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.

Budget does not affect the number of Tx completions we can process for
NAPI, so we use the ring size as the limit instead of budget. As we no
longer return the number of descriptors processed to axienet_tx_poll, we
now update tx_bd_ci in axienet_free_tx_chain.

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

Changes in v3:
- Don't limit transmit packets processed to budget, since it doesn't
  apply to Tx completions. This allows a few more simplifications.
- Add a note to the commit message regarding the movement of the
  tx_bd_ci update

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

 .../net/ethernet/xilinx/xilinx_axienet_main.c | 23 +++++++++++--------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 9eb300fc3590..1beb439deaf3 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -674,15 +674,15 @@ static int axienet_device_reset(struct net_device *ndev)
  *
  * 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++) {
 		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
@@ -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))
+		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
 			napi_consume_skb(cur_p->skb, 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);
-- 
2.35.1.1320.gc452695387.dirty