Re: [PATCH 1/3] net/hns3: fix the hardware GRO function is abnormal

2025-06-09 Thread huangdengdui
On 2025/6/10 1:13, Stephen Hemminger wrote: > On Mon, 9 Jun 2025 21:06:49 +0800 > Dengdui Huang wrote: > >> +rem = dma_addr & (HNS3_RX_DMA_ADDR_ALIGN_128 - 1); >> +if ((rx_offload & RTE_ETH_RX_OFFLOAD_TCP_LRO) && rem > 0) { >> +hns3_err(hw, "Hardware GRO is not supported whe

Re: [PATCH 1/3] net/hns3: fix the hardware GRO function is abnormal

2025-06-09 Thread Stephen Hemminger
On Mon, 9 Jun 2025 21:06:49 +0800 Dengdui Huang wrote: > + rem = dma_addr & (HNS3_RX_DMA_ADDR_ALIGN_128 - 1); > + if ((rx_offload & RTE_ETH_RX_OFFLOAD_TCP_LRO) && rem > 0) { > + hns3_err(hw, "Hardware GRO is not supported when mbuf DMA " > + "address is 64

[PATCH 1/3] net/hns3: fix the hardware GRO function is abnormal

2025-06-09 Thread Dengdui Huang
Currently, the alignment requirements of the data address in mbuf is 64-byte on HIP08 platform. However, the GRO feature will be abnormal in this case. Many online applications already use 64-byte aligned. So a check is added to avoid using the GRO function when 64-byte aligned is used. Fixes: d1