static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { int ret; bool found_slot = false; struct memory_tier *memtier, *new_memtier; int adistance = memtype->adistance; unsigned int memtier_adistance_chunk_size = MEMTIER_CHUNK_SIZE; lockdep_assert_held_once(&memory_tier_lock); adistance = round_down(adistance, memtier_adistance_chunk_size); /* * If the memtype is already part of a memory tier, * just return that. */ if (!list_empty(&memtype->tier_sibiling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; } WARN_ON(1); return ERR_PTR(-EINVAL); } list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) { goto link_memtype; } else if (adistance < memtier->adistance_start) { found_slot = true; break; } } new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL); if (!new_memtier) return ERR_PTR(-ENOMEM); new_memtier->adistance_start = adistance; INIT_LIST_HEAD(&new_memtier->list); INIT_LIST_HEAD(&new_memtier->memory_types); if (found_slot) list_add_tail(&new_memtier->list, &memtier->list); else list_add_tail(&new_memtier->list, &memory_tiers); new_memtier->dev.id = adistance >> MEMTIER_CHUNK_BITS; new_memtier->dev.bus = &memory_tier_subsys; new_memtier->dev.release = memory_tier_device_release; new_memtier->dev.groups = memtier_dev_groups; ret = device_register(&new_memtier->dev); if (ret) { list_del(&new_memtier->list); put_device(&new_memtier->dev); return ERR_PTR(ret); } memtier = new_memtier; link_memtype: list_add(&memtype->tier_sibiling, &memtier->memory_types); return memtier; }

static void establish_demotion_targets(void) { struct memory_tier *memtier; struct demotion_nodes *nd; int target = NUMA_NO_NODE, node; int distance, best_distance; nodemask_t tier_nodes, lower_tier; lockdep_assert_held_once(&memory_tier_lock); if (!node_demotion) return; disable_all_demotion_targets(); for_each_node_state(node, N_MEMORY) { best_distance = -1; nd = &node_demotion[node]; memtier = __node_get_memory_tier(node); if (!memtier || list_is_last(&memtier->list, &memory_tiers)) continue; /* * Get the lower memtier to find the demotion node list. */ memtier = list_next_entry(memtier, list); tier_nodes = get_memtier_nodemask(memtier); /* * find_next_best_node, use 'used' nodemask as a skip list. * Add all memory nodes except the selected memory tier * nodelist to skip list so that we find the best node from the * memtier nodelist. */ nodes_andnot(tier_nodes, node_states[N_MEMORY], tier_nodes); /* * Find all the nodes in the memory tier node list of same best distance. * add them to the preferred mask. We randomly select between nodes * in the preferred mask when allocating pages during demotion. */ do { target = find_next_best_node(node, &tier_nodes); if (target == NUMA_NO_NODE) break; distance = node_distance(node, target); if (distance == best_distance || best_distance == -1) { best_distance = distance; node_set(target, nd->preferred); } else { break; } } while (1); } /* * Promotion is allowed from a memory tier to higher * memory tier only if the memory tier doesn't include * compute. We want to skip promotion from a memory tier, * if any node that is part of the memory tier have CPUs. * Once we detect such a memory tier, we consider that tier * as top tiper from which promotion is not allowed. */ list_for_each_entry_reverse(memtier, &memory_tiers, list) { tier_nodes = get_memtier_nodemask(memtier); nodes_and(tier_nodes, node_states[N_CPU], tier_nodes); if (!nodes_empty(tier_nodes)) { /* * abstract distance below the max value of this memtier * is considered toptier. */ top_tier_adistance = memtier->adistance_start + MEMTIER_CHUNK_SIZE - 1; break; } } /* * Now build the lower_tier mask for each node collecting node mask from * all memory tier below it. This allows us to fallback demotion page * allocation to a set of nodes that is closer the above selected * perferred node. */ lower_tier = node_states[N_MEMORY]; list_for_each_entry(memtier, &memory_tiers, list) { /* * Keep removing current tier from lower_tier nodes, * This will remove all nodes in current and above * memory tier from the lower_tier mask. */ tier_nodes = get_memtier_nodemask(memtier); nodes_andnot(lower_tier, lower_tier, tier_nodes); memtier->lower_tier_mask = lower_tier; } }

enum get_ksm_page_flags { GET_KSM_PAGE_NOLOCK, GET_KSM_PAGE_LOCK, GET_KSM_PAGE_TRYLOCK };

static struct page *get_ksm_page(struct ksm_stable_node *stable_node, enum get_ksm_page_flags flags) { struct page *page; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ page = pfn_to_page(kpfn); if (READ_ONCE(page->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * the same is in reuse_ksm_page() case; but if page is swapcache * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ while (!get_page_unless_zero(page)) { /* * Another check for page->mapping != expected_mapping would * work here too. We have chosen the !PageSwapCache test to * optimize the common case, when the page is or is about to * be freed: PageSwapCache is cleared (under spin_lock_irq) * in the ref_freeze section of __remove_mapping(); but Anon * page->mapping reset to NULL later, in free_pages_prepare(). */ if (!PageSwapCache(page)) goto stale; cpu_relax(); } if (READ_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } if (flags == GET_KSM_PAGE_TRYLOCK) { if (!trylock_page(page)) { put_page(page); return ERR_PTR(-EBUSY); } } else if (flags == GET_KSM_PAGE_LOCK) lock_page(page); if (flags != GET_KSM_PAGE_NOLOCK) { if (READ_ONCE(page->mapping) != expected_mapping) { unlock_page(page); put_page(page); goto stale; } } return page; stale: /* * We come here from above when page->mapping or !PageSwapCache * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; }

struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct folio *folio = page_folio(page); struct anon_vma *anon_vma = folio_anon_vma(folio); struct page *new_page; if (PageKsm(page)) { if (page_stable_node(page) && !(ksm_run & KSM_RUN_UNMERGE)) return page; /* no need to copy it */ } else if (!anon_vma) { return page; /* no need to copy it */ } else if (page->index == linear_page_index(vma, address) && anon_vma->root == vma->anon_vma->root) { return page; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); if (!PageUptodate(page)) return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page && mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { put_page(new_page); new_page = NULL; } if (new_page) { if (copy_mc_user_highpage(new_page, page, address, vma)) { put_page(new_page); memory_failure_queue(page_to_pfn(page), 0); return ERR_PTR(-EHWPOISON); } SetPageDirty(new_page); __SetPageUptodate(new_page); __SetPageLocked(new_page); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } return new_page; }

static struct page *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) { err = try_to_merge_with_ksm_page(tree_rmap_item, tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it. */ if (err) break_cow(rmap_item); } return err ? NULL : page; }

static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), rmap_item, mm, err); return err; }

static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); }

static unsigned int ksm_thread_sleep_millisecs = 20;

static unsigned int ksm_thread_pages_to_scan = 100;

static int ksm_max_page_sharing = 256;

static unsigned int ksm_stable_node_chains_prune_millisecs = 2000;