diff mbox series

[v6,08/18] arm64/mm: Convert set_pte_at() to set_ptes(..., 1)

Message ID 20240215103205.2607016-9-ryan.roberts@arm.com (mailing list archive)
State New, archived
Headers show
Series Transparent Contiguous PTEs for User Mappings | expand

Commit Message

Ryan Roberts Feb. 15, 2024, 10:31 a.m. UTC
Since set_ptes() was introduced, set_pte_at() has been implemented as a
generic macro around set_ptes(..., 1). So this change should continue to
generate the same code. However, making this change prepares us for the
transparent contpte support. It means we can reroute set_ptes() to
__set_ptes(). Since set_pte_at() is a generic macro, there will be no
equivalent __set_pte_at() to reroute to.

Note that a couple of calls to set_pte_at() remain in the arch code.
This is intentional, since those call sites are acting on behalf of
core-mm and should continue to call into the public set_ptes() rather
than the arch-private __set_ptes().

Tested-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
 arch/arm64/include/asm/pgtable.h |  2 +-
 arch/arm64/kernel/mte.c          |  2 +-
 arch/arm64/kvm/guest.c           |  2 +-
 arch/arm64/mm/fault.c            |  2 +-
 arch/arm64/mm/hugetlbpage.c      | 10 +++++-----
 5 files changed, 9 insertions(+), 9 deletions(-)

Comments

Mark Rutland Feb. 15, 2024, 11:19 a.m. UTC | #1
On Thu, Feb 15, 2024 at 10:31:55AM +0000, Ryan Roberts wrote:
> Since set_ptes() was introduced, set_pte_at() has been implemented as a
> generic macro around set_ptes(..., 1). So this change should continue to
> generate the same code. However, making this change prepares us for the
> transparent contpte support. It means we can reroute set_ptes() to
> __set_ptes(). Since set_pte_at() is a generic macro, there will be no
> equivalent __set_pte_at() to reroute to.
> 
> Note that a couple of calls to set_pte_at() remain in the arch code.
> This is intentional, since those call sites are acting on behalf of
> core-mm and should continue to call into the public set_ptes() rather
> than the arch-private __set_ptes().
> 
> Tested-by: John Hubbard <jhubbard@nvidia.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>

Acked-by: Mark Rutland <mark.rutland@arm.com>

Mark.

