diff options
| -rw-r--r-- | include/linux/mm.h | 25 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 1 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 99 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 1 | ||||
| -rw-r--r-- | mm/huge_memory.c | 17 | ||||
| -rw-r--r-- | mm/memory.c | 11 | ||||
| -rw-r--r-- | mm/migrate.c | 12 | ||||
| -rw-r--r-- | mm/mprotect.c | 8 |
8 files changed, 169 insertions, 5 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 21f8b27bd9fd..27839b158ca4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1255,6 +1255,18 @@ static inline int folio_nid(const struct folio *folio) } #ifdef CONFIG_NUMA_BALANCING +/* page access time bits needs to hold at least 4 seconds */ +#define PAGE_ACCESS_TIME_MIN_BITS 12 +#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS +#define PAGE_ACCESS_TIME_BUCKETS \ + (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) +#else +#define PAGE_ACCESS_TIME_BUCKETS 0 +#endif + +#define PAGE_ACCESS_TIME_MASK \ + (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) + static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); @@ -1318,12 +1330,25 @@ static inline void page_cpupid_reset_last(struct page *page) page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ + +static inline int xchg_page_access_time(struct page *page, int time) +{ + int last_time; + + last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + return last_time << PAGE_ACCESS_TIME_BUCKETS; +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } +static inline int xchg_page_access_time(struct page *page, int time) +{ + return 0; +} + static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index bb3d63bdf4ae..ad63dbfc54f1 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -333,6 +333,7 @@ static __init int sched_init_debug(void) debugfs_create_u32("scan_period_min_ms", 0644, numa, &sysctl_numa_balancing_scan_period_min); debugfs_create_u32("scan_period_max_ms", 0644, numa, &sysctl_numa_balancing_scan_period_max); debugfs_create_u32("scan_size_mb", 0644, numa, &sysctl_numa_balancing_scan_size); + debugfs_create_u32("hot_threshold_ms", 0644, numa, &sysctl_numa_balancing_hot_threshold); #endif debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 914096c5b1ae..06db566c7660 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1094,6 +1094,9 @@ unsigned int sysctl_numa_balancing_scan_size = 256; /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ unsigned int sysctl_numa_balancing_scan_delay = 1000; +/* The page with hint page fault latency < threshold in ms is considered hot */ +unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC; + struct numa_group { refcount_t refcount; @@ -1436,6 +1439,68 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, return 1000 * faults / total_faults; } +/* + * If memory tiering mode is enabled, cpupid of slow memory page is + * used to record scan time instead of CPU and PID. When tiering mode + * is disabled at run time, the scan time (in cpupid) will be + * interpreted as CPU and PID. So CPU needs to be checked to avoid to + * access out of array bound. + */ +static inline bool cpupid_valid(int cpupid) +{ + return cpupid_to_cpu(cpupid) < nr_cpu_ids; +} + +/* + * For memory tiering mode, if there are enough free pages (more than + * enough watermark defined here) in fast memory node, to take full + * advantage of fast memory capacity, all recently accessed slow + * memory pages will be migrated to fast memory node without + * considering hot threshold. + */ +static bool pgdat_free_space_enough(struct pglist_data *pgdat) +{ + int z; + unsigned long enough_wmark; + + enough_wmark = max(1UL * 1024 * 1024 * 1024 >> PAGE_SHIFT, + pgdat->node_present_pages >> 4); + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + if (zone_watermark_ok(zone, 0, + wmark_pages(zone, WMARK_PROMO) + enough_wmark, + ZONE_MOVABLE, 0)) + return true; + } + return false; +} + +/* + * For memory tiering mode, when page tables are scanned, the scan + * time will be recorded in struct page in addition to make page + * PROT_NONE for slow memory page. So when the page is accessed, in + * hint page fault handler, the hint page fault latency is calculated + * via, + * + * hint page fault latency = hint page fault time - scan time + * + * The smaller the hint page fault latency, the higher the possibility + * for the page to be hot. + */ +static int numa_hint_fault_latency(struct page *page) +{ + int last_time, time; + + time = jiffies_to_msecs(jiffies); + last_time = xchg_page_access_time(page, time); + + return (time - last_time) & PAGE_ACCESS_TIME_MASK; +} + bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { @@ -1443,9 +1508,34 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; + /* + * 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)) { + struct pglist_data *pgdat; + unsigned long latency, th; + + pgdat = NODE_DATA(dst_nid); + if (pgdat_free_space_enough(pgdat)) + return true; + + th = sysctl_numa_balancing_hot_threshold; + latency = numa_hint_fault_latency(page); + if (latency >= th) + return false; + + return true; + } + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && + !