diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-06 14:08:17 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-06 14:08:17 -0700 |
commit | 512b7931ad0561ffe14265f9ff554a3c081b476b (patch) | |
tree | a94450d08468e094d2d92a495de4650faab09c1f /mm | |
parent | fe91c4725aeed35023ba4f7a1e1adfebb6878c23 (diff) | |
parent | 658f9ae761b5965893727dd4edcdad56e5a439bb (diff) | |
download | linux-stable-512b7931ad0561ffe14265f9ff554a3c081b476b.tar.gz linux-stable-512b7931ad0561ffe14265f9ff554a3c081b476b.tar.bz2 linux-stable-512b7931ad0561ffe14265f9ff554a3c081b476b.zip |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
"257 patches.
Subsystems affected by this patch series: scripts, ocfs2, vfs, and
mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
cleanups, kfence, and damon)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
mm/damon: remove return value from before_terminate callback
mm/damon: fix a few spelling mistakes in comments and a pr_debug message
mm/damon: simplify stop mechanism
Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
Docs/admin-guide/mm/damon/start: simplify the content
Docs/admin-guide/mm/damon/start: fix a wrong link
Docs/admin-guide/mm/damon/start: fix wrong example commands
mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
mm/damon: remove unnecessary variable initialization
Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
selftests/damon: support watermarks
mm/damon/dbgfs: support watermarks
mm/damon/schemes: activate schemes based on a watermarks mechanism
tools/selftests/damon: update for regions prioritization of schemes
mm/damon/dbgfs: support prioritization weights
mm/damon/vaddr,paddr: support pageout prioritization
mm/damon/schemes: prioritize regions within the quotas
mm/damon/selftests: support schemes quotas
mm/damon/dbgfs: support quotas of schemes
...
Diffstat (limited to 'mm')
65 files changed, 3682 insertions, 1136 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index d16ba9249bc5..ae1f151c2924 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -123,15 +123,11 @@ config ARCH_ENABLE_MEMORY_HOTPLUG config MEMORY_HOTPLUG bool "Allow for memory hot-add" select MEMORY_ISOLATION - depends on SPARSEMEM || X86_64_ACPI_NUMA + depends on SPARSEMEM depends on ARCH_ENABLE_MEMORY_HOTPLUG - depends on 64BIT || BROKEN + depends on 64BIT select NUMA_KEEP_MEMINFO if NUMA -config MEMORY_HOTPLUG_SPARSE - def_bool y - depends on SPARSEMEM && MEMORY_HOTPLUG - config MEMORY_HOTPLUG_DEFAULT_ONLINE bool "Online the newly added memory blocks by default" depends on MEMORY_HOTPLUG @@ -371,7 +367,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT select COMPACTION select XARRAY_MULTI help diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c878d995af06..1eead4761011 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -292,8 +292,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, memset(wb, 0, sizeof(*wb)); - if (wb != &bdi->wb) - bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); @@ -317,7 +315,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, err = fprop_local_init_percpu(&wb->completions, gfp); if (err) - goto out_put_bdi; + return err; for (i = 0; i < NR_WB_STAT_ITEMS; i++) { err = percpu_counter_init(&wb->stat[i], 0, gfp); @@ -331,9 +329,6 @@ out_destroy_stat: while (i--) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); -out_put_bdi: - if (wb != &bdi->wb) - bdi_put(bdi); return err; } @@ -374,8 +369,6 @@ static void wb_exit(struct bdi_writeback *wb) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); - if (wb != &wb->bdi->wb) - bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -398,6 +391,7 @@ static void cgwb_release_workfn(struct work_struct *work) struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); + struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -417,6 +411,7 @@ static void cgwb_release_workfn(struct work_struct *work) percpu_ref_exit(&wb->refcnt); wb_exit(wb); + bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); } @@ -498,6 +493,7 @@ static int cgwb_create(struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); + bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and @@ -529,6 +525,7 @@ static int cgwb_create(struct backing_dev_info *bdi, goto out_put; err_fprop_exit: + bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); @@ -959,14 +956,14 @@ void bdi_unregister(struct backing_dev_info *bdi) bdi->owner = NULL; } } +EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); - if (test_bit(WB_registered, &bdi->wb.state)) - bdi_unregister(bdi); + WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); @@ -1058,51 +1055,3 @@ long congestion_wait(int sync, long timeout) return ret; } EXPORT_SYMBOL(congestion_wait); - -/** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * In the event of a congested backing_dev (any backing_dev) this waits - * for up to @timeout jiffies for either a BDI to exit congestion of the - * given @sync queue or a write to complete. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function - * returned. return_value == timeout implies the function did not sleep. - */ -long wait_iff_congested(int sync, long timeout) -{ - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - /* - * If there is no congestion, yield if necessary instead - * of sleeping on the congestion queue - */ - if (atomic_read(&nr_wb_congested[sync]) == 0) { - cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); - if (ret < 0) - ret = 0; - - goto out; - } - - /* Sleep until uncongested or a write happens */ - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - -out: - trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; -} -EXPORT_SYMBOL(wait_iff_congested); @@ -378,7 +378,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, return 0; free_mem: - memblock_free(base, size); + memblock_phys_free(base, size); err: pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); return ret; @@ -524,6 +524,25 @@ out: return page; } +bool cma_pages_valid(struct cma *cma, const struct page *pages, + unsigned long count) +{ + unsigned long pfn; + + if (!cma || !pages) + return false; + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) { + pr_debug("%s(page %p, count %lu)\n", __func__, + (void *)pages, count); + return false; + } + + return true; +} + /** * cma_release() - release allocated pages * @cma: Contiguous memory region for which the allocation is performed. @@ -539,16 +558,13 @@ bool cma_release(struct cma *cma, const struct page *pages, { unsigned long pfn; - if (!cma || !pages) + if (!cma_pages_valid(cma, pages, count)) return false; pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); - if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) - return false; - VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); free_contig_range(pfn, count); diff --git a/mm/compaction.c b/mm/compaction.c index fbc60f964c38..6e446094ce90 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -761,6 +761,8 @@ isolate_freepages_range(struct compact_control *cc, /* Similar to reclaim, but different enough that they don't share logic */ static bool too_many_isolated(pg_data_t *pgdat) { + bool too_many; + unsigned long active, inactive, isolated; inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + @@ -770,7 +772,11 @@ static bool too_many_isolated(pg_data_t *pgdat) isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + node_page_state(pgdat, NR_ISOLATED_ANON); - return isolated > (inactive + active) / 2; + too_many = isolated > (inactive + active) / 2; + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /** @@ -822,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); if (fatal_signal_pending(current)) return -EINTR; diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 37024798a97c..5bcf05851ad0 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -30,7 +30,15 @@ config DAMON_VADDR select PAGE_IDLE_FLAG help This builds the default data access monitoring primitives for DAMON - that works for virtual address spaces. + that work for virtual address spaces. + +config DAMON_PADDR + bool "Data access monitoring primitives for the physical address space" + depends on DAMON && MMU + select PAGE_IDLE_FLAG + help + This builds the default data access monitoring primitives for DAMON + that works for the physical address space. config DAMON_VADDR_KUNIT_TEST bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS @@ -46,7 +54,7 @@ config DAMON_VADDR_KUNIT_TEST config DAMON_DBGFS bool "DAMON debugfs interface" - depends on DAMON_VADDR && DEBUG_FS + depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS help This builds the debugfs interface for DAMON. The user space admins can use the interface for arbitrary data access monitoring. @@ -65,4 +73,16 @@ config DAMON_DBGFS_KUNIT_TEST If unsure, say N. +config DAMON_RECLAIM + bool "Build DAMON-based reclaim (DAMON_RECLAIM)" + depends on DAMON_PADDR + help + This builds the DAMON-based reclamation subsystem. It finds pages + that not accessed for a long time (cold) using DAMON and reclaim + those. + + This is suggested to be used as a proactive and lightweight + reclamation under light memory pressure, while the traditional page + scanning-based reclamation is used for heavy pressure. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index fed4be3bace3..f7d5ac377a2b 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DAMON) := core.o -obj-$(CONFIG_DAMON_VADDR) += vaddr.o +obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o +obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o +obj-$(CONFIG_DAMON_RECLAIM) += reclaim.o diff --git a/mm/damon/core.c b/mm/damon/core.c index 30e9211f494a..c381b3c525d0 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -10,8 +10,10 @@ #include <linux/damon.h> #include <linux/delay.h> #include <linux/kthread.h> +#include <linux/mm.h> #include <linux/random.h> #include <linux/slab.h> +#include <linux/string.h> #define CREATE_TRACE_POINTS #include <trace/events/damon.h> @@ -45,6 +47,9 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) region->nr_accesses = 0; INIT_LIST_HEAD(®ion->list); + region->age = 0; + region->last_nr_accesses = 0; + return region; } @@ -82,6 +87,74 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t) damon_free_region(r); } +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks) +{ + struct damos *scheme; + + scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); + if (!scheme) + return NULL; + scheme->min_sz_region = min_sz_region; + scheme->max_sz_region = max_sz_region; + scheme->min_nr_accesses = min_nr_accesses; + scheme->max_nr_accesses = max_nr_accesses; + scheme->min_age_region = min_age_region; + scheme->max_age_region = max_age_region; + scheme->action = action; + scheme->stat_count = 0; + scheme->stat_sz = 0; + INIT_LIST_HEAD(&scheme->list); + + scheme->quota.ms = quota->ms; + scheme->quota.sz = quota->sz; + scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.weight_sz = quota->weight_sz; + scheme->quota.weight_nr_accesses = quota->weight_nr_accesses; + scheme->quota.weight_age = quota->weight_age; + scheme->quota.total_charged_sz = 0; + scheme->quota.total_charged_ns = 0; + scheme->quota.esz = 0; + scheme->quota.charged_sz = 0; + scheme->quota.charged_from = 0; + scheme->quota.charge_target_from = NULL; + scheme->quota.charge_addr_from = 0; + + scheme->wmarks.metric = wmarks->metric; + scheme->wmarks.interval = wmarks->interval; + scheme->wmarks.high = wmarks->high; + scheme->wmarks.mid = wmarks->mid; + scheme->wmarks.low = wmarks->low; + scheme->wmarks.activated = true; + + return scheme; +} + +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) +{ + list_add_tail(&s->list, &ctx->schemes); +} + +static void damon_del_scheme(struct damos *s) +{ + list_del(&s->list); +} + +static void damon_free_scheme(struct damos *s) +{ + kfree(s); +} + +void damon_destroy_scheme(struct damos *s) +{ + damon_del_scheme(s); + damon_free_scheme(s); +} + /* * Construct a damon_target struct * @@ -107,6 +180,11 @@ void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) list_add_tail(&t->list, &ctx->adaptive_targets); } +bool damon_targets_empty(struct damon_ctx *ctx) +{ + return list_empty(&ctx->adaptive_targets); +} + static void damon_del_target(struct damon_target *t) { list_del(&t->list); @@ -153,6 +231,7 @@ struct damon_ctx *damon_new_ctx(void) ctx->max_nr_regions = 1000; INIT_LIST_HEAD(&ctx->adaptive_targets); + INIT_LIST_HEAD(&ctx->schemes); return ctx; } @@ -172,7 +251,13 @@ static void damon_destroy_targets(struct damon_ctx *ctx) void damon_destroy_ctx(struct damon_ctx *ctx) { + struct damos *s, *next_s; + damon_destroy_targets(ctx); + + damon_for_each_scheme_safe(s, next_s, ctx) + damon_destroy_scheme(s); + kfree(ctx); } @@ -248,6 +333,30 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, } /** + * damon_set_schemes() - Set data access monitoring based operation schemes. + * @ctx: monitoring context + * @schemes: array of the schemes + * @nr_schemes: number of entries in @schemes + * + * This function should not be called while the kdamond of the context is + * running. + * + * Return: 0 if success, or negative error code otherwise. + */ +int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, + ssize_t nr_schemes) +{ + struct damos *s, *next; + ssize_t i; + + damon_for_each_scheme_safe(s, next, ctx) + damon_destroy_scheme(s); + for (i = 0; i < nr_schemes; i++) + damon_add_scheme(ctx, schemes[i]); + return 0; +} + +/** * damon_nr_running_ctxs() - Return number of currently running contexts. */ int damon_nr_running_ctxs(void) @@ -281,17 +390,6 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) return sz; } -static bool damon_kdamond_running(struct damon_ctx *ctx) -{ - bool running; - - mutex_lock(&ctx->kdamond_lock); - running = ctx->kdamond != NULL; - mutex_unlock(&ctx->kdamond_lock); - - return running; -} - static int kdamond_fn(void *data); /* @@ -309,12 +407,11 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; - ctx->kdamond_stop = false; ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); - ctx->kdamond = 0; + ctx->kdamond = NULL; } } mutex_unlock(&ctx->kdamond_lock); @@ -365,13 +462,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs) */ static int __damon_stop(struct damon_ctx *ctx) { + struct task_struct *tsk; + mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ctx->kdamond_stop = true; + tsk = ctx->kdamond; + if (tsk) { + get_task_struct(tsk); mutex_unlock(&ctx->kdamond_lock); - while (damon_kdamond_running(ctx)) - usleep_range(ctx->sample_interval, - ctx->sample_interval * 2); + kthread_stop(tsk); + put_task_struct(tsk); return 0; } mutex_unlock(&ctx->kdamond_lock); @@ -444,11 +543,203 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) damon_for_each_region(r, t) { trace_damon_aggregated(t, r, damon_nr_regions(t)); + r->last_nr_accesses = r->nr_accesses; r->nr_accesses = 0; } } } +static void damon_split_region_at(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + unsigned long sz_r); + +static bool __damos_valid_target(struct damon_region *r, struct damos *s) +{ + unsigned long sz; + + sz = r->ar.end - r->ar.start; + return s->min_sz_region <= sz && sz <= s->max_sz_region && + s->min_nr_accesses <= r->nr_accesses && + r->nr_accesses <= s->max_nr_accesses && + s->min_age_region <= r->age && r->age <= s->max_age_region; +} + +static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t, + struct damon_region *r, struct damos *s) +{ + bool ret = __damos_valid_target(r, s); + + if (!ret || !s->quota.esz || !c->primitive.get_scheme_score) + return ret; + + return c->primitive.get_scheme_score(c, t, r, s) >= s->quota.min_score; +} + +static void damon_do_apply_schemes(struct damon_ctx *c, + struct damon_target *t, + struct damon_region *r) +{ + struct damos *s; + + damon_for_each_scheme(s, c) { + struct damos_quota *quota = &s->quota; + unsigned long sz = r->ar.end - r->ar.start; + struct timespec64 begin, end; + + if (!s->wmarks.activated) + continue; + + /* Check the quota */ + if (quota->esz && quota->charged_sz >= quota->esz) + continue; + + /* Skip previously charged regions */ + if (quota->charge_target_from) { + if (t != quota->charge_target_from) + continue; + if (r == damon_last_region(t)) { + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + continue; + } + if (quota->charge_addr_from && + r->ar.end <= quota->charge_addr_from) + continue; + + if (quota->charge_addr_from && r->ar.start < + quota->charge_addr_from) { + sz = ALIGN_DOWN(quota->charge_addr_from - + r->ar.start, DAMON_MIN_REGION); + if (!sz) { + if (r->ar.end - r->ar.start <= + DAMON_MIN_REGION) + continue; + sz = DAMON_MIN_REGION; + } + damon_split_region_at(c, t, r, sz); + r = damon_next_region(r); + sz = r->ar.end - r->ar.start; + } + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + } + + if (!damos_valid_target(c, t, r, s)) + continue; + + /* Apply the scheme */ + if (c->primitive.apply_scheme) { + if (quota->esz && + quota->charged_sz + sz > quota->esz) { + sz = ALIGN_DOWN(quota->esz - quota->charged_sz, + DAMON_MIN_REGION); + if (!sz) + goto update_stat; + damon_split_region_at(c, t, r, sz); + } + ktime_get_coarse_ts64(&begin); + c->primitive.apply_scheme(c, t, r, s); + ktime_get_coarse_ts64(&end); + quota->total_charged_ns += timespec64_to_ns(&end) - + timespec64_to_ns(&begin); + quota->charged_sz += sz; + if (quota->esz && quota->charged_sz >= quota->esz) { + quota->charge_target_from = t; + quota->charge_addr_from = r->ar.end + 1; + } + } + if (s->action != DAMOS_STAT) + r->age = 0; + +update_stat: + s->stat_count++; + s->stat_sz += sz; + } +} + +/* Shouldn't be called if quota->ms and quota->sz are zero */ +static void damos_set_effective_quota(struct damos_quota *quota) +{ + unsigned long throughput; + unsigned long esz; + + if (!quota->ms) { + quota->esz = quota->sz; + return; + } + + if (quota->total_charged_ns) + throughput = quota->total_charged_sz * 1000000 / + quota->total_charged_ns; + else + throughput = PAGE_SIZE * 1024; + esz = throughput * quota->ms; + + if (quota->sz && quota->sz < esz) + esz = quota->sz; + quota->esz = esz; +} + +static void kdamond_apply_schemes(struct damon_ctx *c) +{ + struct damon_target *t; + struct damon_region *r, *next_r; + struct damos *s; + + damon_for_each_scheme(s, c) { + struct damos_quota *quota = &s->quota; + unsigned long cumulated_sz; + unsigned int score, max_score = 0; + + if (!s->wmarks.activated) + continue; + + if (!quota->ms && !quota->sz) + continue; + + /* New charge window starts */ + if (time_after_eq(jiffies, quota->charged_from + + msecs_to_jiffies( + quota->reset_interval))) { + quota->total_charged_sz += quota->charged_sz; + quota->charged_from = jiffies; + quota->charged_sz = 0; + damos_set_effective_quota(quota); + } + + if (!c->primitive.get_scheme_score) + continue; + + /* Fill up the score histogram */ + memset(quota->histogram, 0, sizeof(quota->histogram)); + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + if (!__damos_valid_target(r, s)) + continue; + score = c->primitive.get_scheme_score( + c, t, r, s); + quota->histogram[score] += + r->ar.end - r->ar.start; + if (score > max_score) + max_score = score; + } + } + + /* Set the min score limit */ + for (cumulated_sz = 0, score = max_score; ; score--) { + cumulated_sz += quota->histogram[score]; + if (cumulated_sz >= quota->esz || !score) + break; + } + quota->min_score = score; + } + + damon_for_each_target(t, c) { + damon_for_each_region_safe(r, next_r, t) + damon_do_apply_schemes(c, t, r); + } +} + #define sz_damon_region(r) (r->ar.end - r->ar.start) /* @@ -461,6 +752,7 @@ 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->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r); l->ar.end = r->ar.end; damon_destroy_region(r, t); } @@ -480,6 +772,11 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, struct damon_region *r, *prev = NULL, *next; damon_for_each_region_safe(r, next, t) { + if (diff_of(r->nr_accesses, r->last_nr_accesses) > thres) + r->age = 0; + else + r->age++; + if (prev && prev->ar.end == r->ar.start && diff_of(prev->nr_accesses, r->nr_accesses) <= thres && sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) @@ -527,6 +824,9 @@ static void damon_split_region_at(struct damon_ctx *ctx, r->ar.end = new->ar.start; + new->age = r->age; + new->last_nr_accesses = r->last_nr_accesses; + damon_insert_region(new, r, damon_next_region(r), t); } @@ -615,12 +915,8 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx) static bool kdamond_need_stop(struct damon_ctx *ctx) { struct damon_target *t; - bool stop; - mutex_lock(&ctx->kdamond_lock); - stop = ctx->kdamond_stop; - mutex_unlock(&ctx->kdamond_lock); - if (stop) + if (kthread_should_stop()) return true; if (!ctx->primitive.target_valid) @@ -634,11 +930,81 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) return true; } -static void set_kdamond_stop(struct damon_ctx *ctx) +static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric) { - mutex_lock(&ctx->kdamond_lock); - ctx->kdamond_stop = true; - mutex_unlock(&ctx->kdamond_lock); + struct sysinfo i; + + switch (metric) { + case DAMOS_WMARK_FREE_MEM_RATE: + si_meminfo(&i); + return i.freeram * 1000 / i.totalram; + default: + break; + } + return -EINVAL; +} + +/* + * Returns zero if the scheme is active. Else, returns time to wait for next + * watermark check in micro-seconds. + */ +static unsigned long damos_wmark_wait_us(struct damos *scheme) +{ + unsigned long metric; + + if (scheme->wmarks.metric == DAMOS_WMARK_NONE) + return 0; + + metric = damos_wmark_metric_value(scheme->wmarks.metric); + /* higher than high watermark or lower than low watermark */ + if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) { + if (scheme->wmarks.activated) + pr_debug("deactivate a scheme (%d) for %s wmark\n", + scheme->action, + metric > scheme->wmarks.high ? + "high" : "low"); + scheme->wmarks.activated = false; + return scheme->wmarks.interval; + } + + /* inactive and higher than middle watermark */ + if ((scheme->wmarks.high >= metric && metric >= scheme->wmarks.mid) && + !scheme->wmarks.activated) + return scheme->wmarks.interval; + + if (!scheme->wmarks.activated) + pr_debug("activate a scheme (%d)\n", scheme->action); + scheme->wmarks.activated = true; + return 0; +} + +static void kdamond_usleep(unsigned long usecs) +{ + if (usecs > 100 * 1000) + schedule_timeout_interruptible(usecs_to_jiffies(usecs)); + else + usleep_range(usecs, usecs + 1); +} + +/* Returns negative error code if it's not activated but should return */ +static int kdamond_wait_activation(struct damon_ctx *ctx) +{ + struct damos *s; + unsigned long wait_time; + unsigned long min_wait_time = 0; + + while (!kdamond_need_stop(ctx)) { + damon_for_each_scheme(s, ctx) { + wait_time = damos_wmark_wait_us(s); + if (!min_wait_time || wait_time < min_wait_time) + min_wait_time = wait_time; + } + if (!min_wait_time) + return 0; + + kdamond_usleep(min_wait_time); + } + return -EBUSY; } /* @@ -651,24 +1017,26 @@ static int kdamond_fn(void *data) struct damon_region *r, *next; unsigned int max_nr_accesses = 0; unsigned long sz_limit = 0; + bool done = false; - mutex_lock(&ctx->kdamond_lock); - pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); - mutex_unlock(&ctx->kdamond_lock); + pr_debug("kdamond (%d) starts\n", current->pid); if (ctx->primitive.init) ctx->primitive.