mlx4_core: Reset device when internal error is detected

Reset the device when an internal error is detected.

Also, detect errors by polling the error buffer rather than using
interrupts.  This is more robust and doesn't depend on MSI-X.  Remove
the old interrupt handler entirely, since we don't want to support two
mechanisms for detecting internal errors.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
Jack Morgenstein
2007-07-12 17:50:45 +03:00
committed by Roland Dreier
parent 41179e2de6
commit ee49bd9397
5 changed files with 130 additions and 73 deletions

View File

@@ -39,6 +39,7 @@
#include <linux/mutex.h>
#include <linux/radix-tree.h>
#include <linux/timer.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
@@ -67,7 +68,6 @@ enum {
enum {
MLX4_EQ_ASYNC,
MLX4_EQ_COMP,
MLX4_EQ_CATAS,
MLX4_NUM_EQ
};
@@ -248,7 +248,8 @@ struct mlx4_mcg_table {
struct mlx4_catas_err {
u32 __iomem *map;
int size;
struct timer_list timer;
struct list_head list;
};
struct mlx4_priv {
@@ -311,9 +312,11 @@ void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
void mlx4_map_catas_buf(struct mlx4_dev *dev);
void mlx4_unmap_catas_buf(struct mlx4_dev *dev);
void mlx4_start_catas_poll(struct mlx4_dev *dev);
void mlx4_stop_catas_poll(struct mlx4_dev *dev);
int mlx4_catas_init(void);
void mlx4_catas_cleanup(void);
int mlx4_restart_one(struct pci_dev *pdev);
int mlx4_register_device(struct mlx4_dev *dev);
void mlx4_unregister_device(struct mlx4_dev *dev);
void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_event type,