diff mbox series

[v4,03/13] mm/vmemmap: Improve vmemmap_can_optimize and allow architectures to override

Message ID 20230710160842.56300-4-aneesh.kumar@linux.ibm.com (mailing list archive)
State New
Headers show
Series Add support for DAX vmemmap optimization for ppc64 | expand

Commit Message

Aneesh Kumar K.V July 10, 2023, 4:08 p.m. UTC
dax vmemmap optimization requires a minimum of 2 PAGE_SIZE area within
vmemmap such that tail page mapping can point to the second PAGE_SIZE area.
Enforce that in vmemmap_can_optimize() function.

Architectures like powerpc also want to enable vmemmap optimization
conditionally (only with radix MMU translation). Hence allow architecture
override.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 include/linux/mm.h | 27 +++++++++++++++++++++++----
 mm/mm_init.c       |  2 +-
 2 files changed, 24 insertions(+), 5 deletions(-)

Comments

Christophe Leroy July 10, 2023, 5:20 p.m. UTC | #1
Le 10/07/2023 à 18:08, Aneesh Kumar K.V a écrit :
> dax vmemmap optimization requires a minimum of 2 PAGE_SIZE area within
> vmemmap such that tail page mapping can point to the second PAGE_SIZE area.
> Enforce that in vmemmap_can_optimize() function.
> 
> Architectures like powerpc also want to enable vmemmap optimization
> conditionally (only with radix MMU translation). Hence allow architecture
> override.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>

Why renaming vmemmap_can_optimize() to __vmemmap_can_optimize() and keep 
it when vmemmap_can_optimize() has been override ? Is that because you 
expect overriding version of vmemmap_can_optimize() to call 
__vmemmap_can_optimize() ?

> ---
>   include/linux/mm.h | 27 +++++++++++++++++++++++----
>   mm/mm_init.c       |  2 +-
>   2 files changed, 24 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 2dd73e4f3d8e..1a2234ee14d2 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3639,13 +3639,32 @@ void vmemmap_free(unsigned long start, unsigned long end,
>   		struct vmem_altmap *altmap);
>   #endif
>   
> +#define VMEMMAP_RESERVE_NR	2
>   #ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
> -static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
> -					   struct dev_pagemap *pgmap)
> +static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
> +					  struct dev_pagemap *pgmap)
>   {
> -	return is_power_of_2(sizeof(struct page)) &&
> -		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
> +	unsigned long nr_pages;
> +	unsigned long nr_vmemmap_pages;
> +
> +	if (!pgmap || !is_power_of_2(sizeof(struct page)))
> +		return false;
> +
> +	nr_pages = pgmap_vmemmap_nr(pgmap);
> +	nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT);
> +	/*
> +	 * For vmemmap optimization with DAX we need minimum 2 vmemmap
> +	 * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
> +	 */
> +	return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
>   }
> +/*
> + * If we don't have an architecture override, use the generic rule
> + */
> +#ifndef vmemmap_can_optimize
> +#define vmemmap_can_optimize __vmemmap_can_optimize
> +#endif
> +
>   #else
>   static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
>   					   struct dev_pagemap *pgmap)
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index a1963c3322af..245ac69b66a5 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -1020,7 +1020,7 @@ static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
>   	if (!vmemmap_can_optimize(altmap, pgmap))
>   		return pgmap_vmemmap_nr(pgmap);
>   
> -	return 2 * (PAGE_SIZE / sizeof(struct page));
> +	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
>   }
>   
>   static void __ref memmap_init_compound(struct page *head,
Aneesh Kumar K.V July 11, 2023, 4:25 a.m. UTC | #2
Christophe Leroy <christophe.leroy@csgroup.eu> writes:

> Le 10/07/2023 à 18:08, Aneesh Kumar K.V a écrit :
>> dax vmemmap optimization requires a minimum of 2 PAGE_SIZE area within
>> vmemmap such that tail page mapping can point to the second PAGE_SIZE area.
>> Enforce that in vmemmap_can_optimize() function.
>> 
>> Architectures like powerpc also want to enable vmemmap optimization
>> conditionally (only with radix MMU translation). Hence allow architecture
>> override.
>> 
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>
> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
>
> Why renaming vmemmap_can_optimize() to __vmemmap_can_optimize() and keep 
> it when vmemmap_can_optimize() has been override ? Is that because you 
> expect overriding version of vmemmap_can_optimize() to call 
> __vmemmap_can_optimize() ?
>

Yes, __vmemap_can_optimize will be used in patch 11
https://lore.kernel.org/linuxppc-dev/20230710160842.56300-12-aneesh.kumar@linux.ibm.com

-aneesh
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2dd73e4f3d8e..1a2234ee14d2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3639,13 +3639,32 @@  void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
+#define VMEMMAP_RESERVE_NR	2
 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
-static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
-					   struct dev_pagemap *pgmap)
+static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
+					  struct dev_pagemap *pgmap)
 {
-	return is_power_of_2(sizeof(struct page)) &&
-		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
+	unsigned long nr_pages;
+	unsigned long nr_vmemmap_pages;
+
+	if (!pgmap || !is_power_of_2(sizeof(struct page)))
+		return false;
+
+	nr_pages = pgmap_vmemmap_nr(pgmap);
+	nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT);
+	/*
+	 * For vmemmap optimization with DAX we need minimum 2 vmemmap
+	 * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
+	 */
+	return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
 }
+/*
+ * If we don't have an architecture override, use the generic rule
+ */
+#ifndef vmemmap_can_optimize
+#define vmemmap_can_optimize __vmemmap_can_optimize
+#endif
+
 #else
 static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
 					   struct dev_pagemap *pgmap)
diff --git a/mm/mm_init.c b/mm/mm_init.c
index a1963c3322af..245ac69b66a5 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1020,7 +1020,7 @@  static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
 	if (!vmemmap_can_optimize(altmap, pgmap))
 		return pgmap_vmemmap_nr(pgmap);
 
-	return 2 * (PAGE_SIZE / sizeof(struct page));
+	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
 }
 
 static void __ref memmap_init_compound(struct page *head,