| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2024-06-16 | LoongArch: Add all CPUs enabled by fdt to NUMA node 0 | Jiaxun Yang | |
| commit 3de9c42d02a79a5e09bbee7a4421ddc00cfd5c6d upstream. NUMA enabled kernel on FDT based machine fails to boot because CPUs are all in NUMA_NO_NODE and mm subsystem won't accept that. Fix by adding them to default NUMA node at FDT parsing phase and move numa_add_cpu(0) to a later point. Cc: stable@vger.kernel.org Fixes: 88d4d957edc7 ("LoongArch: Add FDT booting support from efi system table") Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> | |||
| 2022-06-03 | LoongArch: Add Non-Uniform Memory Access (NUMA) support | Huacai Chen | |
| Add Non-Uniform Memory Access (NUMA) support for LoongArch. LoongArch has 48-bit physical address, but the HyperTransport I/O bus only support 40-bit address, so we need a custom phys_to_dma() and dma_to_phys() to extract the 4-bit node id (bit 44~47) from Loongson-3's 48-bit physical address space and embed it into 40-bit. In the 40-bit dma address, node id offset can be read from the LS7A_DMA_CFG register. Reviewed-by: WANG Xuerui <git@xen0n.name> Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> | |||
 |
index : linux/linux-stable.git | |
| Linux kernel stable tree | kernel.org maintainers |
| summaryrefslogtreecommitdiff |