diff options
Diffstat (limited to 'mm')
81 files changed, 5645 insertions, 3295 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 264a2df5ec..57cd378c73 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -130,6 +130,7 @@ config ZSWAP_COMPRESSOR_DEFAULT choice prompt "Default allocator" depends on ZSWAP + default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if MMU default ZSWAP_ZPOOL_DEFAULT_ZBUD help Selects the default allocator for the compressed cache for @@ -704,6 +705,17 @@ config HUGETLB_PAGE_SIZE_VARIABLE config CONTIG_ALLOC def_bool (MEMORY_ISOLATION && COMPACTION) || CMA +config PCP_BATCH_SCALE_MAX + int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" + default 5 + range 0 6 + help + In page allocator, PCP (Per-CPU pageset) is refilled and drained in + batches. The batch number is scaled automatically to improve page + allocation/free throughput. But too large scale factor may hurt + latency. This option sets the upper limit of scale factor to limit + the maximum latency. + config PHYS_ADDR_T_64BIT def_bool 64BIT @@ -1189,13 +1201,6 @@ config ANON_VMA_NAME area from being merged with adjacent virtual memory areas due to the difference in their name. -config USERFAULTFD - bool "Enable userfaultfd() system call" - depends on MMU - help - Enable the userfaultfd() system call that allows to intercept and - handle page faults in userland. - config HAVE_ARCH_USERFAULTFD_WP bool help @@ -1206,6 +1211,14 @@ config HAVE_ARCH_USERFAULTFD_MINOR help Arch has userfaultfd minor fault support +menuconfig USERFAULTFD + bool "Enable userfaultfd() system call" + depends on MMU + help + Enable the userfaultfd() system call that allows to intercept and + handle page faults in userland. + +if USERFAULTFD config PTE_MARKER_UFFD_WP bool "Userfaultfd write protection support for shmem/hugetlbfs" default y @@ -1215,6 +1228,7 @@ config PTE_MARKER_UFFD_WP Allows to create marker PTEs for userfaultfd write protection purposes. It is required to enable userfaultfd write protection on file-backed memory types like shmem and hugetlbfs. +endif # USERFAULTFD # multi-gen LRU { config LRU_GEN diff --git a/mm/Makefile b/mm/Makefile index ec65984e2a..33873c8aed 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -48,8 +48,8 @@ endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page-writeback.o folio-compat.o \ - readahead.o swap.o truncate.o vmscan.o shmem.o \ - util.o mmzone.o vmstat.o backing-dev.o \ + readahead.o swap.o truncate.o vmscan.o shrinker.o \ + shmem.o util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ compaction.o show_mem.o shmem_quota.o\ interval_tree.o list_lru.o workingset.o \ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1e3447bccd..e039d05304 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); - wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); if (err) @@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi) INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); + bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c index b1efebfcf9..fa7cb0c87c 100644 --- a/mm/bootmem_info.c +++ b/mm/bootmem_info.c @@ -34,7 +34,7 @@ void put_page_bootmem(struct page *page) ClearPagePrivate(page); set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); - kmemleak_free_part(page_to_virt(page), PAGE_SIZE); + kmemleak_free_part_phys(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE); free_reserved_page(page); } } diff --git a/mm/compaction.c b/mm/compaction.c index 38c8d216c6..01ba298739 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -382,6 +382,7 @@ static void __reset_isolation_suitable(struct zone *zone) bool source_set = false; bool free_set = false; + /* Only flush if a full compaction finished recently */ if (!zone->compact_blockskip_flush) return; @@ -434,9 +435,7 @@ void reset_isolation_suitable(pg_data_t *pgdat) if (!populated_zone(zone)) continue; - /* Only flush if a full compaction finished recently */ - if (zone->compact_blockskip_flush) - __reset_isolation_suitable(zone); + __reset_isolation_suitable(zone); } } @@ -626,11 +625,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (likely(order <= MAX_ORDER)) { + if (blockpfn + (1UL << order) <= end_pfn) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } + goto isolate_fail; } @@ -678,8 +678,7 @@ isolate_fail: spin_unlock_irqrestore(&cc->zone->lock, flags); /* - * There is a tiny chance that we have read bogus compound_order(), - * so be careful to not go outside of the pageblock. + * Be careful to not go outside of the pageblock. */ if (unlikely(blockpfn > end_pfn)) blockpfn = end_pfn; @@ -1395,8 +1394,8 @@ move_freelist_head(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); - if (!list_is_last(freelist, &freepage->lru)) { - list_cut_before(&sublist, freelist, &freepage->lru); + if (!list_is_first(&freepage->buddy_list, freelist)) { + list_cut_before(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } @@ -1412,8 +1411,8 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); - if (!list_is_first(freelist, &freepage->lru)) { - list_cut_position(&sublist, freelist, &freepage->lru); + if (!list_is_last(&freepage->buddy_list, freelist)) { + list_cut_position(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } @@ -2066,8 +2065,10 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) } /* - * order == -1 is expected when compacting via - * /proc/sys/vm/compact_memory + * order == -1 is expected when compacting proactively via + * 1. /proc/sys/vm/compact_memory + * 2. /sys/devices/system/node/nodex/compact + * 3. /proc/sys/vm/compaction_proactiveness */ static inline bool is_via_compact_memory(int order) { @@ -2377,6 +2378,30 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, return false; } +/* + * Should we do compaction for target allocation order. + * Return COMPACT_SUCCESS if allocation for target order can be already + * satisfied + * Return COMPACT_SKIPPED if compaction for target order is likely to fail + * Return COMPACT_CONTINUE if compaction for target order should be ran + */ +static enum compact_result +compaction_suit_allocation_order(struct zone *zone, unsigned int order, + int highest_zoneidx, unsigned int alloc_flags) +{ + unsigned long watermark; + + watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, + alloc_flags)) + return COMPACT_SUCCESS; + + if (!compaction_suitable(zone, order, highest_zoneidx)) + return COMPACT_SKIPPED; + + return COMPACT_CONTINUE; +} + static enum compact_result compact_zone(struct compact_control *cc, struct capture_control *capc) { @@ -2402,19 +2427,11 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) cc->migratetype = gfp_migratetype(cc->gfp_mask); if (!is_via_compact_memory(cc->order)) { - unsigned long watermark; - - /* Allocation can already succeed, nothing to do */ - watermark = wmark_pages(cc->zone, - cc->alloc_flags & ALLOC_WMARK_MASK); - if (zone_watermark_ok(cc->zone, cc->order, watermark, - cc->highest_zoneidx, cc->alloc_flags)) - return COMPACT_SUCCESS; - - /* Compaction is likely to fail */ - if (!compaction_suitable(cc->zone, cc->order, - cc->highest_zoneidx)) - return COMPACT_SKIPPED; + ret = compaction_suit_allocation_order(cc->zone, cc->order, + cc->highest_zoneidx, + cc->alloc_flags); + if (ret != COMPACT_CONTINUE) + return ret; } /* @@ -2913,6 +2930,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) int zoneid; struct zone *zone; enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; + enum compact_result ret; for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; @@ -2920,14 +2938,10 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) if (!populated_zone(zone)) continue; - /* Allocation can already succeed, check other zones */ - if (zone_watermark_ok(zone, pgdat->kcompactd_max_order, - min_wmark_pages(zone), - highest_zoneidx, 0)) - continue; - - if (compaction_suitable(zone, pgdat->kcompactd_max_order, - highest_zoneidx)) + ret = compaction_suit_allocation_order(zone, + pgdat->kcompactd_max_order, + highest_zoneidx, ALLOC_WMARK_MIN); + if (ret == COMPACT_CONTINUE) return true; } @@ -2950,6 +2964,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) .ignore_skip_hint = false, .gfp_mask = GFP_KERNEL, }; + enum compact_result ret; + trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.highest_zoneidx); count_compact_event(KCOMPACTD_WAKE); @@ -2964,12 +2980,9 @@ static void kcompactd_do_work(pg_data_t *pgdat) if (compaction_deferred(zone, cc.order)) continue; - /* Allocation can already succeed, nothing to do */ - if (zone_watermark_ok(zone, cc.order, - min_wmark_pages(zone), zoneid, 0)) - continue; - - if (!compaction_suitable(zone, cc.order, zoneid)) + ret = compaction_suit_allocation_order(zone, + cc.order, zoneid, ALLOC_WMARK_MIN); + if (ret != COMPACT_CONTINUE) continue; if (kthread_should_stop()) diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 436c6b4cb5..29f43fbc2e 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -59,6 +59,18 @@ config DAMON_SYSFS This builds the sysfs interface for DAMON. The user space can use the interface for arbitrary data access monitoring. +config DAMON_SYSFS_KUNIT_TEST + bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS + depends on DAMON_SYSFS && KUNIT=y + default KUNIT_ALL_TESTS + help + This builds the DAMON sysfs interface Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + config DAMON_DBGFS bool "DAMON debugfs interface (DEPRECATED!)" depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index 6cc8b24558..649adf91eb 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -30,7 +30,7 @@ static void damon_test_regions(struct kunit *test) damon_add_region(r, t); KUNIT_EXPECT_EQ(test, 1u, damon_nr_regions(t)); - damon_del_region(r, t); + damon_destroy_region(r, t); KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); damon_free_target(t); @@ -94,6 +94,7 @@ static void damon_test_aggregate(struct kunit *test) for (ir = 0; ir < 3; ir++) { r = damon_new_region(saddr[it][ir], eaddr[it][ir]); r->nr_accesses = accesses[it][ir]; + r->nr_accesses_bp = accesses[it][ir] * 10000; damon_add_region(r, t); } it++; @@ -147,9 +148,11 @@ static void damon_test_merge_two(struct kunit *test) t = damon_new_target(); r = damon_new_region(0, 100); r->nr_accesses = 10; + r->nr_accesses_bp = 100000; damon_add_region(r, t); r2 = damon_new_region(100, 300); r2->nr_accesses = 20; + r2->nr_accesses_bp = 200000; damon_add_region(r2, t); damon_merge_two_regions(t, r, r2); @@ -196,6 +199,7 @@ static void damon_test_merge_regions_of(struct kunit *test) for (i = 0; i < ARRAY_SIZE(sa); i++) { r = damon_new_region(sa[i], ea[i]); r->nr_accesses = nrs[i]; + r->nr_accesses_bp = nrs[i] * 10000; damon_add_region(r, t); } @@ -265,6 +269,8 @@ static void damon_test_ops_registration(struct kunit *test) /* Check double-registration failure again */ KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + + damon_destroy_ctx(c); } static void damon_test_set_regions(struct kunit *test) @@ -297,6 +303,7 @@ static void damon_test_update_monitoring_result(struct kunit *test) struct damon_region *r = damon_new_region(3, 7); r->nr_accesses = 15; + r->nr_accesses_bp = 150000; r->age = 20; new_attrs = (struct damon_attrs){ @@ -316,6 +323,8 @@ static void damon_test_update_monitoring_result(struct kunit *test) damon_update_monitoring_result(r, &old_attrs, &new_attrs); KUNIT_EXPECT_EQ(test, r->nr_accesses, 150); KUNIT_EXPECT_EQ(test, r->age, 20); + + damon_free_region(r); } static void damon_test_set_attrs(struct kunit *test) @@ -339,6 +348,23 @@ static void damon_test_set_attrs(struct kunit *test) invalid_attrs = valid_attrs; invalid_attrs.aggr_interval = 4999; KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &invalid_attrs), -EINVAL); + + damon_destroy_ctx(c); +} + +static void damon_test_moving_sum(struct kunit *test) +{ + unsigned int mvsum = 50000, nomvsum = 50000, len_window = 10; + unsigned int new_values[] = {10000, 0, 10000, 0, 0, 0, 10000, 0, 0, 0}; + unsigned int expects[] = {55000, 50000, 55000, 50000, 45000, 40000, + 45000, 40000, 35000, 30000}; + int i; + + for (i = 0; i < ARRAY_SIZE(new_values); i++) { + mvsum = damon_moving_sum(mvsum, nomvsum, len_window, + new_values[i]); + KUNIT_EXPECT_EQ(test, mvsum, expects[i]); + } } static void damos_test_new_filter(struct kunit *test) @@ -425,6 +451,7 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_set_regions), KUNIT_CASE(damon_test_update_monitoring_result), KUNIT_CASE(damon_test_set_attrs), + KUNIT_CASE(damon_test_moving_sum), KUNIT_CASE(damos_test_new_filter), KUNIT_CASE(damos_test_filter_out), {}, diff --git a/mm/damon/core.c b/mm/damon/core.c index aff611b6ea..fb38183576 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -128,6 +128,7 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) region->ar.start = start; region->ar.end = end; region->nr_accesses = 0; + region->nr_accesses_bp = 0; INIT_LIST_HEAD(®ion->list); region->age = 0; @@ -312,7 +313,9 @@ static struct damos_quota *damos_quota_init_priv(struct damos_quota *quota) } struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + struct damos_quota *quota, struct damos_watermarks *wmarks) { struct damos *scheme; @@ -322,6 +325,13 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return NULL; scheme->pattern = *pattern; scheme->action = action; + scheme->apply_interval_us = apply_interval_us; + /* + * next_apply_sis will be set when kdamond starts. While kdamond is + * running, it will also updated when it is added to the DAMON context, + * or damon_attrs are updated. + */ + scheme->next_apply_sis = 0; INIT_LIST_HEAD(&scheme->filters); scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); @@ -334,9 +344,21 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return scheme; } +static void damos_set_next_apply_sis(struct damos *s, struct damon_ctx *ctx) +{ + unsigned long sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + unsigned long apply_interval = s->apply_interval_us ? + s->apply_interval_us : ctx->attrs.aggr_interval; + + s->next_apply_sis = ctx->passed_sample_intervals + + apply_interval / sample_interval; +} + void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) { list_add_tail(&s->list, &ctx->schemes); + damos_set_next_apply_sis(s, ctx); } static void damon_del_scheme(struct damos *s) @@ -504,6 +526,7 @@ static void damon_update_monitoring_result(struct damon_region *r, { r->nr_accesses = damon_nr_accesses_for_new_attrs(r->nr_accesses, old_attrs, new_attrs); + r->nr_accesses_bp = r->nr_accesses * 10000; r->age = damon_age_for_new_attrs(r->age, old_attrs, new_attrs); } @@ -539,7 +562,11 @@ static void damon_update_monitoring_results(struct damon_ctx *ctx, * @ctx: monitoring context * @attrs: monitoring attributes * - * This function should not be called while the kdamond is running. + * This function should be called while the kdamond is not running, or an + * access check results aggregation is not ongoing (e.g., from + * &struct damon_callback->after_aggregation or + * &struct damon_callback->after_wmarks_check callbacks). + * * Every time interval is in micro-seconds. * * Return: 0 on success, negative error code otherwise. @@ -548,6 +575,7 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) { unsigned long sample_interval = attrs->sample_interval ? attrs->sample_interval : 1; + struct damos *s; if (attrs->min_nr_regions < 3) return -EINVAL; @@ -563,6 +591,10 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; + + damon_for_each_scheme(s, ctx) + damos_set_next_apply_sis(s, ctx); + return 0; } @@ -708,8 +740,7 @@ static int __damon_stop(struct damon_ctx *ctx) if (tsk) { get_task_struct(tsk); mutex_unlock(&ctx->kdamond_lock); - kthread_stop(tsk); - put_task_struct(tsk); + kthread_stop_put(tsk); return 0; } mutex_unlock(&ctx->kdamond_lock); @@ -749,7 +780,7 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) struct damon_region *r; damon_for_each_region(r, t) { - trace_damon_aggregated(t, ti, r, damon_nr_regions(t)); + trace_damon_aggregated(ti, r, damon_nr_regions(t)); r->last_nr_accesses = r->nr_accesses; r->nr_accesses = 0; } @@ -763,12 +794,13 @@ static void damon_split_region_at(struct damon_target *t, static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; + unsigned int nr_accesses = r->nr_accesses_bp / 10000; sz = damon_sz_region(r); return s->pattern.min_sz_region <= sz && sz <= s->pattern.max_sz_region && - s->pattern.min_nr_accesses <= r->nr_accesses && - r->nr_accesses <= s->pattern.max_nr_accesses && + s->pattern.min_nr_accesses <= nr_accesses && + nr_accesses <= s->pattern.max_nr_accesses && s->pattern.min_age_region <= r->age && r->age <= s->pattern.max_age_region; } @@ -923,6 +955,33 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, struct timespec64 begin, end; unsigned long sz_applied = 0; int err = 0; + /* + * We plan to support multiple context per kdamond, as DAMON sysfs + * implies with 'nr_contexts' file. Nevertheless, only single context + * per kdamond is supported for now. So, we can simply use '0' context + * index here. + */ + unsigned int cidx = 0; + struct damos *siter; /* schemes iterator */ + unsigned int sidx = 0; + struct damon_target *titer; /* targets iterator */ + unsigned int tidx = 0; + bool do_trace = false; + + /* get indices for trace_damos_before_apply() */ + if (trace_damos_before_apply_enabled()) { + damon_for_each_scheme(siter, c) { + if (siter == s) + break; + sidx++; + } + damon_for_each_target(titer, c) { + if (titer == t) + break; + tidx++; + } + do_trace = true; + } if (c->ops.apply_scheme) { if (quota->esz && quota->charged_sz + sz > quota->esz) { @@ -937,8 +996,11 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, ktime_get_coarse_ts64(&begin); if (c->callback.before_damos_apply) err = c->callback.before_damos_apply(c, t, r, s); - if (!err) + if (!err) { + trace_damos_before_apply(cidx, sidx, tidx, r, + damon_nr_regions(t), do_trace); sz_applied = c->ops.apply_scheme(c, t, r, s); + } ktime_get_coarse_ts64(&end); quota->total_charged_ns += timespec64_to_ns(&end) - timespec64_to_ns(&begin); @@ -964,6 +1026,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; + if (c->passed_sample_intervals != s->next_apply_sis) + continue; + if (!s->wmarks.activated) continue; @@ -1056,18 +1121,37 @@ static void kdamond_apply_schemes(struct damon_ctx *c) struct damon_target *t; struct damon_region *r, *next_r; struct damos *s; + unsigned long sample_interval = c->attrs.sample_interval ? + c->attrs.sample_interval : 1; + bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { + if (c->passed_sample_intervals != s->next_apply_sis) + continue; + if (!s->wmarks.activated) continue; + has_schemes_to_apply = true; + damos_adjust_quota(c, s); } + if (!has_schemes_to_apply) + return; + damon_for_each_target(t, c) { damon_for_each_region_safe(r, next_r, t) damon_do_apply_schemes(c, t, r); } + + damon_for_each_scheme(s, c) { + if (c->passed_sample_intervals != s->next_apply_sis) + continue; + s->next_apply_sis += + (s->apply_interval_us ? s->apply_interval_us : + c->attrs.aggr_interval) / sample_interval; + } } /* @@ -1080,6 +1164,7 @@ static void damon_merge_two_regions(struct damon_target *t, l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); + l->nr_accesses_bp = l->nr_accesses * 10000; l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r); l->ar.end = r->ar.end; damon_destroy_region(r, t); @@ -1151,6 +1236,8 @@ static void damon_split_region_at(struct damon_target *t, new->age = r->age; new->last_nr_accesses = r->last_nr_accesses; + new->nr_accesses_bp = r->nr_accesses_bp; + new->nr_accesses = r->nr_accesses; damon_insert_region(new, r, damon_next_region(r), t); } @@ -1245,12 +1332,10 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric) { - struct sysinfo i; - switch (metric) { case DAMOS_WMARK_FREE_MEM_RATE: - si_meminfo(&i); - return i.freeram * 1000 / i.totalram; + return global_zone_page_state(NR_FREE_PAGES) * 1000 / + totalram_pages(); default: break; } @@ -1332,11 +1417,19 @@ static void kdamond_init_intervals_sis(struct damon_ctx *ctx) { unsigned long sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; + unsigned long apply_interval; + struct damos *scheme; ctx->passed_sample_intervals = 0; ctx->next_aggregation_sis = ctx->attrs.aggr_interval / sample_interval; ctx->next_ops_update_sis = ctx->attrs.ops_update_interval / sample_interval; + + damon_for_each_scheme(scheme, ctx) { + apply_interval = scheme->apply_interval_us ? + scheme->apply_interval_us : ctx->attrs.aggr_interval; + scheme->next_apply_sis = apply_interval / sample_interval; + } } /* @@ -1389,19 +1482,28 @@ static int kdamond_fn(void *data) if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - sample_interval = ctx->attrs.sample_interval ? - ctx->attrs.sample_interval : 1; if (ctx->passed_sample_intervals == next_aggregation_sis) { - ctx->next_aggregation_sis = next_aggregation_sis + - ctx->attrs.aggr_interval / sample_interval; kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) break; - if (!list_empty(&ctx->schemes)) - kdamond_apply_schemes(ctx); + } + + /* + * do kdamond_apply_schemes() after kdamond_merge_regions() if + * possible, to reduce overhead + */ + if (!list_empty(&ctx->schemes)) + kdamond_apply_schemes(ctx); + + sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + if (ctx->passed_sample_intervals == next_aggregation_sis) { + ctx->next_aggregation_sis = next_aggregation_sis + + ctx->attrs.aggr_interval / sample_interval; + kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->ops.reset_aggregated) @@ -1515,6 +1617,76 @@ int damon_set_region_biggest_system_ram_default(struct damon_target *t, return damon_set_regions(t, &addr_range, 1); } +/* + * damon_moving_sum() - Calculate an inferred moving sum value. + * @mvsum: Inferred sum of the last @len_window values. + * @nomvsum: Non-moving sum of the last discrete @len_window window values. + * @len_window: The number of last values to take care of. + * @new_value: New value that will be added to the pseudo moving sum. + * + * Moving sum (moving average * window size) is good for handling noise, but + * the cost of keeping past values can be high for arbitrary window size. This + * function implements a lightweight pseudo moving sum function that doesn't + * keep the past window values. + * + * It simply assumes there was no noise in the past, and get the no-noise + * assumed past value to drop from @nomvsum and @len_window. @nomvsum is a + * non-moving sum of the last window. For example, if @len_window is 10 and we + * have 25 values, @nomvsum is the sum of the 11th to 20th values of the 25 + * values. Hence, this function simply drops @nomvsum / @len_window from + * given @mvsum and add @new_value. + * + * For example, if @len_window is 10 and @nomvsum is 50, the last 10 values for + * the last window could be vary, e.g., 0, 10, 0, 10, 0, 10, 0, 0, 0, 20. For + * calculating next moving sum with a new value, we should drop 0 from 50 and + * add the new value. However, this function assumes it got value 5 for each + * of the last ten times. Based on the assumption, when the next value is + * measured, it drops the assumed past value, 5 from the current sum, and add + * the new value to get the updated pseduo-moving average. + * + * This means the value could have errors, but the errors will be disappeared + * for every @len_window aligned calls. For example, if @len_window is 10, the + * pseudo moving sum with 11th value to 19th value would have an error. But + * the sum with 20th value will not have the error. + * + * Return: Pseudo-moving average after getting the @new_value. + */ +static unsigned int damon_moving_sum(unsigned int mvsum, unsigned int nomvsum, + unsigned int len_window, unsigned int new_value) +{ + return mvsum - nomvsum / len_window + new_value; +} + +/** + * damon_update_region_access_rate() - Update the access rate of a region. + * @r: The DAMON region to update for its access check result. + * @accessed: Whether the region has accessed during last sampling interval. + * @attrs: The damon_attrs of the DAMON context. + * + * Update the access rate of a region with the region's last sampling interval + * access check result. + * + * Usually this will be called by &damon_operations->check_accesses callback. + */ +void damon_update_region_access_rate(struct damon_region *r, bool accessed, + struct damon_attrs *attrs) +{ + unsigned int len_window = 1; + + /* + * sample_interval can be zero, but cannot be larger than + * aggr_interval, owing to validation of damon_set_attrs(). + */ + if (attrs->sample_interval) + len_window = damon_max_nr_accesses(attrs); + r->nr_accesses_bp = damon_moving_sum(r->nr_accesses_bp, + r->last_nr_accesses * 10000, len_window, + accessed ? 10000 : 0); + + if (accessed) + r->nr_accesses++; +} + static int __init damon_init(void) { damon_region_cache = KMEM_CACHE(damon_region, 0); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 124f0f8c97..dc0ea1fc30 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -278,7 +278,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, goto fail; pos += parsed; - scheme = damon_new_scheme(&pattern, action, "a, &wmarks); + scheme = damon_new_scheme(&pattern, action, 0, "a, + &wmarks); if (!scheme) goto fail; diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 3071e08e8b..3de2916a65 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -158,6 +158,8 @@ static struct damos *damon_lru_sort_new_scheme( pattern, /* (de)prioritize on LRU-lists */ action, + /* for each aggregation interval */ + 0, /* under the quota. */ "a, /* (De)activate this according to the watermarks. */ @@ -183,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres) return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO); } +static void damon_lru_sort_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_lru_sort_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *hot_scheme, *cold_scheme; + struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL; unsigned int hot_thres, cold_thres; int err = 0; @@ -193,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void) if (err) return err; + damon_for_each_scheme(scheme, ctx) { + if (!old_hot_scheme) { + old_hot_scheme = scheme; + continue; + } + old_cold_scheme = scheme; + } + hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) * hot_thres_access_freq / 1000; - scheme = damon_lru_sort_new_hot_scheme(hot_thres); - if (!scheme) + hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres); + if (!hot_scheme) return -ENOMEM; - damon_set_schemes(ctx, &scheme, 1); + if (old_hot_scheme) + damon_lru_sort_copy_quota_status(&hot_scheme->quota, + &old_hot_scheme->quota); cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval; - scheme = damon_lru_sort_new_cold_scheme(cold_thres); - if (!scheme) + cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres); + if (!cold_scheme) { + damon_destroy_scheme(hot_scheme); return -ENOMEM; - damon_add_scheme(ctx, scheme); + } + if (old_cold_scheme) + damon_lru_sort_copy_quota_status(&cold_scheme->quota, + &old_cold_scheme->quota); + + damon_set_schemes(ctx, &hot_scheme, 1); + damon_add_scheme(ctx, cold_scheme); return damon_set_region_biggest_system_ram_default(target, &monitor_region_start, diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 909db25efb..081e2a3257 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -148,7 +148,8 @@ out: return accessed; } -static void __damon_pa_check_access(struct damon_region *r) +static void __damon_pa_check_access(struct damon_region *r, + struct damon_attrs *attrs) { static unsigned long last_addr; static unsigned long last_folio_sz = PAGE_SIZE; @@ -157,14 +158,12 @@ static void __damon_pa_check_access(struct damon_region *r) /* If the region is in the last checked page, reuse the result */ if (ALIGN_DOWN(last_addr, last_folio_sz) == ALIGN_DOWN(r->sampling_addr, last_folio_sz)) { - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); return; } last_accessed = damon_pa_young(r->sampling_addr, &last_folio_sz); - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); last_addr = r->sampling_addr; } @@ -177,7 +176,7 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) { - __damon_pa_check_access(r); + __damon_pa_check_access(r, &ctx->attrs); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); } } diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 648d2a8552..66e190f037 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -142,15 +142,28 @@ static struct damos *damon_reclaim_new_scheme(void) &pattern, /* page out those, as soon as found */ DAMOS_PAGEOUT, + /* for each aggregation interval */ + 0, /* under the quota. */ &damon_reclaim_quota, /* (De)activate this according to the watermarks. */ &damon_reclaim_wmarks); } +static void damon_reclaim_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_reclaim_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *old_scheme; struct damos_filter *filter; int err = 0; @@ -162,6 +175,11 @@ static int damon_reclaim_apply_parameters(void) scheme = damon_reclaim_new_scheme(); if (!scheme) return -ENOMEM; + if (!list_empty(&ctx->schemes)) { + damon_for_each_scheme(old_scheme, ctx) + damon_reclaim_copy_quota_status(&scheme->quota, + &old_scheme->quota); + } if (skip_anon) { filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true); if (!filter) { diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index fd482a0639..5ff081226e 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -49,6 +49,8 @@ int damon_sysfs_schemes_update_regions_start( struct damon_sysfs_schemes *sysfs_schemes, struct damon_ctx *ctx, bool total_bytes_only); +bool damos_sysfs_regions_upd_done(void); + int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx); int damon_sysfs_schemes_clear_regions( diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 36dcd881a1..786b06239c 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -31,7 +31,7 @@ static struct damon_sysfs_scheme_region *damon_sysfs_scheme_region_alloc( return NULL; sysfs_region->kobj = (struct kobject){}; sysfs_region->ar = region->ar; - sysfs_region->nr_accesses = region->nr_accesses; + sysfs_region->nr_accesses = region->nr_accesses_bp / 10000; sysfs_region->age = region->age; INIT_LIST_HEAD(&sysfs_region->list); return sysfs_region; @@ -113,11 +113,55 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = { * scheme regions directory */ +/* + * enum damos_sysfs_regions_upd_status - Represent DAMOS tried regions update + * status + * @DAMOS_TRIED_REGIONS_UPD_IDLE: Waiting for next request. + * @DAMOS_TRIED_REGIONS_UPD_STARTED: Update started. + * @DAMOS_TRIED_REGIONS_UPD_FINISHED: Update finished. + * + * Each DAMON-based operation scheme (&struct damos) has its own apply + * interval, and we need to expose the scheme tried regions based on only + * single snapshot. For this, we keep the tried regions update status for each + * scheme. The status becomes 'idle' at the beginning. + * + * Once the tried regions update request is received, the request handling + * start function (damon_sysfs_scheme_update_regions_start()) sets the status + * of all schemes as 'idle' again, and register ->before_damos_apply() and + * ->after_sampling() callbacks. + * + * Then, the first followup ->before_damos_apply() callback + * (damon_sysfs_before_damos_apply()) sets the status 'started'. The first + * ->after_sampling() callback (damon_sysfs_after_sampling()) after the call + * is called only after the scheme is completely applied + * to the given snapshot. Hence the callback knows the situation by showing + * 'started' status, and sets the status as 'finished'. Then, + * damon_sysfs_before_damos_apply() understands the situation by showing the + * 'finished' status and do nothing. + * + * If DAMOS is not applied to any region due to any reasons including the + * access pattern, the watermarks, the quotas, and the filters, + * ->before_damos_apply() will not be called back. Until the situation is + * changed, the update will not be finished. To avoid this, + * damon_sysfs_after_sampling() set the status as 'finished' if more than two + * apply intervals of the scheme is passed while the state is 'idle'. + * + * Finally, the tried regions request handling finisher function + * (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks. + */ +enum damos_sysfs_regions_upd_status { + DAMOS_TRIED_REGIONS_UPD_IDLE, + DAMOS_TRIED_REGIONS_UPD_STARTED, + DAMOS_TRIED_REGIONS_UPD_FINISHED, +}; + struct damon_sysfs_scheme_regions { struct kobject kobj; struct list_head regions_list; int nr_regions; unsigned long total_bytes; + enum damos_sysfs_regions_upd_status upd_status; + unsigned long upd_timeout_jiffies; }; static struct damon_sysfs_scheme_regions * @@ -133,6 +177,7 @@ damon_sysfs_scheme_regions_alloc(void) INIT_LIST_HEAD(®ions->regions_list); regions->nr_regions = 0; regions->total_bytes = 0; + regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE; return regions; } @@ -1124,6 +1169,7 @@ struct damon_sysfs_scheme { struct kobject kobj; enum damos_action action; struct damon_sysfs_access_pattern *access_pattern; + unsigned long apply_interval_us; struct damon_sysfs_quotas *quotas; struct damon_sysfs_watermarks *watermarks; struct damon_sysfs_scheme_filters *filters; @@ -1144,7 +1190,7 @@ static const char * const damon_sysfs_damos_action_strs[] = { }; static struct damon_sysfs_scheme *damon_sysfs_scheme_alloc( - enum damos_action action) + enum damos_action action, unsigned long apply_interval_us) { struct damon_sysfs_scheme *scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); @@ -1153,6 +1199,7 @@ static struct damon_sysfs_scheme *damon_sysfs_scheme_alloc( return NULL; scheme->kobj = (struct kobject){}; scheme->action = action; + scheme->apply_interval_us = apply_interval_us; return scheme; } @@ -1356,6 +1403,25 @@ static ssize_t action_store(struct kobject *kobj, struct kobj_attribute *attr, return -EINVAL; } +static ssize_t apply_interval_us_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_scheme *scheme = container_of(kobj, + struct damon_sysfs_scheme, kobj); + + return sysfs_emit(buf, "%lu\n", scheme->apply_interval_us); +} + +static ssize_t apply_interval_us_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_scheme *scheme = container_of(kobj, + struct damon_sysfs_scheme, kobj); + int err = kstrtoul(buf, 0, &scheme->apply_interval_us); + + return err ? err : count; +} + static void damon_sysfs_scheme_release(struct kobject *kobj) { kfree(container_of(kobj, struct damon_sysfs_scheme, kobj)); @@ -1364,8 +1430,12 @@ static void damon_sysfs_scheme_release(struct kobject *kobj) static struct kobj_attribute damon_sysfs_scheme_action_attr = __ATTR_RW_MODE(action, 0600); +static struct kobj_attribute damon_sysfs_scheme_apply_interval_us_attr = + __ATTR_RW_MODE(apply_interval_us, 0600); + static struct attribute *damon_sysfs_scheme_attrs[] = { &damon_sysfs_scheme_action_attr.attr, + &damon_sysfs_scheme_apply_interval_us_attr.attr, NULL, }; ATTRIBUTE_GROUPS(damon_sysfs_scheme); @@ -1416,7 +1486,11 @@ static int damon_sysfs_schemes_add_dirs(struct damon_sysfs_schemes *schemes, schemes->schemes_arr = schemes_arr; for (i = 0; i < nr_schemes; i++) { - scheme = damon_sysfs_scheme_alloc(DAMOS_STAT); + /* + * apply_interval_us as 0 means same to aggregation interval + * (same to before-apply_interval behavior) + */ + scheme = damon_sysfs_scheme_alloc(DAMOS_STAT, 0); if (!scheme) { damon_sysfs_schemes_rm_dirs(schemes); return -ENOMEM; @@ -1613,8 +1687,8 @@ static struct damos *damon_sysfs_mk_scheme( .low = sysfs_wmarks->low, }; - scheme = damon_new_scheme(&pattern, sysfs_scheme->action, "a, - &wmarks); + scheme = damon_new_scheme(&pattern, sysfs_scheme->action, + sysfs_scheme->apply_interval_us, "a, &wmarks); if (!scheme) return NULL; @@ -1644,6 +1718,7 @@ static void damon_sysfs_update_scheme(struct damos *scheme, scheme->pattern.max_age_region = access_pattern->age->max; scheme->action = sysfs_scheme->action; + scheme->apply_interval_us = sysfs_scheme->apply_interval_us; scheme->quota.ms = sysfs_quotas->ms; scheme->quota.sz = sysfs_quotas->sz; @@ -1750,6 +1825,10 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, return 0; sysfs_regions = sysfs_schemes->schemes_arr[schemes_idx]->tried_regions; + if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_FINISHED) + return 0; + if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_IDLE) + sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_STARTED; sysfs_regions->total_bytes += r->ar.end - r->ar.start; if (damos_regions_upd_total_bytes_only) return 0; @@ -1768,6 +1847,31 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, return 0; } +/* + * DAMON callback that called after each accesses sampling. While this + * callback is registered, damon_sysfs_lock should be held to ensure the + * regions directories exist. + */ +static int damon_sysfs_after_sampling(struct damon_ctx *ctx) +{ + struct damon_sysfs_schemes *sysfs_schemes = + damon_sysfs_schemes_for_damos_callback; + struct damon_sysfs_scheme_regions *sysfs_regions; + int i; + + for (i = 0; i < sysfs_schemes->nr; i++) { + sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; + if (sysfs_regions->upd_status == + DAMOS_TRIED_REGIONS_UPD_STARTED || + time_after(jiffies, + sysfs_regions->upd_timeout_jiffies)) + sysfs_regions->upd_status = + DAMOS_TRIED_REGIONS_UPD_FINISHED; + } + + return 0; +} + /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ int damon_sysfs_schemes_clear_regions( struct damon_sysfs_schemes *sysfs_schemes, @@ -1791,6 +1895,43 @@ int damon_sysfs_schemes_clear_regions( return 0; } +static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx) +{ + struct damos *scheme; + int i = 0; + + damon_for_each_scheme(scheme, ctx) { + if (i == n) + return scheme; + i++; + } + return NULL; +} + +static void damos_tried_regions_init_upd_status( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx) +{ + int i; + struct damos *scheme; + struct damon_sysfs_scheme_regions *sysfs_regions; + + for (i = 0; i < sysfs_schemes->nr; i++) { + sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; + scheme = damos_sysfs_nth_scheme(i, ctx); + if (!scheme) { + sysfs_regions->upd_status = + DAMOS_TRIED_REGIONS_UPD_FINISHED; + continue; + } + sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE; + sysfs_regions->upd_timeout_jiffies = jiffies + + 2 * usecs_to_jiffies(scheme->apply_interval_us ? + scheme->apply_interval_us : + ctx->attrs.aggr_interval); + } +} + /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ int damon_sysfs_schemes_update_regions_start( struct damon_sysfs_schemes *sysfs_schemes, @@ -1798,11 +1939,29 @@ int damon_sysfs_schemes_update_regions_start( { damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx); damon_sysfs_schemes_for_damos_callback = sysfs_schemes; + damos_tried_regions_init_upd_status(sysfs_schemes, ctx); damos_regions_upd_total_bytes_only = total_bytes_only; ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply; + ctx->callback.after_sampling = damon_sysfs_after_sampling; return 0; } +bool damos_sysfs_regions_upd_done(void) +{ + struct damon_sysfs_schemes *sysfs_schemes = + damon_sysfs_schemes_for_damos_callback; + struct damon_sysfs_scheme_regions *sysfs_regions; + int i; + + for (i = 0; i < sysfs_schemes->nr; i++) { + sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions; + if (sysfs_regions->upd_status != + DAMOS_TRIED_REGIONS_UPD_FINISHED) + return false; + } + return true; +} + /* * Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock. Caller * should unlock damon_sysfs_lock which held before @@ -1812,6 +1971,7 @@ int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx) { damon_sysfs_schemes_for_damos_callback = NULL; ctx->callback.before_damos_apply = NULL; + ctx->callback.after_sampling = NULL; damon_sysfs_schemes_region_idx = 0; return 0; } diff --git a/mm/damon/sysfs-test.h b/mm/damon/sysfs-test.h new file mode 100644 index 0000000000..73bdce2452 --- /dev/null +++ b/mm/damon/sysfs-test.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data Access Monitor Unit Tests + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#ifdef CONFIG_DAMON_SYSFS_KUNIT_TEST + +#ifndef _DAMON_SYSFS_TEST_H +#define _DAMON_SYSFS_TEST_H + +#include <kunit/test.h> + +static unsigned int nr_damon_targets(struct damon_ctx *ctx) +{ + struct damon_target *t; + unsigned int nr_targets = 0; + + damon_for_each_target(t, ctx) + nr_targets++; + + return nr_targets; +} + +static int __damon_sysfs_test_get_any_pid(int min, int max) +{ + struct pid *pid; + int i; + + for (i = min; i <= max; i++) { + pid = find_get_pid(i); + if (pid) { + put_pid(pid); + return i; + } + } + return -1; +} + +static void damon_sysfs_test_set_targets(struct kunit *test) +{ + struct damon_sysfs_targets *sysfs_targets; + struct damon_sysfs_target *sysfs_target; + struct damon_ctx *ctx; + + sysfs_targets = damon_sysfs_targets_alloc(); + sysfs_targets->nr = 1; + sysfs_targets->targets_arr = kmalloc_array(1, + sizeof(*sysfs_targets->targets_arr), GFP_KERNEL); + + sysfs_target = damon_sysfs_target_alloc(); + sysfs_target->pid = __damon_sysfs_test_get_any_pid(12, 100); + sysfs_target->regions = damon_sysfs_regions_alloc(); + sysfs_targets->targets_arr[0] = sysfs_target; + + ctx = damon_new_ctx(); + + damon_sysfs_set_targets(ctx, sysfs_targets); + KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(ctx)); + + sysfs_target->pid = __damon_sysfs_test_get_any_pid( + sysfs_target->pid + 1, 200); + damon_sysfs_set_targets(ctx, sysfs_targets); + KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(ctx)); + + damon_destroy_ctx(ctx); + kfree(sysfs_targets->targets_arr); + kfree(sysfs_targets); + kfree(sysfs_target); +} + +static struct kunit_case damon_sysfs_test_cases[] = { + KUNIT_CASE(damon_sysfs_test_set_targets), + {}, +}; + +static struct kunit_suite damon_sysfs_test_suite = { + .name = "damon-sysfs", + .test_cases = damon_sysfs_test_cases, +}; +kunit_test_suite(damon_sysfs_test_suite); + +#endif /* _DAMON_SYSFS_TEST_H */ + +#endif /* CONFIG_DAMON_SYSFS_KUNIT_TEST */ diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index b317f51dcc..7472404456 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1353,12 +1353,13 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) /* * damon_sysfs_cmd_request_callback() - DAMON callback for handling requests. - * @c: The DAMON context of the callback. + * @c: The DAMON context of the callback. + * @active: Whether @c is not deactivated due to watermarks. * * This function is periodically called back from the kdamond thread for @c. * Then, it checks if there is a waiting DAMON sysfs request and handles it. */ -static int damon_sysfs_cmd_request_callback(struct damon_ctx *c) +static int damon_sysfs_cmd_request_callback(struct damon_ctx *c, bool active) { struct damon_sysfs_kdamond *kdamond; bool total_bytes_only = false; @@ -1390,6 +1391,13 @@ static int damon_sysfs_cmd_request_callback(struct damon_ctx *c) goto keep_lock_out; } } else { + /* + * Continue regions updating if DAMON is till + * active and the update for all schemes is not + * finished. + */ + if (active && !damos_sysfs_regions_upd_done()) + goto keep_lock_out; err = damon_sysfs_upd_schemes_regions_stop(kdamond); damon_sysfs_schemes_regions_updating = false; } @@ -1409,6 +1417,24 @@ keep_lock_out: return err; } +static int damon_sysfs_after_wmarks_check(struct damon_ctx *c) +{ + /* + * after_wmarks_check() is called back while the context is deactivated + * by watermarks. + */ + return damon_sysfs_cmd_request_callback(c, false); +} + +static int damon_sysfs_after_aggregation(struct damon_ctx *c) +{ + /* + * after_aggregation() is called back only while the context is not + * deactivated by watermarks. + */ + return damon_sysfs_cmd_request_callback(c, true); +} + static struct damon_ctx *damon_sysfs_build_ctx( struct damon_sysfs_context *sys_ctx) { @@ -1424,8 +1450,8 @@ static struct damon_ctx *damon_sysfs_build_ctx( return ERR_PTR(err); } - ctx->callback.after_wmarks_check = damon_sysfs_cmd_request_callback; - ctx->callback.after_aggregation = damon_sysfs_cmd_request_callback; + ctx->callback.after_wmarks_check = damon_sysfs_after_wmarks_check; + ctx->callback.after_aggregation = damon_sysfs_after_aggregation; ctx->callback.before_terminate = damon_sysfs_before_terminate; return ctx; } @@ -1827,3 +1853,5 @@ out: return err; } subsys_initcall(damon_sysfs_init); + +#include "sysfs-test.h" diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index cf8a9fc5c9..a4d1f63c5b 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -558,23 +558,27 @@ static bool damon_va_young(struct mm_struct *mm, unsigned long addr, * r the region to be checked */ static void __damon_va_check_access(struct mm_struct *mm, - struct damon_region *r, bool same_target) + struct damon_region *r, bool same_target, + struct damon_attrs *attrs) { static unsigned long last_addr; static unsigned long last_folio_sz = PAGE_SIZE; static bool last_accessed; + if (!mm) { + damon_update_region_access_rate(r, false, attrs); + return; + } + /* If the region is in the last checked page, reuse the result */ if (same_target && (ALIGN_DOWN(last_addr, last_folio_sz) == ALIGN_DOWN(r->sampling_addr, last_folio_sz))) { - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); return; } last_accessed = damon_va_young(mm, r->sampling_addr, &last_folio_sz); - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); last_addr = r->sampling_addr; } @@ -589,15 +593,15 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { mm = damon_get_mm(t); - if (!mm) - continue; same_target = false; damon_for_each_region(r, t) { - __damon_va_check_access(mm, r, same_target); + __damon_va_check_access(mm, r, same_target, + &ctx->attrs); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); same_target = true; } - mmput(mm); + if (mm) + mmput(mm); } return max_nr_accesses; diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 48e329ea5b..e651500e59 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -1322,8 +1322,8 @@ static int __init debug_vm_pgtable(void) * true irrespective of the starting protection value for a * given page table entry. * - * Protection based vm_flags combinatins are always linear - * and increasing i.e starting from VM_NONE and going upto + * Protection based vm_flags combinations are always linear + * and increasing i.e starting from VM_NONE and going up to * (VM_SHARED | READ | WRITE | EXEC). */ #define VM_FLAGS_START (VM_NONE) diff --git a/mm/filemap.c b/mm/filemap.c index b1ef7be120..ad5b4aa049 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -131,11 +131,8 @@ static void page_cache_delete(struct address_space *mapping, mapping_set_update(&xas, mapping); - /* hugetlb pages are represented by a single entry in the xarray */ - if (!folio_test_hugetlb(folio)) { - xas_set_order(&xas, folio->index, folio_order(folio)); - nr = folio_nr_pages(folio); - } + xas_set_order(&xas, folio->index, folio_order(folio)); + nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -234,7 +231,7 @@ void filemap_free_folio(struct address_space *mapping, struct folio *folio) if (free_folio) free_folio(folio); - if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } @@ -819,7 +816,7 @@ void replace_page_cache_folio(struct folio *old, struct folio *new) new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(old, new); + mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); @@ -855,14 +852,15 @@ noinline int __filemap_add_folio(struct address_space *mapping, if (!huge) { int error = mem_cgroup_charge(folio, NULL, gfp); - VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) return error; charged = true; - xas_set_order(&xas, index, folio_order(folio)); - nr = folio_nr_pages(folio); } + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); + xas_set_order(&xas, index, folio_order(folio)); + nr = folio_nr_pages(folio); + gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; @@ -1135,32 +1133,13 @@ static void folio_wake_bit(struct folio *folio, int bit_nr) wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; - wait_queue_entry_t bookmark; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; - bookmark.flags = 0; - bookmark.private = NULL; - bookmark.func = NULL; - INIT_LIST_HEAD(&bookmark.entry); - spin_lock_irqsave(&q->lock, flags); - __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); - - while (bookmark.flags & WQ_FLAG_BOOKMARK) { - /* - * Take a breather from holding the lock, - * allow pages that finish wake up asynchronously - * to acquire the lock and remove themselves - * from wait queue - */ - spin_unlock_irqrestore(&q->lock, flags); - cpu_relax(); - spin_lock_irqsave(&q->lock, flags); - __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); - } + __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page @@ -1177,13 +1156,6 @@ static void folio_wake_bit(struct folio *folio, int bit_nr) spin_unlock_irqrestore(&q->lock, flags); } -static void folio_wake(struct folio *folio, int bit) -{ - if (!folio_test_waiters(folio)) - return; - folio_wake_bit(folio, bit); -} - /* * A choice of three behaviors for folio_wait_bit_common(): */ @@ -1484,29 +1456,6 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) } EXPORT_SYMBOL_GPL(folio_add_wait_queue); -#ifndef clear_bit_unlock_is_negative_byte - -/* - * PG_waiters is the high bit in the same byte as PG_lock. - * - * On x86 (and on many other architectures), we can clear PG_lock and - * test the sign bit at the same time. But if the architecture does - * not support that special operation, we just do this all by hand - * instead. - * - * The read of PG_waiters has to be after (or concurrently with) PG_locked - * being cleared, but a memory barrier should be unnecessary since it is - * in the same byte as PG_locked. - */ -static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) -{ - clear_bit_unlock(nr, mem); - /* smp_mb__after_atomic(); */ - return test_bit(PG_waiters, mem); -} - -#endif - /** * folio_unlock - Unlock a locked folio. * @folio: The folio. @@ -1522,12 +1471,42 @@ void folio_unlock(struct folio *folio) BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0))) + if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** + * folio_end_read - End read on a folio. + * @folio: The folio. + * @success: True if all reads completed successfully. + * + * When all reads against a folio have completed, filesystems should + * call this function to let the pagecache know that no more reads + * are outstanding. This will unlock the folio and wake up any thread + * sleeping on the lock. The folio will also be marked uptodate if all + * reads succeeded. + * + * Context: May be called from interrupt or process context. May not be + * called from NMI context. + */ +void folio_end_read(struct folio *folio, bool success) +{ + unsigned long mask = 1 << PG_locked; + + /* Must be in bottom byte for x86 to work */ + BUILD_BUG_ON(PG_uptodate > 7); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); + + if (likely(success)) + mask |= 1 << PG_uptodate; + if (folio_xor_flags_has_waiters(folio, mask)) + folio_wake_bit(folio, PG_locked); +} +EXPORT_SYMBOL(folio_end_read); + +/** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * @@ -1588,9 +1567,15 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. + * + * The folio must actually be under writeback. + * + * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { + VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); + /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing @@ -1607,14 +1592,11 @@ void folio_end_writeback(struct folio *folio) * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and - * reused before the folio_wake(). + * reused before the folio_wake_bit(). */ folio_get(folio); - if (!