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) - set_kdamond_stop(ctx); + done = true; sz_limit = damon_region_sz_limit(ctx); - while (!kdamond_need_stop(ctx)) { + while (!kdamond_need_stop(ctx) && !done) { + if (kdamond_wait_activation(ctx)) + continue; + if (ctx->primitive.prepare_access_checks) ctx->primitive.prepare_access_checks(ctx); if (ctx->callback.after_sampling && ctx->callback.after_sampling(ctx)) - set_kdamond_stop(ctx); + done = true; usleep_range(ctx->sample_interval, ctx->sample_interval + 1); @@ -681,7 +1049,8 @@ static int kdamond_fn(void *data) sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) - set_kdamond_stop(ctx); + done = true; + kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->primitive.reset_aggregated) @@ -699,13 +1068,12 @@ static int kdamond_fn(void *data) damon_destroy_region(r, t); } - if (ctx->callback.before_terminate && - ctx->callback.before_terminate(ctx)) - set_kdamond_stop(ctx); + if (ctx->callback.before_terminate) + ctx->callback.before_terminate(ctx); if (ctx->primitive.cleanup) ctx->primitive.cleanup(ctx); - pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid); + pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); @@ -714,7 +1082,7 @@ static int kdamond_fn(void *data) nr_running_ctxs--; mutex_unlock(&damon_lock); - do_exit(0); + return 0; } #include "core-test.h" diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h index 4eddcfa73996..86b9f9528231 100644 --- a/mm/damon/dbgfs-test.h +++ b/mm/damon/dbgfs-test.h @@ -109,9 +109,63 @@ static void damon_dbgfs_test_set_targets(struct kunit *test) dbgfs_destroy_ctx(ctx); } +static void damon_dbgfs_test_set_init_regions(struct kunit *test) +{ + struct damon_ctx *ctx = damon_new_ctx(); + unsigned long ids[] = {1, 2, 3}; + /* Each line represents one region in ``<target id> <start> <end>`` */ + char * const valid_inputs[] = {"2 10 20\n 2 20 30\n2 35 45", + "2 10 20\n", + "2 10 20\n1 39 59\n1 70 134\n 2 20 25\n", + ""}; + /* Reading the file again will show sorted, clean output */ + char * const valid_expects[] = {"2 10 20\n2 20 30\n2 35 45\n", + "2 10 20\n", + "1 39 59\n1 70 134\n2 10 20\n2 20 25\n", + ""}; + char * const invalid_inputs[] = {"4 10 20\n", /* target not exists */ + "2 10 20\n 2 14 26\n", /* regions overlap */ + "1 10 20\n2 30 40\n 1 5 8"}; /* not sorted by address */ + char *input, *expect; + int i, rc; + char buf[256]; + + damon_set_targets(ctx, ids, 3); + + /* Put valid inputs and check the results */ + for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) { + input = valid_inputs[i]; + expect = valid_expects[i]; + + rc = set_init_regions(ctx, input, strnlen(input, 256)); + KUNIT_EXPECT_EQ(test, rc, 0); + + memset(buf, 0, 256); + sprint_init_regions(ctx, buf, 256); + + KUNIT_EXPECT_STREQ(test, (char *)buf, expect); + } + /* Put invalid inputs and check the return error code */ + for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) { + input = invalid_inputs[i]; + pr_info("input: %s\n", input); + rc = set_init_regions(ctx, input, strnlen(input, 256)); + KUNIT_EXPECT_EQ(test, rc, -EINVAL); + + memset(buf, 0, 256); + sprint_init_regions(ctx, buf, 256); + + KUNIT_EXPECT_STREQ(test, (char *)buf, ""); + } + + damon_set_targets(ctx, NULL, 0); + damon_destroy_ctx(ctx); +} + static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_dbgfs_test_str_to_target_ids), KUNIT_CASE(damon_dbgfs_test_set_targets), + KUNIT_CASE(damon_dbgfs_test_set_init_regions), {}, }; diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index faee070977d8..eccc14b34901 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -69,8 +69,7 @@ static ssize_t dbgfs_attrs_write(struct file *file, struct damon_ctx *ctx = file->private_data; unsigned long s, a, r, minr, maxr; char *kbuf; - ssize_t ret = count; - int err; + ssize_t ret; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -88,11 +87,182 @@ static ssize_t dbgfs_attrs_write(struct file *file, goto unlock_out; } - err = damon_set_attrs(ctx, s, a, r, minr, maxr); - if (err) - ret = err; + ret = damon_set_attrs(ctx, s, a, r, minr, maxr); + if (!ret) + ret = count; +unlock_out: + mutex_unlock(&ctx->kdamond_lock); +out: + kfree(kbuf); + return ret; +} + +static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) +{ + struct damos *s; + int written = 0; + int rc; + + damon_for_each_scheme(s, c) { + rc = scnprintf(&buf[written], len - written, + "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu\n", + s->min_sz_region, s->max_sz_region, + s->min_nr_accesses, s->max_nr_accesses, + s->min_age_region, s->max_age_region, + s->action, + s->quota.ms, s->quota.sz, + s->quota.reset_interval, + s->quota.weight_sz, + s->quota.weight_nr_accesses, + s->quota.weight_age, + s->wmarks.metric, s->wmarks.interval, + s->wmarks.high, s->wmarks.mid, s->wmarks.low, + s->stat_count, s->stat_sz); + if (!rc) + return -ENOMEM; + + written += rc; + } + return written; +} + +static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t len; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + mutex_lock(&ctx->kdamond_lock); + len = sprint_schemes(ctx, kbuf, count); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + goto out; + len = simple_read_from_buffer(buf, count, ppos, kbuf, len); + +out: + kfree(kbuf); + return len; +} + +static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes) +{ + ssize_t i; + + for (i = 0; i < nr_schemes; i++) + kfree(schemes[i]); + kfree(schemes); +} + +static bool damos_action_valid(int action) +{ + switch (action) { + case DAMOS_WILLNEED: + case DAMOS_COLD: + case DAMOS_PAGEOUT: + case DAMOS_HUGEPAGE: + case DAMOS_NOHUGEPAGE: + case DAMOS_STAT: + return true; + default: + return false; + } +} + +/* + * Converts a string into an array of struct damos pointers + * + * Returns an array of struct damos pointers that converted if the conversion + * success, or NULL otherwise. + */ +static struct damos **str_to_schemes(const char *str, ssize_t len, + ssize_t *nr_schemes) +{ + struct damos *scheme, **schemes; + const int max_nr_schemes = 256; + int pos = 0, parsed, ret; + unsigned long min_sz, max_sz; + unsigned int min_nr_a, max_nr_a, min_age, max_age; + unsigned int action; + + schemes = kmalloc_array(max_nr_schemes, sizeof(scheme), + GFP_KERNEL); + if (!schemes) + return NULL; + + *nr_schemes = 0; + while (pos < len && *nr_schemes < max_nr_schemes) { + struct damos_quota quota = {}; + struct damos_watermarks wmarks; + + ret = sscanf(&str[pos], + "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n", + &min_sz, &max_sz, &min_nr_a, &max_nr_a, + &min_age, &max_age, &action, "a.ms, + "a.sz, "a.reset_interval, + "a.weight_sz, "a.weight_nr_accesses, + "a.weight_age, &wmarks.metric, + &wmarks.interval, &wmarks.high, &wmarks.mid, + &wmarks.low, &parsed); + if (ret != 18) + break; + if (!damos_action_valid(action)) { + pr_err("wrong action %d\n", action); + goto fail; + } + + pos += parsed; + scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, + min_age, max_age, action, "a, &wmarks); + if (!scheme) + goto fail; + + schemes[*nr_schemes] = scheme; + *nr_schemes += 1; + } + return schemes; +fail: + free_schemes_arr(schemes, *nr_schemes); + return NULL; +} + +static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + struct damos **schemes; + ssize_t nr_schemes = 0, ret; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + schemes = str_to_schemes(kbuf, count, &nr_schemes); + if (!schemes) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + ret = damon_set_schemes(ctx, schemes, nr_schemes); + if (!ret) { + ret = count; + nr_schemes = 0; + } + unlock_out: mutex_unlock(&ctx->kdamond_lock); + free_schemes_arr(schemes, nr_schemes); out: kfree(kbuf); return ret; @@ -185,26 +355,31 @@ static ssize_t dbgfs_target_ids_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct damon_ctx *ctx = file->private_data; + bool id_is_pid = true; char *kbuf, *nrs; unsigned long *targets; ssize_t nr_targets; - ssize_t ret = count; + ssize_t ret; int i; - int err; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); nrs = kbuf; + if (!strncmp(kbuf, "paddr\n", count)) { + id_is_pid = false; + /* target id is meaningless here, but we set it just for fun */ + scnprintf(kbuf, count, "42 "); + } - targets = str_to_target_ids(nrs, ret, &nr_targets); + targets = str_to_target_ids(nrs, count, &nr_targets); if (!targets) { ret = -ENOMEM; goto out; } - if (targetid_is_pid(ctx)) { + if (id_is_pid) { for (i = 0; i < nr_targets; i++) { targets[i] = (unsigned long)find_get_pid( (int)targets[i]); @@ -218,17 +393,27 @@ static ssize_t dbgfs_target_ids_write(struct file *file, mutex_lock(&ctx->kdamond_lock); if (ctx->kdamond) { - if (targetid_is_pid(ctx)) + if (id_is_pid) dbgfs_put_pids(targets, nr_targets); ret = -EBUSY; goto unlock_out; } - err = damon_set_targets(ctx, targets, nr_targets); - if (err) { - if (targetid_is_pid(ctx)) + /* remove targets with previously-set primitive */ + damon_set_targets(ctx, NULL, 0); + + /* Configure the context for the address space type */ + if (id_is_pid) + damon_va_set_primitives(ctx); + else + damon_pa_set_primitives(ctx); + + ret = damon_set_targets(ctx, targets, nr_targets); + if (ret) { + if (id_is_pid) dbgfs_put_pids(targets, nr_targets); - ret = err; + } else { + ret = count; } unlock_out: @@ -240,6 +425,152 @@ out: return ret; } +static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len) +{ + struct damon_target *t; + struct damon_region *r; + int written = 0; + int rc; + + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + rc = scnprintf(&buf[written], len - written, + "%lu %lu %lu\n", + t->id, r->ar.start, r->ar.end); + if (!rc) + return -ENOMEM; + written += rc; + } + } + return written; +} + +static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t len; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + mutex_unlock(&ctx->kdamond_lock); + len = -EBUSY; + goto out; + } + + len = sprint_init_regions(ctx, kbuf, count); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + goto out; + len = simple_read_from_buffer(buf, count, ppos, kbuf, len); + +out: + kfree(kbuf); + return len; +} + +static int add_init_region(struct damon_ctx *c, + unsigned long target_id, struct damon_addr_range *ar) +{ + struct damon_target *t; + struct damon_region *r, *prev; + unsigned long id; + int rc = -EINVAL; + + if (ar->start >= ar->end) + return -EINVAL; + + damon_for_each_target(t, c) { + id = t->id; + if (targetid_is_pid(c)) + id = (unsigned long)pid_vnr((struct pid *)id); + if (id == target_id) { + r = damon_new_region(ar->start, ar->end); + if (!r) + return -ENOMEM; + damon_add_region(r, t); + if (damon_nr_regions(t) > 1) { + prev = damon_prev_region(r); + if (prev->ar.end > r->ar.start) { + damon_destroy_region(r, t); + return -EINVAL; + } + } + rc = 0; + } + } + return rc; +} + +static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len) +{ + struct damon_target *t; + struct damon_region *r, *next; + int pos = 0, parsed, ret; + unsigned long target_id; + struct damon_addr_range ar; + int err; + + damon_for_each_target(t, c) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r, t); + } + + while (pos < len) { + ret = sscanf(&str[pos], "%lu %lu %lu%n", + &target_id, &ar.start, &ar.end, &parsed); + if (ret != 3) + break; + err = add_init_region(c, target_id, &ar); + if (err) + goto fail; + pos += parsed; + } + + return 0; + +fail: + damon_for_each_target(t, c) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r, t); + } + return err; +} + +static ssize_t dbgfs_init_regions_write(struct file *file, + const char __user *buf, size_t count, + loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + err = set_init_regions(ctx, kbuf, ret); + if (err) + ret = err; + +unlock_out: + mutex_unlock(&ctx->kdamond_lock); + kfree(kbuf); + return ret; +} + static ssize_t dbgfs_kdamond_pid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -279,12 +610,24 @@ static const struct file_operations attrs_fops = { .write = dbgfs_attrs_write, }; +static const struct file_operations schemes_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_schemes_read, + .write = dbgfs_schemes_write, +}; + static const struct file_operations target_ids_fops = { .open = damon_dbgfs_open, .read = dbgfs_target_ids_read, .write = dbgfs_target_ids_write, }; +static const struct file_operations init_regions_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_init_regions_read, + .write = dbgfs_init_regions_write, +}; + static const struct file_operations kdamond_pid_fops = { .open = damon_dbgfs_open, .read = dbgfs_kdamond_pid_read, @@ -292,28 +635,27 @@ static const struct file_operations kdamond_pid_fops = { static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) { - const char * const file_names[] = {"attrs", "target_ids", - "kdamond_pid"}; - const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops, - &kdamond_pid_fops}; + const char * const file_names[] = {"attrs", "schemes", "target_ids", + "init_regions", "kdamond_pid"}; + const struct file_operations *fops[] = {&attrs_fops, &schemes_fops, + &target_ids_fops, &init_regions_fops, &kdamond_pid_fops}; int i; for (i = 0; i < ARRAY_SIZE(file_names); i++) debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); } -static int dbgfs_before_terminate(struct damon_ctx *ctx) +static void dbgfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; if (!targetid_is_pid(ctx)) - return 0; + return; damon_for_each_target_safe(t, next, ctx) { put_pid((struct pid *)t->id); damon_destroy_target(t); } - return 0; } static struct damon_ctx *dbgfs_new_ctx(void) @@ -388,8 +730,7 @@ static ssize_t dbgfs_mk_context_write(struct file *file, { char *kbuf; char *ctx_name; - ssize_t ret = count; - int err; + ssize_t ret; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -407,9 +748,9 @@ static ssize_t dbgfs_mk_context_write(struct file *file, } mutex_lock(&damon_dbgfs_lock); - err = dbgfs_mk_context(ctx_name); - if (err) - ret = err; + ret = dbgfs_mk_context(ctx_name); + if (!ret) + ret = count; mutex_unlock(&damon_dbgfs_lock); out: @@ -478,8 +819,7 @@ static ssize_t dbgfs_rm_context_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *kbuf; - ssize_t ret = count; - int err; + ssize_t ret; char *ctx_name; kbuf = user_input_str(buf, count, ppos); @@ -498,9 +838,9 @@ static ssize_t dbgfs_rm_context_write(struct file *file, } mutex_lock(&damon_dbgfs_lock); - err = dbgfs_rm_context(ctx_name); - if (err) - ret = err; + ret = dbgfs_rm_context(ctx_name); + if (!ret) + ret = count; mutex_unlock(&damon_dbgfs_lock); out: @@ -524,9 +864,8 @@ static ssize_t dbgfs_monitor_on_read(struct file *file, static ssize_t dbgfs_monitor_on_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - ssize_t ret = count; + ssize_t ret; char *kbuf; - int err; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -538,15 +877,24 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return -EINVAL; } - if (!strncmp(kbuf, "on", count)) - err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); - else if (!strncmp(kbuf, "off", count)) - err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); - else - err = -EINVAL; + if (!strncmp(kbuf, "on", count)) { + int i; - if (err) - ret = err; + for (i = 0; i < dbgfs_nr_ctxs; i++) { + if (damon_targets_empty(dbgfs_ctxs[i])) { + kfree(kbuf); + return -EINVAL; + } + } + ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); + } else if (!strncmp(kbuf, "off", count)) { + ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); + } else { + ret = -EINVAL; + } + + if (!ret) + ret = count; kfree(kbuf); return ret; } diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c new file mode 100644 index 000000000000..a496d6f203d6 --- /dev/null +++ b/mm/damon/paddr.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Primitives for The Physical Address Space + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#define pr_fmt(fmt) "damon-pa: " fmt + +#include <linux/mmu_notifier.h> +#include <linux/page_idle.h> +#include <linux/pagemap.h> +#include <linux/rmap.h> +#include <linux/swap.h> + +#include "../internal.h" +#include "prmtv-common.h" + +static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) + damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr); + else + damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr); + } + return true; +} + +static void damon_pa_mkold(unsigned long paddr) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct rmap_walk_control rwc = { + .rmap_one = __damon_pa_mkold, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return; + + if (!page_mapped(page) || !page_rmapping(page)) { + set_page_idle(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) + goto out; + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + +out: + put_page(page); +} + +static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, + struct damon_region *r) +{ + r->sampling_addr = damon_rand(r->ar.start, r->ar.end); + + damon_pa_mkold(r->sampling_addr); +} + +void damon_pa_prepare_access_checks(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) + __damon_pa_prepare_access_check(ctx, r); + } +} + +struct damon_pa_access_chk_result { + unsigned long page_sz; + bool accessed; +}; + +static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct damon_pa_access_chk_result *result = arg; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + result->accessed = false; + result->page_sz = PAGE_SIZE; + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) { + result->accessed = pte_young(*pvmw.pte) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + } else { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + result->accessed = pmd_young(*pvmw.pmd) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + result->page_sz = ((1UL) << HPAGE_PMD_SHIFT); +#else + WARN_ON_ONCE(1); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + } + if (result->accessed) { + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + /* If accessed, stop walking */ + return !result->accessed; +} + +static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct damon_pa_access_chk_result result = { + .page_sz = PAGE_SIZE, + .accessed = false, + }; + struct rmap_walk_control rwc = { + .arg = &result, + .rmap_one = __damon_pa_young, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return false; + + if (!page_mapped(page) || !page_rmapping(page)) { + if (page_is_idle(page)) + result.accessed = false; + else + result.accessed = true; + put_page(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) { + put_page(page); + return NULL; + } + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + put_page(page); + +out: + *page_sz = result.page_sz; + return result.accessed; +} + +static void __damon_pa_check_access(struct damon_ctx *ctx, + struct damon_region *r) +{ + static unsigned long last_addr; + static unsigned long last_page_sz = PAGE_SIZE; + static bool last_accessed; + + /* If the region is in the last checked page, reuse the result */ + if (ALIGN_DOWN(last_addr, last_page_sz) == + ALIGN_DOWN(r->sampling_addr, last_page_sz)) { + if (last_accessed) + r->nr_accesses++; + return; + } + + last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz); + if (last_accessed) + r->nr_accesses++; + + last_addr = r->sampling_addr; +} + +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + unsigned int max_nr_accesses = 0; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) { + __damon_pa_check_access(ctx, r); + max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + } + } + + return max_nr_accesses; +} + +bool damon_pa_target_valid(void *t) +{ + return true; +} + +int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + unsigned long addr; + LIST_HEAD(page_list); + + if (scheme->action != DAMOS_PAGEOUT) + return -EINVAL; + + for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + struct page *page = damon_get_page(PHYS_PFN(addr)); + + if (!page) + continue; + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (isolate_lru_page(page)) { + put_page(page); + continue; + } + if (PageUnevictable(page)) { + putback_lru_page(page); + } else { + list_add(&page->lru, &page_list); + put_page(page); + } + } + reclaim_pages(&page_list); + cond_resched(); + return 0; +} + +int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + +void damon_pa_set_primitives(struct damon_ctx *ctx) +{ + ctx->primitive.init = NULL; + ctx->primitive.update = NULL; + ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks; + ctx->primitive.check_accesses = damon_pa_check_accesses; + ctx->primitive.reset_aggregated = NULL; + ctx->primitive.target_valid = damon_pa_target_valid; + ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = damon_pa_apply_scheme; + ctx->primitive.get_scheme_score = damon_pa_scheme_score; +} diff --git a/mm/damon/prmtv-common.c b/mm/damon/prmtv-common.c new file mode 100644 index 000000000000..92a04f5831d6 --- /dev/null +++ b/mm/damon/prmtv-common.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Primitives for Data Access Monitoring + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#include <linux/mmu_notifier.h> +#include <linux/page_idle.h> +#include <linux/pagemap.h> +#include <linux/rmap.h> + +#include "prmtv-common.h" + +/* + * Get an online page for a pfn if it's in the LRU list. Otherwise, returns + * NULL. + * + * The body of this function is stolen from the 'page_idle_get_page()'. We + * steal rather than reuse it because the code is quite simple. + */ +struct page *damon_get_page(unsigned long pfn) +{ + struct page *page = pfn_to_online_page(pfn); + + if (!page || !PageLRU(page) || !get_page_unless_zero(page)) + return NULL; + + if (unlikely(!PageLRU(page))) { + put_page(page); + page = NULL; + } + return page; +} + +void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr) +{ + bool referenced = false; + struct page *page = damon_get_page(pte_pfn(*pte)); + + if (!page) + return; + + if (pte_young(*pte)) { + referenced = true; + *pte = pte_mkold(*pte); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +} + +void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool referenced = false; + struct page *page = damon_get_page(pmd_pfn(*pmd)); + + if (!page) + return; + + if (pmd_young(*pmd)) { + referenced = true; + *pmd = pmd_mkold(*pmd); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, + addr + ((1UL) << HPAGE_PMD_SHIFT))) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +} + +#define DAMON_MAX_SUBSCORE (100) +#define DAMON_MAX_AGE_IN_LOG (32) + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s) +{ + unsigned int max_nr_accesses; + int freq_subscore; + unsigned int age_in_sec; + int age_in_log, age_subscore; + unsigned int freq_weight = s->quota.weight_nr_accesses; + unsigned int age_weight = s->quota.weight_age; + int hotness; + + max_nr_accesses = c->aggr_interval / c->sample_interval; + freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; + + age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000; + for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec; + age_in_log++, age_in_sec >>= 1) + ; + + /* If frequency is 0, higher age means it's colder */ + if (freq_subscore == 0) + age_in_log *= -1; + + /* + * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG]. + * Scale it to be in [0, 100] and set it as age subscore. + */ + age_in_log += DAMON_MAX_AGE_IN_LOG; + age_subscore = age_in_log * DAMON_MAX_SUBSCORE / + DAMON_MAX_AGE_IN_LOG / 2; + + hotness = (freq_weight * freq_subscore + age_weight * age_subscore); + if (freq_weight + age_weight) + hotness /= freq_weight + age_weight; + /* + * Transform it to fit in [0, DAMOS_MAX_SCORE] + */ + hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + + /* Return coldness of the region */ + return DAMOS_MAX_SCORE - hotness; +} diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h new file mode 100644 index 000000000000..61f27037603e --- /dev/null +++ b/mm/damon/prmtv-common.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common Primitives for Data Access Monitoring + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#include <linux/damon.h> +#include <linux/random.h> + +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + +struct page *damon_get_page(unsigned long pfn); + +void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr); +void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr); + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s); diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c new file mode 100644 index 000000000000..dc1485044eaf --- /dev/null +++ b/mm/damon/reclaim.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON-based page reclamation + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#define pr_fmt(fmt) "damon-reclaim: " fmt + +#include <linux/damon.h> +#include <linux/ioport.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/workqueue.h> + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "damon_reclaim." + +/* + * Enable or disable DAMON_RECLAIM. + * + * You can enable DAMON_RCLAIM by setting the value of this parameter as ``Y``. + * Setting it as ``N`` disables DAMON_RECLAIM. Note that DAMON_RECLAIM could + * do no real monitoring and reclamation due to the watermarks-based activation + * condition. Refer to below descriptions for the watermarks parameter for + * this. + */ +static bool enabled __read_mostly; +module_param(enabled, bool, 0600); + +/* + * Time threshold for cold memory regions identification in microseconds. + * + * If a memory region is not accessed for this or longer time, DAMON_RECLAIM + * identifies the region as cold, and reclaims. 120 seconds by default. + */ +static unsigned long min_age __read_mostly = 120000000; +module_param(min_age, ulong, 0600); + +/* + * Limit of time for trying the reclamation in milliseconds. + * + * DAMON_RECLAIM tries to use only up to this time within a time window + * (quota_reset_interval_ms) for trying reclamation of cold pages. This can be + * used for limiting CPU consumption of DAMON_RECLAIM. If the value is zero, + * the limit is disabled. + * + * 10 ms by default. + */ +static unsigned long quota_ms __read_mostly = 10; +module_param(quota_ms, ulong, 0600); + +/* + * Limit of size of memory for the reclamation in bytes. + * + * DAMON_RECLAIM charges amount of memory which it tried to reclaim within a + * time window (quota_reset_interval_ms) and makes no more than this limit is + * tried. This can be used for limiting consumption of CPU and IO. If this + * value is zero, the limit is disabled. + * + * 128 MiB by default. + */ +static unsigned long quota_sz __read_mostly = 128 * 1024 * 1024; +module_param(quota_sz, ulong, 0600); + +/* + * The time/size quota charge reset interval in milliseconds. + * + * The charge reset interval for the quota of time (quota_ms) and size + * (quota_sz). That is, DAMON_RECLAIM does not try reclamation for more than + * quota_ms milliseconds or quota_sz bytes within quota_reset_interval_ms + * milliseconds. + * + * 1 second by default. + */ +static unsigned long quota_reset_interval_ms __read_mostly = 1000; +module_param(quota_reset_interval_ms, ulong, 0600); + +/* + * The watermarks check time interval in microseconds. + * + * Minimal time to wait before checking the watermarks, when DAMON_RECLAIM is + * enabled but inactive due to its watermarks rule. 5 seconds by default. + */ +static unsigned long wmarks_interval __read_mostly = 5000000; +module_param(wmarks_interval, ulong, 0600); + +/* + * Free memory rate (per thousand) for the high watermark. + * + * If free memory of the system in bytes per thousand bytes is higher than + * this, DAMON_RECLAIM becomes inactive, so it does nothing but periodically + * checks the watermarks. 500 (50%) by default. + */ +static unsigned long wmarks_high __read_mostly = 500; +module_param(wmarks_high, ulong, 0600); + +/* + * Free memory rate (per thousand) for the middle watermark. + * + * If free memory of the system in bytes per thousand bytes is between this and + * the low watermark, DAMON_RECLAIM becomes active, so starts the monitoring + * and the reclaiming. 400 (40%) by default. + */ +static unsigned long wmarks_mid __read_mostly = 400; +module_param(wmarks_mid, ulong, 0600); + +/* + * Free memory rate (per thousand) for the low watermark. + * + * If free memory of the system in bytes per thousand bytes is lower than this, + * DAMON_RECLAIM becomes inactive, so it does nothing but periodically checks + * the watermarks. In the case, the system falls back to the LRU-based page + * granularity reclamation logic. 200 (20%) by default. + */ +static unsigned long wmarks_low __read_mostly = 200; +module_param(wmarks_low, ulong, 0600); + +/* + * Sampling interval for the monitoring in microseconds. + * + * The sampling interval of DAMON for the cold memory monitoring. Please refer + * to the DAMON documentation for more detail. 