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid)) + return false; + /* * Allow first faults or private faults to migrate immediately early in * the lifetime of a task. The magic number 4 is based on waiting for @@ -2685,6 +2775,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (!p->mm) return; + /* + * NUMA faults statistics are unnecessary for the slow memory + * node for memory tiering mode. + */ + if (!node_is_toptier(mem_node) && + (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING || + !cpupid_valid(last_cpupid))) + return; + /* Allocate buffer to track faults on a per-node basis */ if (unlikely(!p->numa_faults)) { int size = sizeof(*p->numa_faults) * diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index e26688d387ae..8e914e85ba8e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2452,6 +2452,7 @@ extern unsigned int sysctl_numa_balancing_scan_delay; extern unsigned int sysctl_numa_balancing_scan_period_min; extern unsigned int sysctl_numa_balancing_scan_period_max; extern unsigned int sysctl_numa_balancing_scan_size; +extern unsigned int sysctl_numa_balancing_hot_threshold; #endif #ifdef CONFIG_SCHED_HRTICK diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3222b40a0f6d..37105d9aa4d2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1477,7 +1477,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; int page_nid = NUMA_NO_NODE; - int target_nid, last_cpupid = -1; + int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); bool migrated = false; bool was_writable = pmd_savedwrite(oldpmd); int flags = 0; @@ -1498,7 +1498,12 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) flags |= TNF_NO_GROUP; page_nid = page_to_nid(page); - last_cpupid = page_cpupid_last(page); + /* + * For memory tiering mode, cpupid of slow memory page is used + * to record page access time. So use default value. + */ + if (node_is_toptier(page_nid)) + last_cpupid = page_cpupid_last(page); target_nid = numa_migrate_prep(page, vma, haddr, page_nid, &flags); @@ -1822,6 +1827,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (prot_numa) { struct page *page; + bool toptier; /* * Avoid trapping faults against the zero page. The read-only * data is likely to be read-cached on the local CPU and @@ -1834,13 +1840,18 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, goto unlock; page = pmd_page(*pmd); + toptier = node_is_toptier(page_to_nid(page)); /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && - node_is_toptier(page_to_nid(page))) + toptier) goto unlock; + + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && + !toptier) + xchg_page_access_time(page, jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical diff --git a/mm/memory.c b/mm/memory.c index bd8e7e79be99..b994784158f5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -74,6 +74,7 @@ #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> +#include <linux/sched/sysctl.h> #include <trace/events/kmem.h> @@ -4725,8 +4726,16 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; - last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); + /* + * 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(page_nid)) + last_cpupid = (-1 & LAST_CPUPID_MASK); + else + last_cpupid = page_cpupid_last(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); if (target_nid == NUMA_NO_NODE) { diff --git a/mm/migrate.c b/mm/migrate.c index 581dfaad9257..ce6a58f3b21f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -560,6 +560,18 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) * future migrations of this same page. */ cpupid = page_cpupid_xchg_last(&folio->page, -1); + /* + * For memory tiering mode, when migrate between slow and fast + * memory node, reset cpupid, because that is used to record + * page access time in slow memory node. + */ + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) { + bool f_toptier = node_is_toptier(page_to_nid(&folio->page)); + bool t_toptier = node_is_toptier(page_to_nid(&newfolio->page)); + + if (f_toptier != t_toptier) + cpupid = -1; + } page_cpupid_xchg_last(&newfolio->page, cpupid); folio_migrate_ksm(newfolio, folio); diff --git a/mm/mprotect.c b/mm/mprotect.c index bc6bddd156ca..ed013f836b4a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -121,6 +121,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, if (prot_numa) { struct page *page; int nid; + bool toptier; /* Avoid TLB flush if possible */ if (pte_protnone(oldpte)) @@ -150,14 +151,19 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, nid = page_to_nid(page); if (target_node == nid) continue; + toptier = node_is_toptier(nid); /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && - node_is_toptier(nid)) + toptier) continue; + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && + !toptier) + xchg_page_access_time(page, + jiffies_to_msecs(jiffies)); } oldpte = ptep_modify_prot_start(vma, addr, pte); |