Re: [PATCH net v4] net: stmmac: xgmac: fix handling of DPP safety error for DMA channels

[Jon Hunter <jonathanh@nvidia.com>]

On 03/02/2024 05:14, Furong Xu wrote:
> Commit 56e58d6c8a56 ("net: stmmac: Implement Safety Features in
> XGMAC core") checks and reports safety errors, but leaves the
> Data Path Parity Errors for each channel in DMA unhandled at all, lead to
> a storm of interrupt.
> Fix it by checking and clearing the DMA_DPP_Interrupt_Status register.
> 
> Fixes: 56e58d6c8a56 ("net: stmmac: Implement Safety Features in XGMAC core")
> Signed-off-by: Furong Xu <0x1207@gmail.com>
> Reviewed-by: Simon Horman <horms@kernel.org>
> Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
> ---
> Changes in v4:
>   - fix a typo name of DDPP bit, thanks Serge Semin
> 
> Changes in v3:
>   - code style fix, thanks Paolo Abeni
> 
> Changes in v2:
>    - explicit enable Data Path Parity Protection
>    - add new counters to stmmac_safety_stats
>    - add detailed log
> ---
>   drivers/net/ethernet/stmicro/stmmac/common.h  |  1 +
>   .../net/ethernet/stmicro/stmmac/dwxgmac2.h    |  3 +
>   .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 57 ++++++++++++++++++-
>   3 files changed, 60 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
> index 721c1f8e892f..b4f60ab078d6 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/common.h
> +++ b/drivers/net/ethernet/stmicro/stmmac/common.h
> @@ -216,6 +216,7 @@ struct stmmac_safety_stats {
>   	unsigned long mac_errors[32];
>   	unsigned long mtl_errors[32];
>   	unsigned long dma_errors[32];
> +	unsigned long dma_dpp_errors[32];
>   };
>   
>   /* Number of fields in Safety Stats */
> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
> index 207ff1799f2c..5c67a3f89f08 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
> @@ -303,6 +303,8 @@
>   #define XGMAC_RXCEIE			BIT(4)
>   #define XGMAC_TXCEIE			BIT(0)
>   #define XGMAC_MTL_ECC_INT_STATUS	0x000010cc
> +#define XGMAC_MTL_DPP_CONTROL		0x000010e0
> +#define XGMAC_DPP_DISABLE		BIT(0)
>   #define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
>   #define XGMAC_TQS			GENMASK(25, 16)
>   #define XGMAC_TQS_SHIFT			16
> @@ -385,6 +387,7 @@
>   #define XGMAC_DCEIE			BIT(1)
>   #define XGMAC_TCEIE			BIT(0)
>   #define XGMAC_DMA_ECC_INT_STATUS	0x0000306c
> +#define XGMAC_DMA_DPP_INT_STATUS	0x00003074
>   #define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
>   #define XGMAC_SPH			BIT(24)
>   #define XGMAC_PBLx8			BIT(16)
> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
> index eb48211d9b0e..04d7c4dc2e35 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
> @@ -830,6 +830,43 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
>   	{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
>   };
>   
> +static const char * const dpp_rx_err = "Read Rx Descriptor Parity checker Error";
> +static const char * const dpp_tx_err = "Read Tx Descriptor Parity checker Error";
> +static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
> +	{ true, "TDPES0", dpp_tx_err },
> +	{ true, "TDPES1", dpp_tx_err },
> +	{ true, "TDPES2", dpp_tx_err },
> +	{ true, "TDPES3", dpp_tx_err },
> +	{ true, "TDPES4", dpp_tx_err },
> +	{ true, "TDPES5", dpp_tx_err },
> +	{ true, "TDPES6", dpp_tx_err },
> +	{ true, "TDPES7", dpp_tx_err },
> +	{ true, "TDPES8", dpp_tx_err },
> +	{ true, "TDPES9", dpp_tx_err },
> +	{ true, "TDPES10", dpp_tx_err },
> +	{ true, "TDPES11", dpp_tx_err },
> +	{ true, "TDPES12", dpp_tx_err },
> +	{ true, "TDPES13", dpp_tx_err },
> +	{ true, "TDPES14", dpp_tx_err },
> +	{ true, "TDPES15", dpp_tx_err },
> +	{ true, "RDPES0", dpp_rx_err },
> +	{ true, "RDPES1", dpp_rx_err },
> +	{ true, "RDPES2", dpp_rx_err },
> +	{ true, "RDPES3", dpp_rx_err },
> +	{ true, "RDPES4", dpp_rx_err },
> +	{ true, "RDPES5", dpp_rx_err },
> +	{ true, "RDPES6", dpp_rx_err },
> +	{ true, "RDPES7", dpp_rx_err },
> +	{ true, "RDPES8", dpp_rx_err },
> +	{ true, "RDPES9", dpp_rx_err },
> +	{ true, "RDPES10", dpp_rx_err },
> +	{ true, "RDPES11", dpp_rx_err },
> +	{ true, "RDPES12", dpp_rx_err },
> +	{ true, "RDPES13", dpp_rx_err },
> +	{ true, "RDPES14", dpp_rx_err },
> +	{ true, "RDPES15", dpp_rx_err },
> +};
> +
>   static void dwxgmac3_handle_dma_err(struct net_device *ndev,
>   				    void __iomem *ioaddr, bool correctable,
>   				    struct stmmac_safety_stats *stats)
> @@ -841,6 +878,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
>   
>   	dwxgmac3_log_error(ndev, value, correctable, "DMA",
>   			   dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
> +
> +	value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS);
> +	writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS);
> +
> +	dwxgmac3_log_error(ndev, value, false, "DMA_DPP",
> +			   dwxgmac3_dma_dpp_errors,
> +			   STAT_OFF(dma_dpp_errors), stats);
>   }
>   
>   static int
> @@ -881,6 +925,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
>   	value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */
>   	writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL);
>   
> +	/* 5. Enable Data Path Parity Protection */
> +	value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
> +	/* already enabled by default, explicit enable it again */
> +	value &= ~XGMAC_DPP_DISABLE;
> +	writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
> +
>   	return 0;
>   }
>   
> @@ -914,7 +964,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev,
>   		ret |= !corr;
>   	}
>   
> -	err = dma & (XGMAC_DEUIS | XGMAC_DECIS);
> +	/* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in
> +	 * DMA_Safety_Interrupt_Status, so we handle DMA Data Path
> +	 * Parity Errors here
> +	 */
> +	err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS);
>   	corr = dma & XGMAC_DECIS;
>   	if (err) {
>   		dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats);
> @@ -930,6 +984,7 @@ static const struct dwxgmac3_error {
>   	{ dwxgmac3_mac_errors },
>   	{ dwxgmac3_mtl_errors },
>   	{ dwxgmac3_dma_errors },
> +	{ dwxgmac3_dma_dpp_errors },
>   };
>   
>   static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats,


This change is breaking the build on some of our builders that are still using GCC 6.x ...

drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c:836:20: error: initialiser element is not constant
   { true, "TDPES0", dpp_tx_err },
                     ^~~~~~~~~~
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c:836:20: note: (near initialisation for ‘dwxgmac3_dma_dpp_errors[0].detailed_desc’)
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c:837:20: error: initialiser element is not constant
   { true, "TDPES1", dpp_tx_err },
                     ^~~~~~~~~~
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c:837:20: note: (near initialisation for ‘dwxgmac3_dma_dpp_errors[1].detailed_desc’)
...

I know that this is quite old but the minimum supported by the kernel is v5.1 ...

https://www.kernel.org/doc/html/next/process/changes.html

Jon

-- 
nvpublic