diff mbox series

[v2,04/14] mm: handle hashdist initialization in mm/mm_init.c

Message ID 20230321170513.2401534-5-rppt@kernel.org
State New
Headers
Series mm: move core MM initialization to mm/mm_init.c |

Commit Message

Mike Rapoport March 21, 2023, 5:05 p.m. UTC 
  From: "Mike Rapoport (IBM)" <rppt@kernel.org>

The hashdist variable must be initialized before the first call to
alloc_large_system_hash() and free_area_init() looks like a better place
for it than page_alloc_init().

Move hashdist handling to mm/mm_init.c

Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
---
 mm/mm_init.c    | 22 ++++++++++++++++++++++
 mm/page_alloc.c | 18 ------------------
 2 files changed, 22 insertions(+), 18 deletions(-)

Comments

Vlastimil Babka March 22, 2023, 2:49 p.m. UTC | #1 
On 3/21/23 18:05, Mike Rapoport wrote:
> From: "Mike Rapoport (IBM)" <rppt@kernel.org>
> 
> The hashdist variable must be initialized before the first call to
> alloc_large_system_hash() and free_area_init() looks like a better place
> for it than page_alloc_init().
> 
> Move hashdist handling to mm/mm_init.c
> 
> Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
> Acked-by: David Hildenbrand <david@redhat.com>

Reviewed-by: Vlastimil Babka <vbabka@suse.cz>

Looks like this will move the fixup_hashdist() call earlier, but can't
result in seeing less N_MEMORY nodes than before, right?
I wonder if the whole thing lacks hotplug support anyway, what if system
boots with one node and more are added later? Hmm.

> ---
>  mm/mm_init.c    | 22 ++++++++++++++++++++++
>  mm/page_alloc.c | 18 ------------------
>  2 files changed, 22 insertions(+), 18 deletions(-)
> 
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index 68d0187c7886..2e60c7186132 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -607,6 +607,25 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
>  
>  	return nid;
>  }
> +
> +int hashdist = HASHDIST_DEFAULT;
> +
> +static int __init set_hashdist(char *str)
> +{
> +	if (!str)
> +		return 0;
> +	hashdist = simple_strtoul(str, &str, 0);
> +	return 1;
> +}
> +__setup("hashdist=", set_hashdist);
> +
> +static inline void fixup_hashdist(void)
> +{
> +	if (num_node_state(N_MEMORY) == 1)
> +		hashdist = 0;
> +}
> +#else
> +static inline void fixup_hashdist(void) {}
>  #endif /* CONFIG_NUMA */
>  
>  #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> @@ -1855,6 +1874,9 @@ void __init free_area_init(unsigned long *max_zone_pfn)
>  	}
>  
>  	memmap_init();
> +
> +	/* disable hash distribution for systems with a single node */
> +	fixup_hashdist();
>  }
>  
>  /**
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index c56c147bdf27..ff6a2fff2880 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -6383,28 +6383,10 @@ static int page_alloc_cpu_online(unsigned int cpu)
>  	return 0;
>  }
>  
> -#ifdef CONFIG_NUMA
> -int hashdist = HASHDIST_DEFAULT;
> -
> -static int __init set_hashdist(char *str)
> -{
> -	if (!str)
> -		return 0;
> -	hashdist = simple_strtoul(str, &str, 0);
> -	return 1;
> -}
> -__setup("hashdist=", set_hashdist);
> -#endif
> -
>  void __init page_alloc_init(void)
>  {
>  	int ret;
>  
> -#ifdef CONFIG_NUMA
> -	if (num_node_state(N_MEMORY) == 1)
> -		hashdist = 0;
> -#endif
> -
>  	ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC,
>  					"mm/page_alloc:pcp",
>  					page_alloc_cpu_online,
Mike Rapoport March 22, 2023, 3 p.m. UTC | #2 
On Wed, Mar 22, 2023 at 03:49:24PM +0100, Vlastimil Babka wrote:
> On 3/21/23 18:05, Mike Rapoport wrote:
> > From: "Mike Rapoport (IBM)" <rppt@kernel.org>
> > 
> > The hashdist variable must be initialized before the first call to
> > alloc_large_system_hash() and free_area_init() looks like a better place
> > for it than page_alloc_init().
> > 
> > Move hashdist handling to mm/mm_init.c
> > 
> > Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
> > Acked-by: David Hildenbrand <david@redhat.com>
> 
> Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
> 
> Looks like this will move the fixup_hashdist() call earlier, but can't
> result in seeing less N_MEMORY nodes than before, right?

hashdist must be set before the first call to alloc_large_system_hash() and
after the nodes present at boot time are initialized, so setting it in the
end of free_area_init() is Ok.