5 ms by default. + */ +static unsigned long sample_interval __read_mostly = 5000; +module_param(sample_interval, ulong, 0600); + +/* + * Aggregation interval for the monitoring in microseconds. + * + * The aggregation interval of DAMON for the cold memory monitoring. Please + * refer to the DAMON documentation for more detail. 100 ms by default. + */ +static unsigned long aggr_interval __read_mostly = 100000; +module_param(aggr_interval, ulong, 0600); + +/* + * Minimum number of monitoring regions. + * + * The minimal number of monitoring regions of DAMON for the cold memory + * monitoring. This can be used to set lower-bound of the monitoring quality. + * But, setting this too high could result in increased monitoring overhead. + * Please refer to the DAMON documentation for more detail. 10 by default. + */ +static unsigned long min_nr_regions __read_mostly = 10; +module_param(min_nr_regions, ulong, 0600); + +/* + * Maximum number of monitoring regions. + * + * The maximum number of monitoring regions of DAMON for the cold memory + * monitoring. This can be used to set upper-bound of the monitoring overhead. + * However, setting this too low could result in bad monitoring quality. + * Please refer to the DAMON documentation for more detail. 1000 by default. + */ +static unsigned long max_nr_regions __read_mostly = 1000; +module_param(max_nr_regions, ulong, 0600); + +/* + * Start of the target memory region in physical address. + * + * The start physical address of memory region that DAMON_RECLAIM will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_start __read_mostly; +module_param(monitor_region_start, ulong, 0600); + +/* + * End of the target memory region in physical address. + * + * The end physical address of memory region that DAMON_RECLAIM will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_end __read_mostly; +module_param(monitor_region_end, ulong, 0600); + +/* + * PID of the DAMON thread + * + * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +static int kdamond_pid __read_mostly = -1; +module_param(kdamond_pid, int, 0400); + +static struct damon_ctx *ctx; +static struct damon_target *target; + +struct damon_reclaim_ram_walk_arg { + unsigned long start; + unsigned long end; +}; + +static int walk_system_ram(struct resource *res, void *arg) +{ + struct damon_reclaim_ram_walk_arg *a = arg; + + if (a->end - a->start < res->end - res->start) { + a->start = res->start; + a->end = res->end; + } + return 0; +} + +/* + * Find biggest 'System RAM' resource and store its start and end address in + * @start and @end, respectively. If no System RAM is found, returns false. + */ +static bool get_monitoring_region(unsigned long *start, unsigned long *end) +{ + struct damon_reclaim_ram_walk_arg arg = {}; + + walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram); + if (arg.end <= arg.start) + return false; + + *start = arg.start; + *end = arg.end; + return true; +} + +static struct damos *damon_reclaim_new_scheme(void) +{ + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = wmarks_interval, + .high = wmarks_high, + .mid = wmarks_mid, + .low = wmarks_low, + }; + struct damos_quota quota = { + /* + * Do not try reclamation for more than quota_ms milliseconds + * or quota_sz bytes within quota_reset_interval_ms. + */ + .ms = quota_ms, + .sz = quota_sz, + .reset_interval = quota_reset_interval_ms, + /* Within the quota, page out older regions first. */ + .weight_sz = 0, + .weight_nr_accesses = 0, + .weight_age = 1 + }; + struct damos *scheme = damon_new_scheme( + /* Find regions having PAGE_SIZE or larger size */ + PAGE_SIZE, ULONG_MAX, + /* and not accessed at all */ + 0, 0, + /* for min_age or more micro-seconds, and */ + min_age / aggr_interval, UINT_MAX, + /* page out those, as soon as found */ + DAMOS_PAGEOUT, + /* under the quota. */ + "a, + /* (De)activate this according to the watermarks. */ + &wmarks); + + return scheme; +} + +static int damon_reclaim_turn(bool on) +{ + struct damon_region *region; + struct damos *scheme; + int err; + + if (!on) { + err = damon_stop(&ctx, 1); + if (!err) + kdamond_pid = -1; + return err; + } + + err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0, + min_nr_regions, max_nr_regions); + if (err) + return err; + + if (monitor_region_start > monitor_region_end) + return -EINVAL; + if (!monitor_region_start && !monitor_region_end && + !get_monitoring_region(&monitor_region_start, + &monitor_region_end)) + return -EINVAL; + /* DAMON will free this on its own when finish monitoring */ + region = damon_new_region(monitor_region_start, monitor_region_end); + if (!region) + return -ENOMEM; + damon_add_region(region, target); + + /* Will be freed by 'damon_set_schemes()' below */ + scheme = damon_reclaim_new_scheme(); + if (!scheme) { + err = -ENOMEM; + goto free_region_out; + } + err = damon_set_schemes(ctx, &scheme, 1); + if (err) + goto free_scheme_out; + + err = damon_start(&ctx, 1); + if (!err) { + kdamond_pid = ctx->kdamond->pid; + return 0; + } + +free_scheme_out: + damon_destroy_scheme(scheme); +free_region_out: + damon_destroy_region(region, target); + return err; +} + +#define ENABLE_CHECK_INTERVAL_MS 1000 +static struct delayed_work damon_reclaim_timer; +static void damon_reclaim_timer_fn(struct work_struct *work) +{ + static bool last_enabled; + bool now_enabled; + + now_enabled = enabled; + if (last_enabled != now_enabled) { + if (!damon_reclaim_turn(now_enabled)) + last_enabled = now_enabled; + else + enabled = last_enabled; + } + + schedule_delayed_work(&damon_reclaim_timer, + msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS)); +} +static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn); + +static int __init damon_reclaim_init(void) +{ + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + + damon_pa_set_primitives(ctx); + + /* 4242 means nothing but fun */ + target = damon_new_target(4242); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + + schedule_delayed_work(&damon_reclaim_timer, 0); + return 0; +} + +module_init(damon_reclaim_init); diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index 1f5c13257dba..ecfd0b2ed222 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -233,7 +233,7 @@ static void damon_test_apply_three_regions3(struct kunit *test) * and 70-100) has totally freed and mapped to different area (30-32 and * 65-68). The target regions which were in the old second and third big * regions should now be removed and new target regions covering the new second - * and third big regions should be crated. + * and third big regions should be created. */ static void damon_test_apply_three_regions4(struct kunit *test) { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 58c1fb2aafa9..35fe49080ee9 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -7,25 +7,20 @@ #define pr_fmt(fmt) "damon-va: " fmt -#include <linux/damon.h> +#include <asm-generic/mman-common.h> +#include <linux/highmem.h> #include <linux/hugetlb.h> -#include <linux/mm.h> #include <linux/mmu_notifier.h> -#include <linux/highmem.h> #include <linux/page_idle.h> #include <linux/pagewalk.h> -#include <linux/random.h> -#include <linux/sched/mm.h> -#include <linux/slab.h> + +#include "prmtv-common.h" #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST #undef DAMON_MIN_REGION #define DAMON_MIN_REGION 1 #endif -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) - /* * 't->id' should be the pointer to the relevant 'struct pid' having reference * count. Caller must put the returned task, unless it is NULL. @@ -311,7 +306,7 @@ static void damon_va_apply_three_regions(struct damon_target *t, struct damon_addr_range bregions[3]) { struct damon_region *r, *next; - unsigned int i = 0; + unsigned int i; /* Remove regions which are not in the three big regions now */ damon_for_each_region_safe(r, next, t) { @@ -372,82 +367,6 @@ void damon_va_update(struct damon_ctx *ctx) } } -/* - * Get an online page for a pfn if it's in the LRU list. Otherwise, returns - * NULL. - * - * The body of this function is stolen from the 'page_idle_get_page()'. We - * steal rather than reuse it because the code is quite simple. - */ -static struct page *damon_get_page(unsigned long pfn) -{ - struct page *page = pfn_to_online_page(pfn); - - if (!page || !PageLRU(page) || !get_page_unless_zero(page)) - return NULL; - - if (unlikely(!PageLRU(page))) { - put_page(page); - page = NULL; - } - return page; -} - -static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, - unsigned long addr) -{ - bool referenced = false; - struct page *page = damon_get_page(pte_pfn(*pte)); - - if (!page) - return; - - if (pte_young(*pte)) { - referenced = true; - *pte = pte_mkold(*pte); - } - -#ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) - referenced = true; -#endif /* CONFIG_MMU_NOTIFIER */ - - if (referenced) - set_page_young(page); - - set_page_idle(page); - put_page(page); -} - -static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, - unsigned long addr) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - bool referenced = false; - struct page *page = damon_get_page(pmd_pfn(*pmd)); - - if (!page) - return; - - if (pmd_young(*pmd)) { - referenced = true; - *pmd = pmd_mkold(*pmd); - } - -#ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, - addr + ((1UL) << HPAGE_PMD_SHIFT))) - referenced = true; -#endif /* CONFIG_MMU_NOTIFIER */ - - if (referenced) - set_page_young(page); - - set_page_idle(page); - put_page(page); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -} - static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { @@ -475,7 +394,7 @@ out: return 0; } -static struct mm_walk_ops damon_mkold_ops = { +static const struct mm_walk_ops damon_mkold_ops = { .pmd_entry = damon_mkold_pmd_entry, }; @@ -571,7 +490,7 @@ out: return 0; } -static struct mm_walk_ops damon_young_ops = { +static const struct mm_walk_ops damon_young_ops = { .pmd_entry = damon_young_pmd_entry, }; @@ -658,6 +577,76 @@ bool damon_va_target_valid(void *target) return false; } +#ifndef CONFIG_ADVISE_SYSCALLS +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + return -EINVAL; +} +#else +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + struct mm_struct *mm; + int ret = -ENOMEM; + + mm = damon_get_mm(target); + if (!mm) + goto out; + + ret = do_madvise(mm, PAGE_ALIGN(r->ar.start), + PAGE_ALIGN(r->ar.end - r->ar.start), behavior); + mmput(mm); +out: + return ret; +} +#endif /* CONFIG_ADVISE_SYSCALLS */ + +int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + int madv_action; + + switch (scheme->action) { + case DAMOS_WILLNEED: + madv_action = MADV_WILLNEED; + break; + case DAMOS_COLD: + madv_action = MADV_COLD; + break; + case DAMOS_PAGEOUT: + madv_action = MADV_PAGEOUT; + break; + case DAMOS_HUGEPAGE: + madv_action = MADV_HUGEPAGE; + break; + case DAMOS_NOHUGEPAGE: + madv_action = MADV_NOHUGEPAGE; + break; + case DAMOS_STAT: + return 0; + default: + pr_warn("Wrong action %d\n", scheme->action); + return -EINVAL; + } + + return damos_madvise(t, r, madv_action); +} + +int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + void damon_va_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = damon_va_init; @@ -667,6 +656,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.reset_aggregated = NULL; ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = damon_va_apply_scheme; + ctx->primitive.get_scheme_score = damon_va_scheme_score; } #include "vaddr-test.h" diff --git a/mm/debug.c b/mm/debug.c index d0020fc58202..a05a39ff8fe4 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -16,17 +16,19 @@ #include <linux/ctype.h> #include "internal.h" +#include <trace/events/migrate.h> + +/* + * Define EM() and EMe() so that MIGRATE_REASON from trace/events/migrate.h can + * be used to populate migrate_reason_names[]. + */ +#undef EM +#undef EMe +#define EM(a, b) b, +#define EMe(a, b) b const char *migrate_reason_names[MR_TYPES] = { - "compaction", - "memory_failure", - "memory_hotplug", - "syscall_or_cpuset", - "mempolicy_mbind", - "numa_misplaced", - "contig_range", - "longterm_pin", - "demotion", + MIGRATE_REASON }; const struct trace_print_flags pageflag_names[] = { diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 1403639302e4..228e3954b90c 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -1104,13 +1104,14 @@ static int __init init_args(struct pgtable_debug_args *args) /* * Initialize the debugging data. * - * __P000 (or even __S000) will help create page table entries with - * PROT_NONE permission as required for pxx_protnone_tests(). + * protection_map[0] (or even protection_map[8]) will help create + * page table entries with PROT_NONE permission as required for + * pxx_protnone_tests(). */ memset(args, 0, sizeof(*args)); args->vaddr = get_random_vaddr(); args->page_prot = vm_get_page_prot(VMFLAGS); - args->page_prot_none = __P000; + args->page_prot_none = protection_map[0]; args->is_contiguous_page = false; args->pud_pfn = ULONG_MAX; args->pmd_pfn = ULONG_MAX; diff --git a/mm/filemap.c b/mm/filemap.c index bfcef6ff7a27..615512caa0b5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -638,6 +638,30 @@ static bool mapping_needs_writeback(struct address_space *mapping) return mapping->nrpages; } +static bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); + pgoff_t max = end_byte >> PAGE_SHIFT; + struct page *page; + + if (end_byte < start_byte) + return false; + + rcu_read_lock(); + xas_for_each(&xas, page, max) { + if (xas_retry(&xas, page)) + continue; + if (xa_is_value(page)) + continue; + if (PageDirty(page) || PageLocked(page) || PageWriteback(page)) + break; + } + rcu_read_unlock(); + return page != NULL; + +} + /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check @@ -655,29 +679,12 @@ static bool mapping_needs_writeback(struct address_space *mapping) bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { - XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); - pgoff_t max = end_byte >> PAGE_SHIFT; - struct page *page; - if (!mapping_needs_writeback(mapping)) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; - if (end_byte < start_byte) - return false; - - rcu_read_lock(); - xas_for_each(&xas, page, max) { - if (xas_retry(&xas, page)) - continue; - if (xa_is_value(page)) - continue; - if (PageDirty(page) || PageLocked(page) || PageWriteback(page)) - break; - } - rcu_read_unlock(); - return page != NULL; + return filemap_range_has_writeback(mapping, start_byte, end_byte); } EXPORT_SYMBOL_GPL(filemap_range_needs_writeback); @@ -1592,6 +1599,7 @@ void folio_end_writeback(struct folio *folio) smp_mb__after_atomic(); folio_wake(folio, PG_writeback); + acct_reclaim_writeback(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); @@ -2088,7 +2096,6 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, if (!xa_is_value(page)) { if (page->index < start) goto put; - VM_BUG_ON_PAGE(page->index != xas.xa_index, page); if (page->index + thp_nr_pages(page) - 1 > end) goto put; if (!trylock_page(page)) @@ -2621,6 +2628,9 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; + if (unlikely(iocb->ki_pos >= i_size_read(inode))) + break; + error = filemap_get_pages(iocb, iter, &pvec); if (error < 0) break; @@ -2733,9 +2743,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - loff_t size; - size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) @@ -2767,8 +2775,9 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ - if (retval < 0 || !count || iocb->ki_pos >= size || - IS_DAX(inode)) + if (retval < 0 || !count || IS_DAX(inode)) + return retval; + if (iocb->ki_pos >= i_size_read(inode)) return retval; } @@ -3193,24 +3202,17 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) } if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { - vm_fault_t ret = do_set_pmd(vmf, page); - if (!ret) { - /* The page is mapped successfully, reference consumed. */ - unlock_page(page); - return true; - } - } - - if (pmd_none(*vmf->pmd)) { - vmf->ptl = pmd_lock(mm, vmf->pmd); - if (likely(pmd_none(*vmf->pmd))) { - mm_inc_nr_ptes(mm); - pmd_populate(mm, vmf->pmd, vmf->prealloc_pte); - vmf->prealloc_pte = NULL; + vm_fault_t ret = do_set_pmd(vmf, page); + if (!ret) { + /* The page is mapped successfully, reference consumed. */ + unlock_page(page); + return true; } - spin_unlock(vmf->ptl); } + if (pmd_none(*vmf->pmd)) + pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); + /* See comment in handle_pte_fault() */ if (pmd_devmap_trans_unstable(vmf->pmd)) { unlock_page(page); @@ -2365,7 +2365,6 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; - int ret = 1; do { struct page *page = pfn_to_page(pfn); @@ -2373,14 +2372,12 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { undo_dev_pagemap(nr, nr_start, flags, pages); - ret = 0; break; } SetPageReferenced(page); pages[*nr] = page; if (unlikely(!try_grab_page(page, flags))) { undo_dev_pagemap(nr, nr_start, flags, pages); - ret = 0; break; } (*nr)++; @@ -2388,7 +2385,7 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); - return ret; + return addr == end; } static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, diff --git a/mm/highmem.c b/mm/highmem.c index 471d9779a7f4..88f65f155845 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -382,7 +382,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); if (end1 > start1) { - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start1, 0, this_end - start1); } end1 -= this_end; @@ -397,7 +397,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, if (end2 > start2) { if (!kaddr) - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start2, 0, this_end - start2); } end2 -= this_end; @@ -405,7 +405,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, } if (kaddr) { - kunmap_atomic(kaddr); + kunmap_local(kaddr); flush_dcache_page(page + i); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6378c1066459..e09159c957e3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -50,6 +50,17 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; +static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, + 1 << order); +} +#else +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return false; +} #endif static unsigned long hugetlb_cma_size __initdata; @@ -66,6 +77,7 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, @@ -321,8 +333,7 @@ static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB - return rg && org && - rg->reservation_counter == org->reservation_counter && + return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else @@ -435,7 +446,6 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t, add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); - VM_BUG_ON(add < 0); return add; } @@ -1004,6 +1014,35 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) vma->vm_private_data = (void *)0; } +/* + * Reset and decrement one ref on hugepage private reservation. + * Called with mm->mmap_sem writer semaphore held. + * This function should be only used by move_vma() and operate on + * same sized vma. It should never come here with last ref on the + * reservation. + */ +void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ + /* + * Clear the old hugetlb private page reservation. + * It has already been transferred to new_vma. + * + * During a mremap() operation of a hugetlb vma we call move_vma() + * which copies vma into new_vma and unmaps vma. After the copy + * operation both new_vma and vma share a reference to the resv_map + * struct, and at that point vma is about to be unmapped. We don't + * want to return the reservation to the pool at unmap of vma because + * the reservation still lives on in new_vma, so simply decrement the + * ref here and remove the resv_map reference from this vma. + */ + struct resv_map *reservations = vma_resv_map(vma); + + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&reservations->refs, resv_map_release); + + reset_vma_resv_huge_pages(vma); +} + /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { @@ -1260,9 +1299,9 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_page(struct page *page, - unsigned int order) +/* used to demote non-gigantic_huge pages as well */ +static void __destroy_compound_gigantic_page(struct page *page, + unsigned int order, bool demote) { int i; int nr_pages = 1 << order; @@ -1272,8 +1311,10 @@ static void destroy_compound_gigantic_page(struct page *page, atomic_set(compound_pincount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + p->mapping = NULL; clear_compound_head(p); - set_page_refcounted(p); + if (!demote) + set_page_refcounted(p); } set_compound_order(page, 0); @@ -1281,6 +1322,19 @@ static void destroy_compound_gigantic_page(struct page *page, __ClearPageHead(page); } +static void destroy_compound_hugetlb_page_for_demote(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, true); +} + +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +static void destroy_compound_gigantic_page(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, false); +} + static void free_gigantic_page(struct page *page, unsigned int order) { /* @@ -1353,12 +1407,15 @@ static inline void destroy_compound_gigantic_page(struct page *page, /* * Remove hugetlb page from lists, and update dtor so that page appears - * as just a compound page. A reference is held on the page. + * as just a compound page. + * + * A reference is held on the page, except in the case of demote. * * Must be called with hugetlb lock held. */ -static void remove_hugetlb_page(struct hstate *h, struct page *page, - bool adjust_surplus) +static void __remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus, + bool demote) { int nid = page_to_nid(page); @@ -1396,8 +1453,12 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, * * This handles the case where more than one ref is held when and * after update_and_free_page is called. + * + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ - set_page_refcounted(page); + if (!demote) + set_page_refcounted(page); if (hstate_is_gigantic(h)) set_compound_page_dtor(page, NULL_COMPOUND_DTOR); else @@ -1407,6 +1468,18 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->nr_huge_pages_node[nid]--; } +static void remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, false); +} + +static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, true); +} + static void add_hugetlb_page(struct hstate *h, struct page *page, bool adjust_surplus) { @@ -1476,7 +1549,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } - if (hstate_is_gigantic(h)) { + + /* + * Non-gigantic pages demoted from CMA allocated gigantic pages + * need to be given back to CMA in free_gigantic_page. + */ + if (hstate_is_gigantic(h) || + hugetlb_cma_page(page, huge_page_order(h))) { destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { @@ -1664,7 +1743,8 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) spin_unlock_irq(&hugetlb_lock); } -static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, + bool demote) { int i, j; int nr_pages = 1 << order; @@ -1702,12 +1782,17 @@ static bool prep_compound_gigantic_page(struct page *page, unsigned int order) * the set of pages can not be converted to a gigantic page. * The caller who allocated the pages should then discard the * pages using the appropriate free interface. + * + * In the case of demote, the ref count will be zero. */ - if (!page_ref_freeze(p, 1)) { - pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); - goto out_error; + if (!demote) { + if (!page_ref_freeze(p, 1)) { + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + goto out_error; + } + } else { + VM_BUG_ON_PAGE(page_count(p), p); } - set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); @@ -1730,6 +1815,17 @@ out_error: return false; } +static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, false); +} + +static bool prep_compound_gigantic_page_for_demote(struct page *page, + unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, true); +} + /* * PageHuge() only returns true for hugetlbfs pages, but not for normal or * transparent huge pages. See the PageTransHuge() documentation for more @@ -2868,33 +2964,39 @@ out_subpool_put: return ERR_PTR(-ENOSPC); } -int alloc_bootmem_huge_page(struct hstate *h) +int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); -int __alloc_bootmem_huge_page(struct hstate *h) +int __alloc_bootmem_huge_page(struct hstate *h, int nid) { - struct huge_bootmem_page *m; + struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; + if (nid >= nr_online_nodes) + return 0; + /* do node specific alloc */ + if (nid != NUMA_NO_NODE) { + m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!m) + return 0; + goto found; + } + /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { - void *addr; - - addr = memblock_alloc_try_nid_raw( + m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); - if (addr) { - /* - * Use the beginning of the huge page to store the - * huge_bootmem_page struct (until gather_bootmem - * puts them into the mem_map). - */ - m = addr; - goto found; - } + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + if (!m) + return 0; + goto found; } - return 0; found: - BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* 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); @@ -2934,12 +3036,61 @@ static void __init gather_bootmem_prealloc(void) cond_resched(); } } +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) +{ + unsigned long i; + char buf[32]; + + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { + if (hstate_is_gigantic(h)) { + if (!alloc_bootmem_huge_page(h, nid)) + break; + } else { + struct page *page; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); + if (!page) + break; + put_page(page); /* free it into the hugepage allocator */ + } + cond_resched(); + } + if (i == h->max_huge_pages_node[nid]) + return; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", + h->max_huge_pages_node[nid], buf, nid, i); + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); + h->max_huge_pages_node[nid] = i; +} static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; + bool