> ---
>  arch/arm64/include/asm/pgtable.h |  2 +-
>  arch/arm64/kernel/mte.c          |  2 +-
>  arch/arm64/kvm/guest.c           |  2 +-
>  arch/arm64/mm/fault.c            |  2 +-
>  arch/arm64/mm/hugetlbpage.c      | 10 +++++-----
>  5 files changed, 9 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index de034ca40bad..9a2df85eb493 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -1084,7 +1084,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
>  #endif /* CONFIG_ARM64_MTE */
>  
>  /*
> - * On AArch64, the cache coherency is handled via the set_pte_at() function.
> + * On AArch64, the cache coherency is handled via the set_ptes() function.
>   */
>  static inline void update_mmu_cache_range(struct vm_fault *vmf,
>  		struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
> diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
> index a41ef3213e1e..59bfe2e96f8f 100644
> --- a/arch/arm64/kernel/mte.c
> +++ b/arch/arm64/kernel/mte.c
> @@ -67,7 +67,7 @@ int memcmp_pages(struct page *page1, struct page *page2)
>  	/*
>  	 * If the page content is identical but at least one of the pages is
>  	 * tagged, return non-zero to avoid KSM merging. If only one of the
> -	 * pages is tagged, set_pte_at() may zero or change the tags of the
> +	 * pages is tagged, set_ptes() may zero or change the tags of the
>  	 * other page via mte_sync_tags().
>  	 */
>  	if (page_mte_tagged(page1) || page_mte_tagged(page2))
> diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
> index aaf1d4939739..6e0df623c8e9 100644
> --- a/arch/arm64/kvm/guest.c
> +++ b/arch/arm64/kvm/guest.c
> @@ -1072,7 +1072,7 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
>  		} else {
>  			/*
>  			 * Only locking to serialise with a concurrent
> -			 * set_pte_at() in the VMM but still overriding the
> +			 * set_ptes() in the VMM but still overriding the
>  			 * tags, hence ignoring the return value.
>  			 */
>  			try_page_mte_tagging(page);
> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
> index a254761fa1bd..3235e23309ec 100644
> --- a/arch/arm64/mm/fault.c
> +++ b/arch/arm64/mm/fault.c
> @@ -205,7 +205,7 @@ static void show_pte(unsigned long addr)
>   *
>   * It needs to cope with hardware update of the accessed/dirty state by other
>   * agents in the system and can safely skip the __sync_icache_dcache() call as,
> - * like set_pte_at(), the PTE is never changed from no-exec to exec here.
> + * like set_ptes(), the PTE is never changed from no-exec to exec here.
>   *
>   * Returns whether or not the PTE actually changed.
>   */
> diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> index 2892f925ed66..27f6160890d1 100644
> --- a/arch/arm64/mm/hugetlbpage.c
> +++ b/arch/arm64/mm/hugetlbpage.c
> @@ -247,12 +247,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
>  
>  	if (!pte_present(pte)) {
>  		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
> -			set_pte_at(mm, addr, ptep, pte);
> +			set_ptes(mm, addr, ptep, pte, 1);
>  		return;
>  	}
>  
>  	if (!pte_cont(pte)) {
> -		set_pte_at(mm, addr, ptep, pte);
> +		set_ptes(mm, addr, ptep, pte, 1);
>  		return;
>  	}
>  
> @@ -263,7 +263,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
>  	clear_flush(mm, addr, ptep, pgsize, ncontig);
>  
>  	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
> -		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
> +		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
>  }
>  
>  pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
> @@ -471,7 +471,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
>  
>  	hugeprot = pte_pgprot(pte);
>  	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
> -		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
> +		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
>  
>  	return 1;
>  }
> @@ -500,7 +500,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
>  	pfn = pte_pfn(pte);
>  
>  	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
> -		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
> +		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
>  }
>  
>  pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
> -- 
> 2.25.1
>
Catalin Marinas Feb. 15, 2024, 6:34 p.m. UTC | #2
On Thu, Feb 15, 2024 at 10:31:55AM +0000, Ryan Roberts wrote:
> Since set_ptes() was introduced, set_pte_at() has been implemented as a
> generic macro around set_ptes(..., 1). So this change should continue to
> generate the same code. However, making this change prepares us for the
> transparent contpte support. It means we can reroute set_ptes() to
> __set_ptes(). Since set_pte_at() is a generic macro, there will be no
> equivalent __set_pte_at() to reroute to.
> 
> Note that a couple of calls to set_pte_at() remain in the arch code.
> This is intentional, since those call sites are acting on behalf of
> core-mm and should continue to call into the public set_ptes() rather
> than the arch-private __set_ptes().
> 
> Tested-by: John Hubbard <jhubbard@nvidia.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index de034ca40bad..9a2df85eb493 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1084,7 +1084,7 @@  static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 #endif /* CONFIG_ARM64_MTE */
 
 /*
- * On AArch64, the cache coherency is handled via the set_pte_at() function.
+ * On AArch64, the cache coherency is handled via the set_ptes() function.
  */
 static inline void update_mmu_cache_range(struct vm_fault *vmf,
 		struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index a41ef3213e1e..59bfe2e96f8f 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -67,7 +67,7 @@  int memcmp_pages(struct page *page1, struct page *page2)
 	/*
 	 * If the page content is identical but at least one of the pages is
 	 * tagged, return non-zero to avoid KSM merging. If only one of the
-	 * pages is tagged, set_pte_at() may zero or change the tags of the
+	 * pages is tagged, set_ptes() may zero or change the tags of the
 	 * other page via mte_sync_tags().
 	 */
 	if (page_mte_tagged(page1) || page_mte_tagged(page2))
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index aaf1d4939739..6e0df623c8e9 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -1072,7 +1072,7 @@  int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 		} else {
 			/*
 			 * Only locking to serialise with a concurrent
-			 * set_pte_at() in the VMM but still overriding the
+			 * set_ptes() in the VMM but still overriding the
 			 * tags, hence ignoring the return value.
 			 */
 			try_page_mte_tagging(page);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index a254761fa1bd..3235e23309ec 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -205,7 +205,7 @@  static void show_pte(unsigned long addr)
  *
  * It needs to cope with hardware update of the accessed/dirty state by other
  * agents in the system and can safely skip the __sync_icache_dcache() call as,
- * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ * like set_ptes(), the PTE is never changed from no-exec to exec here.
  *
  * Returns whether or not the PTE actually changed.
  */
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 2892f925ed66..27f6160890d1 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -247,12 +247,12 @@  void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-			set_pte_at(mm, addr, ptep, pte);
+			set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
 	if (!pte_cont(pte)) {
-		set_pte_at(mm, addr, ptep, pte);
+		set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
@@ -263,7 +263,7 @@  void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	clear_flush(mm, addr, ptep, pgsize, ncontig);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -471,7 +471,7 @@  int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 
 	return 1;
 }
@@ -500,7 +500,7 @@  void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	pfn = pte_pfn(pte);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,