Re: [RFC PATCH 2/3] memory tiering: introduce folio_has_cpupid() check

[Huang, Ying]

Zi Yan <zi.yan@xxxxxxxx> writes:

> From: Zi Yan <ziy@xxxxxxxxxx>
>
> Instead of open coded check for if memory tiering mode is on and a folio
> is in the top tier memory, use a function to encapsulate the check.
>
> Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>

LGTM, Thanks!  Feel free to add

Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>

in your future versions.

> ---
>  include/linux/memory-tiers.h |  8 ++++++++
>  kernel/sched/fair.c          |  3 +--
>  mm/huge_memory.c             |  6 ++----
>  mm/memory-tiers.c            | 17 +++++++++++++++++
>  mm/memory.c                  |  3 +--
>  mm/mprotect.c                |  3 +--
>  6 files changed, 30 insertions(+), 10 deletions(-)
>
> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
> index 0dc0cf2863e2..10c127d461c4 100644
> --- a/include/linux/memory-tiers.h
> +++ b/include/linux/memory-tiers.h
> @@ -73,6 +73,10 @@ static inline bool node_is_toptier(int node)
>  }
>  #endif
>  
> +
> +bool folio_has_cpupid(struct folio *folio);
> +
> +
>  #else
>  
>  #define numa_demotion_enabled	false
> @@ -151,5 +155,9 @@ static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist,
>  static inline void mt_put_memory_types(struct list_head *memory_types)
>  {
>  }
> +static inline bool folio_has_cpupid(struct folio *folio)
> +{
> +	return true;
> +}
>  #endif	/* CONFIG_NUMA */
>  #endif  /* _LINUX_MEMORY_TIERS_H */
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 8a5b1ae0aa55..03de808cb3cc 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1840,8 +1840,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
>  	 * The pages in slow memory node should be migrated according
>  	 * to hot/cold instead of private/shared.
>  	 */
> -	if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
> -	    !node_is_toptier(src_nid)) {
> +	if (!folio_has_cpupid(folio)) {
>  		struct pglist_data *pgdat;
>  		unsigned long rate_limit;
>  		unsigned int latency, th, def_th;
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 07d9dde4ca33..8c11d6da4b36 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1705,8 +1705,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
>  	 * For memory tiering mode, cpupid of slow memory page is used
>  	 * to record page access time.  So use default value.
>  	 */
> -	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) ||
> -	    node_is_toptier(nid))
> +	if (folio_has_cpupid(folio))
>  		last_cpupid = folio_last_cpupid(folio);
>  	target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
>  	if (target_nid == NUMA_NO_NODE)
> @@ -2059,8 +2058,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  		    toptier)
>  			goto unlock;
>  
> -		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
> -		    !toptier)
> +		if (!folio_has_cpupid(folio))
>  			folio_xchg_access_time(folio,
>  					       jiffies_to_msecs(jiffies));
>  	}
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 4775b3a3dabe..7f0360d4e3a0 100644
> --- a/mm/memory-tiers.c
> +++ b/mm/memory-tiers.c
> @@ -6,6 +6,7 @@
>  #include <linux/memory.h>
>  #include <linux/memory-tiers.h>
>  #include <linux/notifier.h>
> +#include <linux/sched/sysctl.h>
>  
>  #include "internal.h"
>  
> @@ -50,6 +51,22 @@ static const struct bus_type memory_tier_subsys = {
>  	.dev_name = "memory_tier",
>  };
>  
> +/**
> + * folio_has_cpupid - check if a folio has cpupid information
> + * @folio: folio to check
> + *
> + * folio's _last_cpupid field is repurposed by memory tiering. In memory
> + * tiering mode, cpupid of slow memory folio (not toptier memory) is used to
> + * record page access time.
> + *
> + * Return: the folio _last_cpupid is used as cpupid
> + */
> +bool folio_has_cpupid(struct folio *folio)
> +{
> +	return !(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) ||
> +	       node_is_toptier(folio_nid(folio));
> +}
> +
>  #ifdef CONFIG_MIGRATION
>  static int top_tier_adistance;
>  /*
> diff --git a/mm/memory.c b/mm/memory.c
> index dceb62f3fa34..96c2f5b3d796 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -5344,8 +5344,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
>  	 * For memory tiering mode, cpupid of slow memory page is used
>  	 * to record page access time.  So use default value.
>  	 */
> -	if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
> -	    !node_is_toptier(nid))
> +	if (!folio_has_cpupid(folio))
>  		last_cpupid = (-1 & LAST_CPUPID_MASK);
>  	else
>  		last_cpupid = folio_last_cpupid(folio);
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 222ab434da54..787c3c2bf1b6 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -161,8 +161,7 @@ static long change_pte_range(struct mmu_gather *tlb,
>  				if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
>  				    toptier)
>  					continue;
> -				if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
> -				    !toptier)
> +				if (!folio_has_cpupid(folio))
>  					folio_xchg_access_time(folio,
>  						jiffies_to_msecs(jiffies));
>  			}