From 3e5b72ac2f298423902169db7893fef43365e0a6 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 12 Nov 2018 16:40:17 +0200 Subject: net/mlx5: Issue SW reset on FW assert If a FW assert is considered fatal, indicated by a new bit in the health buffer, reset the FW. After the reset go through the normal recovery flow. Only one PF needs to issue the reset, so an attempt is made to prevent the 2nd function from also issuing the reset. It's not an error if that happens, it just slows recovery. Signed-off-by: Feras Daoud Signed-off-by: Alex Vesker Signed-off-by: Moshe Shemesh Signed-off-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 10 +++++++++- include/linux/mlx5/driver.h | 1 + 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 5e760067ac41..35ed38c2ae6c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -510,6 +510,10 @@ struct mlx5_cmd_layout { u8 status_own; }; +enum mlx5_fatal_assert_bit_offsets { + MLX5_RFR_OFFSET = 31, +}; + struct health_buffer { __be32 assert_var[5]; __be32 rsvd0[3]; @@ -518,12 +522,16 @@ struct health_buffer { __be32 rsvd1[2]; __be32 fw_ver; __be32 hw_id; - __be32 rsvd2; + __be32 rfr; u8 irisc_index; u8 synd; __be16 ext_synd; }; +enum mlx5_initializing_bit_offsets { + MLX5_FW_RESET_SUPPORTED_OFFSET = 30, +}; + enum mlx5_cmd_addr_l_sz_offset { MLX5_NIC_IFC_OFFSET = 8, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index cc7fd8e62844..89205b6cc7ef 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,6 +583,7 @@ struct mlx5_priv { }; enum mlx5_device_state { + MLX5_DEVICE_STATE_UNINITIALIZED, MLX5_DEVICE_STATE_UP, MLX5_DEVICE_STATE_INTERNAL_ERROR, }; -- cgit v1.2.3