,16 @@ enum {
 	MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK	= 1 << 4,
 };
 
+enum {
+	MLX4_DEVICE_STATE_UP			= 1 << 0,
+	MLX4_DEVICE_STATE_INTERNAL_ERROR	= 1 << 1,
+};
+
+enum {
+	MLX4_INTERFACE_STATE_UP		= 1 << 0,
+	MLX4_INTERFACE_STATE_DELETION	= 1 << 1,
+};
+
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
 			     MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
 
@@ -535,6 +549,7 @@ struct mlx4_caps {
 	u8			alloc_res_qp_mask;
 	u32			dmfs_high_rate_qpn_base;
 	u32			dmfs_high_rate_qpn_range;
+	u32			vf_caps;
 };
 
 struct mlx4_buf_list {
@@ -744,8 +759,23 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
-struct mlx4_dev {
+struct mlx4_dev_persistent {
 	struct pci_dev	       *pdev;
+	struct mlx4_dev	       *dev;
+	int                     nvfs[MLX4_MAX_PORTS + 1];
+	int			num_vfs;
+	enum mlx4_port_type curr_port_type[MLX4_MAX_PORTS + 1];
+	enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1];
+	struct work_struct      catas_work;
+	struct workqueue_struct *catas_wq;
+	struct mutex	device_state_mutex; /* protect HW state */
+	u8		state;
+	struct mutex	interface_state_mutex; /* protect SW state */
+	u8	interface_state;
+};
+
+struct mlx4_dev {
+	struct mlx4_dev_persistent *persist;
 	unsigned long		flags;
 	unsigned long		num_slaves;
 	struct mlx4_caps	caps;
@@ -754,13 +784,11 @@ struct mlx4_dev {
 	struct radix_tree_root	qp_table_tree;
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
-	int			num_vfs;
 	int			numa_node;
 	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 	struct mlx4_vf_dev     *dev_vfs;
-	int                     nvfs[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_eqe {