From: Feras Daoud <fera...@mellanox.com>
Since the FW can be shared between different PFs/VFs it is common
that more than one health poll will detected a failure, this can
lead to multiple resets which are unneeded.
The solution is to use a FW locking mechanism using semaphore space
to provide a way to allow only one device to collect the cr-dump and
to issue a sw-reset.
Signed-off-by: Feras Daoud <fera...@mellanox.com>
Signed-off-by: Saeed Mahameed <sae...@mellanox.com>
Reviewed-by: Alex Vesker <va...@mellanox.com>
Signed-off-by: Saeed Mahameed <sae...@mellanox.com>
---
.../ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 40 ++++++++++++++++---
.../ethernet/mellanox/mlx5/core/lib/pci_vsc.h | 8 ++++
.../ethernet/mellanox/mlx5/core/mlx5_core.h | 4 ++
3 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
index f42890bdd6b1..b6b8fb13f621 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
@@ -24,11 +24,6 @@
pci_write_config_dword((dev)->pdev, (dev)->vsc_addr + (offset), (val))
#define VSC_MAX_RETRIES 2048
-enum mlx5_vsc_state {
- MLX5_VSC_UNLOCK,
- MLX5_VSC_LOCK,
-};
-
enum {
VSC_CTRL_OFFSET = 0x4,
VSC_COUNTER_OFFSET = 0x8,
@@ -281,3 +276,38 @@ int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev,
u32 *data,
}
return length;
}
+
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+ enum mlx5_vsc_state state)
+{
+ u32 data, id = 0;
+ int ret;
+
+ ret = mlx5_vsc_gw_set_space(dev, MLX5_SEMAPHORE_SPACE_DOMAIN, NULL);
+ if (ret) {
+ mlx5_core_warn(dev, "Failed to set gw space %d\n", ret);
+ return ret;
+ }
+
+ if (state == MLX5_VSC_LOCK) {
+ /* Get a unique ID based on the counter */
+ ret = vsc_read(dev, VSC_COUNTER_OFFSET, &id);
+ if (ret)
+ return ret;
+ }
+
+ /* Try to modify lock */
+ ret = mlx5_vsc_gw_write(dev, space, id);
+ if (ret)
+ return ret;
+
+ /* Verify lock was modified */
+ ret = mlx5_vsc_gw_read(dev, space, &data);
+ if (ret)
+ return -EINVAL;
+
+ if (data != id)
+ return -EBUSY;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
index c6ebf59006c5..4264b65f7437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
@@ -4,6 +4,11 @@
#ifndef __MLX5_PCI_VSC_H__
#define __MLX5_PCI_VSC_H__
+enum mlx5_vsc_state {
+ MLX5_VSC_UNLOCK,
+ MLX5_VSC_LOCK,
+};
+
enum {
MLX5_VSC_SPACE_SCAN_CRSPACE = 0x7,
};
@@ -22,4 +27,7 @@ static inline bool mlx5_vsc_accessible(struct mlx5_core_dev
*dev)
return !!dev->vsc_addr;
}
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+ enum mlx5_vsc_state state);
+
#endif /* __MLX5_PCI_VSC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index d31b77ad533d..439cf23945a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -111,6 +111,10 @@ enum {
MLX5_DRIVER_SYND = 0xbadd00de,
};
+enum mlx5_semaphore_space_address {
+ MLX5_SEMAPHORE_SPACE_DOMAIN = 0xA,
+};
+
int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
int mlx5_query_board_id(struct mlx5_core_dev *dev);
int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
--
2.20.1