__folio_end_writeback(folio)) - BUG(); - - smp_mb__after_atomic(); - folio_wake(folio, PG_writeback); + if (__folio_end_writeback(folio)) + folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); folio_put(folio); } @@ -2040,7 +2022,7 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; - if (!xa_is_value(folio) && !folio_test_hugetlb(folio)) + if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } @@ -2104,7 +2086,7 @@ put: int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; - if (!xa_is_value(folio) && !folio_test_hugetlb(folio)) + if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } @@ -2122,51 +2104,13 @@ put: * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * - * The first folio may start before @start; if it does, it will contain - * @start. The final folio may extend beyond @end; if it does, it will - * contain @end. The folios have ascending indices. There may be gaps - * between the folios if there are indices which have no folio in the - * page cache. If folios are added to or removed from the page cache - * while this is running, they may or may not be found by this call. - * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { - XA_STATE(xas, &mapping->i_pages, *start); - struct folio *folio; - - rcu_read_lock(); - while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { - /* Skip over shadow, swap and DAX entries */ - if (xa_is_value(folio)) - continue; - if (!folio_batch_add(fbatch, folio)) { - unsigned long nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; - *start = folio->index + nr; - goto out; - } - } - - /* - * We come here when there is no page beyond @end. We take care to not - * overflow the index @start as it confuses some of the callers. This - * breaks the iteration when there is a page at index -1 but that is - * already broken anyway. - */ - if (end == (pgoff_t)-1) - *start = (pgoff_t)-1; - else - *start = end + 1; -out: - rcu_read_unlock(); - - return folio_batch_count(fbatch); + return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); @@ -2213,9 +2157,6 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; *start = folio->index + nr; goto out; } @@ -2232,10 +2173,7 @@ update_start: if (nr) { folio = fbatch->folios[nr - 1]; - if (folio_test_hugetlb(folio)) - *start = folio->index + 1; - else - *start = folio_next_index(folio); + *start = folio->index + folio_nr_pages(folio); } out: rcu_read_unlock(); @@ -2251,7 +2189,13 @@ EXPORT_SYMBOL(filemap_get_folios_contig); * @tag: The tag index * @fbatch: The batch to fill * - * Same as filemap_get_folios(), but only returning folios tagged with @tag. + * The first folio may start before @start; if it does, it will contain + * @start. The final folio may extend beyond @end; if it does, it will + * contain @end. The folios have ascending indices. There may be gaps + * between the folios if there are indices which have no folio in the + * page cache. If folios are added to or removed from the page cache + * while this is running, they may or may not be found by this call. + * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. @@ -2273,9 +2217,6 @@ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; *start = folio->index + nr; goto out; } @@ -3113,7 +3054,7 @@ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, /* * NOTE! This will make us return with VM_FAULT_RETRY, but with - * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT + * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) @@ -3123,13 +3064,14 @@ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* - * We didn't have the right flags to drop the mmap_lock, - * but all fault_handlers only check for fatal signals - * if we return VM_FAULT_RETRY, so we need to drop the - * mmap_lock here and return 0 if we don't have a fpin. + * We didn't have the right flags to drop the + * fault lock, but all fault_handlers only check + * for fatal signals if we return VM_FAULT_RETRY, + * so we need to drop the fault lock here and + * return 0 if we don't have a fpin. */ if (*fpin == NULL) - mmap_read_unlock(vmf->vma->vm_mm); + release_fault_lock(vmf); return 0; } } else @@ -3330,21 +3272,28 @@ retry_find: VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* - * We have a locked page in the page cache, now we need to check - * that it's up-to-date. If not, it is going to be due to an error. + * We have a locked folio in the page cache, now we need to check + * that it's up-to-date. If not, it is going to be due to an error, + * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* - * The page was in cache and uptodate and now it is not. - * Strange but possible since we didn't hold the page lock all - * the time. Let's drop everything get the invalidate lock and - * try again. + * If the invalidate lock is not held, the folio was in cache + * and uptodate and now it is not. Strange but possible since we + * didn't hold the page lock all the time. Let's drop + * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } + + /* + * OK, the folio is really not uptodate. This can be because the + * VMA has the VM_RAND_READ flag set, or because an error + * arose. Let's read it in directly. + */ goto page_not_uptodate; } @@ -3503,7 +3452,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ - if (!pte_none(vmf->pte[count])) + if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; @@ -3600,7 +3549,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - end = folio->index + folio_nr_pages(folio) - 1; + end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) @@ -3678,7 +3627,7 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } @@ -1471,6 +1471,9 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, long ret, pages_done; bool must_unlock = false; + if (!nr_pages) + return 0; + /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. @@ -1595,6 +1598,14 @@ retry: mmap_read_unlock(mm); *locked = 0; } + + /* + * Failing to pin anything implies something has gone wrong (except when + * FOLL_NOWAIT is specified). + */ + if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) + return -EFAULT; + return pages_done; } @@ -2227,12 +2238,11 @@ static bool is_valid_gup_args(struct page **pages, int *locked, /* * These flags not allowed to be specified externally to the gup * interfaces: - * - FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only + * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only and used on follow_page() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ - if (WARN_ON_ONCE(gup_flags & (FOLL_PIN | FOLL_TRIED | FOLL_UNLOCKABLE | - FOLL_REMOTE | FOLL_FAST_ONLY))) + if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 874000f97b..3f50578eb9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -37,6 +37,7 @@ #include <linux/page_owner.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> +#include <linux/compat.h> #include <asm/tlb.h> #include <asm/pgalloc.h> @@ -65,7 +66,11 @@ unsigned long transparent_hugepage_flags __read_mostly = (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); -static struct shrinker deferred_split_shrinker; +static struct shrinker *deferred_split_shrinker; +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc); static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; @@ -96,11 +101,11 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, return in_pf; /* - * Special VMA and hugetlb VMA. + * khugepaged special VMA and hugetlb VMA. * Must be checked after dax since some dax mappings may have * VM_MIXEDMAP set. */ - if (vm_flags & VM_NO_KHUGEPAGED) + if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) return false; /* @@ -128,12 +133,18 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, !hugepage_flags_always()))) return false; - /* Only regular file is valid */ - if (!in_pf && file_thp_enabled(vma)) - return true; - - if (!vma_is_anonymous(vma)) + if (!vma_is_anonymous(vma)) { + /* + * Trust that ->huge_fault() handlers know what they are doing + * in fault path. + */ + if (((in_pf || smaps)) && vma->vm_ops->huge_fault) + return true; + /* Only regular file is valid in collapse path */ + if (((!in_pf || smaps)) && file_thp_enabled(vma)) + return true; return false; + } if (vma_is_temporary_stack(vma)) return false; @@ -229,11 +240,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, return 0; } -static struct shrinker huge_zero_page_shrinker = { - .count_objects = shrink_huge_zero_page_count, - .scan_objects = shrink_huge_zero_page_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *huge_zero_page_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, @@ -454,6 +461,38 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) } #endif /* CONFIG_SYSFS */ +static int __init thp_shrinker_init(void) +{ + huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero"); + if (!huge_zero_page_shrinker) + return -ENOMEM; + + deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE | + SHRINKER_NONSLAB, + "thp-deferred_split"); + if (!deferred_split_shrinker) { + shrinker_free(huge_zero_page_shrinker); + return -ENOMEM; + } + + huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count; + huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan; + shrinker_register(huge_zero_page_shrinker); + + deferred_split_shrinker->count_objects = deferred_split_count; + deferred_split_shrinker->scan_objects = deferred_split_scan; + shrinker_register(deferred_split_shrinker); + + return 0; +} + +static void __init thp_shrinker_exit(void) +{ + shrinker_free(huge_zero_page_shrinker); + shrinker_free(deferred_split_shrinker); +} + static int __init hugepage_init(void) { int err; @@ -482,12 +521,9 @@ static int __init hugepage_init(void) if (err) goto err_slab; - err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); - if (err) - goto err_hzp_shrinker; - err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); + err = thp_shrinker_init(); if (err) - goto err_split_shrinker; + goto err_shrinker; /* * By default disable transparent hugepages on smaller systems, @@ -505,10 +541,8 @@ static int __init hugepage_init(void) return 0; err_khugepaged: - unregister_shrinker(&deferred_split_shrinker); -err_split_shrinker: - unregister_shrinker(&huge_zero_page_shrinker); -err_hzp_shrinker: + thp_shrinker_exit(); +err_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); @@ -599,7 +633,10 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, { loff_t off_end = off + len; loff_t off_align = round_up(off, size); - unsigned long len_pad, ret; + unsigned long len_pad, ret, off_sub; + + if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall()) + return 0; if (off_end <= off_align || (off_end - off_align) < size) return 0; @@ -625,7 +662,13 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, if (ret == addr) return addr; - ret += (off - ret) & (size - 1); + off_sub = (off - ret) & (size - 1); + + if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown && + !off_sub) + return ret + size; + + ret += off_sub; return ret; } @@ -1349,7 +1392,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) if (folio_ref_count(folio) == 1) { pmd_t entry; - page_move_anon_rmap(page, vma); + folio_move_anon_rmap(folio, vma); + SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { @@ -1490,9 +1534,9 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; pmd_t oldpmd = vmf->orig_pmd; pmd_t pmd; - struct page *page; + struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = NUMA_NO_NODE; + int nid = NUMA_NO_NODE; int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); bool migrated = false, writable = false; int flags = 0; @@ -1514,36 +1558,34 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) can_change_pmd_writable(vma, vmf->address, pmd)) writable = true; - page = vm_normal_page_pmd(vma, haddr, pmd); - if (!page) + folio = vm_normal_folio_pmd(vma, haddr, pmd); + if (!folio) goto out_map; /* See similar comment in do_numa_page for explanation */ if (!writable) flags |= TNF_NO_GROUP; - page_nid = page_to_nid(page); + nid = folio_nid(folio); /* * 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); - + if (node_is_toptier(nid)) + last_cpupid = folio_last_cpupid(folio); + target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags); if (target_nid == NUMA_NO_NODE) { - put_page(page); + folio_put(folio); goto out_map; } spin_unlock(vmf->ptl); writable = false; - migrated = migrate_misplaced_page(page, vma, target_nid); + migrated = migrate_misplaced_folio(folio, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; - page_nid = target_nid; + nid = target_nid; } else { flags |= TNF_MIGRATE_FAIL; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); @@ -1555,9 +1597,8 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) } out: - if (page_nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, - flags); + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); return 0; @@ -1825,7 +1866,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); - struct page *page = pfn_swap_entry_to_page(entry); + struct folio *folio = page_folio(pfn_swap_entry_to_page(entry)); pmd_t newpmd; VM_BUG_ON(!is_pmd_migration_entry(*pmd)); @@ -1834,7 +1875,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, * A protection check is difficult so * just be safe and disable write */ - if (PageAnon(page)) + if (folio_test_anon(folio)) entry = make_readable_exclusive_migration_entry(swp_offset(entry)); else entry = make_readable_migration_entry(swp_offset(entry)); @@ -1856,7 +1897,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, #endif if (prot_numa) { - struct page *page; + struct folio *folio; bool toptier; /* * Avoid trapping faults against the zero page. The read-only @@ -1869,8 +1910,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_protnone(*pmd)) goto unlock; - page = pmd_page(*pmd); - toptier = node_is_toptier(page_to_nid(page)); + folio = page_folio(pmd_page(*pmd)); + toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa * balancing is disabled @@ -1881,7 +1922,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && !toptier) - xchg_page_access_time(page, jiffies_to_msecs(jiffies)); + folio_xchg_access_time(folio, + jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical @@ -2483,7 +2525,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail, if (page_is_idle(head)) set_page_idle(page_tail); - page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); + folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); /* * always add to the tail because some iterators expect new @@ -2791,7 +2833,7 @@ void folio_undo_large_rmappable(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(&folio->_deferred_list); + list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } @@ -2830,7 +2872,7 @@ void deferred_split_folio(struct folio *folio) #ifdef CONFIG_MEMCG if (memcg) set_shrinker_bit(memcg, folio_nid(folio), - deferred_split_shrinker.id); + deferred_split_shrinker->id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); @@ -2904,14 +2946,6 @@ next: return split; } -static struct shrinker deferred_split_shrinker = { - .count_objects = deferred_split_count, - .scan_objects = deferred_split_scan, - .seeks = DEFAULT_SEEKS, - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | - SHRINKER_NONSLAB, -}; - #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5e6c4d367d..6feb3e0630 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -984,7 +984,7 @@ static long region_count(struct resv_map *resv, long f, long t) /* * Convert the address within this vma to the page offset within - * the mapping, in pagecache page units; huge pages here. + * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) @@ -993,13 +993,6 @@ static pgoff_t vma_hugecache_offset(struct hstate *h, (vma->vm_pgoff >> huge_page_order(h)); } -pgoff_t linear_hugepage_index(struct vm_area_struct *vma, - unsigned long address) -{ - return vma_hugecache_offset(hstate_vma(vma), vma, address); -} -EXPORT_SYMBOL_GPL(linear_hugepage_index); - /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. @@ -1485,7 +1478,7 @@ static int hstate_next_node_to_alloc(struct hstate *h, } /* - * helper for remove_pool_huge_page() - return the previously saved + * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. @@ -1759,7 +1752,12 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; - if (hugetlb_vmemmap_restore(h, &folio->page)) { + /* + * If folio is not vmemmap optimized (!clear_dtor), then the folio + * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio + * can only be passed hugetlb pages and will BUG otherwise. + */ + if (clear_dtor && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1821,22 +1819,22 @@ static void free_hpage_workfn(struct work_struct *work) node = llist_del_all(&hpage_freelist); while (node) { - struct page *page; + struct folio *folio; struct hstate *h; - page = container_of((struct address_space **)node, - struct page, mapping); + folio = container_of((struct address_space **)node, + struct folio, mapping); node = node->next; - page->mapping = NULL; + folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ - h = size_to_hstate(page_size(page)); + h = size_to_hstate(folio_size(folio)); - __update_and_free_hugetlb_folio(h, page_folio(page)); + __update_and_free_hugetlb_folio(h, folio); cond_resched(); } @@ -1868,13 +1866,93 @@ static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, schedule_work(&free_hpage_work); } -static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) +static void bulk_vmemmap_restore_error(struct hstate *h, + struct list_head *folio_list, + struct list_head *non_hvo_folios) { - struct page *page, *t_page; - struct folio *folio; + struct folio *folio, *t_folio; + + if (!list_empty(non_hvo_folios)) { + /* + * Free any restored hugetlb pages so that restore of the + * entire list can be retried. + * The idea is that in the common case of ENOMEM errors freeing + * hugetlb pages with vmemmap we will free up memory so that we + * can allocate vmemmap for more hugetlb pages. + */ + list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { + list_del(&folio->lru); + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, folio); + spin_unlock_irq(&hugetlb_lock); + update_and_free_hugetlb_folio(h, folio, false); + cond_resched(); + } + } else { + /* + * In the case where there are no folios which can be + * immediately freed, we loop through the list trying to restore + * vmemmap individually in the hope that someone elsewhere may + * have done something to cause success (such as freeing some + * memory). If unable to restore a hugetlb page, the hugetlb + * page is made a surplus page and removed from the list. + * If are able to restore vmemmap and free one hugetlb page, we + * quit processing the list to retry the bulk operation. + */ + list_for_each_entry_safe(folio, t_folio, folio_list, lru) + if (hugetlb_vmemmap_restore_folio(h, folio)) { + list_del(&folio->lru); + spin_lock_irq(&hugetlb_lock); + add_hugetlb_folio(h, folio, true); + spin_unlock_irq(&hugetlb_lock); + } else { + list_del(&folio->lru); + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, folio); + spin_unlock_irq(&hugetlb_lock); + update_and_free_hugetlb_folio(h, folio, false); + cond_resched(); + break; + } + } +} + +static void update_and_free_pages_bulk(struct hstate *h, + struct list_head *folio_list) +{ + long ret; + struct folio *folio, *t_folio; + LIST_HEAD(non_hvo_folios); + + /* + * First allocate required vmemmmap (if necessary) for all folios. + * Carefully handle errors and free up any available hugetlb pages + * in an effort to make forward progress. + */ +retry: + ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); + if (ret < 0) { + bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); + goto retry; + } + + /* + * At this point, list should be empty, ret should be >= 0 and there + * should only be pages on the non_hvo_folios list. + * Do note that the non_hvo_folios list could be empty. + * Without HVO enabled, ret will be 0 and there is no need to call + * __clear_hugetlb_destructor as this was done previously. + */ + VM_WARN_ON(!list_empty(folio_list)); + VM_WARN_ON(ret < 0); + if (!list_empty(&non_hvo_folios) && ret) { + spin_lock_irq(&hugetlb_lock); + list_for_each_entry(folio, &non_hvo_folios, lru) + __clear_hugetlb_destructor(h, folio); + spin_unlock_irq(&hugetlb_lock); + } - list_for_each_entry_safe(page, t_page, list, lru) { - folio = page_folio(page); + list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } @@ -1938,6 +2016,7 @@ void free_huge_folio(struct folio *folio) pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; @@ -1967,16 +2046,21 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) h->nr_huge_pages_node[nid]++; } -static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) +static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - hugetlb_vmemmap_optimize(h, &folio->page); - INIT_LIST_HEAD(&folio->lru); folio_set_hugetlb(folio); + INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } +static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) +{ + init_new_hugetlb_folio(h, folio); + hugetlb_vmemmap_optimize_folio(h, folio); +} + static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { __prep_new_hugetlb_folio(h, folio); @@ -2110,20 +2194,6 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; } -pgoff_t hugetlb_basepage_index(struct page *page) -{ - struct page *page_head = compound_head(page); - pgoff_t index = page_index(page_head); - unsigned long compound_idx; - - if (compound_order(page_head) > MAX_ORDER) - compound_idx = page_to_pfn(page) - page_to_pfn(page_head); - else - compound_idx = page - page_head; - - return (index << compound_order(page_head)) + compound_idx; -} - static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) @@ -2187,16 +2257,9 @@ retry: return page_folio(page); } -/* - * Common helper to allocate a fresh hugetlb page. All specific allocators - * should use this function to get new hugetlb pages - * - * Note that returned page is 'frozen': ref count of head page and all tail - * pages is zero. - */ -static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, - gfp_t gfp_mask, int nid, nodemask_t *nmask, - nodemask_t *node_alloc_noretry) +static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h, + gfp_t gfp_mask, int nid, nodemask_t *nmask, + nodemask_t *node_alloc_noretry) { struct folio *folio; bool retry = false; @@ -2209,6 +2272,7 @@ retry: nid, nmask, node_alloc_noretry); if (!folio) return NULL; + if (hstate_is_gigantic(h)) { if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* @@ -2223,32 +2287,84 @@ retry: return NULL; } } - prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return folio; } +static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, + gfp_t gfp_mask, int nid, nodemask_t *nmask, + nodemask_t *node_alloc_noretry) +{ + struct folio *folio; + + folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, + node_alloc_noretry); + if (folio) + init_new_hugetlb_folio(h, folio); + return folio; +} + /* - * Allocates a fresh page to the hugetlb allocator pool in the node interleaved - * manner. + * Common helper to allocate a fresh hugetlb page. All specific allocators + * should use this function to get new hugetlb pages + * + * Note that returned page is 'frozen': ref count of head page and all tail + * pages is zero. */ -static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, - nodemask_t *node_alloc_noretry) +static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, + gfp_t gfp_mask, int nid, nodemask_t *nmask, + nodemask_t *node_alloc_noretry) { struct folio *folio; - int nr_nodes, node; + + folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, + node_alloc_noretry); + if (!folio) + return NULL; + + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); + return folio; +} + +static void prep_and_add_allocated_folios(struct hstate *h, + struct list_head *folio_list) +{ + unsigned long flags; + struct folio *folio, *tmp_f; + + /* Send list for bulk vmemmap optimization processing */ + hugetlb_vmemmap_optimize_folios(h, folio_list); + + /* Add all new pool pages to free lists in one lock cycle */ + spin_lock_irqsave(&hugetlb_lock, flags); + list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { + __prep_account_new_huge_page(h, folio_nid(folio)); + enqueue_hugetlb_folio(h, folio); + } + spin_unlock_irqrestore(&hugetlb_lock, flags); +} + +/* + * Allocates a fresh hugetlb page in a node interleaved manner. The page + * will later be added to the appropriate hugetlb pool. + */ +static struct folio *alloc_pool_huge_folio(struct hstate *h, + nodemask_t *nodes_allowed, + nodemask_t *node_alloc_noretry) +{ gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + int nr_nodes, node; for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { - folio = alloc_fresh_hugetlb_folio(h, gfp_mask, node, + struct folio *folio; + + folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); - if (folio) { - free_huge_folio(folio); /* free it into the hugepage allocator */ - return 1; - } + if (folio) + return folio; } - return 0; + return NULL; } /* @@ -2258,13 +2374,11 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ -static struct page *remove_pool_huge_page(struct hstate *h, - nodemask_t *nodes_allowed, - bool acct_surplus) +static struct folio *remove_pool_hugetlb_folio(struct hstate *h, + nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; - struct page *page = NULL; - struct folio *folio; + struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { @@ -2274,15 +2388,14 @@ static struct page *remove_pool_huge_page(struct hstate *h, */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { - page = list_entry(h->hugepage_freelists[node].next, - struct page, lru); - folio = page_folio(page); + folio = list_entry(h->hugepage_freelists[node].next, + struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } - return page; + return folio; } /* @@ -2350,17 +2463,23 @@ retry: * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. + * + * The folio_test_hugetlb check here is because + * remove_hugetlb_folio will clear hugetlb folio flag for + * non-vmemmap optimized hugetlb folios. */ - rc = hugetlb_vmemmap_restore(h, &folio->page); - if (!rc) { - update_and_free_hugetlb_folio(h, folio, false); - } else { - spin_lock_irq(&hugetlb_lock); - add_hugetlb_folio(h, folio, false); - h->max_huge_pages++; - spin_unlock_irq(&hugetlb_lock); - } + if (folio_test_hugetlb(folio)) { + rc = hugetlb_vmemmap_restore_folio(h, folio); + if (rc) { + spin_lock_irq(&hugetlb_lock); + add_hugetlb_folio(h, folio, false); + h->max_huge_pages++; + goto out; + } + } else + rc = 0; + update_and_free_hugetlb_folio(h, folio, false); return rc; } out: @@ -2518,24 +2637,6 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } -/* mempolicy aware migration callback */ -struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address) -{ - struct mempolicy *mpol; - nodemask_t *nodemask; - struct folio *folio; - gfp_t gfp_mask; - int node; - - gfp_mask = htlb_alloc_mask(h); - node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); - mpol_cond_put(mpol); - - return folio; -} - /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. @@ -2636,7 +2737,6 @@ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; - struct page *page; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); @@ -2657,15 +2757,17 @@ static void return_unused_surplus_pages(struct hstate *h, * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. - * remove_pool_huge_page() will balance the freed pages across the + * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { - page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1); - if (!page) + struct folio *folio; + + folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); + if (!folio) goto out; - list_add(&page->lru, &page_list); + list_add(&folio->lru, &page_list); } out: @@ -3047,11 +3149,20 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long map_chg, map_commit; + long map_chg, map_commit, nr_pages = pages_per_huge_page(h); long gbl_chg; - int ret, idx; + int memcg_charge_ret, ret, idx; struct hugetlb_cgroup *h_cg = NULL; + struct mem_cgroup *memcg; bool deferred_reserve; + gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; + + memcg = get_mem_cgroup_from_current(); + memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); + if (memcg_charge_ret == -ENOMEM) { + mem_cgroup_put(memcg); + return ERR_PTR(-ENOMEM); + } idx = hstate_index(h); /* @@ -3060,8 +3171,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); - if (map_chg < 0) + if (map_chg < 0) { + if (!memcg_charge_ret) + mem_cgroup_cancel_charge(memcg, nr_pages); + mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); + } /* * Processes that did not create the mapping will have no @@ -3072,10 +3187,8 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); - if (gbl_chg < 0) { - vma_end_reservation(h, vma, addr); - return ERR_PTR(-ENOSPC); - } + if (gbl_chg < 0) + goto out_end_reservation; /* * Even though there was no reservation in the region/reserve @@ -3157,6 +3270,11 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); } + + if (!memcg_charge_ret) + mem_cgroup_commit_charge(folio, memcg); + mem_cgroup_put(memcg); + return folio; out_uncharge_cgroup: @@ -3168,7 +3286,11 @@ out_uncharge_cgroup_reservation: out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); +out_end_reservation: vma_end_reservation(h, vma, addr); + if (!memcg_charge_ret) + mem_cgroup_cancel_charge(memcg, nr_pages); + mem_cgroup_put(memcg); return ERR_PTR(-ENOSPC); } @@ -3203,6 +3325,16 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) } found: + + /* + * Only initialize the head struct page in memmap_init_reserved_pages, + * rest of the struct pages will be initialized by the HugeTLB + * subsystem itself. + * The head struct page is used to get folio information by the HugeTLB + * subsystem like zone id and node id. + */ + memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), + huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -3210,29 +3342,102 @@ found: return 1; } +/* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ +static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, + unsigned long start_page_number, + unsigned long end_page_number) +{ + enum zone_type zone = zone_idx(folio_zone(folio)); + int nid = folio_nid(folio); + unsigned long head_pfn = folio_pfn(folio); + unsigned long pfn, end_pfn = head_pfn + end_page_number; + int ret; + + for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone, nid); + prep_compound_tail((struct page *)folio, pfn - head_pfn); + ret = page_ref_freeze(page, 1); + VM_BUG_ON(!ret); + } +} + +static void __init hugetlb_folio_init_vmemmap(struct folio *folio, + struct hstate *h, + unsigned long nr_pages) +{ + int ret; + + /* Prepare folio head */ + __folio_clear_reserved(folio); + __folio_set_head(folio); + ret = folio_ref_freeze(folio, 1); + VM_BUG_ON(!ret); + /* Initialize the necessary tail struct pages */ + hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); + prep_compound_head((struct page *)folio, huge_page_order(h)); +} + +static void __init prep_and_add_bootmem_folios(struct hstate *h, + struct list_head *folio_list) +{ + unsigned long flags; + struct folio *folio, *tmp_f; + + /* Send list for bulk vmemmap optimization processing */ + hugetlb_vmemmap_optimize_folios(h, folio_list); + + /* Add all new pool pages to free lists in one lock cycle */ + spin_lock_irqsave(&hugetlb_lock, flags); + list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { + if (!folio_test_hugetlb_vmemmap_optimized(folio)) { + /* + * If HVO fails, initialize all tail struct pages + * We do not worry about potential long lock hold + * time as this is early in boot and there should + * be no contention. + */ + hugetlb_folio_init_tail_vmemmap(folio, + HUGETLB_VMEMMAP_RESERVE_PAGES, + pages_per_huge_page(h)); + } + __prep_account_new_huge_page(h, folio_nid(folio)); + enqueue_hugetlb_folio(h, folio); + } + spin_unlock_irqrestore(&hugetlb_lock, flags); +} + /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_ORDER) pages. */ static void __init gather_bootmem_prealloc(void) { + LIST_HEAD(folio_list); struct huge_bootmem_page *m; + struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); - struct folio *folio = page_folio(page); - struct hstate *h = m->hstate; + struct folio *folio = (void *)page; + + h = m->hstate; + /* + * It is possible to have multiple huge page sizes (hstates) + * in this list. If so, process each size separately. + */ + if (h != prev_h && prev_h != NULL) + prep_and_add_bootmem_folios(prev_h, &folio_list); + prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); - if (prep_compound_gigantic_folio(folio, huge_page_order(h))) { - WARN_ON(folio_test_reserved(folio)); - prep_new_hugetlb_folio(h, folio, folio_nid(folio)); - free_huge_folio(folio); /* add to the hugepage allocator */ - } else { - /* VERY unlikely inflated ref count on a tail page */ - free_gigantic_folio(folio, huge_page_order(h)); - } + + hugetlb_folio_init_vmemmap(folio, h, + HUGETLB_VMEMMAP_RESERVE_PAGES); + init_new_hugetlb_folio(h, folio); + list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages @@ -3242,7 +3447,10 @@ static void __init gather_bootmem_prealloc(void) adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } + + prep_and_add_bootmem_folios(h, &folio_list); } + static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; @@ -3274,9 +3482,22 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) h->max_huge_pages_node[nid] = i; } +/* + * NOTE: this routine is called in different contexts for gigantic and + * non-gigantic pages. + * - For gigantic pages, this is called early in the boot process and + * pages are allocated from memblock allocated or something similar. + * Gigantic pages are actually added to pools later with the routine + * gather_bootmem_prealloc. + * - For non-gigantic pages, this is called later in the boot process after + * all of mm is up and functional. Pages are allocated from buddy and + * then added to hugetlb pools. + */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; + struct folio *folio; + LIST_HEAD(folio_list); nodemask_t *node_alloc_noretry; bool node_specific_alloc = false; @@ -3318,14 +3539,25 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { + /* + * gigantic pages not added to list as they are not + * added to pools now. + */ if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; - } else if (!alloc_pool_huge_page(h, - &node_states[N_MEMORY], - node_alloc_noretry)) - break; + } else { + folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], + node_alloc_noretry); + if (!folio) + break; + list_add(&folio->lru, &folio_list); + } cond_resched(); } + + /* list will be empty if hstate_is_gigantic */ + prep_and_add_allocated_folios(h, &folio_list); + if (i < h->max_huge_pages) { char buf[32]; @@ -3398,15 +3630,15 @@ static void try_to_free_low(struct hstate *h, unsigned long count, * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { - struct page *page, *next; + struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; - list_for_each_entry_safe(page, next, freel, lru) { + list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; - if (PageHighMem(page)) + if (folio_test_highmem(folio)) continue; - remove_hugetlb_folio(h, page_folio(page), false); - list_add(&page->lru, &page_list); + remove_hugetlb_folio(h, folio, false); + list_add(&folio->lru, &page_list); } } @@ -3459,8 +3691,9 @@ found: static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { - unsigned long min_count, ret; - struct page *page; + unsigned long min_count; + unsigned long allocated; + struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); @@ -3491,7 +3724,9 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, if (nid != NUMA_NO_NODE) { unsigned long old_count = count; - count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; + count += persistent_huge_pages(h) - + (h->nr_huge_pages_node[nid] - + h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted @@ -3535,7 +3770,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, break; } - while (count > persistent_huge_pages(h)) { + allocated = 0; + while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page @@ -3546,15 +3782,32 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, /* yield cpu to avoid soft lockup */ cond_resched(); - ret = alloc_pool_huge_page(h, nodes_allowed, + folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry); - spin_lock_irq(&hugetlb_lock); - if (!ret) + if (!folio) { + prep_and_add_allocated_folios(h, &page_list); + spin_lock_irq(&hugetlb_lock); goto out; + } + + list_add(&folio->lru, &page_list); + allocated++; /* Bail for signals. Probably ctrl-c from user */ - if (signal_pending(current)) + if (signal_pending(current)) { + prep_and_add_allocated_folios(h, &page_list); + spin_lock_irq(&hugetlb_lock); goto out; + } + + spin_lock_irq(&hugetlb_lock); + } + + /* Add allocated pages to the pool */ + if (!list_empty(&page_list)) { + spin_unlock_irq(&hugetlb_lock); + prep_and_add_allocated_folios(h, &page_list); + spin_lock_irq(&hugetlb_lock); } /* @@ -3580,11 +3833,11 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { - page = remove_pool_huge_page(h, nodes_allowed, 0); - if (!page) + folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); + if (!folio) break; - list_add(&page->lru, &page_list); + list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); @@ -3619,13 +3872,21 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); - rc = hugetlb_vmemmap_restore(h, &folio->page); - if (rc) { - /* Allocation of vmemmmap failed, we can not demote folio */ - spin_lock_irq(&hugetlb_lock); - folio_ref_unfreeze(folio, 1); - add_hugetlb_folio(h, folio, false); - return rc; + /* + * If vmemmap already existed for folio, the remove routine above would + * have cleared the hugetlb folio flag. Hence the folio is technically + * no longer a hugetlb folio. hugetlb_vmemmap_restore_folio can only be + * passed hugetlb folios and will BUG otherwise. + */ + if (folio_test_hugetlb(folio)) { + rc = hugetlb_vmemmap_restore_folio(h, folio); + if (rc) { + /* Allocation of vmemmmap failed, we can not demote folio */ + spin_lock_irq(&hugetlb_lock); + folio_ref_unfreeze(folio, 1); + add_hugetlb_folio(h, folio, false); + return rc; + } } /* @@ -4321,7 +4582,7 @@ void __init hugetlb_add_hstate(unsigned int order) return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); - BUG_ON(order == 0); + BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); h = &hstates[hugetlb_max_hstate++]; mutex_init(&h->resize_lock); h->order = order; @@ -5004,7 +5265,7 @@ bool is_hugetlb_entry_migration(pte_t pte) return false; } -static bool is_hugetlb_entry_hwpoisoned(pte_t pte) +bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; @@ -5612,8 +5873,10 @@ retry_avoidcopy: * owner and can reuse this page. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { - if (!PageAnonExclusive(&old_folio->page)) - page_move_anon_rmap(&old_folio->page, vma); + if (!PageAnonExclusive(&old_folio->page)) { + folio_move_anon_rmap(old_folio, vma); + SetPageAnonExclusive(&old_folio->page); + } if (likely(!unshare)) set_huge_ptep_writable(vma, haddr, ptep); @@ -5759,7 +6022,7 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; - pgoff_t idx = vma_hugecache_offset(h, vma, address); + pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); @@ -5776,6 +6039,7 @@ int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping struct hstate *h = hstate_inode(inode); int err; + idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); @@ -5883,7 +6147,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * before we get page_table_lock. */ new_folio = false; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) @@ -6192,7 +6456,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - pagecache_folio = filemap_lock_folio(mapping, idx); + pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } @@ -6206,21 +6470,28 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { - struct vm_fault vmf = { - .vma = vma, - .address = haddr, - .real_address = address, - .flags = flags, - }; + if (!userfaultfd_wp_async(vma)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = address, + .flags = flags, + }; - spin_unlock(ptl); - if (pagecache_folio) { - folio_unlock(pagecache_folio); - folio_put(pagecache_folio); + spin_unlock(ptl); + if (pagecache_folio) { + folio_unlock(pagecache_folio); + folio_put(pagecache_folio); + } + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + return handle_userfault(&vmf, VM_UFFD_WP); } - hugetlb_vma_unlock_read(vma); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - return handle_userfault(&vmf, VM_UFFD_WP); + + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(mm, haddr, ptep, entry, + huge_page_size(hstate_vma(vma))); + /* Fallthrough to CoW */ } /* @@ -6278,6 +6549,26 @@ out_mutex: #ifdef CONFIG_USERFAULTFD /* + * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). + */ +static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct mempolicy *mpol; + nodemask_t *nodemask; + struct folio *folio; + gfp_t gfp_mask; + int node; + + gfp_mask = htlb_alloc_mask(h); + node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); + folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); + mpol_cond_put(mpol); + + return folio; +} + +/* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ @@ -6325,7 +6616,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (is_continue) { ret = -EFAULT; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index dedd2edb07..aa4486bd39 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -262,12 +262,6 @@ static int __hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, if (hugetlb_cgroup_disabled()) goto done; - /* - * We don't charge any cgroup if the compound page have less - * than 3 pages. - */ - if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) - goto done; again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); @@ -397,9 +391,6 @@ static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, if (hugetlb_cgroup_disabled() || !h_cg) return; - if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) - return; - page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); @@ -869,15 +860,8 @@ void __init hugetlb_cgroup_file_init(void) { struct hstate *h; - for_each_hstate(h) { - /* - * Add cgroup control files only if the huge page consists - * of more than two normal pages. This is because we use - * page[2].private for storing cgroup details. - */ - if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER) - __hugetlb_cgroup_file_init(hstate_index(h)); - } + for_each_hstate(h) + __hugetlb_cgroup_file_init(hstate_index(h)); } /* diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4b9734777f..87818ee7f0 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -13,6 +13,7 @@ #include <linux/pgtable.h> #include <linux/moduleparam.h> #include <linux/bootmem_info.h> +#include <linux/mmdebug.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "hugetlb_vmemmap.h" @@ -26,6 +27,8 @@ * @reuse_addr: the virtual address of the @reuse_page page. * @vmemmap_pages: the list head of the vmemmap pages that can be freed * or is mapped from. + * @flags: used to modify behavior in vmemmap page table walking + * operations. */ struct vmemmap_remap_walk { void (*remap_pte)(pte_t *pte, unsigned long addr, @@ -34,9 +37,15 @@ struct vmemmap_remap_walk { struct page *reuse_page; unsigned long reuse_addr; struct list_head *vmemmap_pages; + +/* Skip the TLB flush when we split the PMD */ +#define VMEMMAP_SPLIT_NO_TLB_FLUSH BIT(0) +/* Skip the TLB flush when we remap the PTE */ +#define VMEMMAP_REMAP_NO_TLB_FLUSH BIT(1) + unsigned long flags; }; -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush) { pmd_t __pmd; int i; @@ -79,7 +88,8 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); - flush_tlb_kernel_range(start, start + PMD_SIZE); + if (flush) + flush_tlb_kernel_range(start, start + PMD_SIZE); } else { pte_free_kernel(&init_mm, pgtable); } @@ -126,11 +136,20 @@ static int vmemmap_pmd_range(pud_t *pud, unsigned long addr, do { int ret; - ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK); + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, + !(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH)); if (ret) return ret; next = pmd_addr_end(addr, end); + + /* + * We are only splitting, not remapping the hugetlb vmemmap + * pages. + */ + if (!walk->remap_pte) + continue; + vmemmap_pte_range(pmd, addr, next, walk); } while (pmd++, addr = next, addr != end); @@ -197,7 +216,8 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, return ret; } while (pgd++, addr = next, addr != end); - flush_tlb_kernel_range(start, end); + if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH)) + flush_tlb_kernel_range(start, end); return 0; } @@ -250,7 +270,7 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, } entry = mk_pte(walk->reuse_page, pgprot); - list_add_tail(&page->lru, walk->vmemmap_pages); + list_add(&page->lru, walk->vmemmap_pages); set_pte_at(&init_mm, addr, pte, entry); } @@ -297,6 +317,36 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, } /** + * vmemmap_remap_split - split the vmemmap virtual address range [@start, @end) + * backing PMDs of the directmap into PTEs + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * + * Return: %0 on success, negative error code otherwise. + */ +static int vmemmap_remap_split(unsigned long start, unsigned long end, + unsigned long reuse) +{ + int ret; + struct vmemmap_remap_walk walk = { + .remap_pte = NULL, + .flags = VMEMMAP_SPLIT_NO_TLB_FLUSH, + }; + + /* See the comment in the vmemmap_remap_free(). */ + BUG_ON(start - reuse != PAGE_SIZE); + + mmap_read_lock(&init_mm); + ret = vmemmap_remap_range(reuse, end, &walk); + mmap_read_unlock(&init_mm); + + return ret; +} + +/** * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end) * to the page which @reuse is mapped to, then free vmemmap * which the range are mapped to. @@ -305,22 +355,26 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, * @end: end address of the vmemmap virtual address range that we want to * remap. * @reuse: reuse address. + * @vmemmap_pages: list to deposit vmemmap pages to be freed. It is callers + * responsibility to free pages. + * @flags: modifications to vmemmap_remap_walk flags * * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_free(unsigned long start, unsigned long end, - unsigned long reuse) + unsigned long reuse, + struct list_head *vmemmap_pages, + unsigned long flags) { int ret; - LIST_HEAD(vmemmap_pages); struct vmemmap_remap_walk walk = { .remap_pte = vmemmap_remap_pte, .reuse_addr = reuse, - .vmemmap_pages = &vmemmap_pages, + .vmemmap_pages = vmemmap_pages, + .flags = flags, }; - int nid = page_to_nid((struct page *)start); - gfp_t gfp_mask = GFP_KERNEL | __GFP_THISNODE | __GFP_NORETRY | - __GFP_NOWARN; + int nid = page_to_nid((struct page *)reuse); + gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; /* * Allocate a new head vmemmap page to avoid breaking a contiguous @@ -334,7 +388,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, if (walk.reuse_page) { copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); - list_add(&walk.reuse_page->lru, &vmemmap_pages); + list_add(&walk.reuse_page->lru, vmemmap_pages); } /* @@ -365,22 +419,21 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, walk = (struct vmemmap_remap_walk) { .remap_pte = vmemmap_restore_pte, .reuse_addr = reuse, - .vmemmap_pages = &vmemmap_pages, + .vmemmap_pages = vmemmap_pages, + .flags = 0, }; vmemmap_remap_range(reuse, end, &walk); } mmap_read_unlock(&init_mm); - free_vmemmap_page_list(&vmemmap_pages); - return ret; } static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, struct list_head *list) { - gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_THISNODE; + gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL; unsigned long nr_pages = (end - start) >> PAGE_SHIFT; int nid = page_to_nid((struct page *)start); struct page *page, *next; @@ -389,7 +442,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, page = alloc_pages_node(nid, gfp_mask, 0); if (!page) goto out; - list_add_tail(&page->lru, list); + list_add(&page->lru, list); } return 0; @@ -408,17 +461,19 @@ out: * @end: end address of the vmemmap virtual address range that we want to * remap. * @reuse: reuse address. + * @flags: modifications to vmemmap_remap_walk flags * * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_alloc(unsigned long start, unsigned long end, - unsigned long reuse) + unsigned long reuse, unsigned long flags) { LIST_HEAD(vmemmap_pages); struct vmemmap_remap_walk walk = { .remap_pte = vmemmap_restore_pte, .reuse_addr = reuse, .vmemmap_pages = &vmemmap_pages, + .flags = flags, }; /* See the comment in the vmemmap_remap_free(). */ @@ -440,23 +495,15 @@ EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON); core_param(hugetlb_free_vmemmap, vmemmap_optimize_enabled, bool, 0); -/** - * hugetlb_vmemmap_restore - restore previously optimized (by - * hugetlb_vmemmap_optimize()) vmemmap pages which - * will be reallocated and remapped. - * @h: struct hstate. - * @head: the head page whose vmemmap pages will be restored. - * - * Return: %0 if @head's vmemmap pages have been reallocated and remapped, - * negative error code otherwise. - */ -int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head) +static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio, unsigned long flags) { int ret; + struct page *head = &folio->page; unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; unsigned long vmemmap_reuse; - if (!HPageVmemmapOptimized(head)) + VM_WARN_ON_ONCE(!PageHuge(head)); + if (!folio_test_hugetlb_vmemmap_optimized(folio)) return 0; vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); @@ -470,18 +517,77 @@ int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head) * When a HugeTLB page is freed to the buddy allocator, previously * discarded vmemmap pages must be allocated and remapping. */ - ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, vmemmap_reuse); + ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, vmemmap_reuse, flags); if (!ret) { - ClearHPageVmemmapOptimized(head); + folio_clear_hugetlb_vmemmap_optimized(folio); static_branch_dec(&hugetlb_optimize_vmemmap_key); } return ret; } +/** + * hugetlb_vmemmap_restore_folio - restore previously optimized (by + * hugetlb_vmemmap_optimize_folio()) vmemmap pages which + * will be reallocated and remapped. + * @h: struct hstate. + * @folio: the folio whose vmemmap pages will be restored. + * + * Return: %0 if @folio's vmemmap pages have been reallocated and remapped, + * negative error code otherwise. + */ +int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio) +{ + return __hugetlb_vmemmap_restore_folio(h, folio, 0); +} + +/** + * hugetlb_vmemmap_restore_folios - restore vmemmap for every folio on the list. + * @h: hstate. + * @folio_list: list of folios. + * @non_hvo_folios: Output list of folios for which vmemmap exists. + * + * Return: number of folios for which vmemmap was restored, or an error code + * if an error was encountered restoring vmemmap for a folio. + * Folios that have vmemmap are moved to the non_hvo_folios + * list. Processing of entries stops when the first error is + * encountered. The folio that experienced the error and all + * non-processed folios will remain on folio_list. + */ +long hugetlb_vmemmap_restore_folios(const struct hstate *h, + struct list_head *folio_list, + struct list_head *non_hvo_folios) +{ + struct folio *folio, *t_folio; + long restored = 0; + long ret = 0; + + list_for_each_entry_safe(folio, t_folio, folio_list, lru) { + if (folio_test_hugetlb_vmemmap_optimized(folio)) { + ret = __hugetlb_vmemmap_restore_folio(h, folio, + VMEMMAP_REMAP_NO_TLB_FLUSH); + if (ret) + break; + restored++; + } + + /* Add non-optimized folios to output list */ + list_move(&folio->lru, non_hvo_folios); + } + + if (restored) + flush_tlb_all(); + if (!ret) + ret = restored; + return ret; +} + /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head) { + if (HPageVmemmapOptimized((struct page *)head)) + return false; + if (!READ_ONCE(vmemmap_optimize_enabled)) return false; @@ -535,39 +641,136 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h return true; } +static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h, + struct folio *folio, + struct list_head *vmemmap_pages, + unsigned long flags) +{ + int ret = 0; + struct page *head = &folio->page; + unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; + unsigned long vmemmap_reuse; + + VM_WARN_ON_ONCE(!PageHuge(head)); + if (!vmemmap_should_optimize(h, head)) + return ret; + + static_branch_inc(&hugetlb_optimize_vmemmap_key); + /* + * Very Subtle + * If VMEMMAP_REMAP_NO_TLB_FLUSH