node_specific_alloc = false; + + /* skip gigantic hugepages allocation if hugetlb_cma enabled */ + if (hstate_is_gigantic(h) && hugetlb_cma_size) { + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); + return; + } + + /* do node specific alloc */ + for (i = 0; i < nr_online_nodes; i++) { + if (h->max_huge_pages_node[i] > 0) { + hugetlb_hstate_alloc_pages_onenode(h, i); + node_specific_alloc = true; + } + } + if (node_specific_alloc) + return; + + /* below will do all node balanced alloc */ if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. @@ -2960,11 +3111,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (hugetlb_cma_size) { - pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); - goto free; - } - if (!alloc_bootmem_huge_page(h)) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], @@ -2980,13 +3127,12 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) h->max_huge_pages, buf, i); h->max_huge_pages = i; } -free: kfree(node_alloc_noretry); } static void __init hugetlb_init_hstates(void) { - struct hstate *h; + struct hstate *h, *h2; for_each_hstate(h) { if (minimum_order > huge_page_order(h)) @@ -2995,6 +3141,26 @@ static void __init hugetlb_init_hstates(void) /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); + + /* + * Set demote order for each hstate. Note that + * h->demote_order is initially 0. + * - We can not demote gigantic pages if runtime freeing + * is not supported, so skip this. + * - If CMA allocation is possible, we can not demote + * HUGETLB_PAGE_ORDER or smaller size pages. + */ + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + continue; + if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) + continue; + for_each_hstate(h2) { + if (h2 == h) + continue; + if (h2->order < h->order && + h2->order > h->demote_order) + h->demote_order = h2->order; + } } VM_BUG_ON(minimum_order == UINT_MAX); } @@ -3235,9 +3401,100 @@ out: return 0; } +static int demote_free_huge_page(struct hstate *h, struct page *page) +{ + int i, nid = page_to_nid(page); + struct hstate *target_hstate; + int rc = 0; + + target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); + + remove_hugetlb_page_for_demote(h, page, false); + spin_unlock_irq(&hugetlb_lock); + + rc = alloc_huge_page_vmemmap(h, page); + if (rc) { + /* Allocation of vmemmmap failed, we can not demote page */ + spin_lock_irq(&hugetlb_lock); + set_page_refcounted(page); + add_hugetlb_page(h, page, false); + return rc; + } + + /* + * Use destroy_compound_hugetlb_page_for_demote for all huge page + * sizes as it will not ref count pages. + */ + destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h)); + + /* + * Taking target hstate mutex synchronizes with set_max_huge_pages. + * Without the mutex, pages added to target hstate could be marked + * as surplus. + * + * Note that we already hold h->resize_lock. To prevent deadlock, + * use the convention of always taking larger size hstate mutex first. + */ + mutex_lock(&target_hstate->resize_lock); + for (i = 0; i < pages_per_huge_page(h); + i += pages_per_huge_page(target_hstate)) { + if (hstate_is_gigantic(target_hstate)) + prep_compound_gigantic_page_for_demote(page + i, + target_hstate->order); + else + prep_compound_page(page + i, target_hstate->order); + set_page_private(page + i, 0); + set_page_refcounted(page + i); + prep_new_huge_page(target_hstate, page + i, nid); + put_page(page + i); + } + mutex_unlock(&target_hstate->resize_lock); + + spin_lock_irq(&hugetlb_lock); + + /* + * Not absolutely necessary, but for consistency update max_huge_pages + * based on pool changes for the demoted page. + */ + h->max_huge_pages--; + target_hstate->max_huge_pages += pages_per_huge_page(h); + + return rc; +} + +static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) + __must_hold(&hugetlb_lock) +{ + int nr_nodes, node; + struct page *page; + int rc = 0; + + lockdep_assert_held(&hugetlb_lock); + + /* We should never get here if no demote order */ + if (!h->demote_order) { + pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); + return -EINVAL; /* internal error */ + } + + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (!list_empty(&h->hugepage_freelists[node])) { + page = list_entry(h->hugepage_freelists[node].next, + struct page, lru); + rc = demote_free_huge_page(h, page); + break; + } + } + + return rc; +} + #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) +#define HSTATE_ATTR_WO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_WO(_name) + #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) @@ -3433,6 +3690,103 @@ static ssize_t surplus_hugepages_show(struct kobject *kobj, } HSTATE_ATTR_RO(surplus_hugepages); +static ssize_t demote_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + unsigned long nr_demote; + unsigned long nr_available; + nodemask_t nodes_allowed, *n_mask; + struct hstate *h; + int err = 0; + int nid; + + err = kstrtoul(buf, 10, &nr_demote); + if (err) + return err; + h = kobj_to_hstate(kobj, &nid); + + if (nid != NUMA_NO_NODE) { + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } else { + n_mask = &node_states[N_MEMORY]; + } + + /* Synchronize with other sysfs operations modifying huge pages */ + mutex_lock(&h->resize_lock); + spin_lock_irq(&hugetlb_lock); + + while (nr_demote) { + /* + * Check for available pages to demote each time thorough the + * loop as demote_pool_huge_page will drop hugetlb_lock. + */ + if (nid != NUMA_NO_NODE) + nr_available = h->free_huge_pages_node[nid]; + else + nr_available = h->free_huge_pages; + nr_available -= h->resv_huge_pages; + if (!nr_available) + break; + + err = demote_pool_huge_page(h, n_mask); + if (err) + break; + + nr_demote--; + } + + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); + + if (err) + return err; + return len; +} +HSTATE_ATTR_WO(demote); + +static ssize_t demote_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int nid; + struct hstate *h = kobj_to_hstate(kobj, &nid); + unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; + + return sysfs_emit(buf, "%lukB\n", demote_size); +} + +static ssize_t demote_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct hstate *h, *demote_hstate; + unsigned long demote_size; + unsigned int demote_order; + int nid; + + demote_size = (unsigned long)memparse(buf, NULL); + + demote_hstate = size_to_hstate(demote_size); + if (!demote_hstate) + return -EINVAL; + demote_order = demote_hstate->order; + if (demote_order < HUGETLB_PAGE_ORDER) + return -EINVAL; + + /* demote order must be smaller than hstate order */ + h = kobj_to_hstate(kobj, &nid); + if (demote_order >= h->order) + return -EINVAL; + + /* resize_lock synchronizes access to demote size and writes */ + mutex_lock(&h->resize_lock); + h->demote_order = demote_order; + mutex_unlock(&h->resize_lock); + + return count; +} +HSTATE_ATTR(demote_size); + static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, @@ -3449,6 +3803,16 @@ static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; +static struct attribute *hstate_demote_attrs[] = { + &demote_size_attr.attr, + &demote_attr.attr, + NULL, +}; + +static const struct attribute_group hstate_demote_attr_group = { + .attrs = hstate_demote_attrs, +}; + static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) @@ -3466,6 +3830,12 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, hstate_kobjs[hi] = NULL; } + if (h->demote_order) { + if (sysfs_create_group(hstate_kobjs[hi], + &hstate_demote_attr_group)) + pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); + } + return retval; } @@ -3671,6 +4041,10 @@ static int __init hugetlb_init(void) } default_hstate.max_huge_pages = default_hstate_max_huge_pages; + + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; } } @@ -3731,6 +4105,10 @@ void __init hugetlb_add_hstate(unsigned int order) parsed_hstate = h; } +bool __init __weak hugetlb_node_alloc_supported(void) +{ + return true; +} /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz @@ -3742,6 +4120,10 @@ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; + int node = NUMA_NO_NODE; + int count; + unsigned long tmp; + char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); @@ -3765,8 +4147,40 @@ static int __init hugepages_setup(char *s) return 0; } - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; + while (*p) { + count = 0; + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + /* Parameter is node format */ + if (p[count] == ':') { + if (!hugetlb_node_alloc_supported()) { + pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); + return 0; + } + node = tmp; + p += count + 1; + if (node < 0 || node >= nr_online_nodes) + goto invalid; + /* Parse hugepages */ + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + if (!hugetlb_max_hstate) + default_hugepages_in_node[node] = tmp; + else + parsed_hstate->max_huge_pages_node[node] = tmp; + *mhp += tmp; + /* Go to parse next node*/ + if (p[count] == ',') + p += count + 1; + else + break; + } else { + if (p != s) + goto invalid; + *mhp = tmp; + break; + } + } /* * Global state is always initialized later in hugetlb_init. @@ -3779,6 +4193,10 @@ static int __init hugepages_setup(char *s) last_mhp = mhp; return 1; + +invalid: + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); + return 0; } __setup("hugepages=", hugepages_setup); @@ -3840,6 +4258,7 @@ __setup("hugepagesz=", hugepagesz_setup); static int __init default_hugepagesz_setup(char *s) { unsigned long size; + int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { @@ -3868,6 +4287,9 @@ static int __init default_hugepagesz_setup(char *s) */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; @@ -4426,9 +4848,85 @@ again: return ret; } -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page) +static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pte_t *src_pte) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + pte_t *dst_pte, pte; + spinlock_t *src_ptl, *dst_ptl; + + dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h)); + dst_ptl = huge_pte_lock(h, mm, dst_pte); + src_ptl = huge_pte_lockptr(h, mm, src_pte); + + /* + * We don't have to worry about the ordering of src and dst ptlocks + * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + */ + if (src_ptl != dst_ptl) + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte); + + if (src_ptl != dst_ptl) + spin_unlock(src_ptl); + spin_unlock(dst_ptl); +} + +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len) +{ + struct hstate *h = hstate_vma(vma); + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + unsigned long old_end = old_addr + len; + unsigned long old_addr_copy; + pte_t *src_pte, *dst_pte; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, + old_end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + mmu_notifier_invalidate_range_start(&range); + /* Prevent race with file truncation */ + i_mmap_lock_write(mapping); + for (; old_addr < old_end; old_addr += sz, new_addr += sz) { + src_pte = huge_pte_offset(mm, old_addr, sz); + if (!src_pte) + continue; + if (huge_pte_none(huge_ptep_get(src_pte))) + continue; + + /* old_addr arg to huge_pmd_unshare() is a pointer and so the + * arg may be modified. Pass a copy instead to preserve the + * value in old_addr. + */ + old_addr_copy = old_addr; + + if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) + continue; + + dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); + if (!dst_pte) + break; + + move_huge_pte(vma, old_addr, new_addr, src_pte); + } + i_mmap_unlock_write(mapping); + flush_tlb_range(vma, old_end - len, old_end); + mmu_notifier_invalidate_range_end(&range); + + return len + old_addr - old_end; +} + +static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -4616,7 +5114,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, /* * Hugetlb_cow() should be called with page lock of the original hugepage held. - * Called with hugetlb_instantiation_mutex held and pte_page locked so we + * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ @@ -5965,12 +6463,6 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * sharing is possible. For hugetlbfs, this prevents removal of any page * table entries associated with the address space. This is important as we * are setting up sharing based on existing page table entries (mappings). - * - * NOTE: This routine is only called from huge_pte_alloc. Some callers of - * huge_pte_alloc know that sharing is not possible and do not take - * i_mmap_rwsem as a performance optimization. This is handled by the - * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is - * only required for subsequent processing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) @@ -6371,7 +6863,38 @@ static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { - hugetlb_cma_size = memparse(p, &p); + int nid, count = 0; + unsigned long tmp; + char *s = p; + + while (*s) { + if (sscanf(s, "%lu%n", &tmp, &count) != 1) + break; + + if (s[count] == ':') { + nid = tmp; + if (nid < 0 || nid >= MAX_NUMNODES) + break; + + s += count + 1; + tmp = memparse(s, &s); + hugetlb_cma_size_in_node[nid] = tmp; + hugetlb_cma_size += tmp; + + /* + * Skip the separator if have one, otherwise + * break the parsing. + */ + if (*s == ',') + s++; + else + break; + } else { + hugetlb_cma_size = memparse(p, &p); + break; + } + } + return 0; } @@ -6380,6 +6903,7 @@ early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; + bool node_specific_cma_alloc = false; int nid; cma_reserve_called = true; @@ -6387,30 +6911,72 @@ void __init hugetlb_cma_reserve(int order) if (!hugetlb_cma_size) return; + for (nid = 0; nid < MAX_NUMNODES; nid++) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + if (!node_state(nid, N_ONLINE)) { + pr_warn("hugetlb_cma: invalid node %d specified\n", nid); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + continue; + } + + if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { + pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", + nid, (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + } else { + node_specific_cma_alloc = true; + } + } + + /* Validate the CMA size again in case some invalid nodes specified. */ + if (!hugetlb_cma_size) + return; + if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size = 0; return; } - /* - * If 3 GB area is requested on a machine with 4 numa nodes, - * let's allocate 1 GB on first three nodes and ignore the last one. - */ - per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); - pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", - hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + if (!node_specific_cma_alloc) { + /* + * If 3 GB area is requested on a machine with 4 numa nodes, + * let's allocate 1 GB on first three nodes and ignore the last one. + */ + per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); + pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", + hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + } reserved = 0; for_each_node_state(nid, N_ONLINE) { int res; char name[CMA_MAX_NAME]; - size = min(per_node, hugetlb_cma_size - reserved); + if (node_specific_cma_alloc) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + size = hugetlb_cma_size_in_node[nid]; + } else { + size = min(per_node, hugetlb_cma_size - reserved); + } + size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); - res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, + /* + * Note that 'order per bit' is based on smallest size that + * may be returned to CMA allocator in the case of + * huge page demotion. + */ + res = cma_declare_contiguous_nid(0, size, 0, + PAGE_SIZE << HUGETLB_PAGE_ORDER, 0, false, name, &hugetlb_cma[nid], nid); if (res) { @@ -6426,6 +6992,13 @@ void __init hugetlb_cma_reserve(int order) if (reserved >= hugetlb_cma_size) break; } + + if (!reserved) + /* + * hugetlb_cma_size is used to determine if allocations from + * cma are possible. Set to zero if no cma regions are set up. + */ + hugetlb_cma_size = 0; } void __init hugetlb_cma_check(void) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 5383023d0cca..79d93534ef1e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -27,9 +27,6 @@ #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -#define hugetlb_cgroup_from_counter(counter, idx) \ - container_of(counter, struct hugetlb_cgroup, hugepage[idx]) - static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static inline struct page_counter * diff --git a/mm/internal.h b/mm/internal.h index b1001ebeb286..3b79a5c9427a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -41,12 +41,33 @@ static inline void *folio_raw_mapping(struct folio *folio) return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } +void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, + int nr_throttled); +static inline void acct_reclaim_writeback(struct folio *folio) +{ + pg_data_t *pgdat = folio_pgdat(folio); + int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); + + if (nr_throttled) + __acct_reclaim_writeback(pgdat, folio, nr_throttled); +} + +static inline void wake_throttle_isolated(pg_data_t *pgdat) +{ + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; + if (waitqueue_active(wqh)) + wake_up(wqh); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); +void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { @@ -129,6 +150,7 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); +extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 2baf121fb8c5..8428da2aaf17 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -30,20 +30,20 @@ #include "kasan.h" #include "../slab.h" -depot_stack_handle_t kasan_save_stack(gfp_t flags) +depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc) { unsigned long entries[KASAN_STACK_DEPTH]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); nr_entries = filter_irq_stacks(entries, nr_entries); - return stack_depot_save(entries, nr_entries, flags); + return __stack_depot_save(entries, nr_entries, flags, can_alloc); } void kasan_set_track(struct kasan_track *track, gfp_t flags) { track->pid = current->pid; - track->stack = kasan_save_stack(flags); + track->stack = kasan_save_stack(flags, true); } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) @@ -298,7 +298,7 @@ static inline u8 assign_tag(struct kmem_cache *cache, /* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */ #ifdef CONFIG_SLAB /* For SLAB assign tags based on the object index in the freelist. */ - return (u8)obj_to_index(cache, virt_to_page(object), (void *)object); + return (u8)obj_to_index(cache, virt_to_head_page(object), (void *)object); #else /* * For SLUB assign a random tag during slab creation, otherwise reuse diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index c3f5ba7a294a..84a038b07c6f 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -328,7 +328,7 @@ DEFINE_ASAN_SET_SHADOW(f3); DEFINE_ASAN_SET_SHADOW(f5); DEFINE_ASAN_SET_SHADOW(f8); -void kasan_record_aux_stack(void *addr) +static void __kasan_record_aux_stack(void *addr, bool can_alloc) { struct page *page = kasan_addr_to_page(addr); struct kmem_cache *cache; @@ -345,7 +345,17 @@ void kasan_record_aux_stack(void *addr) return; alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0]; - alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT); + alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT, can_alloc); +} + +void kasan_record_aux_stack(void *addr) +{ + return __kasan_record_aux_stack(addr, true); +} + +void kasan_record_aux_stack_noalloc(void *addr) +{ + return __kasan_record_aux_stack(addr, false); } void kasan_set_free_info(struct kmem_cache *cache, diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index b495e17445ad..aebd8df86a1f 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -266,7 +266,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip); struct page *kasan_addr_to_page(const void *addr); -depot_stack_handle_t kasan_save_stack(gfp_t flags); +depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc); void kasan_set_track(struct kasan_track *track, gfp_t flags); void kasan_set_free_info(struct kmem_cache *cache, void *object, u8 tag); struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 8d95ee52d019..4a4929b29a23 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -254,6 +254,11 @@ core_initcall(kasan_memhotplug_init); #ifdef CONFIG_KASAN_VMALLOC +void __init __weak kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ +} + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, void *unused) { diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 7a97db8bc8e7..09945784df9e 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -10,12 +10,15 @@ #include <linux/atomic.h> #include <linux/bug.h> #include <linux/debugfs.h> +#include <linux/hash.h> #include <linux/irq_work.h> +#include <linux/jhash.h> #include <linux/kcsan-checks.h> #include <linux/kfence.h> #include <linux/kmemleak.h> #include <linux/list.h> #include <linux/lockdep.h> +#include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> #include <linux/random.h> @@ -82,6 +85,10 @@ static const struct kernel_param_ops sample_interval_param_ops = { }; module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); +/* Pool usage% threshold when currently covered allocations are skipped. */ +static unsigned long kfence_skip_covered_thresh __read_mostly = 75; +module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644); + /* The pool of pages used for guard pages and objects. */ char *__kfence_pool __ro_after_init; EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ @@ -97,14 +104,41 @@ struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ -#ifdef CONFIG_KFENCE_STATIC_KEYS -/* The static key to set up a KFENCE allocation. */ +/* + * The static key to set up a KFENCE allocation; or if static keys are not used + * to gate allocations, to avoid a load and compare if KFENCE is disabled. + */ DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); -#endif /* Gates the allocation, ensuring only one succeeds in a given period. */ atomic_t kfence_allocation_gate = ATOMIC_INIT(1); +/* + * A Counting Bloom filter of allocation coverage: limits currently covered + * allocations of the same source filling up the pool. + * + * Assuming a range of 15%-85% unique allocations in the pool at any point in + * time, the below parameters provide a probablity of 0.02-0.33 for false + * positive hits respectively: + * + * P(alloc_traces) = (1 - e^(-HNUM * (alloc_traces / SIZE)) ^ HNUM + */ +#define ALLOC_COVERED_HNUM 2 +#define ALLOC_COVERED_ORDER (const_ilog2(CONFIG_KFENCE_NUM_OBJECTS) + 2) +#define ALLOC_COVERED_SIZE (1 << ALLOC_COVERED_ORDER) +#define ALLOC_COVERED_HNEXT(h) hash_32(h, ALLOC_COVERED_ORDER) +#define ALLOC_COVERED_MASK (ALLOC_COVERED_SIZE - 1) +static atomic_t alloc_covered[ALLOC_COVERED_SIZE]; + +/* Stack depth used to determine uniqueness of an allocation. */ +#define UNIQUE_ALLOC_STACK_DEPTH ((size_t)8) + +/* + * Randomness for stack hashes, making the same collisions across reboots and + * different machines less likely. + */ +static u32 stack_hash_seed __ro_after_init; + /* Statistics counters for debugfs. */ enum kfence_counter_id { KFENCE_COUNTER_ALLOCATED, @@ -112,6 +146,9 @@ enum kfence_counter_id { KFENCE_COUNTER_FREES, KFENCE_COUNTER_ZOMBIES, KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_SKIP_INCOMPAT, + KFENCE_COUNTER_SKIP_CAPACITY, + KFENCE_COUNTER_SKIP_COVERED, KFENCE_COUNTER_COUNT, }; static atomic_long_t counters[KFENCE_COUNTER_COUNT]; @@ -121,11 +158,59 @@ static const char *const counter_names[] = { [KFENCE_COUNTER_FREES] = "total frees", [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", [KFENCE_COUNTER_BUGS] = "total bugs", + [KFENCE_COUNTER_SKIP_INCOMPAT] = "skipped allocations (incompatible)", + [KFENCE_COUNTER_SKIP_CAPACITY] = "skipped allocations (capacity)", + [KFENCE_COUNTER_SKIP_COVERED] = "skipped allocations (covered)", }; static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); /* === Internals ============================================================ */ +static inline bool should_skip_covered(void) +{ + unsigned long thresh = (CONFIG_KFENCE_NUM_OBJECTS * kfence_skip_covered_thresh) / 100; + + return atomic_long_read(&counters[KFENCE_COUNTER_ALLOCATED]) > thresh; +} + +static u32 get_alloc_stack_hash(unsigned long *stack_entries, size_t num_entries) +{ + num_entries = min(num_entries, UNIQUE_ALLOC_STACK_DEPTH); + num_entries = filter_irq_stacks(stack_entries, num_entries); + return jhash(stack_entries, num_entries * sizeof(stack_entries[0]), stack_hash_seed); +} + +/* + * Adds (or subtracts) count @val for allocation stack trace hash + * @alloc_stack_hash from Counting Bloom filter. + */ +static void alloc_covered_add(u32 alloc_stack_hash, int val) +{ + int i; + + for (i = 0; i < ALLOC_COVERED_HNUM; i++) { + atomic_add(val, &alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK]); + alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); + } +} + +/* + * Returns true if the allocation stack trace hash @alloc_stack_hash is + * currently contained (non-zero count) in Counting Bloom filter. + */ +static bool alloc_covered_contains(u32 alloc_stack_hash) +{ + int i; + + for (i = 0; i < ALLOC_COVERED_HNUM; i++) { + if (!atomic_read(&alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK])) + return false; + alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); + } + + return true; +} + static bool kfence_protect(unsigned long addr) { return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); @@ -183,19 +268,26 @@ static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *m * Update the object's metadata state, including updating the alloc/free stacks * depending on the state transition. */ -static noinline void metadata_update_state(struct kfence_metadata *meta, - enum kfence_object_state next) +static noinline void +metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state next, + unsigned long *stack_entries, size_t num_stack_entries) { struct kfence_track *track = next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; lockdep_assert_held(&meta->lock); - /* - * Skip over 1 (this) functions; noinline ensures we do not accidentally - * skip over the caller by never inlining. - */ - track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + if (stack_entries) { + memcpy(track->stack_entries, stack_entries, + num_stack_entries * sizeof(stack_entries[0])); + } else { + /* + * Skip over 1 (this) functions; noinline ensures we do not + * accidentally skip over the caller by never inlining. + */ + num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + } + track->num_stack_entries = num_stack_entries; track->pid = task_pid_nr(current); track->cpu = raw_smp_processor_id(); track->ts_nsec = local_clock(); /* Same source as printk timestamps. */ @@ -218,12 +310,19 @@ static inline bool set_canary_byte(u8 *addr) /* Check canary byte at @addr. */ static inline bool check_canary_byte(u8 *addr) { + struct kfence_metadata *meta; + unsigned long flags; + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, false, NULL, addr_to_metadata((unsigned long)addr), - KFENCE_ERROR_CORRUPTION); + + meta = addr_to_metadata((unsigned long)addr); + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_report_error((unsigned long)addr, false, NULL, meta, KFENCE_ERROR_CORRUPTION); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return false; } @@ -233,8 +332,6 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); unsigned long addr; - lockdep_assert_held(&meta->lock); - /* * We'll iterate over each canary byte per-side until fn() returns * false. However, we'll still iterate over the canary bytes to the @@ -257,7 +354,9 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, } } -static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp, + unsigned long *stack_entries, size_t num_stack_entries, + u32 alloc_stack_hash) { struct kfence_metadata *meta = NULL; unsigned long flags; @@ -271,8 +370,10 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g list_del_init(&meta->list); } raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); - if (!meta) + if (!meta) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_CAPACITY]); return NULL; + } if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { /* @@ -314,11 +415,14 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g addr = (void *)meta->addr; /* Update remaining metadata. */ - metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED, stack_entries, num_stack_entries); /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ WRITE_ONCE(meta->cache, cache); meta->size = size; - for_each_canary(meta, set_canary_byte); + meta->alloc_stack_hash = alloc_stack_hash; + raw_spin_unlock_irqrestore(&meta->lock, flags); + + alloc_covered_add(alloc_stack_hash, 1); /* Set required struct page fields. */ page = virt_to_page(meta->addr); @@ -328,9 +432,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g if (IS_ENABLED(CONFIG_SLAB)) page->s_mem = addr; - raw_spin_unlock_irqrestore(&meta->lock, flags); - /* Memory initialization. */ + for_each_canary(meta, set_canary_byte); /* * We check slab_want_init_on_alloc() ourselves, rather than letting @@ -355,6 +458,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z { struct kcsan_scoped_access assert_page_exclusive; unsigned long flags; + bool init; raw_spin_lock_irqsave(&meta->lock, flags); @@ -382,6 +486,13 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z meta->unprotected_page = 0; } + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0); + init = slab_want_init_on_free(meta->cache); + raw_spin_unlock_irqrestore(&meta->lock, flags); + + alloc_covered_add(meta->alloc_stack_hash, -1); + /* Check canary bytes for memory corruption. */ for_each_canary(meta, check_canary_byte); @@ -390,14 +501,9 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z * data is still there, and after a use-after-free is detected, we * unprotect the page, so the data is still accessible. */ - if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + if (!zombie && unlikely(init)) memzero_explicit(addr, meta->size); - /* Mark the object as freed. */ - metadata_update_state(meta, KFENCE_OBJECT_FREED); - - raw_spin_unlock_irqrestore(&meta->lock, flags); - /* Protect to detect use-after-frees. */ kfence_protect((unsigned long)addr); @@ -663,11 +769,14 @@ void __init kfence_init(void) if (!kfence_sample_interval) return; + stack_hash_seed = (u32)random_get_entropy(); if (!kfence_init_pool()) { pr_err("%s failed\n", __func__); return; } + if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS)) + static_branch_enable(&kfence_allocation_key); WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, @@ -736,12 +845,18 @@ void kfence_shutdown_cache(struct kmem_cache *s) void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { + unsigned long stack_entries[KFENCE_STACK_DEPTH]; + size_t num_stack_entries; + u32 alloc_stack_hash; + /* * Perform size check before switching kfence_allocation_gate, so that * we don't disable KFENCE without making an allocation. */ - if (size > PAGE_SIZE) + if (size > PAGE_SIZE) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; + } /* * Skip allocations from non-default zones, including DMA. We cannot @@ -749,15 +864,12 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || - (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) + (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; + } - /* - * allocation_gate only needs to become non-zero, so it doesn't make - * sense to continue writing to it and pay the associated contention - * cost, in case we have a large number of concurrent allocations. - */ - if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + if (atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; #ifdef CONFIG_KFENCE_STATIC_KEYS /* @@ -776,7 +888,25 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (!READ_ONCE(kfence_enabled)) return NULL; - return kfence_guarded_alloc(s, size, flags); + num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 0); + + /* + * Do expensive check for coverage of allocation in slow-path after + * allocation_gate has already become non-zero, even though it might + * mean not making any allocation within a given sample interval. + * + * This ensures reasonable allocation coverage when the pool is almost + * full, including avoiding long-lived allocations of the same source + * filling up the pool (e.g. pagecache allocations). + */ + alloc_stack_hash = get_alloc_stack_hash(stack_entries, num_stack_entries); + if (should_skip_covered() && alloc_covered_contains(alloc_stack_hash)) { + atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_COVERED]); + return NULL; + } + + return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries, + alloc_stack_hash); } size_t kfence_ksize(const void *addr) diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index c1f23c61e5f9..2a2d5de9d379 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -87,6 +87,8 @@ struct kfence_metadata { /* Allocation and free stack information. */ struct kfence_track alloc_track; struct kfence_track free_track; + /* For updating alloc_covered on frees. */ + u32 alloc_stack_hash; }; extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index f1690cf54199..695030c1fff8 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -32,6 +32,11 @@ #define arch_kfence_test_address(addr) (addr) #endif +#define KFENCE_TEST_REQUIRES(test, cond) do { \ + if (!(cond)) \ + kunit_skip((test), "Test requires: " #cond); \ +} while (0) + /* Report as observed from console. */ static struct { spinlock_t lock; @@ -555,8 +560,7 @@ static void test_init_on_free(struct kunit *test) }; int i; - if (!IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)) - return; + KFENCE_TEST_REQUIRES(test, IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)); /* Assume it hasn't been disabled on command line. */ setup_test_cache(test, size, 0, NULL); @@ -603,10 +607,8 @@ static void test_gfpzero(struct kunit *test) char *buf1, *buf2; int i; - if (CONFIG_KFENCE_SAMPLE_INTERVAL > 100) { - kunit_warn(test, "skipping ... would take too long\n"); - return; - } + /* Skip if we think it'd take too long. */ + KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100); setup_test_cache(test, size, 0, NULL); buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 5f02fda6f265..e99101162f1a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2299,6 +2299,11 @@ static void set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; + if (!khugepaged_enabled()) { + calculate_min_free_kbytes(); + goto update_wmarks; + } + for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of @@ -2334,6 +2339,8 @@ static void set_recommended_min_free_kbytes(void) min_free_kbytes = recommended_min; } + +update_wmarks: setup_per_zone_wmarks(); } @@ -2355,12 +2362,11 @@ int start_stop_khugepaged(void) if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); - - set_recommended_min_free_kbytes(); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } + set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; diff --git a/mm/list_lru.c b/mm/list_lru.c index cd58790d0fb3..0cd5e89ca063 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -15,18 +15,29 @@ #include "slab.h" #ifdef CONFIG_MEMCG_KMEM -static LIST_HEAD(list_lrus); +static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return lru->memcg_aware; +} + static void list_lru_register(struct list_lru *lru) { + if (!list_lru_memcg_aware(lru)) + return; + mutex_lock(&list_lrus_mutex); - list_add(&lru->list, &list_lrus); + list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { + if (!list_lru_memcg_aware(lru)) + return; + mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); @@ -37,11 +48,6 @@ static int lru_shrinker_id(struct list_lru *lru) return lru->shrinker_id; } -static inline bool list_lru_memcg_aware(struct list_lru *lru) -{ - return lru->memcg_aware; -} - static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) { @@ -176,13 +182,16 @@ unsigned long list_lru_count_one(struct list_lru *lru, { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; - unsigned long count; + long count; rcu_read_lock(); l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); count = READ_ONCE(l->nr_items); rcu_read_unlock(); + if (unlikely(count < 0)) + count = 0; + return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); @@ -354,8 +363,7 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) struct list_lru_memcg *memcg_lrus; int size = memcg_nr_cache_ids; - memcg_lrus = kvmalloc(sizeof(*memcg_lrus) + - size * sizeof(void *), GFP_KERNEL); + memcg_lrus = kvmalloc(struct_size(memcg_lrus, lru, size), GFP_KERNEL); if (!memcg_lrus) return -ENOMEM; @@ -389,7 +397,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, old = rcu_dereference_protected(nlru->memcg_lrus, lockdep_is_held(&list_lrus_mutex)); - new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL); + new = kvmalloc(struct_size(new, lru, new_size), GFP_KERNEL); if (!new) return -ENOMEM; @@ -398,19 +406,8 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, return -ENOMEM; } - memcpy(&new->lru, &old->lru, old_size * sizeof(void *)); - - /* - * The locking below allows readers that hold nlru->lock avoid taking - * rcu_read_lock (see list_lru_from_memcg_idx). - * - * Since list_lru_{add,del} may be called under an IRQ-safe lock, - * we have to use IRQ-safe primitives here to avoid deadlock. - */ - spin_lock_irq(&nlru->lock); + memcpy(&new->lru, &old->lru, flex_array_size(new, lru, old_size)); rcu_assign_pointer(nlru->memcg_lrus, new); - spin_unlock_irq(&nlru->lock); - kvfree_rcu(old, rcu); return 0; } @@ -466,9 +463,6 @@ static int memcg_update_list_lru(struct list_lru *lru, { int i; - if (!list_lru_memcg_aware(lru)) - return 0; - for_each_node(i) { if (memcg_update_list_lru_node(&lru->node[i], old_size, new_size)) @@ -491,9 +485,6 @@ static void memcg_cancel_update_list_lru(struct list_lru *lru, { int i; - if (!list_lru_memcg_aware(lru)) - return; - for_each_node(i) memcg_cancel_update_list_lru_node(&lru->node[i], old_size, new_size); @@ -506,7 +497,7 @@ int memcg_update_all_list_lrus(int new_size) int old_size = memcg_nr_cache_ids; mutex_lock(&list_lrus_mutex); - list_for_each_entry(lru, &list_lrus, list) { + list_for_each_entry(lru, &memcg_list_lrus, list) { ret = memcg_update_list_lru(lru, old_size, new_size); if (ret) goto fail; @@ -515,7 +506,7 @@ out: mutex_unlock(&list_lrus_mutex); return ret; fail: - list_for_each_entry_continue_reverse(lru, &list_lrus, list) + list_for_each_entry_continue_reverse(lru, &memcg_list_lrus, list) memcg_cancel_update_list_lru(lru, old_size, new_size); goto out; } @@ -552,9 +543,6 @@ static void memcg_drain_list_lru(struct list_lru *lru, { int i; - if (!list_lru_memcg_aware(lru)) - return; - for_each_node(i) memcg_drain_list_lru_node(lru, i, src_idx, dst_memcg); } @@ -564,7 +552,7 @@ void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg) struct list_lru *lru; mutex_lock(&list_lrus_mutex); - list_for_each_entry(lru, &list_lrus, list) + list_for_each_entry(lru, &memcg_list_lrus, list) memcg_drain_list_lru(lru, src_idx, dst_memcg); mutex_unlock(&list_lrus_mutex); } diff --git a/mm/memblock.c b/mm/memblock.c index 5096500b2647..659bf0ffb086 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,14 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } memblock_memory = NULL; @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free_ptr(old_array, old_alloc_size); + memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -655,6 +655,7 @@ repeat: * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details @@ -663,14 +664,14 @@ repeat: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, - int nid) + int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; - memblock_dbg("%s: [%pa-%pa] nid=%d %pS\n", __func__, - &base, &end, nid, (void *)_RET_IP_); + memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, + &base, &end, nid, flags, (void *)_RET_IP_); - return memblock_add_range(&memblock.memory, base, size, nid, 0); + return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** @@ -796,28 +797,28 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) } /** - * memblock_free_ptr - free boot memory allocation + * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -void __init_memblock memblock_free_ptr(void *ptr, size_t size) +void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } /** - * memblock_free - free boot memory block + * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; @@ -981,6 +982,10 @@ static bool should_skip_region(struct memblock_type *type, if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; + /* skip driver-managed memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) + return true; + return false; } @@ -1589,7 +1594,7 @@ void * __init memblock_alloc_try_nid( } /** - * __memblock_free_late - free pages directly to buddy allocator + * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * @@ -1597,7 +1602,7 @@ void * __init memblock_alloc_try_nid( * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ -void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; @@ -1937,7 +1942,7 @@ static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) * memmap array. */ if (pg < pgend) - memblock_free(pg, pgend - pg); + memblock_phys_free(pg, pgend - pg); } /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8dab23a71fc4..508bcea7df56 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -103,11 +103,6 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap; } -/* memcg and lruvec stats flushing */ -static void flush_memcg_stats_dwork(struct work_struct *w); -static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); -static DEFINE_SPINLOCK(stats_flush_lock); - #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 @@ -239,7 +234,7 @@ enum res_type { iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) -static inline bool should_force_charge(void) +static inline bool task_is_dying(void) { return tsk_is_oom_victim(current) || fatal_signal_pending(current) || (current->flags & PF_EXITING); @@ -613,6 +608,58 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) return mz; } +/* + * memcg and lruvec stats flushing + * + * Many codepaths leading to stats update or read are performance sensitive and + * adding stats flushing in such codepaths is not desirable. So, to optimize the + * flushing the kernel does: + * + * 1) Periodically and asynchronously flush the stats every 2 seconds to not let + * rstat update tree grow unbounded. + * + * 2) Flush the stats synchronously on reader side only when there are more than + * (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization + * will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but + * only for 2 seconds due to (1). + */ +static void flush_memcg_stats_dwork(struct work_struct *w); +static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); +static DEFINE_SPINLOCK(stats_flush_lock); +static DEFINE_PER_CPU(unsigned int, stats_updates); +static atomic_t stats_flush_threshold = ATOMIC_INIT(0); + +static inline void memcg_rstat_updated(struct mem_cgroup *memcg) +{ + cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); + if (!(__this_cpu_inc_return(stats_updates) % MEMCG_CHARGE_BATCH)) + atomic_inc(&stats_flush_threshold); +} + +static void __mem_cgroup_flush_stats(void) +{ + unsigned long flag; + + if (!spin_trylock_irqsave(&stats_flush_lock, flag)) + return; + + cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); + atomic_set(&stats_flush_threshold, 0); + spin_unlock_irqrestore(&stats_flush_lock, flag); +} + +void mem_cgroup_flush_stats(void) +{ + if (atomic_read(&stats_flush_threshold) > num_online_cpus()) + __mem_cgroup_flush_stats(); +} + +static void flush_memcg_stats_dwork(struct work_struct *w) +{ + mem_cgroup_flush_stats(); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); +} + /** * __mod_memcg_state - update cgroup memory statistics * @memcg: the memory cgroup @@ -625,7 +672,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) return; __this_cpu_add(memcg->vmstats_percpu->state[idx], val); - cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); + memcg_rstat_updated(memcg); } /* idx can be of type enum memcg_stat_item or node_stat_item. */ @@ -653,10 +700,12 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, memcg = pn->memcg; /* Update memcg */ - __mod_memcg_state(memcg, idx, val); + __this_cpu_add(memcg->vmstats_percpu->state[idx], val); /* Update lruvec */ __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val); + + memcg_rstat_updated(memcg); } /** @@ -758,7 +807,7 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, return; __this_cpu_add(memcg->vmstats_percpu->events[idx], count); - cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); + memcg_rstat_updated(memcg); } static unsigned long memcg_events(struct mem_cgroup *memcg, int event) @@ -1415,7 +1464,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) * * Current memory state: */ - cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats(); for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { u64 size; @@ -1576,7 +1625,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * A few threads which were not waiting at mutex_lock_killable() can * fail to bail out. Therefore, check again after holding oom_lock. */ - ret = should_force_charge() || out_of_memory(&oc); + ret = task_is_dying() || out_of_memory(&oc); unlock: mutex_unlock(&oom_lock); @@ -2544,6 +2593,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, struct page_counter *counter; enum oom_status oom_status; unsigned long nr_reclaimed; + bool passed_oom = false; bool may_swap = true; bool drained = false; unsigned long pflags; @@ -2579,15 +2629,6 @@ retry: goto force; /* - * Unlike in global OOM situations, memcg is not in a physical - * memory shortage. Allow dying and OOM-killed tasks to - * bypass the last charges so that they can exit quickly and - * free their memory. - */ - if (unlikely(should_force_charge())) - goto force; - - /* * Prevent unbounded recursion when reclaim operations need to * allocate memory. This might exceed the limits temporarily, * but we prefer facilitating memory reclaim and getting back @@ -2644,8 +2685,9 @@ retry: if (gfp_mask & __GFP_RETRY_MAYFAIL) goto nomem; - if (fatal_signal_pending(current)) - goto force; + /* Avoid endless loop for tasks bypassed by the oom killer */ + if (passed_oom && task_is_dying()) + goto nomem; /* * keep retrying as long as the memcg oom killer is able to make @@ -2654,14 +2696,10 @@ retry: */ oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages * PAGE_SIZE)); - switch (oom_status) { - case OOM_SUCCESS: + if (oom_status == OOM_SUCCESS) { + passed_oom = true; nr_retries = MAX_RECLAIM_RETRIES; goto retry; - case OOM_FAILED: - goto force; - default: - goto nomem; } nomem: if (!(gfp_mask & __GFP_NOFAIL)) @@ -2736,8 +2774,7 @@ static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, return try_charge_memcg(memcg, gfp_mask, nr_pages); } -#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) -static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) +static inline void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) return; @@ -2746,7 +2783,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); } -#endif static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { @@ -2965,7 +3001,6 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, unsigned int nr_pages) { - struct page_counter *counter; struct mem_cgroup *memcg; int ret; @@ -2975,21 +3010,8 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, if (ret) goto out; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && - !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { - - /* - * Enforce __GFP_NOFAIL allocation because callers are not - * prepared to see failures and likely do not have any failure - * handling code. - */ - if (gfp & __GFP_NOFAIL) { - page_counter_charge(&memcg->kmem, nr_pages); - goto out; - } - cancel_charge(memcg, nr_pages); - ret = -ENOMEM; - } + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_charge(&memcg->kmem, nr_pages); out: css_put(&memcg->css); @@ -3481,19 +3503,11 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) /* try to free all pages in this cgroup */ while (nr_retries && page_counter_read(&memcg->memory)) { - int progress; - if (signal_pending(current)) return -EINTR; - progress = try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, true); - if (!progress) { + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true)) nr_retries--; - /* maybe some writeback is necessary */ - congestion_wait(BLK_RW_ASYNC, HZ/10); - } - } return 0; @@ -3534,8 +3548,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - /* mem_cgroup_threshold() calls here from irqsafe context */ - cgroup_rstat_flush_irqsafe(memcg->css.cgroup); + mem_cgroup_flush_stats(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) @@ -3610,7 +3623,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) return 0; BUG_ON(memcg->kmemcg_id >= 0); - BUG_ON(memcg->kmem_state); memcg_id = memcg_alloc_cache_id(); if (memcg_id < 0) @@ -3627,22 +3639,18 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) static_branch_enable(&memcg_kmem_enabled_key); memcg->kmemcg_id = memcg_id; - memcg->kmem_state = KMEM_ONLINE; return 0; } static void memcg_offline_kmem(struct mem_cgroup *memcg) { - struct cgroup_subsys_state *css; - struct mem_cgroup *parent, *child; + struct mem_cgroup *parent; int kmemcg_id; - if (memcg->kmem_state != KMEM_ONLINE) + if (memcg->kmemcg_id == -1) return; - memcg->kmem_state = KMEM_ALLOCATED; - parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; @@ -3653,31 +3661,15 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) BUG_ON(kmemcg_id < 0); /* - * Change kmemcg_id of this cgroup and all its descendants to the - * parent's id, and then move all entries from this cgroup's list_lrus - * to ones of the parent. After we have finished, all list_lrus - * corresponding to this cgroup are guaranteed to remain empty. The - * ordering is imposed by list_lru_node->lock taken by + * After we have finished memcg_reparent_objcgs(), all list_lrus + * corresponding to this cgroup are guaranteed to remain empty. + * The ordering is imposed by list_lru_node->lock taken by * memcg_drain_all_list_lrus(). */ - rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */ - css_for_each_descendant_pre(css, &memcg->css) { - child = mem_cgroup_from_css(css); - BUG_ON(child->kmemcg_id != kmemcg_id); - child->kmemcg_id = parent->kmemcg_id; - } - rcu_read_unlock(); - memcg_drain_all_list_lrus(kmemcg_id, parent); memcg_free_cache_id(kmemcg_id); -} - -static void memcg_free_kmem(struct mem_cgroup *memcg) -{ - /* css_alloc() failed, offlining didn't happen */ - if (unlikely(memcg->kmem_state == KMEM_ONLINE)) - memcg_offline_kmem(memcg); + memcg->kmemcg_id = -1; } #else static int memcg_online_kmem(struct mem_cgroup *memcg) @@ -3687,22 +3679,8 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) static void memcg_offline_kmem(struct mem_cgroup *memcg) { } -static void memcg_free_kmem(struct mem_cgroup *memcg) -{ -} #endif /* CONFIG_MEMCG_KMEM */ -static int memcg_update_kmem_max(struct mem_cgroup *memcg, - unsigned long max) -{ - int ret; - - mutex_lock(&memcg_max_mutex); - ret = page_counter_set_max(&memcg->kmem, max); - mutex_unlock(&memcg_max_mutex); - return ret; -} - static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max) { int ret; @@ -3768,10 +3746,8 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; case _KMEM: - pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); - ret = memcg_update_kmem_max(memcg, nr_pages); + /* kmem.limit_in_bytes is deprecated. */ + ret = -EOPNOTSUPP; break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); @@ -3916,7 +3892,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) int nid; struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats(); for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { seq_printf(m, "%s=%lu", stat->name, @@ -3988,7 +3964,7 @@ static int memcg_stat_show(struct seq_file *m, void *v) BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); - cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats(); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; @@ -4491,7 +4467,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - cgroup_rstat_flush_irqsafe(memcg->css.cgroup); + mem_cgroup_flush_stats(); *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); @@ -5324,7 +5300,9 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) cancel_work_sync(&memcg->high_work); mem_cgroup_remove_from_trees(memcg); free_shrinker_info(memcg); - memcg_free_kmem(memcg); + + /* Need to offline kmem if online_css() fails */ + memcg_offline_kmem(memcg); mem_cgroup_free(memcg); } @@ -5357,21 +5335,6 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) memcg_wb_domain_size_changed(memcg); } -void mem_cgroup_flush_stats(void) -{ - if (!spin_trylock(&stats_flush_lock)) - return; - - cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); - spin_unlock(&stats_flush_lock); -} - -static void flush_memcg_stats_dwork(struct work_struct *w) -{ - mem_cgroup_flush_stats(); - queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); -} - static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); @@ -5561,7 +5524,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, #endif static struct page *mc_handle_file_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, swp_entry_t *entry) + unsigned long addr, pte_t ptent) { if (!vma->vm_file) /* anonymous vma */ return NULL; @@ -5736,7 +5699,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, ptent, &ent); else if (pte_none(ptent)) - page = mc_handle_file_pte(vma, addr, ptent, &ent); + page = mc_handle_file_pte(vma, addr, ptent); if (!page && !ent.val) return ret; @@ -6391,7 +6354,7 @@ static int memory_numa_stat_show(struct seq_file *m, void *v) int i; struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats(); for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { int nid; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ff51edd6e992..f64ebb6226cb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -39,6 +39,7 @@ #include <linux/kernel-page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> +#include <linux/dax.