Skip to contentSkip to conversation

nfp: correct desc type when header dma len is 4096

PATCH Applied Simon Horman 3 participants 3 messages Dec 2, 2022 – Dec 4, 2022

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 nfp: correct desc type when header dma len is 4096

From: Yinjun Zhang <[email protected]>

When there's only one buffer to dma and its length is 4096, then only one data descriptor is needed to carry it according to current descriptor definition. So the descriptor type should be simple instead of gather, the latter requires more than one descriptor, otherwise it'll be dropped by application firmware.

Fixes c10d12e3dce8 ("nfp: add support for NFDK data path")
Fixes d9d950490a0a ("nfp: nfdk: implement xdp tx path for NFDK")
---
 drivers/net/ethernet/netronome/nfp/nfdk/dp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/ethernet/netronome/nfp/nfdk/dp.c +3 -3
index 2b427d8ccb2f..ccacb6ab6c39 100644
@@ -282,7 +282,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev)
 	dma_len = skb_headlen(skb);
 	if (skb_is_gso(skb))
 		type = NFDK_DESC_TX_TYPE_TSO;
-	else if (!nr_frags && dma_len < NFDK_TX_MAX_DATA_PER_HEAD)
+	else if (!nr_frags && dma_len <= NFDK_TX_MAX_DATA_PER_HEAD)
 		type = NFDK_DESC_TX_TYPE_SIMPLE;
 	else
 		type = NFDK_DESC_TX_TYPE_GATHER;
@@ -927,7 +927,7 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
 	dma_len = pkt_len;
 	dma_addr = rxbuf->dma_addr + dma_off;
 
-	if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD)
+	if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD)
 		type = NFDK_DESC_TX_TYPE_SIMPLE;
 	else
 		type = NFDK_DESC_TX_TYPE_GATHER;
@@ -1325,7 +1325,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	txbuf = &tx_ring->ktxbufs[wr_idx];
 
 	dma_len = skb_headlen(skb);
-	if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD)
+	if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD)
 		type = NFDK_DESC_TX_TYPE_SIMPLE;
 	else
 		type = NFDK_DESC_TX_TYPE_GATHER;
Signature · 1 line
2.30.2
Reviewed-by on v1 1/1
#1 lore raw
Quoted 14 lines · Simon Horman

From: Yinjun Zhang <[email protected]>

When there's only one buffer to dma and its length is 4096, then only one data descriptor is needed to carry it according to current descriptor definition. So the descriptor type should be simple instead of gather, the latter requires more than one descriptor, otherwise it'll be dropped by application firmware.

Fixes c10d12e3dce8 ("nfp: add support for NFDK data path")
Fixes d9d950490a0a ("nfp: nfdk: implement xdp tx path for NFDK")
Quoted 4 lines
---
 drivers/net/ethernet/netronome/nfp/nfdk/dp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

Thanks,

#2 lore raw
In reply to Simon Horman
This patch was applied to netdev/net.git (master) by Jakub Kicinski <[email protected]>:

Hello:

This patch was applied to netdev/net.git (master)
by Jakub Kicinski <[email protected]>:

Quoted 9 lines · On Fri, 2 Dec 2022 14:46:46 +0100 you wrote:

From: Yinjun Zhang <[email protected]>

When there's only one buffer to dma and its length is 4096, then only one data descriptor is needed to carry it according to current descriptor definition. So the descriptor type should be simple instead of gather, the latter requires more than one descriptor, otherwise it'll be dropped by application firmware.

[...]

Here is the summary with links:
- [net] nfp: correct desc type when header dma len is 4096

    https://git.kernel.org/netdev/net/c/5c306de8f787

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html