diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 2 | ||||
| -rw-r--r-- | mm/backing-dev.c | 7 | ||||
| -rw-r--r-- | mm/damon/core.c | 20 | ||||
| -rw-r--r-- | mm/damon/dbgfs.c | 4 | ||||
| -rw-r--r-- | mm/damon/vaddr-test.h | 79 | ||||
| -rw-r--r-- | mm/damon/vaddr.c | 2 | ||||
| -rw-r--r-- | mm/filemap.c | 2 | ||||
| -rw-r--r-- | mm/highmem.c | 2 | ||||
| -rw-r--r-- | mm/hugetlb.c | 27 | ||||
| -rw-r--r-- | mm/memcontrol.c | 108 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 1 | ||||
| -rw-r--r-- | mm/shmem.c | 3 | ||||
| -rw-r--r-- | mm/slub.c | 15 | ||||
| -rw-r--r-- | mm/swap_slots.c | 1 | ||||
| -rw-r--r-- | mm/util.c | 2 |
15 files changed, 143 insertions, 132 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 28edafc820ad..356f4f2c779e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -428,7 +428,7 @@ config THP_SWAP # UP and nommu archs use km based percpu allocator # config NEED_PER_CPU_KM - depends on !SMP + depends on !SMP || !MMU bool default y diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1eead4761011..eae96dfe0261 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_info *bdi) wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); + /* + * If this BDI's min ratio has been set, use bdi_set_min_ratio() to + * update the global bdi_min_ratio. + */ + if (bdi->min_ratio) + bdi_set_min_ratio(bdi, 0); + if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); diff --git a/mm/damon/core.c b/mm/damon/core.c index c381b3c525d0..e92497895202 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *ctx, for (i = 0; i < nr_ids; i++) { t = damon_new_target(ids[i]); if (!t) { - pr_err("Failed to alloc damon_target\n"); /* The caller should do cleanup of the ids itself */ damon_for_each_target_safe(t, next, ctx) damon_destroy_target(t); @@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg) { - if (min_nr_reg < 3) { - pr_err("min_nr_regions (%lu) must be at least 3\n", - min_nr_reg); + if (min_nr_reg < 3) return -EINVAL; - } - if (min_nr_reg > max_nr_reg) { - pr_err("invalid nr_regions. min (%lu) > max (%lu)\n", - min_nr_reg, max_nr_reg); + if (min_nr_reg > max_nr_reg) return -EINVAL; - } ctx->sample_interval = sample_int; ctx->aggr_interval = aggr_int; @@ -980,10 +973,11 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme) static void kdamond_usleep(unsigned long usecs) { - if (usecs > 100 * 1000) - schedule_timeout_interruptible(usecs_to_jiffies(usecs)); + /* See Documentation/timers/timers-howto.rst for the thresholds */ + if (usecs > 20 * USEC_PER_MSEC) + schedule_timeout_idle(usecs_to_jiffies(usecs)); else - usleep_range(usecs, usecs + 1); + usleep_idle_range(usecs, usecs + 1); } /* Returns negative error code if it's not activated but should return */ @@ -1038,7 +1032,7 @@ static int kdamond_fn(void *data) ctx->callback.after_sampling(ctx)) done = true; - usleep_range(ctx->sample_interval, ctx->sample_interval + 1); + kdamond_usleep(ctx->sample_interval); if (ctx->primitive.check_accesses) max_nr_accesses = ctx->primitive.check_accesses(ctx); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 9b520bb4a3e7..1efac0022e9a 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -210,10 +210,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, &wmarks.low, &parsed); if (ret != 18) break; - if (!damos_action_valid(action)) { - pr_err("wrong action %d\n", action); + if (!damos_action_valid(action)) goto fail; - } pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index ecfd0b2ed222..6a1b9272ea12 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -135,7 +135,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, struct damon_addr_range *three_regions, unsigned long *expected, int nr_expected) { - struct damon_ctx *ctx = damon_new_ctx(); struct damon_target *t; struct damon_region *r; int i; @@ -145,7 +144,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, r = damon_new_region(regions[i * 2], regions[i * 2 + 1]); damon_add_region(r, t); } - damon_add_target(ctx, t); damon_va_apply_three_regions(t, three_regions); @@ -154,8 +152,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]); KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]); } - - damon_destroy_ctx(ctx); } /* @@ -252,60 +248,59 @@ static void damon_test_apply_three_regions4(struct kunit *test) new_three_regions, expected, ARRAY_SIZE(expected)); } -static void damon_test_split_evenly(struct kunit *test) +static void damon_test_split_evenly_fail(struct kunit *test, + unsigned long start, unsigned long end, unsigned int nr_pieces) { - struct damon_ctx *c = damon_new_ctx(); - struct damon_target *t; - struct damon_region *r; - unsigned long i; - - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5), - -EINVAL); - - t = damon_new_target(42); - r = damon_new_region(0, 100); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL); + struct damon_target *t = damon_new_target(42); + struct damon_region *r = damon_new_region(start, end); damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u); + KUNIT_EXPECT_EQ(test, + damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u); - i = 0; damon_for_each_region(r, t) { - KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10); - KUNIT_EXPECT_EQ(test, r->ar.end, i * 10); + KUNIT_EXPECT_EQ(test, r->ar.start, start); + KUNIT_EXPECT_EQ(test, r->ar.end, end); } + damon_free_target(t); +} + +static void damon_test_split_evenly_succ(struct kunit *test, + unsigned long start, unsigned long end, unsigned int nr_pieces) +{ + struct damon_target *t = damon_new_target(42); + struct damon_region *r = damon_new_region(start, end); + unsigned long expected_width = (end - start) / nr_pieces; + unsigned long i = 0; - t = damon_new_target(42); - r = damon_new_region(5, 59); damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u); + KUNIT_EXPECT_EQ(test, + damon_va_evenly_split_region(t, r, nr_pieces), 0); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces); - i = 0; damon_for_each_region(r, t) { - if (i == 4) + if (i == nr_pieces - 1) break; - KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++); - KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i); + KUNIT_EXPECT_EQ(test, + r->ar.start, start + i++ * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width); } - KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i); - KUNIT_EXPECT_EQ(test, r->ar.end, 59ul); + KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, end); damon_free_target(t); +} - t = damon_new_target(42); - r = damon_new_region(5, 6); - damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u); +static void damon_test_split_evenly(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5), + -EINVAL); - damon_for_each_region(r, t) { - KUNIT_EXPECT_EQ(test, r->ar.start, 5ul); - KUNIT_EXPECT_EQ(test, r->ar.end, 6ul); - } - damon_free_target(t); - damon_destroy_ctx(c); + damon_test_split_evenly_fail(test, 0, 100, 0); + damon_test_split_evenly_succ(test, 0, 100, 10); + damon_test_split_evenly_succ(test, 5, 59, 5); + damon_test_split_evenly_fail(test, 5, 6, 2); } static struct kunit_case damon_test_cases[] = { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 35fe49080ee9..20a9a9d69eb1 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -13,6 +13,7 @@ #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/pagewalk.h> +#include <linux/sched/mm.h> #include "prmtv-common.h" @@ -626,7 +627,6 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_STAT: return 0; default: - pr_warn("Wrong action %d\n", scheme->action); return -EINVAL; } diff --git a/mm/filemap.c b/mm/filemap.c index daa0e23a6ee6..39c4c46c6133 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(struct page *page, goto skip; if (!PageUptodate(page) || PageReadahead(page)) goto skip; - if (PageHWPoison(page)) - goto skip; if (!trylock_page(page)) goto skip; if (page->mapping != mapping) diff --git a/mm/highmem.c b/mm/highmem.c index ca9fa8c92593..762679050c9a 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -359,7 +359,6 @@ void kunmap_high(struct page *page) } EXPORT_SYMBOL(kunmap_high); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { @@ -416,7 +415,6 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, BUG_ON((start1 | start2 | end1 | end2) != 0); } EXPORT_SYMBOL(zero_user_segments); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HIGHMEM */ #ifdef CONFIG_KMAP_LOCAL diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f025d234522f..a1baa198519a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2973,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; - if (nid >= nr_online_nodes) + if (nid != NUMA_NO_NODE && nid >= nr_online_nodes) return 0; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { @@ -4919,9 +4919,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, 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); + i_mmap_unlock_write(mapping); return len + old_addr - old_end; } @@ -4939,6 +4939,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -4967,10 +4968,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -5027,6 +5026,22 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 781605e92015..2ed5f2a0879d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } -/* - * mod_objcg_mlstate() may be called with irq enabled, so - * mod_memcg_lruvec_state() should be used. - */ -static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, - struct pglist_data *pgdat, - enum node_stat_item idx, int nr) -{ - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - rcu_read_lock(); - memcg = obj_cgroup_memcg(objcg); - lruvec = mem_cgroup_lruvec(memcg, pgdat); - mod_memcg_lruvec_state(lruvec, idx, nr); - rcu_read_unlock(); -} - /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, } #endif -/* - * Most kmem_cache_alloc() calls are from user context. The irq disable/enable - * sequence used in this case to access content from object stock is slow. - * To optimize for user context access, there are now two object