diff options
Diffstat (limited to 'mm/mempolicy.c')
| -rw-r--r-- | mm/mempolicy.c | 721 |
1 files changed, 616 insertions, 105 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 10a590ee1c89..bbaadbeeb291 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -8,7 +8,7 @@ * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * - * Support four policies per VMA and per process: + * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * @@ -19,6 +19,13 @@ * for anonymous memory. For process policy an process counter * is used. * + * weighted interleave + * Allocate memory interleaved over a set of nodes based on + * a set of weights (per-node), with normal fallback if it + * fails. Otherwise operates the same as interleave. + * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated + * on node 0 for every 1 page allocated on node 1. + * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node @@ -131,6 +138,32 @@ static struct mempolicy default_policy = { static struct mempolicy preferred_node_policy[MAX_NUMNODES]; +/* + * iw_table is the sysfs-set interleave weight table, a value of 0 denotes + * system-default value should be used. A NULL iw_table also denotes that + * system-default values should be used. Until the system-default table + * is implemented, the system-default is always 1. + * + * iw_table is RCU protected + */ +static u8 __rcu *iw_table; +static DEFINE_MUTEX(iw_table_lock); + +static u8 get_il_weight(int node) +{ + u8 *table; + u8 weight; + + rcu_read_lock(); + table = rcu_dereference(iw_table); + /* if no iw_table, use system default */ + weight = table ? table[node] : 1; + /* if value in iw_table is 0, use system default */ + weight = weight ? weight : 1; + rcu_read_unlock(); + return weight; +} + /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search @@ -415,6 +448,10 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, + [MPOL_WEIGHTED_INTERLEAVE] = { + .create = mpol_new_nodemask, + .rebind = mpol_rebind_nodemask, + }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, @@ -472,8 +509,8 @@ static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) qp->nr_failed++; return; } - folio = pfn_folio(pmd_pfn(*pmd)); - if (is_huge_zero_page(&folio->page)) { + folio = pmd_folio(*pmd); + if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } @@ -587,7 +624,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); - entry = huge_ptep_get(pte); + entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; @@ -605,13 +642,12 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * - * To check if the folio is shared, ideally we want to make sure - * every page is mapped to the same process. Doing that is very - * expensive, so check the estimated sharers of the folio instead. + * See folio_likely_mapped_shared() on possible imprecision when we + * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || - (folio_estimated_sharers(folio) == 1 && !hugetlb_pmd_shared(pte))) - if (!isolate_hugetlb(folio, qp->pagelist)) + (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) + if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); @@ -640,8 +676,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); - if (nr_updated > 0) + if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); + count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); + } tlb_finish_mmu(&tlb); @@ -654,7 +692,6 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; - unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; /* range check first */ @@ -682,9 +719,6 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, !(flags & MPOL_MF_STRICT)) return 1; - if (endvma > end) - endvma = end; - /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. @@ -836,8 +870,11 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, old = current->mempolicy; current->mempolicy = new; - if (new && new->mode == MPOL_INTERLEAVE) + if (new && (new->mode == MPOL_INTERLEAVE || + new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; + current->il_weight = 0; + } task_unlock(current); mpol_put(old); ret = 0; @@ -862,6 +899,7 @@ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: + case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: @@ -946,6 +984,13 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); + } else if (pol == current->mempolicy && + pol->mode == MPOL_WEIGHTED_INTERLEAVE) { + if (current->il_weight) + *policy = current->il_prev; + else + *policy = next_node_in(current->il_prev, + pol->nodes); } else { err = -EINVAL; goto out; @@ -988,11 +1033,10 @@ static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * - * To check if the folio is shared, ideally we want to make sure - * every page is mapped to the same process. Doing that is very - * expensive, so check the estimated sharers of the folio instead. + * See folio_likely_mapped_shared() on possible imprecision when we + * cannot easily