> I wonder if the whole thing lacks hotplug support anyway, what if system
> boots with one node and more are added later? Hmm.

alloc_large_system_hash() is called really early even for !HASH_EARLY
cases. Not sure it's feasible to redistribute the hashes allocated with it
when new node is added.
 
> > ---
> >  mm/mm_init.c    | 22 ++++++++++++++++++++++
> >  mm/page_alloc.c | 18 ------------------
> >  2 files changed, 22 insertions(+), 18 deletions(-)
> > 
> > diff --git a/mm/mm_init.c b/mm/mm_init.c
> > index 68d0187c7886..2e60c7186132 100644
> > --- a/mm/mm_init.c
> > +++ b/mm/mm_init.c
> > @@ -607,6 +607,25 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
> >  
> >  	return nid;
> >  }
> > +
> > +int hashdist = HASHDIST_DEFAULT;
> > +
> > +static int __init set_hashdist(char *str)
> > +{
> > +	if (!str)
> > +		return 0;
> > +	hashdist = simple_strtoul(str, &str, 0);
> > +	return 1;
> > +}
> > +__setup("hashdist=", set_hashdist);
> > +
> > +static inline void fixup_hashdist(void)
> > +{
> > +	if (num_node_state(N_MEMORY) == 1)
> > +		hashdist = 0;
> > +}
> > +#else
> > +static inline void fixup_hashdist(void) {}
> >  #endif /* CONFIG_NUMA */
> >  
> >  #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> > @@ -1855,6 +1874,9 @@ void __init free_area_init(unsigned long *max_zone_pfn)
> >  	}
> >  
> >  	memmap_init();
> > +
> > +	/* disable hash distribution for systems with a single node */
> > +	fixup_hashdist();
> >  }
> >  
> >  /**
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index c56c147bdf27..ff6a2fff2880 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -6383,28 +6383,10 @@ static int page_alloc_cpu_online(unsigned int cpu)
> >  	return 0;
> >  }
> >  
> > -#ifdef CONFIG_NUMA
> > -int hashdist = HASHDIST_DEFAULT;
> > -
> > -static int __init set_hashdist(char *str)
> > -{
> > -	if (!str)
> > -		return 0;
> > -	hashdist = simple_strtoul(str, &str, 0);
> > -	return 1;
> > -}
> > -__setup("hashdist=", set_hashdist);
> > -#endif
> > -
> >  void __init page_alloc_init(void)
> >  {
> >  	int ret;
> >  
> > -#ifdef CONFIG_NUMA
> > -	if (num_node_state(N_MEMORY) == 1)
> > -		hashdist = 0;
> > -#endif
> > -
> >  	ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC,
> >  					"mm/page_alloc:pcp",
> >  					page_alloc_cpu_online,
>
diff mbox series

Patch

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 68d0187c7886..2e60c7186132 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -607,6 +607,25 @@  int __meminit early_pfn_to_nid(unsigned long pfn)
 
 	return nid;
 }
+
+int hashdist = HASHDIST_DEFAULT;
+
+static int __init set_hashdist(char *str)
+{
+	if (!str)
+		return 0;
+	hashdist = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("hashdist=", set_hashdist);
+
+static inline void fixup_hashdist(void)
+{
+	if (num_node_state(N_MEMORY) == 1)
+		hashdist = 0;
+}
+#else
+static inline void fixup_hashdist(void) {}
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1855,6 +1874,9 @@  void __init free_area_init(unsigned long *max_zone_pfn)
 	}
 
 	memmap_init();
+
+	/* disable hash distribution for systems with a single node */
+	fixup_hashdist();
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c56c147bdf27..ff6a2fff2880 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6383,28 +6383,10 @@  static int page_alloc_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_NUMA
-int hashdist = HASHDIST_DEFAULT;
-
-static int __init set_hashdist(char *str)
-{
-	if (!str)
-		return 0;
-	hashdist = simple_strtoul(str, &str, 0);
-	return 1;
-}
-__setup("hashdist=", set_hashdist);
-#endif
-
 void __init page_alloc_init(void)
 {
 	int ret;
 
-#ifdef CONFIG_NUMA
-	if (num_node_state(N_MEMORY) == 1)
-		hashdist = 0;
-#endif
-
 	ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC,
 					"mm/page_alloc:pcp",
 					page_alloc_cpu_online,