From: "hpreg@vmware.com" <hpreg@vmware.com>
Date: Mon, 14 May 2018 08:14:49 -0400
Subject: vmxnet3: use DMA memory barriers where required
Patch-mainline: v4.17-rc7
Git-commit: f3002c1374fb2367c9d8dbb28852791ef90d2bac
References: bsc#1091860

The gen bits must be read first from (resp. written last to) DMA memory.
The proper way to enforce this on Linux is to call dma_rmb() (resp.
dma_wmb()).

Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/vmxnet3/vmxnet3_drv.c |   22 ++++++++++++++++++++++
 drivers/net/vmxnet3/vmxnet3_int.h |    4 ++--
 2 files changed, 24 insertions(+), 2 deletions(-)

--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -369,6 +369,11 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx
 
 	gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
 	while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
+		/* Prevent any &gdesc->tcd field from being (speculatively)
+		 * read before (&gdesc->tcd)->gen is read.
+		 */
+		dma_rmb();
+
 		completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
 					       &gdesc->tcd), tq, adapter->pdev,
 					       adapter);
@@ -1103,6 +1108,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, str
 		gdesc->txd.tci = skb_vlan_tag_get(skb);
 	}
 
+	/* Ensure that the write to (&gdesc->txd)->gen will be observed after
+	 * all other writes to &gdesc->txd.
+	 */
+	dma_wmb();
+
 	/* finally flips the GEN bit of the SOP desc. */
 	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
 						  VMXNET3_TXD_GEN);
@@ -1298,6 +1308,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx
 			 */
 			break;
 		}
+
+		/* Prevent any rcd field from being (speculatively) read before
+		 * rcd->gen is read.
+		 */
+		dma_rmb();
+
 		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
 		       rcd->rqID != rq->dataRingQid);
 		idx = rcd->rxdIdx;
@@ -1528,6 +1544,12 @@ rcd_done:
 		ring->next2comp = idx;
 		num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring);
 		ring = rq->rx_ring + ring_idx;
+
+		/* Ensure that the writes to rxd->gen bits will be observed
+		 * after all other writes to rxd objects.
+		 */
+		dma_wmb();
+
 		while (num_to_alloc) {
 			vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd,
 					  &rxCmdDesc);
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,12 +69,12 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.15.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.16.0-k"
 
 /* Each byte of this 32-bit integer encodes a version number in
  * VMXNET3_DRIVER_VERSION_STRING.
  */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040f00
+#define VMXNET3_DRIVER_VERSION_NUM      0x01041000
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */