axienet_free_tx_chain returns the number of DMA descriptors it's
handled. However, axienet_tx_poll treats the return as the number of
packets. When scatter-gather SKBs are enabled, a single packet may use
multiple DMA descriptors, which causes incorrect packet counts. Fix this
by explicitly keepting track of the number of packets processed as
separate from the DMA descriptors.

Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
---

Changes in v2:
- Only call napi_consume_skb with non-zero budget when force is false

 .../net/ethernet/xilinx/xilinx_axienet_main.c | 31 +++++++++++--------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 9aeb7b9f3ae4..556033849d55 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -670,21 +670,21 @@ static int axienet_device_reset(struct net_device *ndev)
  * @force:	Whether to clean descriptors even if not complete
  * @sizep:	Pointer to a u32 filled with the total sum of all bytes
  *		in all cleaned-up descriptors. Ignored if NULL.
- * @budget:	NAPI budget (use 0 when not called from NAPI poll)
+ * @budget:	NAPI budget (use INT_MAX when not called from NAPI poll)
  *
  * Would either be called after a successful transmit operation, or after
  * there was an error when setting up the chain.
- * Returns the number of descriptors handled.
+ * Returns the number of packets handled.
  */
 static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 int nr_bds, bool force, u32 *sizep, int budget)
 {
 	struct axidma_bd *cur_p;
 	unsigned int status;
+	int i, packets = 0;
 	dma_addr_t phys;
-	int i;
 
-	for (i = 0; i < nr_bds; i++) {
+	for (i = 0; i < nr_bds && packets < budget; i++) {
 		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
 		status = cur_p->status;
 
@@ -701,8 +701,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
 				 DMA_TO_DEVICE);
 
-		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
-			napi_consume_skb(cur_p->skb, budget);
+		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
+			napi_consume_skb(cur_p->skb, force ? 0 : budget);
+			packets++;
+		}
 
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
@@ -718,7 +720,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
-	return i;
+	if (!force) {
+		lp->tx_bd_ci += i;
+		if (lp->tx_bd_ci >= lp->tx_bd_num)
+			lp->tx_bd_ci %= lp->tx_bd_num;
+	}
+
+	return packets;
 }
 
 /**
@@ -891,13 +899,10 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 	u32 size = 0;
 	int packets;
 
-	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, budget, false, &size, budget);
+	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, lp->tx_bd_num, false,
+					&size, budget);
 
 	if (packets) {
-		lp->tx_bd_ci += packets;
-		if (lp->tx_bd_ci >= lp->tx_bd_num)
-			lp->tx_bd_ci %= lp->tx_bd_num;
-
 		u64_stats_update_begin(&lp->tx_stat_sync);
 		u64_stats_add(&lp->tx_packets, packets);
 		u64_stats_add(&lp->tx_bytes, size);
@@ -1003,7 +1008,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 				netdev_err(ndev, "TX DMA mapping error\n");
 			ndev->stats.tx_dropped++;
 			axienet_free_tx_chain(lp, orig_tail_ptr, ii + 1,
-					      true, NULL, 0);
+					      true, NULL, INT_MAX);
 			return NETDEV_TX_OK;
 		}
 		desc_set_phys_addr(lp, phys, cur_p);
-- 
2.35.1.1320.gc452695387.dirty

On Fri,  6 Sep 2024 12:42:27 -0400 Sean Anderson wrote:
> axienet_free_tx_chain returns the number of DMA descriptors it's
> handled. However, axienet_tx_poll treats the return as the number of
> packets. When scatter-gather SKBs are enabled, a single packet may use
> multiple DMA descriptors, which causes incorrect packet counts. Fix this
> by explicitly keepting track of the number of packets processed as
> separate from the DMA descriptors.
> 
> Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
> Signed-off-by: Sean Anderson <sean.anderson@linux.dev>

> diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
> index 9aeb7b9f3ae4..556033849d55 100644
> --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
> +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
> @@ -670,21 +670,21 @@ static int axienet_device_reset(struct net_device *ndev)
>   * @force:	Whether to clean descriptors even if not complete
>   * @sizep:	Pointer to a u32 filled with the total sum of all bytes
>   *		in all cleaned-up descriptors. Ignored if NULL.
> - * @budget:	NAPI budget (use 0 when not called from NAPI poll)
> + * @budget:	NAPI budget (use INT_MAX when not called from NAPI poll)

use INT_MAX and force=true when ... ?
To make sure the dependency is clear.
But actually...

>   *
>   * Would either be called after a successful transmit operation, or after
>   * there was an error when setting up the chain.
> - * Returns the number of descriptors handled.
> + * Returns the number of packets handled.
>   */
>  static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>  				 int nr_bds, bool force, u32 *sizep, int budget)
>  {
>  	struct axidma_bd *cur_p;
>  	unsigned int status;
> +	int i, packets = 0;
>  	dma_addr_t phys;
> -	int i;
>  
> -	for (i = 0; i < nr_bds; i++) {
> +	for (i = 0; i < nr_bds && packets < budget; i++) {

why are you doing this? To make sure drivers doesn't complete more 
than "budget" Tx skbs? The budget is really for Rx, for Tx you can
use a reasonable fixed value, independent of what budget core
passes in, e.g. 128. See:
https://www.kernel.org/doc/html/next/networking/napi.html#datapath-api

