Re: [PATCH v3 2/3] memory tiering: introduce folio_use_access_time() check

[Kefeng Wang]

On 2024/7/24 21:01, Zi Yan wrote:
> If memory tiering mode is on and a folio is not in the top tier memory,
> folio's cpupid field is repurposed to store page access time. Instead of
> an open coded check, use a function to encapsulate the check.
>
> Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
> Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
> Acked-by: David Hildenbrand <david@xxxxxxxxxx>

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

> ---
>   include/linux/mm.h  |  6 ++++++
>   kernel/sched/fair.c |  3 +--
>   mm/huge_memory.c    |  6 ++----
>   mm/memory-tiers.c   | 19 +++++++++++++++++++
>   mm/memory.c         |  3 +--
>   mm/mprotect.c       |  3 +--
>   6 files changed, 30 insertions(+), 10 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 17753a463e01..2c6ccf088c7b 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1717,6 +1717,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
>   		__set_bit(pid_bit, &vma->numab_state->pids_active[1]);
>   	}
>   }
> +
> +bool folio_use_access_time(struct folio *folio);
>   #else /* !CONFIG_NUMA_BALANCING */
>   static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
>   {
> @@ -1770,6 +1772,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
>   static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
>   {
>   }
> +static inline bool folio_use_access_time(struct folio *folio)
> +{
> +	return false;
> +}
>   #endif /* CONFIG_NUMA_BALANCING */
>   
>   #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 9057584ec06d..416e29b56cc4 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_use_access_time(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 15234b2e252e..5c0a6a4e3a6e 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1707,8 +1707,7 @@ 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_use_access_time(folio))
>   		last_cpupid = folio_last_cpupid(folio);
>   	target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
>   	if (target_nid == NUMA_NO_NODE)
> @@ -2061,8 +2060,7 @@ 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_use_access_time(folio))
>   			folio_xchg_access_time(folio,
>   					       jiffies_to_msecs(jiffies));
>   	}
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 4775b3a3dabe..2a642ea86cb2 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 +51,24 @@ static const struct bus_type memory_tier_subsys = {
>   	.dev_name = "memory_tier",
>   };
>   
> +#ifdef CONFIG_NUMA_BALANCING
> +/**
> + * folio_use_access_time - check if a folio reuses cpupid for page access time
> + * @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 to record page access time
> + */
> +bool folio_use_access_time(struct folio *folio)
> +{
> +	return (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
> +	       !node_is_toptier(folio_nid(folio));
> +}
> +#endif
> +
>   #ifdef CONFIG_MIGRATION
>   static int top_tier_adistance;
>   /*
> diff --git a/mm/memory.c b/mm/memory.c
> index 802d0d8a40f9..833d2cad6eb2 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -5337,8 +5337,7 @@ 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_use_access_time(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..37cf8d249405 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_use_access_time(folio))
>   					folio_xchg_access_time(folio,
>   						jiffies_to_msecs(jiffies));
>   			}