[PATCH net] net: stmmac: Clear DMA errors for multi-channel interrupts

[PATCH net] net: stmmac: Clear DMA errors for multi-channel interrupts

[Maxime Chevallier]

The Multi-MSI interrupt handler doesn't clear the DMA error interrupts,
and this leads to interrupt storms when one of these interrupts starts
firing :

 - The RBU (rx buff unav) which triggers under high traffic load

   This triggers easily with iperf3 and small udp packets, and shows
   when running the netpoll kselftest

 - The RPS (rx process stop) which triggers when we stop the DMA RX.

   This one shows when restarting the RX logic without doing a down/up
   cycle, like when attaching an XDP program. The XSK kselftests
   triggers it.

Let's make sure we clear these interrupts for multi-MSI cases. It's
already properly done for the single-chan interrupt, and for that
introduce an "ERR" DMA dir, as we don't want to touch the RI/TI bits
when handling these interrupts.

To avoid duplication, the DMA TX error handling is factored out in a
dedicated helper (in the same commit to ease backporting).

Both of the above storms have been found on dwmac-motorcomm (YT8601),
and are triggered by the xdp.py, xsk_reconfig.py, xdp_features.py,
ring_reconfig.py and netpoll_basic kernel selftests.

This seems to only affect dwmac4, there's no multi-msi mode on
dwmac1000, and on dwxgmac these interrupts are masked as of today.

Fixes: 6ccf12ae111e ("net: stmmac: use interrupt mode INTM=1 for multi-MSI")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  1 +
 .../net/ethernet/stmicro/stmmac/dwmac4_dma.h  |  5 ++
 .../net/ethernet/stmicro/stmmac/dwmac4_lib.c  |  2 +
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 46 +++++++++++++------
 4 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index c74bc7c9750e..a972bee66504 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -382,6 +382,7 @@ enum dma_irq_dir {
 	DMA_DIR_RX = 0x1,
 	DMA_DIR_TX = 0x2,
 	DMA_DIR_RXTX = 0x3,
+	DMA_DIR_ERR = 0x4,
 };
 
 enum request_irq_err {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 43b036d4e95b..a7caac3c98e6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -173,6 +173,11 @@ static inline u32 dma_chanx_base_addr(const struct dwmac4_addrs *addrs,
 					 DMA_CHAN_STATUS_TI | \
 					 DMA_CHAN_STATUS_MSK_COMMON)
 
+#define DMA_CHAN_STATUS_MSK_ERR		(DMA_CHAN_STATUS_AIS | \
+					 DMA_CHAN_STATUS_FBE | \
+					 DMA_CHAN_STATUS_RPS | \
+					 DMA_CHAN_STATUS_RBU)
+
 int dwmac4_dma_reset(void __iomem *ioaddr);
 void dwmac4_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
 			   u32 chan, bool rx, bool tx);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index a0249715fafa..02aa1a3dd1e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -150,6 +150,8 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 		intr_status &= DMA_CHAN_STATUS_MSK_RX;
 	else if (dir == DMA_DIR_TX)
 		intr_status &= DMA_CHAN_STATUS_MSK_TX;
+	else if (dir == DMA_DIR_ERR)
+		intr_status &= DMA_CHAN_STATUS_MSK_ERR;
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9ded31150fbe..2068b57df8d5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3141,6 +3141,16 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan, u32 dir)
 	return status;
 }
 
+static void stmmac_dma_tx_error(struct stmmac_priv *priv, u32 chan, int status)
+{
+	if (unlikely(status & tx_hard_error_bump_tc)) {
+		/* Try to bump up the dma threshold on this failure */
+		stmmac_bump_dma_threshold(priv, chan);
+	} else if (unlikely(status == tx_hard_error)) {
+		stmmac_tx_err(priv, chan);
+	}
+}
+
 /**
  * stmmac_dma_interrupt - DMA ISR
  * @priv: driver private structure
@@ -3165,13 +3175,24 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 		status[chan] = stmmac_napi_check(priv, chan,
 						 DMA_DIR_RXTX);
 
-	for (chan = 0; chan < tx_channel_count; chan++) {
-		if (unlikely(status[chan] & tx_hard_error_bump_tc)) {
-			/* Try to bump up the dma threshold on this failure */
-			stmmac_bump_dma_threshold(priv, chan);
-		} else if (unlikely(status[chan] == tx_hard_error)) {
-			stmmac_tx_err(priv, chan);
-		}
+	for (chan = 0; chan < tx_channel_count; chan++)
+		stmmac_dma_tx_error(priv, chan, status[chan]);
+}
+
+static void stmmac_dma_err_interrupt(struct stmmac_priv *priv)
+{
+	u8 tx_channel_count = priv->plat->tx_queues_to_use;
+	u8 channels_to_check = max(priv->plat->rx_queues_to_use,
+				   tx_channel_count);
+	int status;
+	u8 chan;
+
+	for (chan = 0; chan < channels_to_check; chan++) {
+		status = stmmac_dma_interrupt_status(priv, priv->ioaddr,
+						     &priv->xstats, chan,
+						     DMA_DIR_ERR);
+		if (chan < tx_channel_count)
+			stmmac_dma_tx_error(priv, chan, status);
 	}
 }
 
