diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/compaction.c | 98 | ||||
| -rw-r--r-- | mm/gup.c | 10 | ||||
| -rw-r--r-- | mm/huge_memory.c | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 8 | ||||
| -rw-r--r-- | mm/internal.h | 10 | ||||
| -rw-r--r-- | mm/kasan/quarantine.c | 7 | ||||
| -rw-r--r-- | mm/kmemleak.c | 51 | ||||
| -rw-r--r-- | mm/memcontrol-v1.c | 6 | ||||
| -rw-r--r-- | mm/memcontrol.c | 13 | ||||
| -rw-r--r-- | mm/memory.c | 49 | ||||
| -rw-r--r-- | mm/mempolicy.c | 21 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/mm_init.c | 9 | ||||
| -rw-r--r-- | mm/page_alloc.c | 76 | ||||
| -rw-r--r-- | mm/page_table_check.c | 12 | ||||
| -rw-r--r-- | mm/pagewalk.c | 6 | ||||
| -rw-r--r-- | mm/rmap.c | 20 | ||||
| -rw-r--r-- | mm/swapfile.c | 6 | ||||
| -rw-r--r-- | mm/vmscan.c | 21 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 11 | ||||
| -rw-r--r-- | mm/zswap.c | 13 |
21 files changed, 293 insertions, 160 deletions
diff --git a/mm/compaction.c b/mm/compaction.c index 6769a9d6f16a..7bb638df5db9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1364,12 +1364,44 @@ static bool suitable_migration_source(struct compact_control *cc, if (pageblock_skip_persistent(page)) return false; - if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) + /* + * Background compaction produces blocks for the zone at + * large, with no particular allocation context. Allow all + * block types, including CMA. + */ + if (!cc->direct_compaction) return true; block_mt = get_pageblock_migratetype(page); - if (cc->migratetype == MIGRATE_MOVABLE) + /* + * CMA pages can only be taken by ALLOC_CMA requests. For anybody + * else, vacating a CMA block consumes free pages the caller + * could have used, and produces free pages it cannot. + */ + if (is_migrate_cma(block_mt) && !(cc->alloc_flags & ALLOC_CMA)) + return false; + + /* + * Per default, scans are restricted to blocks compatible with + * the request, to prevent cross-contamination. Once + * compaction priority escalates to synchronous scans, though, + * scan all blocks to try to make forward progress. For + * movable request, this likely helps little: there shouldn't + * be many migratable pages inside non-movable blocks besides + * allocator fallbacks. For non-movable requests, this helps a + * lot, as they can finally scan movable blocks. + */ + if (cc->mode != MIGRATE_ASYNC) + return true; + + /* + * Prevent <pageblock_order unmovable/reclaimable requests from + * polluting movable blocks through fallbacks. Whole-block production + * (directly requested, or defrag_mode) is exempt as the allocator + * claims and converts these. + */ + if (cc->migratetype == MIGRATE_MOVABLE || cc->order >= pageblock_order) return is_migrate_movable(block_mt); else return block_mt == cc->migratetype; @@ -1957,12 +1989,12 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) return pfn; /* - * Only allow kcompactd and direct requests for movable pages to - * quickly clear out a MOVABLE pageblock for allocation. This - * reduces the risk that a large movable pageblock is freed for - * an unmovable/reclaimable small allocation. + * Prevent <pageblock_order unmovable/reclaimable requests from + * polluting movable blocks through fallbacks. Whole-block production + * is exempt as the allocator claims and converts these. */ - if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) + if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE && + cc->order < pageblock_order) return pfn; /* @@ -2748,9 +2780,8 @@ out: static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, unsigned int alloc_flags, int highest_zoneidx, - struct page **capture) + struct capture_control *capc) { - enum compact_result ret; struct compact_control cc = { .order = order, .search_order = order, @@ -2765,54 +2796,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; - struct capture_control capc = { - .cc = &cc, - .page = NULL, - }; - /* - * Make sure the structs are really initialized before we expose the - * capture control, in case we are interrupted and the interrupt handler - * frees a page. - */ - barrier(); - WRITE_ONCE(current->capture_control, &capc); - - ret = compact_zone(&cc, &capc); - - /* - * Make sure we hide capture control first before we read the captured - * page pointer, otherwise an interrupt could free and capture a page - * and we would leak it. - */ - WRITE_ONCE(current->capture_control, NULL); - *capture = READ_ONCE(capc.page); - /* - * Technically, it is also possible that compaction is skipped but - * the page is still captured out of luck(IRQ came and freed the page). - * Returning COMPACT_SUCCESS in such cases helps in properly accounting - * the COMPACT[STALL|FAIL] when compaction is skipped. - */ - if (*capture) - ret = COMPACT_SUCCESS; - - return ret; + return compact_zone(&cc, capc); } /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation - * @order: The order of the current allocation + * @order: The order to try to make available * @alloc_flags: The allocation flags of the current allocation * @ac: The context of current allocation * @prio: Determines how hard direct compaction should try to succeed - * @capture: Pointer to free page created by compaction will be stored here + * @capc: Free page capture bypassing the freelist * * This is the main entry point for direct page compaction. */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, - enum compact_priority prio, struct page **capture) + enum compact_priority prio, struct capture_control *capc) { struct zoneref *z; struct zone *zone; @@ -2839,8 +2840,17 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, continue; } + WRITE_ONCE(capc->zone, zone); + status = compact_zone_order(zone, order, gfp_mask, prio, - alloc_flags, ac->highest_zoneidx, capture); + alloc_flags, ac->highest_zoneidx, capc); + + WRITE_ONCE(capc->zone, NULL); + + /* Stop if a page has been captured */ + if (READ_ONCE(capc->page)) + status = COMPACT_SUCCESS; + rc = max(status, rc); /* The allocation should succeed, stop compacting */ @@ -2273,6 +2273,7 @@ static unsigned long collect_longterm_unpinnable_folios( for (folio = pofs_get_folio(pofs, i); folio; folio = pofs_next_folio(folio, pofs, &i)) { + const int pin_refs = folio_has_pincount(folio) ? 1 : GUP_PIN_COUNTING_BIAS; if (folio_is_longterm_pinnable(folio)) continue; @@ -2287,15 +2288,20 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } + /* + * We drain not only to make the folio_isolate_lru() succeed, + * but also to remove any other folio references from LRU + * caches. + */ if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + folio_expected_ref_count(folio) + pin_refs) { lru_add_drain(); drained = 1; } if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + folio_expected_ref_count(folio) + pin_refs) { lru_add_drain_all(); drained = 2; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 227aeffae8ee..8564a92d83f0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2293,9 +2293,11 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) static pmd_t clear_uffd_wp_pmd(pmd_t pmd) { + if (pmd_none(pmd)) + return pmd; if (pmd_present(pmd)) pmd = pmd_clear_uffd_wp(pmd); - else if (is_swap_pmd(pmd)) + else pmd = pmd_swp_clear_uffd_wp(pmd); return pmd; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5515870b5b15..e9f4cbf50a2b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5876,6 +5876,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, bool adjust_reservation; unsigned long last_addr_mask; + i_mmap_assert_write_locked(vma->vm_file->f_mapping); WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); @@ -5967,7 +5968,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, /* * Restore the reservation for anonymous page, otherwise the - * backing page could be stolen by someone. + * backing page could be stolen by someone. Restore only on the + * last unmap, otherwise the owner could empty its resv map + * while the folio is still mapped by a child. Note that holding + * i_mmap_lock_write is needed to check the number of mappings. * If there we are freeing a surplus, do not set the restore * reservation bit. */ @@ -5975,7 +5979,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && - folio_test_anon(folio)) { + !folio_mapped(folio) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; diff --git a/mm/internal.h b/mm/internal.h index f5c0d927924d..ef42eee87c7b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -908,7 +908,15 @@ struct compact_control { * immediately when one is created during the free path. */ struct capture_control { - struct compact_control *cc; + struct zone *zone; + int migratetype; + /* + * Allocation request order. May differ from the compaction + * order: defrag_mode promotes sub-block allocations to + * pageblock-order compaction; capture still matches at the + * original allocation order so prep_new_page() is consistent. + */ + int order; struct page *page; }; diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 6958aa713c67..16f4e67beee8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -355,7 +355,12 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); - for_each_online_cpu(cpu) { + /* + * A CPU can go offline after on_each_cpu() returns, leaving cache + * objects on that CPU's shrink list. Scan all possible CPUs to + * drain those lists. + */ + for_each_possible_cpu(cpu) { sq = per_cpu_ptr(&shrink_qlist, cpu); raw_spin_lock_irqsave(&sq->lock, flags); qlist_move_cache(&sq->qlist, &to_free, cache); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 