diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/debug_vm_pgtable.c | 2 | ||||
| -rw-r--r-- | mm/gup.c | 92 | ||||
| -rw-r--r-- | mm/hugetlb.c | 11 | ||||
| -rw-r--r-- | mm/kfence/core.c | 3 | ||||
| -rw-r--r-- | mm/kfence/kfence_test.c | 8 | ||||
| -rw-r--r-- | mm/khugepaged.c | 37 | ||||
| -rw-r--r-- | mm/kmemleak.c | 13 | ||||
| -rw-r--r-- | mm/madvise.c | 92 | ||||
| -rw-r--r-- | mm/memblock.c | 10 | ||||
| -rw-r--r-- | mm/memcontrol.c | 10 | ||||
| -rw-r--r-- | mm/memfd.c | 40 | ||||
| -rw-r--r-- | mm/memory-failure.c | 6 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/mlock.c | 2 | ||||
| -rw-r--r-- | mm/mmap.c | 13 | ||||
| -rw-r--r-- | mm/mprotect.c | 4 | ||||
| -rw-r--r-- | mm/page_isolation.c | 2 | ||||
| -rw-r--r-- | mm/page_table_check.c | 55 | ||||
| -rw-r--r-- | mm/swap_state.c | 2 | ||||
| -rw-r--r-- | mm/util.c | 4 | ||||
| -rw-r--r-- | mm/vmscan.c | 4 |
21 files changed, 217 insertions, 195 deletions
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index a7ac97c76762..db2abd9e415b 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -171,6 +171,8 @@ static void __init pte_advanced_tests(struct pgtable_debug_args *args) ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep); pte = ptep_get(args->ptep); WARN_ON(pte_young(pte)); + + ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1); } static void __init pte_savedwrite_tests(struct pgtable_debug_args *args) @@ -124,8 +124,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * considered failure, and furthermore, a likely bug in the caller, so a warning * is also emitted. */ -struct page *try_grab_compound_head(struct page *page, - int refs, unsigned int flags) +__maybe_unused struct page *try_grab_compound_head(struct page *page, + int refs, unsigned int flags) { if (flags & FOLL_GET) return try_get_compound_head(page, refs); @@ -208,10 +208,35 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) */ bool __must_check try_grab_page(struct page *page, unsigned int flags) { - if (!(flags & (FOLL_GET | FOLL_PIN))) - return true; + WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); - return try_grab_compound_head(page, 1, flags); + if (flags & FOLL_GET) + return try_get_page(page); + else if (flags & FOLL_PIN) { + int refs = 1; + + page = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + + if (hpage_pincount_available(page)) + hpage_pincount_add(page, 1); + else + refs = GUP_PIN_COUNTING_BIAS; + + /* + * Similar to try_grab_compound_head(): even if using the + * hpage_pincount_add/_sub() routines, be sure to + * *also* increment the normal page refcount field at least + * once, so that the page really is pinned. + */ + page_ref_add(page, refs); + + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); + } + + return true; } /** @@ -1704,11 +1729,11 @@ EXPORT_SYMBOL(fault_in_writeable); * @uaddr: start of address range * @size: length of address range * - * Faults in an address range using get_user_pages, i.e., without triggering - * hardware page faults. This is primarily useful when we already know that - * some or all of the pages in the address range aren't in memory. + * Faults in an address range for writing. This is primarily useful when we + * already know that some or all of the pages in the address range aren't in + * memory. * - * Other than fault_in_writeable(), this function is non-destructive. + * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of @@ -1719,46 +1744,27 @@ EXPORT_SYMBOL(fault_in_writeable); */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { - unsigned long start = (unsigned long)untagged_addr(uaddr); - unsigned long end, nstart, nend; + unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma = NULL; - int locked = 0; + bool unlocked = false; - nstart = start & PAGE_MASK; + if (unlikely(size == 0)) + return 0; end = PAGE_ALIGN(start + size); - if (end < nstart) + if (end < start) end = 0; - for (; nstart != end; nstart = nend) { - unsigned long nr_pages; - long ret; - if (!locked) { - locked = 1; - mmap_read_lock(mm); - vma = find_vma(mm, nstart); - } else if (nstart >= vma->vm_end) - vma = vma->vm_next; - if (!vma || vma->vm_start >= end) - break; - nend = end ? min(end, vma->vm_end) : vma->vm_end; - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - continue; - if (nstart < vma->vm_start) - nstart = vma->vm_start; - nr_pages = (nend - nstart) / PAGE_SIZE; - ret = __get_user_pages_locked(mm, nstart, nr_pages, - NULL, NULL, &locked, - FOLL_TOUCH | FOLL_WRITE); - if (ret <= 0) + mmap_read_lock(mm); + do { + if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; - nend = nstart + ret * PAGE_SIZE; - } - if (locked) - mmap_read_unlock(mm); - if (nstart == end) - return 0; - return size - min_t(size_t, nstart - start, size); + start = (start + PAGE_SIZE) & PAGE_MASK; + } while (start != end); + mmap_read_unlock(mm); + + if (size > (unsigned long)uaddr - start) + return size - ((unsigned long)uaddr - start); + return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 