diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 7 | ||||
| -rw-r--r-- | mm/filemap.c | 60 | ||||
| -rw-r--r-- | mm/gup.c | 54 | ||||
| -rw-r--r-- | mm/huge_memory.c | 6 | ||||
| -rw-r--r-- | mm/hugetlb.c | 50 | ||||
| -rw-r--r-- | mm/internal.h | 10 | ||||
| -rw-r--r-- | mm/madvise.c | 17 | ||||
| -rw-r--r-- | mm/memory-failure.c | 18 | ||||
| -rw-r--r-- | mm/mmap.c | 4 | ||||
| -rw-r--r-- | mm/page-writeback.c | 1 | ||||
| -rw-r--r-- | mm/page_owner.c | 192 | ||||
| -rw-r--r-- | mm/readahead.c | 4 | ||||
| -rw-r--r-- | mm/shmem.c | 9 | ||||
| -rw-r--r-- | mm/slab.h | 3 | ||||
| -rw-r--r-- | mm/slab_common.c | 27 | ||||
| -rw-r--r-- | mm/slub.c | 170 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 35 | ||||
| -rw-r--r-- | mm/vmalloc.c | 2 | ||||
| -rw-r--r-- | mm/zswap.c | 25 |
19 files changed, 436 insertions, 258 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index b1448aa81e15..f30a18a0e37d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -333,10 +333,9 @@ config SHUFFLE_PAGE_ALLOCATOR While the randomization improves cache utilization it may negatively impact workloads on platforms without a cache. For - this reason, by default, the randomization is enabled only - after runtime detection of a direct-mapped memory-side-cache. - Otherwise, the randomization may be force enabled with the - 'page_alloc.shuffle' kernel command line parameter. + this reason, by default, the randomization is not enabled even + if SHUFFLE_PAGE_ALLOCATOR=y. The randomization may be force enabled + with the 'page_alloc.shuffle' kernel command line parameter. Say Y if unsure. diff --git a/mm/filemap.c b/mm/filemap.c index 30de18c4fd28..1d6b3a369077 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1540,7 +1540,7 @@ EXPORT_SYMBOL(folio_end_private_2); * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio. + * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { @@ -1553,8 +1553,8 @@ EXPORT_SYMBOL(folio_wait_private_2); * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a - * fatal signal is received by the calling task. + * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is + * received by the calling task. * * Return: * - 0 if successful. @@ -4134,6 +4134,60 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) } EXPORT_SYMBOL(filemap_release_folio); +/** + * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache + * @inode: The inode to flush + * @flush: Set to write back rather than simply invalidate. + * @start: First byte to in range. + * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start + * onwards. + * + * Invalidate all the folios on an inode that contribute to the specified + * range, possibly writing them back first. Whilst the operation is + * undertaken, the invalidate lock is held to prevent new folios from being + * installed. + */ +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t first = start >> PAGE_SHIFT; + pgoff_t last = end >> PAGE_SHIFT; + pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; + + if (!mapping || !mapping->nrpages || end < start) + goto out; + + /* Prevent new folios from being added to the inode. */ + filemap_invalidate_lock(mapping); + + if (!mapping->nrpages) + goto unlock; + + unmap_mapping_pages(mapping, first, nr, false); + + /* Write back the data if we're asked to. */ + if (flush) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .range_start = start, + .range_end = end, + }; + + filemap_fdatawrite_wbc(mapping, &wbc); + } + + /* Wait for writeback to complete on all folios and discard. */ + truncate_inode_pages_range(mapping, start, end); + +unlock: + filemap_invalidate_unlock(mapping); +out: + return filemap_check_errors(mapping); +} +EXPORT_SYMBOL_GPL(filemap_invalidate_inode); + #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping @@ -1206,6 +1206,22 @@ static long __get_user_pages(struct mm_struct *mm, /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { + /* + * MADV_POPULATE_(READ|WRITE) wants to handle VMA + * lookups+error reporting differently. + */ + if (gup_flags & FOLL_MADV_POPULATE) { + vma = vma_lookup(mm, start); + if (!vma) { + ret = -ENOMEM; + goto out; + } + if (check_vma_flags(vma, gup_flags)) { + ret = -EINVAL; + goto out; + } + goto retry; + } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, @@ -1685,35 +1701,35 @@ long populate_vma_page_range(struct vm_area_struct *vma, } /* - * faultin_vma_page_range() - populate (prefault) page tables inside the - * given VMA range readable/writable + * faultin_page_range() - populate (prefault) page tables inside the + * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * - * @vma: target vma + * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * - * Returns