is set, TLB flushing is not performed + * immediately after remapping. As a result, subsequent accesses + * and modifications to struct pages associated with the hugetlb + * page could be to the OLD struct pages. Set the vmemmap optimized + * flag here so that it is copied to the new head page. This keeps + * the old and new struct pages in sync. + * If there is an error during optimization, we will immediately FLUSH + * the TLB and clear the flag below. + */ + folio_set_hugetlb_vmemmap_optimized(folio); + + vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); + vmemmap_reuse = vmemmap_start; + vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE; + + /* + * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end) + * to the page which @vmemmap_reuse is mapped to. Add pages previously + * mapping the range to vmemmap_pages list so that they can be freed by + * the caller. + */ + ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, + vmemmap_pages, flags); + if (ret) { + static_branch_dec(&hugetlb_optimize_vmemmap_key); + folio_clear_hugetlb_vmemmap_optimized(folio); + } + + return ret; +} + /** - * hugetlb_vmemmap_optimize - optimize @head page's vmemmap pages. + * hugetlb_vmemmap_optimize_folio - optimize @folio's vmemmap pages. * @h: struct hstate. - * @head: the head page whose vmemmap pages will be optimized. + * @folio: the folio whose vmemmap pages will be optimized. * - * This function only tries to optimize @head's vmemmap pages and does not + * This function only tries to optimize @folio's vmemmap pages and does not * guarantee that the optimization will succeed after it returns. The caller - * can use HPageVmemmapOptimized(@head) to detect if @head's vmemmap pages - * have been optimized. + * can use folio_test_hugetlb_vmemmap_optimized(@folio) to detect if @folio's + * vmemmap pages have been optimized. */ -void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head) +void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) +{ + LIST_HEAD(vmemmap_pages); + + __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, 0); + free_vmemmap_page_list(&vmemmap_pages); +} + +static int hugetlb_vmemmap_split(const struct hstate *h, struct page *head) { unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; unsigned long vmemmap_reuse; if (!vmemmap_should_optimize(h, head)) - return; - - static_branch_inc(&hugetlb_optimize_vmemmap_key); + return 0; vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); vmemmap_reuse = vmemmap_start; vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE; /* - * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end) - * to the page which @vmemmap_reuse is mapped to, then free the pages - * which the range [@vmemmap_start, @vmemmap_end] is mapped to. + * Split PMDs on the vmemmap virtual address range [@vmemmap_start, + * @vmemmap_end] */ - if (vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse)) - static_branch_dec(&hugetlb_optimize_vmemmap_key); - else - SetHPageVmemmapOptimized(head); + return vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse); +} + +void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list) +{ + struct folio *folio; + LIST_HEAD(vmemmap_pages); + + list_for_each_entry(folio, folio_list, lru) { + int ret = hugetlb_vmemmap_split(h, &folio->page); + + /* + * Spliting the PMD requires allocating a page, thus lets fail + * early once we encounter the first OOM. No point in retrying + * as it can be dynamically done on remap with the memory + * we get back from the vmemmap deduplication. + */ + if (ret == -ENOMEM) + break; + } + + flush_tlb_all(); + + list_for_each_entry(folio, folio_list, lru) { + int ret = __hugetlb_vmemmap_optimize_folio(h, folio, + &vmemmap_pages, + VMEMMAP_REMAP_NO_TLB_FLUSH); + + /* + * Pages to be freed may have been accumulated. If we + * encounter an ENOMEM, free what we have and try again. + * This can occur in the case that both spliting fails + * halfway and head page allocation also failed. In this + * case __hugetlb_vmemmap_optimize_folio() would free memory + * allowing more vmemmap remaps to occur. + */ + if (ret == -ENOMEM && !list_empty(&vmemmap_pages)) { + flush_tlb_all(); + free_vmemmap_page_list(&vmemmap_pages); + INIT_LIST_HEAD(&vmemmap_pages); + __hugetlb_vmemmap_optimize_folio(h, folio, + &vmemmap_pages, + VMEMMAP_REMAP_NO_TLB_FLUSH); + } + } + + flush_tlb_all(); + free_vmemmap_page_list(&vmemmap_pages); } static struct ctl_table hugetlb_vmemmap_sysctls[] = { @@ -586,7 +789,7 @@ static int __init hugetlb_vmemmap_init(void) const struct hstate *h; /* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */ - BUILD_BUG_ON(__NR_USED_SUBPAGE * sizeof(struct page) > HUGETLB_VMEMMAP_RESERVE_SIZE); + BUILD_BUG_ON(__NR_USED_SUBPAGE > HUGETLB_VMEMMAP_RESERVE_PAGES); for_each_hstate(h) { if (hugetlb_vmemmap_optimizable(h)) { diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h index 25bd0e0024..2fcae92d33 100644 --- a/mm/hugetlb_vmemmap.h +++ b/mm/hugetlb_vmemmap.h @@ -10,15 +10,20 @@ #define _LINUX_HUGETLB_VMEMMAP_H #include <linux/hugetlb.h> -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP -int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head); -void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head); - /* * Reserve one vmemmap page, all vmemmap addresses are mapped to it. See - * Documentation/vm/vmemmap_dedup.rst. + * Documentation/mm/vmemmap_dedup.rst. */ #define HUGETLB_VMEMMAP_RESERVE_SIZE PAGE_SIZE +#define HUGETLB_VMEMMAP_RESERVE_PAGES (HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page)) + +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio); +long hugetlb_vmemmap_restore_folios(const struct hstate *h, + struct list_head *folio_list, + struct list_head *non_hvo_folios); +void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio); +void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list); static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h) { @@ -38,12 +43,24 @@ static inline unsigned int hugetlb_vmemmap_optimizable_size(const struct hstate return size > 0 ? size : 0; } #else -static inline int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head) +static inline int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio) { return 0; } -static inline void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head) +static long hugetlb_vmemmap_restore_folios(const struct hstate *h, + struct list_head *folio_list, + struct list_head *non_hvo_folios) +{ + list_splice_init(folio_list, non_hvo_folios); + return 0; +} + +static inline void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) +{ +} + +static inline void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list) { } diff --git a/mm/internal.h b/mm/internal.h index 30cf724ddb..b61034bd50 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -415,6 +415,15 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) void folio_undo_large_rmappable(struct folio *folio); +static inline struct folio *page_rmappable_folio(struct page *page) +{ + struct folio *folio = (struct folio *)page; + + if (folio && folio_order(folio) > 1) + folio_prep_large_rmappable(folio); + return folio; +} + static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; @@ -586,6 +595,56 @@ extern long faultin_vma_page_range(struct vm_area_struct *vma, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); + +/* + * NOTE: This function can't tell whether the folio is "fully mapped" in the + * range. + * "fully mapped" means all the pages of folio is associated with the page + * table of range while this function just check whether the folio range is + * within the range [start, end). Function caller needs to do page table + * check if it cares about the page table association. + * + * Typical usage (like mlock or madvise) is: + * Caller knows at least 1 page of folio is associated with page table of VMA + * and the range [start, end) is intersect with the VMA range. Caller wants + * to know whether the folio is fully associated with the range. It calls + * this function to check whether the folio is in the range first. Then checks + * the page table to know whether the folio is fully mapped to the range. + */ +static inline bool +folio_within_range(struct folio *folio, struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + pgoff_t pgoff, addr; + unsigned long vma_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + + VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); + if (start > end) + return false; + + if (start < vma->vm_start) + start = vma->vm_start; + + if (end > vma->vm_end) + end = vma->vm_end; + + pgoff = folio_pgoff(folio); + + /* if folio start address is not in vma range */ + if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) + return false; + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + + return !(addr < start || end - addr < folio_size(folio)); +} + +static inline bool +folio_within_vma(struct folio *folio, struct vm_area_struct *vma) +{ + return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); +} + /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, @@ -594,14 +653,10 @@ extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, * mlock is usually called at the end of page_add_*_rmap(), munlock at * the end of page_remove_rmap(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). - * - * @compound is used to include pmd mappings of THPs, but filter out - * pte mappings of THPs, which cannot be consistently counted: a pte - * mapping of the THP head cannot be distinguished by the page alone. */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. @@ -611,17 +666,24 @@ static inline void mlock_vma_folio(struct folio *folio, * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ - if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED) && - (compound || !folio_test_large(folio))) + if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { - if (unlikely(vma->vm_flags & VM_LOCKED) && - (compound || !folio_test_large(folio))) + /* + * munlock if the function is called. Ideally, we should only + * do munlock if any page of folio is unmapped from VMA and + * cause folio not fully mapped to VMA. + * + * But it's not easy to confirm that's the situation. So we + * always munlock the folio and page reclaim will correct it + * if it's wrong. + */ + if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } @@ -930,7 +992,7 @@ void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags); void free_zone_device_page(struct page *page); @@ -949,6 +1011,13 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); +/* + * mm/mmap.c + */ +struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta); + enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, @@ -964,6 +1033,9 @@ enum { FOLL_UNLOCKABLE = 1 << 21, }; +#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ + FOLL_FAST_ONLY | FOLL_UNLOCKABLE) + /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the @@ -1154,4 +1226,57 @@ struct vma_prepare { struct vm_area_struct *remove; struct vm_area_struct *remove2; }; + +void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid); + +/* shrinker related functions */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority); + +#ifdef CONFIG_SHRINKER_DEBUG +static inline __printf(2, 0) int shrinker_debugfs_name_alloc( + struct shrinker *shrinker, const char *fmt, va_list ap) +{ + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + + return shrinker->name ? 0 : -ENOMEM; +} + +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) +{ + kfree_const(shrinker->name); + shrinker->name = NULL; +} + +extern int shrinker_debugfs_add(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); +#else /* CONFIG_SHRINKER_DEBUG */ +static inline int shrinker_debugfs_add(struct shrinker *shrinker) +{ + return 0; +} +static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, + const char *fmt, va_list ap) +{ + return 0; +} +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) +{ +} +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) +{ + *debugfs_id = -1; + return NULL; +} +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} +#endif /* CONFIG_SHRINKER_DEBUG */ + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d37831b851..8b06bab5c4 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -562,7 +562,6 @@ void kasan_restore_multi_shot(bool enabled); * code. Declared here to avoid warnings about missing declarations. */ -asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(void *globals, ssize_t size); void __asan_unregister_globals(void *globals, ssize_t size); void __asan_handle_no_return(void); diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index b61cc6a425..34515a106c 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -5,7 +5,7 @@ * Author: Andrey Ryabinin <a.ryabinin@samsung.com> */ -#define pr_fmt(fmt) "kasan_test: " fmt +#define pr_fmt(fmt) "kasan: test: " fmt #include <kunit/test.h> #include <linux/bitops.h> @@ -91,10 +91,11 @@ static void kasan_test_exit(struct kunit *test) } /** - * KUNIT_EXPECT_KASAN_FAIL() - check that the executed expression produces a - * KASAN report; causes a test failure otherwise. This relies on a KUnit - * resource named "kasan_status". Do not use this name for KUnit resources - * outside of KASAN tests. + * KUNIT_EXPECT_KASAN_FAIL - check that the executed expression produces a + * KASAN report; causes a KUnit test failure otherwise. + * + * @test: Currently executing KUnit test. + * @expression: Expression that must produce a KASAN report. * * For hardware tag-based KASAN, when a synchronous tag fault happens, tag * checking is auto-disabled. When this happens, this test handler reenables @@ -492,14 +493,17 @@ static void kmalloc_oob_memset_2(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 2; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, memset_size)); kfree(ptr); } @@ -507,14 +511,17 @@ static void kmalloc_oob_memset_4(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 4; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, memset_size)); kfree(ptr); } @@ -522,14 +529,17 @@ static void kmalloc_oob_memset_8(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 8; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, memset_size)); kfree(ptr); } @@ -537,14 +547,17 @@ static void kmalloc_oob_memset_16(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 16; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, memset_size)); kfree(ptr); } @@ -1097,11 +1110,9 @@ static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr) KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr)); KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr)); KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr)); - -#if defined(clear_bit_unlock_is_negative_byte) - KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = - clear_bit_unlock_is_negative_byte(nr, addr)); -#endif + if (nr < 7) + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = + xor_unlock_is_negative_byte(1 << nr, addr)); } static void kasan_bitops_generic(struct kunit *test) diff --git a/mm/kasan/kasan_test_module.c b/mm/kasan/kasan_test_module.c index 7be7bed456..8b7b3ea2c7 100644 --- a/mm/kasan/kasan_test_module.c +++ b/mm/kasan/kasan_test_module.c @@ -5,7 +5,7 @@ * Author: Andrey Ryabinin <a.ryabinin@samsung.com> */ -#define pr_fmt(fmt) "kasan test: %s " fmt, __func__ +#define pr_fmt(fmt) "kasan: test: " fmt #include <linux/mman.h> #include <linux/module.h> diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 152dca73f3..ca45291567 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -8,6 +8,8 @@ * Based on code by Dmitry Chernenkov. */ +#define pr_fmt(fmt) "kasan: " fmt + #include <linux/gfp.h> #include <linux/hash.h> #include <linux/kernel.h> @@ -414,7 +416,7 @@ static int __init kasan_cpu_quarantine_init(void) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online", kasan_cpu_online, kasan_cpu_offline); if (ret < 0) - pr_err("kasan cpu quarantine register failed [%d]\n", ret); + pr_err("cpu quarantine register failed [%d]\n", ret); return ret; } late_initcall(kasan_cpu_quarantine_init); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 6e3cb118d2..e77facb629 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -538,7 +538,7 @@ void kasan_report_invalid_free(void *ptr, unsigned long ip, enum kasan_report_ty start_report(&flags, true); - memset(&info, 0, sizeof(info)); + __memset(&info, 0, sizeof(info)); info.type = type; info.access_addr = ptr; info.access_size = 0; @@ -576,7 +576,7 @@ bool kasan_report(const void *addr, size_t size, bool is_write, start_report(&irq_flags, true); - memset(&info, 0, sizeof(info)); + __memset(&info, 0, sizeof(info)); info.type = KASAN_REPORT_ACCESS; info.access_addr = addr; info.access_size = size; diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c index 51a1e8a887..99cbcd73cf 100644 --- a/mm/kasan/report_generic.c +++ b/mm/kasan/report_generic.c @@ -220,7 +220,7 @@ static bool __must_check tokenize_frame_descr(const char **frame_descr, const size_t tok_len = sep - *frame_descr; if (tok_len + 1 > max_tok_len) { - pr_err("KASAN internal error: frame description too long: %s\n", + pr_err("internal error: frame description too long: %s\n", *frame_descr); return false; } @@ -233,7 +233,7 @@ static bool __must_check tokenize_frame_descr(const char **frame_descr, *frame_descr = sep + 1; if (value != NULL && kstrtoul(token, 10, value)) { - pr_err("KASAN internal error: not a valid number: %s\n", token); + pr_err("internal error: not a valid number: %s\n", token); return false; } @@ -323,7 +323,7 @@ static bool __must_check get_address_stack_frame_info(const void *addr, frame = (const unsigned long *)(mem_ptr + KASAN_GRANULE_SIZE); if (frame[0] != KASAN_CURRENT_STACK_FRAME_MAGIC) { - pr_err("KASAN internal error: frame info validation failed; invalid marker: %lu\n", + pr_err("internal error: frame has invalid marker: %lu\n", frame[0]); return false; } diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index dd772f9d0f..d687f09a7a 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -324,7 +324,7 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, if (!page) return -ENOMEM; - memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); + __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 88433cc25d..0646547178 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -91,7 +91,7 @@ static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); -static struct kmem_cache *mm_slot_cache __read_mostly; +static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; @@ -524,15 +524,15 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte, } } -static bool is_refcount_suitable(struct page *page) +static bool is_refcount_suitable(struct folio *folio) { int expected_refcount; - expected_refcount = total_mapcount(page); - if (PageSwapCache(page)) - expected_refcount += compound_nr(page); + expected_refcount = folio_mapcount(folio); + if (folio_test_swapcache(folio)) + expected_refcount += folio_nr_pages(folio); - return page_count(page) == expected_refcount; + return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, @@ -542,6 +542,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, struct list_head *compound_pagelist) { struct page *page = NULL; + struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; @@ -576,7 +577,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } - VM_BUG_ON_PAGE(!PageAnon(page), page); + folio = page_folio(page); + VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); if (page_mapcount(page) > 1) { ++shared; @@ -588,16 +590,15 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } } - if (PageCompound(page)) { - struct page *p; - page = compound_head(page); + if (folio_test_large(folio)) { + struct folio *f; /* * Check if we have dealt with the compound page * already */ - list_for_each_entry(p, compound_pagelist, lru) { - if (page == p) + list_for_each_entry(f, compound_pagelist, lru) { + if (folio == f) goto next; } } @@ -608,7 +609,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * is needed to serialize against split_huge_page * when invoked from the VM. */ - if (!trylock_page(page)) { + if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } @@ -624,8 +625,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ - if (!is_refcount_suitable(page)) { - unlock_page(page); + if (!is_refcount_suitable(folio)) { + folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } @@ -634,27 +635,27 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ - if (!isolate_lru_page(page)) { - unlock_page(page); + if (!folio_isolate_lru(folio)) { + folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_is_file_lru(page), - compound_nr(page)); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - if (PageCompound(page)) - list_add_tail(&page->lru, compound_pagelist); + if (folio_test_large(folio)) + list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && - (pte_young(pteval) || page_is_young(page) || - PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + (pte_young(pteval) || folio_test_young(folio) || + folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; @@ -668,13 +669,13 @@ next: result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, + trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); - trace_mm_collapse_huge_page_isolate(page, none_or_zero, + trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } @@ -887,16 +888,16 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node, +static bool hpage_collapse_alloc_folio(struct folio **folio, gfp_t gfp, int node, nodemask_t *nmask) { - *hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask); - if (unlikely(!*hpage)) { + *folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, nmask); + + if (unlikely(!*folio)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return false; } - folio_prep_large_rmappable((struct folio *)*hpage); count_vm_event(THP_COLLAPSE_ALLOC); return true; } @@ -1063,17 +1064,20 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, int node = hpage_collapse_find_target_node(cc); struct folio *folio; - if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) + if (!hpage_collapse_alloc_folio(&folio, gfp, node, &cc->alloc_nmask)) { + *hpage = NULL; return SCAN_ALLOC_HUGE_PAGE_FAIL; + } - folio = page_folio(*hpage); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *hpage = NULL; return SCAN_CGROUP_CHARGE_FAIL; } - count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC); + count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); + + *hpage = folio_page(folio, 0); return SCAN_SUCCEED; } @@ -1247,6 +1251,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; + struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; @@ -1333,29 +1338,28 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, } } - page = compound_head(page); - + folio = page_folio(page); /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ - node = page_to_nid(page); + node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; - if (!PageLRU(page)) { + if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } - if (PageLocked(page)) { + if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } - if (!PageAnon(page)) { + if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } @@ -1370,7 +1374,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ - if (!is_refcount_suitable(page)) { + if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } @@ -1380,8 +1384,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && - (pte_young(pteval) || page_is_young(page) || - PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + (pte_young(pteval) || folio_test_young(folio) || + folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } @@ -1403,7 +1407,7 @@ out_unmap: *mmap_locked = false; } out: - trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, + trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } @@ -1473,7 +1477,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); - struct page *hpage; + struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; @@ -1506,19 +1510,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; - hpage = find_lock_page(vma->vm_file->f_mapping, + folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); - if (!hpage) + if (IS_ERR(folio)) return SCAN_PAGE_NULL; - if (!PageHead(hpage)) { - result = SCAN_FAIL; - goto drop_hpage; - } - - if (compound_order(hpage) != HPAGE_PMD_ORDER) { + if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; - goto drop_hpage; + goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); @@ -1532,13 +1531,13 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, */ goto maybe_install_pmd; default: - goto drop_hpage; + goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ - goto drop_hpage; + goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; @@ -1563,7 +1562,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort; } @@ -1578,7 +1577,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. - * So page lock of hpage does not protect from it, so we must not drop + * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) @@ -1602,7 +1601,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: - * page lock stops more PTEs of the hpage being faulted in, but + * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ @@ -1611,7 +1610,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto abort; } page = vm_normal_page(vma, addr, ptent); - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort; /* @@ -1630,8 +1629,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); } /* step 4: remove empty page table */ @@ -1655,14 +1654,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd - ? set_huge_pmd(vma, haddr, pmd, hpage) + ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; - goto drop_hpage; + goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); @@ -1670,9 +1669,9 @@ abort: spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); -drop_hpage: - unlock_page(hpage); - put_page(hpage); +drop_folio: + folio_unlock(folio); + folio_put(folio); return result; } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 54c2c90d3a..5501363d6b 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -583,6 +583,19 @@ static void __remove_object(struct kmemleak_object *object) object->del_state |= DELSTATE_REMOVED; } +static struct kmemleak_object *__find_and_remove_object(unsigned long ptr, + int alias, + bool is_phys) +{ + struct kmemleak_object *object; + + object = __lookup_object(ptr, alias, is_phys); + if (object) + __remove_object(object); + + return object; +} + /* * Look up an object in the object search tree and remove it from both * object_tree_root (or object_phys_tree_root) and object_list. The @@ -596,9 +609,7 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali struct kmemleak_object *object; raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = __lookup_object(ptr, alias, is_phys); - if (object) - __remove_object(object); + object = __find_and_remove_object(ptr, alias, is_phys); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); return object; @@ -623,25 +634,15 @@ static noinline depot_stack_handle_t set_track_prepare(void) return trace_handle; } -/* - * Create the metadata (struct kmemleak_object) corresponding to an allocated - * memory block and add it to the object_list and object_tree_root (or - * object_phys_tree_root). - */ -static void __create_object(unsigned long ptr, size_t size, - int min_count, gfp_t gfp, bool is_phys) +static struct kmemleak_object *__alloc_object(gfp_t gfp) { - unsigned long flags; - struct kmemleak_object *object, *parent; - struct rb_node **link, *rb_parent; - unsigned long untagged_ptr; - unsigned long untagged_objp; + struct kmemleak_object *object; object = mem_pool_alloc(gfp); if (!object) { pr_warn("Cannot allocate a kmemleak_object structure\n"); kmemleak_disable(); - return; + return NULL; } INIT_LIST_HEAD(&object->object_list); @@ -649,13 +650,8 @@ static void __create_object(unsigned long ptr, size_t size, INIT_HLIST_HEAD(&object->area_list); raw_spin_lock_init(&object->lock); atomic_set(&object->use_count, 1); - object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0); - object->pointer = ptr; - object->size = kfence_ksize((void *)ptr) ?: size; object->excess_ref = 0; - object->min_count = min_count; object->count = 0; /* white color initially */ - object->jiffies = jiffies; object->checksum = 0; object->del_state = 0; @@ -680,7 +676,23 @@ static void __create_object(unsigned long ptr, size_t size, /* kernel backtrace */ object->trace_handle = set_track_prepare(); - raw_spin_lock_irqsave(&kmemleak_lock, flags); + return object; +} + +static int __link_object(struct kmemleak_object *object, unsigned long ptr, + size_t size, int min_count, bool is_phys) +{ + + struct kmemleak_object *parent; + struct rb_node **link, *rb_parent; + unsigned long untagged_ptr; + unsigned long untagged_objp; + + object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0); + object->pointer = ptr; + object->size = kfence_ksize((void *)ptr) ?: size; + object->min_count = min_count; + object->jiffies = jiffies; untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); /* @@ -710,16 +722,38 @@ static void __create_object(unsigned long ptr, size_t size, * be freed while the kmemleak_lock is held. */ dump_object_info(parent); - kmem_cache_free(object_cache, object); - goto out; + return -EEXIST; } } rb_link_node(&object->rb_node, rb_parent, link); rb_insert_color(&object->rb_node, is_phys ? &object_phys_tree_root : &object_tree_root); list_add_tail_rcu(&object->object_list, &object_list); -out: + + return 0; +} + +/* + * Create the metadata (struct kmemleak_object) corresponding to an allocated + * memory block and add it to the object_list and object_tree_root (or + * object_phys_tree_root). + */ +static void __create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp, bool is_phys) +{ + struct kmemleak_object *object; + unsigned long flags; + int ret; + + object = __alloc_object(gfp); + if (!object) + return; + + raw_spin_lock_irqsave(&kmemleak_lock, flags); + ret = __link_object(object, ptr, size, min_count, is_phys); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (ret) + mem_pool_free(object); } /* Create kmemleak object which allocated with virtual address. */ @@ -782,16 +816,25 @@ static void delete_object_full(unsigned long ptr) */ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) { - struct kmemleak_object *object; - unsigned long start, end; + struct kmemleak_object *object, *object_l, *object_r; + unsigned long start, end, flags; + + object_l = __alloc_object(GFP_KERNEL); + if (!object_l) + return; + + object_r = __alloc_object(GFP_KERNEL); + if (!object_r) + goto out; - object = find_and_remove_object(ptr, 1, is_phys); + raw_spin_lock_irqsave(&kmemleak_lock, flags); + object = __find_and_remove_object(ptr, 1, is_phys); if (!object) { #ifdef DEBUG kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", ptr, size); #endif - return; + goto unlock; } /* @@ -801,14 +844,25 @@ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) */ start = object->pointer; end = object->pointer + object->size; - if (ptr > start) - __create_object(start, ptr - start, object->min_count, - GFP_KERNEL, is_phys); - if (ptr + size < end) - __create_object(ptr + size, end - ptr - size, object->min_count, - GFP_KERNEL, is_phys); + if ((ptr > start) && + !__link_object(object_l, start, ptr - start, + object->min_count, is_phys)) + object_l = NULL; + if ((ptr + size < end) && + !__link_object(object_r, ptr + size, end - ptr - size, + object->min_count, is_phys)) + object_r = NULL; + +unlock: + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (object) + __delete_object(object); - __delete_object(object); +out: + if (object_l) + mem_pool_free(object_l); + if (object_r) + mem_pool_free(object_r); } static void __paint_it(struct kmemleak_object *object, int color) @@ -975,7 +1029,7 @@ static void object_no_scan(unsigned long ptr) void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) { - pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count); + pr_debug("%s(0x%px, %zu, %d)\n", __func__, ptr, size, min_count); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) create_object((unsigned long)ptr, size, min_count, gfp); @@ -996,7 +1050,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, { unsigned int cpu; - pr_debug("%s(0x%p, %zu)\n", __func__, ptr, size); + pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); /* * Percpu allocations are only scanned and not reported as leaks @@ -1020,7 +1074,7 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); */ void __ref kmemleak_vmalloc(const struct vm_struct *area, size_t size, gfp_t gfp) { - pr_debug("%s(0x%p, %zu)\n", __func__, area, size); + pr_debug("%s(0x%px, %zu)\n", __func__, area, size); /* * A min_count = 2 is needed because vm_struct contains a reference to @@ -1043,7 +1097,7 @@ EXPORT_SYMBOL_GPL(kmemleak_vmalloc); */ void __ref kmemleak_free(const void *ptr) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) delete_object_full((unsigned long)ptr); @@ -1061,7 +1115,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free); */ void __ref kmemleak_free_part(const void *ptr, size_t size) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) delete_object_part((unsigned long)ptr, size, false); @@ -1079,7 +1133,7 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) { unsigned int cpu; - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) for_each_possible_cpu(cpu) @@ -1098,9 +1152,10 @@ EXPORT_SYMBOL_GPL(kmemleak_free_percpu); void __ref kmemleak_update_trace(const void *ptr) { struct kmemleak_object *object; + depot_stack_handle_t trace_handle; unsigned long flags; - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (!kmemleak_enabled || IS_ERR_OR_NULL(ptr)) return; @@ -1114,8 +1169,9 @@ void __ref kmemleak_update_trace(const void *ptr) return; } + trace_handle = set_track_prepare(); raw_spin_lock_irqsave(&object->lock, flags); - object->trace_handle = set_track_prepare(); + object->trace_handle = trace_handle; raw_spin_unlock_irqrestore(&object->lock, flags); put_object(object); @@ -1131,7 +1187,7 @@ EXPORT_SYMBOL(kmemleak_update_trace); */ void __ref kmemleak_not_leak(const void *ptr) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_gray_object((unsigned long)ptr); @@ -1149,7 +1205,7 @@ EXPORT_SYMBOL(kmemleak_not_leak); */ void __ref kmemleak_ignore(const void *ptr) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) make_black_object((unsigned long)ptr, false); @@ -1169,7 +1225,7 @@ EXPORT_SYMBOL(kmemleak_ignore); */ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && size && !IS_ERR(ptr)) add_scan_area((unsigned long)ptr, size, gfp); @@ -1187,7 +1243,7 @@ EXPORT_SYMBOL(kmemleak_scan_area); */ void __ref kmemleak_no_scan(const void *ptr) { - pr_debug("%s(0x%p)\n", __func__, ptr); + pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) object_no_scan((unsigned long)ptr); @@ -1203,7 +1259,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); */ void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, gfp_t gfp) { - pr_debug("%s(0x%pa, %zu)\n", __func__, &phys, size); + pr_debug("%s(0x%px, %zu)\n", __func__, &phys, size); if (kmemleak_enabled) /* @@ -1223,7 +1279,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - pr_debug("%s(0x%pa)\n", __func__, &phys); + pr_debug("%s(0x%px)\n", __func__, &phys); if (kmemleak_enabled) delete_object_part((unsigned long)phys, size, true); @@ -1237,7 +1293,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - pr_debug("%s(0x%pa)\n", __func__, &phys); + pr_debug("%s(0x%px)\n", __func__, &phys); if (kmemleak_enabled) make_black_object((unsigned long)phys, true); diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index 3adb4c1d3b..c19f47af04 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -83,131 +83,66 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, /* Copy the metadata following the memmove() behavior. */ void kmsan_internal_memmove_metadata(void *dst, void *src, size_t n) { + depot_stack_handle_t prev_old_origin = 0, prev_new_origin = 0; + int i, iter, step, src_off, dst_off, oiter_src, oiter_dst; depot_stack_handle_t old_origin = 0, new_origin = 0; - int src_slots, dst_slots, i, iter, step, skip_bits; depot_stack_handle_t *origin_src, *origin_dst; - void *shadow_src, *shadow_dst; - u32 *align_shadow_src, shadow; + u8 *shadow_src, *shadow_dst; + u32 *align_shadow_dst; bool backwards; shadow_dst = kmsan_get_metadata(dst, KMSAN_META_SHADOW); if (!shadow_dst) return; KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(dst, n)); + align_shadow_dst = + (u32 *)ALIGN_DOWN((u64)shadow_dst, KMSAN_ORIGIN_SIZE); shadow_src = kmsan_get_metadata(src, KMSAN_META_SHADOW); if (!shadow_src) { - /* - * @src is untracked: zero out destination shadow, ignore the - * origins, we're done. - */ - __memset(shadow_dst, 0, n); + /* @src is untracked: mark @dst as initialized. */ + kmsan_internal_unpoison_memory(dst, n, /*checked*/ false); return; } KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(src, n)); - __memmove(shadow_dst, shadow_src, n); - origin_dst = kmsan_get_metadata(dst, KMSAN_META_ORIGIN); origin_src = kmsan_get_metadata(src, KMSAN_META_ORIGIN); KMSAN_WARN_ON(!origin_dst || !origin_src); - src_slots = (ALIGN((u64)src + n, KMSAN_ORIGIN_SIZE) - - ALIGN_DOWN((u64)src, KMSAN_ORIGIN_SIZE)) / - KMSAN_ORIGIN_SIZE; - dst_slots = (ALIGN((u64)dst + n, KMSAN_ORIGIN_SIZE) - - ALIGN_DOWN((u64)dst, KMSAN_ORIGIN_SIZE)) / - KMSAN_ORIGIN_SIZE; - KMSAN_WARN_ON((src_slots < 1) || (dst_slots < 1)); - KMSAN_WARN_ON((src_slots - dst_slots > 1) || - (dst_slots - src_slots < -1)); backwards = dst > src; - i = backwards ? min(src_slots, dst_slots) - 1 : 0; - iter = backwards ? -1 : 1; - - align_shadow_src = - (u32 *)ALIGN_DOWN((u64)shadow_src, KMSAN_ORIGIN_SIZE); - for (step = 0; step < min(src_slots, dst_slots); step++, i += iter) { - KMSAN_WARN_ON(i < 0); - shadow = align_shadow_src[i]; - if (i == 0) { - /* - * If @src isn't aligned on KMSAN_ORIGIN_SIZE, don't - * look at the first @src % KMSAN_ORIGIN_SIZE bytes - * of the first shadow slot. - */ - skip_bits = ((u64)src % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow >> skip_bits) << skip_bits; + step = backwards ? -1 : 1; + iter = backwards ? n - 1 : 0; + src_off = (u64)src % KMSAN_ORIGIN_SIZE; + dst_off = (u64)dst % KMSAN_ORIGIN_SIZE; + + /* Copy shadow bytes one by one, updating the origins if necessary. */ + for (i = 0; i < n; i++, iter += step) { + oiter_src = (iter + src_off) / KMSAN_ORIGIN_SIZE; + oiter_dst = (iter + dst_off) / KMSAN_ORIGIN_SIZE; + if (!shadow_src[iter]) { + shadow_dst[iter] = 0; + if (!align_shadow_dst[oiter_dst]) + origin_dst[oiter_dst] = 0; + continue; } - if (i == src_slots - 1) { - /* - * If @src + n isn't aligned on - * KMSAN_ORIGIN_SIZE, don't look at the last - * (@src + n) % KMSAN_ORIGIN_SIZE bytes of the - * last shadow slot. - */ - skip_bits = (((u64)src + n) % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow << skip_bits) >> skip_bits; - } - /* - * Overwrite the origin only if the corresponding - * shadow is nonempty. - */ - if (origin_src[i] && (origin_src[i] != old_origin) && shadow) { - old_origin = origin_src[i]; - new_origin = kmsan_internal_chain_origin(old_origin); + shadow_dst[iter] = shadow_src[iter]; + old_origin = origin_src[oiter_src]; + if (old_origin == prev_old_origin) + new_origin = prev_new_origin; + else { /* * kmsan_internal_chain_origin() may return * NULL, but we don't want to lose the previous * origin value. */ + new_origin = kmsan_internal_chain_origin(old_origin); if (!new_origin) new_origin = old_origin; } - if (shadow) - origin_dst[i] = new_origin; - else - origin_dst[i] = 0; - } - /* - * If dst_slots is greater than src_slots (i.e. - * dst_slots == src_slots + 1), there is an extra origin slot at the - * beginning or end of the destination buffer, for which we take the - * origin from the previous slot. - * This is only done if the part of the source shadow corresponding to - * slot is non-zero. - * - * E.g. if we copy 8 aligned bytes that are marked as uninitialized - * and have origins o111 and o222, to an unaligned buffer with offset 1, - * these two origins are copied to three origin slots, so one of then - * needs to be duplicated, depending on the copy direction (@backwards) - * - * src shadow: |uuuu|uuuu|....| - * src origin: |o111|o222|....| - * - * backwards = 0: - * dst shadow: |.uuu|uuuu|u...| - * dst origin: |....|o111|o222| - fill the empty slot with o111 - * backwards = 1: - * dst shadow: |.uuu|uuuu|u...| - * dst origin: |o111|o222|....| - fill the empty slot with o222 - */ - if (src_slots < dst_slots) { - if (backwards) { - shadow = align_shadow_src[src_slots - 1]; - skip_bits = (((u64)dst + n) % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow << skip_bits) >> skip_bits; - if (shadow) - /* src_slots > 0, therefore dst_slots is at least 2 */ - origin_dst[dst_slots - 1] = - origin_dst[dst_slots - 2]; - } else { - shadow = align_shadow_src[0]; - skip_bits = ((u64)dst % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow >> skip_bits) << skip_bits; - if (shadow) - origin_dst[0] = origin_dst[1]; - } + origin_dst[oiter_dst] = new_origin; + prev_new_origin = new_origin; + prev_old_origin = old_origin; } } diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 312989aa28..07d3a3a5a9 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -67,6 +67,17 @@ static bool report_available(void) return READ_ONCE(observed.available); } +/* Reset observed.available, so that the test can trigger another report. */ +static void report_reset(void) +{ + unsigned long flags; + + spin_lock_irqsave(&observed.lock, flags); + WRITE_ONCE(observed.available, false); + observed.ignore = false; + spin_unlock_irqrestore(&observed.lock, flags); +} + /* Information we expect in a report. */ struct expect_report { const char *error_type; /* Error type. */ @@ -407,33 +418,25 @@ static void test_printk(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } -/* - * Prevent the compiler from optimizing @var away. Without this, Clang may - * notice that @var is uninitialized and drop memcpy() calls that use it. - * - * There is OPTIMIZER_HIDE_VAR() in linux/compier.h that we cannot use here, - * because it is implemented as inline assembly receiving @var as a parameter - * and will enforce a KMSAN check. Same is true for e.g. barrier_data(var). - */ -#define DO_NOT_OPTIMIZE(var) barrier() +/* Prevent the compiler from inlining a memcpy() call. */ +static noinline void *memcpy_noinline(volatile void *dst, + const volatile void *src, size_t size) +{ + return memcpy((void *)dst, (const void *)src, size); +} -/* - * Test case: ensure that memcpy() correctly copies initialized values. - * Also serves as a regression test to ensure DO_NOT_OPTIMIZE() does not cause - * extra checks. - */ +/* Test case: ensure that memcpy() correctly copies initialized values. */ static void test_init_memcpy(struct kunit *test) { EXPECTATION_NO_REPORT(expect); - volatile int src; - volatile int dst = 0; + volatile long long src; + volatile long long dst = 0; - DO_NOT_OPTIMIZE(src); src = 1; kunit_info( test, "memcpy()ing aligned initialized src to aligned dst (no reports)\n"); - memcpy((void *)&dst, (void *)&src, sizeof(src)); + memcpy_noinline((void *)&dst, (void *)&src, sizeof(src)); kmsan_check_memory((void *)&dst, sizeof(dst)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -451,8 +454,7 @@ static void test_memcpy_aligned_to_aligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to aligned dst (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); + memcpy_noinline((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); kmsan_check_memory((void *)&dst, sizeof(dst)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -463,7 +465,7 @@ static void test_memcpy_aligned_to_aligned(struct kunit *test) * * Copying aligned 4-byte value to an unaligned one leads to touching two * aligned 4-byte values. This test case checks that KMSAN correctly reports an - * error on the first of the two values. + * error on the mentioned two values. */ static void test_memcpy_aligned_to_unaligned(struct kunit *test) { @@ -474,33 +476,65 @@ static void test_memcpy_aligned_to_unaligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to unaligned dst (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); + kmsan_check_memory((void *)&uninit_src, sizeof(uninit_src)); + memcpy_noinline((void *)&dst[1], (void *)&uninit_src, + sizeof(uninit_src)); kmsan_check_memory((void *)dst, 4); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } /* - * Test case: ensure that memcpy() correctly copies uninitialized values between - * aligned `src` and unaligned `dst`. + * Test case: ensure that origin slots do not accidentally get overwritten with + * zeroes during memcpy(). * - * Copying aligned 4-byte value to an unaligned one leads to touching two - * aligned 4-byte values. This test case checks that KMSAN correctly reports an - * error on the second of the two values. + * Previously, when copying memory from an aligned buffer to an unaligned one, + * if there were zero origins corresponding to zero shadow values in the source + * buffer, they could have ended up being copied to nonzero shadow values in the + * destination buffer: + * + * memcpy(0xffff888080a00000, 0xffff888080900002, 8) + * + * src (0xffff888080900002): ..xx .... xx.. + * src origins: o111 0000 o222 + * dst (0xffff888080a00000): xx.. ..xx + * dst origins: o111 0000 + * (or 0000 o222) + * + * (here . stands for an initialized byte, and x for an uninitialized one. + * + * Ensure that this does not happen anymore, and for both destination bytes + * the origin is nonzero (i.e. KMSAN reports an error). */ -static void test_memcpy_aligned_to_unaligned2(struct kunit *test) +static void test_memcpy_initialized_gap(struct kunit *test) { - EXPECTATION_UNINIT_VALUE_FN(expect, - "test_memcpy_aligned_to_unaligned2"); - volatile int uninit_src; + EXPECTATION_UNINIT_VALUE_FN(expect, "test_memcpy_initialized_gap"); + volatile char uninit_src[12]; volatile char dst[8] = { 0 }; kunit_info( test, - "memcpy()ing aligned uninit src to unaligned dst - part 2 (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); - kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); + "unaligned 4-byte initialized value gets a nonzero origin after memcpy() - (2 UMR reports)\n"); + + uninit_src[0] = 42; + uninit_src[1] = 42; + uninit_src[4] = 42; + uninit_src[5] = 42; + uninit_src[6] = 42; + uninit_src[7] = 42; + uninit_src[10] = 42; + uninit_src[11] = 42; + memcpy_noinline((void *)&dst[0], (void *)&uninit_src[2], 8); + + kmsan_check_memory((void *)&dst[0], 4); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[2], 4); + KUNIT_EXPECT_FALSE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[4], 4); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -513,7 +547,6 @@ static void test_memcpy_aligned_to_unaligned2(struct kunit *test) \ kunit_info(test, \ "memset" #size "() should initialize memory\n"); \ - DO_NOT_OPTIMIZE(uninit); \ memset##size((uint##size##_t *)&uninit, 0, 1); \ kmsan_check_memory((void *)&uninit, sizeof(uninit)); \ KUNIT_EXPECT_TRUE(test, report_matches(&expect)); \ @@ -598,7 +631,7 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_init_memcpy), KUNIT_CASE(test_memcpy_aligned_to_aligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned), - KUNIT_CASE(test_memcpy_aligned_to_unaligned2), + KUNIT_CASE(test_memcpy_initialized_gap), KUNIT_CASE(test_memset16), KUNIT_CASE(test_memset32), KUNIT_CASE(test_memset64), diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index 87318f9170..b9d05aff31 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -285,12 +285,17 @@ void __init kmsan_init_alloc_meta_for_range(void *start, void *end) size = PAGE_ALIGN((u64)end - (u64)start); shadow = memblock_alloc(size, PAGE_SIZE); origin = memblock_alloc(size, PAGE_SIZE); + + if (!shadow || !origin) + panic("%s: Failed to allocate metadata memory for early boot range of size %llu", + __func__, size); + for (u64 addr = 0; addr < size; addr += PAGE_SIZE) { page = virt_to_page_or_null((char *)start + addr); - shadow_p = virt_to_page_or_null((char *)shadow + addr); + shadow_p = virt_to_page((char *)shadow + addr); set_no_shadow_origin_page(shadow_p); shadow_page_for(page) = shadow_p; - origin_p = virt_to_page_or_null((char *)origin + addr); + origin_p = virt_to_page((char *)origin + addr); set_no_shadow_origin_page(origin_p); origin_page_for(page) = origin_p; } @@ -56,6 +56,8 @@ #define DO_NUMA(x) do { } while (0) #endif +typedef u8 rmap_age_t; + /** * DOC: Overview * @@ -193,6 +195,8 @@ struct ksm_stable_node { * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node + * @age: number of scan iterations since creation + * @remaining_skips: how many scans to skip */ struct ksm_rmap_item { struct ksm_rmap_item *rmap_list; @@ -205,6 +209,8 @@ struct ksm_rmap_item { struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ + rmap_age_t age; + rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ @@ -281,9 +287,16 @@ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; +/* Skip pages that couldn't be de-duplicated previously */ +/* Default to true at least temporarily, for testing */ +static bool ksm_smart_scan = true; + /* The number of zero pages which is placed by KSM */ unsigned long ksm_zero_pages; +/* The number of pages that have been skipped due to "smart scanning" */ +static unsigned long ksm_pages_skipped; + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -455,7 +468,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex page = pfn_swap_entry_to_page(entry); } /* return 1 if the page is an normal ksm page or KSM-placed zero page */ - ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte); + ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent); pte_unmap_unlock(pte, ptl); return ret; } @@ -2305,6 +2318,74 @@ static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, return rmap_item; } +/* + * Calculate skip age for the ksm page age. The age determines how often + * de-duplicating has already been tried unsuccessfully. If the age is + * smaller, the scanning of this page is skipped for less scans. + * + * @age: rmap_item age of page + */ +static unsigned int skip_age(rmap_age_t age) +{ + if (age <= 3) + return 1; + if (age <= 5) + return 2; + if (age <= 8) + return 4; + + return 8; +} + +/* + * Determines if a page should be skipped for the current scan. + * + * @page: page to check + * @rmap_item: associated rmap_item of page + */ +static bool should_skip_rmap_item(struct page *page, + struct ksm_rmap_item *rmap_item) +{ + rmap_age_t age; + + if (!ksm_smart_scan) + return false; + + /* + * Never skip pages that are already KSM; pages cmp_and_merge_page() + * will essentially ignore them, but we still have to process them + * properly. + */ + if (PageKsm(page)) + return false; + + age = rmap_item->age; + if (age != U8_MAX) + rmap_item->age++; + + /* + * Smaller ages are not skipped, they need to get a chance to go + * through the different phases of the KSM merging. + */ + if (age < 3) + return false; + + /* + * Are we still allowed to skip? If not, then don't skip it + * and determine how much more often we are allowed to skip next. + */ + if (!rmap_item->remaining_skips) { + rmap_item->remaining_skips = skip_age(age); + return false; + } + + /* Skip this page */ + ksm_pages_skipped++; + rmap_item->remaining_skips--; + remove_rmap_item_from_tree(rmap_item); + return true; +} + static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; @@ -2409,6 +2490,10 @@ next_mm: if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; + + if (should_skip_rmap_item(*page, rmap_item)) + goto next_page; + ksm_scan.address += PAGE_SIZE; } else put_page(*page); @@ -3383,6 +3468,13 @@ static ssize_t pages_volatile_show(struct kobject *kobj, } KSM_ATTR_RO(pages_volatile); +static ssize_t pages_skipped_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); +} +KSM_ATTR_RO(pages_skipped); + static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -3449,6 +3541,28 @@ static ssize_t full_scans_show(struct kobject *kobj, } KSM_ATTR_RO(full_scans); +static ssize_t