[PATCH v5 1/1] riscv: mm: use svinval instructions instead of sfence.vma

[Andrew Jones]

On Fri, Jun 23, 2023 at 06:08:49PM +0530, Mayuresh Chitale wrote:
> When svinval is supported the local_flush_tlb_page*
> functions would prefer to use the following sequence
> to optimize the tlb flushes instead of a simple sfence.vma:
> 
> sfence.w.inval
> svinval.vma
>   .
>   .
> svinval.vma
> sfence.inval.ir
> 
> The maximum number of consecutive svinval.vma instructions
> that can be executed in local_flush_tlb_page* functions is
> limited to 64. This is required to avoid soft lockups and the
> approach is similar to that used in arm64.
> 
> Signed-off-by: Mayuresh Chitale <mchitale at ventanamicro.com>
> ---
>  arch/riscv/include/asm/tlbflush.h |  1 +
>  arch/riscv/mm/tlbflush.c          | 66 +++++++++++++++++++++++++++----
>  2 files changed, 59 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
> index a09196f8de68..56490c04b0bd 100644
> --- a/arch/riscv/include/asm/tlbflush.h
> +++ b/arch/riscv/include/asm/tlbflush.h
> @@ -30,6 +30,7 @@ static inline void local_flush_tlb_page(unsigned long addr)
>  #endif /* CONFIG_MMU */
>  
>  #if defined(CONFIG_SMP) && defined(CONFIG_MMU)
> +extern unsigned long tlb_flush_all_threshold;
>  void flush_tlb_all(void);
>  void flush_tlb_mm(struct mm_struct *mm);
>  void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
> diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
> index 77be59aadc73..f63cdf8644f3 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -5,6 +5,17 @@
>  #include <linux/sched.h>
>  #include <asm/sbi.h>
>  #include <asm/mmu_context.h>
> +#include <asm/hwcap.h>
> +#include <asm/insn-def.h>
> +
> +#define has_svinval()	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
> +
> +/*
> + * Flush entire TLB if number of entries to be flushed is greater
> + * than the threshold below. Platforms may override the threshold
> + * value based on marchid, mvendorid, and mimpid.
> + */
> +unsigned long tlb_flush_all_threshold __read_mostly = 64;
>  
>  static inline void local_flush_tlb_all_asid(unsigned long asid)
>  {
> @@ -24,21 +35,60 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
>  }
>  
>  static inline void local_flush_tlb_range(unsigned long start,
> -		unsigned long size, unsigned long stride)
> +					 unsigned long size,
> +					 unsigned long stride)
>  {
> -	if (size <= stride)
> -		local_flush_tlb_page(start);
> -	else
> +	unsigned long end = start + size;
> +	unsigned long num_entries = DIV_ROUND_UP(size, stride);
> +
> +	if (!num_entries || num_entries > tlb_flush_all_threshold) {
>  		local_flush_tlb_all();
> +		return;
> +	}
> +
> +	if (has_svinval())
> +		asm volatile(SFENCE_W_INVAL() ::: "memory");
> +
> +	while (start < end) {
> +		if (has_svinval())
> +			asm volatile(SINVAL_VMA(%0, zero)
> +				     : : "r" (start) : "memory");
> +		else
> +			local_flush_tlb_page(start);
> +		start += stride;
> +	}
> +
> +	if (has_svinval())
> +		asm volatile(SFENCE_INVAL_IR() ::: "memory");
>  }
>  
>  static inline void local_flush_tlb_range_asid(unsigned long start,
> -		unsigned long size, unsigned long stride, unsigned long asid)
> +					      unsigned long size,
> +					      unsigned long stride,
> +					      unsigned long asid)
>  {
> -	if (size <= stride)
> -		local_flush_tlb_page_asid(start, asid);
> -	else
> +	unsigned long end = start + size;
> +	unsigned long num_entries = DIV_ROUND_UP(size, stride);
> +
> +	if (!num_entries || num_entries > tlb_flush_all_threshold) {
>  		local_flush_tlb_all_asid(asid);
> +		return;
> +	}
> +
> +	if (has_svinval())
> +		asm volatile(SFENCE_W_INVAL() ::: "memory");
> +
> +	while (start < end) {
> +		if (has_svinval())
> +			asm volatile(SINVAL_VMA(%0, %1) : : "r" (start),
> +				     "r" (asid) : "memory");
> +		else
> +			local_flush_tlb_page_asid(start, asid);
> +		start += stride;
> +	}
> +
> +	if (has_svinval())
> +		asm volatile(SFENCE_INVAL_IR() ::: "memory");
>  }
>  
>  static void __ipi_flush_tlb_all(void *info)
> -- 
> 2.34.1
> 

Reviewed-by: Andrew Jones <ajones at ventanamicro.com>