>  		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
>  		status = cur_p->status;
>  
> @@ -701,8 +701,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>  				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
>  				 DMA_TO_DEVICE);
>  
> -		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
> -			napi_consume_skb(cur_p->skb, budget);
> +		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
> +			napi_consume_skb(cur_p->skb, force ? 0 : budget);
> +			packets++;
> +		}
>  
>  		cur_p->app0 = 0;
>  		cur_p->app1 = 0;
> @@ -718,7 +720,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>  			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
>  	}
>  
> -	return i;
> +	if (!force) {
> +		lp->tx_bd_ci += i;
> +		if (lp->tx_bd_ci >= lp->tx_bd_num)
> +			lp->tx_bd_ci %= lp->tx_bd_num;
> +	}

Moving this chunk into axienet_free_tx_chain() is a noop, right?
Please avoid code cleanups in fixes.

> +	return packets;
>  }
>  
>  /**
-- 
pw-bot: cr

On 9/9/24 21:00, Jakub Kicinski wrote:
> On Fri,  6 Sep 2024 12:42:27 -0400 Sean Anderson wrote:
>> axienet_free_tx_chain returns the number of DMA descriptors it's
>> handled. However, axienet_tx_poll treats the return as the number of
>> packets. When scatter-gather SKBs are enabled, a single packet may use
>> multiple DMA descriptors, which causes incorrect packet counts. Fix this
>> by explicitly keepting track of the number of packets processed as
>> separate from the DMA descriptors.
>> 
>> Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
>> Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
> 
>> diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
>> index 9aeb7b9f3ae4..556033849d55 100644
>> --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
>> +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
>> @@ -670,21 +670,21 @@ static int axienet_device_reset(struct net_device *ndev)
>>   * @force:	Whether to clean descriptors even if not complete
>>   * @sizep:	Pointer to a u32 filled with the total sum of all bytes
>>   *		in all cleaned-up descriptors. Ignored if NULL.
>> - * @budget:	NAPI budget (use 0 when not called from NAPI poll)
>> + * @budget:	NAPI budget (use INT_MAX when not called from NAPI poll)
> 
> use INT_MAX and force=true when ... ?
> To make sure the dependency is clear.
> But actually...
> 
>>   *
>>   * Would either be called after a successful transmit operation, or after
>>   * there was an error when setting up the chain.
>> - * Returns the number of descriptors handled.
>> + * Returns the number of packets handled.
>>   */
>>  static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>>  				 int nr_bds, bool force, u32 *sizep, int budget)
>>  {
>>  	struct axidma_bd *cur_p;
>>  	unsigned int status;
>> +	int i, packets = 0;
>>  	dma_addr_t phys;
>> -	int i;
>>  
>> -	for (i = 0; i < nr_bds; i++) {
>> +	for (i = 0; i < nr_bds && packets < budget; i++) {
> 
> why are you doing this? To make sure drivers doesn't complete more 
> than "budget" Tx skbs? The budget is really for Rx, for Tx you can
> use a reasonable fixed value, independent of what budget core
> passes in, e.g. 128. See:
> https://www.kernel.org/doc/html/next/networking/napi.html#datapath-api

I read this but it was unclear to me because it seems oriented towards
"combined" NAPI instances, while we have separate instances for RX and
TX. So even for TX-only instances, we can ignore budget?

>>  		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
>>  		status = cur_p->status;
>>  
>> @@ -701,8 +701,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>>  				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
>>  				 DMA_TO_DEVICE);
>>  
>> -		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
>> -			napi_consume_skb(cur_p->skb, budget);
>> +		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
>> +			napi_consume_skb(cur_p->skb, force ? 0 : budget);
>> +			packets++;
>> +		}
>>  
>>  		cur_p->app0 = 0;
>>  		cur_p->app1 = 0;
>> @@ -718,7 +720,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
>>  			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
>>  	}
>>  
>> -	return i;
>> +	if (!force) {
>> +		lp->tx_bd_ci += i;
>> +		if (lp->tx_bd_ci >= lp->tx_bd_num)
>> +			lp->tx_bd_ci %= lp->tx_bd_num;
>> +	}
> 
> Moving this chunk into axienet_free_tx_chain() is a noop, right?
> Please avoid code cleanups in fixes.

The relevant variable (number of descriptors handled) is no longer
returned to axienet_tx_poll, so it can't update the current descriptor
properly.

--Sean

>> +	return packets;
>>  }
>>  
>>  /**

On Tue, 10 Sep 2024 10:24:36 -0400 Sean Anderson wrote:
> > why are you doing this? To make sure drivers doesn't complete more 
> > than "budget" Tx skbs? The budget is really for Rx, for Tx you can
> > use a reasonable fixed value, independent of what budget core
> > passes in, e.g. 128. See:
> > https://www.kernel.org/doc/html/next/networking/napi.html#datapath-api  
> 
> I read this but it was unclear to me because it seems oriented towards
> "combined" NAPI instances, while we have separate instances for RX and
> TX. So even for TX-only instances, we can ignore budget?

Yes, combined or dedicated it should still reap completions regardless
of budget.

> > Moving this chunk into axienet_free_tx_chain() is a noop, right?
> > Please avoid code cleanups in fixes.  
> 
> The relevant variable (number of descriptors handled) is no longer
> returned to axienet_tx_poll, so it can't update the current descriptor
> properly.

Got it, worth mentioning in the commit msg.