diff mbox series

[v3,2/4] mm/tlbbatch: Introduce arch_tlbbatch_should_defer()

Message ID 20220822082120.8347-3-yangyicong@huawei.com (mailing list archive)
State New
Headers show
Series mm: arm64: bring up BATCHED_UNMAP_TLB_FLUSH | expand

Commit Message

Yicong Yang Aug. 22, 2022, 8:21 a.m. UTC 
From: Anshuman Khandual <khandual@linux.vnet.ibm.com>

The entire scheme of deferred TLB flush in reclaim path rests on the
fact that the cost to refill TLB entries is less than flushing out
individual entries by sending IPI to remote CPUs. But architecture
can have different ways to evaluate that. Hence apart from checking
TTU_BATCH_FLUSH in the TTU flags, rest of the decision should be
architecture specific.

Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
[https://lore.kernel.org/linuxppc-dev/20171101101735.2318-2-khandual@linux.vnet.ibm.com/]
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
[Rebase and fix incorrect return value type]
---
 arch/x86/include/asm/tlbflush.h | 12 ++++++++++++
 mm/rmap.c                       |  9 +--------
 2 files changed, 13 insertions(+), 8 deletions(-)

Comments

Kefeng Wang Aug. 24, 2022, 9:40 a.m. UTC | #1 
On 2022/8/22 16:21, Yicong Yang wrote:
> From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
>
> The entire scheme of deferred TLB flush in reclaim path rests on the
> fact that the cost to refill TLB entries is less than flushing out
> individual entries by sending IPI to remote CPUs. But architecture
> can have different ways to evaluate that. Hence apart from checking
> TTU_BATCH_FLUSH in the TTU flags, rest of the decision should be
> architecture specific.
>
> Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
> [https://lore.kernel.org/linuxppc-dev/20171101101735.2318-2-khandual@linux.vnet.ibm.com/]
> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
> [Rebase and fix incorrect return value type]

Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>

> ---
>   arch/x86/include/asm/tlbflush.h | 12 ++++++++++++
>   mm/rmap.c                       |  9 +--------
>   2 files changed, 13 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
> index cda3118f3b27..8a497d902c16 100644
> --- a/arch/x86/include/asm/tlbflush.h
> +++ b/arch/x86/include/asm/tlbflush.h
> @@ -240,6 +240,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
>   	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
>   }
>   
> +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
> +{
> +	bool should_defer = false;
> +
> +	/* If remote CPUs need to be flushed then defer batch the flush */
> +	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> +		should_defer = true;
> +	put_cpu();
> +
> +	return should_defer;
> +}
> +
>   static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
>   {
>   	/*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index edc06c52bc82..a17a004550c6 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -687,17 +687,10 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
>    */
>   static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
>   {
> -	bool should_defer = false;
> -
>   	if (!(flags & TTU_BATCH_FLUSH))
>   		return false;
>   
> -	/* If remote CPUs need to be flushed then defer batch the flush */
> -	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> -		should_defer = true;
> -	put_cpu();
> -
> -	return should_defer;
> +	return arch_tlbbatch_should_defer(mm);
>   }
>   
>   /*
Anshuman Khandual Sept. 9, 2022, 4:16 a.m. UTC | #2 
On 8/22/22 13:51, Yicong Yang wrote:
> From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
> 
> The entire scheme of deferred TLB flush in reclaim path rests on the
> fact that the cost to refill TLB entries is less than flushing out
> individual entries by sending IPI to remote CPUs. But architecture
> can have different ways to evaluate that. Hence apart from checking
> TTU_BATCH_FLUSH in the TTU flags, rest of the decision should be
> architecture specific.
> 
> Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
> [https://lore.kernel.org/linuxppc-dev/20171101101735.2318-2-khandual@linux.vnet.ibm.com/]
> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
> [Rebase and fix incorrect return value type]

From semantics perspective, this patch still makes sense, even on its own.

Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>

> ---
>  arch/x86/include/asm/tlbflush.h | 12 ++++++++++++
>  mm/rmap.c                       |  9 +--------
>  2 files changed, 13 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
> index cda3118f3b27..8a497d902c16 100644
> --- a/arch/x86/include/asm/tlbflush.h
> +++ b/arch/x86/include/asm/tlbflush.h
> @@ -240,6 +240,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
>  	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
>  }
>  
> +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
> +{
> +	bool should_defer = false;
> +
> +	/* If remote CPUs need to be flushed then defer batch the flush */
> +	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> +		should_defer = true;
> +	put_cpu();
> +
> +	return should_defer;
> +}
> +
>  static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
>  {
>  	/*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index edc06c52bc82..a17a004550c6 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -687,17 +687,10 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
>   */
>  static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
>  {
> -	bool should_defer = false;
> -
>  	if (!(flags & TTU_BATCH_FLUSH))
>  		return false;
>  
> -	/* If remote CPUs need to be flushed then defer batch the flush */
> -	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> -		should_defer = true;
> -	put_cpu();
> -
> -	return should_defer;
> +	return arch_tlbbatch_should_defer(mm);
>  }
>  
>  /*
diff mbox series

Patch

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cda3118f3b27..8a497d902c16 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -240,6 +240,18 @@  static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
 }
 
+static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+	bool should_defer = false;
+
+	/* If remote CPUs need to be flushed then defer batch the flush */
+	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
+		should_defer = true;
+	put_cpu();
+
+	return should_defer;
+}
+
 static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 {
 	/*
diff --git a/mm/rmap.c b/mm/rmap.c
index edc06c52bc82..a17a004550c6 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -687,17 +687,10 @@  static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
  */
 static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
 {
-	bool should_defer = false;
-
 	if (!(flags & TTU_BATCH_FLUSH))
 		return false;
 
-	/* If remote CPUs need to be flushed then defer batch the flush */
-	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
-		should_defer = true;
-	put_cpu();
-
-	return should_defer;
+	return arch_tlbbatch_should_defer(mm);
 }
 
 /*