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> @@ -57,6 +58,7 @@ #include <linux/ratelimit.h> #include <linux/page-isolation.h> #include <linux/pagewalk.h> +#include <linux/shmem_fs.h> #include "internal.h" #include "ras/ras_event.h" @@ -673,7 +675,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, #define hwpoison_hugetlb_range NULL #endif -static struct mm_walk_ops hwp_walk_ops = { +static const struct mm_walk_ops hwp_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, }; @@ -806,12 +808,44 @@ static int truncate_error_page(struct page *p, unsigned long pfn, return ret; } +struct page_state { + unsigned long mask; + unsigned long res; + enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ + int (*action)(struct page_state *ps, struct page *p); +}; + +/* + * Return true if page is still referenced by others, otherwise return + * false. + * + * The extra_pins is true when one extra refcount is expected. + */ +static bool has_extra_refcount(struct page_state *ps, struct page *p, + bool extra_pins) +{ + int count = page_count(p) - 1; + + if (extra_pins) + count -= 1; + + if (count > 0) { + pr_err("Memory failure: %#lx: %s still referenced by %d users\n", + page_to_pfn(p), action_page_types[ps->type], count); + return true; + } + + return false; +} + /* * Error hit kernel page. * Do nothing, try to be lucky and not touch this instead. For a few cases we * could be more sophisticated. */ -static int me_kernel(struct page *p, unsigned long pfn) +static int me_kernel(struct page_state *ps, struct page *p) { unlock_page(p); return MF_IGNORED; @@ -820,9 +854,9 @@ static int me_kernel(struct page *p, unsigned long pfn) /* * Page in unknown state. Do nothing. */ -static int me_unknown(struct page *p, unsigned long pfn) +static int me_unknown(struct page_state *ps, struct page *p) { - pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + pr_err("Memory failure: %#lx: Unknown page state\n", page_to_pfn(p)); unlock_page(p); return MF_FAILED; } @@ -830,10 +864,11 @@ static int me_unknown(struct page *p, unsigned long pfn) /* * Clean (or cleaned) page cache page. */ -static int me_pagecache_clean(struct page *p, unsigned long pfn) +static int me_pagecache_clean(struct page_state *ps, struct page *p) { int ret; struct address_space *mapping; + bool extra_pins; delete_from_lru_cache(p); @@ -863,13 +898,23 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) } /* + * The shmem page is kept in page cache instead of truncating + * so is expected to have an extra refcount after error-handling. + */ + extra_pins = shmem_mapping(mapping); + + /* * Truncation is a bit tricky. Enable it per file system for now. * * Open: to take i_rwsem or not for this? Right now we don't. */ - ret = truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, page_to_pfn(p), mapping); + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + out: unlock_page(p); + return ret; } @@ -878,7 +923,7 @@ out: * Issues: when the error hit a hole page the error is not properly * propagated. */ -static int me_pagecache_dirty(struct page *p, unsigned long pfn) +static int me_pagecache_dirty(struct page_state *ps, struct page *p) { struct address_space *mapping = page_mapping(p); @@ -922,7 +967,7 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) mapping_set_error(mapping, -EIO); } - return me_pagecache_clean(p, pfn); + return me_pagecache_clean(ps, p); } /* @@ -944,9 +989,10 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) * Clean swap cache pages can be directly isolated. A later page fault will * bring in the known good data from disk. */ -static int me_swapcache_dirty(struct page *p, unsigned long pfn) +static int me_swapcache_dirty(struct page_state *ps, struct page *p) { int ret; + bool extra_pins = false; ClearPageDirty(p); /* Trigger EIO in shmem: */ @@ -954,10 +1000,17 @@ static int me_swapcache_dirty(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; unlock_page(p); + + if (ret == MF_DELAYED) + extra_pins = true; + + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + return ret; } -static int me_swapcache_clean(struct page *p, unsigned long pfn) +static int me_swapcache_clean(struct page_state *ps, struct page *p) { int ret; @@ -965,6 +1018,10 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; unlock_page(p); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } @@ -974,7 +1031,7 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) * - Error on hugepage is contained in hugepage unit (not in raw page unit.) * To narrow down kill region to one page, we need to break up pmd. */ -static int me_huge_page(struct page *p, unsigned long pfn) +static int me_huge_page(struct page_state *ps, struct page *p) { int res; struct page *hpage = compound_head(p); @@ -985,7 +1042,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { - res = truncate_error_page(hpage, pfn, mapping); + res = truncate_error_page(hpage, page_to_pfn(p), mapping); unlock_page(hpage); } else { res = MF_FAILED; @@ -1003,6 +1060,9 @@ static int me_huge_page(struct page *p, unsigned long pfn) } } + if (has_extra_refcount(ps, p, false)) + res = MF_FAILED; + return res; } @@ -1028,14 +1088,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) #define slab (1UL << PG_slab) #define reserved (1UL << PG_reserved) -static struct page_state { - unsigned long mask; - unsigned long res; - enum mf_action_page_type type; - - /* Callback ->action() has to unlock the relevant page inside it. */ - int (*action)(struct page *p, unsigned long pfn); -} error_states[] = { +static struct page_state error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: @@ -1095,19 +1148,10 @@ static int page_action(struct page_state *ps, struct page *p, unsigned long pfn) { int result; - int count; /* page p should be unlocked after returning from ps->action(). */ - result = ps->action(p, pfn); + result = ps->action(ps, p); - count = page_count(p) - 1; - if (ps->action == me_swapcache_dirty && result == MF_DELAYED) - count--; - if (count > 0) { - pr_err("Memory failure: %#lx: %s still referenced by %d users\n", - pfn, action_page_types[ps->type], count); - result = MF_FAILED; - } action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ @@ -1400,14 +1444,11 @@ static int identify_page_state(unsigned long pfn, struct page *p, static int try_to_split_thp_page(struct page *page, const char *msg) { lock_page(page); - if (!PageAnon(page) || unlikely(split_huge_page(page))) { + if (unlikely(split_huge_page(page))) { unsigned long pfn = page_to_pfn(page); unlock_page(page); - if (!PageAnon(page)) - pr_info("%s: %#lx: non anonymous thp\n", msg, pfn); - else - pr_info("%s: %#lx: thp split failed\n", msg, pfn); + pr_info("%s: %#lx: thp split failed\n", msg, pfn); put_page(page); return -EBUSY; } diff --git a/mm/memory.c b/mm/memory.c index bcc4b0727a63..8f1de811a1dc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -433,35 +433,39 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, } } -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) +void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) { - spinlock_t *ptl; - pgtable_t new = pte_alloc_one(mm); - if (!new) - return -ENOMEM; + spinlock_t *ptl = pmd_lock(mm, pmd); - /* - * Ensure all pte setup (eg. pte page lock and page clearing) are - * visible before the pte is made visible to other CPUs by being - * put into page tables. - * - * The other side of the story is the pointer chasing in the page - * table walking code (when walking the page table without locking; - * ie. most of the time). Fortunately, these data accesses consist - * of a chain of data-dependent loads, meaning most CPUs (alpha - * being the notable exception) will already guarantee loads are - * seen in-order. See the alpha page table accessors for the - * smp_rmb() barriers in page table walking code. - */ - smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ - - ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); - pmd_populate(mm, pmd, new); - new = NULL; + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_rmb() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + pmd_populate(mm, pmd, *pte); + *pte = NULL; } spin_unlock(ptl); +} + +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) +{ + pgtable_t new = pte_alloc_one(mm); + if (!new) + return -ENOMEM; + + pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; @@ -473,10 +477,9 @@ int __pte_alloc_kernel(pmd_t *pmd) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + smp_wmb(); /* See comment in pmd_install() */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } @@ -1333,16 +1336,8 @@ again: struct page *page; page = vm_normal_page(vma, addr, ptent); - if (unlikely(details) && page) { - /* - * unmap_shared_mapping_pages() wants to - * invalidate cache without truncating: - * unmap shared but keep private pages. - */ - if (details->check_mapping && - details->check_mapping != page_rmapping(page)) - continue; - } + if (unlikely(zap_skip_check_mapping(details, page))) + continue; ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); @@ -1375,17 +1370,8 @@ again: is_device_exclusive_entry(entry)) { struct page *page = pfn_swap_entry_to_page(entry); - if (unlikely(details && details->check_mapping)) { - /* - * unmap_shared_mapping_pages() wants to - * invalidate cache without truncating: - * unmap shared but keep private pages. - */ - if (details->check_mapping != - page_rmapping(page)) - continue; - } - + if (unlikely(zap_skip_check_mapping(details, page))) + continue; pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; @@ -2724,19 +2710,19 @@ EXPORT_SYMBOL_GPL(apply_to_existing_page_range); * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ -static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, - pte_t *page_table, pte_t orig_pte) +static inline int pte_unmap_same(struct vm_fault *vmf) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { - spinlock_t *ptl = pte_lockptr(mm, pmd); + spinlock_t *ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(ptl); - same = pte_same(*page_table, orig_pte); + same = pte_same(*vmf->pte, vmf->orig_pte); spin_unlock(ptl); } #endif - pte_unmap(page_table); + pte_unmap(vmf->pte); + vmf->pte = NULL; return same; } @@ -3321,20 +3307,20 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, + pgoff_t first_index, + pgoff_t last_index, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; - vma_interval_tree_foreach(vma, root, - details->first_index, details->last_index) { - + vma_interval_tree_foreach(vma, root, first_index, last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; - zba = details->first_index; + zba = first_index; if (zba < vba) zba = vba; - zea = details->last_index; + zea = last_index; if (zea > vea) zea = vea; @@ -3360,18 +3346,22 @@ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; + pgoff_t first_index; + pgoff_t last_index; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); - details.check_mapping = mapping; - details.first_index = page->index; - details.last_index = page->index + thp_nr_pages(page) - 1; + first_index = page->index; + last_index = page->index + thp_nr_pages(page) - 1; + + details.zap_mapping = mapping; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); i_mmap_unlock_write(mapping); } @@ -3391,16 +3381,17 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; + pgoff_t first_index = start; + pgoff_t last_index = start + nr - 1; - details.check_mapping = even_cows ? NULL : mapping; - details.first_index = start; - details.last_index = start + nr - 1; - if (details.last_index < details.first_index) - details.last_index = ULONG_MAX; + details.zap_mapping = even_cows ? NULL : mapping; + if (last_index < first_index) + last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); @@ -3488,7 +3479,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) vm_fault_t ret = 0; void *shadow = NULL; - if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) + if (!pte_unmap_same(vmf)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); @@ -3853,7 +3844,6 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; - smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); @@ -3924,7 +3914,6 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; - smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); @@ -4037,17 +4026,10 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return ret; } - if (vmf->prealloc_pte) { - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (likely(pmd_none(*vmf->pmd))) { - mm_inc_nr_ptes(vma->vm_mm); - pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); - vmf->prealloc_pte = NULL; - } - spin_unlock(vmf->ptl); - } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { + if (vmf->prealloc_pte) + pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); + else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) return VM_FAULT_OOM; - } } /* See comment in handle_pte_fault() */ @@ -4156,7 +4138,6 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; - smp_wmb(); /* See comment in __pte_alloc() */ } return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); @@ -4831,13 +4812,13 @@ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ + if (pgd_present(*pgd)) { /* Another has populated it */ p4d_free(mm, new); - else + } else { + smp_wmb(); /* See comment in pmd_install() */ pgd_populate(mm, pgd, new); + } spin_unlock(&mm->page_table_lock); return 0; } @@ -4854,11 +4835,10 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); + smp_wmb(); /* See comment in pmd_install() */ p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); @@ -4879,14 +4859,14 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); + smp_wmb(); /* See comment in pmd_install() */ pud_populate(mm, pud, new); - } else /* Another has populated it */ + } else { /* Another has populated it */ pmd_free(mm, new); + } spin_unlock(ptl); return 0; } @@ -5423,7 +5403,6 @@ long copy_huge_page_from_user(struct page *dst_page, unsigned int pages_per_huge_page, bool allow_pagefault) { - void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; @@ -5436,8 +5415,7 @@ long copy_huge_page_from_user(struct page *dst_page, else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, - (const void __user *)(src + i * PAGE_SIZE), - PAGE_SIZE); + usr_src + i * PAGE_SIZE, PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fd0be32a281..852041f6be41 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -21,7 +21,6 @@ #include <linux/memory.h> #include <linux/memremap.h> #include <linux/memory_hotplug.h> -#include <linux/highmem.h> #include <linux/vmalloc.h> #include <linux/ioport.h> #include <linux/delay.h> @@ -57,7 +56,7 @@ enum { ONLINE_POLICY_AUTO_MOVABLE, }; -const char *online_policy_to_str[] = { +static const char * const online_policy_to_str[] = { [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", }; @@ -220,7 +219,6 @@ static void release_memory_resource(struct resource *res) kfree(res); } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -586,10 +584,6 @@ void generic_online_page(struct page *page, unsigned int order) debug_pagealloc_map_pages(page, 1 << order); __free_pages_core(page, order); totalram_pages_add(1UL << order); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(1UL << order); -#endif } EXPORT_SYMBOL_GPL(generic_online_page); @@ -626,16 +620,11 @@ static void node_states_check_changes_online(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; -#ifdef CONFIG_HIGHMEM - if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY)) - arg->status_change_nid_high = nid; -#endif } static void node_states_set_node(int node, struct memory_notify *arg) @@ -643,9 +632,6 @@ static void node_states_set_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_set_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_set_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_set_state(node, N_MEMORY); } @@ -1163,7 +1149,6 @@ failed_addition: mem_hotplug_done(); return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static void reset_node_present_pages(pg_data_t *pgdat) { @@ -1357,6 +1342,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + enum memblock_flags memblock_flags = MEMBLOCK_NONE; struct vmem_altmap mhp_altmap = {}; struct memory_group *group = NULL; u64 start, size; @@ -1384,8 +1370,13 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); - if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) - memblock_add_node(start, size, nid); + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { + if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) + memblock_flags = MEMBLOCK_DRIVER_MANAGED; + ret = memblock_add_node(start, size, nid, memblock_flags); + if (ret) + goto error_mem_hotplug_end; + } ret = __try_online_node(nid, false); if (ret < 0) @@ -1458,6 +1449,7 @@ error: rollback_node_hotadd(nid); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); +error_mem_hotplug_end: mem_hotplug_done(); return ret; } @@ -1803,7 +1795,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. @@ -1818,24 +1809,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); -#ifdef CONFIG_HIGHMEM /* - * node_states[N_HIGH_MEMORY] contains nodes which - * have normal memory or high memory. - * Here we add the present_pages belonging to ZONE_HIGHMEM. - * If the zone is within the range of [0..ZONE_HIGHMEM), and - * we determine that the zones in that range become empty, - * we need to clear the node for N_HIGH_MEMORY. - */ - present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; - if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) - arg->status_change_nid_high = zone_to_nid(zone); -#endif - - /* - * We have accounted the pages from [0..ZONE_NORMAL), and - * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM - * as well. + * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM + * does not apply as we don't support 32bit. * Here we count the possible pages from ZONE_MOVABLE. * If after having accounted all the pages, we see that the nr_pages * to be offlined is over or equal to the accounted pages, @@ -1853,9 +1829,6 @@ static void node_states_clear_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_clear_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_clear_state(node, N_MEMORY); } @@ -2204,7 +2177,7 @@ static int __ref try_remove_memory(u64 start, u64 size) arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - memblock_free(start, size); + memblock_phys_free(start, size); memblock_remove(start, size); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f4b4be7af4d3..10e9c87260ed 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2206,6 +2206,88 @@ struct folio *folio_alloc(gfp_t gfp, unsigned order) } EXPORT_SYMBOL(folio_alloc); +static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + int nodes; + unsigned long nr_pages_per_node; + int delta; + int i; + unsigned long nr_allocated; + unsigned long total_allocated = 0; + + nodes = nodes_weight(pol->nodes); + nr_pages_per_node = nr_pages / nodes; + delta = nr_pages - nodes * nr_pages_per_node; + + for (i = 0; i < nodes; i++) { + if (delta) { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node + 1, NULL, + page_array); + delta--; + } else { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node, NULL, page_array); + } + + page_array += nr_allocated; + total_allocated += nr_allocated; + } + + return total_allocated; +} + +static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + gfp_t preferred_gfp; + unsigned long nr_allocated = 0; + + preferred_gfp = gfp | __GFP_NOWARN; + preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); + + nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes, + nr_pages, NULL, page_array); + + if (nr_allocated < nr_pages) + nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL, + nr_pages - nr_allocated, NULL, + page_array + nr_allocated); + return nr_allocated; +} + +/* alloc pages bulk and mempolicy should be considered at the + * same time in some situation such as vmalloc. + * + * It can accelerate memory allocation especially interleaving + * allocate memory. + */ +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, struct page **page_array) +{ + struct mempolicy *pol = &default_policy; + + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + if (pol->mode == MPOL_INTERLEAVE) + return alloc_pages_bulk_array_interleave(gfp, pol, + nr_pages, page_array); + + if (pol->mode == MPOL_PREFERRED_MANY) + 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); +} + int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); @@ -2985,64 +3067,3 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } - -bool numa_demotion_enabled = false; - -#ifdef CONFIG_SYSFS -static ssize_t numa_demotion_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%s\n", - numa_demotion_enabled? "true" : "false"); -} - -static ssize_t numa_demotion_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - numa_demotion_enabled = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - numa_demotion_enabled = false; - else - return -EINVAL; - - return count; -} - -static struct kobj_attribute numa_demotion_enabled_attr = - __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, - numa_demotion_enabled_store); - -static struct attribute *numa_attrs[] = { - &numa_demotion_enabled_attr.attr, - NULL, -}; - -static const struct attribute_group numa_attr_group = { - .attrs = numa_attrs, -}; - -static int __init numa_init_sysfs(void) -{ - int err; - struct kobject *numa_kobj; - - numa_kobj = kobject_create_and_add("numa", mm_kobj); - if (!numa_kobj) { - pr_err("failed to create numa kobject\n"); - return -ENOMEM; - } - err = sysfs_create_group(numa_kobj, &numa_attr_group); - if (err) { - pr_err("failed to register numa group\n"); - goto delete_obj; - } - return 0; - -delete_obj: - kobject_put(numa_kobj); - return err; -} -subsys_initcall(numa_init_sysfs); -#endif diff --git a/mm/migrate.c b/mm/migrate.c index efa9941ebe03..a11e948593df 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -3305,3 +3305,64 @@ static int __init migrate_on_reclaim_init(void) } late_initcall(migrate_on_reclaim_init); #endif /* CONFIG_HOTPLUG_CPU */ + +bool numa_demotion_enabled = false; + +#ifdef CONFIG_SYSFS +static ssize_t numa_demotion_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", + numa_demotion_enabled ? "true" : "false"); +} + +static ssize_t numa_demotion_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + numa_demotion_enabled = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + numa_demotion_enabled = false; + else + return -EINVAL; + + return count; +} + +static struct kobj_attribute numa_demotion_enabled_attr = + __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, + numa_demotion_enabled_store); + +static struct attribute *numa_attrs[] = { + &numa_demotion_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group numa_attr_group = { + .attrs = numa_attrs, +}; + +static int __init numa_init_sysfs(void) +{ + int err; + struct kobject *numa_kobj; + + numa_kobj = kobject_create_and_add("numa", mm_kobj); + if (!numa_kobj) { + pr_err("failed to create numa kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(numa_kobj, &numa_attr_group); + if (err) { + pr_err("failed to register numa group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(numa_kobj); + return err; +} +subsys_initcall(numa_init_sysfs); +#endif diff --git a/mm/mmap.c b/mm/mmap.c index 88dcc5c25225..b22a07f5e761 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3332,7 +3332,7 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { - mm->total_vm += npages; + WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; diff --git a/mm/mprotect.c b/mm/mprotect.c index 883e2cc85cad..e552f5e0ccbd 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -563,7 +563,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, error = -ENOMEM; if (!vma) goto out; - prev = vma->vm_prev; + if (unlikely(grows & PROT_GROWSDOWN)) { if (vma->vm_start >= end) goto out; @@ -581,8 +581,11 @@ static int do_mprotect_pkey(unsigned long start, size_t len, goto out; } } + if (start > vma->vm_start) prev = vma; + else + prev = vma->vm_prev; for (nstart = start ; ; ) { unsigned long mask_off_old_flags; diff --git a/mm/mremap.c b/mm/mremap.c index badfe17ade1f..002eec83e91e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -489,6 +489,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); + if (is_vm_hugetlb_page(vma)) + return move_hugetlb_page_tables(vma, new_vma, old_addr, + new_addr, len); + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, old_addr, old_end); mmu_notifier_invalidate_range_start(&range); @@ -565,6 +569,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, bool *locked, unsigned long flags, struct vm_userfaultfd_ctx *uf, struct list_head *uf_unmap) { + long to_account = new_len - old_len; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; unsigned long vm_flags = vma->vm_flags; @@ -583,6 +588,9 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (mm->map_count >= sysctl_max_map_count - 3) return -ENOMEM; + if (unlikely(flags & MREMAP_DONTUNMAP)) + to_account = new_len; + if (vma->vm_ops && vma->vm_ops->may_split) { if (vma->vm_start != old_addr) err = vma->vm_ops->may_split(vma, old_addr); @@ -604,8 +612,8 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (err) return err; - if (unlikely(flags & MREMAP_DONTUNMAP && vm_flags & VM_ACCOUNT)) { - if (security_vm_enough_memory_mm(mm, new_len >> PAGE_SHIFT)) + if (vm_flags & VM_ACCOUNT) { + if (security_vm_enough_memory_mm(mm, to_account >> PAGE_SHIFT)) return -ENOMEM; } @@ -613,8 +621,8 @@ static unsigned long move_vma(struct vm_area_struct *vma, new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff, &need_rmap_locks); if (!new_vma) { - if (unlikely(flags & MREMAP_DONTUNMAP && vm_flags & VM_ACCOUNT)) - vm_unacct_memory(new_len >> PAGE_SHIFT); + if (vm_flags & VM_ACCOUNT) + vm_unacct_memory(to_account >> PAGE_SHIFT); return -ENOMEM; } @@ -642,6 +650,10 @@ static unsigned long move_vma(struct vm_area_struct *vma, mremap_userfaultfd_prep(new_vma, uf); } + if (is_vm_hugetlb_page(vma)) { + clear_vma_resv_huge_pages(vma); + } + /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { vma->vm_flags &= ~VM_ACCOUNT; @@ -708,8 +720,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, } static struct vm_area_struct *vma_to_resize(unsigned long addr, - unsigned long old_len, unsigned long new_len, unsigned long flags, - unsigned long *p) + unsigned long old_len, unsigned long new_len, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -736,9 +747,6 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))) return ERR_PTR(-EINVAL); - if (is_vm_hugetlb_page(vma)) - return ERR_PTR(-EINVAL); - /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) return ERR_PTR(-EFAULT); @@ -768,13 +776,6 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, (new_len - old_len) >> PAGE_SHIFT)) return ERR_PTR(-ENOMEM); - if (vma->vm_flags & VM_ACCOUNT) { - unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; - if (security_vm_enough_memory_mm(mm, charged)) - return ERR_PTR(-ENOMEM); - *p = charged; - } - return vma; } @@ -787,7 +788,6 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long ret = -EINVAL; - unsigned long charged = 0; unsigned long map_flags = 0; if (offset_in_page(new_addr)) @@ -830,7 +830,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, old_len = new_len; } - vma = vma_to_resize(addr, old_len, new_len, flags, &charged); + vma = vma_to_resize(addr, old_len, new_len, flags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; @@ -853,7 +853,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); if (IS_ERR_VALUE(ret)) - goto out1; + goto out; /* We got a new mapping */ if (!(flags & MREMAP_FIXED)) @@ -862,12 +862,6 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf, uf_unmap); - if (!(offset_in_page(ret))) - goto out; - -out1: - vm_unacct_memory(charged); - out: return ret; } @@ -899,7 +893,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long ret = -EINVAL; - unsigned long charged = 0; bool locked = false; bool downgraded = false; struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; @@ -949,6 +942,31 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (mmap_write_lock_killable(current->mm)) return -EINTR; + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) { + ret = EFAULT; + goto out; + } + + if (is_vm_hugetlb_page(vma)) { + struct hstate *h __maybe_unused = hstate_vma(vma); + + old_len = ALIGN(old_len, huge_page_size(h)); + new_len = ALIGN(new_len, huge_page_size(h)); + + /* addrs must be huge page aligned */ + if (addr & ~huge_page_mask(h)) + goto out; + if (new_addr & ~huge_page_mask(h)) + goto out; + + /* + * Don't allow remap expansion, because the underlying hugetlb + * reservation is not yet capable to handle split reservation. + */ + if (new_len > old_len) + goto out; + } if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) { ret = mremap_to(addr, old_len, new_addr, new_len, @@ -981,7 +999,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Ok, we need to grow.. */ - vma = vma_to_resize(addr, old_len, new_len, flags, &charged); + vma = vma_to_resize(addr, old_len, new_len, flags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; @@ -992,10 +1010,18 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (old_len == vma->vm_end - addr) { /* can we just expand the current mapping? */ if (vma_expandable(vma, new_len - old_len)) { - int pages = (new_len - old_len) >> PAGE_SHIFT; + long pages = (new_len - old_len) >> PAGE_SHIFT; + + if (vma->vm_flags & VM_ACCOUNT) { + if (security_vm_enough_memory_mm(mm, pages)) { + ret = -ENOMEM; + goto out; + } + } if (vma_adjust(vma, vma->vm_start, addr + new_len, vma->vm_pgoff, NULL)) { + vm_unacct_memory(pages); ret = -ENOMEM; goto out; } @@ -1034,10 +1060,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, &locked, flags, &uf, &uf_unmap); } out: - if (offset_in_page(ret)) { - vm_unacct_memory(charged); + if (offset_in_page(ret)) locked = false; - } if (downgraded) mmap_read_unlock(current->mm); else diff --git a/mm/nommu.c b/mm/nommu.c index 41ef204e7482..55a9e48a7a02 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1638,12 +1638,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - return -ENOMEM; -} - vm_fault_t filemap_fault(struct vm_fault *vmf) { BUG(); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 50b984d048ce..195b3661da3d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -641,6 +641,8 @@ done: static int oom_reaper(void *unused) { + set_freezable(); + while (true) { struct task_struct *tsk = NULL; @@ -1120,27 +1122,24 @@ bool out_of_memory(struct oom_control *oc) } /* - * The pagefault handler calls here because it is out of memory, so kill a - * memory-hogging task. If oom_lock is held by somebody else, a parallel oom - * killing is already in progress so do nothing. + * The pagefault handler calls here because some allocation has failed. We have + * to take care of the memcg OOM here because this is the only safe context without + * any locks held but let the oom killer triggered from the allocation context care + * about the global OOM. */ void pagefault_out_of_memory(void) { - struct oom_control oc = { - .zonelist = NULL, - .nodemask = NULL, - .memcg = NULL, - .gfp_mask = 0, - .order = 0, - }; + static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); if (mem_cgroup_oom_synchronize(true)) return; - if (!mutex_trylock(&oom_lock)) + if (fatal_signal_pending(current)) return; - out_of_memory(&oc); - mutex_unlock(&oom_lock); + + if (__ratelimit(&pfoom_rs)) + pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n"); } SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 9c64490171e0..2d498bb62248 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2366,8 +2366,15 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) ret = generic_writepages(mapping, wbc); if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) break; - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + + /* + * Lacking an allocation context or the locality or writeback + * state of any of the inode's pages, throttle based on + * writeback activity on the local node. It's as good a + * guess as any. + */ + reclaim_throttle(NODE_DATA(numa_node_id()), + VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fee18ada46a2..c5952749ad40 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -677,10 +677,8 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order > PAGE_ALLOC_COSTLY_ORDER) { + if (order > PAGE_ALLOC_COSTLY_ORDER) order = pageblock_order; - VM_BUG_ON(order != pageblock_order); - } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); #endif @@ -1430,14 +1428,8 @@ static inline void prefetch_buddy(struct page *page) /* * Frees a number of pages from the PCP lists - * Assumes all pages on list are in same zone, and of same order. + * Assumes all pages on list are in same zone. * count is the number of pages to free. - * - * If the zone was previously in an "all pages pinned" state then look to - * see if this freeing clears that state. - * - * And clear the zone's pages_scanned counter, to hold off the "all pages are - * pinned" detection logic. */ static void free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp) @@ -1591,7 +1583,7 @@ static void __meminit init_reserved_page(unsigned long pfn) for (zid = 0; zid < MAX_NR_ZONES; zid++) { struct zone *zone = &pgdat->node_zones[zid]; - if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + if (zone_spans_pfn(zone, pfn)) break; } __init_single_page(pfn_to_page(pfn), pfn, zid, nid); @@ -3149,9 +3141,9 @@ static void drain_local_pages_wq(struct work_struct *work) * cpu which is alright but we also have to make sure to not move to * a different one. */ - preempt_disable(); + migrate_disable(); drain_local_pages(drain->zone); - preempt_enable(); + migrate_enable(); } /* @@ -3968,6 +3960,8 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, } #ifdef CONFIG_NUMA +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; + static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= @@ -4797,30 +4791,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, trace_reclaim_retry_zone(z, order, reclaimable, available, min_wmark, *no_progress_loops, wmark); if (wmark) { - /* - * If we didn't make any progress and have a lot of - * dirty + writeback pages then we should wait for - * an IO to complete to slow down the reclaim and - * prevent from pre mature OOM - */ - if (!did_some_progress) { - unsigned long write_pending; - - write_pending = zone_page_state_snapshot(zone, - NR_ZONE_WRITE_PENDING); - - if (2 * write_pending > reclaimable) { - congestion_wait(BLK_RW_ASYNC, HZ/10); - return true; - } - } - ret = true; - goto out; + break; } } -out: /* * Memory allocation/reclaim might be called from a WQ context and the * current implementation of the WQ concurrency control doesn't @@ -4916,6 +4891,19 @@ retry_cpuset: if (!ac->preferred_zoneref->zone) goto nopage; + /* + * Check for insane configurations where the cpuset doesn't contain + * any suitable zone to satisfy the request - e.g. non-movable + * GFP_HIGHUSER allocations from MOVABLE nodes only. + */ + if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { + struct zoneref *z = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, + &cpuset_current_mems_allowed); + if (!z->zone) + goto nopage; + } + if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); @@ -5630,8 +5618,8 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); unsigned long addr; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); addr = __get_free_pages(gfp_mask, order); return make_alloc_exact(addr, order, size); @@ -5655,8 +5643,8 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); struct page *p; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); p = alloc_pages_node(nid, gfp_mask, order); if (!p) @@ -5998,6 +5986,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) printk(KERN_CONT "%s" " free:%lukB" + " boost:%lukB" " min:%lukB" " low:%lukB" " high:%lukB" @@ -6018,6 +6007,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), + K(zone->watermark_boost), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), @@ -6273,7 +6263,7 @@ static void build_zonelists(pg_data_t *pgdat) */ if (node_distance(local_node, node) != node_distance(local_node, prev_node)) - node_load[node] = load; + node_load[node] += load; node_order[nr_nodes++] = node; prev_node = node; @@ -6282,6 +6272,10 @@ static void build_zonelists(pg_data_t *pgdat) build_zonelists_in_node_order(pgdat, node_order, nr_nodes); build_thisnode_zonelists(pgdat); + pr_info("Fallback order for Node %d: ", local_node); + for (node = 0; node < nr_nodes; node++) + pr_cont("%d ", node_order[node]); + pr_cont("\n"); } #ifdef CONFIG_HAVE_MEMORYLESS_NODES @@ -7407,6 +7401,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { + int i; + pgdat_resize_init(pgdat); pgdat_init_split_queue(pgdat); @@ -7415,6 +7411,9 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + pgdat_page_ext_init(pgdat); lruvec_init(&pgdat->__lruvec); } @@ -8144,8 +8143,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char } if (pages && s) - pr_info("Freeing %s memory: %ldK\n", - s, pages << (PAGE_SHIFT - 10)); + pr_info("Freeing %s memory: %ldK\n", s, K(pages)); return pages; } @@ -8190,14 +8188,13 @@ void __init mem_init_print_info(void) ", %luK highmem" #endif ")\n", - nr_free_pages() << (PAGE_SHIFT - 10), - physpages << (PAGE_SHIFT - 10), + K(nr_free_pages()), K(physpages), codesize >> 10, datasize >> 10, rosize >> 10, (init_data_size + init_code_size) >> 10, bss_size >> 10, - (physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10), - totalcma_pages << (PAGE_SHIFT - 10) + K(physpages - totalram_pages() - totalcma_pages), + K(totalcma_pages) #ifdef CONFIG_HIGHMEM - , totalhigh_pages() << (PAGE_SHIFT - 10) + , K(totalhigh_pages()) #endif ); } @@ -8470,7 +8467,7 @@ void setup_per_zone_wmarks(void) * 8192MB: 11584k * 16384MB: 16384k */ -int __meminit init_per_zone_wmark_min(void) +void calculate_min_free_kbytes(void) { unsigned long lowmem_kbytes; int new_min_free_kbytes; @@ -8478,16 +8475,17 @@ int __meminit init_per_zone_wmark_min(void) lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); - if (new_min_free_kbytes > user_min_free_kbytes) { - min_free_kbytes = new_min_free_kbytes; - if (min_free_kbytes < 128) - min_free_kbytes = 128; - if (min_free_kbytes > 262144) - min_free_kbytes = 262144; - } else { + if (new_min_free_kbytes > user_min_free_kbytes) + min_free_kbytes = clamp(new_min_free_kbytes, 128, 262144); + else pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", new_min_free_kbytes, user_min_free_kbytes); - } + +} + +int __meminit init_per_zone_wmark_min(void) +{ + calculate_min_free_kbytes(); setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); @@ -8774,7 +8772,8 @@ void *__init alloc_large_system_hash(const char *tablename, } else if (get_order(size) >= MAX_ORDER || hashdist) { table = __vmalloc(size, gfp_flags); virt = true; - huge = is_vm_area_hugepages(table); + if (table) + huge = is_vm_area_hugepages(table); } else { /* * If bucketsize is not a power-of-two, we may free @@ -9371,21 +9370,21 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) } #endif +/* + * This function returns a stable result only if called under zone lock. + */ bool is_free_buddy_page(struct page *page) { - struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); - unsigned long flags; unsigned int order; - spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); - if (PageBuddy(page_head) && buddy_order(page_head) >= order) + if (PageBuddy(page_head) && + buddy_order_unsafe(page_head) >= order) break; } - spin_unlock_irqrestore(&zone->lock, flags); return order < MAX_ORDER; } diff --git a/mm/page_ext.c b/mm/page_ext.c index 2a52fd9ed464..6242afb24d84 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -201,7 +201,7 @@ fail: panic("Out of memory"); } -#else /* CONFIG_FLATMEM */ +#else /* CONFIG_SPARSEMEM */ struct page_ext *lookup_page_ext(const struct page *page) { diff --git a/mm/page_isolation.c b/mm/page_isolation.c index a95c2c6562d0..f67c4c70f17f 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -94,8 +94,13 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy = page + (buddy_pfn - pfn); if (!is_migrate_isolate_page(buddy)) { - __isolate_free_page(page, order); - isolated_page = true; + isolated_page = !!__isolate_free_page(page, order); + /* + * Isolating a free page in an isolated pageblock + * is expected to always work as watermarks don't + * apply here. + */ + VM_WARN_ON(!isolated_page); } } } @@ -183,7 +188,6 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype, int flags) { unsigned long pfn; - unsigned long undo_pfn; struct page *page; BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); @@ -193,25 +197,12 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page) { - if (set_migratetype_isolate(page, migratetype, flags)) { - undo_pfn = pfn; - goto undo; - } + if (page && set_migratetype_isolate(page, migratetype, flags)) { + undo_isolate_page_range(start_pfn, pfn, migratetype); + return -EBUSY; } } return 0; -undo: - for (pfn = start_pfn; - pfn < undo_pfn; - pfn += pageblock_nr_pages) { - struct page *page = pfn_to_online_page(pfn); - if (!page) - continue; - unset_migratetype_isolate(page, migratetype); - } - - return -EBUSY; } /* diff --git a/mm/percpu.c b/mm/percpu.c index e0a986818903..f5b2c2ea5a54 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_free_early(__pa(ai), ai->__ai_size); + memblock_free(ai, ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_free_early(__pa(areas), areas_size); + memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_free_early(__pa(pages), pages_size); + memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(ptr, size); } void __init setup_per_cpu_areas(void) diff --git a/mm/readahead.c b/mm/readahead.c index e71e719e36c9..6ae5693de28c 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -308,7 +308,7 @@ void force_page_cache_ra(struct readahead_control *ractl, * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra - * 1-8 page = 32k initial, > 8 page = 128k initial + * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { diff --git a/mm/rmap.c b/mm/rmap.c index 3a1059c284c3..163ac4e6bcee 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1807,6 +1807,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, update_hiwater_rss(mm); if (is_zone_device_page(page)) { + unsigned long pfn = page_to_pfn(page); swp_entry_t entry; pte_t swp_pte; @@ -1815,8 +1816,11 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - entry = make_readable_migration_entry( - page_to_pfn(page)); + entry = pte_to_swp_entry(pteval); + if (is_writable_device_private_entry(entry)) + entry = make_writable_migration_entry(pfn); + else + entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); /* diff --git a/mm/shmem.c b/mm/shmem.c index 17e344e26e73..23c91a8beb78 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -855,9 +855,8 @@ unsigned long shmem_swap_usage(struct vm_area_struct *vma) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ - return shmem_partial_swap_usage(mapping, - linear_page_index(vma, vma->vm_start), - linear_page_index(vma, vma->vm_end)); + return shmem_partial_swap_usage(mapping, vma->vm_pgoff, + vma->vm_pgoff + vma_pages(vma)); } /* @@ -2426,7 +2425,6 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); - SetPageDirty(page); unlock_page(page); return 0; out_delete_from_cache: @@ -2458,6 +2456,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; + int ret = 0; /* i_rwsem is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | @@ -2468,7 +2467,15 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; } - return shmem_getpage(inode, index, pagep, SGP_WRITE); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE); + + if (*pagep && PageHWPoison(*pagep)) { + unlock_page(*pagep); + put_page(*pagep); + ret = -EIO; + } + + return ret; } static int @@ -2555,6 +2562,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); + + if (PageHWPoison(page)) { + put_page(page); + error = -EIO; + break; + } } /* @@ -3116,7 +3129,8 @@ static const char *shmem_get_link(struct dentry *dentry, page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); - if (!PageUptodate(page)) { + if (PageHWPoison(page) || + !PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } @@ -3124,6 +3138,11 @@ static const char *shmem_get_link(struct dentry *dentry, error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); + if (page && PageHWPoison(page)) { + unlock_page(page); + put_page(page); + return ERR_PTR(-ECHILD); + } unlock_page(page); } set_delayed_call(done, shmem_put_link, page); @@ -3774,6 +3793,13 @@ static void shmem_destroy_inodecache(void) kmem_cache_destroy(shmem_inode_cachep); } +/* Keep the page in page cache instead of truncating it */ +static int shmem_error_remove_page(struct address_space *mapping, + struct page *page) +{ + return 0; +} + const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, @@ -3784,7 +3810,7 @@ const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif - .error_remove_page = generic_error_remove_page, + .error_remove_page = shmem_error_remove_page, }; EXPORT_SYMBOL(shmem_aops); @@ -4195,6 +4221,10 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, page = ERR_PTR(error); else unlock_page(page); + + if (PageHWPoison(page)) + page = ERR_PTR(-EIO); + return page; #else /* diff --git a/mm/slab.c b/mm/slab.c index 874b3f8fe80d..da132a9ae6f8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3900,8 +3900,6 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) if (err) goto end; - if (limit && shared && batchcount) - goto skip_setup; /* * The head array serves three purposes: * - create a LIFO ordering, i.e. return objects that are cache-warm @@ -3944,7 +3942,6 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) limit = 32; #endif batchcount = (limit + 1) / 2; -skip_setup: err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp); end: if (err) @@ -4207,19 +4204,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= cachep->useroffset - offset + cachep->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - if (usercopy_fallback && - offset <= cachep->object_size && - n <= cachep->object_size - offset) { - usercopy_warn("SLAB object", cachep->name, to_user, offset, n); - return; - } - usercopy_abort("SLAB object", cachep->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ diff --git a/mm/slab_common.c b/mm/slab_common.c index ec2bb0beed75..e5d080a93009 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,14 +37,6 @@ LIST_HEAD(slab_caches); DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; -#ifdef CONFIG_HARDENED_USERCOPY -bool usercopy_fallback __ro_after_init = - IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK); -module_param(usercopy_fallback, bool, 0400); -MODULE_PARM_DESC(usercopy_fallback, - "WARN instead of reject usercopy whitelist violations"); -#endif - static LIST_HEAD(slab_caches_to_rcu_destroy); static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); static DECLARE_WORK(slab_caches_to_rcu_destroy_work, diff --git a/mm/slub.c b/mm/slub.c index e87fd492a65b..f7368bfffb7a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -354,7 +354,7 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object) static void prefetch_freepointer(const struct kmem_cache *s, void *object) { - prefetch(object + s->offset); + prefetchw(object + s->offset); } static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) @@ -414,6 +414,29 @@ static inline unsigned int oo_objects(struct kmem_cache_order_objects x) return x.x & OO_MASK; } +#ifdef CONFIG_SLUB_CPU_PARTIAL +static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) +{ + unsigned int nr_pages; + + s->cpu_partial = nr_objects; + + /* + * We take the number of objects but actually limit the number of + * pages on the per cpu partial list, in order to limit excessive + * growth of the list. For simplicity we assume that the pages will + * be half-full. + */ + nr_pages = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); + s->cpu_partial_pages = nr_pages; +} +#else +static inline void +slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) +{ +} +#endif /* CONFIG_SLUB_CPU_PARTIAL */ + /* * Per slab locking using the pagelock */ @@ -2052,7 +2075,7 @@ static inline void remove_partial(struct kmem_cache_node *n, */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, - int mode, int *objects) + int mode) { void *freelist; unsigned long counters; @@ -2068,7 +2091,6 @@ static inline void *acquire_slab(struct kmem_cache *s, freelist = page->freelist; counters = page->counters; new.counters = counters; - *objects = new.objects - new.inuse; if (mode) { new.inuse = page->objects; new.freelist = NULL; @@ -2106,9 +2128,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, { struct page *page, *page2; void *object = NULL; - unsigned int available = 0; unsigned long flags; - int objects; + unsigned int partial_pages = 0; /* * Racy check. If we mistakenly see no partial slabs then we @@ -2126,11 +2147,10 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!pfmemalloc_match(page, gfpflags)) continue; - t = acquire_slab(s, n, page, object == NULL, &objects); + t = acquire_slab(s, n, page, object == NULL); if (!t) break; - available += objects; if (!object) { *ret_page = page; stat(s, ALLOC_FROM_PARTIAL); @@ -2138,10 +2158,15 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, } else { put_cpu_partial(s, page, 0); stat(s, CPU_PARTIAL_NODE); + partial_pages++; } +#ifdef CONFIG_SLUB_CPU_PARTIAL if (!kmem_cache_has_cpu_partial(s) - || available > slub_cpu_partial(s) / 2) + || partial_pages > s->cpu_partial_pages / 2) break; +#else + break; +#endif } spin_unlock_irqrestore(&n->list_lock, flags); @@ -2546,14 +2571,13 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) struct page *page_to_unfreeze = NULL; unsigned long flags; int pages = 0; - int pobjects = 0; local_lock_irqsave(&s->cpu_slab->lock, flags); oldpage = this_cpu_read(s->cpu_slab->partial); if (oldpage) { - if (drain && oldpage->pobjects > slub_cpu_partial(s)) { + if (drain && oldpage->pages >= s->cpu_partial_pages) { /* * Partial array is full. Move the existing set to the * per node partial list. Postpone the actual unfreezing @@ -2562,16 +2586,13 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) page_to_unfreeze = oldpage; oldpage = NULL; } else { - pobjects = oldpage->pobjects; pages = oldpage->pages; } } pages++; - pobjects += page->objects - page->inuse; page->pages = pages; - page->pobjects = pobjects; page->next = oldpage; this_cpu_write(s->cpu_slab->partial, page); @@ -3522,7 +3543,9 @@ static inline void free_nonslab_page(struct page *page, void *object) { unsigned int order = compound_order(page); - VM_BUG_ON_PAGE(!PageCompound(page), page); + if (WARN_ON_ONCE(!PageCompound(page))) + pr_warn_once("object pointer: 0x%p\n", object); + kfree_hook(object); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(page, order); @@ -3989,6 +4012,8 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min) static void set_cpu_partial(struct kmem_cache *s) { #ifdef CONFIG_SLUB_CPU_PARTIAL + unsigned int nr_objects; + /* * cpu_partial determined the maximum number of objects kept in the * per cpu partial lists of a processor. @@ -3998,24 +4023,22 @@ static void set_cpu_partial(struct kmem_cache *s) * filled up again with minimal effort. The slab will never hit the * per node partial lists and therefore no locking will be required. * - * This setting also determines - * - * A) The number of objects from per cpu partial slabs dumped to the - * per node list when we reach the limit. - * B) The number of objects in cpu partial slabs to extract from the - * per node list when we run out of per cpu objects. We only fetch - * 50% to keep some capacity around for frees. + * For backwards compatibility reasons, this is determined as number + * of objects, even though we now limit maximum number of pages, see + * slub_set_cpu_partial() */ if (!kmem_cache_has_cpu_partial(s)) - slub_set_cpu_partial(s, 0); + nr_objects = 0; else if (s->size >= PAGE_SIZE) - slub_set_cpu_partial(s, 2); + nr_objects = 6; else if (s->size >= 1024) - slub_set_cpu_partial(s, 6); + nr_objects = 24; else if (s->size >= 256) - slub_set_cpu_partial(s, 13); + nr_objects = 52; else - slub_set_cpu_partial(s, 30); + nr_objects = 120; + + slub_set_cpu_partial(s, nr_objects); #endif } @@ -4466,7 +4489,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, { struct kmem_cache *s; unsigned int offset; - size_t object_size; bool is_kfence = is_kfence_address(ptr); ptr = kasan_reset_tag(ptr); @@ -4499,19 +4521,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= s->useroffset - offset + s->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - object_size = slab_ksize(s); - if (usercopy_fallback && - offset <= object_size && n <= object_size - offset) { - usercopy_warn("SLUB object", s->name, to_user, offset, n); - return; - } - usercopy_abort("SLUB object", s->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ @@ -5390,7 +5399,12 @@ SLAB_ATTR(min_partial); static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) { - return sysfs_emit(buf, "%u\n", slub_cpu_partial(s)); + unsigned int nr_partial = 0; +#ifdef CONFIG_SLUB_CPU_PARTIAL + nr_partial = s->cpu_partial; +#endif + + return sysfs_emit(buf, "%u\n", nr_partial); } static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, @@ -5461,12 +5475,12 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) { + if (page) pages += page->pages; - objects += page->pobjects; - } } + /* Approximate half-full pages , see slub_set_cpu_partial() */ + objects = (pages * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, "%d(%d)", objects, pages); #ifdef CONFIG_SMP @@ -5474,9 +5488,12 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) struct page *page; page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) + if (page) { + pages = READ_ONCE(page->pages); + objects = (pages * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, " C%d=%d(%d)", - cpu, page->pobjects, page->pages); + cpu, objects, pages); + } } #endif len += sysfs_emit_at(buf, len, "\n"); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index bdce883f9286..db6df27c852a 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -76,7 +76,7 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, set_pte_at(&init_mm, addr, pte, entry); } - /* Make pte visible before pmd. See comment in __pte_alloc(). */ + /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); diff --git a/mm/sparse.c b/mm/sparse.c index 120bc8ea5293..e5c84b0cf0c9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_free_early(__pa(sparsemap_buf), size); + memblock_free(sparsemap_buf, size); } static void __init sparse_buffer_init(unsigned long size, int nid) diff --git a/mm/swap.c b/mm/swap.c index 8ff9ba7cf2de..1841c24682f8 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -135,18 +135,27 @@ EXPORT_SYMBOL(__put_page); * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * - * Release a list of pages which are strung together on page.lru. Currently - * used by read_cache_pages() and related error recovery code. + * Release a list of pages which are strung together on page.lru. */ void put_pages_list(struct list_head *pages) { - while (!list_empty(pages)) { - struct page *victim; + struct page *page, *next; - victim = lru_to_page(pages); - list_del(&victim->lru); - put_page(victim); + list_for_each_entry_safe(page, next, pages, lru) { + if (!put_page_testzero(page)) { + list_del(&page->lru); + continue; + } + if (PageHead(page)) { + list_del(&page->lru); + __put_compound_page(page); + continue; + } + /* Cannot be PageLRU because it's passed to us using the lru */ + __ClearPageWaiters(page); } + + free_unref_page_list(pages); } EXPORT_SYMBOL(put_pages_list); diff --git a/mm/swapfile.c b/mm/swapfile.c index 41c9e92f1f00..e59e08ef46e1 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2763,7 +2763,7 @@ static int swap_show(struct seq_file *swap, void *v) struct swap_info_struct *si = v; struct file *file; int len; - unsigned int bytes, inuse; + unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); @@ -2775,7 +2775,7 @@ static int swap_show(struct seq_file *swap, void *v) file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); - seq_printf(swap, "%*s%s\t%u\t%s%u\t%s%d\n", + seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", @@ -3118,7 +3118,7 @@ static bool swap_discardable(struct swap_info_struct *si) { struct request_queue *q = bdev_get_queue(si->bdev); - if (!q || !blk_queue_discard(q)) + if (!blk_queue_discard(q)) return false; return true; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 36e5f6ab976f..0780c2a57ff1 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -69,10 +69,9 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, pgoff_t offset, max_off; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); + _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; - if (writable || !page_in_cache) - _dst_pte = pte_mkdirty(_dst_pte); if (writable) { if (wp_copy) _dst_pte = pte_mkuffd_wp(_dst_pte); @@ -233,6 +232,11 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, goto out; } + if (PageHWPoison(page)) { + ret = -EIO; + goto out_release; + } + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, page, false, wp_copy); if (ret) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e8a807c78110..d2a00ad4e1dd 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1195,18 +1195,14 @@ find_vmap_lowest_match(unsigned long size, { struct vmap_area *va; struct rb_node *node; - unsigned long length; /* Start from the root. */ node = free_vmap_area_root.rb_node; - /* Adjust the search size for alignment overhead. */ - length = size + align - 1; - while (node) { va = rb_entry(node, struct vmap_area, rb_node); - if (get_subtree_max_size(node->rb_left) >= length && + if (get_subtree_max_size(node->rb_left) >= size && vstart < va->va_start) { node = node->rb_left; } else { @@ -1216,9 +1212,9 @@ find_vmap_lowest_match(unsigned long size, /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is - * equal or bigger to the requested search length. + * equal or bigger to the requested search size. */ - if (get_subtree_max_size(node->rb_right) >= length) { + if (get_subtree_max_size(node->rb_right) >= size) { node = node->rb_right; continue; } @@ -1226,15 +1222,23 @@ find_vmap_lowest_match(unsigned long size, /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen - * only once due to "vstart" restriction. + * due to "vstart" restriction or an alignment overhead + * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; - if (get_subtree_max_size(node->rb_right) >= length && + if (get_subtree_max_size(node->rb_right) >= size && vstart <= va->va_start) { + /* + * Shift the vstart forward. Please note, we update it with + * parent's start address adding "1" because we do not want + * to enter same sub-tree after it has already been checked + * and no suitable free block found there. + */ + vstart = va->va_start + 1; node = node->rb_right; break; } @@ -1265,7 +1269,7 @@ find_vmap_lowest_linear_match(unsigned long size, } static void -find_vmap_lowest_match_check(unsigned long size) +find_vmap_lowest_match_check(unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; @@ -1274,8 +1278,8 @@ find_vmap_lowest_match_check(unsigned long size) get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; - va_1 = find_vmap_lowest_match(size, 1, vstart); - va_2 = find_vmap_lowest_linear_match(size, 1, vstart); + va_1 = find_vmap_lowest_match(size, align, vstart); + va_2 = find_vmap_lowest_linear_match(size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", @@ -1454,7 +1458,7 @@ __alloc_vmap_area(unsigned long size, unsigned long align, return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK - find_vmap_lowest_match_check(size); + find_vmap_lowest_match_check(size, align); #endif return nva_start_addr; @@ -2272,15 +2276,22 @@ void __init vm_area_add_early(struct vm_struct *vm) */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { - static size_t vm_init_off __initdata; - unsigned long addr; + unsigned long addr = ALIGN(VMALLOC_START, align); + struct vm_struct *cur, **p; - addr = ALIGN(VMALLOC_START + vm_init_off, align); - vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + BUG_ON(vmap_initialized); - vm->addr = (void *)addr; + for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { + if ((unsigned long)cur->addr - addr >= vm->size) + break; + addr = ALIGN((unsigned long)cur->addr + cur->size, align); + } - vm_area_add_early(vm); + BUG_ON(addr > VMALLOC_END - vm->size); + vm->addr = (void *)addr; + vm->next = *p; + *p = vm; + kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void vmap_init_free_space(void) @@ -2743,6 +2754,13 @@ void *vmap(struct page **pages, unsigned int count, might_sleep(); + /* + * Your top guard is someone else's bottom guard. Not having a top + * guard compromises someone else's mappings too. + */ + if (WARN_ON_ONCE(flags & VM_NO_GUARD)) + flags &= ~VM_NO_GUARD; + if (count > totalram_pages()) return NULL; @@ -2825,7 +2843,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * to fails, fallback to a single page allocator that is * more permissive. */ - if (!order && nid != NUMA_NO_NODE) { + if (!order) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -2837,8 +2855,20 @@ vm_area_alloc_pages(gfp_t gfp, int nid, */ nr_pages_request = min(100U, nr_pages - nr_allocated); - nr = alloc_pages_bulk_array_node(gfp, nid, - nr_pages_request, pages + nr_allocated); + /* memory allocation should consider mempolicy, we can't + * wrongly use nearest node when nid == NUMA_NO_NODE, + * otherwise memory may be allocated in only one node, + * but mempolcy want to alloc memory by interleaving. + */ + if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) + nr = alloc_pages_bulk_array_mempolicy(gfp, + nr_pages_request, + pages + nr_allocated); + + else + nr = alloc_pages_bulk_array_node(gfp, nid, + nr_pages_request, + pages + nr_allocated); nr_allocated += nr; cond_resched(); @@ -2850,7 +2880,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else if (order) + } else /* * Compound pages required for remap_vmalloc_page if * high-order pages. @@ -2860,6 +2890,9 @@ vm_area_alloc_pages(gfp_t gfp, int nid, /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { + if (fatal_signal_pending(current)) + break; + if (nid == NUMA_NO_NODE) page = alloc_pages(gfp, order); else @@ -2887,6 +2920,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; + const gfp_t orig_gfp_mask = gfp_mask; unsigned long addr = (unsigned long)area->addr; unsigned long size = get_vm_area_size(area); unsigned long array_size; @@ -2907,7 +2941,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, } if (!area->pages) { - warn_alloc(gfp_mask, NULL, + warn_alloc(orig_gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); free_vm_area(area); @@ -2927,7 +2961,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via __vfree() if any. */ if (area->nr_pages != nr_small_pages) { - warn_alloc(gfp_mask, NULL, + warn_alloc(orig_gfp_mask, NULL, "vmalloc error: size %lu, page order %u, failed to allocate pages", area->nr_pages * PAGE_SIZE, page_order); goto fail; @@ -2935,7 +2969,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (vmap_pages_range(addr, addr + size, prot, area->pages, page_shift) < 0) { - warn_alloc(gfp_mask, NULL, + warn_alloc(orig_gfp_mask, NULL, "vmalloc error: size %lu, failed to map pages", area->nr_pages * PAGE_SIZE); goto fail; @@ -2961,8 +2995,16 @@ fail: * @caller: caller's return address * * Allocate enough pages to cover @size from the page level - * allocator with @gfp_mask flags. Map them into contiguous - * kernel virtual space, using a pagetable protection of @prot. + * allocator with @gfp_mask flags. Please note that the full set of gfp + * flags are not supported. GFP_KERNEL would be a preferred allocation mode + * but GFP_NOFS and GFP_NOIO are supported as well. Zone modifiers are not + * supported. From the reclaim modifiers__GFP_DIRECT_RECLAIM is required (aka + * GFP_NOWAIT is not supported) and only __GFP_NOFAIL is supported (aka + * __GFP_NORETRY and __GFP_RETRY_MAYFAIL are not supported). + * __GFP_NOWARN can be used to suppress error messages about failures. + * + * Map them into contiguous kernel virtual space, using a pagetable + * protection of @prot. * * Return: the address of the area or %NULL on failure */ @@ -3856,6 +3898,7 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; + unsigned int step = 1U << vm_area_page_order(v); if (!counters) return; @@ -3867,9 +3910,8 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr++) - counters[page_to_nid(v->pages[nr])]++; - + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); @@ -3905,7 +3947,7 @@ static int s_show(struct seq_file *m, void *p) (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); - return 0; + goto final; } v = va->vm; @@ -3946,6 +3988,7 @@ static int s_show(struct seq_file *m, void *p) /* * As a final step, dump "unpurged" areas. */ +final: if (list_is_last(&va->list, &vmap_area_list)) show_purge_info(m); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 76518e4166dc..b52644771cc4 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -308,7 +308,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, * asserted for a second in which subsequent * pressure events can occur. */ - memcg->socket_pressure = jiffies + HZ; + WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } } } diff --git a/mm/vmscan.c b/mm/vmscan.c index 71f178f85f5b..ef4a6dc7f000 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1021,6 +1021,91 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) +{ + wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; + long timeout, ret; + DEFINE_WAIT(wait); + + /* + * Do not throttle IO workers, kthreads other than kswapd or + * workqueues. They may be required for reclaim to make + * forward progress (e.g. journalling workqueues or kthreads). + */ + if (!current_is_kswapd() && + current->flags & (PF_IO_WORKER|PF_KTHREAD)) + return; + + /* + * These figures are pulled out of thin air. + * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many + * parallel reclaimers which is a short-lived event so the timeout is + * short. Failing to make progress or waiting on writeback are + * potentially long-lived events so use a longer timeout. This is shaky + * logic as a failure to make progress could be due to anything from + * writeback to a slow device to excessive references pages at the tail + * of the inactive LRU. + */ + switch(reason) { + case VMSCAN_THROTTLE_WRITEBACK: + timeout = HZ/10; + + if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + WRITE_ONCE(pgdat->nr_reclaim_start, + node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + } + + break; + case VMSCAN_THROTTLE_NOPROGRESS: + timeout = HZ/2; + break; + case VMSCAN_THROTTLE_ISOLATED: + timeout = HZ/50; + break; + default: + WARN_ON_ONCE(1); + timeout = HZ; + break; + } + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = schedule_timeout(timeout); + finish_wait(wqh, &wait); + + if (reason == VMSCAN_THROTTLE_WRITEBACK) + atomic_dec(&pgdat->nr_writeback_throttled); + + trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), + jiffies_to_usecs(timeout - ret), + reason); +} + +/* + * Account for pages written if tasks are throttled waiting on dirty + * pages to clean. If enough pages have been cleaned since throttling + * started then wakeup the throttled tasks. + */ +void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, + int nr_throttled) +{ + unsigned long nr_written; + + node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); + + /* + * This is an inaccurate read as the per-cpu deltas may not + * be synchronised. However, given that the system is + * writeback throttled, it is not worth taking the penalty + * of getting an accurate count. At worst, the throttle + * timeout guarantees forward progress. + */ + nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - + READ_ONCE(pgdat->nr_reclaim_start); + + if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) + wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); +} + /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ @@ -1352,7 +1437,6 @@ static unsigned int demote_page_list(struct list_head *demote_pages, { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; - int err; if (list_empty(demote_pages)) return 0; @@ -1361,7 +1445,7 @@ static unsigned int demote_page_list(struct list_head *demote_pages, return 0; /* Demotion ignores all cpuset and mempolicy settings */ - err = migrate_pages(demote_pages, alloc_demote_page, NULL, + migrate_pages(demote_pages, alloc_demote_page, NULL, target_nid, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); @@ -1427,9 +1511,8 @@ retry: /* * The number of dirty pages determines if a node is marked - * reclaim_congested which affects wait_iff_congested. kswapd - * will stall and start writing pages if the tail of the LRU - * is all dirty unqueued pages. + * reclaim_congested. kswapd will stall and start writing + * pages if the tail of the LRU is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) @@ -2135,6 +2218,7 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; + bool too_many; if (current_is_kswapd()) return 0; @@ -2158,7 +2242,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; - return isolated > inactive; + too_many = isolated > inactive; + + /* Wake up tasks throttled due to too_many_isolated. */ + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /* @@ -2267,8 +2357,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; /* wait a bit for the reclaimer. */ - msleep(100); stalled = true; + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) @@ -3196,19 +3286,19 @@ again: * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU - * faster than they are written so also forcibly stall. + * faster than they are written so forcibly stall + * until some pages complete writeback. */ if (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. + * Tag a node/memcg as congested if all the dirty pages were marked + * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). + * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && @@ -3216,15 +3306,15 @@ again: set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it + * Stall direct reclaim for IO completions if the lruvec is + * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -3272,6 +3362,36 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } +static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) +{ + /* + * If reclaim is making progress greater than 12% efficiency then + * wake all the NOPROGRESS throttled tasks. + */ + if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; + if (waitqueue_active(wqh)) + wake_up(wqh); + + return; + } + + /* + * Do not throttle kswapd on NOPROGRESS as it will throttle on + * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under + * writeback and marked for immediate reclaim at the tail of + * the LRU. + */ + if (current_is_kswapd()) + return; + + /* Throttle if making no progress at high prioities. */ + if (sc->priority < DEF_PRIORITY - 2) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); +} + /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation @@ -3356,6 +3476,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); + consider_reclaim_throttle(zone->zone_pgdat, sc); } /* @@ -4302,6 +4423,7 @@ static int kswapd(void *p) WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ce2620344b2..d701c335628c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -165,6 +165,34 @@ atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); EXPORT_SYMBOL(vm_node_stat); +#ifdef CONFIG_NUMA +static void fold_vm_zone_numa_events(struct zone *zone) +{ + unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; + int cpu; + enum numa_stat_item item; + + for_each_online_cpu(cpu) { + struct per_cpu_zonestat *pzstats; + + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); + } + + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_event_add(zone_numa_events[item], zone, item); +} + +void fold_vm_numa_events(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + fold_vm_zone_numa_events(zone); +} +#endif + #ifdef CONFIG_SMP int calculate_pressure_threshold(struct zone *zone) @@ -771,34 +799,6 @@ static int fold_diff(int *zone_diff, int *node_diff) return changes; } -#ifdef CONFIG_NUMA -static void fold_vm_zone_numa_events(struct zone *zone) -{ - unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; - int cpu; - enum numa_stat_item item; - - for_each_online_cpu(cpu) { - struct per_cpu_zonestat *pzstats; - - pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) - zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); - } - - for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) - zone_numa_event_add(zone_numa_events[item], zone, item); -} - -void fold_vm_numa_events(void) -{ - struct zone *zone; - - for_each_populated_zone(zone) - fold_vm_zone_numa_events(zone); -} -#endif - /* * Update the zone counters for the current cpu. * @@ -1070,8 +1070,13 @@ static void fill_contig_page_info(struct zone *zone, for (order = 0; order < MAX_ORDER; order++) { unsigned long blocks; - /* Count number of free blocks */ - blocks = zone->free_area[order].nr_free; + /* + * Count number of free blocks. + * + * Access to nr_free is lockless as nr_free is used only for + * diagnostic purposes. Use data_race to avoid KCSAN warning. + */ + blocks = data_race(zone->free_area[order].nr_free); info->free_blocks_total += blocks; /* Count free base pages */ @@ -1225,6 +1230,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", + "nr_throttled_written", "nr_kernel_misc_reclaimable", "nr_foll_pin_acquired", "nr_foll_pin_released", @@ -1445,7 +1451,11 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (order = 0; order < MAX_ORDER; ++order) - seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + /* + * Access to nr_free is lockless as nr_free is used only for + * printing purposes. Use data_race to avoid KCSAN warning. + */ + seq_printf(m, "%6lu ", data_race(zone->free_area[order].nr_free)); seq_putc(m, '\n'); } @@ -1656,6 +1666,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, } seq_printf(m, "\n pages free %lu" + "\n boost %lu" "\n min %lu" "\n low %lu" "\n high %lu" @@ -1664,6 +1675,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n managed %lu" "\n cma %lu", zone_page_state(zone, NR_FREE_PAGES), + zone->watermark_boost, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), @@ -2179,7 +2191,7 @@ static void extfrag_show_print(struct seq_file *m, for (order = 0; order < MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); index = __fragmentation_index(order, &info); - seq_printf(m, "%d.%03d ", index / 1000, index % 1000); + seq_printf(m, "%2d.%03d ", index / 1000, index % 1000); } seq_putc(m, '\n'); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 68e8831068f4..b897ce3b399a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1830,10 +1830,11 @@ static inline void zs_pool_dec_isolated(struct zs_pool *pool) VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); atomic_long_dec(&pool->isolated_pages); /* - * There's no possibility of racing, since wait_for_isolated_drain() - * checks the isolated count under &class->lock after enqueuing - * on migration_wait. + * Checking pool->destroying must happen after atomic_long_dec() + * for pool->isolated_pages above. Paired with the smp_mb() in + * zs_unregister_migration(). */ + smp_mb__after_atomic(); if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) wake_up_all(&pool->migration_wait); } |