smart_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", ksm_smart_scan); +} + +static ssize_t smart_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + bool value; + + err = kstrtobool(buf, &value); + if (err) + return -EINVAL; + + ksm_smart_scan = value; + return count; +} +KSM_ATTR(smart_scan); + static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, @@ -3458,6 +3572,7 @@ static struct attribute *ksm_attrs[] = { &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, + &pages_skipped_attr.attr, &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA @@ -3469,6 +3584,7 @@ static struct attribute *ksm_attrs[] = { &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, &general_profit_attr.attr, + &smart_scan_attr.attr, NULL, }; diff --git a/mm/madvise.c b/mm/madvise.c index 4dded5d27e..6214a1ab56 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -141,7 +141,6 @@ static int madvise_update_vma(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; int error; - pgoff_t pgoff; VMA_ITERATOR(vmi, mm, start); if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { @@ -149,30 +148,13 @@ static int madvise_update_vma(struct vm_area_struct *vma, return 0; } - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vma_merge(&vmi, mm, *prev, start, end, new_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_name); - if (*prev) { - vma = *prev; - goto success; - } + vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags, + anon_name); + if (IS_ERR(vma)) + return PTR_ERR(vma); *prev = vma; - if (start != vma->vm_start) { - error = split_vma(&vmi, vma, start, 1); - if (error) - return error; - } - - if (end != vma->vm_end) { - error = split_vma(&vmi, vma, end, 0); - if (error) - return error; - } - -success: /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vm_flags_reset(vma, new_flags); @@ -353,6 +335,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; + unsigned int batch_count = 0; if (fatal_signal_pending(current)) return -EINTR; @@ -434,6 +417,7 @@ huge_unlock: regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); +restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; @@ -442,6 +426,15 @@ regular_folio: for (; addr < end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); + if (++batch_count == SWAP_CLUSTER_MAX) { + batch_count = 0; + if (need_resched()) { + pte_unmap_unlock(start_pte, ptl); + cond_resched(); + goto restart; + } + } + if (pte_none(ptent)) continue; @@ -746,11 +739,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, folio_mark_lazyfree(folio); } - if (nr_swap) { - if (current->mm == mm) - sync_mm_rss(mm); + if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); - } if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); @@ -991,7 +981,7 @@ static long madvise_remove(struct vm_area_struct *vma, return -EINVAL; } - if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE)) + if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) diff --git a/mm/memblock.c b/mm/memblock.c index 6d18485571..9a5248fe9c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -180,8 +180,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) /* * Address comparison utilities */ -static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, - phys_addr_t base2, phys_addr_t size2) +unsigned long __init_memblock +memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, + phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } @@ -424,7 +425,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, * of memory that aren't suitable for allocation */ if (!memblock_can_resize) - return -1; + panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); @@ -892,6 +893,7 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) /** * memblock_setclr_flag - set or clear flag for a memory region + * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag @@ -901,10 +903,9 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) * * Return: 0 on success, -errno on failure. */ -static int __init_memblock memblock_setclr_flag(phys_addr_t base, - phys_addr_t size, int set, int flag) +static int __init_memblock memblock_setclr_flag(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, int set, int flag) { - struct memblock_type *type = &memblock.memory; int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); @@ -933,7 +934,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base, */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** @@ -945,7 +946,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG); + return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** @@ -962,7 +963,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) system_has_some_mirror = true; - return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** @@ -982,7 +983,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** @@ -994,7 +995,25 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); + return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); +} + +/** + * memblock_reserved_mark_noinit - Mark a reserved memory region with flag + * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized + * for this region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * struct pages will not be initialized for reserved memory regions marked with + * %MEMBLOCK_RSRV_NOINIT. + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(&memblock.reserved, base, size, 1, + MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, @@ -2113,16 +2132,21 @@ static void __init memmap_init_reserved_pages(void) memblock_set_node(start, end, &memblock.reserved, nid); } - /* initialize struct pages for the reserved regions */ + /* + * initialize struct pages for reserved regions that don't have + * the MEMBLOCK_RSRV_NOINIT flag set + */ for_each_reserved_mem_region(region) { - nid = memblock_get_region_node(region); - start = region->base; - end = start + region->size; + if (!memblock_is_reserved_noinit(region)) { + nid = memblock_get_region_node(region); + start = region->base; + end = start + region->size; - if (nid == NUMA_NO_NODE || nid >= MAX_NUMNODES) - nid = early_pfn_to_nid(PFN_DOWN(start)); + if (nid == NUMA_NO_NODE || nid >= MAX_NUMNODES) + nid = early_pfn_to_nid(PFN_DOWN(start)); - reserve_bootmem_region(start, end, nid); + reserve_bootmem_region(start, end, nid); + } } } @@ -2191,6 +2215,7 @@ static const char * const flagname[] = { [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", + [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8a881ab21f..792fb3a5ce 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -249,6 +249,9 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) return container_of(vmpr, struct mem_cgroup, vmpressure); } +#define CURRENT_OBJCG_UPDATE_BIT 0 +#define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT) + #ifdef CONFIG_MEMCG_KMEM static DEFINE_SPINLOCK(objcg_lock); @@ -704,6 +707,8 @@ static const unsigned int memcg_vm_event_stat[] = { #ifdef CONFIG_TRANSPARENT_HUGEPAGE THP_FAULT_ALLOC, THP_COLLAPSE_ALLOC, + THP_SWPOUT, + THP_SWPOUT_FALLBACK, #endif }; @@ -761,6 +766,22 @@ unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) return x; } +static int memcg_page_state_unit(int item); + +/* + * Normalize the value passed into memcg_rstat_updated() to be in pages. Round + * up non-zero sub-page updates to 1 page as zero page updates are ignored. + */ +static int memcg_state_val_in_pages(int idx, int val) +{ + int unit = memcg_page_state_unit(idx); + + if (!val || unit == PAGE_SIZE) + return val; + else + return max(val * unit / PAGE_SIZE, 1UL); +} + /** * __mod_memcg_state - update cgroup memory statistics * @memcg: the memory cgroup @@ -773,7 +794,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) return; __this_cpu_add(memcg->vmstats_percpu->state[idx], val); - memcg_rstat_updated(memcg, val); + memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val)); } /* idx can be of type enum memcg_stat_item or node_stat_item. */ @@ -798,7 +819,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, memcg = pn->memcg; /* - * The caller from rmap relay on disabled preemption becase they never + * The caller from rmap relies on disabled preemption because they never * update their counter from in-interrupt context. For these two * counters we check that the update is never performed from an * interrupt context while other caller need to have disabled interrupt. @@ -824,7 +845,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, /* Update lruvec */ __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val); - memcg_rstat_updated(memcg, val); + memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val)); memcg_stats_unlock(); } @@ -1068,17 +1089,25 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) } EXPORT_SYMBOL(get_mem_cgroup_from_mm); -static __always_inline bool memcg_kmem_bypass(void) +/** + * get_mem_cgroup_from_current - Obtain a reference on current task's memcg. + */ +struct mem_cgroup *get_mem_cgroup_from_current(void) { - /* Allow remote memcg charging from any context. */ - if (unlikely(active_memcg())) - return false; + struct mem_cgroup *memcg; - /* Memcg to charge can't be determined. */ - if (!in_task() || !current->mm || (current->flags & PF_KTHREAD)) - return true; + if (mem_cgroup_disabled()) + return NULL; - return false; +again: + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + if (!css_tryget(&memcg->css)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + return memcg; } /** @@ -1533,7 +1562,7 @@ static const struct memory_stat memory_stats[] = { { "workingset_nodereclaim", WORKINGSET_NODERECLAIM }, }; -/* Translate stat items to the correct unit for memory.stat output */ +/* The actual unit of the state item, not the same as the output unit */ static int memcg_page_state_unit(int item) { switch (item) { @@ -1541,6 +1570,22 @@ static int memcg_page_state_unit(int item) case MEMCG_ZSWAP_B: case NR_SLAB_RECLAIMABLE_B: case NR_SLAB_UNRECLAIMABLE_B: + return 1; + case NR_KERNEL_STACK_KB: + return SZ_1K; + default: + return PAGE_SIZE; + } +} + +/* Translate stat items to the correct unit for memory.stat output */ +static int memcg_page_state_output_unit(int item) +{ + /* + * Workingset state is actually in pages, but we export it to userspace + * as a scalar count of events, so special case it here. + */ + switch (item) { case WORKINGSET_REFAULT_ANON: case WORKINGSET_REFAULT_FILE: case WORKINGSET_ACTIVATE_ANON: @@ -1549,17 +1594,23 @@ static int memcg_page_state_unit(int item) case WORKINGSET_RESTORE_FILE: case WORKINGSET_NODERECLAIM: return 1; - case NR_KERNEL_STACK_KB: - return SZ_1K; default: - return PAGE_SIZE; + return memcg_page_state_unit(item); } } static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item) { - return memcg_page_state(memcg, item) * memcg_page_state_unit(item); + return memcg_page_state(memcg, item) * + memcg_page_state_output_unit(item); +} + +static inline unsigned long memcg_page_state_local_output( + struct mem_cgroup *memcg, int item) +{ + return memcg_page_state_local(memcg, item) * + memcg_page_state_output_unit(item); } static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) @@ -2833,7 +2884,12 @@ static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, return try_charge_memcg(memcg, gfp_mask, nr_pages); } -static inline void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) +/** + * mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call. + * @memcg: memcg previously charged. + * @nr_pages: number of pages previously charged. + */ +void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) return; @@ -2858,6 +2914,22 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) folio->memcg_data = (unsigned long)memcg; } +/** + * mem_cgroup_commit_charge - commit a previously successful try_charge(). + * @folio: folio to commit the charge to. + * @memcg: memcg previously charged. + */ +void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg) +{ + css_get(&memcg->css); + commit_charge(folio, memcg); + + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, folio_nr_pages(folio)); + memcg_check_events(memcg, folio_nid(folio)); + local_irq_enable(); +} + #ifdef CONFIG_MEMCG_KMEM /* * The allocated objcg pointers array is not accounted directly. @@ -3008,28 +3080,105 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg) for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { objcg = rcu_dereference(memcg->objcg); - if (objcg && obj_cgroup_tryget(objcg)) + if (likely(objcg && obj_cgroup_tryget(objcg))) break; objcg = NULL; } return objcg; } -__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) +static struct obj_cgroup *current_objcg_update(void) { - struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg; + struct obj_cgroup *old, *objcg = NULL; - if (memcg_kmem_bypass()) - return NULL; + do { + /* Atomically drop the update bit. */ + old = xchg(¤t->objcg, NULL); + if (old) { + old = (struct obj_cgroup *) + ((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG); + if (old) + obj_cgroup_put(old); + + old = NULL; + } - rcu_read_lock(); - if (unlikely(active_memcg())) - memcg = active_memcg(); - else + /* If new objcg is NULL, no reason for the second atomic update. */ + if (!current->mm || (current->flags & PF_KTHREAD)) + return NULL; + + /* + * Release the objcg pointer from the previous iteration, + * if try_cmpxcg() below fails. + */ + if (unlikely(objcg)) { + obj_cgroup_put(objcg); + objcg = NULL; + } + + /* + * Obtain the new objcg pointer. The current task can be + * asynchronously moved to another memcg and the previous + * memcg can be offlined. So let's get the memcg pointer + * and try get a reference to objcg under a rcu read lock. + */ + + rcu_read_lock(); memcg = mem_cgroup_from_task(current); - objcg = __get_obj_cgroup_from_memcg(memcg); - rcu_read_unlock(); + objcg = __get_obj_cgroup_from_memcg(memcg); + rcu_read_unlock(); + + /* + * Try set up a new objcg pointer atomically. If it + * fails, it means the update flag was set concurrently, so + * the whole procedure should be repeated. + */ + } while (!try_cmpxchg(¤t->objcg, &old, objcg)); + + return objcg; +} + +__always_inline struct obj_cgroup *current_obj_cgroup(void) +{ + struct mem_cgroup *memcg; + struct obj_cgroup *objcg; + + if (in_task()) { + memcg = current->active_memcg; + if (unlikely(memcg)) + goto from_memcg; + + objcg = READ_ONCE(current->objcg); + if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG)) + objcg = current_objcg_update(); + /* + * Objcg reference is kept by the task, so it's safe + * to use the objcg by the current task. + */ + return objcg; + } + + memcg = this_cpu_read(int_active_memcg); + if (unlikely(memcg)) + goto from_memcg; + + return NULL; + +from_memcg: + objcg = NULL; + for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { + /* + * Memcg pointer is protected by scope (see set_active_memcg()) + * and is pinning the corresponding objcg, so objcg can't go + * away and can be used within the scope without any additional + * protection. + */ + objcg = rcu_dereference_check(memcg->objcg, 1); + if (likely(objcg)) + break; + } + return objcg; } @@ -3127,15 +3276,15 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) struct obj_cgroup *objcg; int ret = 0; - objcg = get_obj_cgroup_from_current(); + objcg = current_obj_cgroup(); if (objcg) { ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order); if (!ret) { + obj_cgroup_get(objcg); page->memcg_data = (unsigned long)objcg | MEMCG_DATA_KMEM; return 0; } - obj_cgroup_put(objcg); } return ret; } @@ -3762,6 +3911,8 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) objcg->memcg = memcg; rcu_assign_pointer(memcg->objcg, objcg); + obj_cgroup_get(objcg); + memcg->orig_objcg = objcg; static_branch_enable(&memcg_kmem_online_key); @@ -4067,7 +4218,10 @@ static const unsigned int memcg1_stats[] = { NR_WRITEBACK, WORKINGSET_REFAULT_ANON, WORKINGSET_REFAULT_FILE, +#ifdef CONFIG_SWAP MEMCG_SWAP, + NR_SWAPCACHE, +#endif }; static const char *const memcg1_stat_names[] = { @@ -4082,7 +4236,10 @@ static const char *const memcg1_stat_names[] = { "writeback", "workingset_refault_anon", "workingset_refault_file", +#ifdef CONFIG_SWAP "swap", + "swapcached", +#endif }; /* Universal VM events cgroup1 shows, original sort order */ @@ -4106,11 +4263,8 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; - nr = memcg_page_state_local(memcg, memcg1_stats[i]); - seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i], - nr * memcg_page_state_unit(memcg1_stats[i])); + nr = memcg_page_state_local_output(memcg, memcg1_stats[i]); + seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i], nr); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -4130,18 +4284,15 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) } seq_buf_printf(s, "hierarchical_memory_limit %llu\n", (u64)memory * PAGE_SIZE); - if (do_memsw_account()) - seq_buf_printf(s, "hierarchical_memsw_limit %llu\n", - (u64)memsw * PAGE_SIZE); + seq_buf_printf(s, "hierarchical_memsw_limit %llu\n", + (u64)memsw * PAGE_SIZE); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; - nr = memcg_page_state(memcg, memcg1_stats[i]); + nr = memcg_page_state_output(memcg, memcg1_stats[i]); seq_buf_printf(s, "total_%s %llu\n", memcg1_stat_names[i], - (u64)nr * memcg_page_state_unit(memcg1_stats[i])); + (u64)nr); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -5269,6 +5420,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; + if (memcg->orig_objcg) + obj_cgroup_put(memcg->orig_objcg); + for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); kfree(memcg->vmstats); @@ -6077,7 +6231,7 @@ static void __mem_cgroup_clear_mc(void) /* we must uncharge all the leftover precharges from mc.to */ if (mc.precharge) { - cancel_charge(mc.to, mc.precharge); + mem_cgroup_cancel_charge(mc.to, mc.precharge); mc.precharge = 0; } /* @@ -6085,7 +6239,7 @@ static void __mem_cgroup_clear_mc(void) * we must uncharge here. */ if (mc.moved_charge) { - cancel_charge(mc.from, mc.moved_charge); + mem_cgroup_cancel_charge(mc.from, mc.moved_charge); mc.moved_charge = 0; } /* we must fixup refcnts and charges */ @@ -6365,6 +6519,7 @@ static void mem_cgroup_move_task(void) mem_cgroup_clear_mc(); } } + #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { @@ -6378,8 +6533,39 @@ static void mem_cgroup_move_task(void) } #endif +#ifdef CONFIG_MEMCG_KMEM +static void mem_cgroup_fork(struct task_struct *task) +{ + /* + * Set the update flag to cause task->objcg to be initialized lazily + * on the first allocation. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). + */ + task->objcg = (struct obj_cgroup *)CURRENT_OBJCG_UPDATE_FLAG; +} + +static void mem_cgroup_exit(struct task_struct *task) +{ + struct obj_cgroup *objcg = task->objcg; + + objcg = (struct obj_cgroup *) + ((unsigned long)objcg & ~CURRENT_OBJCG_UPDATE_FLAG); + if (objcg) + obj_cgroup_put(objcg); + + /* + * Some kernel allocations can happen after this point, + * but let's ignore them. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). + */ + task->objcg = NULL; +} +#endif + #ifdef CONFIG_LRU_GEN -static void mem_cgroup_attach(struct cgroup_taskset *tset) +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *css; @@ -6397,10 +6583,31 @@ static void mem_cgroup_attach(struct cgroup_taskset *tset) task_unlock(task); } #else +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) {} +#endif /* CONFIG_LRU_GEN */ + +#ifdef CONFIG_MEMCG_KMEM +static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(task, css, tset) { + /* atomically set the update bit */ + set_bit(CURRENT_OBJCG_UPDATE_BIT, (unsigned long *)&task->objcg); + } +} +#else +static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) {} +#endif /* CONFIG_MEMCG_KMEM */ + +#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM) static void mem_cgroup_attach(struct cgroup_taskset *tset) { + mem_cgroup_lru_gen_attach(tset); + mem_cgroup_kmem_attach(tset); } -#endif /* CONFIG_LRU_GEN */ +#endif static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value) { @@ -6623,7 +6830,8 @@ static int memory_stat_show(struct seq_file *m, void *v) static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec, int item) { - return lruvec_page_state(lruvec, item) * memcg_page_state_unit(item); + return lruvec_page_state(lruvec, item) * + memcg_page_state_output_unit(item); } static int memory_numa_stat_show(struct seq_file *m, void *v) @@ -6809,9 +7017,15 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .css_rstat_flush = mem_cgroup_css_rstat_flush, .can_attach = mem_cgroup_can_attach, +#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM) .attach = mem_cgroup_attach, +#endif .cancel_attach = mem_cgroup_cancel_attach, .post_attach = mem_cgroup_move_task, +#ifdef CONFIG_MEMCG_KMEM + .fork = mem_cgroup_fork, + .exit = mem_cgroup_exit, +#endif .dfl_cftypes = memory_files, .legacy_cftypes = mem_cgroup_legacy_files, .early_init = 0, @@ -6991,20 +7205,13 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, gfp_t gfp) { - long nr_pages = folio_nr_pages(folio); int ret; - ret = try_charge(memcg, gfp, nr_pages); + ret = try_charge(memcg, gfp, folio_nr_pages(folio)); if (ret) goto out; - css_get(&memcg->css); - commit_charge(folio, memcg); - - local_irq_disable(); - mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, folio_nid(folio)); - local_irq_enable(); + mem_cgroup_commit_charge(folio, memcg); out: return ret; } @@ -7022,6 +7229,41 @@ int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) } /** + * mem_cgroup_hugetlb_try_charge - try to charge the memcg for a hugetlb folio + * @memcg: memcg to charge. + * @gfp: reclaim mode. + * @nr_pages: number of pages to charge. + * + * This function is called when allocating a huge page folio to determine if + * the memcg has the capacity for it. It does not commit the charge yet, + * as the hugetlb folio itself has not been obtained from the hugetlb pool. + * + * Once we have obtained the hugetlb folio, we can call + * mem_cgroup_commit_charge() to commit the charge. If we fail to obtain the + * folio, we should instead call mem_cgroup_cancel_charge() to undo the effect + * of try_charge(). + * + * Returns 0 on success. Otherwise, an error code is returned. + */ +int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, + long nr_pages) +{ + /* + * If hugetlb memcg charging is not enabled, do not fail hugetlb allocation, + * but do not attempt to commit charge later (or cancel on error) either. + */ + if (mem_cgroup_disabled() || !memcg || + !cgroup_subsys_on_dfl(memory_cgrp_subsys) || + !(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)) + return -EOPNOTSUPP; + + if (try_charge(memcg, gfp, nr_pages)) + return -ENOMEM; + + return 0; +} + +/** * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin. * @folio: folio to charge. * @mm: mm context of the victim @@ -7217,16 +7459,17 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) } /** - * mem_cgroup_migrate - Charge a folio's replacement. + * mem_cgroup_replace_folio - Charge a folio's replacement. * @old: Currently circulating folio. * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will - * be uncharged upon free. + * be uncharged upon free. This is only used by the page cache + * (in replace_page_cache_folio()). * * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct folio *old, struct folio *new) +void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { struct mem_cgroup *memcg; long nr_pages = folio_nr_pages(new); @@ -7265,6 +7508,55 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) local_irq_restore(flags); } +/** + * mem_cgroup_migrate - Transfer the memcg data from the old to the new folio. + * @old: Currently circulating folio. + * @new: Replacement folio. + * + * Transfer the memcg data from the old folio to the new folio for migration. + * The old folio's data info will be cleared. Note that the memory counters + * will remain unchanged throughout the process. + * + * Both folios must be locked, @new->mapping must be set up. + */ +void mem_cgroup_migrate(struct folio *old, struct folio *new) +{ + struct mem_cgroup *memcg; + + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != folio_nr_pages(new), new); + + if (mem_cgroup_disabled()) + return; + + memcg = folio_memcg(old); + /* + * Note that it is normal to see !memcg for a hugetlb folio. + * For e.g, itt could have been allocated when memory_hugetlb_accounting + * was not selected. + */ + VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(old) && !memcg, old); + if (!memcg) + return; + + /* Transfer the charge and the css ref */ + commit_charge(new, memcg); + /* + * If the old folio is a large folio and is in the split queue, it needs + * to be removed from the split queue now, in case getting an incorrect + * split queue in destroy_large_folio() after the memcg of the old folio + * is cleared. + * + * In addition, the old folio is about to be freed after migration, so + * removing from the split queue a bit earlier seems reasonable. + */ + if (folio_test_large(old) && folio_test_large_rmappable(old)) + folio_undo_large_rmappable(old); + old->memcg_data = 0; +} + DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); EXPORT_SYMBOL(memcg_sockets_enabled_key); @@ -7613,9 +7905,13 @@ bool mem_cgroup_swap_full(struct folio *folio) static int __init setup_swap_account(char *s) { - pr_warn_once("The swapaccount= commandline option is deprecated. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); + bool res; + + if (!kstrtobool(s, &res) && !res) + pr_warn_once("The swapaccount=0 commandline option is deprecated " + "in favor of configuring swap control via cgroupfs. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); return 1; } __setup("swapaccount=", setup_swap_account); @@ -7764,7 +8060,7 @@ static struct cftype memsw_files[] = { * * This doesn't check for specific headroom, and it is not atomic * either. But with zswap, the size of the allocation is only known - * once compression has occured, and this optimistic pre-check avoids + * once compression has occurred, and this optimistic pre-check avoids * spending cycles on compression when there is already no room left * or zswap is disabled altogether somewhere in the hierarchy. */ diff --git a/mm/memfd.c b/mm/memfd.c index 2dba2cb6f0..d3a1ba4208 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -315,12 +315,6 @@ SYSCALL_DEFINE2(memfd_create, if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL; - if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { - pr_warn_once( - "%s[%d]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set\n", - current->comm, task_pid_nr(current)); - } - error = check_sysctl_memfd_noexec(&flags); if (error < 0) return error; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 455093f73a..17298a615a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -976,7 +976,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p, int count = page_count(p) - 1; if (extra_pins) - count -= 1; + count -= folio_nr_pages(page_folio(p)); if (count > 0) { pr_err("%#lx: %s still referenced by %d users\n", diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 37a4f59d95..8d5291add2 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -5,6 +5,7 @@ #include <linux/kobject.h> #include <linux/memory.h> #include <linux/memory-tiers.h> +#include <linux/notifier.h> #include "internal.h" @@ -36,7 +37,7 @@ struct node_memory_type_map { static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; -static struct memory_dev_type *default_dram_type; +struct memory_dev_type *default_dram_type; static struct bus_type memory_tier_subsys = { .name = "memory_tiering", @@ -105,6 +106,13 @@ static int top_tier_adistance; static struct demotion_nodes *node_demotion __read_mostly; #endif /* CONFIG_MIGRATION */ +static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); + +static bool default_dram_perf_error; +static struct node_hmem_attrs default_dram_perf; +static int default_dram_perf_ref_nid = NUMA_NO_NODE; +static const char *default_dram_perf_ref_source; + static inline struct memory_tier *to_memory_tier(struct device *device) { return container_of(device, struct memory_tier, dev); @@ -115,7 +123,7 @@ static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memti nodemask_t nodes = NODE_MASK_NONE; struct memory_dev_type *memtype; - list_for_each_entry(memtype, &memtier->memory_types, tier_sibiling) + list_for_each_entry(memtype, &memtier->memory_types, tier_sibling) nodes_or(nodes, nodes, memtype->nodes); return nodes; @@ -174,7 +182,7 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty * If the memtype is already part of a memory tier, * just return that. */ - if (!list_empty(&memtype->tier_sibiling)) { + if (!list_empty(&memtype->tier_sibling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; @@ -218,7 +226,7 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty memtier = new_memtier; link_memtype: - list_add(&memtype->tier_sibiling, &memtier->memory_types); + list_add(&memtype->tier_sibling, &memtier->memory_types); return memtier; } @@ -527,7 +535,7 @@ static bool clear_node_memory_tier(int node) memtype = node_memory_types[node].memtype; node_clear(node, memtype->nodes); if (nodes_empty(memtype->nodes)) { - list_del_init(&memtype->tier_sibiling); + list_del_init(&memtype->tier_sibling); if (list_empty(&memtier->memory_types)) destroy_memory_tier(memtier); } @@ -553,7 +561,7 @@ struct memory_dev_type *alloc_memory_type(int adistance) return ERR_PTR(-ENOMEM); memtype->adistance = adistance; - INIT_LIST_HEAD(&memtype->tier_sibiling); + INIT_LIST_HEAD(&memtype->tier_sibling); memtype->nodes = NODE_MASK_NONE; kref_init(&memtype->kref); return memtype; @@ -578,13 +586,14 @@ EXPORT_SYMBOL_GPL(init_node_memory_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); - if (node_memory_types[node].memtype == memtype) + if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--; /* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { + memtype = node_memory_types[node].memtype; node_memory_types[node].memtype = NULL; put_memory_type(memtype); } @@ -592,6 +601,158 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) } EXPORT_SYMBOL_GPL(clear_node_memory_type); +static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix) +{ + pr_info( +"%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n", + prefix, attrs->read_latency, attrs->write_latency, + attrs->read_bandwidth, attrs->write_bandwidth); +} + +int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source) +{ + int rc = 0; + + mutex_lock(&memory_tier_lock); + if (default_dram_perf_error) { + rc = -EIO; + goto out; + } + + if (perf->read_latency + perf->write_latency == 0 || + perf->read_bandwidth + perf->write_bandwidth == 0) { + rc = -EINVAL; + goto out; + } + + if (default_dram_perf_ref_nid == NUMA_NO_NODE) { + default_dram_perf = *perf; + default_dram_perf_ref_nid = nid; + default_dram_perf_ref_source = kstrdup(source, GFP_KERNEL); + goto out; + } + + /* + * The performance of all default DRAM nodes is expected to be + * same (that is, the variation is less than 10%). And it + * will be used as base to calculate the abstract distance of + * other memory nodes. + */ + if (abs(perf->read_latency - default_dram_perf.read_latency) * 10 > + default_dram_perf.read_latency || + abs(perf->write_latency - default_dram_perf.write_latency) * 10 > + default_dram_perf.write_latency || + abs(perf->read_bandwidth - default_dram_perf.read_bandwidth) * 10 > + default_dram_perf.read_bandwidth || + abs(perf->write_bandwidth - default_dram_perf.write_bandwidth) * 10 > + default_dram_perf.write_bandwidth) { + pr_info( +"memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" +"DRAM node %d.\n", nid, default_dram_perf_ref_nid); + pr_info(" performance of reference DRAM node %d:\n", + default_dram_perf_ref_nid); + dump_hmem_attrs(&default_dram_perf, " "); + pr_info(" performance of DRAM node %d:\n", nid); + dump_hmem_attrs(perf, " "); + pr_info( +" disable default DRAM node performance based abstract distance algorithm.\n"); + default_dram_perf_error = true; + rc = -EINVAL; + } + +out: + mutex_unlock(&memory_tier_lock); + return rc; +} + +int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +{ + if (default_dram_perf_error) + return -EIO; + + if (default_dram_perf_ref_nid == NUMA_NO_NODE) + return -ENOENT; + + if (perf->read_latency + perf->write_latency == 0 || + perf->read_bandwidth + perf->write_bandwidth == 0) + return -EINVAL; + + mutex_lock(&memory_tier_lock); + /* + * The abstract distance of a memory node is in direct proportion to + * its memory latency (read + write) and inversely proportional to its + * memory bandwidth (read + write). The abstract distance, memory + * latency, and memory bandwidth of the default DRAM nodes are used as + * the base. + */ + *adist = MEMTIER_ADISTANCE_DRAM * + (perf->read_latency + perf->write_latency) / + (default_dram_perf.read_latency + default_dram_perf.write_latency) * + (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / + (perf->read_bandwidth + perf->write_bandwidth); + mutex_unlock(&memory_tier_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(mt_perf_to_adistance); + +/** + * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm + * @nb: The notifier block which describe the algorithm + * + * Return: 0 on success, errno on error. + * + * Every memory tiering abstract distance algorithm provider needs to + * register the algorithm with register_mt_adistance_algorithm(). To + * calculate the abstract distance for a specified memory node, the + * notifier function will be called unless some high priority + * algorithm has provided result. The prototype of the notifier + * function is as follows, + * + * int (*algorithm_notifier)(struct notifier_block *nb, + * unsigned long nid, void *data); + * + * Where "nid" specifies the memory node, "data" is the pointer to the + * returned abstract distance (that is, "int *adist"). If the + * algorithm provides the result, NOTIFY_STOP should be returned. + * Otherwise, return_value & %NOTIFY_STOP_MASK == 0 to allow the next + * algorithm in the chain to provide the result. + */ +int register_mt_adistance_algorithm(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&mt_adistance_algorithms, nb); +} +EXPORT_SYMBOL_GPL(register_mt_adistance_algorithm); + +/** + * unregister_mt_adistance_algorithm() - Unregister memory tiering abstract distance algorithm + * @nb: the notifier block which describe the algorithm + * + * Return: 0 on success, errno on error. + */ +int unregister_mt_adistance_algorithm(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&mt_adistance_algorithms, nb); +} +EXPORT_SYMBOL_GPL(unregister_mt_adistance_algorithm); + +/** + * mt_calc_adistance() - Calculate abstract distance with registered algorithms + * @node: the node to calculate abstract distance for + * @adist: the returned abstract distance + * + * Return: if return_value & %NOTIFY_STOP_MASK != 0, then some + * abstract distance algorithm provides the result, and return it via + * @adist. Otherwise, no algorithm can provide the result and @adist + * will be kept as it is. + */ +int mt_calc_adistance(int node, int *adist) +{ + return blocking_notifier_call_chain(&mt_adistance_algorithms, node, adist); +} +EXPORT_SYMBOL_GPL(mt_calc_adistance); + static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { diff --git a/mm/memory.c b/mm/memory.c index dccf9203dd..ec7b775fb4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1,3 +1,4 @@ + // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c @@ -471,8 +472,6 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; - if (current->mm == mm) - sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); @@ -691,6 +690,16 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, out: return pfn_to_page(pfn); } + +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd) +{ + struct page *page = vm_normal_page_pmd(vma, addr, pmd); + + if (page) + return page_folio(page); + return NULL; +} #endif static void restore_exclusive_pte(struct vm_area_struct *vma, @@ -1508,6 +1517,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; } else { /* We should have covered all the swap entry types */ + pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); @@ -3006,23 +3016,24 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ -static inline void wp_page_reuse(struct vm_fault *vmf) +static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; - struct page *page = vmf->page; pte_t entry; VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); - VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page)); - /* - * Clear the pages cpupid information as the existing - * information potentially belongs to a now completely - * unrelated process. - */ - if (page) - page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); + if (folio) { + VM_BUG_ON(folio_test_anon(folio) && + !PageAnonExclusive(vmf->page)); + /* + * Clear the folio's cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. + */ + folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1); + } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); @@ -3034,6 +3045,36 @@ static inline void wp_page_reuse(struct vm_fault *vmf) } /* + * We could add a bitflag somewhere, but for now, we know that all + * vm_ops that have a ->map_pages have been audited and don't need + * the mmap_lock to be held. + */ +static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK)) + return 0; + vma_end_read(vma); + return VM_FAULT_RETRY; +} + +static vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + if (likely(vma->anon_vma)) + return 0; + if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + vma_end_read(vma); + return VM_FAULT_RETRY; + } + if (__anon_vma_prepare(vma)) + return VM_FAULT_OOM; + return 0; +} + +/* * Handle the case of a page which we actually need to copy to a new page, * either due to COW or unsharing. * @@ -3060,27 +3101,29 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) pte_t entry; int page_copied = 0; struct mmu_notifier_range range; - int ret; + vm_fault_t ret; delayacct_wpcopy_start(); if (vmf->page) old_folio = page_folio(vmf->page); - if (unlikely(anon_vma_prepare(vma))) - goto oom; + ret = vmf_anon_prepare(vmf); + if (unlikely(ret)) + goto out; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address); if (!new_folio) goto oom; } else { + int err; new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); if (!new_folio) goto oom; - ret = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); - if (ret) { + err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); + if (err) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on @@ -3093,7 +3136,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) folio_put(old_folio); delayacct_wpcopy_end(); - return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0; + return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0; } kmsan_copy_page_meta(&new_folio->page, vmf->page); } @@ -3203,11 +3246,13 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) oom_free_new: folio_put(new_folio); oom: + ret = VM_FAULT_OOM; +out: if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); - return VM_FAULT_OOM; + return ret; } /** @@ -3215,6 +3260,7 @@ oom: * writeable once the page is prepared * * @vmf: structure describing the fault + * @folio: the folio of vmf->page * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. @@ -3226,7 +3272,7 @@ oom: * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ -vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) +static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, @@ -3242,7 +3288,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } - wp_page_reuse(vmf); + wp_page_reuse(vmf, folio); return 0; } @@ -3258,18 +3304,17 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); - if (vmf->flags & FAULT_FLAG_VMA_LOCK) { - vma_end_read(vmf->vma); - return VM_FAULT_RETRY; - } + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; - return finish_mkwrite_fault(vmf); + return finish_mkwrite_fault(vmf, NULL); } - wp_page_reuse(vmf); + wp_page_reuse(vmf, NULL); return 0; } @@ -3285,10 +3330,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); - if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + tmp = vmf_can_call_fault(vmf); + if (tmp) { folio_put(folio); - vma_end_read(vmf->vma); - return VM_FAULT_RETRY; + return tmp; } tmp = do_page_mkwrite(vmf, folio); @@ -3297,14 +3342,14 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) folio_put(folio); return tmp; } - tmp = finish_mkwrite_fault(vmf); + tmp = finish_mkwrite_fault(vmf, folio); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { folio_unlock(folio); folio_put(folio); return tmp; } } else { - wp_page_reuse(vmf); + wp_page_reuse(vmf, folio); folio_lock(folio); } ret |= fault_dirty_shared_page(vmf); @@ -3313,6 +3358,44 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) return ret; } +static bool wp_can_reuse_anon_folio(struct folio *folio, + struct vm_area_struct *vma) +{ + /* + * We have to verify under folio lock: these early checks are + * just an optimization to avoid locking the folio and freeing + * the swapcache if there is little hope that we can reuse. + * + * KSM doesn't necessarily raise the folio refcount. + */ + if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) + return false; + if (!folio_test_lru(folio)) + /* + * We cannot easily detect+handle references from + * remote LRU caches or references to LRU folios. + */ + lru_add_drain(); + if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) + return false; + if (!folio_trylock(folio)) + return false; + if (folio_test_swapcache(folio)) + folio_free_swap(folio); + if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { + folio_unlock(folio); + return false; + } + /* + * Ok, we've got the only folio reference from our mapping + * and the folio is locked, it's dark out, and we're wearing + * sunglasses. Hit it. + */ + folio_move_anon_rmap(folio, vma); + folio_unlock(folio); + return true; +} + /* * This routine handles present pages, when * * users try to write to a shared page (FAULT_FLAG_WRITE) @@ -3341,11 +3424,28 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; + pte_t pte; if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return handle_userfault(vmf, VM_UFFD_WP); + if (!userfaultfd_wp_async(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Nothing needed (cache flush, TLB invalidations, + * etc.) because we're only removing the uffd-wp bit, + * which is completely invisible to the user. + */ + pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); + + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + /* + * Update this to be prepared for following up CoW + * handling + */ + vmf->orig_pte = pte; } /* @@ -3382,62 +3482,21 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) /* * Private mapping: create an exclusive anonymous page copy if reuse * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. + * + * If we encounter a page that is marked exclusive, we must reuse + * the page without further checks. */ - if (folio && folio_test_anon(folio)) { - /* - * If the page is exclusive to this process we must reuse the - * page without further checks. - */ - if (PageAnonExclusive(vmf->page)) - goto reuse; - - /* - * We have to verify under folio lock: these early checks are - * just an optimization to avoid locking the folio and freeing - * the swapcache if there is little hope that we can reuse. - * - * KSM doesn't necessarily raise the folio refcount. - */ - if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) - goto copy; - if (!folio_test_lru(folio)) - /* - * We cannot easily detect+handle references from - * remote LRU caches or references to LRU folios. - */ - lru_add_drain(); - if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) - goto copy; - if (!folio_trylock(folio)) - goto copy; - if (folio_test_swapcache(folio)) - folio_free_swap(folio); - if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { - folio_unlock(folio); - goto copy; - } - /* - * Ok, we've got the only folio reference from our mapping - * and the folio is locked, it's dark out, and we're wearing - * sunglasses. Hit it. - */ - page_move_anon_rmap(vmf->page, vma); - folio_unlock(folio); -reuse: + if (folio && folio_test_anon(folio) && + (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { + if (!PageAnonExclusive(vmf->page)) + SetPageAnonExclusive(vmf->page); if (unlikely(unshare)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } - wp_page_reuse(vmf); + wp_page_reuse(vmf, folio); return 0; } -copy: - if ((vmf->flags & FAULT_FLAG_VMA_LOCK) && !vma->anon_vma) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - vma_end_read(vmf->vma); - return VM_FAULT_RETRY; - } - /* * Ok, we need to copy. Oh, well.. */ @@ -3726,6 +3785,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3794,6 +3854,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4040,6 +4114,9 @@ unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4054,6 +4131,8 @@ out_release: folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4563,10 +4642,9 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) return ret; } - if (vmf->flags & FAULT_FLAG_VMA_LOCK) { - vma_end_read(vmf->vma); - return VM_FAULT_RETRY; - } + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -4585,13 +4663,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; - if (vmf->flags & FAULT_FLAG_VMA_LOCK) { - vma_end_read(vma); - return VM_FAULT_RETRY; - } - - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; + ret = vmf_can_call_fault(vmf); + if (!ret) + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) @@ -4630,10 +4706,9 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) vm_fault_t ret, tmp; struct folio *folio; - if (vmf->flags & FAULT_FLAG_VMA_LOCK) { - vma_end_read(vma); - return VM_FAULT_RETRY; - } + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -4719,10 +4794,10 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { - get_page(page); + folio_get(folio); /* Record the current PID acceesing VMA */ vma_set_access_pid_bit(vma); @@ -4733,14 +4808,14 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, *flags |= TNF_FAULT_LOCAL; } - return mpol_misplaced(page, vma, addr); + return mpol_misplaced(folio, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct page *page = NULL; - int page_nid = NUMA_NO_NODE; + struct folio *folio = NULL; + int nid = NUMA_NO_NODE; bool writable = false; int last_cpupid; int target_nid; @@ -4771,12 +4846,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) can_change_pte_writable(vma, vmf->address, pte)) writable = true; - page = vm_normal_page(vma, vmf->address, pte); - if (!page || is_zone_device_page(page)) + folio = vm_normal_folio(vma, vmf->address, pte); + if (!folio || folio_is_zone_device(folio)) goto out_map; /* TODO: handle PTE-mapped THP */ - if (PageCompound(page)) + if (folio_test_large(folio)) goto out_map; /* @@ -4791,34 +4866,33 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) flags |= TNF_NO_GROUP; /* - * Flag if the page is shared between multiple address spaces. This + * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ - if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + if (folio_estimated_sharers(folio) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; - page_nid = page_to_nid(page); + nid = folio_nid(folio); /* * 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)) + !node_is_toptier(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); + last_cpupid = folio_last_cpupid(folio); + target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags); if (target_nid == NUMA_NO_NODE) { - put_page(page); + folio_put(folio); goto out_map; } pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; /* Migrate to the requested node */ - if (migrate_misplaced_page(page, vma, target_nid)) { - page_nid = target_nid; + if (migrate_misplaced_folio(folio, vma, target_nid)) { + nid = target_nid; flags |= TNF_MIGRATED; } else { flags |= TNF_MIGRATE_FAIL; @@ -4834,8 +4908,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) } out: - if (page_nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, page_nid, 1, flags); + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, 1, flags); return 0; out_map: /* @@ -4872,8 +4946,11 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) if (vma_is_anonymous(vma)) { if (likely(!unshare) && - userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) + userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { + if (userfaultfd_wp_async(vmf->vma)) + goto split; return handle_userfault(vmf, VM_UFFD_WP); + } return do_huge_pmd_wp_page(vmf); } @@ -4885,6 +4962,7 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) } } +split: /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); @@ -5315,7 +5393,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs return true; if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } @@ -5340,7 +5418,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } @@ -5736,8 +5814,8 @@ EXPORT_SYMBOL_GPL(generic_access_phys); /* * Access another process' address space as given in mm. */ -int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, - int len, unsigned int gup_flags) +static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) { void *old_buf = buf; int write = gup_flags & FOLL_WRITE; @@ -5760,7 +5838,7 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, struct page *page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); - if (IS_ERR_OR_NULL(page)) { + if (IS_ERR(page)) { /* We might need to expand the stack to access it */ vma = vma_lookup(mm, addr); if (!vma) { @@ -5774,7 +5852,6 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, continue; } - /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f36525a595..c9c2ad5e26 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -2015,12 +2015,16 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); + /* + * Make sure to mark the node as memory-less before rebuilding the zone + * list. Otherwise this node would still appear in the fallback lists. + */ + node_states_clear_node(node, &arg); if (!populated_zone(zone)) { zone_pcp_reset(zone); build_all_zonelists(NULL); } - node_states_clear_node(node, &arg); if (arg.status_change_nid >= 0) { kcompactd_stop(node); kswapd_stop(node); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e52e3a0b8f..10a590ee1c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -25,7 +25,7 @@ * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * - * preferred Try a specific node first before normal fallback. + * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default @@ -52,7 +52,7 @@ * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * - * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between + * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ @@ -111,7 +111,8 @@ /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ -#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ +#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ +#define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; @@ -267,9 +268,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, { struct mempolicy *policy; - pr_debug("setting mode %d flags %d nodes[0] %lx\n", - mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); - if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); @@ -297,6 +295,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); + policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); @@ -309,11 +308,11 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, } /* Slow path of a mpol destructor. */ -void __mpol_put(struct mempolicy *p) +void __mpol_put(struct mempolicy *pol) { - if (!atomic_dec_and_test(&p->refcnt)) + if (!atomic_dec_and_test(&pol->refcnt)) return; - kmem_cache_free(policy_cache, p); + kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) @@ -370,7 +369,6 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) * * Called with task's alloc_lock held. */ - void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); @@ -381,7 +379,6 @@ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ - void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; @@ -420,8 +417,25 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, +static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); +static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, + pgoff_t