detect if a folio is shared. */ - if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) { + if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, @@ -1026,6 +1070,7 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest, struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + .reason = MR_SYSCALL, }; nodes_clear(nmask); @@ -1035,6 +1080,10 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest, mmap_read_lock(mm); vma = find_vma(mm, 0); + if (unlikely(!vma)) { + mmap_read_unlock(mm); + return 0; + } /* * This does not migrate the range, but isolates all pages that @@ -1168,7 +1217,6 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src, struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; - struct page *page; unsigned int order; int nid = numa_node_id(); gfp_t gfp; @@ -1183,7 +1231,8 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src, h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); - return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp); + return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, + htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) @@ -1191,8 +1240,7 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src, else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; - page = alloc_pages_mpol(gfp, order, pol, ilx, nid); - return page_rmappable_folio(page); + return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else @@ -1310,30 +1358,32 @@ static long do_mbind(unsigned long start, unsigned long len, * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ - if (new->mode == MPOL_INTERLEAVE) { - struct page *page; + if (new->mode == MPOL_INTERLEAVE || + new->mode == MPOL_WEIGHTED_INTERLEAVE) { + struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; - list_for_each_entry(page, &pagelist, lru) { - if (!PageKsm(page)) + list_for_each_entry(folio, &pagelist, lru) { + if (!folio_test_ksm(folio)) break; } - if (!list_entry_is_head(page, &pagelist, lru)) { + if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { - addr = page_address_in_vma(page, vma); + addr = page_address_in_vma(folio, + folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { - order = compound_order(page); + order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ - mmpol.ilx -= page->index >> order; + mmpol.ilx -= folio->index >> order; } } } @@ -1458,9 +1508,10 @@ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { - if (*mode != MPOL_BIND) + if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) + *flags |= (MPOL_F_MOF | MPOL_F_MORON); + else return -EINVAL; - *flags |= (MPOL_F_MOF | MPOL_F_MORON); } return 0; } @@ -1758,7 +1809,8 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving - * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE + * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or + * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. @@ -1775,7 +1827,8 @@ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); - if (pol->mode == MPOL_INTERLEAVE) { + if (pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } @@ -1825,12 +1878,40 @@ bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) return zone >= dynamic_policy_zone; } +static unsigned int weighted_interleave_nodes(struct mempolicy *policy) +{ + unsigned int node; + unsigned int cpuset_mems_cookie; + +retry: + /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ + cpuset_mems_cookie = read_mems_allowed_begin(); + node = current->il_prev; + if (!current->il_weight || !node_isset(node, policy->nodes)) { + node = next_node_in(node, policy->nodes); + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry; + if (node == MAX_NUMNODES) + return node; + current->il_prev = node; + current->il_weight = get_il_weight(node); + } + current->il_weight--; + return node; +} + /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; + unsigned int cpuset_mems_cookie; + + /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + nid = next_node_in(current->il_prev, policy->nodes); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); - nid = next_node_in(current->il_prev, policy->nodes); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; @@ -1859,6 +1940,9 @@ unsigned int mempolicy_slab_node(void) case MPOL_INTERLEAVE: return interleave_nodes(policy); + case MPOL_WEIGHTED_INTERLEAVE: + return weighted_interleave_nodes(policy); + case MPOL_BIND: case MPOL_PREFERRED_MANY: { @@ -1873,7 +1957,7 @@ unsigned int mempolicy_slab_node(void) zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); - return z->zone ? zone_to_nid(z->zone) : node; + return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; @@ -1883,6 +1967,59 @@ unsigned int mempolicy_slab_node(void) } } +static unsigned int read_once_policy_nodemask(struct mempolicy *pol, + nodemask_t *mask) +{ + /* + * barrier stabilizes the nodemask locally so that it can be iterated + * over safely without concern for