On Tue, 25 May 2021 22:49:20 PDT (-0700), guoren@xxxxxxxxxx wrote:
From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx> Kernel virtual address translation should avoid to use ASIDs or it'll cause more TLB-miss and TLB-refill. Because the current ASID in satp belongs to the current process, but the target kernel va TLB entry's ASID still belongs to the previous process.
Sorry, I still can't quite figure out what this is trying to say. I went ahead and re-wrote the commit text to
riscv: Use global mappings for kernel pages We map kernel pages into all addresses spages, so they can be marked as global. This allows hardware to avoid flushing the kernel mappings when moving between address spaces. LMK if I'm misunderstanding something here, it's on for-next.
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx> Reviewed-by: Anup Patel <anup@xxxxxxxxxxxxxx> Reviewed-by: Christoph Hellwig <hch@xxxxxx> Cc: Palmer Dabbelt <palmerdabbelt@xxxxxxxxxx> --- arch/riscv/include/asm/pgtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9469f46..346a3c6 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -134,7 +134,8 @@ | _PAGE_WRITE \ | _PAGE_PRESENT \ | _PAGE_ACCESSED \ - | _PAGE_DIRTY) + | _PAGE_DIRTY \ + | _PAGE_GLOBAL) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