ilx, int *nid); + +static bool strictly_unmovable(unsigned long flags) +{ + /* + * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO + * if any misplaced page is found. + */ + return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == + MPOL_MF_STRICT; +} + +struct migration_mpol { /* for alloc_migration_target_by_mpol() */ + struct mempolicy *pol; + pgoff_t ilx; +}; struct queue_pages { struct list_head *pagelist; @@ -430,7 +444,8 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; - bool has_unmovable; + struct folio *large; /* note last large folio encountered */ + long nr_failed; /* could not be isolated at this time */ }; /* @@ -448,61 +463,37 @@ static inline bool queue_folio_required(struct folio *folio, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } -/* - * queue_folios_pmd() has three possible return values: - * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page, or unmovable page is found - * but continue walking (indicated by queue_pages.has_unmovable). - * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an - * existing folio was already on a node that does not follow the - * policy. - */ -static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, - unsigned long end, struct mm_walk *walk) - __releases(ptl) +static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { - int ret = 0; struct folio *folio; struct queue_pages *qp = walk->private; - unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { - ret = -EIO; - goto unlock; + qp->nr_failed++; + return; } folio = pfn_folio(pmd_pfn(*pmd)); if (is_huge_zero_page(&folio->page)) { walk->action = ACTION_CONTINUE; - goto unlock; + return; } if (!queue_folio_required(folio, qp)) - goto unlock; - - flags = qp->flags; - /* go to folio migration */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(walk->vma) || - migrate_folio_add(folio, qp->pagelist, flags)) { - qp->has_unmovable = true; - goto unlock; - } - } else - ret = -EIO; -unlock: - spin_unlock(ptl); - return ret; + return; + if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || + !vma_migratable(walk->vma) || + !migrate_folio_add(folio, qp->pagelist, qp->flags)) + qp->nr_failed++; } /* - * Scan through pages checking if pages follow certain conditions, - * and move them to the pagelist if they do. + * Scan through folios, checking if they satisfy the required conditions, + * moving them from LRU to local pagelist for migration if they do (or not). * - * queue_folios_pte_range() has three possible return values: - * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page, or unmovable page is found - * but continue walking (indicated by queue_pages.has_unmovable). - * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already - * on a node that does not follow the policy. + * queue_folios_pte_range() has two possible return values: + * 0 - continue walking to scan for more, even if an existing folio on the + * wrong node could not be isolated and queued for migration. + * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, + * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -516,8 +507,11 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) - return queue_folios_pmd(pmd, ptl, addr, end, walk); + if (ptl) { + queue_folios_pmd(pmd, walk); + spin_unlock(ptl); + goto out; + } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { @@ -526,8 +520,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); - if (!pte_present(ptent)) + if (pte_none(ptent)) + continue; + if (!pte_present(ptent)) { + if (is_migration_entry(pte_to_swp_entry(ptent))) + qp->nr_failed++; continue; + } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; @@ -539,95 +538,87 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_folio_required(folio, qp)) continue; - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* - * MPOL_MF_STRICT must be specified if we get here. - * Continue walking vmas due to MPOL_MF_MOVE* flags. - */ - if (!vma_migratable(vma)) - qp->has_unmovable = true; - + if (folio_test_large(folio)) { /* - * Do not abort immediately since there may be - * temporary off LRU pages in the range. Still - * need migrate other LRU pages. + * A large folio can only be isolated from LRU once, + * but may be mapped by many PTEs (and Copy-On-Write may + * intersperse PTEs of other, order 0, folios). This is + * a common case, so don't mistake it for failure (but + * there can be other cases of multi-mapped pages which + * this quick check does not help to filter out - and a + * search of the pagelist might grow to be prohibitive). + * + * migrate_pages(&pagelist) returns nr_failed folios, so + * check "large" now so that queue_pages_range() returns + * a comparable nr_failed folios. This does imply that + * if folio could not be isolated for some racy reason + * at its first PTE, later PTEs will not give it another + * chance of isolation; but keeps the accounting simple. */ - if (migrate_folio_add(folio, qp->pagelist, flags)) - qp->has_unmovable = true; - } else - break; + if (folio == qp->large) + continue; + qp->large = folio; + } + if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || + !vma_migratable(vma) || + !migrate_folio_add(folio, qp->pagelist, flags)) { + qp->nr_failed++; + if (strictly_unmovable(flags)) + break; + } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - - return addr != end ? -EIO : 0; +out: + if (qp->nr_failed && strictly_unmovable(flags)) + return -EIO; + return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - int ret = 0; #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; - unsigned long flags = (qp->flags & MPOL_MF_VALID); + unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(pte); - if (!pte_present(entry)) + if (!pte_present(entry)) { + if (unlikely(is_hugetlb_entry_migration(entry))) + qp->nr_failed++; goto unlock; + } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; - - if (flags == MPOL_MF_STRICT) { - /* - * STRICT alone means only detecting misplaced folio and no - * need to further check other vma. - */ - ret = -EIO; + if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || + !vma_migratable(walk->vma)) { + qp->nr_failed++; goto unlock; } - - if (!vma_migratable(walk->vma)) { - /* - * Must be STRICT with MOVE*, otherwise .test_walk() have - * stopped walking current vma. - * Detecting misplaced folio but allow migrating folios which - * have been queued. - */ - qp->has_unmovable = true; - goto unlock; - } - /* - * With MPOL_MF_MOVE, we try to migrate only unshared folios. If it - * is shared it is likely not worth migrating. + * 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 mapcount of the folio instead. + * expensive, so check the estimated sharers of the folio instead. */ - if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && folio_estimated_sharers(folio) == 1 && - !hugetlb_pmd_shared(pte))) { - if (!isolate_hugetlb(folio, qp->pagelist) && - (flags & MPOL_MF_STRICT)) - /* - * Failed to isolate folio but allow migrating pages - * which have been queued. - */ - qp->has_unmovable = true; - } + if ((flags & MPOL_MF_MOVE_ALL) || + (folio_estimated_sharers(folio) == 1 && !hugetlb_pmd_shared(pte))) + if (!isolate_hugetlb(folio, qp->pagelist)) + qp->nr_failed++; unlock: spin_unlock(ptl); -#else - BUG(); + if (qp->nr_failed && strictly_unmovable(flags)) + return -EIO; #endif - return ret; + return 0; } #ifdef CONFIG_NUMA_BALANCING @@ -656,12 +647,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, return nr_updated; } -#else -static unsigned long change_prot_numa(struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - return 0; -} #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, @@ -700,16 +685,11 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, if (endvma > end) endvma = end; - if (flags & MPOL_MF_LAZY) { - /* Similar to task_numa_work, skip inaccessible VMAs */ - if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && - !(vma->vm_flags & VM_MIXEDMAP)) - change_prot_numa(vma, start, endvma); - return 1; - } - - /* queue pages from current vma */ - if (flags & MPOL_MF_VALID) + /* + * 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. + */ + if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } @@ -731,22 +711,21 @@ static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { /* * Walk through page tables and collect pages to be migrated. * - * If pages found in a given range are on a set of nodes (determined by - * @nodes and @flags,) it's isolated and queued to the pagelist which is - * passed via @private. + * If pages found in a given range are not on the required set of @nodes, + * and migration is allowed, they are isolated and queued to @pagelist. * - * queue_pages_range() has three possible return values: - * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. - * 0 - queue pages successfully or no misplaced page. - * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or - * memory range specified by nodemask and maxnode points outside - * your accessible address space (-EFAULT) + * queue_pages_range() may return: + * 0 - all pages already on the right node, or successfully queued for moving + * (or neither strict checking nor moving requested: only range checking). + * >0 - this number of misplaced folios could not be queued for moving + * (a hugetlbfs page or a transparent huge page being counted as 1). + * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. + * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ -static int +static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, - struct list_head *pagelist, bool lock_vma) + struct list_head *pagelist) { int err; struct queue_pages qp = { @@ -756,20 +735,17 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, - .has_unmovable = false, }; - const struct mm_walk_ops *ops = lock_vma ? + const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); - if (qp.has_unmovable) - err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; - return err; + return err ? : qp.nr_failed; } /* @@ -777,7 +753,7 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, - struct mempolicy *pol) + struct mempolicy *pol) { int err; struct mempolicy *old; @@ -785,11 +761,6 @@ static int vma_replace_policy(struct vm_area_struct *vma, vma_assert_write_locked(vma); - pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", - vma->vm_start, vma->vm_end, vma->vm_pgoff, - vma->vm_ops, vma->vm_file, - vma->vm_ops ? vma->vm_ops->set_policy : NULL); - new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); @@ -815,10 +786,7 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { - struct vm_area_struct *merged; unsigned long vmstart, vmend; - pgoff_t pgoff; - int err; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { @@ -828,31 +796,14 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, vmstart = vma->vm_start; } - if (mpol_equal(vma_policy(vma), new_pol)) { + if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } - pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); - merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, new_pol, - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (merged) { - *prev = merged; - return vma_replace_policy(merged, new_pol); - } - - if (vma->vm_start != vmstart) { - err = split_vma(vmi, vma, vmstart, 1); - if (err) - return err; - } - - if (vma->vm_end != vmend) { - err = split_vma(vmi, vma, vmend, 0); - if (err) - return err; - } + vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); + if (IS_ERR(vma)) + return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); @@ -900,18 +851,18 @@ out: * * Called with task's alloc_lock held */ -static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) +static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); - if (p == &default_policy) + if (pol == &default_policy) return; - switch (p->mode) { + switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: - *nodes = p->nodes; + *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ @@ -958,6 +909,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } if (flags & MPOL_F_ADDR) { + pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We @@ -969,10 +921,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, mmap_read_unlock(mm); return -EFAULT; } - if (vma->vm_ops && vma->vm_ops->get_policy) - pol = vma->vm_ops->get_policy(vma, addr); - else - pol = vma->vm_policy; + pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; @@ -1032,16 +981,16 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } #ifdef CONFIG_MIGRATION -static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, +static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* - * We try to migrate only unshared folios. If it is shared it - * is likely not worth migrating. + * 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 mapcount of the folio instead. + * expensive, so check the estimated sharers of the folio instead. */ if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) { if (folio_isolate_lru(folio)) { @@ -1049,32 +998,31 @@ static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); - } else if (flags & MPOL_MF_STRICT) { + } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be - * isolated, so they can't be moved at the moment. It - * should return -EIO for this case too. + * isolated, so they can't be moved at the moment. */ - return -EIO; + return false; } } - - return 0; + return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ -static int migrate_to_node(struct mm_struct *mm, int source, int dest, - int flags) +static long migrate_to_node(struct mm_struct *mm, int source, int dest, + int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); - int err = 0; + long nr_failed; + long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, @@ -1083,23 +1031,30 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodes_clear(nmask); node_set(source, nmask); + VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); + + mmap_read_lock(mm); + vma = find_vma(mm, 0); + /* - * This does not "check" the range but isolates all pages that + * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address - * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. + * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, + * but passes back the count of pages which could not be isolated. */ - vma = find_vma(mm, 0); - VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); - queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, - flags | MPOL_MF_DISCONTIG_OK, &pagelist, false); + nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, + flags | MPOL_MF_DISCONTIG_OK, &pagelist); + mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } + if (err >= 0) + err += nr_failed; return err; } @@ -1112,14 +1067,12 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { - int busy = 0; - int err = 0; + long nr_failed = 0; + long err = 0; nodemask_t tmp; lru_cache_disable(); - mmap_read_lock(mm); - /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' @@ -1195,59 +1148,58 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) - busy += err; + nr_failed += err; if (err < 0) break; } - mmap_read_unlock(mm); lru_cache_enable(); if (err < 0) return err; - return busy; - + return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* - * Allocate a new page for page migration based on vma policy. - * Start by assuming the page is mapped by the same vma as contains @start. - * Search forward from there, if not. N.B., this assumes that the - * list of pages handed to migrate_pages()--which is how we get here-- - * is in virtual address order. + * Allocate a new folio for page migration, according to NUMA mempolicy. */ -static struct folio *new_folio(struct folio *src, unsigned long start) +static struct folio *alloc_migration_target_by_mpol(struct folio *src, + unsigned long private) { - struct vm_area_struct *vma; - unsigned long address; - VMA_ITERATOR(vmi, current->mm, start); - gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; + 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; - for_each_vma(vmi, vma) { - address = page_address_in_vma(&src->page, vma); - if (address != -EFAULT) - break; - } + order = folio_order(src); + ilx += src->index >> order; if (folio_test_hugetlb(src)) { - return alloc_hugetlb_folio_vma(folio_hstate(src), - vma, address); + nodemask_t *nodemask; + struct hstate *h; + + 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); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; + else + gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; - /* - * if !vma, vma_alloc_folio() will use task or system default policy - */ - return vma_alloc_folio(gfp, folio_order(src), vma, address, - folio_test_large(src)); + page = alloc_pages_mpol(gfp, order, pol, ilx, nid); + return page_rmappable_folio(page); } #else -static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, +static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { - return -EIO; + return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, @@ -1256,7 +1208,8 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct folio *new_folio(struct folio *src, unsigned long start) +static struct folio *alloc_migration_target_by_mpol(struct folio *src, + unsigned long private) { return NULL; } @@ -1269,10 +1222,11 @@ static long do_mbind(unsigned long start, unsigned long len, struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; + struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; - int err; - int ret; + long err; + long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) @@ -1298,9 +1252,6 @@ static long do_mbind(unsigned long start, unsigned long len, if (IS_ERR(new)) return PTR_ERR(new); - if (flags & MPOL_MF_LAZY) - new->flags |= MPOL_F_MOF; - /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all @@ -1308,14 +1259,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!new) flags |= MPOL_MF_DISCONTIG_OK; - pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", - start, start + len, mode, mode_flags, - nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); - - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); - } { NODEMASK_SCRATCH(scratch); if (scratch) { @@ -1331,45 +1276,81 @@ static long do_mbind(unsigned long start, unsigned long len, goto mpol_out; /* - * Lock the VMAs before scanning for pages to migrate, to ensure we don't - * miss a concurrently inserted page. + * Lock the VMAs before scanning for pages to migrate, + * to ensure we don't miss a concurrently inserted page. */ - ret = queue_pages_range(mm, start, end, nmask, - flags | MPOL_MF_INVERT, &pagelist, true); + nr_failed = queue_pages_range(mm, start, end, nmask, + flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); - if (ret < 0) { - err = ret; - goto up_out; - } - - vma_iter_init(&vmi, mm, start); - prev = vma_prev(&vmi); - for_each_vma_range(vmi, vma, end) { - err = mbind_range(&vmi, vma, &prev, start, end, new); - if (err) - break; + if (nr_failed < 0) { + err = nr_failed; + nr_failed = 0; + } else { + vma_iter_init(&vmi, mm, start); + prev = vma_prev(&vmi); + for_each_vma_range(vmi, vma, end) { + err = mbind_range(&vmi, vma, &prev, start, end, new); + if (err) + break; + } } - if (!err) { - int nr_failed = 0; - - if (!list_empty(&pagelist)) { - WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_folio, NULL, - start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); - if (nr_failed) - putback_movable_pages(&pagelist); + if (!err && !list_empty(&pagelist)) { + /* Convert MPOL_DEFAULT's NULL to task or default policy */ + if (!new) { + new = get_task_policy(current); + mpol_get(new); } + mmpol.pol = new; + mmpol.ilx = 0; - if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) - err = -EIO; - } else { -up_out: - if (!list_empty(&pagelist)) - putback_movable_pages(&pagelist); + /* + * In the interleaved case, attempt to allocate on exactly the + * targeted nodes, for the first VMA to be migrated; for later + * 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; + unsigned int order; + unsigned long addr = -EFAULT; + + list_for_each_entry(page, &pagelist, lru) { + if (!PageKsm(page)) + break; + } + if (!list_entry_is_head(page, &pagelist, lru)) { + vma_iter_init(&vmi, mm, start); + for_each_vma_range(vmi, vma, end) { + addr = page_address_in_vma(page, vma); + if (addr != -EFAULT) + break; + } + } + if (addr != -EFAULT) { + order = compound_order(page); + /* 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; + } + } } mmap_write_unlock(mm); + + if (!err && !list_empty(&pagelist)) { + nr_failed |= migrate_pages(&pagelist, + alloc_migration_target_by_mpol, NULL, + (unsigned long)&mmpol, MIGRATE_SYNC, + MR_MEMPOLICY_MBIND, NULL); + } + + if (nr_failed && (flags & MPOL_MF_STRICT)) + err = -EIO; + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) @@ -1690,7 +1671,6 @@ out: out_put: put_task_struct(task); goto out; - } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, @@ -1700,7 +1680,6 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } - /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, @@ -1767,34 +1746,19 @@ bool vma_migratable(struct vm_area_struct *vma) } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, pgoff_t *ilx) { - struct mempolicy *pol = NULL; - - if (vma) { - if (vma->vm_ops && vma->vm_ops->get_policy) { - pol = vma->vm_ops->get_policy(vma, addr); - } else if (vma->vm_policy) { - pol = vma->vm_policy; - - /* - * shmem_alloc_page() passes MPOL_F_SHARED policy with - * a pseudo vma whose vma->vm_ops=NULL. Take a reference - * count on these policies which will be dropped by - * mpol_cond_put() later - */ - if (mpol_needs_cond_ref(pol)) - mpol_get(pol); - } - } - - return pol; + *ilx = 0; + return (vma->vm_ops && vma->vm_ops->get_policy) ? + vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* - * get_vma_policy(@vma, @addr) + * get_vma_policy(@vma, @addr, @order, @ilx) * @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 * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. @@ -1803,14 +1767,18 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, - unsigned long addr) +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr, int order, pgoff_t *ilx) { - struct mempolicy *pol = __get_vma_policy(vma, addr); + struct mempolicy *pol; + pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); - + if (pol->mode == MPOL_INTERLEAVE) { + *ilx += vma->vm_pgoff >> order; + *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); + } return pol; } @@ -1820,8 +1788,9 @@ bool vma_policy_mof(struct vm_area_struct *vma) 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); + pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); @@ -1856,64 +1825,15 @@ bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) return zone >= dynamic_policy_zone; } -/* - * Return a nodemask representing a mempolicy for filtering nodes for - * page allocation - */ -nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) -{ - int mode = policy->mode; - - /* Lower zones don't get a nodemask applied for MPOL_BIND */ - if (unlikely(mode == MPOL_BIND) && - apply_policy_zone(policy, gfp_zone(gfp)) && - cpuset_nodemask_valid_mems_allowed(&policy->nodes)) - return &policy->nodes; - - if (mode == MPOL_PREFERRED_MANY) - return &policy->nodes; - - return NULL; -} - -/* - * Return the preferred node id for 'prefer' mempolicy, and return - * the given id for all other policies. - * - * policy_node() is always coupled with policy_nodemask(), which - * secures the nodemask limit for 'bind' and 'prefer-many' policy. - */ -static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) -{ - if (policy->mode == MPOL_PREFERRED) { - nd = first_node(policy->nodes); - } else { - /* - * __GFP_THISNODE shouldn't even be used with the bind policy - * because we might easily break the expectation to stay on the - * requested node and not break the policy. - */ - WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); - } - - if ((policy->mode == MPOL_BIND || - policy->mode == MPOL_PREFERRED_MANY) && - policy->home_node != NUMA_NO_NODE) - return policy->home_node; - - return nd; -} - /* Do dynamic interleaving for a process */ -static unsigned interleave_nodes(struct mempolicy *policy) +static unsigned int interleave_nodes(struct mempolicy *policy) { - unsigned next; - struct task_struct *me = current; + unsigned int nid; - next = next_node_in(me->il_prev, policy->nodes); - if (next < MAX_NUMNODES) - me->il_prev = next; - return next; + nid = next_node_in(current->il_prev, policy->nodes); + if (nid < MAX_NUMNODES) + current->il_prev = nid; + return nid; } /* @@ -1964,11 +1884,11 @@ unsigned int mempolicy_slab_node(void) } /* - * Do static interleaving for a VMA with known offset @n. Returns the n'th - * node in pol->nodes (starting from n=0), wrapping around if n exceeds the - * number of present nodes. + * Do static interleaving for interleave index @ilx. Returns the ilx'th + * node in pol->nodes (starting from ilx=0), wrapping around if ilx + * exceeds the number of present nodes. */ -static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) +static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask = pol->nodes; unsigned int target, nnodes; @@ -1986,33 +1906,54 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) nnodes = nodes_weight(nodemask); if (!nnodes) return numa_node_id(); - target = (unsigned int)n % nnodes; + target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } -/* Determine a node number for interleave */ -static inline unsigned interleave_nid(struct mempolicy *pol, - struct vm_area_struct *vma, unsigned long addr, int shift) +/* + * Return a nodemask representing a mempolicy for filtering nodes for + * page allocation, together with preferred node id (or the input node id). + */ +static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, + pgoff_t ilx, int *nid) { - if (vma) { - unsigned long off; + nodemask_t *nodemask = NULL; + switch (pol->mode) { + case MPOL_PREFERRED: + /* Override input node id */ + *nid = first_node(pol->nodes); + break; + case MPOL_PREFERRED_MANY: + nodemask = &pol->nodes; + if (pol->home_node != NUMA_NO_NODE) + *nid = pol->home_node; + break; + case MPOL_BIND: + /* Restrict to nodemask (but not on lower zones) */ + if (apply_policy_zone(pol, gfp_zone(gfp)) && + cpuset_nodemask_valid_mems_allowed(&pol->nodes)) + nodemask = &pol->nodes; + if (pol->home_node != NUMA_NO_NODE) + *nid = pol->home_node; /* - * for small pages, there is no difference between - * shift and PAGE_SHIFT, so the bit-shift is safe. - * for huge pages, since vm_pgoff is in units of small - * pages, we need to shift off the always 0 bits to get - * a useful offset. + * __GFP_THISNODE shouldn't even be used with the bind policy + * because we might easily break the expectation to stay on the + * requested node and not break the policy. */ - BUG_ON(shift < PAGE_SHIFT); - off = vma->vm_pgoff >> (shift - PAGE_SHIFT); - off += (addr - vma->vm_start) >> shift; - return offset_il_node(pol, off); - } else - return interleave_nodes(pol); + WARN_ON_ONCE(gfp & __GFP_THISNODE); + break; + case MPOL_INTERLEAVE: + /* Override input node id */ + *nid = (ilx == NO_INTERLEAVE_INDEX) ? + interleave_nodes(pol) : interleave_nid(pol, ilx); + break; + } + + return nodemask; } #ifdef CONFIG_HUGETLBFS @@ -2028,27 +1969,16 @@ static inline unsigned interleave_nid(struct mempolicy *pol, * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. - * - * Must be protected by read_mems_allowed_begin() */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, - struct mempolicy **mpol, nodemask_t **nodemask) + struct mempolicy **mpol, nodemask_t **nodemask) { + pgoff_t ilx; int nid; - int mode; - - *mpol = get_vma_policy(vma, addr); - *nodemask = NULL; - mode = (*mpol)->mode; - if (unlikely(mode == MPOL_INTERLEAVE)) { - nid = interleave_nid(*mpol, vma, addr, - huge_page_shift(hstate_vma(vma))); - } else { - nid = policy_node(gfp_flags, *mpol, numa_node_id()); - if (mode == MPOL_BIND || mode == MPOL_PREFERRED_MANY) - *nodemask = &(*mpol)->nodes; - } + nid = numa_node_id(); + *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); + *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } @@ -2126,27 +2056,8 @@ bool mempolicy_in_oom_domain(struct task_struct *tsk, return ret; } -/* Allocate a page in interleaved policy. - Own path because it needs to do special accounting. */ -static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, - unsigned nid) -{ - struct page *page; - - page = __alloc_pages(gfp, order, nid, NULL); - /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ - if (!static_branch_likely(&vm_numa_stat_key)) - return page; - if (page && page_to_nid(page) == nid) { - preempt_disable(); - __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); - preempt_enable(); - } - return page; -} - static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, - int nid, struct mempolicy *pol) + int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; @@ -2159,7 +2070,7 @@ 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, &pol->nodes); + page = __alloc_pages(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_pages(gfp, order, nid, NULL); @@ -2167,61 +2078,29 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, } /** - * vma_alloc_folio - Allocate a folio for a VMA. + * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. - * @order: Order of the folio. - * @vma: Pointer to VMA or NULL if not available. - * @addr: Virtual address of the allocation. Must be inside @vma. - * @hugepage: For hugepages try only the preferred node if possible. + * @order: Order of the page allocation. + * @pol: Pointer to the NUMA mempolicy. + * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). + * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * - * Allocate a folio for a specific address in @vma, using the appropriate - * NUMA policy. When @vma is not NULL 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. - * - * Return: The folio on success or NULL if allocation fails. + * Return: The page 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 page *alloc_pages_mpol(gfp_t gfp, unsigned int order, + struct mempolicy *pol, pgoff_t ilx, int nid) { - struct mempolicy *pol; - int node = numa_node_id(); - struct folio *folio; - int preferred_nid; - nodemask_t *nmask; - - pol = get_vma_policy(vma, addr); - - if (pol->mode == MPOL_INTERLEAVE) { - struct page *page; - unsigned nid; - - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); - mpol_cond_put(pol); - gfp |= __GFP_COMP; - page = alloc_page_interleave(gfp, order, nid); - folio = (struct folio *)page; - if (folio && order > 1) - folio_prep_large_rmappable(folio); - goto out; - } - - if (pol->mode == MPOL_PREFERRED_MANY) { - struct page *page; + nodemask_t *nodemask; + struct page *page; - node = policy_node(gfp, pol, node); - gfp |= __GFP_COMP; - page = alloc_pages_preferred_many(gfp, order, node, pol); - mpol_cond_put(pol); - folio = (struct folio *)page; - if (folio && order > 1) - folio_prep_large_rmappable(folio); - goto out; - } + nodemask = policy_nodemask(gfp, pol, ilx, &nid); - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; + if (pol->mode == MPOL_PREFERRED_MANY) + return alloc_pages_preferred_many(gfp, order, nid, nodemask); + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + /* filter "hugepage" allocation, unless from alloc_pages() */ + order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred @@ -2232,39 +2111,68 @@ struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ - if (pol->mode == MPOL_PREFERRED) - hpage_node = first_node(pol->nodes); - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); + if (pol->mode != MPOL_INTERLEAVE && + (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ - folio = __folio_alloc_node(gfp | __GFP_THISNODE | - __GFP_NORETRY, order, hpage_node); - + page = __alloc_pages_node(nid, + gfp | __GFP_THISNODE | __GFP_NORETRY, order); + if (page || !(gfp & __GFP_DIRECT_RECLAIM)) + return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ - if (!folio && (gfp & __GFP_DIRECT_RECLAIM)) - folio = __folio_alloc(gfp, order, hpage_node, - nmask); + } + } - goto out; + page = __alloc_pages(gfp, order, nid, nodemask); + + if (unlikely(pol->mode == MPOL_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) { + preempt_disable(); + __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); } } - nmask = policy_nodemask(gfp, pol); - preferred_nid = policy_node(gfp, pol, node); - folio = __folio_alloc(gfp, order, preferred_nid, nmask); + return 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. + * + * 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 mempolicy *pol; + pgoff_t ilx; + struct page *page; + + pol = get_vma_policy(vma, addr, order, &ilx); + page = alloc_pages_mpol(gfp | __GFP_COMP, order, + pol, ilx, numa_node_id()); mpol_cond_put(pol); -out: - return folio; + return page_rmappable_folio(page); } EXPORT_SYMBOL(vma_alloc_folio); @@ -2282,40 +2190,25 @@ 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 order) +struct page *alloc_pages(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; - struct page *page; - - if (!in_interrupt() && !(gfp & __GFP_THISNODE)) - pol = get_task_policy(current); /* * No reference counting needed for current->mempolicy * nor system default_policy */ - if (pol->mode == MPOL_INTERLEAVE) - page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); - else if (pol->mode == MPOL_PREFERRED_MANY) - page = alloc_pages_preferred_many(gfp, order, - policy_node(gfp, pol, numa_node_id()), pol); - else - page = __alloc_pages(gfp, order, - policy_node(gfp, pol, numa_node_id()), - policy_nodemask(gfp, pol)); + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); - return page; + return alloc_pages_mpol(gfp, order, + pol, NO_INTERLEAVE_INDEX, numa_node_id()); } EXPORT_SYMBOL(alloc_pages); -struct folio *folio_alloc(gfp_t gfp, unsigned order) +struct folio *folio_alloc(gfp_t gfp, unsigned int order) { - struct page *page = alloc_pages(gfp | __GFP_COMP, order); - struct folio *folio = (struct folio *)page; - - if (folio && order > 1) - folio_prep_large_rmappable(folio); - return folio; + return page_rmappable_folio(alloc_pages(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc); @@ -2384,6 +2277,8 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; + nodemask_t *nodemask; + int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); @@ -2396,14 +2291,15 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); - return __alloc_pages_bulk(gfp, policy_node(gfp, pol, numa_node_id()), - policy_nodemask(gfp, pol), nr_pages, NULL, - 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); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { - struct mempolicy *pol = mpol_dup(vma_policy(src)); + struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); @@ -2488,8 +2384,8 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ -static struct sp_node * -sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) +static struct sp_node *sp_lookup(struct shared_policy *sp, + pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; @@ -2540,13 +2436,11 @@ static void sp_insert(struct shared_policy *sp, struct sp_node *new) } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); - pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, - new->policy ? new->policy->mode : 0); } /* Find shared policy intersecting idx */ -struct mempolicy * -mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) +struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, + pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; @@ -2570,39 +2464,38 @@ static void sp_free(struct sp_node *n) } /** - * mpol_misplaced - check whether current page node is valid in policy + * mpol_misplaced - check whether current folio node is valid in policy * - * @page: page to be checked - * @vma: vm area where page mapped - * @addr: virtual address where page mapped + * @folio: folio to be checked + * @vma: vm area where folio mapped + * @addr: virtual address in @vma for shared policy lookup and interleave policy * - * Lookup current policy node id for vma,addr and "compare to" page's + * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * 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 page from. + * policy, or a suitable node ID to allocate a replacement folio from. */ -int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) +int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, + unsigned long addr) { struct mempolicy *pol; + pgoff_t ilx; struct zoneref *z; - int curnid = page_to_nid(page); - unsigned long pgoff; + int curnid = folio_nid(folio); int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; - pol = get_vma_policy(vma, addr); + pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: - pgoff = vma->vm_pgoff; - pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; - polnid = offset_il_node(pol, pgoff); + polnid = interleave_nid(pol, ilx); break; case MPOL_PREFERRED: @@ -2643,11 +2536,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long BUG(); } - /* Migrate the page towards the node whose CPU is referencing it */ + /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; - if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) + if (!should_numa_migrate_memory(current, folio, curnid, + thiscpu)) goto out; } @@ -2678,7 +2572,6 @@ void mpol_put_task_policy(struct task_struct *task) static void sp_delete(struct shared_policy *sp, struct sp_node *n) { - pr_debug("deleting %lx-l%lx\n", n->start, n->end); rb_erase(&n->nd, &sp->root); sp_free(n); } @@ -2713,8 +2606,8 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end, } /* Replace a policy range. */ -static int shared_policy_replace(struct shared_policy *sp, unsigned long start, - unsigned long end, struct sp_node *new) +static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, + pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; @@ -2797,30 +2690,30 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) rwlock_init(&sp->lock); if (mpol) { - struct vm_area_struct pvma; - struct mempolicy *new; + struct sp_node *sn; + struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; - /* contextualize the tmpfs mount point mempolicy */ - new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); - if (IS_ERR(new)) + + /* contextualize the tmpfs mount point mempolicy to this file */ + npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); + if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); - ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); + ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) - goto put_new; - - /* Create pseudo-vma that contains just the policy */ - vma_init(&pvma, NULL); - pvma.vm_end = TASK_SIZE; /* policy covers entire file */ - mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ - -put_new: - mpol_put(new); /* drop initial ref */ + goto put_npol; + + /* alloc node covering entire file; adds ref to file's npol */ + sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); + if (sn) + sp_insert(sp, sn); +put_npol: + mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: @@ -2828,46 +2721,40 @@ put_mpol: } } -int mpol_set_shared_policy(struct shared_policy *info, - struct vm_area_struct *vma, struct mempolicy *npol) +int mpol_set_shared_policy(struct shared_policy *sp, + struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); - pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", - vma->vm_pgoff, - sz, npol ? npol->mode : -1, - npol ? npol->flags : -1, - npol ? nodes_addr(npol->nodes)[0] : NUMA_NO_NODE); - - if (npol) { - new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); + if (pol) { + new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } - err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); + err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ -void mpol_free_shared_policy(struct shared_policy *p) +void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; - if (!p->root.rb_node) + if (!sp->root.rb_node) return; - write_lock(&p->lock); - next = rb_first(&p->root); + write_lock(&sp->lock); + next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); - sp_delete(p, n); + sp_delete(sp, n); } - write_unlock(&p->lock); + write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING @@ -2917,7 +2804,6 @@ static inline void __init check_numabalancing_enable(void) } #endif /* CONFIG_NUMA_BALANCING */ -/* assumes fs == KERNEL_DS */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; @@ -2980,7 +2866,6 @@ void numa_default_policy(void) /* * Parse and format mempolicy from/to strings */ - static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", @@ -2991,7 +2876,6 @@ static const char * const policy_modes[] = [MPOL_PREFERRED_MANY] = "prefer (many)", }; - #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. diff --git a/mm/migrate.c b/mm/migrate.c index b4d972d80b..bad3039d16 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -157,8 +157,8 @@ void putback_movable_pages(struct list_head *l) list_del(&folio->lru); /* * We isolated non-lru movable folio so here we can use - * __PageMovable because LRU folio's mapping cannot have - * PAGE_MAPPING_MOVABLE. + * __folio_test_movable because LRU folio's mapping cannot + * have PAGE_MAPPING_MOVABLE. */ if (unlikely(__folio_test_movable(folio))) { VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio); @@ -249,7 +249,7 @@ static bool remove_migration_pte(struct folio *folio, pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) - hugepage_add_anon_rmap(new, vma, pvmw.address, + hugepage_add_anon_rmap(folio, vma, pvmw.address, rmap_flags); else page_dup_file_rmap(new, true); @@ -531,7 +531,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, int expected_count; xas_lock_irq(&xas); - expected_count = 2 + folio_has_private(src); + expected_count = folio_expected_refs(mapping, src); if (!folio_ref_freeze(src, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; @@ -540,11 +540,11 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, dst->index = src->index; dst->mapping = src->mapping; - folio_get(dst); + folio_ref_add(dst, folio_nr_pages(dst)); xas_store(&xas, dst); - folio_ref_unfreeze(src, expected_count - 1); + folio_ref_unfreeze(src, expected_count - folio_nr_pages(src)); xas_unlock_irq(&xas); @@ -595,20 +595,20 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. */ - cpupid = page_cpupid_xchg_last(&folio->page, -1); + cpupid = folio_xchg_last_cpupid(folio, -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)); + bool f_toptier = node_is_toptier(folio_nid(folio)); + bool t_toptier = node_is_toptier(folio_nid(newfolio)); if (f_toptier != t_toptier) cpupid = -1; } - page_cpupid_xchg_last(&newfolio->page, cpupid); + folio_xchg_last_cpupid(newfolio, cpupid); folio_migrate_ksm(newfolio, folio); /* @@ -640,8 +640,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_copy_owner(newfolio, folio); - if (!folio_test_hugetlb(folio)) - mem_cgroup_migrate(folio, newfolio); + mem_cgroup_migrate(folio, newfolio); } EXPORT_SYMBOL(folio_migrate_flags); @@ -953,7 +952,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc = -EAGAIN; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); VM_BUG_ON_FOLIO(!folio_test_locked(src), src); VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); @@ -1000,7 +999,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, * src is freed; but stats require that PageAnon be left as PageAnon. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (__PageMovable(&src->page)) { + if (__folio_test_movable(src)) { VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); /* @@ -1091,7 +1090,7 @@ static void migrate_folio_done(struct folio *src, /* * Compaction can migrate also non-LRU pages which are * not accounted to NR_ISOLATED_*. They can be recognized - * as __PageMovable + * as __folio_test_movable */ if (likely(!__folio_test_movable(src))) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + @@ -1112,7 +1111,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio, int rc = -EAGAIN; int old_page_state = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); bool locked = false; bool dst_locked = false; @@ -1273,7 +1272,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, int rc; int old_page_state = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); struct list_head *prev; __migrate_folio_extract(dst, &old_page_state, &anon_vma); @@ -1506,6 +1505,7 @@ struct migrate_pages_stats { int nr_thp_succeeded; /* THP migrated successfully */ int nr_thp_failed; /* THP failed to be migrated */ int nr_thp_split; /* THP split before migrating */ + int nr_split; /* Large folio (include THP) split before migrating */ }; /* @@ -1625,6 +1625,7 @@ static int migrate_pages_batch(struct list_head *from, int nr_retry_pages = 0; int pass = 0; bool is_thp = false; + bool is_large = false; struct folio *folio, *folio2, *dst = NULL, *dst2; int rc, rc_saved = 0, nr_pages; LIST_HEAD(unmap_folios); @@ -1640,7 +1641,8 @@ static int migrate_pages_batch(struct list_head *from, nr_retry_pages = 0; list_for_each_entry_safe(folio, folio2, from, lru) { - is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio); + is_large = folio_test_large(folio); + is_thp = is_large && folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); cond_resched(); @@ -1660,6 +1662,7 @@ static int migrate_pages_batch(struct list_head *from, stats->nr_thp_failed++; if (!try_split_folio(folio, split_folios)) { stats->nr_thp_split++; + stats->nr_split++; continue; } stats->nr_failed_pages += nr_pages; @@ -1688,11 +1691,12 @@ static int migrate_pages_batch(struct list_head *from, nr_failed++; stats->nr_thp_failed += is_thp; /* Large folio NUMA faulting doesn't split to retry. */ - if (folio_test_large(folio) && !nosplit) { + if (is_large && !nosplit) { int ret = try_split_folio(folio, split_folios); if (!ret) { stats->nr_thp_split += is_thp; + stats->nr_split++; break; } else if (reason == MR_LONGTERM_PIN && ret == -EAGAIN) { @@ -1838,6 +1842,7 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio, stats->nr_succeeded += astats.nr_succeeded; stats->nr_thp_succeeded += astats.nr_thp_succeeded; stats->nr_thp_split += astats.nr_thp_split; + stats->nr_split += astats.nr_split; if (rc < 0) { stats->nr_failed_pages += astats.nr_failed_pages; stats->nr_thp_failed += astats.nr_thp_failed; @@ -1845,7 +1850,11 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio, return rc; } stats->nr_thp_failed += astats.nr_thp_split; - nr_failed += astats.nr_thp_split; + /* + * Do not count rc, as pages will be retried below. + * Count nr_split only, since it includes nr_thp_split. + */ + nr_failed += astats.nr_split; /* * Fall back to migrate all failed folios one by one synchronously. All * failed folios except split THPs will be retried, so their failure @@ -1980,7 +1989,8 @@ out: count_vm_events(THP_MIGRATION_SPLIT, stats.nr_thp_split); trace_mm_migrate_pages(stats.nr_succeeded, stats.nr_failed_pages, stats.nr_thp_succeeded, stats.nr_thp_failed, - stats.nr_thp_split, mode, reason); + stats.nr_thp_split, stats.nr_split, mode, + reason); if (ret_succeeded) *ret_succeeded = stats.nr_succeeded; @@ -2039,8 +2049,7 @@ static int store_status(int __user *status, int start, int value, int nr) return 0; } -static int do_move_pages_to_node(struct mm_struct *mm, - struct list_head *pagelist, int node) +static int do_move_pages_to_node(struct list_head *pagelist, int node) { int err; struct migration_target_control mtc = { @@ -2070,8 +2079,8 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p, struct vm_area_struct *vma; unsigned long addr; struct page *page; + struct folio *folio; int err; - bool isolated; mmap_read_lock(mm); addr = (unsigned long)untagged_addr_remote(mm, p); @@ -2092,51 +2101,44 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p, if (!page) goto out; - if (is_zone_device_page(page)) - goto out_putpage; + folio = page_folio(page); + if (folio_is_zone_device(folio)) + goto out_putfolio; err = 0; - if (page_to_nid(page) == node) - goto out_putpage; + if (folio_nid(folio) == node) + goto out_putfolio; err = -EACCES; if (page_mapcount(page) > 1 && !migrate_all) - goto out_putpage; + goto out_putfolio; - if (PageHuge(page)) { - if (PageHead(page)) { - isolated = isolate_hugetlb(page_folio(page), pagelist); - err = isolated ? 