changes. Allocators validate node + * selection does not violate mems_allowed, so this is safe. + */ + barrier(); + memcpy(mask, &pol->nodes, sizeof(nodemask_t)); + barrier(); + return nodes_weight(*mask); +} + +static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) +{ + nodemask_t nodemask; + unsigned int target, nr_nodes; + u8 *table; + unsigned int weight_total = 0; + u8 weight; + int nid; + + nr_nodes = read_once_policy_nodemask(pol, &nodemask); + if (!nr_nodes) + return numa_node_id(); + + rcu_read_lock(); + table = rcu_dereference(iw_table); + /* calculate the total weight */ + for_each_node_mask(nid, nodemask) { + /* detect system default usage */ + weight = table ? table[nid] : 1; + weight = weight ? weight : 1; + weight_total += weight; + } + + /* Calculate the node offset based on totals */ + target = ilx % weight_total; + nid = first_node(nodemask); + while (target) { + /* detect system default usage */ + weight = table ? table[nid] : 1; + weight = weight ? weight : 1; + if (target < weight) + break; + target -= weight; + nid = next_node_in(nid, nodemask); + } + rcu_read_unlock(); + return nid; +} + /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx @@ -1890,20 +2027,12 @@ unsigned int mempolicy_slab_node(void) */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { - nodemask_t nodemask = pol->nodes; + nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; - /* - * The barrier will stabilize the nodemask in a register or on - * the stack so that it will stop changing under the code. - * - * Between first_node() and next_node(), pol->nodes could be changed - * by other threads. So we put pol->nodes in a local stack. - */ - barrier(); - nnodes = nodes_weight(nodemask); + nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; @@ -1951,6 +2080,11 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; + case MPOL_WEIGHTED_INTERLEAVE: + *nid = (ilx == NO_INTERLEAVE_INDEX) ? + weighted_interleave_nodes(pol) : + weighted_interleave_nid(pol, ilx); + break; } return nodemask; @@ -2012,6 +2146,7 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; @@ -2070,9 +2205,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - page = __alloc_pages(preferred_gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) - page = __alloc_pages(gfp, order, nid, NULL); + page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } @@ -2087,7 +2222,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * * Return: The page on success or NULL if allocation fails. */ -struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; @@ -2112,13 +2247,15 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && + pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ - page = __alloc_pages_node(nid, - gfp | __GFP_THISNODE | __GFP_NORETRY, order); + page = __alloc_frozen_pages_noprof( + gfp | __GFP_THISNODE | __GFP_NORETRY, order, + nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* @@ -2130,9 +2267,10 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, } } - page = __alloc_pages(gfp, order, nid, nodemask); + page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); - if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { + if (unlikely(pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { @@ -2145,36 +2283,64 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, return page; } +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid) +{ + struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, + ilx, nid); + if (!page) + return NULL; + + set_page_refcounted(page); + return page_rmappable_folio(page); +} + /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. - * @hugepage: Unused (was: For hugepages try only preferred node if possible). * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and - * excepting where direct use of alloc_pages_mpol() is more appropriate. + * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, bool hugepage) +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; - struct page *page; + struct folio *folio; + + if (vma->vm_flags & VM_DROPPABLE) + gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); - page = alloc_pages_mpol(gfp | __GFP_COMP, order, - pol, ilx, numa_node_id()); + folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); - return page_rmappable_folio(page); + return folio; +} +EXPORT_SYMBOL(vma_alloc_folio_noprof); + +struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) +{ + struct mempolicy *pol = &default_policy; + + /* + * No reference counting needed for current->mempolicy + * nor system default_policy + */ + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, + numa_node_id()); } -EXPORT_SYMBOL(vma_alloc_folio); /** * alloc_pages - Allocate pages. @@ -2190,29 +2356,23 @@ EXPORT_SYMBOL(vma_alloc_folio); * flags are used. * Return: The page on success or NULL if allocation fails. */ -struct page *alloc_pages(gfp_t gfp, unsigned int order) +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { - struct mempolicy *pol = &default_policy; - - /* - * No reference counting needed for current->mempolicy - * nor system default_policy - */ - if (!in_interrupt() && !