diff mbox

[dpdk-dev] i40e: fix the issue of wrongly reporting descriptor done

Message ID 1438207699-11848-1-git-send-email-helin.zhang@intel.com (mailing list archive)
State Accepted, archived
Headers

Commit Message

Zhang, Helin July 29, 2015, 10:08 p.m. UTC 
  Header buffer address for header split will be filled with the
physical address for DMA, which is actually not needed at all,
as header split hasn't been supported. Hardware requires the
least bit of header address which is 'Descriptor Done' bit when
write back should be set to 0 by driver.
The issue is that if the user wants to reserve an odd number of
bytes between the mbuf header and data buffer, the physical address
to be filled in the descriptor would happen to be odd. That means
the DD bit would be set to non-zero by driver. That will result in
reporting descriptor done wrongly.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
---
 drivers/net/i40e/i40e_rxtx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

Comments

Thomas Monjalon Aug. 2, 2015, 9:57 p.m. UTC | #1 
2015-07-30 06:08, Helin Zhang:
> Header buffer address for header split will be filled with the
> physical address for DMA, which is actually not needed at all,
> as header split hasn't been supported. Hardware requires the
> least bit of header address which is 'Descriptor Done' bit when
> write back should be set to 0 by driver.
> The issue is that if the user wants to reserve an odd number of
> bytes between the mbuf header and data buffer, the physical address
> to be filled in the descriptor would happen to be odd. That means
> the DD bit would be set to non-zero by driver. That will result in
> reporting descriptor done wrongly.
> 
> Signed-off-by: Helin Zhang <helin.zhang@intel.com>

Applied, thanks
diff mbox

Patch

diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 891a221..a267b4d 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -1367,7 +1367,7 @@  i40e_rx_alloc_bufs(struct i40e_rx_queue *rxq)
 		mb->port = rxq->port_id;
 		dma_addr = rte_cpu_to_le_64(\
 			RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb));
-		rxdp[i].read.hdr_addr = dma_addr;
+		rxdp[i].read.hdr_addr = 0;
 		rxdp[i].read.pkt_addr = dma_addr;
 	}
 
@@ -1514,7 +1514,7 @@  i40e_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		rxe->mbuf = nmb;
 		dma_addr =
 			rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb));
-		rxdp->read.hdr_addr = dma_addr;
+		rxdp->read.hdr_addr = 0;
 		rxdp->read.pkt_addr = dma_addr;
 
 		rx_packet_len = ((qword1 & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
@@ -1640,7 +1640,7 @@  i40e_recv_scattered_pkts(void *rx_queue,
 			rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb));
 
 		/* Set data buffer address and data length of the mbuf */
-		rxdp->read.hdr_addr = dma_addr;
+		rxdp->read.hdr_addr = 0;
 		rxdp->read.pkt_addr = dma_addr;
 		rx_packet_len = (qword1 & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
 					I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
@@ -3047,7 +3047,7 @@  i40e_alloc_rx_queue_mbufs(struct i40e_rx_queue *rxq)
 
 		rxd = &rxq->rx_ring[i];
 		rxd->read.pkt_addr = dma_addr;
-		rxd->read.hdr_addr = dma_addr;
+		rxd->read.hdr_addr = 0;
 #ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
 		rxd->read.rsvd1 = 0;
 		rxd->read.rsvd2 = 0;