415b154fdf38..452f3714f337 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1690,6 +1690,42 @@ unlock_put: } /* + * Scan all task kernel stacks, rescheduling between tasks. Each task is looked + * up and pinned within its own RCU read-side section, so no lock is held across + * the scan and the walk cannot trip the soft lockup watchdog. + */ +static void kmemleak_scan_task_stacks(void) +{ + struct pid *pid; + int nr = 1; + + do { + struct task_struct *p = NULL; + + rcu_read_lock(); + pid = find_ge_pid(nr, &init_pid_ns); + if (pid) { + nr = pid_nr(pid) + 1; + p = pid_task(pid, PIDTYPE_PID); + if (p) + get_task_struct(p); + } + rcu_read_unlock(); + + if (p) { + void *stack = try_get_task_stack(p); + + if (stack) { + scan_block(stack, stack + THREAD_SIZE, NULL); + put_task_stack(p); + } + put_task_struct(p); + } + cond_resched(); + } while (pid && !scan_should_stop()); +} + +/* * Scan data sections and all the referenced memory blocks allocated via the * kernel's standard allocators. This function must be called with the * scan_mutex held. @@ -1780,19 +1816,8 @@ static void kmemleak_scan(void) /* * Scanning the task stacks (may introduce false negatives). */ - if (kmemleak_stack_scan) { - struct task_struct *p, *g; - - rcu_read_lock(); - for_each_process_thread(g, p) { - void *stack = try_get_task_stack(p); - if (stack) { - scan_block(stack, stack + THREAD_SIZE, NULL); - put_task_stack(p); - } - } - rcu_read_unlock(); - } + if (kmemleak_stack_scan) + kmemleak_scan_task_stacks(); /* * Scan the objects already referenced from the sections scanned diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 6eed14bff742..74d3a4d78ec6 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -1139,13 +1139,13 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, event->unregister_event = mem_cgroup_usage_unregister_event; } else if (!strcmp(name, "memory.oom_control")) { pr_warn_once("oom_control is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org" + "Please report your usecase to linux-mm@kvack.org" " if you depend on this functionality.\n"); event->register_event = mem_cgroup_oom_register_event; event->unregister_event = mem_cgroup_oom_unregister_event; } else if (!strcmp(name, "memory.pressure_level")) { pr_warn_once("pressure_level is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org " + "Please report your usecase to linux-mm@kvack.org " "if you depend on this functionality.\n"); event->register_event = vmpressure_register_event; event->unregister_event = vmpressure_unregister_event; @@ -1982,7 +1982,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct mem_cgroup *memcg = mem_cgroup_from_css(css); pr_warn_once("oom_control is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org if you " + "Please report your usecase to linux-mm@kvack.org if you " "depend on this functionality.\n"); /* cannot set to root cgroup and only 0 and 1 are allowed */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 752d98fd3921..898821793349 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3809,9 +3809,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_init(&memcg->swap, &parent->swap, false); #ifdef CONFIG_MEMCG_V1 memcg->memory.track_failcnt = !memcg_on_dfl; + memcg->memsw.track_failcnt = !memcg_on_dfl; WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); page_counter_init(&memcg->kmem, &parent->kmem, false); page_counter_init(&memcg->tcpmem, &parent->tcpmem, false); + memcg->tcpmem.track_failcnt = !memcg_on_dfl; #endif } else { init_memcg_stats(); @@ -4028,6 +4030,7 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(MEMCG_KMEM); memcg->vmstats->state[index] += kmem; + memcg->vmstats->state_local[index] += kmem; if (parent) parent->vmstats->state_pending[index] += kmem; } @@ -4045,9 +4048,11 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B); lstats->state[index] += slab; + lstats->state_local[index] += slab; if (plstats) plstats->state_pending[index] += slab; memcg->vmstats->state[index] += slab; + memcg->vmstats->state_local[index] += slab; if (parent) parent->vmstats->state_pending[index] += slab; } @@ -4056,9 +4061,11 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B); lstats->state[index] += slab; + lstats->state_local[index] += slab; if (plstats) plstats->state_pending[index] += slab; memcg->vmstats->state[index] += slab; + memcg->vmstats->state_local[index] += slab; if (parent) parent->vmstats->state_pending[index] += slab; } @@ -4378,6 +4385,9 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, unsigned long nr_pages = page_counter_read(&memcg->memory); unsigned long reclaimed; + if (high != READ_ONCE(memcg->memory.high)) + break; + if (nr_pages <= high) break; @@ -4429,6 +4439,9 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); + if (max != READ_ONCE(memcg->memory.max)) + break; + if (nr_pages <= max) break; diff --git a/mm/memory.c b/mm/memory.c index 6b4cdb8bd8db..72793ec63107 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6320,34 +6320,39 @@ retry_pud: if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PMD_ORDER)) { ret = create_huge_pmd(&vmf); - if (!