either number of processed pages in the vma, or a negative error - * code on error (see __get_user_pages()). + * Returns either number of processed pages in the MM, or a negative error + * code on error (see __get_user_pages()). Note that this function reports + * errors related to VMAs, such as incompatible mappings, as expected by + * MADV_POPULATE_(READ|WRITE). * - * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and - * covered by the VMA. If it's released, *@locked will be set to 0. + * The range must be page-aligned. + * + * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ -long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, bool write, int *locked) +long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked) { - struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* @@ -1725,19 +1741,13 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ - gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | + FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; - /* - * We want to report -EINVAL instead of -EFAULT for any permission - * problems or incompatible mappings. - */ - if (check_vma_flags(vma, gup_flags)) - return -EINVAL; - - ret = __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, locked); + ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, + gup_flags); lru_add_drain(); return ret; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9859aa4f7553..89f58c7603b2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2259,9 +2259,6 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } - folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); - src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { @@ -2270,6 +2267,9 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 23ef240ba48a..ce7be5c24442 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1624,7 +1624,7 @@ static inline void __clear_hugetlb_destructor(struct hstate *h, { lockdep_assert_held(&hugetlb_lock); - folio_clear_hugetlb(folio); + __folio_clear_hugetlb(folio); } /* @@ -1711,7 +1711,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, h->surplus_huge_pages_node[nid]++; } - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above @@ -1781,7 +1781,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, * If vmemmap pages were allocated above, then we need to clear the * hugetlb destructor under the hugetlb lock. */ - if (clear_dtor) { + if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __clear_hugetlb_destructor(h, folio); spin_unlock_irq(&hugetlb_lock); @@ -2049,7 +2049,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); @@ -2160,22 +2160,6 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, } /* - * PageHuge() only returns true for hugetlbfs pages, but not for normal or - * transparent huge pages. See the PageTransHuge() documentation for more - * details. - */ -int PageHuge(const struct page *page) -{ - const struct folio *folio; - - if (!PageCompound(page)) - return 0; - folio = page_folio(page); - return folio_test_hugetlb(folio); -} -EXPORT_SYMBOL_GPL(PageHuge); - -/* * Find and lock address space (mapping) in write mode. * * Upon entry, the page is locked which means that page_mapping() is @@ -3268,9 +3252,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) + if (deferred_reserve) { + spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + spin_unlock_irq(&hugetlb_lock); + } } if (!memcg_charge_ret) @@ -6274,6 +6261,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, VM_UFFD_MISSING); } + if (!(vma->vm_flags & VM_MAYSHARE)) { + ret = vmf_anon_prepare(vmf); + if (unlikely(ret)) + goto out; + } + folio = alloc_hugetlb_folio(vma, haddr, 0); if (IS_ERR(folio)) { /* @@ -6310,15 +6303,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ restore_reserve_on_error(h, vma, haddr, folio); folio_put(folio); + ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); - - ret = vmf_anon_prepare(vmf); - if (unlikely(ret)) - goto backout_unlocked; anon_rmap = 1; } } else { @@ -7044,9 +7034,13 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { - /* No other markers apply for now. */ - WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); - if (uffd_wp_resolve) + /* + * Do nothing on a poison marker; page is + * corrupted, permissons do not apply. Here + * pte_marker_uffd_wp()==true implies !poison + * because they're mutual exclusive. + */ + if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { diff --git a/mm/internal.h b/mm/internal.h index 7e486f2c502c..07ad2675a88b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -686,9 +686,8 @@ struct anon_vma *folio_anon_vma(struct folio *folio); void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); -extern