vmxnet3: must split too big fragments

vmxnet3 has a 16Kbytes limit per tx descriptor, that happened to work
as long as we provided PAGE_SIZE fragments.

Our stack can now build larger fragments, so we need to split them to
the 16kbytes boundary.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: jongman heo <jongman.heo@samsung.com>
Tested-by: jongman heo <jongman.heo@samsung.com>
Cc: Shreyas Bhatewara <sbhatewara@vmware.com>
Reviewed-by: Bhavesh Davda <bhavesh@vmware.com>
Signed-off-by: Shreyas Bhatewara <sbhatewara@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vmxnet3/vmxnet3_drv.c

@@ -744,20 +744,31 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+		u32 buf_size;
 
+		buf_offset = 0;
+		len = skb_frag_size(frag);
+		while (len) {
 			tbi = tq->buf_info + tq->tx_ring.next2fill;
+			if (len < VMXNET3_MAX_TX_BUF_SIZE) {
+				buf_size = len;
+				dw2 |= len;
+			} else {
+				buf_size = VMXNET3_MAX_TX_BUF_SIZE;
+				/* spec says that for TxDesc.len, 0 == 2^14 */
+			}
 			tbi->map_type = VMXNET3_MAP_PAGE;
 			tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag,
-						 0, skb_frag_size(frag),
+							 buf_offset, buf_size,
 							 DMA_TO_DEVICE);
 
-		tbi->len = skb_frag_size(frag);
+			tbi->len = buf_size;
 
 			gdesc = tq->tx_ring.base + tq->tx_ring.next2fill;
 			BUG_ON(gdesc->txd.gen == tq->tx_ring.gen);
 
 			gdesc->txd.addr = cpu_to_le64(tbi->dma_addr);
-		gdesc->dword[2] = cpu_to_le32(dw2 | skb_frag_size(frag));
+			gdesc->dword[2] = cpu_to_le32(dw2);
 			gdesc->dword[3] = 0;
 
 			dev_dbg(&adapter->netdev->dev,
@@ -766,6 +777,10 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 				le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]);
 			vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
 			dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT;
+
+			len -= buf_size;
+			buf_offset += buf_size;
+		}
 	}
 
 	ctx->eop_txd = gdesc;
@@ -886,6 +901,18 @@ vmxnet3_prepare_tso(struct sk_buff *skb,
 	}
 }
 
+static int txd_estimate(const struct sk_buff *skb)
+{
+	int count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+
+		count += VMXNET3_TXD_NEEDED(skb_frag_size(frag));
+	}
+	return count;
+}
 
 /*
  * Transmits a pkt thru a given tq
@@ -914,9 +941,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	union Vmxnet3_GenericDesc tempTxDesc;
 #endif
 
-	/* conservatively estimate # of descriptors to use */
-	count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) +
-		skb_shinfo(skb)->nr_frags + 1;
+	count = txd_estimate(skb);
 
 	ctx.ipv4 = (vlan_get_protocol(skb) == cpu_to_be16(ETH_P_IP));