(gfp & __GFP_THISNODE)) - pol = get_task_policy(current); + struct page *page = alloc_frozen_pages_noprof(gfp, order); - return alloc_pages_mpol(gfp, order, - pol, NO_INTERLEAVE_INDEX, numa_node_id()); + if (page) + set_page_refcounted(page); + return page; } -EXPORT_SYMBOL(alloc_pages); +EXPORT_SYMBOL(alloc_pages_noprof); -struct folio *folio_alloc(gfp_t gfp, unsigned int order) +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { - return page_rmappable_folio(alloc_pages(gfp | __GFP_COMP, order)); + return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } -EXPORT_SYMBOL(folio_alloc); +EXPORT_SYMBOL(folio_alloc_noprof); -static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, +static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { @@ -2229,15 +2389,15 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, for (i = 0; i < nodes; i++) { if (delta) { - nr_allocated = __alloc_pages_bulk(gfp, + nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, - nr_pages_per_node + 1, NULL, + nr_pages_per_node + 1, page_array); delta--; } else { - nr_allocated = __alloc_pages_bulk(gfp, + nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, - nr_pages_per_node, NULL, page_array); + nr_pages_per_node, page_array); } page_array += nr_allocated; @@ -2247,7 +2407,122 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, return total_allocated; } -static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, +static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + struct task_struct *me = current; + unsigned int cpuset_mems_cookie; + unsigned long total_allocated = 0; + unsigned long nr_allocated = 0; + unsigned long rounds; + unsigned long node_pages, delta; + u8 *table, *weights, weight; + unsigned int weight_total = 0; + unsigned long rem_pages = nr_pages; + nodemask_t nodes; + int nnodes, node; + int resume_node = MAX_NUMNODES - 1; + u8 resume_weight = 0; + int prev_node; + int i; + + if (!nr_pages) + return 0; + + /* read the nodes onto the stack, retry if done during rebind */ + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + nnodes = read_once_policy_nodemask(pol, &nodes); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); + + /* if the nodemask has become invalid, we cannot do anything */ + if (!nnodes) + return 0; + + /* Continue allocating from most recent node and adjust the nr_pages */ + node = me->il_prev; + weight = me->il_weight; + if (weight && node_isset(node, nodes)) { + node_pages = min(rem_pages, weight); + nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, + page_array); + page_array += nr_allocated; + total_allocated += nr_allocated; + /* if that's all the pages, no need to interleave */ + if (rem_pages <= weight) { + me->il_weight -= rem_pages; + return total_allocated; + } + /* Otherwise we adjust remaining pages, continue from there */ + rem_pages -= weight; + } + /* clear active weight in case of an allocation failure */ + me->il_weight = 0; + prev_node = node; + + /* create a local copy of node weights to operate on outside rcu */ + weights = kzalloc(nr_node_ids, GFP_KERNEL); + if (!weights) + return total_allocated; + + rcu_read_lock(); + table = rcu_dereference(iw_table); + if (table) + memcpy(weights, table, nr_node_ids); + rcu_read_unlock(); + + /* calculate total, detect system default usage */ + for_each_node_mask(node, nodes) { + if (!weights[node]) + weights[node] = 1; + weight_total += weights[node]; + } + + /* + * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. + * Track which node weighted interleave should resume from. + * + * if (rounds > 0) and (delta == 0), resume_node will always be + * the node following prev_node and its weight. + */ + rounds = rem_pages / weight_total; + delta = rem_pages % weight_total; + resume_node = next_node_in(prev_node, nodes); + resume_weight = weights[resume_node]; + for (i = 0; i < nnodes; i++) { + node = next_node_in(prev_node, nodes); + weight = weights[node]; + node_pages = weight * rounds; + /* If a delta exists, add this node's portion of the delta */ + if (delta > weight) { + node_pages += weight; + delta -= weight; + } else if (delta) { + /* when delta is depleted, resume from that node */ + node_pages += delta; + resume_node = node; + resume_weight = weight - delta; + delta = 0; + } + /* node_pages can be 0 if an allocation fails and rounds == 0 */ + if (!node_pages) + break; + nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, + page_array); + page_array += nr_allocated; + total_allocated += nr_allocated; + if (total_allocated == nr_pages) + break; + prev_node = node; + } + me->il_prev = resume_node; + me->il_weight = resume_weight; + kfree(weights); + return