net: macb: Allocate valid memory for TX and RX BD prefetch

GEM version in ZynqMP and most versions greater than r1p07 supports
TX and RX BD prefetch. The number of BDs that can be prefetched is a
HW configurable parameter. For ZynqMP, this parameter is 4.

When GEM DMA is accessing the last BD in the ring, even before the
BD is processed and the WRAP bit is noticed, it will have prefetched
BDs outside the BD ring. These will not be processed but it is
necessary to have accessible memory after the last BD. Especially
in cases where SMMU is used, memory locations immediately after the
last BD may not have translation tables triggering HRESP errors. Hence
always allocate extra BDs to accommodate for prefetch.
The value of tx/rx bd prefetch for any given SoC version is:
2 ^ (corresponding field in design config 10 register).
(value of this field >= 1)

Added a capability flag so that older IP versions that do not have
DCFG10 or this prefetch capability are not affected.

Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 21 insertions, 6 deletions

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 2d5d0d110151..a6c911bb5ce2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1811,6 +1811,7 @@ static void macb_free_consistent(struct macb *bp)
 {
         struct macb_queue *queue;
         unsigned int q;
+        int size;
 
         bp->macbgem_ops.mog_free_rx_buffers(bp);
 
@@ -1818,12 +1819,14 @@ static void macb_free_consistent(struct macb *bp)
                 kfree(queue->tx_skb);
                 queue->tx_skb = NULL;
                 if (queue->tx_ring) {
-                        dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp),
+                        size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
+                        dma_free_coherent(&bp->pdev->dev, size,
                                           queue->tx_ring, queue->tx_ring_dma);
                         queue->tx_ring = NULL;
                 }
                 if (queue->rx_ring) {
-                        dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp),
+                        size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
+                        dma_free_coherent(&bp->pdev->dev, size,
                                           queue->rx_ring, queue->rx_ring_dma);
                         queue->rx_ring = NULL;
                 }
@@ -1873,7 +1876,7 @@ static int macb_alloc_consistent(struct macb *bp)
         int size;
 
         for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-                size = TX_RING_BYTES(bp);
+                size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
                 queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
                                                     &queue->tx_ring_dma,
                                                     GFP_KERNEL);
@@ -1889,7 +1892,7 @@ static int macb_alloc_consistent(struct macb *bp)
                 if (!queue->tx_skb)
                         goto out_err;
 
-                size = RX_RING_BYTES(bp);
+                size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
                 queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
                                                  &queue->rx_ring_dma, GFP_KERNEL);
                 if (!queue->rx_ring)
@@ -3796,7 +3799,7 @@ static const struct macb_config np4_config = {
 static const struct macb_config zynqmp_config = {
         .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
                         MACB_CAPS_JUMBO |
-                        MACB_CAPS_GEM_HAS_PTP,
+                        MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH,
         .dma_burst_length = 16,
         .clk_init = macb_clk_init,
         .init = macb_init,
@@ -3857,7 +3860,7 @@ static int macb_probe(struct platform_device *pdev)
         void __iomem *mem;
         const char *mac;
         struct macb *bp;
-        int err;
+        int err, val;
 
         regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
         mem = devm_ioremap_resource(&pdev->dev, regs);
@@ -3946,6 +3949,18 @@ static int macb_probe(struct platform_device *pdev)
         else
                 dev->max_mtu = ETH_DATA_LEN;
 
+        if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
+                val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
+                if (val)
+                        bp->rx_bd_rd_prefetch = (2 << (val - 1)) *
+                                                macb_dma_desc_get_size(bp);
+
+                val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10));
+                if (val)
+                        bp->tx_bd_rd_prefetch = (2 << (val - 1)) *
+                                                macb_dma_desc_get_size(bp);
+        }
+
         mac = of_get_mac_address(np);
         if (mac) {
                 ether_addr_copy(bp->dev->dev_addr, mac);