(ret & VM_FAULT_FALLBACK)) + if (ret & VM_FAULT_FALLBACK) + goto fallback; + else return ret; - } else { - vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); + } - if (unlikely(is_swap_pmd(vmf.orig_pmd))) { - VM_BUG_ON(thp_migration_supported() && - !pmd_is_migration_entry(vmf.orig_pmd)); - if (pmd_is_migration_entry(vmf.orig_pmd)) - pmd_migration_entry_wait(mm, vmf.pmd); - return 0; - } - if (pmd_trans_huge(vmf.orig_pmd)) { - if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) - return do_huge_pmd_numa_page(&vmf); + vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); + if (pmd_none(vmf.orig_pmd)) + goto fallback; - if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !pmd_write(vmf.orig_pmd)) { - ret = wp_huge_pmd(&vmf); - if (!(ret & VM_FAULT_FALLBACK)) - return ret; - } else { - huge_pmd_set_accessed(&vmf); - return 0; - } + if (unlikely(!pmd_present(vmf.orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !pmd_is_migration_entry(vmf.orig_pmd)); + if (pmd_is_migration_entry(vmf.orig_pmd)) + pmd_migration_entry_wait(mm, vmf.pmd); + return 0; + } + if (pmd_trans_huge(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); + + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !pmd_write(vmf.orig_pmd)) { + ret = wp_huge_pmd(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pmd_set_accessed(&vmf); + return 0; } } +fallback: return handle_pte_fault(&vmf); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b4aa4f2cb8ec..d18cee845354 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1989,24 +1989,15 @@ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; + pgoff_t ilx; + bool mof; - if (vma->vm_ops && vma->vm_ops->get_policy) { - bool ret = false; - pgoff_t ilx; /* ignored here */ - - pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); - if (pol && (pol->flags & MPOL_F_MOF)) - ret = true; - mpol_cond_put(pol); - - return ret; - } - - pol = vma->vm_policy; + pol = __get_vma_policy(vma, vma->vm_start, &ilx); if (!pol) pol = get_task_policy(current); - - return pol->flags & MPOL_F_MOF; + mof = pol->flags & MPOL_F_MOF; + mpol_cond_put(pol); + return mof; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) diff --git a/mm/migrate.c b/mm/migrate.c index e66d9cc67dda..d03b5d265e71 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1821,7 +1821,7 @@ static int migrate_pages_batch(struct list_head *from, is_thp = folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); - cond_resched(); + cond_resched_tasks_rcu_qs(); /* * The rare folio on the deferred split list should diff --git a/mm/mm_init.c b/mm/mm_init.c index d2d915984611..922493a35a28 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2238,10 +2238,13 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) } /* - * There were no pages to initialize and free which means the zone's - * memory map is completely initialized. + * The loop only tests spfn before entering an iteration, so on exit it + * may point up to a section past the end of the zone. When it does, + * the rest of the zone has already been handed to + * deferred_init_memmap_chunk() and nothing is left to initialize. */ - pgdat->first_deferred_pfn = nr_pages ? spfn : ULONG_MAX; + pgdat->first_deferred_pfn = + spfn < zone_end_pfn(zone) ? spfn : ULONG_MAX; pgdat_resize_unlock(pgdat, &flags); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 775e02b797a3..af37e0c2d6f8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -763,14 +763,14 @@ static inline struct capture_control *task_capc(struct zone *zone) return unlikely(capc) && !(current->flags & PF_KTHREAD) && !capc->page && - capc->cc->zone == zone ? capc : NULL; + capc->zone == zone ? capc : NULL; } static inline bool compaction_capture(struct capture_control *capc, struct page *page, int order, int migratetype) { - if (!capc || order != capc->cc->order) + if (!capc || order != capc->order) return false; /* Do not accidentally pollute CMA or isolated regions*/ @@ -786,12 +786,12 @@ compaction_capture(struct capture_control *capc, struct page *page, * have trouble finding a high-order free page. */ if (order < pageblock_order && migratetype == MIGRATE_MOVABLE && - capc->cc->migratetype != MIGRATE_MOVABLE) + capc->migratetype != MIGRATE_MOVABLE) return false; - if (migratetype != capc->cc->migratetype) - trace_mm_page_alloc_extfrag(page, capc->cc->order, order, - capc->cc->migratetype, migratetype); + if (migratetype != capc->migratetype) + trace_mm_page_alloc_extfrag(page, capc->order, order, + capc->migratetype, migratetype); capc->page = page; return true; @@ -4132,18 +4132,67 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned long pflags; unsigned int noreclaim_flag; + struct capture_control capc = { + .zone = NULL, + .migratetype = ac->migratetype, + .order = order, + .page = NULL, + }; + int compact_order = order; - if (!order) + /* + * If fallbacks are not permitted (defrag_mode), we either + * need to reclaim space in a block of matching type, or clear + * out an entire block to allow __rmqueue_claim() to convert. + * + * Reclaim by itself is primarily freeing space in movable + * blocks, since that's where the LRU pages live. So this + * works for movable requests, but not for others. + * + * For those, promote the order to help make blocks, instead + * of spinning in reclaim alone unproductively. + */ + if ((alloc_flags & ALLOC_NOFRAGMENT) && ac->migratetype != MIGRATE_MOVABLE) + compact_order = max(order, pageblock_order); + + if (!compact_order) return NULL; psi_memstall_enter(&pflags); delayacct_compact_start(); + fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); - *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - prio, &page); + /* + * Make sure the structs are really initialized before we expose the + * capture control, in case we are interrupted and the interrupt handler + * frees a page. + */ + barrier(); + WRITE_ONCE(current->capture_control, &capc); + + *compact_result = try_to_compact_pages(gfp_mask, compact_order, + alloc_flags, ac, prio, &capc); + + /* + * Make sure we hide capture control first before we read the captured + * page pointer, otherwise an interrupt could free and capture a page + * and we would leak it. + */ + WRITE_ONCE(current->capture_control, NULL); + page = READ_ONCE(capc.page); + + /* + * Technically, it is also possible that compaction is skipped but + * the page is still captured out of luck(IRQ came and freed the page). + * Returning COMPACT_SUCCESS in such cases helps in properly accounting + * the COMPACT[STALL|FAIL] when compaction is skipped. + */ + if (page) + *compact_result = COMPACT_SUCCESS; memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(gfp_mask); psi_memstall_leave(&pflags); delayacct_compact_end(); @@ -4167,7 +4216,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zone *zone = page_zone(page); zone->compact_blockskip_flush = false; - compaction_defer_reset(zone, order, true); + compaction_defer_reset(zone, compact_order, true); count_vm_event(COMPACTSUCCESS); return page; } @@ -4404,9 +4453,14 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned long pflags; bool drained = false; + int reclaim_order = order; + + /* Match the slowpath compaction promotion in __alloc_pages_direct_compact */ + if ((alloc_flags & ALLOC_NOFRAGMENT) && ac->migratetype != MIGRATE_MOVABLE) + reclaim_order = max(order, pageblock_order); psi_memstall_enter(&pflags); - *did_some_progress = __perform_reclaim(gfp_mask, order, ac); + *did_some_progress = __perform_reclaim(gfp_mask, reclaim_order, ac); if (unlikely(!(*did_some_progress))) goto out; diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 0a5ab62c9c59..91c4dacc41fb 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -223,10 +223,14 @@ EXPORT_SYMBOL(__page_table_check_ptes_set); static inline void page_table_check_pmd_flags(pmd_t pmd) { - if (pmd_present(pmd) && pmd_uffd_wp(pmd)) - WARN_ON_ONCE(pmd_write(pmd)); - else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd)) - WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd))); + if (pmd_present(pmd)) { + if (pmd_uffd_wp(pmd)) + WARN_ON_ONCE(pmd_write(pmd)); + } else if (pmd_swp_uffd_wp(pmd)) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + WARN_ON_ONCE(swap_cached_writable(entry)); + } } void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ca6c51598aed..47befc414adc 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -127,6 +127,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pmd = pmd_offset(pud, addr); do { again: + walk->action = ACTION_SUBTREE; next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { if (has_install) @@ -139,8 +140,6 @@ again: continue; } - walk->action = ACTION_SUBTREE; - /* * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds @@ -197,6 +196,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pud = pud_offset(p4d, addr); do { again: + walk->action = ACTION_SUBTREE; next = pud_addr_end(addr, end); if (pud_none(*pud)) { if (has_install) @@ -209,8 +209,6 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, continue; } - walk->action = ACTION_SUBTREE; - if (ops->pud_entry) err = ops->pud_entry(pud, addr, next, walk); if (err) diff --git a/mm/rmap.c b/mm/rmap.c index 4c78c7109909..4348b35db465 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1983,20 +1983,26 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); - /* - * Handle PFN swap PTEs, such as device-exclusive ones, that - * actually map pages. - */ - pteval = ptep_get(pvmw.pte); + address = pvmw.address; + if (folio_test_hugetlb(folio)) { + pteval = huge_ptep_get(mm, address, pvmw.pte); + } else { + pteval = ptep_get(pvmw.pte); + } if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { - pfn = swp_offset_pfn(pte_to_swp_entry(pteval)); + /* + * Handle PFN swap PTEs, such as device-exclusive ones, + * that actually map pages. + */ + const softleaf_t entry = softleaf_from_pte(pteval); + + pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); - address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); diff --git a/mm/swapfile.c b/mm/swapfile.c index 841cf1ab8330..cf33c3b2c31f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1613,11 +1613,11 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) return si; bad_nofile: - pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); + pr_err_ratelimited("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: - pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); + pr_err_ratelimited("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } @@ -3753,7 +3753,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) si = swap_entry_to_info(entry); if (WARN_ON_ONCE(!si)) { - pr_err("%s%08lx\n", Bad_file, entry.val); + pr_err_ratelimited("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 95b1179a14e7..05027b320eda 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -201,6 +201,13 @@ struct scan_control { */ int vm_swappiness = 60; +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + if (sc->proactive && sc->proactive_swappiness) + return *sc->proactive_swappiness; + return mem_cgroup_swappiness(memcg); +} + #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ @@ -241,13 +248,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) #endif return false; } - -static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) -{ - if (sc->proactive && sc->proactive_swappiness) - return *sc->proactive_swappiness; - return mem_cgroup_swappiness(memcg); -} #else static bool cgroup_reclaim(struct scan_control *sc) { @@ -263,11 +263,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) { return true; } - -static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) -{ - return READ_ONCE(vm_swappiness); -} #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to @@ -5864,7 +5859,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) } } - cond_resched(); + cond_resched_tasks_rcu_qs(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index bb1f1e124dc0..3564b37f1fce 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -508,6 +508,11 @@ static int get_size_class_index(int size) return min_t(int, ZS_SIZE_CLASSES - 1, idx); } +static struct size_class *lookup_size_class(struct zs_pool *pool, size_t size) +{ + return pool->size_class[get_size_class_index(size + ZS_HANDLE_SIZE)]; +} + static inline void class_stat_add(struct size_class *class, int type, unsigned long cnt) { @@ -1052,7 +1057,7 @@ unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size) { struct size_class *class; - class = pool->size_class[get_size_class_index(size)]; + class = lookup_size_class(pool, size); return class->index; } @@ -1279,9 +1284,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp, if (!handle) return (unsigned long)ERR_PTR(-ENOMEM); - /* extra space in chunk to keep the handle */ - size += ZS_HANDLE_SIZE; - class = pool->size_class[get_size_class_index(size)]; + class = lookup_size_class(pool, size); /* class->lock effectively protects the zpage migration */ spin_lock(&class->lock); diff --git a/mm/zswap.c b/mm/zswap.c index 12fb0e395412..18249dd96ef8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1375,11 +1375,12 @@ static void shrink_worker(struct work_struct *w) } while (memcg && !mem_cgroup_tryget_online(memcg)); spin_unlock(&zswap_shrink_lock); - if (!memcg) { - /* - * Continue shrinking without incrementing failures if - * we found candidate memcgs in the last tree walk. - */ + /* + * A NULL memcg ends a full hierarchy pass (except when memcg is + * disabled, where it is always NULL: fall through to the root LRU). + * Count a failure only if the last pass found no candidates. + */ + if (!memcg && !mem_cgroup_disabled()) { if (!attempts && ++failures == MAX_RECLAIM_RETRIES) break; @@ -1398,7 +1399,7 @@ static void shrink_worker(struct work_struct *w) * and failures. */ if (ret == -ENOENT) - continue; + goto resched; ++attempts; if (ret && ++failures == MAX_RECLAIM_RETRIES) |