1 : -EBUSY; - } + err = -EBUSY; + if (folio_test_hugetlb(folio)) { + if (isolate_hugetlb(folio, pagelist)) + err = 1; } else { - struct page *head; - - head = compound_head(page); - isolated = isolate_lru_page(head); - if (!isolated) { - err = -EBUSY; - goto out_putpage; - } + if (!folio_isolate_lru(folio)) + goto out_putfolio; err = 1; - list_add_tail(&head->lru, pagelist); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + page_is_file_lru(head), - thp_nr_pages(head)); + list_add_tail(&folio->lru, pagelist); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); } -out_putpage: +out_putfolio: /* - * Either remove the duplicate refcount from - * isolate_lru_page() or drop the page ref if it was - * not isolated. + * Either remove the duplicate refcount from folio_isolate_lru() + * or drop the folio ref if it was not isolated. */ - put_page(page); + folio_put(folio); out: mmap_read_unlock(mm); return err; } -static int move_pages_and_store_status(struct mm_struct *mm, int node, +static int move_pages_and_store_status(int node, struct list_head *pagelist, int __user *status, int start, int i, unsigned long nr_pages) { @@ -2145,7 +2147,7 @@ static int move_pages_and_store_status(struct mm_struct *mm, int node, if (list_empty(pagelist)) return 0; - err = do_move_pages_to_node(mm, pagelist, node); + err = do_move_pages_to_node(pagelist, node); if (err) { /* * Positive err means the number of failed @@ -2213,7 +2215,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, current_node = node; start = i; } else if (node != current_node) { - err = move_pages_and_store_status(mm, current_node, + err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err) goto out; @@ -2248,7 +2250,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, if (err) goto out_flush; - err = move_pages_and_store_status(mm, current_node, &pagelist, + err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err) { /* We have accounted for page i */ @@ -2260,7 +2262,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, } out_flush: /* Make sure we do not overwrite the existing error */ - err1 = move_pages_and_store_status(mm, current_node, &pagelist, + err1 = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err >= 0) err = err1; @@ -2501,16 +2503,9 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src, return __folio_alloc_node(gfp, order, nid); } -static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio) { - int nr_pages = thp_nr_pages(page); - int order = compound_order(page); - - VM_BUG_ON_PAGE(order && !PageTransHuge(page), page); - - /* Do not migrate THP mapped by multiple processes */ - if (PageTransHuge(page) && total_mapcount(page) > 1) - return 0; + int nr_pages = folio_nr_pages(folio); /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, nr_pages)) { @@ -2522,75 +2517,79 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (managed_zone(pgdat->node_zones + z)) break; } - wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); + wakeup_kswapd(pgdat->node_zones + z, 0, + folio_order(folio), ZONE_MOVABLE); return 0; } - if (!isolate_lru_page(page)) + if (!folio_isolate_lru(folio)) return 0; - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), + node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), nr_pages); /* - * Isolating the page has taken another reference, so the - * caller's reference can be safely dropped without the page + * Isolating the folio has taken another reference, so the + * caller's reference can be safely dropped without the folio * disappearing underneath us during migration. */ - put_page(page); + folio_put(folio); return 1; } /* - * Attempt to migrate a misplaced page to the specified destination + * Attempt to migrate a misplaced folio to the specified destination * node. Caller is expected to have an elevated reference count on - * the page that will be dropped by this function before returning. + * the folio that will be dropped by this function before returning. */ -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, - int node) +int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, + int node) { pg_data_t *pgdat = NODE_DATA(node); int isolated; int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - int nr_pages = thp_nr_pages(page); + int nr_pages = folio_nr_pages(folio); /* - * Don't migrate file pages that are mapped in multiple processes + * Don't migrate file folios that are mapped in multiple processes * with execute permissions as they are probably shared libraries. + * 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 mapcount of the folio instead. */ - if (page_mapcount(page) != 1 && page_is_file_lru(page) && + if (folio_estimated_sharers(folio) != 1 && folio_is_file_lru(folio) && (vma->vm_flags & VM_EXEC)) goto out; /* - * Also do not migrate dirty pages as not all filesystems can move - * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles. + * Also do not migrate dirty folios as not all filesystems can move + * dirty folios in MIGRATE_ASYNC mode which is a waste of cycles. */ - if (page_is_file_lru(page) && PageDirty(page)) + if (folio_is_file_lru(folio) && folio_test_dirty(folio)) goto out; - isolated = numamigrate_isolate_page(pgdat, page); + isolated = numamigrate_isolate_folio(pgdat, folio); if (!isolated) goto out; - list_add(&page->lru, &migratepages); + list_add(&folio->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio, NULL, node, MIGRATE_ASYNC, MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { - list_del(&page->lru); - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + - page_is_file_lru(page), -nr_pages); - putback_lru_page(page); + list_del(&folio->lru); + node_stat_mod_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio), -nr_pages); + folio_putback_lru(folio); } isolated = 0; } if (nr_succeeded) { count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); - if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node)) + if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node)) mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, nr_succeeded); } @@ -2598,7 +2597,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, return isolated; out: - put_page(page); + folio_put(folio); return 0; } #endif /* CONFIG_NUMA_BALANCING */ diff --git a/mm/mlock.c b/mm/mlock.c index 06bdfab83b..086546ac57 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -305,6 +305,62 @@ void munlock_folio(struct folio *folio) local_unlock(&mlock_fbatch.lock); } +static inline unsigned int folio_mlock_step(struct folio *folio, + pte_t *pte, unsigned long addr, unsigned long end) +{ + unsigned int count, i, nr = folio_nr_pages(folio); + unsigned long pfn = folio_pfn(folio); + pte_t ptent = ptep_get(pte); + + if (!folio_test_large(folio)) + return 1; + + count = pfn + nr - pte_pfn(ptent); + count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT); + + for (i = 0; i < count; i++, pte++) { + pte_t entry = ptep_get(pte); + + if (!pte_present(entry)) + break; + if (pte_pfn(entry) - pfn >= nr) + break; + } + + return i; +} + +static inline bool allow_mlock_munlock(struct folio *folio, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned int step) +{ + /* + * For unlock, allow munlock large folio which is partially + * mapped to VMA. As it's possible that large folio is + * mlocked and VMA is split later. + * + * During memory pressure, such kind of large folio can + * be split. And the pages are not in VM_LOCKed VMA + * can be reclaimed. + */ + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + /* folio_within_range() cannot take KSM, but any small folio is OK */ + if (!folio_test_large(folio)) + return true; + + /* folio not in range [start, end), skip mlock */ + if (!folio_within_range(folio, vma, start, end)) + return false; + + /* folio is not fully mapped, skip mlock */ + if (step != folio_nr_pages(folio)) + return false; + + return true; +} + static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -314,6 +370,8 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; + unsigned int step = 1; + unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { @@ -334,6 +392,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, walk->action = ACTION_AGAIN; return 0; } + for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) @@ -341,12 +400,19 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; - if (folio_test_large(folio)) - continue; + + step = folio_mlock_step(folio, pte, addr, end); + if (!allow_mlock_munlock(folio, vma, start, end, step)) + goto next_entry; + if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); + +next_entry: + pte += step - 1; + addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: @@ -414,7 +480,6 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; - pgoff_t pgoff; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; @@ -425,28 +490,12 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vma_merge(vmi, mm, *prev, start, end, newflags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (*prev) { - vma = *prev; - goto success; - } - - if (start != vma->vm_start) { - ret = split_vma(vmi, vma, start, 1); - if (ret) - goto out; - } - - if (end != vma->vm_end) { - ret = split_vma(vmi, vma, end, 0); - if (ret) - goto out; + vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; } -success: /* * Keep track of amount of locked VM. */ diff --git a/mm/mm_init.c b/mm/mm_init.c index 77fd04c83d..513bad6727 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -561,7 +561,7 @@ out: node_states[N_MEMORY] = saved_node_state; } -static void __meminit __init_single_page(struct page *page, unsigned long pfn, +void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { mm_zero_struct_page(page); @@ -1877,8 +1877,6 @@ void __init free_area_init(unsigned long *max_zone_pfn) pg_data_t *pgdat; if (!node_online(nid)) { - pr_info("Initializing node %d as memoryless\n", nid); - /* Allocator not initialized yet */ pgdat = arch_alloc_nodedata(nid); if (!pgdat) @@ -107,7 +107,7 @@ void vma_set_page_prot(struct vm_area_struct *vma) static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); @@ -384,7 +384,7 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm, static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); @@ -860,13 +860,13 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * **** is not represented - it will be merged and the vma containing the * area is returned, or the function will return NULL */ -struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, - struct vm_area_struct *prev, unsigned long addr, - unsigned long end, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) +static struct vm_area_struct +*vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, + struct vm_area_struct *prev, unsigned long addr, unsigned long end, + unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, + pgoff_t pgoff, struct mempolicy *policy, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) { struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; @@ -943,6 +943,11 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_start_write(curr); remove = curr; remove2 = next; + /* + * Note that the dup_anon_vma below cannot overwrite err + * since the first caller would do nothing unless next + * has an anon_vma. + */ if (!next->anon_vma) err = dup_anon_vma(prev, curr, &anon_dup); } @@ -1218,7 +1223,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec - * mounted, in which case we dont add PROT_EXEC.) + * mounted, in which case we don't add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) @@ -1820,12 +1825,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. - * do_mmap() will clear pgoff, so match alignment. */ - pgoff = 0; get_area = shmem_get_unmapped_area; + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + get_area = thp_get_unmapped_area; } + /* Always treat pgoff as zero for anonymous memory. */ + if (!file) + pgoff = 0; + addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; @@ -1944,9 +1954,9 @@ static int acct_stack_growth(struct vm_area_struct *vma, return 0; } -#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) +#if defined(CONFIG_STACK_GROWSUP) /* - * PA-RISC uses this for its stack; IA64 for its Register Backing Store. + * PA-RISC uses this for its stack. * vma is the last one with address > vma->vm_end. Have to extend vma. */ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) @@ -2043,7 +2053,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) validate_mm(mm); return error; } -#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ +#endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. @@ -2179,8 +2189,6 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return -EINVAL; return expand_downwards(vma, address); } @@ -2343,8 +2351,8 @@ static void unmap_region(struct mm_struct *mm, struct ma_state *mas, * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the end VMA. */ -int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; @@ -2425,8 +2433,8 @@ out_free_vma: * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ -int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; @@ -2435,6 +2443,85 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, } /* + * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd + * context and anonymous VMA name within the range [start, end). + * + * As a result, we might be able to merge the newly modified VMA range with an + * adjacent VMA with identical properties. + * + * If no merge is possible and the range does not span the entirety of the VMA, + * we then need to split the VMA to accommodate the change. + * + * The function returns either the merged VMA, the original VMA if a split was + * required instead, or an error if the split failed. + */ +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name) +{ + pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + struct vm_area_struct *merged; + + merged = vma_merge(vmi, vma->vm_mm, prev, start, end, vm_flags, + vma->anon_vma, vma->vm_file, pgoff, policy, + uffd_ctx, anon_name); + if (merged) + return merged; + + if (vma->vm_start < start) { + int err = split_vma(vmi, vma, start, 1); + + if (err) + return ERR_PTR(err); + } + + if (vma->vm_end > end) { + int err = split_vma(vmi, vma, end, 0); + + if (err) + return ERR_PTR(err); + } + + return vma; +} + +/* + * Attempt to merge a newly mapped VMA with those adjacent to it. The caller + * must ensure that [start, end) does not overlap any existing VMA. + */ +static struct vm_area_struct +*vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff) +{ + return vma_merge(vmi, vma->vm_mm, prev, start, end, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* + * Expand vma by delta bytes, potentially merging with an immediately adjacent + * VMA with identical properties. + */ +struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta) +{ + pgoff_t pgoff = vma->vm_pgoff + vma_pages(vma); + + /* vma is specified as prev, so case 1 or 2 will apply. */ + return vma_merge(vmi, vma->vm_mm, vma, vma->vm_end, vma->vm_end + delta, + vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct @@ -2670,6 +2757,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; + bool writable_file_mapping = false; pgoff_t vm_pgoff; int error; VMA_ITERATOR(vmi, mm, addr); @@ -2764,17 +2852,19 @@ cannot_expand: vma->vm_pgoff = pgoff; if (file) { - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto free_vma; - } - vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; + if (vma_is_shared_maywrite(vma)) { + error = mapping_map_writable(file->f_mapping); + if (error) + goto close_and_free_vma; + + writable_file_mapping = true; + } + /* * Expansion is handled above, merging is handled below. * Drivers should not alter the address of the VMA. @@ -2789,10 +2879,9 @@ cannot_expand: * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { - merge = vma_merge(&vmi, mm, prev, vma->vm_start, - vma->vm_end, vma->vm_flags, NULL, - vma->vm_file, vma->vm_pgoff, NULL, - NULL_VM_UFFD_CTX, NULL); + merge = vma_merge_new_vma(&vmi, prev, vma, + vma->vm_start, vma->vm_end, + vma->vm_pgoff); if (merge) { /* * ->mmap() can change vma->vm_file and fput @@ -2839,7 +2928,7 @@ cannot_expand: mm->map_count++; if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_allow_writable(vma->vm_file->f_mapping); flush_dcache_mmap_lock(vma->vm_file->f_mapping); @@ -2856,7 +2945,7 @@ cannot_expand: /* Once vma denies write, undo our temporary denial count */ unmap_writable: - if (file && vm_flags & VM_SHARED) + if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); file = vma->vm_file; ksm_add_vma(vma); @@ -2904,7 +2993,7 @@ unmap_and_free_vma: unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, vma->vm_end, vma->vm_end, true); } - if (file && (vm_flags & VM_SHARED)) + if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); free_vma: vm_area_free(vma); @@ -3194,12 +3283,6 @@ limits_failed: } EXPORT_SYMBOL(vm_brk_flags); -int vm_brk(unsigned long addr, unsigned long len) -{ - return vm_brk_flags(addr, len, 0); -} -EXPORT_SYMBOL(vm_brk); - /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { @@ -3298,7 +3381,8 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) } if (vma_link(mm, vma)) { - vm_unacct_memory(charged); + if (vma->vm_flags & VM_ACCOUNT) + vm_unacct_memory(charged); return -ENOMEM; } @@ -3333,9 +3417,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - new_vma = vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + new_vma = vma_merge_new_vma(&vmi, prev, vma, addr, addr + len, pgoff); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mmzone.c b/mm/mmzone.c index 68e1511be1..b594d3f268 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -93,19 +93,19 @@ void lruvec_init(struct lruvec *lruvec) } #if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) -int page_cpupid_xchg_last(struct page *page, int cpupid) +int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { unsigned long old_flags, flags; int last_cpupid; - old_flags = READ_ONCE(page->flags); + old_flags = READ_ONCE(folio->flags); do { flags = old_flags; last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT); flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT; - } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } while (unlikely(!try_cmpxchg(&folio->flags, &old_flags, flags))); return last_cpupid; } diff --git a/mm/mprotect.c b/mm/mprotect.c index b94fbb45d5..81991102f7 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -114,7 +114,7 @@ static long change_pte_range(struct mmu_gather *tlb, * pages. See similar comment in change_huge_pmd. */ if (prot_numa) { - struct page *page; + struct folio *folio; int nid; bool toptier; @@ -122,13 +122,14 @@ static long change_pte_range(struct mmu_gather *tlb, if (pte_protnone(oldpte)) continue; - page = vm_normal_page(vma, addr, oldpte); - if (!page || is_zone_device_page(page) || PageKsm(page)) + folio = vm_normal_folio(vma, addr, oldpte); + if (!folio || folio_is_zone_device(folio) || + folio_test_ksm(folio)) continue; /* Also skip shared copy-on-write pages */ if (is_cow_mapping(vma->vm_flags) && - page_count(page) != 1) + folio_ref_count(folio) != 1) continue; /* @@ -136,14 +137,15 @@ static long change_pte_range(struct mmu_gather *tlb, * it cannot move them all from MIGRATE_ASYNC * context. */ - if (page_is_file_lru(page) && PageDirty(page)) + if (folio_is_file_lru(folio) && + folio_test_dirty(folio)) continue; /* * Don't mess with PTEs if page is already on the node * a single-threaded process is running on. */ - nid = page_to_nid(page); + nid = folio_nid(folio); if (target_node == nid) continue; toptier = node_is_toptier(nid); @@ -157,7 +159,7 @@ static long change_pte_range(struct mmu_gather *tlb, continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && !toptier) - xchg_page_access_time(page, + folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } @@ -581,7 +583,6 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, long nrpages = (end - start) >> PAGE_SHIFT; unsigned int mm_cp_flags = 0; unsigned long charged = 0; - pgoff_t pgoff; int error; if (newflags == oldflags) { @@ -608,8 +609,11 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, /* * If we make a private mapping writable we increase our commit; * but (without finer accounting) cannot reduce our commit if we - * make it unwritable again. hugetlb mapping were accounted for - * even if read-only so there is no need to account for them here + * make it unwritable again except in the anonymous case where no + * anon_vma has yet to be assigned. + * + * hugetlb mapping were accounted for even if read-only so there is + * no need to account for them here. */ if (newflags & VM_WRITE) { /* Check space limits when area turns into data. */ @@ -623,36 +627,19 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, return -ENOMEM; newflags |= VM_ACCOUNT; } + } else if ((oldflags & VM_ACCOUNT) && vma_is_anonymous(vma) && + !vma->anon_vma) { + newflags &= ~VM_ACCOUNT; } - /* - * First try to merge with previous and/or next vma. - */ - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *pprev = vma_merge(vmi, mm, *pprev, start, end, newflags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (*pprev) { - vma = *pprev; - VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); - goto success; + vma = vma_modify_flags(vmi, *pprev, vma, start, end, newflags); + if (IS_ERR(vma)) { + error = PTR_ERR(vma); + goto fail; } *pprev = vma; - if (start != vma->vm_start) { - error = split_vma(vmi, vma, start, 1); - if (error) - goto fail; - } - - if (end != vma->vm_end) { - error = split_vma(vmi, vma, end, 0); - if (error) - goto fail; - } - -success: /* * vm_flags and vm_page_prot are protected by the mmap_lock * held in write mode. @@ -665,6 +652,9 @@ success: change_protection(tlb, vma, start, end, mm_cp_flags); + if ((oldflags & VM_ACCOUNT) && !(newflags & VM_ACCOUNT)) + vm_unacct_memory(nrpages); + /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major * fault on access. diff --git a/mm/mremap.c b/mm/mremap.c index 382e81c33f..38d98465f3 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -489,10 +489,62 @@ static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma, return moved; } +/* + * A helper to check if aligning down is OK. The aligned address should fall + * on *no mapping*. For the stack moving down, that's a special move within + * the VMA that is created to span the source and destination of the move, + * so we make an exception for it. + */ +static bool can_align_down(struct vm_area_struct *vma, unsigned long addr_to_align, + unsigned long mask, bool for_stack) +{ + unsigned long addr_masked = addr_to_align & mask; + + /* + * If @addr_to_align of either source or destination is not the beginning + * of the corresponding VMA, we can't align down or we will destroy part + * of the current mapping. + */ + if (!for_stack && vma->vm_start != addr_to_align) + return false; + + /* In the stack case we explicitly permit in-VMA alignment. */ + if (for_stack && addr_masked >= vma->vm_start) + return true; + + /* + * Make sure the realignment doesn't cause the address to fall on an + * existing mapping. + */ + return find_vma_intersection(vma->vm_mm, addr_masked, vma->vm_start) == NULL; +} + +/* Opportunistically realign to specified boundary for faster copy. */ +static void try_realign_addr(unsigned long *old_addr, struct vm_area_struct *old_vma, + unsigned long *new_addr, struct vm_area_struct *new_vma, + unsigned long mask, bool for_stack) +{ + /* Skip if the addresses are already aligned. */ + if ((*old_addr & ~mask) == 0) + return; + + /* Only realign if the new and old addresses are mutually aligned. */ + if ((*old_addr & ~mask) != (*new_addr & ~mask)) + return; + + /* Ensure realignment doesn't cause overlap with existing mappings. */ + if (!can_align_down(old_vma, *old_addr, mask, for_stack) || + !can_align_down(new_vma, *new_addr, mask, for_stack)) + return; + + *old_addr = *old_addr & mask; + *new_addr = *new_addr & mask; +} + unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, - bool need_rmap_locks) + bool need_rmap_locks, bool for_stack) { unsigned long extent, old_end; struct mmu_notifier_range range; @@ -508,6 +560,14 @@ unsigned long move_page_tables(struct vm_area_struct *vma, return move_hugetlb_page_tables(vma, new_vma, old_addr, new_addr, len); + /* + * If possible, realign addresses to PMD boundary for faster copy. + * Only realign if the mremap copying hits a PMD boundary. + */ + if (len >= PMD_SIZE - (old_addr & ~PMD_MASK)) + try_realign_addr(&old_addr, vma, &new_addr, new_vma, PMD_MASK, + for_stack); + flush_cache_range(vma, old_addr, old_end); mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, old_addr, old_end); @@ -577,6 +637,13 @@ again: mmu_notifier_invalidate_range_end(&range); + /* + * Prevent negative return values when {old,new}_addr was realigned + * but we broke out of the above loop for the first PMD itself. + */ + if (len + old_addr < old_end) + return 0; + return len + old_addr - old_end; /* how much done */ } @@ -646,7 +713,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, } moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len, - need_rmap_locks); + need_rmap_locks, false); if (moved_len < old_len) { err = -ENOMEM; } else if (vma->vm_ops && vma->vm_ops->mremap) { @@ -660,7 +727,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, * and then proceed to unmap new area instead of old. */ move_page_tables(new_vma, new_addr, vma, old_addr, moved_len, - true); + true, false); vma = new_vma; old_len = new_len; old_addr = new_addr; @@ -1029,36 +1096,34 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* old_len exactly to the end of the area.. */ if (old_len == vma->vm_end - addr) { + unsigned long delta = new_len - old_len; + /* can we just expand the current mapping? */ - if (vma_expandable(vma, new_len - old_len)) { - long pages = (new_len - old_len) >> PAGE_SHIFT; - unsigned long extension_start = addr + old_len; - unsigned long extension_end = addr + new_len; - pgoff_t extension_pgoff = vma->vm_pgoff + - ((extension_start - vma->vm_start) >> PAGE_SHIFT); - VMA_ITERATOR(vmi, mm, extension_start); + if (vma_expandable(vma, delta)) { + long pages = delta >> PAGE_SHIFT; + VMA_ITERATOR(vmi, mm, vma->vm_end); + long charged = 0; if (vma->vm_flags & VM_ACCOUNT) { if (security_vm_enough_memory_mm(mm, pages)) { ret = -ENOMEM; goto out; } + charged = pages; } /* - * Function vma_merge() is called on the extension we - * are adding to the already existing vma, vma_merge() - * will merge this extension with the already existing - * vma (expand operation itself) and possibly also with - * the next vma if it becomes adjacent to the expanded - * vma and otherwise compatible. + * Function vma_merge_extend() is called on the + * extension we are adding to the already existing vma, + * vma_merge_extend() will merge this extension with the + * already existing vma (expand operation itself) and + * possibly also with the next vma if it becomes + * adjacent to the expanded vma and otherwise + * compatible. */ - vma = vma_merge(&vmi, mm, vma, extension_start, - extension_end, vma->vm_flags, vma->anon_vma, - vma->vm_file, extension_pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + vma = vma_merge_extend(&vmi, vma, delta); if (!vma) { - vm_unacct_memory(pages); + vm_unacct_memory(charged); ret = -ENOMEM; goto out; } diff --git a/mm/nommu.c b/mm/nommu.c index 7f9e9e5a0e..b6dc558d31 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1305,8 +1305,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) * split a vma into two pieces at address 'addr', a new vma is allocated either * for the first part or the tail. */ -int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vm_area_struct *new; struct vm_region *region; @@ -1531,11 +1531,6 @@ void exit_mmap(struct mm_struct *mm) mmap_write_unlock(mm); } -int vm_brk(unsigned long addr, unsigned long len) -{ - return -ENOMEM; -} - /* * expand (or shrink) an existing mapping, potentially moving it at the same * time (controlled by the MREMAP_MAYMOVE flag and available VM space) @@ -1651,8 +1646,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, } EXPORT_SYMBOL(filemap_map_pages); -int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, - int len, unsigned int gup_flags) +static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; int write = gup_flags & FOLL_WRITE; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 44bde56ecd..9e6071fde3 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -437,7 +437,7 @@ static void dump_tasks(struct oom_control *oc) } } -static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) +static void dump_oom_victim(struct oom_control *oc, struct task_struct *victim) { /* one line summary of the oom killer context. */ pr_info("oom-kill:constraint=%s,nodemask=%*pbl", @@ -449,7 +449,7 @@ static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) from_kuid(&init_user_ns, task_uid(victim))); } -static void dump_header(struct oom_control *oc, struct task_struct *p) +static void dump_header(struct oom_control *oc) { pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, @@ -467,8 +467,6 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) } if (sysctl_oom_dump_tasks) dump_tasks(oc); - if (p) - dump_oom_summary(oc, p); } /* @@ -1029,8 +1027,10 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } task_unlock(victim); - if (__ratelimit(&oom_rs)) - dump_header(oc, victim); + if (__ratelimit(&oom_rs)) { + dump_header(oc); + dump_oom_victim(oc, victim); + } /* * Do we need to kill the entire memory cgroup? @@ -1072,7 +1072,7 @@ static void check_panic_on_oom(struct oom_control *oc) /* Do not panic for oom kills triggered by sysrq */ if (is_sysrq_oom(oc)) return; - dump_header(oc, NULL); + dump_header(oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -1155,7 +1155,7 @@ bool out_of_memory(struct oom_control *oc) select_bad_process(oc); /* Found nothing?!?! */ if (!oc->chosen) { - dump_header(oc, NULL); + dump_header(oc); pr_warn("Out of memory and no killable processes...\n"); /* * If we got here due to an actual allocation at the diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4656534b8f..f735d28de3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,7 +692,6 @@ static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ra if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; - min_ratio *= BDI_RATIO_SCALE; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { @@ -729,7 +728,8 @@ static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ra ret = -EINVAL; } else { bdi->max_ratio = max_ratio; - bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; + bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / + (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); @@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -1921,7 +1921,7 @@ pause: break; } __set_current_state(TASK_KILLABLE); - wb->dirty_sleep = now; + bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; @@ -2679,7 +2679,7 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function - * from their set_page_dirty address space operation. It ignores the + * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * @@ -2953,19 +2953,16 @@ bool __folio_end_writeback(struct folio *folio) unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - ret = folio_test_clear_writeback(folio); - if (ret) { - __xa_clear_mark(&mapping->i_pages, folio_index(folio), - PAGECACHE_TAG_WRITEBACK); - if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { - struct bdi_writeback *wb = inode_to_wb(inode); - - wb_stat_mod(wb, WB_WRITEBACK, -nr); - __wb_writeout_add(wb, nr); - if (!mapping_tagged(mapping, - PAGECACHE_TAG_WRITEBACK)) - wb_inode_writeback_end(wb); - } + ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); + __xa_clear_mark(&mapping->i_pages, folio_index(folio), + PAGECACHE_TAG_WRITEBACK); + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { + struct bdi_writeback *wb = inode_to_wb(inode); + + wb_stat_mod(wb, WB_WRITEBACK, -nr); + __wb_writeout_add(wb, nr); + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, @@ -2974,14 +2971,14 @@ bool __folio_end_writeback(struct folio *folio) xa_unlock_irqrestore(&mapping->i_pages, flags); } else { - ret = folio_test_clear_writeback(folio); - } - if (ret) { - lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); - zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); - node_stat_mod_folio(folio, NR_WRITTEN, nr); + ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } + + lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + node_stat_mod_folio(folio, NR_WRITTEN, nr); folio_memcg_unlock(folio); + return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index afed33fd87..6d2a74138f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -52,6 +52,7 @@ #include <linux/psi.h> #include <linux/khugepaged.h> #include <linux/delayacct.h> +#include <linux/cacheinfo.h> #include <asm/div64.h> #include "internal.h" #include "shuffle.h" @@ -1078,6 +1079,7 @@ static __always_inline bool free_pages_prepare(struct page *page, int bad = 0; bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags); bool init = want_init_on_free(); + bool compound = PageCompound(page); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1096,16 +1098,15 @@ static __always_inline bool free_pages_prepare(struct page *page, return false; } + VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); + /* * Check tail pages before head page information is cleared to * avoid checking PageCompound for order-0 pages. */ if (unlikely(order)) { - bool compound = PageCompound(page); int i; - VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); - if (compound) page[1].flags &= ~PAGE_FLAGS_SECOND; for (i = 1; i < (1 << order); i++) { @@ -2156,6 +2157,40 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, return i; } +/* + * Called from the vmstat counter updater to decay the PCP high. + * Return whether there are addition works to do. + */ +int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) +{ + int high_min, to_drain, batch; + int todo = 0; + + high_min = READ_ONCE(pcp->high_min); + batch = READ_ONCE(pcp->batch); + /* + * Decrease pcp->high periodically to try to free possible + * idle PCP pages. And, avoid to free too many pages to + * control latency. This caps pcp->high decrement too. + */ + if (pcp->high > high_min) { + pcp->high = max3(pcp->count - (batch << CONFIG_PCP_BATCH_SCALE_MAX), + pcp->high - (pcp->high >> 3), high_min); + if (pcp->high > high_min) + todo++; + } + + to_drain = pcp->count - pcp->high; + if (to_drain > 0) { + spin_lock(&pcp->lock); + free_pcppages_bulk(zone, to_drain, pcp, 0); + spin_unlock(&pcp->lock); + todo++; + } + + return todo; +} + #ifdef CONFIG_NUMA /* * Called from the vmstat counter updater to drain pagesets of this @@ -2317,14 +2352,13 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn, return true; } -static int nr_pcp_free(struct per_cpu_pages *pcp, int high, bool free_high) +static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high) { int min_nr_free, max_nr_free; - int batch = READ_ONCE(pcp->batch); - /* Free everything if batch freeing high-order pages. */ + /* Free as much as possible if batch freeing high-order pages. */ if (unlikely(free_high)) - return pcp->count; + return min(pcp->count, batch << CONFIG_PCP_BATCH_SCALE_MAX); /* Check for PCP disabled or boot pageset */ if (unlikely(high < batch)) @@ -2335,59 +2369,107 @@ static int nr_pcp_free(struct per_cpu_pages *pcp, int high, bool free_high) max_nr_free = high - batch; /* - * Double the number of pages freed each time there is subsequent - * freeing of pages without any allocation. + * Increase the batch number to the number of the consecutive + * freed pages to reduce zone lock contention. */ - batch <<= pcp->free_factor; - if (batch < max_nr_free) - pcp->free_factor++; - batch = clamp(batch, min_nr_free, max_nr_free); + batch = clamp_t(int, pcp->free_count, min_nr_free, max_nr_free); return batch; } static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, - bool free_high) + int batch, bool free_high) { - int high = READ_ONCE(pcp->high); + int high, high_min, high_max; + + high_min = READ_ONCE(pcp->high_min); + high_max = READ_ONCE(pcp->high_max); + high = pcp->high = clamp(pcp->high, high_min, high_max); - if (unlikely(!high || free_high)) + if (unlikely(!high)) return 0; - if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) - return high; + if (unlikely(free_high)) { + pcp->high = max(high - (batch << CONFIG_PCP_BATCH_SCALE_MAX), + high_min); + return 0; + } /* * If reclaim is active, limit the number of pages that can be * stored on pcp lists */ - return min(READ_ONCE(pcp->batch) << 2, high); + if (test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) { + int free_count = max_t(int, pcp->free_count, batch); + + pcp->high = max(high - free_count, high_min); + return min(batch << 2, pcp->high); + } + + if (high_min == high_max) + return high; + + if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) { + int free_count = max_t(int, pcp->free_count, batch); + + pcp->high = max(high - free_count, high_min); + high = max(pcp->count, high_min); + } else if (pcp->count >= high) { + int need_high = pcp->free_count + batch; + + /* pcp->high should be large enough to hold batch freed pages */ + if (pcp->high < need_high) + pcp->high = clamp(need_high, high_min, high_max); + } + + return high; } static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, struct page *page, int migratetype, unsigned int order) { - int high; + int high, batch; int pindex; - bool free_high; + bool free_high = false; + /* + * On freeing, reduce the number of pages that are batch allocated. + * See nr_pcp_alloc() where alloc_factor is increased for subsequent + * allocations. + */ + pcp->alloc_factor >>= 1; __count_vm_events(PGFREE, 1 << order); pindex = order_to_pindex(migratetype, order); list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; + batch = READ_ONCE(pcp->batch); /* * As high-order pages other than THP's stored on PCP can contribute * to fragmentation, limit the number stored when PCP is heavily * freeing without allocation. The remainder after bulk freeing * stops will be drained from vmstat refresh context. */ - free_high = (pcp->free_factor && order && order <= PAGE_ALLOC_COSTLY_ORDER); - - high = nr_pcp_high(pcp, zone, free_high); + if (order && order <= PAGE_ALLOC_COSTLY_ORDER) { + free_high = (pcp->free_count >= batch && + (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) && + (!(pcp->flags & PCPF_FREE_HIGH_BATCH) || + pcp->count >= READ_ONCE(batch))); + pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER; + } else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) { + pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER; + } + if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX)) + pcp->free_count += (1 << order); + high = nr_pcp_high(pcp, zone, batch, free_high); if (pcp->count >= high) { - free_pcppages_bulk(zone, nr_pcp_free(pcp, high, free_high), pcp, pindex); + free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high), + pcp, pindex); + if (test_bit(ZONE_BELOW_HIGH, &zone->flags) && + zone_watermark_ok(zone, 0, high_wmark_pages(zone), + ZONE_MOVABLE, 0)) + clear_bit(ZONE_BELOW_HIGH, &zone->flags); } } @@ -2671,6 +2753,56 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, return page; } +static int nr_pcp_alloc(struct per_cpu_pages *pcp, struct zone *zone, int order) +{ + int high, base_batch, batch, max_nr_alloc; + int high_max, high_min; + + base_batch = READ_ONCE(pcp->batch); + high_min = READ_ONCE(pcp->high_min); + high_max = READ_ONCE(pcp->high_max); + high = pcp->high = clamp(pcp->high, high_min, high_max); + + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < base_batch)) + return 1; + + if (order) + batch = base_batch; + else + batch = (base_batch << pcp->alloc_factor); + + /* + * If we had larger pcp->high, we could avoid to allocate from + * zone. + */ + if (high_min != high_max && !test_bit(ZONE_BELOW_HIGH, &zone->flags)) + high = pcp->high = min(high + batch, high_max); + + if (!order) { + max_nr_alloc = max(high - pcp->count - base_batch, base_batch); + /* + * Double the number of pages allocated each time there is + * subsequent allocation of order-0 pages without any freeing. + */ + if (batch <= max_nr_alloc && + pcp->alloc_factor < CONFIG_PCP_BATCH_SCALE_MAX) + pcp->alloc_factor++; + batch = min(batch, max_nr_alloc); + } + + /* + * Scale batch relative to order if batch implies free pages + * can be stored on the PCP. Batch can be 1 for small zones or + * for boot pagesets which should never store free pages as + * the pages may belong to arbitrary zones. + */ + if (batch > 1) + batch = max(batch >> order, 2); + + return batch; +} + /* Remove page from the per-cpu list, caller must protect the list */ static inline struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, @@ -2683,18 +2815,9 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, do { if (list_empty(list)) { - int batch = READ_ONCE(pcp->batch); + int batch = nr_pcp_alloc(pcp, zone, order); int alloced; - /* - * Scale batch relative to order if batch implies - * free pages can be stored on the PCP. Batch can - * be 1 for small zones or for boot pagesets which - * should never store free pages as the pages may - * belong to arbitrary zones. - */ - if (batch > 1) - batch = max(batch >> order, 2); alloced = rmqueue_bulk(zone, order, batch, list, migratetype, alloc_flags); @@ -2735,7 +2858,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, * See nr_pcp_free() where free_factor is increased for subsequent * frees. */ - pcp->free_factor >>= 1; + pcp->free_count >>= 1; list = &pcp->lists[order_to_pindex(migratetype, order)]; page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); pcp_spin_unlock(pcp); @@ -3115,6 +3238,25 @@ retry: } } + /* + * Detect whether the number of free pages is below high + * watermark. If so, we will decrease pcp->high and free + * PCP pages in free path to reduce the possibility of + * premature page reclaiming. Detection is done here to + * avoid to do that in hotter free path. + */ + if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) + goto check_alloc_wmark; + + mark = high_wmark_pages(zone); + if (zone_watermark_fast(zone, order, mark, + ac->highest_zoneidx, alloc_flags, + gfp_mask)) + goto try_this_zone; + else + set_bit(ZONE_BELOW_HIGH, &zone->flags); + +check_alloc_wmark: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (!zone_watermark_fast(zone, order, mark, ac->highest_zoneidx, alloc_flags, @@ -4456,12 +4598,8 @@ struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask) { struct page *page = __alloc_pages(gfp | __GFP_COMP, order, - preferred_nid, nodemask); - struct folio *folio = (struct folio *)page; - - if (folio && order > 1) - folio_prep_large_rmappable(folio); - return folio; + preferred_nid, nodemask); + return page_rmappable_folio(page); } EXPORT_SYMBOL(__folio_alloc); @@ -4878,8 +5016,11 @@ int find_next_best_node(int node, nodemask_t *used_node_mask) int min_val = INT_MAX; int best_node = NUMA_NO_NODE; - /* Use the local node if we haven't already */ - if (!node_isset(node, *used_node_mask)) { + /* + * Use the local node if we haven't already, but for memoryless local + * node, we should skip it and fall back to other nodes. + */ + if (!node_isset(node, *used_node_mask) && node_state(node, N_MEMORY)) { node_set(node, *used_node_mask); return node; } @@ -5255,14 +5396,15 @@ static int zone_batchsize(struct zone *zone) } static int percpu_pagelist_high_fraction; -static int zone_highsize(struct zone *zone, int batch, int cpu_online) +static int zone_highsize(struct zone *zone, int batch, int cpu_online, + int high_fraction) { #ifdef CONFIG_MMU int high; int nr_split_cpus; unsigned long total_pages; - if (!percpu_pagelist_high_fraction) { + if (!high_fraction) { /* * By default, the high value of the pcp is based on the zone * low watermark so that if they are full then background @@ -5275,15 +5417,15 @@ static int zone_highsize(struct zone *zone, int batch, int cpu_online) * value is based on a fraction of the managed pages in the * zone. */ - total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; + total_pages = zone_managed_pages(zone) / high_fraction; } /* * Split the high value across all online CPUs local to the zone. Note * that early in boot that CPUs may not be online yet and that during * CPU hotplug that the cpumask is not yet updated when a CPU is being - * onlined. For memory nodes that have no CPUs, split pcp->high across - * all online CPUs to mitigate the risk that reclaim is triggered + * onlined. For memory nodes that have no CPUs, split the high value + * across all online CPUs to mitigate the risk that reclaim is triggered * prematurely due to pages stored on pcp lists. */ nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; @@ -5311,19 +5453,21 @@ static int zone_highsize(struct zone *zone, int batch, int cpu_online) * However, guaranteeing these relations at all times would require e.g. write * barriers here but also careful usage of read barriers at the read side, and * thus be prone to error and bad for performance. Thus the update only prevents - * store tearing. Any new users of pcp->batch and pcp->high should ensure they - * can cope with those fields changing asynchronously, and fully trust only the - * pcp->count field on the local CPU with interrupts disabled. + * store tearing. Any new users of pcp->batch, pcp->high_min and pcp->high_max + * should ensure they can cope with those fields changing asynchronously, and + * fully trust only the pcp->count field on the local CPU with interrupts + * disabled. * * mutex_is_locked(&pcp_batch_high_lock) required when calling this function * outside of boot time (or some other assurance that no concurrent updaters * exist). */ -static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, - unsigned long batch) +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high_min, + unsigned long high_max, unsigned long batch) { WRITE_ONCE(pcp->batch, batch); - WRITE_ONCE(pcp->high, high); + WRITE_ONCE(pcp->high_min, high_min); + WRITE_ONCE(pcp->high_max, high_max); } static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) @@ -5343,20 +5487,21 @@ static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonesta * need to be as careful as pageset_update() as nobody can access the * pageset yet. */ - pcp->high = BOOT_PAGESET_HIGH; + pcp->high_min = BOOT_PAGESET_HIGH; + pcp->high_max = BOOT_PAGESET_HIGH; pcp->batch = BOOT_PAGESET_BATCH; - pcp->free_factor = 0; + pcp->free_count = 0; } -static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, - unsigned long batch) +static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high_min, + unsigned long high_max, unsigned long batch) { struct per_cpu_pages *pcp; int cpu; for_each_possible_cpu(cpu) { pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - pageset_update(pcp, high, batch); + pageset_update(pcp, high_min, high_max, batch); } } @@ -5366,19 +5511,34 @@ static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long h */ static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) { - int new_high, new_batch; + int new_high_min, new_high_max, new_batch; new_batch = max(1, zone_batchsize(zone)); - new_high = zone_highsize(zone, new_batch, cpu_online); + if (percpu_pagelist_high_fraction) { + new_high_min = zone_highsize(zone, new_batch, cpu_online, + percpu_pagelist_high_fraction); + /* + * PCP high is tuned manually, disable auto-tuning via + * setting high_min and high_max to the manual value. + */ + new_high_max = new_high_min; + } else { + new_high_min = zone_highsize(zone, new_batch, cpu_online, 0); + new_high_max = zone_highsize(zone, new_batch, cpu_online, + MIN_PERCPU_PAGELIST_HIGH_FRACTION); + } - if (zone->pageset_high == new_high && + if (zone->pageset_high_min == new_high_min && + zone->pageset_high_max == new_high_max && zone->pageset_batch == new_batch) return; - zone->pageset_high = new_high; + zone->pageset_high_min = new_high_min; + zone->pageset_high_max = new_high_max; zone->pageset_batch = new_batch; - __zone_set_pageset_high_and_batch(zone, new_high, new_batch); + __zone_set_pageset_high_and_batch(zone, new_high_min, new_high_max, + new_batch); } void __meminit setup_zone_pageset(struct zone *zone) @@ -5413,6 +5573,39 @@ static void zone_pcp_update(struct zone *zone, int cpu_online) mutex_unlock(&pcp_batch_high_lock); } +static void zone_pcp_update_cacheinfo(struct zone *zone) +{ + int cpu; + struct per_cpu_pages *pcp; + struct cpu_cacheinfo *cci; + + for_each_online_cpu(cpu) { + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + cci = get_cpu_cacheinfo(cpu); + /* + * If data cache slice of CPU is large enough, "pcp->batch" + * pages can be preserved in PCP before draining PCP for + * consecutive high-order pages freeing without allocation. + * This can reduce zone lock contention without hurting + * cache-hot pages sharing. + */ + spin_lock(&pcp->lock); + if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) + pcp->flags |= PCPF_FREE_HIGH_BATCH; + else + pcp->flags &= ~PCPF_FREE_HIGH_BATCH; + spin_unlock(&pcp->lock); + } +} + +void setup_pcp_cacheinfo(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zone_pcp_update_cacheinfo(zone); +} + /* * Allocate per cpu pagesets and initialize them. * Before this call only boot pagesets were available. @@ -5454,7 +5647,8 @@ __meminit void zone_pcp_init(struct zone *zone) */ zone->per_cpu_pageset = &boot_pageset; zone->per_cpu_zonestats = &boot_zonestats; - zone->pageset_high = BOOT_PAGESET_HIGH; + zone->pageset_high_min = BOOT_PAGESET_HIGH; + zone->pageset_high_max = BOOT_PAGESET_HIGH; zone->pageset_batch = BOOT_PAGESET_BATCH; if (populated_zone(zone)) @@ -6356,13 +6550,14 @@ EXPORT_SYMBOL(free_contig_range); void zone_pcp_disable(struct zone *zone) { mutex_lock(&pcp_batch_high_lock); - __zone_set_pageset_high_and_batch(zone, 0, 1); + __zone_set_pageset_high_and_batch(zone, 0, 0, 1); __drain_all_pages(zone, true); } void zone_pcp_enable(struct zone *zone) { - __zone_set_pageset_high_and_batch(zone, zone->pageset_high, zone->pageset_batch); + __zone_set_pageset_high_and_batch(zone, zone->pageset_high_min, + zone->pageset_high_max, zone->pageset_batch); mutex_unlock(&pcp_batch_high_lock); } @@ -6462,28 +6657,24 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page, int migratetype) { unsigned long size = 1 << high; - struct page *current_buddy, *next_page; + struct page *current_buddy; while (high > low) { high--; size >>= 1; if (target >= &page[size]) { - next_page = page + size; current_buddy = page; + page = page + size; } else { - next_page = page; current_buddy = page + size; } - page = next_page; if (set_page_guard(zone, current_buddy, high, migratetype)) continue; - if (current_buddy != target) { - add_to_free_list(current_buddy, zone, high, migratetype); - set_buddy_order(current_buddy, high); - } + add_to_free_list(current_buddy, zone, high, migratetype); + set_buddy_order(current_buddy, high); } } diff --git a/mm/page_io.c b/mm/page_io.c index fe4c21af23..cb559ae324 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -208,8 +208,10 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) static inline void count_swpout_vm_event(struct folio *folio) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (unlikely(folio_test_pmd_mappable(folio))) + if (unlikely(folio_test_pmd_mappable(folio))) { + count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); + } #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } @@ -278,9 +280,6 @@ static void sio_write_complete(struct kiocb *iocb, long ret) set_page_dirty(page); ClearPageReclaim(page); } - } else { - for (p = 0; p < sio->pages; p++) - count_swpout_vm_event(page_folio(sio->bvec[p].bv_page)); } for (p = 0; p < sio->pages; p++) @@ -296,6 +295,7 @@ static void swap_writepage_fs(struct page *page, struct writeback_control *wbc) struct file *swap_file = sis->swap_file; loff_t pos = page_file_offset(page); + count_swpout_vm_event(page_folio(page)); set_page_writeback(page); unlock_page(page); if (wbc->swap_plug) diff --git a/mm/page_owner.c b/mm/page_owner.c index 4e2723e1b3..4f13ce7d24 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -408,11 +408,11 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, return -ENOMEM; ret = scnprintf(kbuf, count, - "Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns, free_ts %llu ns\n", + "Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns\n", page_owner->order, page_owner->gfp_mask, &page_owner->gfp_mask, page_owner->pid, page_owner->tgid, page_owner->comm, - page_owner->ts_nsec, page_owner->free_ts_nsec); + page_owner->ts_nsec); /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); diff --git a/mm/percpu.c b/mm/percpu.c index a7665de848..4e11fc1e6d 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1628,14 +1628,12 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; - objcg = get_obj_cgroup_from_current(); + objcg = current_obj_cgroup(); if (!objcg) return true; - if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) { - obj_cgroup_put(objcg); + if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; - } *objcgp = objcg; return true; @@ -1649,6 +1647,7 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, return; if (likely(chunk && chunk->obj_cgroups)) { + obj_cgroup_get(objcg); chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); @@ -1657,7 +1656,6 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); - obj_cgroup_put(objcg); } } @@ -2245,6 +2243,37 @@ static void pcpu_balance_workfn(struct work_struct *work) } /** + * pcpu_alloc_size - the size of the dynamic percpu area + * @ptr: pointer to the dynamic percpu area + * + * Returns the size of the @ptr allocation. This is undefined for statically + * defined percpu variables as there is no corresponding chunk->bound_map. + * + * RETURNS: + * The size of the dynamic percpu area. + * + * CONTEXT: + * Can be called from atomic context. + */ +size_t pcpu_alloc_size(void __percpu *ptr) +{ + struct pcpu_chunk *chunk; + unsigned long bit_off, end; + void *addr; + + if (!ptr) + return 0; + + addr = __pcpu_ptr_to_addr(ptr); + /* No pcpu_lock here: ptr has not been freed, so chunk is still alive */ + chunk = pcpu_chunk_addr_search(addr); + bit_off = (addr - chunk->base_addr) / PCPU_MIN_ALLOC_SIZE; + end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), + bit_off + 1); + return (end - bit_off) * PCPU_MIN_ALLOC_SIZE; +} + +/** * free_percpu - free percpu area * @ptr: pointer to area to free * @@ -2267,12 +2296,10 @@ void free_percpu(void __percpu *ptr) kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); - - spin_lock_irqsave(&pcpu_lock, flags); - chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; + spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_memcg_free_hook(chunk, off, size); @@ -3306,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); - /* - * FIXME: Archs with virtual cache should flush local - * cache for the linear mapping here - something - * equivalent to flush_cache_vmap() on the local cpu. - * flush_cache_vmap() can't be used as most supporting - * data structures are not set up yet. - */ + flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); @@ -798,6 +798,7 @@ struct folio_referenced_arg { unsigned long vm_flags; struct mem_cgroup *memcg; }; + /* * arg: folio_referenced_arg will be passed */ @@ -807,17 +808,33 @@ static bool folio_referenced_one(struct folio *folio, struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; + unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; - if ((vma->vm_flags & VM_LOCKED) && - (!folio_test_large(folio) || !pvmw.pte)) { - /* Restore the mlock which got missed */ - mlock_vma_folio(folio, vma, !pvmw.pte); - page_vma_mapped_walk_done(&pvmw); - pra->vm_flags |= VM_LOCKED; - return false; /* To break the loop */ + if (vma->vm_flags & VM_LOCKED) { + if (!folio_test_large(folio) || !pvmw.pte) { + /* Restore the mlock which got missed */ + mlock_vma_folio(folio, vma); + page_vma_mapped_walk_done(&pvmw); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } + /* + * For large folio fully mapped to VMA, will + * be handled after the pvmw loop. + * + * For large folio cross VMA boundaries, it's + * expected to be picked by page reclaim. But + * should skip reference of pages which are in + * the range of VM_LOCKED vma. As page reclaim + * should just count the reference of pages out + * the range of VM_LOCKED vma. + */ + ptes++; + pra->mapcount--; + continue; } if (pvmw.pte) { @@ -842,6 +859,23 @@ static bool folio_referenced_one(struct folio *folio, pra->mapcount--; } + if ((vma->vm_flags & VM_LOCKED) && + folio_test_large(folio) && + folio_within_vma(folio, vma)) { + unsigned long s_align, e_align; + + s_align = ALIGN_DOWN(start, PMD_SIZE); + e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); + + /* folio doesn't cross page table boundary and fully mapped */ + if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { + /* Restore the mlock which got missed */ + mlock_vma_folio(folio, vma); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } + } + if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) @@ -1094,19 +1128,17 @@ int folio_total_mapcount(struct folio *folio) } /** - * page_move_anon_rmap - move a page to our anon_vma - * @page: the page to move to our anon_vma - * @vma: the vma the page belongs to + * folio_move_anon_rmap - move a folio to our anon_vma + * @folio: The folio to move to our anon_vma + * @vma: The vma the folio belongs to * - * When a page belongs exclusively to one process after a COW event, - * that page can be moved into the anon_vma that belongs to just that - * process, so the rmap code will not search the parent or sibling - * processes. + * When a folio belongs exclusively to one process after a COW event, + * that folio can be moved into the anon_vma that belongs to just that + * process, so the rmap code will not search the parent or sibling processes. */ -void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) +void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; - struct folio *folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); @@ -1118,31 +1150,25 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); - SetPageAnonExclusive(page); } /** - * __page_set_anon_rmap - set up new anonymous rmap - * @folio: Folio which contains page. - * @page: Page to add to rmap. - * @vma: VM area to add page to. + * __folio_set_anon - set up a new anonymous rmap for a folio + * @folio: The folio to set up the new anonymous rmap for. + * @vma: VM area to add the folio to. * @address: User virtual address of the mapping - * @exclusive: the page is exclusively owned by the current process + * @exclusive: Whether the folio is exclusive to the process. */ -static void __page_set_anon_rmap(struct folio *folio, struct page *page, - struct vm_area_struct *vma, unsigned long address, int exclusive) +static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, + unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); - if (folio_test_anon(folio)) - goto out; - /* - * If the page isn't exclusively mapped into this vma, - * we must use the _oldest_ possible anon_vma for the - * page mapping! + * If the folio isn't exclusive to this vma, we must use the _oldest_ + * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; @@ -1156,9 +1182,6 @@ static void __page_set_anon_rmap(struct folio *folio, struct page *page, anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); -out: - if (exclusive) - SetPageAnonExclusive(page); } /** @@ -1207,7 +1230,7 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, atomic_t *mapped = &folio->_nr_pages_mapped; int nr = 0, nr_pmdmapped = 0; bool compound = flags & RMAP_COMPOUND; - bool first = true; + bool first; /* Is page being mapped by PTE? Is this its first map to be added? */ if (likely(!compound)) { @@ -1236,24 +1259,40 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, } } - VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped); if (nr) __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); - if (likely(!folio_test_ksm(folio))) { - /* address might be in next vma when migration races vma_merge */ - if (first) - __page_set_anon_rmap(folio, page, vma, address, - !!