stocks for - * task context and interrupt context access respectively. - * - * The task context object stock can be accessed by disabling preemption only - * which is cheap in non-preempt kernel. The interrupt context object stock - * can only be accessed after disabling interrupt. User context code can - * access interrupt object stock, but not vice versa. - */ -static inline struct obj_stock *get_obj_stock(unsigned long *pflags) -{ - struct memcg_stock_pcp *stock; - - if (likely(in_task())) { - *pflags = 0UL; - preempt_disable(); - stock = this_cpu_ptr(&memcg_stock); - return &stock->task_obj; - } - - local_irq_save(*pflags); - stock = this_cpu_ptr(&memcg_stock); - return &stock->irq_obj; -} - -static inline void put_obj_stock(unsigned long flags) -{ - if (likely(in_task())) - preempt_enable(); - else - local_irq_restore(flags); -} - /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. @@ -2816,6 +2763,59 @@ retry: */ #define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) +/* + * Most kmem_cache_alloc() calls are from user context. The irq disable/enable + * sequence used in this case to access content from object stock is slow. + * To optimize for user context access, there are now two object stocks for + * task context and interrupt context access respectively. + * + * The task context object stock can be accessed by disabling preemption only + * which is cheap in non-preempt kernel. The interrupt context object stock + * can only be accessed after disabling interrupt. User context code can + * access interrupt object stock, but not vice versa. + */ +static inline struct obj_stock *get_obj_stock(unsigned long *pflags) +{ + struct memcg_stock_pcp *stock; + + if (likely(in_task())) { + *pflags = 0UL; + preempt_disable(); + stock = this_cpu_ptr(&memcg_stock); + return &stock->task_obj; + } + + local_irq_save(*pflags); + stock = this_cpu_ptr(&memcg_stock); + return &stock->irq_obj; +} + +static inline void put_obj_stock(unsigned long flags) +{ + if (likely(in_task())) + preempt_enable(); + else + local_irq_restore(flags); +} + +/* + * mod_objcg_mlstate() may be called with irq enabled, so + * mod_memcg_lruvec_state() should be used. + */ +static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + rcu_read_unlock(); +} + int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page) { @@ -5558,7 +5558,7 @@ static int mem_cgroup_move_account(struct page *page, VM_BUG_ON(from == to); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON(compound && !folio_test_multi(folio)); + VM_BUG_ON(compound && !folio_test_large(folio)); /* * Prevent mem_cgroup_migrate() from looking at diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 852041f6be41..2a9627dc784c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -35,6 +35,7 @@ #include <linux/memblock.h> #include <linux/compaction.h> #include <linux/rmap.h> +#include <linux/module.h> #include <asm/tlbflush.h> diff --git a/mm/shmem.c b/mm/shmem.c index dc038ce78700..18f93c2d68f1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2303,6 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); + mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { default: @@ -3870,7 +3871,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, - .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, + .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) diff --git a/mm/slub.c b/mm/slub.c index a8626825a829..abe7db581d68 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5081,6 +5081,7 @@ struct loc_track { unsigned long max; unsigned long count; struct location *loc; + loff_t idx; }; static struct dentry *slab_debugfs_root; @@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init); #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS) static int slab_debugfs_show(struct seq_file *seq, void *v) { - - struct location *l; - unsigned int idx = *(unsigned int *)v; struct loc_track *t = seq->private; + struct location *l; + unsigned long idx; + idx = (unsigned long) t->idx; if (idx < t->count) { l = &t->loc[idx]; @@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos) { struct loc_track *t = seq->private; - v = ppos; - ++*ppos; + t->idx = ++(*ppos); if (*ppos <= t->count) - return v; + return ppos; return NULL; } static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos) { + struct loc_track *t = seq->private; + + t->idx = *ppos; return ppos; } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 16f706c55d92..2b5531840583 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -30,6 +30,7 @@ #include <linux/swap_slots.h> #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> diff --git a/mm/util.c b/mm/util.c index e58151a61255..741ba32a43ac 100644 --- a/mm/util.c +++ b/mm/util.c @@ -670,7 +670,7 @@ bool folio_mapped(struct folio *folio) { long i, nr; - if (folio_test_single(folio)) + if (!folio_test_large(folio)) return atomic_read(&folio->_mapcount) >= 0; if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; |