@@ -6466,6 +6487,9 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id)
 	/* To handle Common interrupts */
 	stmmac_common_interrupt(priv);
 
+	if (priv->plat->core_type == DWMAC_CORE_GMAC4)
+		stmmac_dma_err_interrupt(priv);
+
 	return IRQ_HANDLED;
 }
 
@@ -6500,13 +6524,7 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
 		return IRQ_HANDLED;
 
 	status = stmmac_napi_check(priv, chan, DMA_DIR_TX);
-
-	if (unlikely(status & tx_hard_error_bump_tc)) {
-		/* Try to bump up the dma threshold on this failure */
-		stmmac_bump_dma_threshold(priv, chan);
-	} else if (unlikely(status == tx_hard_error)) {
-		stmmac_tx_err(priv, chan);
-	}
+	stmmac_dma_tx_error(priv, chan, status);
 
 	return IRQ_HANDLED;
 }
-- 
2.56.0

Re: [PATCH net] net: stmmac: Clear DMA errors for multi-channel interrupts

[Lorenzo Bianconi]

[-- Attachment #1: Type: text/plain, Size: 6572 bytes --]

> The Multi-MSI interrupt handler doesn't clear the DMA error interrupts,
> and this leads to interrupt storms when one of these interrupts starts
> firing :
> 
>  - The RBU (rx buff unav) which triggers under high traffic load
> 
>    This triggers easily with iperf3 and small udp packets, and shows
>    when running the netpoll kselftest
> 
>  - The RPS (rx process stop) which triggers when we stop the DMA RX.
> 
>    This one shows when restarting the RX logic without doing a down/up
>    cycle, like when attaching an XDP program. The XSK kselftests
>    triggers it.
> 
> Let's make sure we clear these interrupts for multi-MSI cases. It's
> already properly done for the single-chan interrupt, and for that
> introduce an "ERR" DMA dir, as we don't want to touch the RI/TI bits
> when handling these interrupts.
> 
> To avoid duplication, the DMA TX error handling is factored out in a
> dedicated helper (in the same commit to ease backporting).
> 
> Both of the above storms have been found on dwmac-motorcomm (YT8601),
> and are triggered by the xdp.py, xsk_reconfig.py, xdp_features.py,
> ring_reconfig.py and netpoll_basic kernel selftests.
> 
> This seems to only affect dwmac4, there's no multi-msi mode on
> dwmac1000, and on dwxgmac these interrupts are masked as of today.
> 
> Fixes: 6ccf12ae111e ("net: stmmac: use interrupt mode INTM=1 for multi-MSI")
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>

