+1
−0
arch/x86/kernel/zhaoxin_kh40000.c
0 → 100644
+353
−0
Loading
Merge Pull Request from: @leoliu-oc The Zhaoxin KH-40000 platform can't keep the PCIE transaction order for DMA writes, whose target addresses are located in different NUMA nodes, from the same device. Patch this issue by flushing the target DMA write with a subsequent PCIE configuration space read operation. ### Issue https://gitee.com/openeuler/kernel/issues/I9ARTM ### Test NA ### Known Issue NA ### Default config change NA Link:https://gitee.com/openeuler/kernel/pulls/5480 Reviewed-by:Jason Zeng <jason.zeng@intel.com> Signed-off-by:
Zhang Peng <zhangpeng362@huawei.com>