Re: [PATCH v5 4/4] riscv: Improve flush_tlb_kernel_range()

[Samuel Holland <samuel.holland@sifive.com>]

On 2023-10-19 9:01 AM, Alexandre Ghiti wrote:
> This function used to simply flush the whole tlb of all harts, be more
> subtile and try to only flush the range.
> 
> The problem is that we can only use PAGE_SIZE as stride since we don't know
> the size of the underlying mapping and then this function will be improved
> only if the size of the region to flush is < threshold * PAGE_SIZE.
> 
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
> Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> # On RZ/Five SMARC
> ---
>  arch/riscv/include/asm/tlbflush.h | 11 ++++++-----
>  arch/riscv/mm/tlbflush.c          | 33 ++++++++++++++++++++++---------
>  2 files changed, 30 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
> index 170a49c531c6..8f3418c5f172 100644
> --- a/arch/riscv/include/asm/tlbflush.h
> +++ b/arch/riscv/include/asm/tlbflush.h
> @@ -40,6 +40,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
>  void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
>  void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  		     unsigned long end);
> +void flush_tlb_kernel_range(unsigned long start, unsigned long end);
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
>  void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
> @@ -56,15 +57,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
>  	local_flush_tlb_all();
>  }
>  
> -#define flush_tlb_mm(mm) flush_tlb_all()
> -#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
> -#endif /* !CONFIG_SMP || !CONFIG_MMU */
> -
>  /* Flush a range of kernel pages */
>  static inline void flush_tlb_kernel_range(unsigned long start,
>  	unsigned long end)
>  {
> -	flush_tlb_all();
> +	local_flush_tlb_all();
>  }
>  
> +#define flush_tlb_mm(mm) flush_tlb_all()
> +#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
> +#endif /* !CONFIG_SMP || !CONFIG_MMU */
> +
>  #endif /* _ASM_RISCV_TLBFLUSH_H */
> diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
> index c27ba720e35f..7e182f2bc0ab 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -97,19 +97,27 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  			      unsigned long size, unsigned long stride)
>  {
>  	struct flush_tlb_range_data ftd;
> -	struct cpumask *cmask = mm_cpumask(mm);
> +	struct cpumask *cmask, full_cmask;
>  	unsigned long asid = FLUSH_TLB_NO_ASID;
> -	unsigned int cpuid;
>  	bool broadcast;
>  
> -	if (cpumask_empty(cmask))
> -		return;
> +	if (mm) {
> +		unsigned int cpuid;
> +
> +		cmask = mm_cpumask(mm);
> +		if (cpumask_empty(cmask))
> +			return;
>  
> -	cpuid = get_cpu();
> -	/* check if the tlbflush needs to be sent to other CPUs */
> -	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
> +		cpuid = get_cpu();
> +		/* check if the tlbflush needs to be sent to other CPUs */
> +		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
> +	} else {
> +		cpumask_setall(&full_cmask);
> +		cmask = &full_cmask;
> +		broadcast = true;

on_each_cpu_mask() only considers CPUs in cpu_online_mask anyway, so you can
more efficiently use:

  cmask = cpu_online_mask;

here (after making cmask const).

> +	}
>  
> -	if (static_branch_unlikely(&use_asid_allocator))
> +	if (static_branch_unlikely(&use_asid_allocator) && mm)
>  		asid = atomic_long_read(&mm->context.id) & asid_mask;

Instead of adding another check, please move this inside "if (mm)" above. Those
are both non-functional changes, so:

Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>

>  
>  	if (broadcast) {
> @@ -128,7 +136,8 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  		local_flush_tlb_range_asid(start, size, stride, asid);
>  	}
>  
> -	put_cpu();
> +	if (mm)
> +		put_cpu();
>  }
>  
>  void flush_tlb_mm(struct mm_struct *mm)
> @@ -181,6 +190,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  
>  	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
>  }
> +
> +void flush_tlb_kernel_range(unsigned long start, unsigned long end)
> +{
> +	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
> +}
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  			unsigned long end)