61895cc01d09..f294db835f4b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4159,10 +4159,10 @@ static int __init hugepages_setup(char *s) pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 0; } + if (tmp >= nr_online_nodes) + goto invalid; 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; @@ -4851,14 +4851,13 @@ again: } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, pte_t *src_pte) + unsigned long new_addr, pte_t *src_pte, pte_t *dst_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; + pte_t pte; - 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); @@ -4917,7 +4916,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (!dst_pte) break; - move_huge_pte(vma, old_addr, new_addr, src_pte); + move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); } flush_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 5ad40e3add45..13128fa13062 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -47,7 +47,8 @@ static bool kfence_enabled __read_mostly; -static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +EXPORT_SYMBOL_GPL(kfence_sample_interval); /* Export for test modules. */ #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index a22b1af85577..50dbb815a2a8 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -268,13 +268,13 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); /* * Especially for non-preemption kernels, ensure the allocation-gate * timer can catch up: after @resched_after, every failed allocation * attempt yields, to ensure the allocation-gate timer is scheduled. */ - resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL); + resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval); do { if (test_cache) alloc = kmem_cache_alloc(test_cache, gfp); @@ -608,7 +608,7 @@ static void test_gfpzero(struct kunit *test) int i; /* Skip if we think it'd take too long. */ - KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100); + KFENCE_TEST_REQUIRES(test, kfence_sample_interval <= 100); setup_test_cache(test, size, 0, NULL); buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); @@ -739,7 +739,7 @@ static void test_memcache_alloc_bulk(struct kunit *test) * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); do { void *objects[100]; int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects), diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 35f14d0a00a6..131492fd1148 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -16,6 +16,7 @@ #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> +#include <linux/page_table_check.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> @@ -1416,6 +1417,21 @@ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, return 0; } +static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + spinlock_t *ptl; + pmd_t pmd; + + mmap_assert_write_locked(mm); + ptl = pmd_lock(vma->vm_mm, pmdp); + pmd = pmdp_collapse_flush(vma, addr, pmdp); + spin_unlock(ptl); + mm_dec_nr_ptes(mm); + page_table_check_pte_clear_range(mm, addr, pmd); + pte_free(mm, pmd_pgtable(pmd)); +} + /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. @@ -1433,7 +1449,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma = find_vma(mm, haddr); struct page *hpage; pte_t *start_pte, *pte; - pmd_t *pmd, _pmd; + pmd_t *pmd; spinlock_t *ptl; int count = 0; int i; @@ -1509,12 +1525,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) } /* step 4: collapse pmd */ - ptl = pmd_lock(vma->vm_mm, pmd); - _pmd = pmdp_collapse_flush(vma, haddr, pmd); - spin_unlock(ptl); - mm_dec_nr_ptes(mm); - pte_free(mm, pmd_pgtable(_pmd)); - + collapse_and_free_pmd(mm, vma, haddr, pmd); drop_hpage: unlock_page(hpage); put_page(hpage); @@ -1552,7 +1563,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) struct vm_area_struct *vma; struct mm_struct *mm; unsigned long addr; - pmd_t *pmd, _pmd; + pmd_t *pmd; i_mmap_lock_write(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { @@ -1591,14 +1602,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * reverse order. Trylock is a way to avoid deadlock. */ if (mmap_write_trylock(mm)) { - if (!khugepaged_test_exit(mm)) { - spinlock_t *ptl = pmd_lock(mm, pmd); - /* assume page table is clear */ - _pmd = pmdp_collapse_flush(vma, addr, pmd); - spin_unlock(ptl); - mm_dec_nr_ptes(mm); - pte_free(mm, pmd_pgtable(_pmd)); - } + if (!khugepaged_test_exit(mm)) + collapse_and_free_pmd(mm, vma, addr, pmd); mmap_write_unlock(mm); } else { /* Try again later */ diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dc3758fdba68..7580baa76af1 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1410,7 +1410,8 @@ static void kmemleak_scan(void) { unsigned long flags; struct kmemleak_object *object; - int i; + struct zone *zone; + int __maybe_unused i; int new_leaks = 0; jiffies_last_scan = jiffies; @@ -1450,9 +1451,9 @@ static void kmemleak_scan(void) * Struct page scanning for each node. */ get_online_mems(); - for_each_online_node(i) { - unsigned long start_pfn = node_start_pfn(i); - unsigned long end_pfn = node_end_pfn(i); + for_each_populated_zone(zone) { + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -1461,8 +1462,8 @@ static void kmemleak_scan(void) if (!page) continue; - /* only scan pages belonging to this node */ - if (page_to_nid(page) != i) + /* only scan pages belonging to this zone */ + if (page_zone(page) != zone) continue; /* only scan if page is in use */ if (page_count(page) == 0) diff --git a/mm/madvise.c b/mm/madvise.c index 5604064df464..38d0f515d548 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -65,7 +65,7 @@ static int madvise_need_mmap_write(int behavior) } #ifdef CONFIG_ANON_VMA_NAME -static struct anon_vma_name *anon_vma_name_alloc(const char *name) +struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; @@ -81,78 +81,48 @@ static struct anon_vma_name *anon_vma_name_alloc(const char *name) return anon_name; } -static void vma_anon_name_free(struct kref *kref) +void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } -static inline bool has_vma_anon_name(struct vm_area_struct *vma) +struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { - return !vma->vm_file && vma->anon_name; -} - -const char *vma_anon_name(struct vm_area_struct *vma) -{ - if (!has_vma_anon_name(vma)) - return NULL; - mmap_assert_locked(vma->vm_mm); - return vma->anon_name->name; -} - -void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) -{ - if (!has_vma_anon_name(orig_vma)) - return; - - kref_get(&orig_vma->anon_name->kref); - new_vma->anon_name = orig_vma->anon_name; -} - -void free_vma_anon_name(struct vm_area_struct *vma) -{ - struct anon_vma_name *anon_name; - - if (!has_vma_anon_name(vma)) - return; + if (vma->vm_file) + return NULL; - anon_name = vma->anon_name; - vma->anon_name = NULL; - kref_put(&anon_name->kref, vma_anon_name_free); + return vma->anon_name; } /* mmap_lock should be write-locked */ -static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +static int replace_anon_vma_name(struct vm_area_struct *vma, + struct anon_vma_name *anon_name) { - const char *anon_name; + struct anon_vma_name *orig_name = anon_vma_name(vma); - if (!name) { - free_vma_anon_name(vma); + if (!anon_name) { + vma->anon_name = NULL; + anon_vma_name_put(orig_name); return 0; } - anon_name = vma_anon_name(vma); - if (anon_name) { - /* Same name, nothing to do here */ - if (!strcmp(name, anon_name)) - return 0; + if (anon_vma_name_eq(orig_name, anon_name)) + return 0; - free_vma_anon_name(vma); - } - vma->anon_name = anon_vma_name_alloc(name); - if (!vma->anon_name) - return -ENOMEM; + vma->anon_name = anon_vma_name_reuse(anon_name); + anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ -static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +static int replace_anon_vma_name(struct vm_area_struct *vma, + struct anon_vma_name *anon_name) { - if (name) + if (anon_name) return -EINVAL; return 0; @@ -161,17 +131,19 @@ static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_sem held for writing; + * Caller should ensure anon_name stability by raising its refcount even when + * anon_name belongs to a valid vma because this function might free that vma. */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long new_flags, - const char *name) + struct anon_vma_name *anon_name) { struct mm_struct *mm = vma->vm_mm; int error; pgoff_t pgoff; - if (new_flags == vma->vm_flags && is_same_vma_anon_name(vma, name)) { + if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { *prev = vma; return 0; } @@ -179,7 +151,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, name); + vma->vm_userfaultfd_ctx, anon_name); if (*prev) { vma = *prev; goto success; @@ -209,7 +181,7 @@ success: */ vma->vm_flags = new_flags; if (!vma->vm_file) { - error = replace_vma_anon_name(vma, name); + error = replace_anon_vma_name(vma, anon_name); if (error) return error; } @@ -975,6 +947,7 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, unsigned long behavior) { int error; + struct anon_vma_name *anon_name; unsigned long new_flags = vma->vm_flags; switch (behavior) { @@ -1040,8 +1013,11 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; } + anon_name = anon_vma_name(vma); + anon_vma_name_get(anon_name); error = madvise_update_vma(vma, prev, start, end, new_flags, - vma_anon_name(vma)); + anon_name); + anon_vma_name_put(anon_name); out: /* @@ -1225,7 +1201,7 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, static int madvise_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, - unsigned long name) + unsigned long anon_name) { int error; @@ -1234,7 +1210,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma, return -EBADF; error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, - (const char *)name); + (struct anon_vma_name *)anon_name); /* * madvise() returns EAGAIN if kernel resources, such as @@ -1246,7 +1222,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma, } int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, const char *name) + unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; @@ -1266,7 +1242,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, if (end == start) return 0; - return madvise_walk_vmas(mm, start, end, (unsigned long)name, + return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name, madvise_vma_anon_name); } #endif /* CONFIG_ANON_VMA_NAME */ diff --git a/mm/memblock.c b/mm/memblock.c index 1018e50566f3..b12a364f2766 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,20 @@ 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); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + 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); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + memblock_free_late(addr, size); } memblock_memory = NULL; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09d342c7cbd0..36e9f38c919d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -254,7 +254,7 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) } #ifdef CONFIG_MEMCG_KMEM -extern spinlock_t css_set_lock; +static DEFINE_SPINLOCK(objcg_lock); bool mem_cgroup_kmem_disabled(void) { @@ -298,9 +298,9 @@ static void obj_cgroup_release(struct percpu_ref *ref) if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); - spin_lock_irqsave(&css_set_lock, flags); + spin_lock_irqsave(&objcg_lock, flags); list_del(&objcg->list); - spin_unlock_irqrestore(&css_set_lock, flags); + spin_unlock_irqrestore(&objcg_lock, flags); percpu_ref_exit(ref); kfree_rcu(objcg, rcu); @@ -332,7 +332,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, objcg = rcu_replace_pointer(memcg->objcg, NULL, true); - spin_lock_irq(&css_set_lock); + spin_lock_irq(&objcg_lock); /* 1) Ready to reparent active objcg. */ list_add(&objcg->list, &memcg->objcg_list); @@ -342,7 +342,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, /* 3) Move already reparented objcgs to the parent's list */ list_splice(&memcg->objcg_list, &parent->objcg_list); - spin_unlock_irq(&css_set_lock); + spin_unlock_irq(&objcg_lock); percpu_ref_kill(&objcg->refcnt); } diff --git a/mm/memfd.c b/mm/memfd.c index 9f80f162791a..08f5f8304746 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -31,20 +31,28 @@ static void memfd_tag_pins(struct xa_state *xas) { struct page *page; - unsigned int tagged = 0; + int latency = 0; + int cache_count; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, page, ULONG_MAX) { - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas->xa_index); - if (page_count(page) - page_mapcount(page) > 1) + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && + page_count(page) - total_mapcount(page) != cache_count) xas_set_mark(xas, MEMFD_TAG_PINNED); + if (cache_count != 1) + xas_set(xas, page->index + cache_count); - if (++tagged % XA_CHECK_SCHED) + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(xas); xas_unlock_irq(xas); @@ -73,7 +81,8 @@ static int memfd_wait_for_pins(struct address_space *mapping) error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { - unsigned int tagged = 0; + int latency = 0; + int cache_count; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; @@ -87,10 +96,14 @@ static int memfd_wait_for_pins(struct address_space *mapping) xas_lock_irq(&xas); xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas.xa_index); - if (page_count(page) - page_mapcount(page) != 1) { + + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && cache_count != + page_count(page) - total_mapcount(page)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still @@ -103,8 +116,11 @@ static int memfd_wait_for_pins(struct address_space *mapping) } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); - if (++tagged % XA_CHECK_SCHED) + + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 14ae5c18e776..97a9ed8f87a9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1596,6 +1596,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, } /* + * Pages instantiated by device-dax (not filesystem-dax) + * may be compound pages. + */ + page = compound_head(page); + + /* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by * lock_page(), but dax pages do not use the page lock. This diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 028e8dd82b44..69284d3b5e53 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -814,7 +814,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx, - vma_anon_name(vma)); + anon_vma_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/mlock.c b/mm/mlock.c index 8f584eddd305..25934e7db3e1 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -512,7 +512,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index 1e8fdb0b51ed..f61a15474dd6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1031,7 +1031,7 @@ again: static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1049,7 +1049,7 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; - if (!is_same_vma_anon_name(vma, anon_name)) + if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) return 0; return 1; } @@ -1084,7 +1084,7 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { @@ -1106,7 +1106,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { @@ -1167,7 +1167,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -3186,6 +3186,7 @@ void exit_mmap(struct mm_struct *mm) vma = remove_vma(vma); cond_resched(); } + mm->mmap = NULL; mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } @@ -3255,7 +3256,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index 0138dfcdb1d8..2887644fd150 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -94,7 +94,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, /* Also skip shared copy-on-write pages */ if (is_cow_mapping(vma->vm_flags) && - page_mapcount(page) != 1) + page_count(page) != 1) continue; /* @@ -464,7 +464,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 6a0ddda6b3c5..f67c4c70f17f 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -115,7 +115,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) * onlining - just onlined memory won't immediately be considered for * allocation. */ - if (!isolated_page && PageBuddy(page)) { + if (!isolated_page) { nr_pages = move_freepages_block(zone, page, migratetype, NULL); __mod_zone_freepage_state(zone, nr_pages, migratetype); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 7504e7caa2a1..3763bd077861 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -86,8 +86,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, { struct page_ext *page_ext; struct page *page; + unsigned long i; bool anon; - int i; if (!pfn_valid(pfn)) return; @@ -121,8 +121,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, { struct page_ext *page_ext; struct page *page; + unsigned long i; bool anon; - int i; if (!pfn_valid(pfn)) return; @@ -152,10 +152,10 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, void __page_table_check_zero(struct page *page, unsigned int order) { struct page_ext *page_ext = lookup_page_ext(page); - int i; + unsigned long i; BUG_ON(!page_ext); - for (i = 0; i < (1 << order); i++) { + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); BUG_ON(atomic_read(&ptc->anon_map_count)); @@ -206,17 +206,10 @@ EXPORT_SYMBOL(__page_table_check_pud_clear); void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - pte_t old_pte; - if (&init_mm == mm) return; - old_pte = *ptep; - if (pte_user_accessible_page(old_pte)) { - page_table_check_clear(mm, addr, pte_pfn(old_pte), - PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pte_clear(mm, addr, *ptep); if (pte_user_accessible_page(pte)) { page_table_check_set(mm, addr, pte_pfn(pte), PAGE_SIZE >> PAGE_SHIFT, @@ -228,17 +221,10 @@ EXPORT_SYMBOL(__page_table_check_pte_set); void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - pmd_t old_pmd; - if (&init_mm == mm) return; - old_pmd = *pmdp; - if (pmd_user_accessible_page(old_pmd)) { - page_table_check_clear(mm, addr, pmd_pfn(old_pmd), - PMD_PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pmd_clear(mm, addr, *pmdp); if (pmd_user_accessible_page(pmd)) { page_table_check_set(mm, addr, pmd_pfn(pmd), PMD_PAGE_SIZE >> PAGE_SHIFT, @@ -250,17 +236,10 @@ EXPORT_SYMBOL(__page_table_check_pmd_set); void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - pud_t old_pud; - if (&init_mm == mm) return; - old_pud = *pudp; - if (pud_user_accessible_page(old_pud)) { - page_table_check_clear(mm, addr, pud_pfn(old_pud), - PUD_PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pud_clear(mm, addr, *pudp); if (pud_user_accessible_page(pud)) { page_table_check_set(mm, addr, pud_pfn(pud), PUD_PAGE_SIZE >> PAGE_SHIFT, @@ -268,3 +247,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, } } EXPORT_SYMBOL(__page_table_check_pud_set); + +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (!pmd_bad(pmd) && !pmd_leaf(pmd)) { + pte_t *ptep = pte_offset_map(&pmd, addr); + unsigned long i; + + pte_unmap(ptep); + for (i = 0; i < PTRS_PER_PTE; i++) { + __page_table_check_pte_clear(mm, addr, *ptep); + addr += PAGE_SIZE; + ptep++; + } + } +} diff --git a/mm/swap_state.c b/mm/swap_state.c index 8d4104242100..ee67164531c0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -478,7 +478,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * __read_swap_cache_async(), which has set SWAP_HAS_CACHE * in swap_map, but not yet added its page to swap cache. */ - cond_resched(); + schedule_timeout_uninterruptible(1); } /* diff --git a/mm/util.c b/mm/util.c index 7e43369064c8..d3102081add0 100644 --- a/mm/util.c +++ b/mm/util.c @@ -587,8 +587,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return ret; /* Don't even allow crazy sizes */ - if (WARN_ON_ONCE(size > INT_MAX)) + if (unlikely(size > INT_MAX)) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; + } return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); diff --git a/mm/vmscan.c b/mm/vmscan.c index 090bfb605ecf..59b14e0d696c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1066,8 +1066,10 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && - current->flags & (PF_IO_WORKER|PF_KTHREAD)) + current->flags & (PF_IO_WORKER|PF_KTHREAD)) { + cond_resched(); return; + } /* * These figures are pulled out of thin air. |