(flags & RMAP_EXCLUSIVE)); - else - __page_check_anon_rmap(folio, page, vma, address); + if (unlikely(!folio_test_anon(folio))) { + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + /* + * For a PTE-mapped large folio, we only know that the single + * PTE is exclusive. Further, __folio_set_anon() might not get + * folio->index right when not given the address of the head + * page. + */ + VM_WARN_ON_FOLIO(folio_test_large(folio) && !compound, folio); + __folio_set_anon(folio, vma, address, + !!(flags & RMAP_EXCLUSIVE)); + } else if (likely(!folio_test_ksm(folio))) { + __page_check_anon_rmap(folio, page, vma, address); } + if (flags & RMAP_EXCLUSIVE) + SetPageAnonExclusive(page); + /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ + VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 || + (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && + PageAnonExclusive(page), folio); - mlock_vma_folio(folio, vma, compound); + /* + * For large folio, only mlock it if it's fully mapped to VMA. It's + * not easy to check whether the large folio is fully mapped to VMA + * here. Only mlock normal 4K folio and leave page reclaim to handle + * large folio. + */ + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); } /** @@ -1290,7 +1329,8 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, } __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); - __page_set_anon_rmap(folio, &folio->page, vma, address, 1); + __folio_set_anon(folio, vma, address, true); + SetPageAnonExclusive(&folio->page); } /** @@ -1352,7 +1392,9 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page, if (nr) __lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr); - mlock_vma_folio(folio, vma, compound); + /* See comments in page_add_anon_rmap() */ + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); } /** @@ -1463,7 +1505,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, * it's only reliable while mapped. */ - munlock_vma_folio(folio, vma, compound); + munlock_vma_folio(folio, vma); } /* @@ -1528,7 +1570,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ - mlock_vma_folio(folio, vma, false); + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); ret = false; break; @@ -2540,22 +2583,16 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) * * RMAP_COMPOUND is ignored. */ -void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, +void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { - struct folio *folio = page_folio(page); - struct anon_vma *anon_vma = vma->anon_vma; - int first; + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); - BUG_ON(!folio_test_locked(folio)); - BUG_ON(!anon_vma); - /* address might be in next vma when migration races vma_merge */ - first = atomic_inc_and_test(&folio->_entire_mapcount); - VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (first) - __page_set_anon_rmap(folio, page, vma, address, - !!(flags & RMAP_EXCLUSIVE)); + atomic_inc(&folio->_entire_mapcount); + if (flags & RMAP_EXCLUSIVE) + SetPageAnonExclusive(&folio->page); + VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && + PageAnonExclusive(&folio->page), folio); } void hugepage_add_new_anon_rmap(struct folio *folio, @@ -2565,6 +2602,7 @@ void hugepage_add_new_anon_rmap(struct folio *folio, /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); - __page_set_anon_rmap(folio, &folio->page, vma, address, 1); + __folio_set_anon(folio, vma, address, true); + SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/mm/shmem.c b/mm/shmem.c index e826be732b..0d1ce70bce 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -42,7 +42,7 @@ #include <linux/iversion.h> #include "swap.h" -static struct vfsmount *shm_mnt; +static struct vfsmount *shm_mnt __ro_after_init; #ifdef CONFIG_SHMEM /* @@ -146,9 +146,8 @@ static unsigned long shmem_default_max_inodes(void) #endif static int shmem_swapin_folio(struct inode *inode, pgoff_t index, - struct folio **foliop, enum sgp_type sgp, - gfp_t gfp, struct vm_area_struct *vma, - vm_fault_t *fault_type); + struct folio **foliop, enum sgp_type sgp, gfp_t gfp, + struct mm_struct *fault_mm, vm_fault_t *fault_type); static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { @@ -189,10 +188,10 @@ static inline int shmem_reacct_size(unsigned long flags, /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. - * shmem_get_folio reports shmem_acct_block failure as -ENOSPC not -ENOMEM, + * shmem_get_folio reports shmem_acct_blocks failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ -static inline int shmem_acct_block(unsigned long flags, long pages) +static inline int shmem_acct_blocks(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; @@ -207,26 +206,26 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } -static int shmem_inode_acct_block(struct inode *inode, long pages) +static int shmem_inode_acct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int err = -ENOSPC; - if (shmem_acct_block(info->flags, pages)) + if (shmem_acct_blocks(info->flags, pages)) return err; might_sleep(); /* when quotas */ if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - pages) > 0) + if (!percpu_counter_limited_add(&sbinfo->used_blocks, + sbinfo->max_blocks, pages)) goto unacct; err = dquot_alloc_block_nodirty(inode, pages); - if (err) + if (err) { + percpu_counter_sub(&sbinfo->used_blocks, pages); goto unacct; - - percpu_counter_add(&sbinfo->used_blocks, pages); + } } else { err = dquot_alloc_block_nodirty(inode, pages); if (err) @@ -447,7 +446,7 @@ bool shmem_charge(struct inode *inode, long pages) { struct address_space *mapping = inode->i_mapping; - if (shmem_inode_acct_block(inode, pages)) + if (shmem_inode_acct_blocks(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ @@ -756,16 +755,14 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * Like filemap_add_folio, but error if expected item has gone. + * Somewhat like filemap_add_folio, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, - pgoff_t index, void *expected, gfp_t gfp, - struct mm_struct *charge_mm) + pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); long nr = folio_nr_pages(folio); - int error; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -776,16 +773,7 @@ static int shmem_add_to_page_cache(struct folio *folio, folio->mapping = mapping; folio->index = index; - if (!folio_test_swapcache(folio)) { - error = mem_cgroup_charge(folio, charge_mm, gfp); - if (error) { - if (folio_test_pmd_mappable(folio)) { - count_vm_event(THP_FILE_FALLBACK); - count_vm_event(THP_FILE_FALLBACK_CHARGE); - } - goto error; - } - } + gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); do { @@ -801,31 +789,26 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) { - count_vm_event(THP_FILE_ALLOC); + if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - } - mapping->nrpages += nr; __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); + mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { - error = xas_error(&xas); - goto error; + folio->mapping = NULL; + folio_ref_sub(folio, nr); + return xas_error(&xas); } return 0; -error: - folio->mapping = NULL; - folio_ref_sub(folio, nr); - return error; } /* - * Like delete_from_page_cache, but substitutes swap for @folio. + * Somewhat like filemap_remove_folio, but substitutes swap for @folio. */ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) { @@ -887,7 +870,6 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, cond_resched_rcu(); } } - rcu_read_unlock(); return swapped << PAGE_SHIFT; @@ -1129,7 +1111,7 @@ whole_folios: void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); inode_inc_iversion(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); @@ -1230,7 +1212,6 @@ static int shmem_setattr(struct mnt_idmap *idmap, if (i_uid_needs_update(idmap, attr, inode) || i_gid_needs_update(idmap, attr, inode)) { error = dquot_transfer(idmap, inode, attr); - if (error) return error; } @@ -1241,7 +1222,7 @@ static int shmem_setattr(struct mnt_idmap *idmap, if (!error && update_ctime) { inode_set_ctime_current(inode); if (update_mtime) - inode->i_mtime = inode_get_ctime(inode); + inode_set_mtime_to_ts(inode, inode_get_ctime(inode)); inode_inc_iversion(inode); } return error; @@ -1343,10 +1324,8 @@ static int shmem_unuse_swap_entries(struct inode *inode, if (!xa_is_value(folio)) continue; - error = shmem_swapin_folio(inode, indices[i], - &folio, SGP_CACHE, - mapping_gfp_mask(mapping), - NULL, NULL); + error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE, + mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { folio_unlock(folio); folio_put(folio); @@ -1582,38 +1561,20 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ -#ifndef CONFIG_NUMA -#define vm_policy vm_private_data -#endif -static void shmem_pseudo_vma_init(struct vm_area_struct *vma, - struct shmem_inode_info *info, pgoff_t index) -{ - /* Create a pseudo vma that just contains the policy */ - vma_init(vma, NULL); - /* Bias interleave by inode number to distribute better across nodes */ - vma->vm_pgoff = index + info->vfs_inode.i_ino; - vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); -} - -static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) -{ - /* Drop reference taken by mpol_shared_policy_lookup() */ - mpol_cond_put(vma->vm_policy); -} +static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, + pgoff_t index, unsigned int order, pgoff_t *ilx); -static struct folio *shmem_swapin(swp_entry_t swap, gfp_t gfp, +static struct folio *shmem_swapin_cluster(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { - struct vm_area_struct pvma; + struct mempolicy *mpol; + pgoff_t ilx; struct page *page; - struct vm_fault vmf = { - .vma = &pvma, - }; - shmem_pseudo_vma_init(&pvma, info, index); - page = swap_cluster_readahead(swap, gfp, &vmf); - shmem_pseudo_vma_destroy(&pvma); + mpol = shmem_get_pgoff_policy(info, index, 0, &ilx); + page = swap_cluster_readahead(swap, gfp, mpol, ilx); + mpol_cond_put(mpol); if (!page) return NULL; @@ -1647,67 +1608,126 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) static struct folio *shmem_alloc_hugefolio(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { - struct vm_area_struct pvma; - struct address_space *mapping = info->vfs_inode.i_mapping; - pgoff_t hindex; - struct folio *folio; + struct mempolicy *mpol; + pgoff_t ilx; + struct page *page; - hindex = round_down(index, HPAGE_PMD_NR); - if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, - XA_PRESENT)) - return NULL; + mpol = shmem_get_pgoff_policy(info, index, HPAGE_PMD_ORDER, &ilx); + page = alloc_pages_mpol(gfp, HPAGE_PMD_ORDER, mpol, ilx, numa_node_id()); + mpol_cond_put(mpol); - shmem_pseudo_vma_init(&pvma, info, hindex); - folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); - shmem_pseudo_vma_destroy(&pvma); - if (!folio) - count_vm_event(THP_FILE_FALLBACK); - return folio; + return page_rmappable_folio(page); } static struct folio *shmem_alloc_folio(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) + struct shmem_inode_info *info, pgoff_t index) { - struct vm_area_struct pvma; - struct folio *folio; + struct mempolicy *mpol; + pgoff_t ilx; + struct page *page; - shmem_pseudo_vma_init(&pvma, info, index); - folio = vma_alloc_folio(gfp, 0, &pvma, 0, false); - shmem_pseudo_vma_destroy(&pvma); + mpol = shmem_get_pgoff_policy(info, index, 0, &ilx); + page = alloc_pages_mpol(gfp, 0, mpol, ilx, numa_node_id()); + mpol_cond_put(mpol); - return folio; + return (struct folio *)page; } -static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode, - pgoff_t index, bool huge) +static struct folio *shmem_alloc_and_add_folio(gfp_t gfp, + struct inode *inode, pgoff_t index, + struct mm_struct *fault_mm, bool huge) { + struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct folio *folio; - int nr; - int err; + long pages; + int error; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) huge = false; - nr = huge ? HPAGE_PMD_NR : 1; - err = shmem_inode_acct_block(inode, nr); - if (err) - goto failed; + if (huge) { + pages = HPAGE_PMD_NR; + index = round_down(index, HPAGE_PMD_NR); + + /* + * Check for conflict before waiting on a huge allocation. + * Conflict might be that a huge page has just been allocated + * and added to page cache by a racing thread, or that there + * is already at least one small page in the huge extent. + * Be careful to retry when appropriate, but not forever! + * Elsewhere -EEXIST would be the right code, but not here. + */ + if (xa_find(&mapping->i_pages, &index, + index + HPAGE_PMD_NR - 1, XA_PRESENT)) + return ERR_PTR(-E2BIG); - if (huge) folio = shmem_alloc_hugefolio(gfp, info, index); - else + if (!folio) + count_vm_event(THP_FILE_FALLBACK); + } else { + pages = 1; folio = shmem_alloc_folio(gfp, info, index); - if (folio) { - __folio_set_locked(folio); - __folio_set_swapbacked(folio); - return folio; } + if (!folio) + return ERR_PTR(-ENOMEM); - err = -ENOMEM; - shmem_inode_unacct_blocks(inode, nr); -failed: - return ERR_PTR(err); + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + + gfp &= GFP_RECLAIM_MASK; + error = mem_cgroup_charge(folio, fault_mm, gfp); + if (error) { + if (xa_find(&mapping->i_pages, &index, + index + pages - 1, XA_PRESENT)) { + error = -EEXIST; + } else if (huge) { + count_vm_event(THP_FILE_FALLBACK); + count_vm_event(THP_FILE_FALLBACK_CHARGE); + } + goto unlock; + } + + error = shmem_add_to_page_cache(folio, mapping, index, NULL, gfp); + if (error) + goto unlock; + + error = shmem_inode_acct_blocks(inode, pages); + if (error) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + long freed; + /* + * Try to reclaim some space by splitting a few + * large folios beyond i_size on the filesystem. + */ + shmem_unused_huge_shrink(sbinfo, NULL, 2); + /* + * And do a shmem_recalc_inode() to account for freed pages: + * except our folio is there in cache, so not quite balanced. + */ + spin_lock(&info->lock); + freed = pages + info->alloced - info->swapped - + READ_ONCE(mapping->nrpages); + if (freed > 0) + info->alloced -= freed; + spin_unlock(&info->lock); + if (freed > 0) + shmem_inode_unacct_blocks(inode, freed); + error = shmem_inode_acct_blocks(inode, pages); + if (error) { + filemap_remove_folio(folio); + goto unlock; + } + } + + shmem_recalc_inode(inode, pages, 0); + folio_add_lru(folio); + return folio; + +unlock: + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(error); } /* @@ -1829,12 +1849,11 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, */ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, - gfp_t gfp, struct vm_area_struct *vma, + gfp_t gfp, struct mm_struct *fault_mm, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; struct swap_info_struct *si; struct folio *folio = NULL; swp_entry_t swap; @@ -1862,10 +1881,10 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); - count_memcg_event_mm(charge_mm, PGMAJFAULT); + count_memcg_event_mm(fault_mm, PGMAJFAULT); } /* Here we actually start the io */ - folio = shmem_swapin(swap, gfp, info, index); + folio = shmem_swapin_cluster(swap, gfp, info, index); if (!folio) { error = -ENOMEM; goto failed; @@ -1899,8 +1918,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, } error = shmem_add_to_page_cache(folio, mapping, index, - swp_to_radix_entry(swap), gfp, - charge_mm); + swp_to_radix_entry(swap), gfp); if (error) goto failed; @@ -1938,37 +1956,29 @@ unlock: * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * - * vma, vmf, and fault_type are only supplied by shmem_fault: - * otherwise they are NULL. + * vmf and fault_type are only supplied by shmem_fault: otherwise they are NULL. */ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, - struct vm_area_struct *vma, struct vm_fault *vmf, - vm_fault_t *fault_type) + struct vm_fault *vmf, vm_fault_t *fault_type) { - struct address_space *mapping = inode->i_mapping; - struct shmem_inode_info *info = SHMEM_I(inode); - struct shmem_sb_info *sbinfo; - struct mm_struct *charge_mm; + struct vm_area_struct *vma = vmf ? vmf->vma : NULL; + struct mm_struct *fault_mm; struct folio *folio; - pgoff_t hindex; - gfp_t huge_gfp; int error; - int once = 0; - int alloced = 0; + bool alloced; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; repeat: if (sgp <= SGP_CACHE && - ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) return -EINVAL; - } - sbinfo = SHMEM_SB(inode->i_sb); - charge_mm = vma ? vma->vm_mm : NULL; + alloced = false; + fault_mm = vma ? vma->vm_mm : NULL; - folio = filemap_get_entry(mapping, index); + folio = filemap_get_entry(inode->i_mapping, index); if (folio && vma && userfaultfd_minor(vma)) { if (!xa_is_value(folio)) folio_put(folio); @@ -1978,7 +1988,7 @@ repeat: if (xa_is_value(folio)) { error = shmem_swapin_folio(inode, index, &folio, - sgp, gfp, vma, fault_type); + sgp, gfp, fault_mm, fault_type); if (error == -EEXIST) goto repeat; @@ -1990,7 +2000,7 @@ repeat: folio_lock(folio); /* Has the folio been truncated or swapped out? */ - if (unlikely(folio->mapping != mapping)) { + if (unlikely(folio->mapping != inode->i_mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; @@ -2025,58 +2035,38 @@ repeat: return 0; } - if (!shmem_is_huge(inode, index, false, - vma ? vma->vm_mm : NULL, vma ? vma->vm_flags : 0)) - goto alloc_nohuge; + if (shmem_is_huge(inode, index, false, fault_mm, + vma ? vma->vm_flags : 0)) { + gfp_t huge_gfp; - huge_gfp = vma_thp_gfp_mask(vma); - huge_gfp = limit_gfp_mask(huge_gfp, gfp); - folio = shmem_alloc_and_acct_folio(huge_gfp, inode, index, true); - if (IS_ERR(folio)) { -alloc_nohuge: - folio = shmem_alloc_and_acct_folio(gfp, inode, index, false); + huge_gfp = vma_thp_gfp_mask(vma); + huge_gfp = limit_gfp_mask(huge_gfp, gfp); + folio = shmem_alloc_and_add_folio(huge_gfp, + inode, index, fault_mm, true); + if (!IS_ERR(folio)) { + count_vm_event(THP_FILE_ALLOC); + goto alloced; + } + if (PTR_ERR(folio) == -EEXIST) + goto repeat; } - if (IS_ERR(folio)) { - int retry = 5; + folio = shmem_alloc_and_add_folio(gfp, inode, index, fault_mm, false); + if (IS_ERR(folio)) { error = PTR_ERR(folio); + if (error == -EEXIST) + goto repeat; folio = NULL; - if (error != -ENOSPC) - goto unlock; - /* - * Try to reclaim some space by splitting a large folio - * beyond i_size on the filesystem. - */ - while (retry--) { - int ret; - - ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); - if (ret == SHRINK_STOP) - break; - if (ret) - goto alloc_nohuge; - } goto unlock; } - hindex = round_down(index, folio_nr_pages(folio)); - - if (sgp == SGP_WRITE) - __folio_set_referenced(folio); - - error = shmem_add_to_page_cache(folio, mapping, hindex, - NULL, gfp & GFP_RECLAIM_MASK, - charge_mm); - if (error) - goto unacct; - - folio_add_lru(folio); - shmem_recalc_inode(inode, folio_nr_pages(folio), 0); +alloced: alloced = true; - if (folio_test_pmd_mappable(folio) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < folio_next_index(folio) - 1) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct shmem_inode_info *info = SHMEM_I(inode); /* * Part of the large folio is beyond i_size: subject * to shrink under memory pressure. @@ -2094,6 +2084,8 @@ alloc_nohuge: spin_unlock(&sbinfo->shrinklist_lock); } + if (sgp == SGP_WRITE) + folio_set_referenced(folio); /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new folio. */ @@ -2117,11 +2109,6 @@ clear: /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { - if (alloced) { - folio_clear_dirty(folio); - filemap_remove_folio(folio); - shmem_recalc_inode(inode, 0, 0); - } error = -EINVAL; goto unlock; } @@ -2132,25 +2119,14 @@ out: /* * Error recovery. */ -unacct: - shmem_inode_unacct_blocks(inode, folio_nr_pages(folio)); - - if (folio_test_large(folio)) { - folio_unlock(folio); - folio_put(folio); - goto alloc_nohuge; - } unlock: + if (alloced) + filemap_remove_folio(folio); + shmem_recalc_inode(inode, 0, 0); if (folio) { folio_unlock(folio); folio_put(folio); } - if (error == -ENOSPC && !once++) { - shmem_recalc_inode(inode, 0, 0); - goto repeat; - } - if (error == -EEXIST) - goto repeat; return error; } @@ -2158,7 +2134,7 @@ int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp) { return shmem_get_folio_gfp(inode, index, foliop, sgp, - mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); + mapping_gfp_mask(inode->i_mapping), NULL, NULL); } /* @@ -2166,87 +2142,99 @@ int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, * entry unconditionally - even if something else had already woken the * target. */ -static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) +static int synchronous_wake_function(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); list_del_init(&wait->entry); return ret; } +/* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_rwsem. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_rwsem in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ +static vm_fault_t shmem_falloc_wait(struct vm_fault *vmf, struct inode *inode) +{ + struct shmem_falloc *shmem_falloc; + struct file *fpin = NULL; + vm_fault_t ret = 0; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); + + ret = VM_FAULT_NOPAGE; + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + } + spin_unlock(&inode->i_lock); + if (fpin) { + fput(fpin); + ret = VM_FAULT_RETRY; + } + return ret; +} + static vm_fault_t shmem_fault(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); struct folio *folio = NULL; + vm_fault_t ret = 0; int err; - vm_fault_t ret = VM_FAULT_LOCKED; /* * Trinity finds that probing a hole which tmpfs is punching can - * prevent the hole-punch from ever completing: which in turn - * locks writers out with its hold on i_rwsem. So refrain from - * faulting pages into the hole while it's being punched. Although - * shmem_undo_range() does remove the additions, it may be unable to - * keep up, as each new page needs its own unmap_mapping_range() call, - * and the i_mmap tree grows ever slower to scan if new vmas are added. - * - * It does not matter if we sometimes reach this check just before the - * hole-punch begins, so that one fault then races with the punch: - * we just need to make racing faults a rare case. - * - * The implementation below would be much simpler if we just used a - * standard mutex or completion: but we cannot take i_rwsem in fault, - * and bloating every shmem inode for this unlikely case would be sad. + * prevent the hole-punch from ever completing: noted in i_private. */ if (unlikely(inode->i_private)) { - struct shmem_falloc *shmem_falloc; - - spin_lock(&inode->i_lock); - shmem_falloc = inode->i_private; - if (shmem_falloc && - shmem_falloc->waitq && - vmf->pgoff >= shmem_falloc->start && - vmf->pgoff < shmem_falloc->next) { - struct file *fpin; - wait_queue_head_t *shmem_falloc_waitq; - DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); - - ret = VM_FAULT_NOPAGE; - fpin = maybe_unlock_mmap_for_io(vmf, NULL); - if (fpin) - ret = VM_FAULT_RETRY; - - shmem_falloc_waitq = shmem_falloc->waitq; - prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, - TASK_UNINTERRUPTIBLE); - spin_unlock(&inode->i_lock); - schedule(); - - /* - * shmem_falloc_waitq points into the shmem_fallocate() - * stack of the hole-punching task: shmem_falloc_waitq - * is usually invalid by the time we reach here, but - * finish_wait() does not dereference it in that case; - * though i_lock needed lest racing with wake_up_all(). - */ - spin_lock(&inode->i_lock); - finish_wait(shmem_falloc_waitq, &shmem_fault_wait); - spin_unlock(&inode->i_lock); - - if (fpin) - fput(fpin); + ret = shmem_falloc_wait(vmf, inode); + if (ret) return ret; - } - spin_unlock(&inode->i_lock); } + WARN_ON_ONCE(vmf->page != NULL); err = shmem_get_folio_gfp(inode, vmf->pgoff, &folio, SGP_CACHE, - gfp, vma, vmf, &ret); + gfp, vmf, &ret); if (err) return vmf_error(err); - if (folio) + if (folio) { vmf->page = folio_file_page(folio, vmf->pgoff); + ret |= VM_FAULT_LOCKED; + } return ret; } @@ -2347,15 +2335,41 @@ static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, pgoff_t *ilx) { struct inode *inode = file_inode(vma->vm_file); pgoff_t index; + /* + * Bias interleave by inode number to distribute better across nodes; + * but this interface is independent of which page order is used, so + * supplies only that bias, letting caller apply the offset (adjusted + * by page order, as in shmem_get_pgoff_policy() and get_vma_policy()). + */ + *ilx = inode->i_ino; index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } -#endif + +static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, + pgoff_t index, unsigned int order, pgoff_t *ilx) +{ + struct mempolicy *mpol; + + /* Bias interleave by inode number to distribute better across nodes */ + *ilx = info->vfs_inode.i_ino + (index >> order); + + mpol = mpol_shared_policy_lookup(&info->policy, index); + return mpol ? mpol : get_task_policy(current); +} +#else +static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, + pgoff_t index, unsigned int order, pgoff_t *ilx) +{ + *ilx = 0; + return NULL; +} +#endif /* CONFIG_NUMA */ int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { @@ -2391,7 +2405,7 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) struct shmem_inode_info *info = SHMEM_I(inode); int ret; - ret = seal_check_future_write(info->seals, vma); + ret = seal_check_write(info->seals, vma); if (ret) return ret; @@ -2462,7 +2476,6 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, if (err) return ERR_PTR(err); - inode = new_inode(sb); if (!inode) { shmem_free_inode(sb, 0); @@ -2472,7 +2485,7 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, inode->i_ino = ino; inode_init_owner(idmap, inode, dir, mode); inode->i_blocks = 0; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_generation = get_random_u32(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); @@ -2480,18 +2493,17 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; - info->i_crtime = inode->i_mtime; + info->i_crtime = inode_get_mtime(inode); info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; if (info->fsflags) shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); - INIT_LIST_HEAD(&info->swaplist); - if (sbinfo->noswap) - mapping_set_unevictable(inode->i_mapping); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); + if (sbinfo->noswap) + mapping_set_unevictable(inode->i_mapping); mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { @@ -2582,7 +2594,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, int ret; pgoff_t max_off; - if (shmem_inode_acct_block(inode, 1)) { + if (shmem_inode_acct_blocks(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, * and now we find ourselves with -ENOMEM. Release the page, to @@ -2654,8 +2666,10 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, if (unlikely(pgoff >= max_off)) goto out_release; - ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, - gfp & GFP_RECLAIM_MASK, dst_vma->vm_mm); + ret = mem_cgroup_charge(folio, dst_vma->vm_mm, gfp); + if (ret) + goto out_release; + ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, gfp); if (ret) goto out_release; @@ -2703,7 +2717,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping, } ret = shmem_get_folio(inode, index, &folio, SGP_WRITE); - if (ret) return ret; @@ -3235,8 +3248,7 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir, error = simple_acl_create(dir, inode); if (error) goto out_iput; - error = security_inode_init_security(inode, dir, - &dentry->d_name, + error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; @@ -3246,7 +3258,7 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir, goto out_iput; dir->i_size += BOGO_DIRENT_SIZE; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ @@ -3265,14 +3277,11 @@ shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir, int error; inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE); - if (IS_ERR(inode)) { error = PTR_ERR(inode); goto err_out; } - - error = security_inode_init_security(inode, dir, - NULL, + error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; @@ -3309,7 +3318,8 @@ static int shmem_create(struct mnt_idmap *idmap, struct inode *dir, /* * Link a file.. */ -static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) +static int shmem_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int ret = 0; @@ -3335,12 +3345,12 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr } dir->i_size += BOGO_DIRENT_SIZE; - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inode_inc_iversion(dir); inc_nlink(inode); ihold(inode); /* New dentry reference */ - dget(dentry); /* Extra pinning count for the created dentry */ + dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: return ret; @@ -3356,11 +3366,11 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) simple_offset_remove(shmem_get_offset_ctx(dir), dentry); dir->i_size -= BOGO_DIRENT_SIZE; - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inode_inc_iversion(dir); drop_nlink(inode); - dput(dentry); /* Undo the count from "create" - this does all the work */ + dput(dentry); /* Undo the count from "create" - does all the work */ return 0; } @@ -3470,7 +3480,6 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); - if (IS_ERR(inode)) return PTR_ERR(inode); @@ -3505,7 +3514,7 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, folio_put(folio); } dir->i_size += BOGO_DIRENT_SIZE; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); d_instantiate(dentry, inode); dget(dentry); @@ -3524,8 +3533,7 @@ static void shmem_put_link(void *arg) folio_put(arg); } -static const char *shmem_get_link(struct dentry *dentry, - struct inode *inode, +static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct folio *folio = NULL; @@ -3599,8 +3607,7 @@ static int shmem_fileattr_set(struct mnt_idmap *idmap, * Callback for security_inode_init_security() for acquiring xattrs. */ static int shmem_initxattrs(struct inode *inode, - const struct xattr *xattr_array, - void *fs_info) + const struct xattr *xattr_array, void *fs_info) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); @@ -3731,7 +3738,7 @@ static const struct xattr_handler shmem_user_xattr_handler = { .set = shmem_xattr_handler_set, }; -static const struct xattr_handler *shmem_xattr_handlers[] = { +static const struct xattr_handler * const shmem_xattr_handlers[] = { &shmem_security_xattr_handler, &shmem_trusted_xattr_handler, &shmem_user_xattr_handler, @@ -3784,7 +3791,6 @@ static struct dentry *shmem_find_alias(struct inode *inode) return alias ?: d_find_any_alias(inode); } - static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { @@ -4368,8 +4374,8 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) } #endif /* CONFIG_TMPFS_QUOTA */ - inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0, - VM_NORESERVE); + inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, + S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (IS_ERR(inode)) { error = PTR_ERR(inode); goto failed; @@ -4411,7 +4417,7 @@ static const struct fs_context_operations shmem_fs_context_ops = { #endif }; -static struct kmem_cache *shmem_inode_cachep; +static struct kmem_cache *shmem_inode_cachep __ro_after_init; static struct inode *shmem_alloc_inode(struct super_block *sb) { @@ -4443,14 +4449,14 @@ static void shmem_init_inode(void *foo) inode_init_once(&info->vfs_inode); } -static void shmem_init_inodecache(void) +static void __init shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); } -static void shmem_destroy_inodecache(void) +static void __init shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } @@ -4602,11 +4608,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, -#ifdef CONFIG_SHMEM .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP, -#else - .fs_flags = FS_USERNS_MOUNT, -#endif }; void __init shmem_init(void) @@ -4672,11 +4674,9 @@ static ssize_t shmem_enabled_show(struct kobject *kobj, for (i = 0; i < ARRAY_SIZE(values); i++) { len += sysfs_emit_at(buf, len, - shmem_huge == values[i] ? "%s[%s]" : "%s%s", - i ? " " : "", - shmem_format_huge(values[i])); + shmem_huge == values[i] ? "%s[%s]" : "%s%s", + i ? " " : "", shmem_format_huge(values[i])); } - len += sysfs_emit_at(buf, len, "\n"); return len; @@ -4773,8 +4773,9 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, - umode_t mode, dev_t dev, unsigned long flags) +static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, + struct super_block *sb, struct inode *dir, + umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode = ramfs_get_inode(sb, dir, mode, dev); return inode ? inode : ERR_PTR(-ENOSPC); @@ -4784,8 +4785,8 @@ static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct supe /* common code */ -static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, - unsigned long flags, unsigned int i_flags) +static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, + loff_t size, unsigned long flags, unsigned int i_flags) { struct inode *inode; struct file *res; @@ -4804,7 +4805,6 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); - if (IS_ERR(inode)) { shmem_unacct_size(flags, size); return ERR_CAST(inode); @@ -4914,7 +4914,7 @@ struct folio *shmem_read_folio_gfp(struct address_space *mapping, BUG_ON(!shmem_mapping(mapping)); error = shmem_get_folio_gfp(inode, index, &folio, SGP_CACHE, - gfp, NULL, NULL, NULL); + gfp, NULL, NULL); if (error) return ERR_PTR(error); diff --git a/mm/show_mem.c b/mm/show_mem.c index 4b888b18bd..ba0808d691 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -34,13 +34,8 @@ long si_mem_available(void) long available; unsigned long pagecache; unsigned long wmark_low = 0; - unsigned long pages[NR_LRU_LISTS]; unsigned long reclaimable; struct zone *zone; - int lru; - - for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_node_page_state(NR_LRU_BASE + lru); for_each_zone(zone) wmark_low += low_wmark_pages(zone); @@ -56,7 +51,8 @@ long si_mem_available(void) * start swapping or thrashing. Assume at least half of the page * cache, or the low watermark worth of cache, needs to stay. */ - pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; + pagecache = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); pagecache -= min(pagecache / 2, wmark_low); available += pagecache; @@ -67,7 +63,8 @@ long si_mem_available(void) */ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); - available += reclaimable - min(reclaimable / 2, wmark_low); + reclaimable -= min(reclaimable / 2, wmark_low); + available += reclaimable; if (available < 0) available = 0; diff --git a/mm/shrinker.c b/mm/shrinker.c new file mode 100644 index 0000000000..dc5d2a6fcf --- /dev/null +++ b/mm/shrinker.c @@ -0,0 +1,809 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/memcontrol.h> +#include <linux/rwsem.h> +#include <linux/shrinker.h> +#include <linux/rculist.h> +#include <trace/events/vmscan.h> + +#include "internal.h" + +LIST_HEAD(shrinker_list); +DEFINE_MUTEX(shrinker_mutex); + +#ifdef CONFIG_MEMCG +static int shrinker_nr_max; + +static inline int shrinker_unit_size(int nr_items) +{ + return (DIV_ROUND_UP(nr_items, SHRINKER_UNIT_BITS) * sizeof(struct shrinker_info_unit *)); +} + +static inline void shrinker_unit_free(struct shrinker_info *info, int start) +{ + struct shrinker_info_unit **unit; + int nr, i; + + if (!info) + return; + + unit = info->unit; + nr = DIV_ROUND_UP(info->map_nr_max, SHRINKER_UNIT_BITS); + + for (i = start; i < nr; i++) { + if (!unit[i]) + break; + + kfree(unit[i]); + unit[i] = NULL; + } +} + +static inline int shrinker_unit_alloc(struct shrinker_info *new, + struct shrinker_info *old, int nid) +{ + struct shrinker_info_unit *unit; + int nr = DIV_ROUND_UP(new->map_nr_max, SHRINKER_UNIT_BITS); + int start = old ? DIV_ROUND_UP(old->map_nr_max, SHRINKER_UNIT_BITS) : 0; + int i; + + for (i = start; i < nr; i++) { + unit = kzalloc_node(sizeof(*unit), GFP_KERNEL, nid); + if (!unit) { + shrinker_unit_free(new, start); + return -ENOMEM; + } + + new->unit[i] = unit; + } + + return 0; +} + +void free_shrinker_info(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct shrinker_info *info; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + info = rcu_dereference_protected(pn->shrinker_info, true); + shrinker_unit_free(info, 0); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); + } +} + +int alloc_shrinker_info(struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + int nid, ret = 0; + int array_size = 0; + + mutex_lock(&shrinker_mutex); + array_size = shrinker_unit_size(shrinker_nr_max); + for_each_node(nid) { + info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); + if (!info) + goto err; + info->map_nr_max = shrinker_nr_max; + if (shrinker_unit_alloc(info, NULL, nid)) + goto err; + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); + } + mutex_unlock(&shrinker_mutex); + + return ret; + +err: + mutex_unlock(&shrinker_mutex); + free_shrinker_info(memcg); + return -ENOMEM; +} + +static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_mutex)); +} + +static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, + int old_size, int new_nr_max) +{ + struct shrinker_info *new, *old; + struct mem_cgroup_per_node *pn; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + old = shrinker_info_protected(memcg, nid); + /* Not yet online memcg */ + if (!old) + return 0; + + /* Already expanded this shrinker_info */ + if (new_nr_max <= old->map_nr_max) + continue; + + new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + new->map_nr_max = new_nr_max; + + memcpy(new->unit, old->unit, old_size); + if (shrinker_unit_alloc(new, old, nid)) { + kvfree(new); + return -ENOMEM; + } + + rcu_assign_pointer(pn->shrinker_info, new); + kvfree_rcu(old, rcu); + } + + return 0; +} + +static int expand_shrinker_info(int new_id) +{ + int ret = 0; + int new_nr_max = round_up(new_id + 1, SHRINKER_UNIT_BITS); + int new_size, old_size = 0; + struct mem_cgroup *memcg; + + if (!root_mem_cgroup) + goto out; + + lockdep_assert_held(&shrinker_mutex); + + new_size = shrinker_unit_size(new_nr_max); + old_size = shrinker_unit_size(shrinker_nr_max); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + ret = expand_one_shrinker_info(memcg, new_size, old_size, + new_nr_max); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto out; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); +out: + if (!ret) + shrinker_nr_max = new_nr_max; + + return ret; +} + +static inline int shrinker_id_to_index(int shrinker_id) +{ + return shrinker_id / SHRINKER_UNIT_BITS; +} + +static inline int shrinker_id_to_offset(int shrinker_id) +{ + return shrinker_id % SHRINKER_UNIT_BITS; +} + +static inline int calc_shrinker_id(int index, int offset) +{ + return index * SHRINKER_UNIT_BITS + offset; +} + +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct shrinker_info *info; + struct shrinker_info_unit *unit; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker_id)]; + if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id_to_offset(shrinker_id), unit->map); + } + rcu_read_unlock(); + } +} + +static DEFINE_IDR(shrinker_idr); + +static int shrinker_memcg_alloc(struct shrinker *shrinker) +{ + int id, ret = -ENOMEM; + + if (mem_cgroup_disabled()) + return -ENOSYS; + + mutex_lock(&shrinker_mutex); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); + if (id < 0) + goto unlock; + + if (id >= shrinker_nr_max) { + if (expand_shrinker_info(id)) { + idr_remove(&shrinker_idr, id); + goto unlock; + } + } + shrinker->id = id; + ret = 0; +unlock: + mutex_unlock(&shrinker_mutex); + return ret; +} + +static void shrinker_memcg_remove(struct shrinker *shrinker) +{ + int id = shrinker->id; + + BUG_ON(id < 0); + + lockdep_assert_held(&shrinker_mutex); + + idr_remove(&shrinker_idr, id); +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + struct shrinker_info_unit *unit; + long nr_deferred; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker->id)]; + nr_deferred = atomic_long_xchg(&unit->nr_deferred[shrinker_id_to_offset(shrinker->id)], 0); + rcu_read_unlock(); + + return nr_deferred; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + struct shrinker_info_unit *unit; + long nr_deferred; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker->id)]; + nr_deferred = + atomic_long_add_return(nr, &unit->nr_deferred[shrinker_id_to_offset(shrinker->id)]); + rcu_read_unlock(); + + return nr_deferred; +} + +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int nid, index, offset; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + struct shrinker_info_unit *child_unit, *parent_unit; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + mutex_lock(&shrinker_mutex); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (index = 0; index < shrinker_id_to_index(child_info->map_nr_max); index++) { + child_unit = child_info->unit[index]; + parent_unit = parent_info->unit[index]; + for (offset = 0; offset < SHRINKER_UNIT_BITS; offset++) { + nr = atomic_long_read(&child_unit->nr_deferred[offset]); + atomic_long_add(nr, &parent_unit->nr_deferred[offset]); + } + } + } + mutex_unlock(&shrinker_mutex); +} +#else +static int shrinker_memcg_alloc(struct shrinker *shrinker) +{ + return -ENOSYS; +} + +static void shrinker_memcg_remove(struct shrinker *shrinker) +{ +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +static long xchg_nr_deferred(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return xchg_nr_deferred_memcg(nid, shrinker, + sc->memcg); + + return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); +} + + +static long add_nr_deferred(long nr, struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return add_nr_deferred_memcg(nr, nid, shrinker, + sc->memcg); + + return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); +} + +#define SHRINK_BATCH 128 + +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, int priority) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + long scanned = 0, next_deferred; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0 || freeable == SHRINK_EMPTY) + return freeable; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = xchg_nr_deferred(shrinker, shrinkctl); + + if (shrinker->seeks) { + delta = freeable >> priority; + delta *= 4; + do_div(delta, shrinker->seeks); + } else { + /* + * These objects don't require any IO to create. Trim + * them aggressively under memory pressure to keep + * them from causing refetches in the IO caches. + */ + delta = freeable / 2; + } + + total_scan = nr >> priority; + total_scan += delta; + total_scan = min(total_scan, (2 * freeable)); + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + freeable, delta, total_scan, priority); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + shrinkctl->nr_scanned = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); + total_scan -= shrinkctl->nr_scanned; + scanned += shrinkctl->nr_scanned; + + cond_resched(); + } + + /* + * The deferred work is increased by any new work (delta) that wasn't + * done, decreased by old deferred work that was done now. + * + * And it is capped to two times of the freeable items. + */ + next_deferred = max_t(long, (nr + delta - scanned), 0); + next_deferred = min(next_deferred, (2 * freeable)); + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. + */ + new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); + + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); + return freed; +} + +#ifdef CONFIG_MEMCG +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + struct shrinker_info *info; + unsigned long ret, freed = 0; + int offset, index = 0; + + if (!mem_cgroup_online(memcg)) + return 0; + + /* + * lockless algorithm of memcg shrink. + * + * The shrinker_info may be freed asynchronously via RCU in the + * expand_one_shrinker_info(), so the rcu_read_lock() needs to be used + * to ensure the existence of the shrinker_info. + * + * The shrinker_info_unit is never freed unless its corresponding memcg + * is destroyed. Here we already hold the refcount of memcg, so the + * memcg will not be destroyed, and of course shrinker_info_unit will + * not be freed. + * + * So in the memcg shrink: + * step 1: use rcu_read_lock() to guarantee existence of the + * shrinker_info. + * step 2: after getting shrinker_info_unit we can safely release the + * RCU lock. + * step 3: traverse the bitmap and calculate shrinker_id + * step 4: use rcu_read_lock() to guarantee existence of the shrinker. + * step 5: use shrinker_id to find the shrinker, then use + * shrinker_try_get() to guarantee existence of the shrinker, + * then we can release the RCU lock to do do_shrink_slab() that + * may sleep. + * step 6: do shrinker_put() paired with step 5 to put the refcount, + * if the refcount reaches 0, then wake up the waiter in + * shrinker_free() by calling complete(). + * Note: here is different from the global shrink, we don't + * need to acquire the RCU lock to guarantee existence of + * the shrinker, because we don't need to use this + * shrinker to traverse the next shrinker in the bitmap. + * step 7: we have already exited the read-side of rcu critical section + * before calling do_shrink_slab(), the shrinker_info may be + * released in expand_one_shrinker_info(), so go back to step 1 + * to reacquire the shrinker_info. + */ +again: + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + if (unlikely(!info)) + goto unlock; + + if (index < shrinker_id_to_index(info->map_nr_max)) { + struct shrinker_info_unit *unit; + + unit = info->unit[index]; + + rcu_read_unlock(); + + for_each_set_bit(offset, unit->map, SHRINKER_UNIT_BITS) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + struct shrinker *shrinker; + int shrinker_id = calc_shrinker_id(index, offset); + + rcu_read_lock(); + shrinker = idr_find(&shrinker_idr, shrinker_id); + if (unlikely(!shrinker || !shrinker_try_get(shrinker))) { + clear_bit(offset, unit->map); + rcu_read_unlock(); + continue; + } + rcu_read_unlock(); + + /* Call non-slab shrinkers even though kmem is disabled */ + if (!memcg_kmem_online() && + !