vmxnet3: add support for large passthrough BAR register

For vmxnet3 to work in UPT mode, the BAR sizes have been increased.
The PT page has been extended to 2 pages and also includes OOB pages
as a part of PT BAR. This patch enhances vmxnet3 to use appropriate
BAR offsets based on the capability registered. To use new offsets,
VMXNET3_CAP_LARGE_BAR needs to be set by the device. If it is not set
then the device will use legacy PT page layout.

Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 38 insertions, 10 deletions

diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 0157155ff677..8d626611ab2d 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -57,8 +57,18 @@ enum {
 	VMXNET3_REG_RXPROD2	= 0xA00	 /* Rx Producer Index for ring 2 */
 };
 
-#define VMXNET3_PT_REG_SIZE     4096	/* BAR 0 */
-#define VMXNET3_VD_REG_SIZE     4096	/* BAR 1 */
+/* For Large PT BAR, the following offset to DB register */
+enum {
+	VMXNET3_REG_LB_TXPROD   = 0x1000, /* Tx Producer Index */
+	VMXNET3_REG_LB_RXPROD   = 0x1400, /* Rx Producer Index for ring 1 */
+	VMXNET3_REG_LB_RXPROD2  = 0x1800, /* Rx Producer Index for ring 2 */
+};
+
+#define VMXNET3_PT_REG_SIZE         4096		/* BAR 0 */
+#define VMXNET3_LARGE_PT_REG_SIZE   8192		/* large PT pages */
+#define VMXNET3_VD_REG_SIZE         4096		/* BAR 1 */
+#define VMXNET3_LARGE_BAR0_REG_SIZE (4096 * 4096)	/* LARGE BAR 0 */
+#define VMXNET3_OOB_REG_SIZE        (4094 * 4096)	/* OOB pages */
 
 #define VMXNET3_REG_ALIGN       8	/* All registers are 8-byte aligned. */
 #define VMXNET3_REG_ALIGN_MASK  0x7
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index edc4f23d4965..93f237db463d 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1207,7 +1207,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) {
 		tq->shared->txNumDeferred = 0;
 		VMXNET3_WRITE_BAR0_REG(adapter,
-				       VMXNET3_REG_TXPROD + tq->qid * 8,
+				       adapter->tx_prod_offset + tq->qid * 8,
 				       tq->tx_ring.next2fill);
 	}
 
@@ -1359,8 +1359,8 @@ static int
 vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		       struct vmxnet3_adapter *adapter, int quota)
 {
-	static const u32 rxprod_reg[2] = {
-		VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2
+	u32 rxprod_reg[2] = {
+		adapter->rx_prod_offset, adapter->rx_prod2_offset
 	};
 	u32 num_pkts = 0;
 	bool skip_page_frags = false;
@@ -2783,9 +2783,9 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		VMXNET3_WRITE_BAR0_REG(adapter,
-				VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN,
+				adapter->rx_prod_offset + i * VMXNET3_REG_ALIGN,
 				adapter->rx_queue[i].rx_ring[0].next2fill);
-		VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_RXPROD2 +
+		VMXNET3_WRITE_BAR0_REG(adapter, (adapter->rx_prod2_offset +
 				(i * VMXNET3_REG_ALIGN)),
 				adapter->rx_queue[i].rx_ring[1].next2fill);
 	}
@@ -3608,6 +3608,10 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	if (VMXNET3_VERSION_GE_7(adapter)) {
 		adapter->devcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DCR);
 		adapter->ptcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_PTCR);
+		if (adapter->devcap_supported[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) {
+			adapter->dev_caps[0] = adapter->devcap_supported[0] &
+							(1UL << VMXNET3_CAP_LARGE_BAR);
+		}
 		if (adapter->dev_caps[0])
 			VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]);
 
@@ -3617,6 +3621,17 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
 	}
 
+	if (VMXNET3_VERSION_GE_7(adapter) &&
+	    adapter->dev_caps[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) {
+		adapter->tx_prod_offset = VMXNET3_REG_LB_TXPROD;
+		adapter->rx_prod_offset = VMXNET3_REG_LB_RXPROD;
+		adapter->rx_prod2_offset = VMXNET3_REG_LB_RXPROD2;
+	} else {
+		adapter->tx_prod_offset = VMXNET3_REG_TXPROD;
+		adapter->rx_prod_offset = VMXNET3_REG_RXPROD;
+		adapter->rx_prod2_offset = VMXNET3_REG_RXPROD2;
+	}
+
 	if (VMXNET3_VERSION_GE_6(adapter)) {
 		spin_lock_irqsave(&adapter->cmd_lock, flags);
 		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 458f2da1ebab..397b268f7bc5 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -520,7 +520,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i];
 
-		buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_TXPROD +
+		buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->tx_prod_offset +
 						 i * VMXNET3_REG_ALIGN);
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA);
@@ -548,9 +548,9 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 
-		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD +
+		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod_offset +
 						  i * VMXNET3_REG_ALIGN);
-		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD2 +
+		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod2_offset +
 						  i * VMXNET3_REG_ALIGN);
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA);
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index a7c8f80702c2..a4f832f0ad5b 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -406,6 +406,9 @@ struct vmxnet3_adapter {
 	u32    devcap_supported[8];
 	u32    ptcap_supported[8];
 	u32    dev_caps[8];
+	u16    tx_prod_offset;
+	u16    rx_prod_offset;
+	u16    rx_prod2_offset;
 };
 
 #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val)  \