[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20231122155117.2816724-2-ioana.ciornei@nxp.com>
Date: Wed, 22 Nov 2023 17:51:15 +0200
From: Ioana Ciornei <ioana.ciornei@....com>
To: davem@...emloft.net,
edumazet@...gle.com,
kuba@...nel.org,
pabeni@...hat.com
Cc: andrew@...n.ch,
netdev@...r.kernel.org,
Ioana Ciornei <ioana.ciornei@....com>
Subject: [PATCH net 1/3] dpaa2-eth: increase the needed headroom to account for alignment
Increase the needed headroom to account for a 64 byte alignment
restriction which, with this patch, we make mandatory on the Tx path.
The case in which the amount of headroom needed is not available is
already handled by the driver which instead sends a S/G frame with the
first buffer only holding the SW and HW annotation areas.
Without this patch, we can empirically see data corruption happening
between Tx and Tx confirmation which sometimes leads to the SW
annotation area being overwritten.
Since this is an old IP where the hardware team cannot help to
understand the underlying behavior, we make the Tx alignment mandatory
for all frames to avoid the crash on Tx conf. Also, remove the comment
that suggested that this is just an optimization.
Fixes: 6e2387e8f19e ("staging: fsl-dpaa2/eth: Add Freescale DPAA2 Ethernet driver")
Closes: https://lore.kernel.org/netdev/aa784d0c-85eb-4e5d-968b-c8f74fa86be6@gin.de/
Signed-off-by: Ioana Ciornei <ioana.ciornei@....com>
---
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 6 ++----
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 2 +-
2 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 15bab41cee48..f2676fd50e1f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1073,14 +1073,12 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv,
dma_addr_t addr;
buffer_start = skb->data - dpaa2_eth_needed_headroom(skb);
-
- /* If there's enough room to align the FD address, do it.
- * It will help hardware optimize accesses.
- */
aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
DPAA2_ETH_TX_BUF_ALIGN);
if (aligned_start >= skb->head)
buffer_start = aligned_start;
+ else
+ return -ENOMEM;
/* Store a backpointer to the skb at the beginning of the buffer
* (in the private data area) such that we can release it
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index bfb6c96c3b2f..834cba8c3a41 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -740,7 +740,7 @@ static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options)
static inline unsigned int dpaa2_eth_needed_headroom(struct sk_buff *skb)
{
- unsigned int headroom = DPAA2_ETH_SWA_SIZE;
+ unsigned int headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN;
/* If we don't have an skb (e.g. XDP buffer), we only need space for
* the software annotation area
--
2.25.1
Powered by blists - more mailing lists