[v2,4/4] riscv: Improve flush_tlb_kernel_range()

Message ID 20230727185553.980262-5-alexghiti@rivosinc.com
State New
Headers
Series riscv: tlb flush improvements |

Commit Message

Alexandre Ghiti July 27, 2023, 6:55 p.m. UTC
  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>
---
 arch/riscv/include/asm/tlbflush.h | 11 +++++-----
 arch/riscv/mm/tlbflush.c          | 35 +++++++++++++++++++++++--------
 2 files changed, 32 insertions(+), 14 deletions(-)
  

Comments

Andrew Jones July 28, 2023, 1:48 p.m. UTC | #1
On Thu, Jul 27, 2023 at 08:55:53PM +0200, 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>
> ---
>  arch/riscv/include/asm/tlbflush.h | 11 +++++-----
>  arch/riscv/mm/tlbflush.c          | 35 +++++++++++++++++++++++--------
>  2 files changed, 32 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
> index f5c4fb0ae642..7426fdcd8ec5 100644
> --- a/arch/riscv/include/asm/tlbflush.h
> +++ b/arch/riscv/include/asm/tlbflush.h
> @@ -37,6 +37,7 @@ 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,
> @@ -53,15 +54,15 @@ 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 8017d2130e27..96aeacb269d5 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -117,18 +117,27 @@ 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);
> -	unsigned int cpuid;
> +	struct cpumask *cmask, full_cmask;
>  	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;
> +	} else {
> +		cpumask_setall(&full_cmask);
> +		cmask = &full_cmask;
> +		broadcast = true;
> +	}
>  
> -	cpuid = get_cpu();
> -	/* check if the tlbflush needs to be sent to other CPUs */
> -	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
>  	if (static_branch_unlikely(&use_asid_allocator)) {
> -		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
> +		unsigned long asid = mm ? atomic_long_read(&mm->context.id) & asid_mask : 0;
>  
>  		if (broadcast) {
>  			if (riscv_use_ipi_for_rfence()) {
> @@ -162,7 +171,8 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  		}
>  	}
>  
> -	put_cpu();
> +	if (mm)
> +		put_cpu();
>  }
>  
>  void flush_tlb_mm(struct mm_struct *mm)
> @@ -194,6 +204,13 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  	__flush_tlb_range(vma->vm_mm,
>  			  start, end - start, 1 << stride_shift);
>  }
> +
> +void flush_tlb_kernel_range(unsigned long start,
> +			    unsigned long end)

No need to wrap this line.

> +{
> +	__flush_tlb_range(NULL, start, end, PAGE_SIZE);
> +}
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  			unsigned long end)
> -- 
> 2.39.2
>

Otherwise,

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

Thanks,
drew
  

Patch

diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index f5c4fb0ae642..7426fdcd8ec5 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -37,6 +37,7 @@  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,
@@ -53,15 +54,15 @@  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 8017d2130e27..96aeacb269d5 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -117,18 +117,27 @@  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);
-	unsigned int cpuid;
+	struct cpumask *cmask, full_cmask;
 	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;
+	} else {
+		cpumask_setall(&full_cmask);
+		cmask = &full_cmask;
+		broadcast = true;
+	}
 
-	cpuid = get_cpu();
-	/* check if the tlbflush needs to be sent to other CPUs */
-	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
 	if (static_branch_unlikely(&use_asid_allocator)) {
-		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
+		unsigned long asid = mm ? atomic_long_read(&mm->context.id) & asid_mask : 0;
 
 		if (broadcast) {
 			if (riscv_use_ipi_for_rfence()) {
@@ -162,7 +171,8 @@  static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 		}
 	}
 
-	put_cpu();
+	if (mm)
+		put_cpu();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
@@ -194,6 +204,13 @@  void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	__flush_tlb_range(vma->vm_mm,
 			  start, end - start, 1 << stride_shift);
 }
+
+void flush_tlb_kernel_range(unsigned long start,
+			    unsigned long end)
+{
+	__flush_tlb_range(NULL, start, end, PAGE_SIZE);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)