(shrinker->flags & SHRINKER_NONSLAB)) + continue; + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) { + clear_bit(offset, unit->map); + /* + * After the shrinker reported that it had no objects to + * free, but before we cleared the corresponding bit in + * the memcg shrinker map, a new object might have been + * added. To make sure, we have the bit set in this + * case, we invoke the shrinker one more time and reset + * the bit if it reports that it is not empty anymore. + * The memory barrier here pairs with the barrier in + * set_shrinker_bit(): + * + * list_lru_add() shrink_slab_memcg() + * list_add_tail() clear_bit() + * <MB> <MB> + * set_bit() do_shrink_slab() + */ + smp_mb__after_atomic(); + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + else + set_shrinker_bit(memcg, nid, shrinker_id); + } + freed += ret; + shrinker_put(shrinker); + } + + index++; + goto again; + } +unlock: + rcu_read_unlock(); + return freed; +} +#else /* !CONFIG_MEMCG */ +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +/** + * shrink_slab - shrink slab caches + * @gfp_mask: allocation context + * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target + * @priority: the reclaim priority + * + * Call the shrink functions to age shrinkable caches. + * + * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, + * unaware shrinkers will receive a node id of 0 instead. + * + * @memcg specifies the memory cgroup to target. Unaware shrinkers + * are called only if it is the root cgroup. + * + * @priority is sc->priority, we take the number of objects and >> by priority + * in order to get the scan target. + * + * Returns the number of reclaimed slab objects. + */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority) +{ + unsigned long ret, freed = 0; + struct shrinker *shrinker; + + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) + return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + + /* + * lockless algorithm of global shrink. + * + * In the unregistration setp, the shrinker will be freed asynchronously + * via RCU after its refcount reaches 0. So both rcu_read_lock() and + * shrinker_try_get() can be used to ensure the existence of the shrinker. + * + * So in the global shrink: + * step 1: use rcu_read_lock() to guarantee existence of the shrinker + * and the validity of the shrinker_list walk. + * step 2: use shrinker_try_get() to try get the refcount, if successful, + * then the existence of the shrinker can also be guaranteed, + * so we can release the RCU lock to do do_shrink_slab() that + * may sleep. + * step 3: *MUST* to reacquire the RCU lock before calling shrinker_put(), + * which ensures that neither this shrinker nor the next shrinker + * will be freed in the next traversal operation. + * step 4: do shrinker_put() paired with step 2 to put the refcount, + * if the refcount reaches 0, then wake up the waiter in + * shrinker_free() by calling complete(). + */ + rcu_read_lock(); + list_for_each_entry_rcu(shrinker, &shrinker_list, list) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + + if (!shrinker_try_get(shrinker)) + continue; + + rcu_read_unlock(); + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + freed += ret; + + rcu_read_lock(); + shrinker_put(shrinker); + } + + rcu_read_unlock(); + cond_resched(); + return freed; +} + +struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...) +{ + struct shrinker *shrinker; + unsigned int size; + va_list ap; + int err; + + shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); + if (!shrinker) + return NULL; + + va_start(ap, fmt); + err = shrinker_debugfs_name_alloc(shrinker, fmt, ap); + va_end(ap); + if (err) + goto err_name; + + shrinker->flags = flags | SHRINKER_ALLOCATED; + shrinker->seeks = DEFAULT_SEEKS; + + if (flags & SHRINKER_MEMCG_AWARE) { + err = shrinker_memcg_alloc(shrinker); + if (err == -ENOSYS) { + /* Memcg is not supported, fallback to non-memcg-aware shrinker. */ + shrinker->flags &= ~SHRINKER_MEMCG_AWARE; + goto non_memcg; + } + + if (err) + goto err_flags; + + return shrinker; + } + +non_memcg: + /* + * The nr_deferred is available on per memcg level for memcg aware + * shrinkers, so only allocate nr_deferred in the following cases: + * - non-memcg-aware shrinkers + * - !CONFIG_MEMCG + * - memcg is disabled by kernel command line + */ + size = sizeof(*shrinker->nr_deferred); + if (flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + goto err_flags; + + return shrinker; + +err_flags: + shrinker_debugfs_name_free(shrinker); +err_name: + kfree(shrinker); + return NULL; +} +EXPORT_SYMBOL_GPL(shrinker_alloc); + +void shrinker_register(struct shrinker *shrinker) +{ + if (unlikely(!(shrinker->flags & SHRINKER_ALLOCATED))) { + pr_warn("Must use shrinker_alloc() to dynamically allocate the shrinker"); + return; + } + + mutex_lock(&shrinker_mutex); + list_add_tail_rcu(&shrinker->list, &shrinker_list); + shrinker->flags |= SHRINKER_REGISTERED; + shrinker_debugfs_add(shrinker); + mutex_unlock(&shrinker_mutex); + + init_completion(&shrinker->done); + /* + * Now the shrinker is fully set up, take the first reference to it to + * indicate that lookup operations are now allowed to use it via + * shrinker_try_get(). + */ + refcount_set(&shrinker->refcount, 1); +} +EXPORT_SYMBOL_GPL(shrinker_register); + +static void shrinker_free_rcu_cb(struct rcu_head *head) +{ + struct shrinker *shrinker = container_of(head, struct shrinker, rcu); + + kfree(shrinker->nr_deferred); + kfree(shrinker); +} + +void shrinker_free(struct shrinker *shrinker) +{ + struct dentry *debugfs_entry = NULL; + int debugfs_id; + + if (!shrinker) + return; + + if (shrinker->flags & SHRINKER_REGISTERED) { + /* drop the initial refcount */ + shrinker_put(shrinker); + /* + * Wait for all lookups of the shrinker to complete, after that, + * no shrinker is running or will run again, then we can safely + * free it asynchronously via RCU and safely free the structure + * where the shrinker is located, such as super_block etc. + */ + wait_for_completion(&shrinker->done); + } + + mutex_lock(&shrinker_mutex); + if (shrinker->flags & SHRINKER_REGISTERED) { + /* + * Now we can safely remove it from the shrinker_list and then + * free it. + */ + list_del_rcu(&shrinker->list); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); + shrinker->flags &= ~SHRINKER_REGISTERED; + } + + shrinker_debugfs_name_free(shrinker); + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + shrinker_memcg_remove(shrinker); + mutex_unlock(&shrinker_mutex); + + if (debugfs_entry) + shrinker_debugfs_remove(debugfs_entry, debugfs_id); + + call_rcu(&shrinker->rcu, shrinker_free_rcu_cb); +} +EXPORT_SYMBOL_GPL(shrinker_free); diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3ab53fad88..12ea5486a3 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -6,8 +6,10 @@ #include <linux/shrinker.h> #include <linux/memcontrol.h> +#include "internal.h" + /* defined in vmscan.c */ -extern struct rw_semaphore shrinker_rwsem; +extern struct mutex shrinker_mutex; extern struct list_head shrinker_list; static DEFINE_IDA(shrinker_debugfs_ida); @@ -49,17 +51,12 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret, nid; + int ret = 0, nid; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - kfree(count_per_node); - return ret; - } rcu_read_lock(); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -92,7 +89,6 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); rcu_read_unlock(); - up_read(&shrinker_rwsem); kfree(count_per_node); return ret; @@ -117,7 +113,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, struct mem_cgroup *memcg = NULL; int nid; char kbuf[72]; - ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -146,12 +141,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - mem_cgroup_put(memcg); - return ret; - } - sc.nid = nid; sc.memcg = memcg; sc.nr_to_scan = nr_to_scan; @@ -159,7 +148,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - up_read(&shrinker_rwsem); mem_cgroup_put(memcg); return size; @@ -177,7 +165,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -220,7 +208,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); old = shrinker->name; shrinker->name = new; @@ -238,7 +226,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); kfree_const(old); @@ -251,10 +239,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_rwsem); - - kfree_const(shrinker->name); - shrinker->name = NULL; + lockdep_assert_held(&shrinker_mutex); *debugfs_id = entry ? shrinker->debugfs_id : -1; shrinker->debugfs_entry = NULL; @@ -280,14 +265,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } @@ -484,7 +484,12 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) return true; - objcg = get_obj_cgroup_from_current(); + /* + * The obtained objcg pointer is safe to use within the current scope, + * defined by current task or set_active_memcg() pair. + * obj_cgroup_get() is used to get a permanent reference. + */ + objcg = current_obj_cgroup(); if (!objcg) return true; @@ -497,17 +502,14 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, css_put(&memcg->css); if (ret) - goto out; + return false; } if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) - goto out; + return false; *objcgp = objcg; return true; -out: - obj_cgroup_put(objcg); - return false; } static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -542,7 +544,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, obj_cgroup_uncharge(objcg, obj_full_size(s)); } } - obj_cgroup_put(objcg); } static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, diff --git a/mm/slab_common.c b/mm/slab_common.c index 9bbffe82d6..8d431193c2 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -528,26 +528,6 @@ bool slab_is_available(void) } #ifdef CONFIG_PRINTK -/** - * kmem_valid_obj - does the pointer reference a valid slab object? - * @object: pointer to query. - * - * Return: %true if the pointer is to a not-yet-freed object from - * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer - * is to an already-freed object, and %false otherwise. - */ -bool kmem_valid_obj(void *object) -{ - struct folio *folio; - - /* Some arches consider ZERO_SIZE_PTR to be a valid address. */ - if (object < (void *)PAGE_SIZE || !virt_addr_valid(object)) - return false; - folio = virt_to_folio(object); - return folio_test_slab(folio); -} -EXPORT_SYMBOL_GPL(kmem_valid_obj); - static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { if (__kfence_obj_info(kpp, object, slab)) @@ -566,11 +546,11 @@ static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab * * and, if available, the slab name, return address, and stack trace from * the allocation and last free path of that object. * - * This function will splat if passed a pointer to a non-slab object. - * If you are not sure what type of object you have, you should instead - * use mem_dump_obj(). + * Return: %true if the pointer is to a not-yet-freed object from + * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer + * is to an already-freed object, and %false otherwise. */ -void kmem_dump_obj(void *object) +bool kmem_dump_obj(void *object) { char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc"; int i; @@ -578,13 +558,13 @@ void kmem_dump_obj(void *object) unsigned long ptroffset; struct kmem_obj_info kp = { }; - if (WARN_ON_ONCE(!virt_addr_valid(object))) - return; + /* Some arches consider ZERO_SIZE_PTR to be a valid address. */ + if (object < (void *)PAGE_SIZE || !virt_addr_valid(object)) + return false; slab = virt_to_slab(object); - if (WARN_ON_ONCE(!slab)) { - pr_cont(" non-slab memory.\n"); - return; - } + if (!slab) + return false; + kmem_obj_info(&kp, object, slab); if (kp.kp_slab_cache) pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); @@ -621,6 +601,7 @@ void kmem_dump_obj(void *object) pr_info(" %pS\n", kp.kp_free_stack[i]); } + return true; } EXPORT_SYMBOL_GPL(kmem_dump_obj); #endif @@ -4110,17 +4110,12 @@ static unsigned int slub_min_objects; * the smallest order which will fit the object. */ static inline unsigned int calc_slab_order(unsigned int size, - unsigned int min_objects, unsigned int max_order, + unsigned int min_order, unsigned int max_order, unsigned int fract_leftover) { - unsigned int min_order = slub_min_order; unsigned int order; - if (order_objects(min_order, size) > MAX_OBJS_PER_PAGE) - return get_order(size * MAX_OBJS_PER_PAGE) - 1; - - for (order = max(min_order, (unsigned int)get_order(min_objects * size)); - order <= max_order; order++) { + for (order = min_order; order <= max_order; order++) { unsigned int slab_size = (unsigned int)PAGE_SIZE << order; unsigned int rem; @@ -4139,16 +4134,8 @@ static inline int calculate_order(unsigned int size) unsigned int order; unsigned int min_objects; unsigned int max_objects; - unsigned int nr_cpus; + unsigned int min_order; - /* - * Attempt to find best configuration for a slab. This - * works by first attempting to generate a layout with - * the best configuration and backing off gradually. - * - * First we increase the acceptable waste in a slab. Then - * we reduce the minimum objects required in a slab. - */ min_objects = slub_min_objects; if (!min_objects) { /* @@ -4160,40 +4147,46 @@ static inline int calculate_order(unsigned int size) * order on systems that appear larger than they are, and too * low order on systems that appear smaller than they are. */ - nr_cpus = num_present_cpus(); + unsigned int nr_cpus = num_present_cpus(); if (nr_cpus <= 1) nr_cpus = nr_cpu_ids; min_objects = 4 * (fls(nr_cpus) + 1); } - max_objects = order_objects(slub_max_order, size); + /* min_objects can't be 0 because get_order(0) is undefined */ + max_objects = max(order_objects(slub_max_order, size), 1U); min_objects = min(min_objects, max_objects); - while (min_objects > 1) { - unsigned int fraction; - - fraction = 16; - while (fraction >= 4) { - order = calc_slab_order(size, min_objects, - slub_max_order, fraction); - if (order <= slub_max_order) - return order; - fraction /= 2; - } - min_objects--; - } + min_order = max_t(unsigned int, slub_min_order, + get_order(min_objects * size)); + if (order_objects(min_order, size) > MAX_OBJS_PER_PAGE) + return get_order(size * MAX_OBJS_PER_PAGE) - 1; /* - * We were unable to place multiple objects in a slab. Now - * lets see if we can place a single object there. + * Attempt to find best configuration for a slab. This works by first + * attempting to generate a layout with the best possible configuration + * and backing off gradually. + * + * We start with accepting at most 1/16 waste and try to find the + * smallest order from min_objects-derived/slub_min_order up to + * slub_max_order that will satisfy the constraint. Note that increasing + * the order can only result in same or less fractional waste, not more. + * + * If that fails, we increase the acceptable fraction of waste and try + * again. The last iteration with fraction of 1/2 would effectively + * accept any waste and give us the order determined by min_objects, as + * long as at least single object fits within slub_max_order. */ - order = calc_slab_order(size, 1, slub_max_order, 1); - if (order <= slub_max_order) - return order; + for (unsigned int fraction = 16; fraction > 1; fraction /= 2) { + order = calc_slab_order(size, min_order, slub_max_order, + fraction); + if (order <= slub_max_order) + return order; + } /* * Doh this slab cannot be placed using slub_max_order. */ - order = calc_slab_order(size, 1, MAX_ORDER, 1); + order = get_order(size); if (order <= MAX_ORDER) return order; return -ENOSYS; @@ -4711,6 +4704,9 @@ static int __init setup_slub_min_order(char *str) { get_option(&str, (int *)&slub_min_order); + if (slub_min_order > slub_max_order) + slub_max_order = slub_min_order; + return 1; } @@ -4721,6 +4717,9 @@ static int __init setup_slub_max_order(char *str) get_option(&str, (int *)&slub_max_order); slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER); + if (slub_min_order > slub_max_order) + slub_min_order = slub_max_order; + return 1; } @@ -2,6 +2,8 @@ #ifndef _MM_SWAP_H #define _MM_SWAP_H +struct mempolicy; + #ifdef CONFIG_SWAP #include <linux/blk_types.h> /* for bio_end_io_t */ @@ -38,6 +40,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -48,11 +51,10 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, unsigned long addr, struct swap_iocb **plug); struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, - struct vm_area_struct *vma, - unsigned long addr, + struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated); struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); + struct mempolicy *mpol, pgoff_t ilx); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); @@ -80,7 +82,7 @@ static inline void show_swap_cache_info(void) } static inline struct page *swap_cluster_readahead(swp_entry_t entry, - gfp_t gfp_mask, struct vm_fault *vmf) + gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx) { return NULL; } @@ -96,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swap_state.c b/mm/swap_state.c index b3b14bd0dd..85d9e5806a 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> +#include <linux/mempolicy.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/init.h> @@ -109,9 +110,9 @@ int add_to_swap_cache(struct folio *folio, swp_entry_t entry, goto unlock; for (i = 0; i < nr; i++) { VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio); - old = xas_load(&xas); - if (xa_is_value(old)) { - if (shadowp) + if (shadowp) { + old = xas_load(&xas); + if (xa_is_value(old)) *shadowp = old; } xas_store(&xas, folio); @@ -410,8 +411,8 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping, } struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated) + struct mempolicy *mpol, pgoff_t ilx, + bool *new_page_allocated) { struct swap_info_struct *si; struct folio *folio; @@ -453,7 +454,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will * cause any racers to loop around until we add it to cache. */ - folio = vma_alloc_folio(gfp_mask, 0, vma, addr, false); + folio = (struct folio *)alloc_pages_mpol(gfp_mask, 0, + mpol, ilx, numa_node_id()); if (!folio) goto fail_put_swap; @@ -528,14 +530,19 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, struct swap_iocb **plug) { - bool page_was_allocated; - struct page *retpage = __read_swap_cache_async(entry, gfp_mask, - vma, addr, &page_was_allocated); + bool page_allocated; + struct mempolicy *mpol; + pgoff_t ilx; + struct page *page; - if (page_was_allocated) - swap_readpage(retpage, false, plug); + mpol = get_vma_policy(vma, addr, 0, &ilx); + page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, + &page_allocated); + mpol_cond_put(mpol); - return retpage; + if (page_allocated) + swap_readpage(page, false, plug); + return page; } static unsigned int __swapin_nr_pages(unsigned long prev_offset, @@ -603,7 +610,8 @@ static unsigned long swapin_nr_pages(unsigned long offset) * swap_cluster_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags - * @vmf: fault information + * @mpol: NUMA memory allocation policy to be applied + * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE * * Returns the struct page for entry and addr, after queueing swapin. * @@ -612,13 +620,12 @@ static unsigned long swapin_nr_pages(unsigned long offset) * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * - * This has been extended to use the NUMA policies from the mm triggering - * the readahead. - * - * Caller must hold read mmap_lock if vmf->vma is not NULL. + * Note: it is intentional that the same NUMA policy and interleave index + * are used for every page of the readahead: neighbouring pages on swap + * are fairly likely to have been swapped out from the same node. */ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, - struct vm_fault *vmf) + struct mempolicy *mpol, pgoff_t ilx) { struct page *page; unsigned long entry_offset = swp_offset(entry); @@ -629,8 +636,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct blk_plug plug; struct swap_iocb *splug = NULL; bool page_allocated; - struct vm_area_struct *vma = vmf->vma; - unsigned long addr = vmf->address; mask = swapin_nr_pages(offset) - 1; if (!mask) @@ -648,8 +653,8 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( - swp_entry(swp_type(entry), offset), - gfp_mask, vma, addr, &page_allocated); + swp_entry(swp_type(entry), offset), + gfp_mask, mpol, ilx, &page_allocated); if (!page) continue; if (page_allocated) { @@ -663,11 +668,14 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, } blk_finish_plug(&plug); swap_read_unplug(splug); - lru_add_drain(); /* Push any new pages onto the LRU now */ skip: /* The page was likely read above, so no need for plugging here */ - return read_swap_cache_async(entry, gfp_mask, vma, addr, NULL); + page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, + &page_allocated); + if (unlikely(page_allocated)) + swap_readpage(page, false, NULL); + return page; } int init_swap_address_space(unsigned int type, unsigned long nr_pages) @@ -765,8 +773,10 @@ static void swap_ra_info(struct vm_fault *vmf, /** * swap_vma_readahead - swap in pages in hope we need them soon - * @fentry: swap entry of this memory + * @targ_entry: swap entry of the targeted memory * @gfp_mask: memory allocation flags + * @mpol: NUMA memory allocation policy to be applied + * @targ_ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. @@ -777,16 +787,17 @@ static void swap_ra_info(struct vm_fault *vmf, * Caller must hold read mmap_lock if vmf->vma is not NULL. * */ -static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, +static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, + struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf) { struct blk_plug plug; struct swap_iocb *splug = NULL; - struct vm_area_struct *vma = vmf->vma; struct page *page; pte_t *pte = NULL, pentry; unsigned long addr; swp_entry_t entry; + pgoff_t ilx; unsigned int i; bool page_allocated; struct vma_swap_readahead ra_info = { @@ -798,9 +809,10 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, goto skip; addr = vmf->address - (ra_info.offset * PAGE_SIZE); + ilx = targ_ilx - ra_info.offset; blk_start_plug(&plug); - for (i = 0; i < ra_info.nr_pte; i++, addr += PAGE_SIZE) { + for (i = 0; i < ra_info.nr_pte; i++, ilx++, addr += PAGE_SIZE) { if (!pte++) { pte = pte_offset_map(vmf->pmd, addr); if (!pte) @@ -814,8 +826,8 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, continue; pte_unmap(pte); pte = NULL; - page = __read_swap_cache_async(entry, gfp_mask, vma, - addr, &page_allocated); + page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, + &page_allocated); if (!page) continue; if (page_allocated) { @@ -834,8 +846,11 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, lru_add_drain(); skip: /* The page was likely read above, so no need for plugging here */ - return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, - NULL); + page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx, + &page_allocated); + if (unlikely(page_allocated)) + swap_readpage(page, false, NULL); + return page; } /** @@ -853,9 +868,16 @@ skip: struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { - return swap_use_vma_readahead() ? - swap_vma_readahead(entry, gfp_mask, vmf) : - swap_cluster_readahead(entry, gfp_mask, vmf); + struct mempolicy *mpol; + pgoff_t ilx; + struct page *page; + + mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx); + page = swap_use_vma_readahead() ? + swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf) : + swap_cluster_readahead(entry, gfp_mask, mpol, ilx); + mpol_cond_put(mpol); + return page; } #ifdef CONFIG_SYSFS diff --git a/mm/swapfile.c b/mm/swapfile.c index e52f486834..022581ec40 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2530,11 +2530,10 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) exit_swap_address_space(p->type); inode = mapping->host; - if (S_ISBLK(inode->i_mode)) { - struct block_device *bdev = I_BDEV(inode); - - set_blocksize(bdev, old_block_size); - blkdev_put(bdev, p); + if (p->bdev_handle) { + set_blocksize(p->bdev, old_block_size); + bdev_release(p->bdev_handle); + p->bdev_handle = NULL; } inode_lock(inode); @@ -2764,13 +2763,14 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) int error; if (S_ISBLK(inode->i_mode)) { - p->bdev = blkdev_get_by_dev(inode->i_rdev, + p->bdev_handle = bdev_open_by_dev(inode->i_rdev, BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL); - if (IS_ERR(p->bdev)) { - error = PTR_ERR(p->bdev); - p->bdev = NULL; + if (IS_ERR(p->bdev_handle)) { + error = PTR_ERR(p->bdev_handle); + p->bdev_handle = NULL; return error; } + p->bdev = p->bdev_handle->bdev; p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) @@ -3206,9 +3206,10 @@ bad_swap: p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; - if (inode && S_ISBLK(inode->i_mode) && p->bdev) { + if (p->bdev_handle) { set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, p); + bdev_release(p->bdev_handle); + p->bdev_handle = NULL; } inode = NULL; destroy_swap_extents(p); @@ -3362,6 +3363,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 96d9eae5c7..2213d887ec 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -312,7 +312,7 @@ static int mfill_atomic_pte_poison(pmd_t *dst_pmd, ret = -EEXIST; /* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */ - if (!pte_none(*dst_pte)) + if (!pte_none(ptep_get(dst_pte))) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ retry: goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ retry: * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; @@ -809,6 +809,7 @@ void folio_copy(struct folio *dst, struct folio *src) cond_resched(); } } +EXPORT_SYMBOL(folio_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; @@ -1070,10 +1071,8 @@ void mem_dump_obj(void *object) { const char *type; - if (kmem_valid_obj(object)) { - kmem_dump_obj(object); + if (kmem_dump_obj(object)) return; - } if (vmalloc_dump_obj(object)) return; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a3fedb3ee0..d12a17fc0c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3809,7 +3809,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); - else if (!(vm->flags & VM_IOREMAP)) + else if (!(vm && (vm->flags & VM_IOREMAP))) copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP area is treated as memory hole */ copied = zero_iter(iter, n); diff --git a/mm/vmscan.c b/mm/vmscan.c index 0dfb9a75df..bba207f41b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,6 @@ #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> -#include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -188,246 +187,7 @@ struct scan_control { */ int vm_swappiness = 60; -LIST_HEAD(shrinker_list); -DECLARE_RWSEM(shrinker_rwsem); - #ifdef CONFIG_MEMCG -static int shrinker_nr_max; - -/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ -static inline int shrinker_map_size(int nr_items) -{ - return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); -} - -static inline int shrinker_defer_size(int nr_items) -{ - return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); -} - -static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, - int nid) -{ - return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, - lockdep_is_held(&shrinker_rwsem)); -} - -static int expand_one_shrinker_info(struct mem_cgroup *memcg, - int map_size, int defer_size, - int old_map_size, int old_defer_size, - int new_nr_max) -{ - struct shrinker_info *new, *old; - struct mem_cgroup_per_node *pn; - int nid; - int size = map_size + defer_size; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - old = shrinker_info_protected(memcg, nid); - /* Not yet online memcg */ - if (!old) - return 0; - - /* Already expanded this shrinker_info */ - if (new_nr_max <= old->map_nr_max) - continue; - - new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); - if (!new) - return -ENOMEM; - - new->nr_deferred = (atomic_long_t *)(new + 1); - new->map = (void *)new->nr_deferred + defer_size; - new->map_nr_max = new_nr_max; - - /* map: set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_map_size); - memset((void *)new->map + old_map_size, 0, map_size - old_map_size); - /* nr_deferred: copy old values, clear all new values */ - memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); - memset((void *)new->nr_deferred + old_defer_size, 0, - defer_size - old_defer_size); - - rcu_assign_pointer(pn->shrinker_info, new); - kvfree_rcu(old, rcu); - } - - return 0; -} - -void free_shrinker_info(struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *pn; - struct shrinker_info *info; - int nid; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - info = rcu_dereference_protected(pn->shrinker_info, true); - kvfree(info); - rcu_assign_pointer(pn->shrinker_info, NULL); - } -} - -int alloc_shrinker_info(struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - int nid, size, ret = 0; - int map_size, defer_size = 0; - - down_write(&shrinker_rwsem); - map_size = shrinker_map_size(shrinker_nr_max); - defer_size = shrinker_defer_size(shrinker_nr_max); - size = map_size + defer_size; - for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); - if (!info) { - free_shrinker_info(memcg); - ret = -ENOMEM; - break; - } - info->nr_deferred = (atomic_long_t *)(info + 1); - info->map = (void *)info->nr_deferred + defer_size; - info->map_nr_max = shrinker_nr_max; - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); - } - up_write(&shrinker_rwsem); - - return ret; -} - -static int expand_shrinker_info(int new_id) -{ - int ret = 0; - int new_nr_max = round_up(new_id + 1, BITS_PER_LONG); - int map_size, defer_size = 0; - int old_map_size, old_defer_size = 0; - struct mem_cgroup *memcg; - - if (!root_mem_cgroup) - goto out; - - lockdep_assert_held(&shrinker_rwsem); - - map_size = shrinker_map_size(new_nr_max); - defer_size = shrinker_defer_size(new_nr_max); - old_map_size = shrinker_map_size(shrinker_nr_max); - old_defer_size = shrinker_defer_size(shrinker_nr_max); - - memcg = mem_cgroup_iter(NULL, NULL, NULL); - do { - ret = expand_one_shrinker_info(memcg, map_size, defer_size, - old_map_size, old_defer_size, - new_nr_max); - if (ret) { - mem_cgroup_iter_break(NULL, memcg); - goto out; - } - } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); -out: - if (!ret) - shrinker_nr_max = new_nr_max; - - return ret; -} - -void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) -{ - if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct shrinker_info *info; - - rcu_read_lock(); - info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); - if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, info->map); - } - rcu_read_unlock(); - } -} - -static DEFINE_IDR(shrinker_idr); - -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - int id, ret = -ENOMEM; - - if (mem_cgroup_disabled()) - return -ENOSYS; - - down_write(&shrinker_rwsem); - /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); - if (id < 0) - goto unlock; - - if (id >= shrinker_nr_max) { - if (expand_shrinker_info(id)) { - idr_remove(&shrinker_idr, id); - goto unlock; - } - } - shrinker->id = id; - ret = 0; -unlock: - up_write(&shrinker_rwsem); - return ret; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ - int id = shrinker->id; - - BUG_ON(id < 0); - - lockdep_assert_held(&shrinker_rwsem); - - idr_remove(&shrinker_idr, id); -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - - info = shrinker_info_protected(memcg, nid); - return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - - info = shrinker_info_protected(memcg, nid); - return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); -} - -void reparent_shrinker_deferred(struct mem_cgroup *memcg) -{ - int i, nid; - long nr; - struct mem_cgroup *parent; - struct shrinker_info *child_info, *parent_info; - - parent = parent_mem_cgroup(memcg); - if (!parent) - parent = root_mem_cgroup; - - /* Prevent from concurrent shrinker_info expand */ - down_read(&shrinker_rwsem); - for_each_node(nid) { - child_info = shrinker_info_protected(memcg, nid); - parent_info = shrinker_info_protected(parent, nid); - for (i = 0; i < child_info->map_nr_max; i++) { - nr = atomic_long_read(&child_info->nr_deferred[i]); - atomic_long_add(nr, &parent_info->nr_deferred[i]); - } - } - up_read(&shrinker_rwsem); -} /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) @@ -468,27 +228,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) return false; } #else -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - return -ENOSYS; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - static bool cgroup_reclaim(struct scan_control *sc) { return false; @@ -557,39 +296,6 @@ static void flush_reclaim_state(struct scan_control *sc) } } -static long xchg_nr_deferred(struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return xchg_nr_deferred_memcg(nid, shrinker, - sc->memcg); - - return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); -} - - -static long add_nr_deferred(long nr, struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return add_nr_deferred_memcg(nr, nid, shrinker, - sc->memcg); - - return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); -} - static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) @@ -671,413 +377,6 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, return size; } -/* - * Add a shrinker callback to be called from the vm. - */ -static int __prealloc_shrinker(struct shrinker *shrinker) -{ - unsigned int size; - int err; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - err = prealloc_memcg_shrinker(shrinker); - if (err != -ENOSYS) - return err; - - shrinker->flags &= ~SHRINKER_MEMCG_AWARE; - } - - size = sizeof(*shrinker->nr_deferred); - if (shrinker->flags & SHRINKER_NUMA_AWARE) - size *= nr_node_ids; - - shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); - if (!shrinker->nr_deferred) - return -ENOMEM; - - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __prealloc_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - - return err; -} -#else -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __prealloc_shrinker(shrinker); -} -#endif - -void free_prealloced_shrinker(struct shrinker *shrinker) -{ -#ifdef CONFIG_SHRINKER_DEBUG - kfree_const(shrinker->name); - shrinker->name = NULL; -#endif - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - down_write(&shrinker_rwsem); - unregister_memcg_shrinker(shrinker); - up_write(&shrinker_rwsem); - return; - } - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} - -void register_shrinker_prepared(struct shrinker *shrinker) -{ - down_write(&shrinker_rwsem); - list_add_tail(&shrinker->list, &shrinker_list); - shrinker->flags |= SHRINKER_REGISTERED; - shrinker_debugfs_add(shrinker); - up_write(&shrinker_rwsem); -} - -static int __register_shrinker(struct shrinker *shrinker) -{ - int err = __prealloc_shrinker(shrinker); - - if (err) - return err; - register_shrinker_prepared(shrinker); - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __register_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - return err; -} -#else -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __register_shrinker(shrinker); -} -#endif -EXPORT_SYMBOL(register_shrinker); - -/* - * Remove one - */ -void unregister_shrinker(struct shrinker *shrinker) -{ - struct dentry *debugfs_entry; - int debugfs_id; - - if (!(shrinker->flags & SHRINKER_REGISTERED)) - return; - - down_write(&shrinker_rwsem); - list_del(&shrinker->list); - shrinker->flags &= ~SHRINKER_REGISTERED; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); - up_write(&shrinker_rwsem); - - shrinker_debugfs_remove(debugfs_entry, debugfs_id); - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} -EXPORT_SYMBOL(unregister_shrinker); - -/** - * synchronize_shrinkers - Wait for all running shrinkers to complete. - * - * This is equivalent to calling unregister_shrink() and register_shrinker(), - * but atomically and with less overhead. This is useful to guarantee that all - * shrinker invocations have seen an update, before freeing memory, similar to - * rcu. - */ -void synchronize_shrinkers(void) -{ - down_write(&shrinker_rwsem); - up_write(&shrinker_rwsem); -} -EXPORT_SYMBOL(synchronize_shrinkers); - -#define SHRINK_BATCH 128 - -static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) -{ - unsigned long freed = 0; - unsigned long long delta; - long total_scan; - long freeable; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - long scanned = 0, next_deferred; - - freeable = shrinker->count_objects(shrinker, shrinkctl); - if (freeable == 0 || freeable == SHRINK_EMPTY) - return freeable; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = xchg_nr_deferred(shrinker, shrinkctl); - - if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; - do_div(delta, shrinker->seeks); - } else { - /* - * These objects don't require any IO to create. Trim - * them aggressively under memory pressure to keep - * them from causing refetches in the IO caches. - */ - delta = freeable / 2; - } - - total_scan = nr >> priority; - total_scan += delta; - total_scan = min(total_scan, (2 * freeable)); - - trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); - - /* - * Normally, we should not scan less than batch_size objects in one - * pass to avoid too frequent shrinker calls, but if the slab has less - * than batch_size objects in total and we are really tight on memory, - * we will try to reclaim all available objects, otherwise we can end - * up failing allocations although there are plenty of reclaimable - * objects spread over several slabs with usage less than the - * batch_size. - * - * We detect the "tight on memory" situations by looking at the total - * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (freeable), we must be - * scanning at high prio and therefore should try to reclaim as much as - * possible. - */ - while (total_scan >= batch_size || - total_scan >= freeable) { - unsigned long ret; - unsigned long nr_to_scan = min(batch_size, total_scan); - - shrinkctl->nr_to_scan = nr_to_scan; - shrinkctl->nr_scanned = nr_to_scan; - ret = shrinker->scan_objects(shrinker, shrinkctl); - if (ret == SHRINK_STOP) - break; - freed += ret; - - count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); - total_scan -= shrinkctl->nr_scanned; - scanned += shrinkctl->nr_scanned; - - cond_resched(); - } - - /* - * The deferred work is increased by any new work (delta) that wasn't - * done, decreased by old deferred work that was done now. - * - * And it is capped to two times of the freeable items. - */ - next_deferred = max_t(long, (nr + delta - scanned), 0); - next_deferred = min(next_deferred, (2 * freeable)); - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. - */ - new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - - trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); - return freed; -} - -#ifdef CONFIG_MEMCG -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - struct shrinker_info *info; - unsigned long ret, freed = 0; - int i; - - if (!mem_cgroup_online(memcg)) - return 0; - - if (!down_read_trylock(&shrinker_rwsem)) - return 0; - - info = shrinker_info_protected(memcg, nid); - if (unlikely(!info)) - goto unlock; - - for_each_set_bit(i, info->map, info->map_nr_max) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - struct shrinker *shrinker; - - shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { - if (!shrinker) - clear_bit(i, info->map); - continue; - } - - /* Call non-slab shrinkers even though kmem is disabled */ - if (!memcg_kmem_online() && - !(shrinker->flags & SHRINKER_NONSLAB)) - continue; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) { - clear_bit(i, info->map); - /* - * After the shrinker reported that it had no objects to - * free, but before we cleared the corresponding bit in - * the memcg shrinker map, a new object might have been - * added. To make sure, we have the bit set in this - * case, we invoke the shrinker one more time and reset - * the bit if it reports that it is not empty anymore. - * The memory barrier here pairs with the barrier in - * set_shrinker_bit(): - * - * list_lru_add() shrink_slab_memcg() - * list_add_tail() clear_bit() - * <MB> <MB> - * set_bit() do_shrink_slab() - */ - smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - else - set_shrinker_bit(memcg, nid, i); - } - freed += ret; - - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } -unlock: - up_read(&shrinker_rwsem); - return freed; -} -#else /* CONFIG_MEMCG */ -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - return 0; -} -#endif /* CONFIG_MEMCG */ - -/** - * shrink_slab - shrink slab caches - * @gfp_mask: allocation context - * @nid: node whose slab caches to target - * @memcg: memory cgroup whose slab caches to target - * @priority: the reclaim priority - * - * Call the shrink functions to age shrinkable caches. - * - * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, - * unaware shrinkers will receive a node id of 0 instead. - * - * @memcg specifies the memory cgroup to target. Unaware shrinkers - * are called only if it is the root cgroup. - * - * @priority is sc->priority, we take the number of objects and >> by priority - * in order to get the scan target. - * - * Returns the number of reclaimed slab objects. - */ -static unsigned long shrink_slab(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, - int priority) -{ - unsigned long ret, freed = 0; - struct shrinker *shrinker; - - /* - * The root memcg might be allocated even though memcg is disabled - * via "cgroup_disable=memory" boot parameter. This could make - * mem_cgroup_is_root() return false, then just run memcg slab - * shrink, but skip global shrink. This may result in premature - * oom. - */ - if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - - if (!down_read_trylock(&shrinker_rwsem)) - goto out; - - list_for_each_entry(shrinker, &shrinker_list, list) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - freed += ret; - /* - * Bail out if someone want to register a new shrinker to - * prevent the registration from being stalled for long periods - * by parallel ongoing shrinking. - */ - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } - - up_read(&shrinker_rwsem); -out: - cond_resched(); - return freed; -} - static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; @@ -1915,6 +1214,7 @@ retry: folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) @@ -2271,7 +1571,7 @@ static bool skip_cma(struct folio *folio, struct scan_control *sc) { return !current_is_kswapd() && gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && - get_pageblock_migratetype(&folio->page) == MIGRATE_CMA; + folio_migratetype(folio) == MIGRATE_CMA; } #else static bool skip_cma(struct folio *folio, struct scan_control *sc) @@ -2389,8 +1689,7 @@ move: } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, - total_scan, skipped, nr_taken, - sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru); + total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } @@ -2909,7 +2208,7 @@ enum scan_balance { SCAN_FILE, }; -static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) +static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; @@ -5010,6 +4309,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int sorted = 0; int scanned = 0; int isolated = 0; + int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); @@ -5023,7 +4323,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); - int skipped = 0; + int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; @@ -5045,16 +4345,17 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, isolated += delta; } else { list_move(&folio->lru, &moved); - skipped += delta; + skipped_zone += delta; } - if (!--remaining || max(isolated, skipped) >= MIN_LRU_BATCH) + if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } - if (skipped) { + if (skipped_zone) { list_splice(&moved, head); - __count_zid_vm_events(PGSCAN_SKIP, zone, skipped); + __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); + skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) @@ -5069,6 +4370,9 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); + trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, + scanned, skipped, isolated, + type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); /* * There might not be eligible folios due to reclaim_idx. Check the @@ -5199,6 +4503,9 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr_reclaimed += reclaimed; + trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, + scanned, reclaimed, &stat, sc->priority, + type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { if (!folio_evictable(folio)) { @@ -6570,7 +5877,7 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - prepare_scan_count(pgdat, sc); + prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); @@ -7927,8 +7234,9 @@ void __meminit kswapd_run(int nid) pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ + pr_err("Failed to start kswapd on node %d，ret=%ld\n", + nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); - pr_err("Failed to start kswapd on node %d\n", nid); pgdat->kswapd = NULL; } } @@ -8061,6 +7369,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in cond_resched(); psi_memstall_enter(&pflags); + delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP @@ -8083,6 +7392,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); + delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index 00e81e99c6..359460deb3 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -559,8 +559,10 @@ static inline void mod_zone_state(struct zone *zone, { struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; - long o, n, t, z; + long n, t, z; + s8 o; + o = this_cpu_read(*p); do { z = 0; /* overflow to zone counters */ @@ -576,8 +578,7 @@ static inline void mod_zone_state(struct zone *zone, */ t = this_cpu_read(pcp->stat_threshold); - o = this_cpu_read(*p); - n = delta + o; + n = delta + (long)o; if (abs(n) > t) { int os = overstep_mode * (t >> 1) ; @@ -586,7 +587,7 @@ static inline void mod_zone_state(struct zone *zone, z = n + os; n = -os; } - } while (this_cpu_cmpxchg(*p, o, n) != o); + } while (!this_cpu_try_cmpxchg(*p, &o, n)); if (z) zone_page_state_add(z, zone, item); @@ -616,7 +617,8 @@ static inline void mod_node_state(struct pglist_data *pgdat, { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; - long o, n, t, z; + long n, t, z; + s8 o; if (vmstat_item_in_bytes(item)) { /* @@ -629,6 +631,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, delta >>= PAGE_SHIFT; } + o = this_cpu_read(*p); do { z = 0; /* overflow to node counters */ @@ -644,8 +647,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, */ t = this_cpu_read(pcp->stat_threshold); - o = this_cpu_read(*p); - n = delta + o; + n = delta + (long)o; if (abs(n) > t) { int os = overstep_mode * (t >> 1) ; @@ -654,7 +656,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, z = n + os; n = -os; } - } while (this_cpu_cmpxchg(*p, o, n) != o); + } while (!this_cpu_try_cmpxchg(*p, &o, n)); if (z) node_page_state_add(z, pgdat, item); @@ -814,9 +816,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets) for_each_populated_zone(zone) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; -#ifdef CONFIG_NUMA struct per_cpu_pages __percpu *pcp = zone->per_cpu_pageset; -#endif for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { int v; @@ -832,10 +832,12 @@ static int refresh_cpu_vm_stats(bool do_pagesets) #endif } } -#ifdef CONFIG_NUMA if (do_pagesets) { cond_resched(); + + changes += decay_pcp_high(zone, this_cpu_ptr(pcp)); +#ifdef CONFIG_NUMA /* * Deal with draining the remote pageset of this * processor @@ -855,15 +857,17 @@ static int refresh_cpu_vm_stats(bool do_pagesets) continue; } - if (__this_cpu_dec_return(pcp->expire)) + if (__this_cpu_dec_return(pcp->expire)) { + changes++; continue; + } if (__this_cpu_read(pcp->count)) { drain_zone_pages(zone, this_cpu_ptr(pcp)); changes++; } - } #endif + } } for_each_online_pgdat(pgdat) { diff --git a/mm/workingset.c b/mm/workingset.c index 2559a1f2fc..33baad2032 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -763,13 +763,6 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, NULL); } -static struct shrinker workingset_shadow_shrinker = { - .count_objects = count_shadow_nodes, - .scan_objects = scan_shadow_nodes, - .seeks = 0, /* ->count reports only fully expendable nodes */ - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, -}; - /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. @@ -778,9 +771,10 @@ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { + struct shrinker *workingset_shadow_shrinker; unsigned int timestamp_bits; unsigned int max_order; - int ret; + int ret = -ENOMEM; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* @@ -797,17 +791,26 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); - if (ret) + workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE, + "mm-shadow"); + if (!workingset_shadow_shrinker) goto err; + ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, - &workingset_shadow_shrinker); + workingset_shadow_shrinker); if (ret) goto err_list_lru; - register_shrinker_prepared(&workingset_shadow_shrinker); + + workingset_shadow_shrinker->count_objects = count_shadow_nodes; + workingset_shadow_shrinker->scan_objects = scan_shadow_nodes; + /* ->count reports only fully expendable nodes */ + workingset_shadow_shrinker->seeks = 0; + + shrinker_register(workingset_shadow_shrinker); return 0; err_list_lru: - free_prealloced_shrinker(&workingset_shadow_shrinker); + shrinker_free(workingset_shadow_shrinker); err: return ret; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b58f957429..b1c0dad7f4 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -229,7 +229,7 @@ struct zs_pool { struct zs_pool_stats stats; /* Compact classes */ - struct shrinker shrinker; + struct shrinker *shrinker; #ifdef CONFIG_ZSMALLOC_STAT struct dentry *stat_dentry; @@ -1839,7 +1839,7 @@ static int zs_page_migrate(struct page *newpage, struct page *page, * Here, any user cannot access all objects in the zspage so let's move. */ d_addr = kmap_atomic(newpage); - memcpy(d_addr, s_addr, PAGE_SIZE); + copy_page(d_addr, s_addr); kunmap_atomic(d_addr); for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE; @@ -2086,8 +2086,7 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long pages_freed; - struct zs_pool *pool = container_of(shrinker, struct zs_pool, - shrinker); + struct zs_pool *pool = shrinker->private_data; /* * Compact classes and calculate compaction delta. @@ -2105,8 +2104,7 @@ static unsigned long zs_shrinker_count(struct shrinker *shrinker, int i; struct size_class *class; unsigned long pages_to_free = 0; - struct zs_pool *pool = container_of(shrinker, struct zs_pool, - shrinker); + struct zs_pool *pool = shrinker->private_data; for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; @@ -2121,18 +2119,23 @@ static unsigned long zs_shrinker_count(struct shrinker *shrinker, static void zs_unregister_shrinker(struct zs_pool *pool) { - unregister_shrinker(&pool->shrinker); + shrinker_free(pool->shrinker); } static int zs_register_shrinker(struct zs_pool *pool) { - pool->shrinker.scan_objects = zs_shrinker_scan; - pool->shrinker.count_objects = zs_shrinker_count; - pool->shrinker.batch = 0; - pool->shrinker.seeks = DEFAULT_SEEKS; + pool->shrinker = shrinker_alloc(0, "mm-zspool:%s", pool->name); + if (!pool->shrinker) + return -ENOMEM; + + pool->shrinker->scan_objects = zs_shrinker_scan; + pool->shrinker->count_objects = zs_shrinker_count; + pool->shrinker->batch = 0; + pool->shrinker->private_data = pool; - return register_shrinker(&pool->shrinker, "mm-zspool:%s", - pool->name); + shrinker_register(pool->shrinker); + + return 0; } static int calculate_zspage_chain_size(int class_size) diff --git a/mm/zswap.c b/mm/zswap.c index 37d2b1cb2e..870fd6f5a5 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -24,6 +24,7 @@ #include <linux/swap.h> #include <linux/crypto.h> #include <linux/scatterlist.h> +#include <linux/mempolicy.h> #include <linux/mempool.h> #include <linux/zpool.h> #include <crypto/acompress.h> @@ -61,6 +62,8 @@ static u64 zswap_pool_limit_hit; static u64 zswap_written_back_pages; /* Store failed due to a reclaim failure after pool limit was reached */ static u64 zswap_reject_reclaim_fail; +/* Store failed due to compression algorithm failure */ +static u64 zswap_reject_compress_fail; /* Compressed page was too big for the allocator to (optimally) store */ static u64 zswap_reject_compress_poor; /* Store failed because underlying allocator could not get memory */ @@ -1057,6 +1060,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, { swp_entry_t swpentry = entry->swpentry; struct page *page; + struct mempolicy *mpol; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; struct zpool *pool = zswap_find_zpool(entry); @@ -1075,8 +1079,9 @@ static int zswap_writeback_entry(struct zswap_entry *entry, } /* try to allocate swap cache page */ - page = __read_swap_cache_async(swpentry, GFP_KERNEL, NULL, 0, - &page_was_allocated); + mpol = get_task_policy(current); + page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, + NO_INTERLEAVE_INDEX, &page_was_allocated); if (!page) { ret = -ENOMEM; goto fail; @@ -1100,6 +1105,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry, if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(page_folio(page)); + unlock_page(page); + put_page(page); ret = -ENOMEM; goto fail; } @@ -1215,7 +1222,7 @@ bool zswap_store(struct folio *folio) if (folio_test_large(folio)) return false; - if (!zswap_enabled || !tree) + if (!tree) return false; /* @@ -1231,6 +1238,9 @@ bool zswap_store(struct folio *folio) } spin_unlock(&tree->lock); + if (!zswap_enabled) + return false; + /* * XXX: zswap reclaim does not work with cgroups yet. Without a * cgroup-aware entry LRU, we will push out entries system-wide based on @@ -1309,8 +1319,10 @@ bool zswap_store(struct folio *folio) ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); dlen = acomp_ctx->req->dlen; - if (ret) + if (ret) { + zswap_reject_compress_fail++; goto put_dstmem; + } /* store */ zpool = zswap_find_zpool(entry); @@ -1550,6 +1562,8 @@ static int zswap_debugfs_init(void) zswap_debugfs_root, &zswap_reject_alloc_fail); debugfs_create_u64("reject_kmemcache_fail", 0444, zswap_debugfs_root, &zswap_reject_kmemcache_fail); + debugfs_create_u64("reject_compress_fail", 0444, + zswap_debugfs_root, &zswap_reject_compress_fail); debugfs_create_u64("reject_compress_poor", 0444, zswap_debugfs_root, &zswap_reject_compress_poor); debugfs_create_u64("written_back_pages", 0444, |