diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 22 | ||||
-rw-r--r-- | mm/cma.c | 12 | ||||
-rw-r--r-- | mm/huge_memory.c | 25 | ||||
-rw-r--r-- | mm/hugetlb.c | 4 | ||||
-rw-r--r-- | mm/kasan/kasan.c | 14 | ||||
-rw-r--r-- | mm/memcontrol.c | 20 | ||||
-rw-r--r-- | mm/memory.c | 17 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 13 | ||||
-rw-r--r-- | mm/mlock.c | 4 | ||||
-rw-r--r-- | mm/mmap.c | 4 | ||||
-rw-r--r-- | mm/mprotect.c | 3 | ||||
-rw-r--r-- | mm/nommu.c | 5 | ||||
-rw-r--r-- | mm/page-writeback.c | 7 | ||||
-rw-r--r-- | mm/page_alloc.c | 12 | ||||
-rw-r--r-- | mm/page_isolation.c | 1 | ||||
-rw-r--r-- | mm/pagewalk.c | 9 | ||||
-rw-r--r-- | mm/rmap.c | 7 | ||||
-rw-r--r-- | mm/shmem.c | 7 | ||||
-rw-r--r-- | mm/slub.c | 6 | ||||
-rw-r--r-- | mm/vmalloc.c | 1 |
20 files changed, 123 insertions, 70 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index de5239c152f9..a03131b6ba8e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -129,28 +129,28 @@ config SPARSEMEM_VMEMMAP efficient option when sufficient kernel resources are available. config HAVE_MEMBLOCK - boolean + bool config HAVE_MEMBLOCK_NODE_MAP - boolean + bool config HAVE_MEMBLOCK_PHYS_MAP - boolean + bool config HAVE_GENERIC_RCU_GUP - boolean + bool config ARCH_DISCARD_MEMBLOCK - boolean + bool config NO_BOOTMEM - boolean + bool config MEMORY_ISOLATION - boolean + bool config MOVABLE_NODE - boolean "Enable to assign a node which has only movable memory" + bool "Enable to assign a node which has only movable memory" depends on HAVE_MEMBLOCK depends on NO_BOOTMEM depends on X86_64 @@ -228,12 +228,12 @@ config SPLIT_PTLOCK_CPUS default "4" config ARCH_ENABLE_SPLIT_PMD_PTLOCK - boolean + bool # # support for memory balloon config MEMORY_BALLOON - boolean + bool # # support for memory balloon compaction @@ -276,7 +276,7 @@ config MIGRATION allocation instead of reclaiming. config ARCH_ENABLE_HUGEPAGE_MIGRATION - boolean + bool config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT @@ -64,15 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) return (1UL << (align_order - cma->order_per_bit)) - 1; } +/* + * Find a PFN aligned to the specified order and return an offset represented in + * order_per_bits. + */ static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order) { - unsigned int alignment; - if (align_order <= cma->order_per_bit) return 0; - alignment = 1UL << (align_order - cma->order_per_bit); - return ALIGN(cma->base_pfn, alignment) - - (cma->base_pfn >> cma->order_per_bit); + + return (ALIGN(cma->base_pfn, (1UL << align_order)) + - cma->base_pfn) >> cma->order_per_bit; } static unsigned long cma_bitmap_maxno(struct cma *cma) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fc00c8cb5a82..6817b0350c71 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1260,6 +1260,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; + bool was_writable; int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -1291,12 +1292,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, flags |= TNF_FAULT_LOCAL; } - /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. - */ - if (!pmd_write(pmd)) + /* See similar comment in do_numa_page for explanation */ + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -1353,12 +1350,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } + } else + flags |= TNF_MIGRATE_FAIL; goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); + was_writable = pmd_write(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); set_pmd_at(mm, haddr, pmdp, pmd); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); @@ -1482,6 +1484,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + bool preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; /* * Avoid trapping faults against the zero page. The read-only @@ -1490,16 +1494,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (prot_numa && is_huge_zero_pmd(*pmd)) { spin_unlock(ptl); - return 0; + return ret; } if (!prot_numa || !pmd_protnone(*pmd)) { - ret = 1; entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(pmd_write(entry)); + BUG_ON(!preserve_write && pmd_write(entry)); } spin_unlock(ptl); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0a9ac6c26832..c41b2a0ee273 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -917,7 +917,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __SetPageHead(page); __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { - __SetPageTail(p); /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic @@ -933,6 +932,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 78fee632a7ee..936d81661c47 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -29,6 +29,7 @@ #include <linux/stacktrace.