total_allocated; +} + +static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { @@ -2257,12 +2532,12 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes, - nr_pages, NULL, page_array); + nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, + nr_pages, page_array); if (nr_allocated < nr_pages) - nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL, - nr_pages - nr_allocated, NULL, + nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, + nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } @@ -2273,7 +2548,7 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, * It can accelerate memory allocation especially interleaving * allocate memory. */ -unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, +unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; @@ -2284,17 +2559,21 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) - return alloc_pages_bulk_array_interleave(gfp, pol, + return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); + if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) + return alloc_pages_bulk_weighted_interleave( + gfp, pol, nr_pages, page_array); + if (pol->mode == MPOL_PREFERRED_MANY) - return alloc_pages_bulk_array_preferred_many(gfp, + return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); - return __alloc_pages_bulk(gfp, nid, nodemask, - nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, nodemask, + nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) @@ -2362,6 +2641,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: + case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; @@ -2467,7 +2747,7 @@ static void sp_free(struct sp_node *n) * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked - * @vma: vm area where folio mapped + * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's @@ -2477,18 +2757,24 @@ static void sp_free(struct sp_node *n) * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ -int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, +int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); + struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); - int thisnid = cpu_to_node(thiscpu); + int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; + /* + * Make sure ptl is held so that we don't preempt and we + * have a stable smp processor id + */ + lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; @@ -2498,6 +2784,10 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, polnid = interleave_nid(pol, ilx); break; + case MPOL_WEIGHTED_INTERLEAVE: + polnid = weighted_interleave_nid(pol, ilx); + break; + case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; @@ -2509,15 +2799,26 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, break; case MPOL_BIND: - /* Optimize placement among multiple nodes via NUMA balancing */ + case MPOL_PREFERRED_MANY: + /* + * Even though MPOL_PREFERRED_MANY can allocate pages outside + * policy nodemask we don't allow numa migration to nodes + * outside policy nodemask for now. This is done so that if we + * want demotion to slow memory to happen, before allocating + * from some DRAM node say 'x', we will end up using a + * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario + * we should not promote to node 'x' from slow memory node. + */ if (pol->flags & MPOL_F_MORON) { + /* + * Optimize placement among multiple nodes + * via NUMA balancing + */ if (node_isset(thisnid, pol->nodes)) break; goto out; } - fallthrough; - case MPOL_PREFERRED_MANY: /* * use current page if in policy nodemask, * else select nearest allowed node, if any. @@ -2526,10 +2827,10 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( - node_zonelist(numa_node_id(), GFP_HIGHUSER), + node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); - polnid = zone_to_nid(z->zone); + polnid = zonelist_node_idx(z); break; default: @@ -2872,6 +3173,7 @@ static const char * const policy_modes[] = [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", + [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; @@ -2931,6 +3233,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) } break; case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ @@ -3018,8 +3321,9 @@ out: * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. - * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the - * longest flag, "relative", and to display at least a few node ids. + * Recommend a @maxlen of at least 51 for the longest mode, "weighted + * interleave", plus the longest flag flags, "relative|balancing", and to + * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { @@ -3028,7 +3332,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; - if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { + if (pol && + pol != &default_policy && + !