[v4,11/12] riscv: mm: Preserve global TLB entries when switching contexts

Message ID 20240102220134.3229156-12-samuel.holland@sifive.com
State New
Headers
Series riscv: ASID-related and UP-related TLB flush enhancements |

Commit Message

Samuel Holland Jan. 2, 2024, 10 p.m. UTC
  If the CPU does not support multiple ASIDs, all MM contexts use ASID 0.
In this case, it is still beneficial to flush the TLB by ASID, as the
single-ASID variant of the sfence.vma instruction preserves TLB entries
for global (kernel) pages.

This optimization is recommended by the RISC-V privileged specification:

  If the implementation does not provide ASIDs, or software chooses
  to always use ASID 0, then after every satp write, software should
  execute SFENCE.VMA with rs1=x0. In the common case that no global
  translations have been modified, rs2 should be set to a register
  other than x0 but which contains the value zero, so that global
  translations are not flushed.

It is not possible to apply this optimization when using the ASID
allocator, because that code must flush the TLB for all ASIDs at once
when incrementing the version number.

Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
---

(no changes since v1)

 arch/riscv/mm/context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
  

Comments

Alexandre Ghiti Jan. 4, 2024, 12:55 p.m. UTC | #1
On Tue, Jan 2, 2024 at 11:01 PM Samuel Holland
<samuel.holland@sifive.com> wrote:
>
> If the CPU does not support multiple ASIDs, all MM contexts use ASID 0.
> In this case, it is still beneficial to flush the TLB by ASID, as the
> single-ASID variant of the sfence.vma instruction preserves TLB entries
> for global (kernel) pages.
>
> This optimization is recommended by the RISC-V privileged specification:
>
>   If the implementation does not provide ASIDs, or software chooses
>   to always use ASID 0, then after every satp write, software should
>   execute SFENCE.VMA with rs1=x0. In the common case that no global
>   translations have been modified, rs2 should be set to a register
>   other than x0 but which contains the value zero, so that global
>   translations are not flushed.
>
> It is not possible to apply this optimization when using the ASID
> allocator, because that code must flush the TLB for all ASIDs at once
> when incrementing the version number.
>
> Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
> ---
>
> (no changes since v1)
>
>  arch/riscv/mm/context.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
> index 43a8bc2d5af4..3ca9b653df7d 100644
> --- a/arch/riscv/mm/context.c
> +++ b/arch/riscv/mm/context.c
> @@ -200,7 +200,7 @@ static void set_mm_noasid(struct mm_struct *mm)
>  {
>         /* Switch the page table and blindly nuke entire local TLB */
>         csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
> -       local_flush_tlb_all();
> +       local_flush_tlb_all_asid(0);
>  }
>
>  static inline void set_mm(struct mm_struct *prev,
> --
> 2.42.0
>

You can add:

Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>

Thanks,

Alex
  

Patch

diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 43a8bc2d5af4..3ca9b653df7d 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -200,7 +200,7 @@  static void set_mm_noasid(struct mm_struct *mm)
 {
 	/* Switch the page table and blindly nuke entire local TLB */
 	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
-	local_flush_tlb_all();
+	local_flush_tlb_all_asid(0);
 }
 
 static inline void set_mm(struct mm_struct *prev,