From fb738b99ef229bd3d25f1b3e5503925dba9b1a7c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 17 Nov 2020 19:33:51 +0200 Subject: [PATCH 1/2] mlxsw: Fix firmware flashing The commit cited below moved firmware flashing functionality from mlxsw_spectrum to mlxsw_core, but did not adjust the Kconfig dependencies. This makes it possible to have mlxsw_core as built-in and mlxfw as a module. The mlxfw code is therefore not reachable from mlxsw_core and firmware flashing fails: # devlink dev flash pci/0000:01:00.0 file mellanox/mlxsw_spectrum-13.2008.1310.mfa2 devlink answers: Operation not supported Fix by having mlxsw_core select mlxfw. Fixes: b79cb787ac70 ("mlxsw: Move fw flashing code into core.c") Signed-off-by: Ido Schimmel Reported-by: Vadim Pasternak Tested-by: Vadim Pasternak Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 872e9910bb7c..a619d90559f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -6,6 +6,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" select NET_DEVLINK + select MLXFW help This driver supports Mellanox Technologies Switch ASICs family. @@ -82,7 +83,6 @@ config MLXSW_SPECTRUM select GENERIC_ALLOCATOR select PARMAN select OBJAGG - select MLXFW imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m From 1f492eab67bced119a0ac7db75ef2047e29a30c6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 17 Nov 2020 19:33:52 +0200 Subject: [PATCH 2/2] mlxsw: core: Use variable timeout for EMAD retries The driver sends Ethernet Management Datagram (EMAD) packets to the device for configuration purposes and waits for up to 200ms for a reply. A request is retried up to 5 times. When the system is under heavy load, replies are not always processed in time and EMAD transactions fail. Make the process more robust to such delays by using exponential backoff. First wait for up to 200ms, then retransmit and wait for up to 400ms and so on. Fixes: caf7297e7ab5 ("mlxsw: core: Introduce support for asynchronous EMAD register access") Reported-by: Denis Yulevich Tested-by: Denis Yulevich Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937b8e46f8c7..1a86535c4968 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -571,7 +571,8 @@ static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) if (trans->core->fw_flash_in_progress) timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); - queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, + timeout << trans->retries); } static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,