diff options
| -rw-r--r-- | Documentation/ABI/testing/sysfs-kernel-mm-numa | 24 | ||||
| -rw-r--r-- | include/linux/mempolicy.h | 4 | ||||
| -rw-r--r-- | mm/mempolicy.c | 61 | ||||
| -rw-r--r-- | mm/vmscan.c | 5 |
4 files changed, 92 insertions, 2 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-numa b/Documentation/ABI/testing/sysfs-kernel-mm-numa new file mode 100644 index 000000000000..77e559d4ed80 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-numa @@ -0,0 +1,24 @@ +What: /sys/kernel/mm/numa/ +Date: June 2021 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Interface for NUMA + +What: /sys/kernel/mm/numa/demotion_enabled +Date: June 2021 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Enable/disable demoting pages during reclaim + + Page migration during reclaim is intended for systems + with tiered memory configurations. These systems have + multiple types of memory with varied performance + characteristics instead of plain NUMA systems where + the same kind of memory is found at varied distances. + Allowing page migration during reclaim enables these + systems to migrate pages from fast tiers to slow tiers + when the fast tier is under pressure. This migration + is performed before swap. It may move data to a NUMA + node that does not fall into the cpuset of the + allocating process which might be construed to violate + the guarantees of cpusets. This should not be enabled + on systems which need strict cpuset location + guarantees. diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0aaf91b496e2..4ca025e2a77e 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -184,6 +184,8 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); +extern bool numa_demotion_enabled; + #else struct mempolicy {}; @@ -292,5 +294,7 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { return NULL; } + +#define numa_demotion_enabled false #endif /* CONFIG_NUMA */ #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 939eabcaf488..e675bfb856da 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -3021,3 +3021,64 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } + +bool numa_demotion_enabled = false; + +#ifdef CONFIG_SYSFS +static ssize_t numa_demotion_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", + numa_demotion_enabled? "true" : "false"); +} + +static ssize_t numa_demotion_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + numa_demotion_enabled = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + numa_demotion_enabled = false; + else + return -EINVAL; + + return count; +} + +static struct kobj_attribute numa_demotion_enabled_attr = + __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, + numa_demotion_enabled_store); + +static struct attribute *numa_attrs[] = { + &numa_demotion_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group numa_attr_group = { + .attrs = numa_attrs, +}; + +static int __init numa_init_sysfs(void) +{ + int err; + struct kobject *numa_kobj; + + numa_kobj = kobject_create_and_add("numa", mm_kobj); + if (!numa_kobj) { + pr_err("failed to create numa kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(numa_kobj, &numa_attr_group); + if (err) { + pr_err("failed to register numa group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(numa_kobj); + return err; +} +subsys_initcall(numa_init_sysfs); +#endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 43289f5f8488..2255025f1891 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -524,6 +524,8 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, static bool can_demote(int nid, struct scan_control *sc) { + if (!numa_demotion_enabled) + return false; if (sc) { if (sc->no_demotion) return false; @@ -534,8 +536,7 @@ static bool can_demote(int nid, struct scan_control *sc) if (next_demotion_node(nid) == NUMA_NO_NODE) return false; - // FIXME: actually enable this later in the series - return false; + return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, |