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/vmalloc.h> #include <linux/kasan.h> #include "kasan.h" @@ -414,12 +415,19 @@ int kasan_module_alloc(void *addr, size_t size) GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, __builtin_return_address(0)); - return ret ? 0 : -ENOMEM; + + if (ret) { + find_vm_area(addr)->flags |= VM_KASAN; + return 0; + } + + return -ENOMEM; } -void kasan_module_free(void *addr) +void kasan_free_shadow(const struct vm_struct *vm) { - vfree(kasan_mem_to_shadow(addr)); + if (vm->flags & VM_KASAN) + vfree(kasan_mem_to_shadow(vm->addr)); } static void register_global(struct kasan_global *global) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d18d3a6e7337..b34ef4a32a3b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5232,7 +5232,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) * on for the root memcg is enough. */ if (cgroup_on_dfl(root_css->cgroup)) - mem_cgroup_from_css(root_css)->use_hierarchy = true; + root_mem_cgroup->use_hierarchy = true; + else + root_mem_cgroup->use_hierarchy = false; } static u64 memory_current_read(struct cgroup_subsys_state *css, @@ -5247,7 +5249,7 @@ static int memory_low_show(struct seq_file *m, void *v) unsigned long low = ACCESS_ONCE(memcg->low); if (low == PAGE_COUNTER_MAX) - seq_puts(m, "infinity\n"); + seq_puts(m, "max\n"); else seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE); @@ -5262,7 +5264,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, int err; buf = strstrip(buf); - err = page_counter_memparse(buf, "infinity", &low); + err = page_counter_memparse(buf, "max", &low); if (err) return err; @@ -5277,7 +5279,7 @@ static int memory_high_show(struct seq_file *m, void *v) unsigned long high = ACCESS_ONCE(memcg->high); if (high == PAGE_COUNTER_MAX) - seq_puts(m, "infinity\n"); + seq_puts(m, "max\n"); else seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE); @@ -5292,7 +5294,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, int err; buf = strstrip(buf); - err = page_counter_memparse(buf, "infinity", &high); + err = page_counter_memparse(buf, "max", &high); if (err) return err; @@ -5307,7 +5309,7 @@ static int memory_max_show(struct seq_file *m, void *v) unsigned long max = ACCESS_ONCE(memcg->memory.limit); if (max == PAGE_COUNTER_MAX) - seq_puts(m, "infinity\n"); + seq_puts(m, "max\n"); else seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); @@ -5322,7 +5324,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, int err; buf = strstrip(buf); - err = page_counter_memparse(buf, "infinity", &max); + err = page_counter_memparse(buf, "max", &max); if (err) return err; @@ -5426,7 +5428,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) if (memcg == root_mem_cgroup) return false; - if (page_counter_read(&memcg->memory) > memcg->low) + if (page_counter_read(&memcg->memory) >= memcg->low) return false; while (memcg != root) { @@ -5435,7 +5437,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) if (memcg == root_mem_cgroup) break; - if (page_counter_read(&memcg->memory) > memcg->low) + if (page_counter_read(&memcg->memory) >= memcg->low) return false; } return true; diff --git a/mm/memory.c b/mm/memory.c index 8068893697bb..97839f5c8c30 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int last_cpupid; int target_nid; bool migrated = false; + bool was_writable = pte_write(pte); int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Make it present again */ pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3069,11 +3072,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. */ - if (!pte_write(pte)) + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -3097,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; - } + } else + flags |= TNF_MIGRATE_FAIL; out: if (page_nid != -1) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fab10795bea..65842d688b7c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1977,15 +1981,6 @@ void try_offline_node(int nid) if (is_vmalloc_addr(zone->wait_table)) vfree(zone->wait_table); } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); diff --git a/mm/mlock.c b/mm/mlock.c index 73cf0987088c..8a54cd214925 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -26,10 +26,10 @@ int can_do_mlock(void) { - if (capable(CAP_IPC_LOCK)) - return 1; if (rlimit(RLIMIT_MEMLOCK) != 0) return 1; + if (capable(CAP_IPC_LOCK)) + return 1; return 0; } EXPORT_SYMBOL(can_do_mlock); diff --git a/mm/mmap.c b/mm/mmap.c index da9990acc08b..9ec50a368634 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -774,10 +774,8 @@ again: remove_next = 1 + (end > next->vm_end); importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) { - importer->anon_vma = NULL; + if (error) return error; - } } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 44727811bf4c..88584838e704 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; + bool preserve_write = prot_numa && pte_write(oldpte); /* * Avoid trapping faults against the zero or KSM @@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); + if (preserve_write) + ptent = pte_mkwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && diff --git a/mm/nommu.c b/mm/nommu.c index 7296360fc057..3fba2dc97c44 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -62,6 +62,7 @@ void *high_memory; EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; +EXPORT_SYMBOL(max_mapnr); unsigned long highest_memmap_pfn; struct percpu_counter vm_committed_as; int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ @@ -1213,11 +1214,9 @@ static int do_mmap_private(struct vm_area_struct *vma, if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { total = point; kdebug("try to alloc exact %lu pages", total); - base = alloc_pages_exact(len, GFP_KERNEL); - } else { - base = (void *)__get_free_pages(GFP_KERNEL, order); } + base = alloc_pages_exact(total << PAGE_SHIFT, GFP_KERNEL); if (!base) goto enomem; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 45e187b2d971..644bcb665773 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); @@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a47f0b229a1a..40e29429e7b0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2353,8 +2353,15 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, if (ac->high_zoneidx < ZONE_NORMAL) goto out; /* The OOM killer does not compensate for light reclaim */ - if (!(gfp_mask & __GFP_FS)) + if (!(gfp_mask & __GFP_FS)) { + /* + * XXX: Page reclaim didn't yield anything, + * and the OOM killer can't be invoked, but + * keep looping as per should_alloc_retry(). + */ + *did_some_progress = 1; goto out; + } /* * GFP_THISNODE contains __GFP_NORETRY and we never hit this. * Sanity check for bare calls of __GFP_THISNODE, not real OOM. @@ -2366,7 +2373,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false) + || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) *did_some_progress = 1; out: oom_zonelist_unlock(ac->zonelist, gfp_mask); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 72f5ac381ab3..755a42c76eb4 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); + kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); isolated_page = page; } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 75c1f2878519..29f2f8b853ae 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end, vma = vma->vm_next; err = walk_page_test(start, next, walk); - if (err > 0) + if (err > 0) { + /* + * positive return values are purely for + * controlling the pagewalk, so should never + * be passed to the callers. + */ + err = 0; continue; + } if (err < 0) break; } diff --git a/mm/rmap.c b/mm/rmap.c index 5e3e09081164..c161a14b6a8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) return 0; enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } diff --git a/mm/shmem.c b/mm/shmem.c index 944b94079bb0..80b360c7bcd1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1455,6 +1455,9 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode bool shmem_mapping(struct address_space *mapping) { + if (!mapping->host) + return false; + return mapping->host->i_sb->s_op == &shmem_ops; } @@ -2319,8 +2322,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { - bool old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode); - bool new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode); + bool old_is_dir = d_is_dir(old_dentry); + bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { diff --git a/mm/slub.c b/mm/slub.c index 6832c4eab104..82c473780c91 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2449,7 +2449,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* * Irqless object alloc/free algorithm used here depends on sequence @@ -2718,7 +2719,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* Same with comment on barrier() in slab_alloc_node() */ barrier(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 35b25e1340ca..49abccf29a29 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1418,6 +1418,7 @@ struct vm_struct *remove_vm_area(const void *addr) spin_unlock(&vmap_area_lock); vmap_debug_free_range(va->va_start, va->va_end); + kasan_free_shadow(vm); free_unmap_vmap_area(va); vm->size -= PAGE_SIZE; |