Reviewed-by: Lorenzo Bianconi <lorenzo.bianconi@oss.qualcomm.com>

> ---
>  drivers/net/ethernet/stmicro/stmmac/common.h  |  1 +
>  .../net/ethernet/stmicro/stmmac/dwmac4_dma.h  |  5 ++
>  .../net/ethernet/stmicro/stmmac/dwmac4_lib.c  |  2 +
>  .../net/ethernet/stmicro/stmmac/stmmac_main.c | 46 +++++++++++++------
>  4 files changed, 40 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
> index c74bc7c9750e..a972bee66504 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/common.h
> +++ b/drivers/net/ethernet/stmicro/stmmac/common.h
> @@ -382,6 +382,7 @@ enum dma_irq_dir {
>  	DMA_DIR_RX = 0x1,
>  	DMA_DIR_TX = 0x2,
>  	DMA_DIR_RXTX = 0x3,
> +	DMA_DIR_ERR = 0x4,
>  };
>  
>  enum request_irq_err {
> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
> index 43b036d4e95b..a7caac3c98e6 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
> @@ -173,6 +173,11 @@ static inline u32 dma_chanx_base_addr(const struct dwmac4_addrs *addrs,
>  					 DMA_CHAN_STATUS_TI | \
>  					 DMA_CHAN_STATUS_MSK_COMMON)
>  
> +#define DMA_CHAN_STATUS_MSK_ERR		(DMA_CHAN_STATUS_AIS | \
> +					 DMA_CHAN_STATUS_FBE | \
> +					 DMA_CHAN_STATUS_RPS | \
> +					 DMA_CHAN_STATUS_RBU)
> +
>  int dwmac4_dma_reset(void __iomem *ioaddr);
>  void dwmac4_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
>  			   u32 chan, bool rx, bool tx);
> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
> index a0249715fafa..02aa1a3dd1e2 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
> @@ -150,6 +150,8 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
>  		intr_status &= DMA_CHAN_STATUS_MSK_RX;
>  	else if (dir == DMA_DIR_TX)
>  		intr_status &= DMA_CHAN_STATUS_MSK_TX;
> +	else if (dir == DMA_DIR_ERR)
> +		intr_status &= DMA_CHAN_STATUS_MSK_ERR;
>  
>  	/* ABNORMAL interrupts */
>  	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index 9ded31150fbe..2068b57df8d5 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -3141,6 +3141,16 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan, u32 dir)
>  	return status;
>  }
>  
> +static void stmmac_dma_tx_error(struct stmmac_priv *priv, u32 chan, int status)
> +{
> +	if (unlikely(status & tx_hard_error_bump_tc)) {
> +		/* Try to bump up the dma threshold on this failure */
> +		stmmac_bump_dma_threshold(priv, chan);
> +	} else if (unlikely(status == tx_hard_error)) {
> +		stmmac_tx_err(priv, chan);
> +	}
> +}
> +
>  /**
>   * stmmac_dma_interrupt - DMA ISR
>   * @priv: driver private structure
> @@ -3165,13 +3175,24 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv)
>  		status[chan] = stmmac_napi_check(priv, chan,
>  						 DMA_DIR_RXTX);
>  
> -	for (chan = 0; chan < tx_channel_count; chan++) {
> -		if (unlikely(status[chan] & tx_hard_error_bump_tc)) {
> -			/* Try to bump up the dma threshold on this failure */
> -			stmmac_bump_dma_threshold(priv, chan);
> -		} else if (unlikely(status[chan] == tx_hard_error)) {
> -			stmmac_tx_err(priv, chan);
> -		}
> +	for (chan = 0; chan < tx_channel_count; chan++)
> +		stmmac_dma_tx_error(priv, chan, status[chan]);
> +}
> +
> +static void stmmac_dma_err_interrupt(struct stmmac_priv *priv)
> +{
> +	u8 tx_channel_count = priv->plat->tx_queues_to_use;
> +	u8 channels_to_check = max(priv->plat->rx_queues_to_use,
> +				   tx_channel_count);
> +	int status;
> +	u8 chan;
> +
> +	for (chan = 0; chan < channels_to_check; chan++) {
> +		status = stmmac_dma_interrupt_status(priv, priv->ioaddr,
> +						     &priv->xstats, chan,
> +						     DMA_DIR_ERR);
> +		if (chan < tx_channel_count)
> +			stmmac_dma_tx_error(priv, chan, status);
>  	}
>  }
>  
> @@ -6466,6 +6487,9 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id)
>  	/* To handle Common interrupts */
>  	stmmac_common_interrupt(priv);
>  
> +	if (priv->plat->core_type == DWMAC_CORE_GMAC4)
> +		stmmac_dma_err_interrupt(priv);
> +
>  	return IRQ_HANDLED;
>  }
>  
> @@ -6500,13 +6524,7 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
>  		return IRQ_HANDLED;
>  
>  	status = stmmac_napi_check(priv, chan, DMA_DIR_TX);
> -
> -	if (unlikely(status & tx_hard_error_bump_tc)) {
> -		/* Try to bump up the dma threshold on this failure */
> -		stmmac_bump_dma_threshold(priv, chan);
> -	} else if (unlikely(status == tx_hard_error)) {
> -		stmmac_tx_err(priv, chan);
> -	}
> +	stmmac_dma_tx_error(priv, chan, status);
>  
>  	return IRQ_HANDLED;
>  }
> -- 
> 2.56.0
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

Re: [PATCH net] net: stmmac: Clear DMA errors for multi-channel interrupts

[Nicolai Buchwitz]

On Fri, 2026-10-30 at 11:22 +0100, Maxime Chevallier wrote:
> The Multi-MSI interrupt handler doesn't clear the DMA error
> interrupts,
> and this leads to interrupt storms when one of these interrupts
> starts
> firing :
> 
>  - The RBU (rx buff unav) which triggers under high traffic load
> 
>    This triggers easily with iperf3 and small udp packets, and shows
>    when running the netpoll kselftest
> 
>  - The RPS (rx process stop) which triggers when we stop the DMA RX.
> 
>    This one shows when restarting the RX logic without doing a
> down/up
>    cycle, like when attaching an XDP program. The XSK kselftests
>    triggers it.
> 
> Let's make sure we clear these interrupts for multi-MSI cases. It's
> already properly done for the single-chan interrupt, and for that
> introduce an "ERR" DMA dir, as we don't want to touch the RI/TI bits
> when handling these interrupts.
> 
> To avoid duplication, the DMA TX error handling is factored out in a
> dedicated helper (in the same commit to ease backporting).
> 
> Both of the above storms have been found on dwmac-motorcomm (YT8601),
> and are triggered by the xdp.py, xsk_reconfig.py, xdp_features.py,
> ring_reconfig.py and netpoll_basic kernel selftests.
> 
> This seems to only affect dwmac4, there's no multi-msi mode on
> dwmac1000, and on dwxgmac these interrupts are masked as of today.
> 
> Fixes: 6ccf12ae111e ("net: stmmac: use interrupt mode INTM=1 for
> multi-MSI")
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
> ---

> [..,]

Reviewed-by: Nicolai Buchwitz <nb@tipi-net.de>

thanks,
Nicolai

-- 
Nicolai Buchwitz <nb@tipi-net.de>