(pol >= &preferred_node_policy[0] && + pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } @@ -3041,6 +3348,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: @@ -3055,15 +3363,218 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += snprintf(p, buffer + maxlen - p, "="); /* - * Currently, the only defined flags are mutually exclusive + * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); + + if (flags & MPOL_F_NUMA_BALANCING) { + if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) + p += snprintf(p, buffer + maxlen - p, "|"); + p += snprintf(p, buffer + maxlen - p, "balancing"); + } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } + +#ifdef CONFIG_SYSFS +struct iw_node_attr { + struct kobj_attribute kobj_attr; + int nid; +}; + +static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct iw_node_attr *node_attr; + u8 weight; + + node_attr = container_of(attr, struct iw_node_attr, kobj_attr); + weight = get_il_weight(node_attr->nid); + return sysfs_emit(buf, "%d\n", weight); +} + +static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct iw_node_attr *node_attr; + u8 *new; + u8 *old; + u8 weight = 0; + + node_attr = container_of(attr, struct iw_node_attr, kobj_attr); + if (count == 0 || sysfs_streq(buf, "")) + weight = 0; + else if (kstrtou8(buf, 0, &weight)) + return -EINVAL; + + new = kzalloc(nr_node_ids, GFP_KERNEL); + if (!new) + return -ENOMEM; + + mutex_lock(&iw_table_lock); + old = rcu_dereference_protected(iw_table, + lockdep_is_held(&iw_table_lock)); + if (old) + memcpy(new, old, nr_node_ids); + new[node_attr->nid] = weight; + rcu_assign_pointer(iw_table, new); + mutex_unlock(&iw_table_lock); + synchronize_rcu(); + kfree(old); + return count; +} + +static struct iw_node_attr **node_attrs; + +static void sysfs_wi_node_release(struct iw_node_attr *node_attr, + struct kobject *parent) +{ + if (!node_attr) + return; + sysfs_remove_file(parent, &node_attr->kobj_attr.attr); + kfree(node_attr->kobj_attr.attr.name); + kfree(node_attr); +} + +static void sysfs_wi_release(struct kobject *wi_kobj) +{ + int i; + + for (i = 0; i < nr_node_ids; i++) + sysfs_wi_node_release(node_attrs[i], wi_kobj); + kobject_put(wi_kobj); +} + +static const struct kobj_type wi_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .release = sysfs_wi_release, +}; + +static int add_weight_node(int nid, struct kobject *wi_kobj) +{ + struct iw_node_attr *node_attr; + char *name; + + node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); + if (!node_attr) + return -ENOMEM; + + name = kasprintf(GFP_KERNEL, "node%d", nid); + if (!name) { + kfree(node_attr); + return -ENOMEM; + } + + sysfs_attr_init(&node_attr->kobj_attr.attr); + node_attr->kobj_attr.attr.name = name; + node_attr->kobj_attr.attr.mode = 0644; + node_attr->kobj_attr.show = node_show; + node_attr->kobj_attr.store = node_store; + node_attr->nid = nid; + + if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { + kfree(node_attr->kobj_attr.attr.name); + kfree(node_attr); + pr_err("failed to add attribute to weighted_interleave\n"); + return -ENOMEM; + } + + node_attrs[nid] = node_attr; + return 0; +} + +static int add_weighted_interleave_group(struct kobject *root_kobj) +{ + struct kobject *wi_kobj; + int nid, err; + + wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); + if (!wi_kobj) + return -ENOMEM; + + err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, + "weighted_interleave"); + if (err) { + kfree(wi_kobj); + return err; + } + + for_each_node_state(nid, N_POSSIBLE) { + err = add_weight_node(nid, wi_kobj); + if (err) { + pr_err("failed to add sysfs [node%d]\n", nid); + break; + } + } + if (err) + kobject_put(wi_kobj); + return 0; +} + +static void mempolicy_kobj_release(struct kobject *kobj) +{ + u8 *old; + + mutex_lock(&iw_table_lock); + old = rcu_dereference_protected(iw_table, + lockdep_is_held(&iw_table_lock)); + rcu_assign_pointer(iw_table, NULL); + mutex_unlock(&iw_table_lock); + synchronize_rcu(); + kfree(old); + kfree(node_attrs); + kfree(kobj); +} + +static const struct kobj_type mempolicy_ktype = { + .release = mempolicy_kobj_release +}; + +static int __init mempolicy_sysfs_init(void) +{ + int err; + static struct kobject *mempolicy_kobj; + + mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); + if (!mempolicy_kobj) { + err = -ENOMEM; + goto err_out; + } + + node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), + GFP_KERNEL); + if (!node_attrs) { + err = -ENOMEM; + goto mempol_out; + } + + err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, + "mempolicy"); + if (err) + goto node_out; + + err = add_weighted_interleave_group(mempolicy_kobj); + if (err) { + pr_err("mempolicy sysfs structure failed to initialize\n"); + kobject_put(mempolicy_kobj); + return err; + } + + return err; +node_out: + kfree(node_attrs); +mempol_out: + kfree(mempolicy_kobj); +err_out: + pr_err("failed to add mempolicy kobject to the system\n"); + return err; +} + +late_initcall(mempolicy_sysfs_init); +#endif /* CONFIG_SYSFS */ |