long faultin_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - bool write, int *locked); +extern long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); @@ -1127,10 +1126,13 @@ enum { FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, + /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ + FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ - FOLL_FAST_ONLY | FOLL_UNLOCKABLE) + FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ + FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, diff --git a/mm/madvise.c b/mm/madvise.c index 44a498c94158..1a073fcc4c0c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -908,27 +908,14 @@ static long madvise_populate(struct vm_area_struct *vma, { const bool write = behavior == MADV_POPULATE_WRITE; struct mm_struct *mm = vma->vm_mm; - unsigned long tmp_end; int locked = 1; long pages; *prev = vma; while (start < end) { - /* - * We might have temporarily dropped the lock. For example, - * our VMA might have been split. - */ - if (!vma || start >= vma->vm_end) { - vma = vma_lookup(mm, start); - if (!vma) - return -ENOMEM; - } - - tmp_end = min_t(unsigned long, end, vma->vm_end); /* Populate (prefault) page tables readable/writable. */ - pages = faultin_vma_page_range(vma, start, tmp_end, write, - &locked); + pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; @@ -949,7 +936,7 @@ static long madvise_populate(struct vm_area_struct *vma, pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; - case -ENOMEM: + case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9349948f1abf..9e62a00b46dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -154,11 +154,23 @@ static int __page_handle_poison(struct page *page) { int ret; - zone_pcp_disable(page_zone(page)); + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ ret = dissolve_free_huge_page(page); - if (!ret) + if (!ret) { + drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); - zone_pcp_enable(page_zone(page)); + } return ret; } diff --git a/mm/mmap.c b/mm/mmap.c index 6dbda99a47da..3490af70f259 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1294,7 +1294,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; - flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; + flags_mask = LEGACY_MAP_MASK; + if (file->f_op->fop_flags & FOP_MMAP_SYNC) + flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e19b87049db..06fc89d981e8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2546,6 +2546,7 @@ done: folio_batch_release(&wbc->fbatch); return NULL; } +EXPORT_SYMBOL_GPL(writeback_iter); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. diff --git a/mm/page_owner.c b/mm/page_owner.c index d17d1351ec84..8eed0f3dc085 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -118,7 +118,6 @@ static __init void init_page_owner(void) register_dummy_stack(); register_failure_stack(); register_early_stack(); - static_branch_enable(&page_owner_inited); init_early_allocated_pages(); /* Initialize dummy and failure stacks and link them to stack_list */ dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle); @@ -129,6 +128,7 @@ static __init void init_page_owner(void) refcount_set(&failure_stack.stack_record->count, 1); dummy_stack.next = &failure_stack; stack_list = &dummy_stack; + static_branch_enable(&page_owner_inited); } struct page_ext_operations page_owner_ops = { @@ -170,7 +170,7 @@ static void add_stack_record_to_list(struct stack_record *stack_record, /* Filter gfp_mask the same way stackdepot does, for consistency */ gfp_mask &= ~GFP_ZONEMASK; - gfp_mask &= (GFP_ATOMIC | GFP_KERNEL); + gfp_mask &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); gfp_mask |= __GFP_NOWARN; set_current_in_page_owner(); @@ -196,7 +196,8 @@ static void add_stack_record_to_list(struct stack_record *stack_record, spin_unlock_irqrestore(&stack_list_lock, flags); } -static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) +static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); @@ -217,20 +218,74 @@ static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) /* Add the new stack_record to our list */ add_stack_record_to_list(stack_record, gfp_mask); } - refcount_inc(&stack_record->count); + refcount_add(nr_base_pages, &stack_record->count); } -static void dec_stack_record_count(depot_stack_handle_t handle) +static void dec_stack_record_count(depot_stack_handle_t handle, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); - if (stack_record) - refcount_dec(&stack_record->count); + if (!stack_record) + return; + + if (refcount_sub_and_test(nr_base_pages, &stack_record->count)) + pr_warn("%s: refcount went to 0 for %u handle\n", __func__, + handle); } -void __reset_page_owner(struct page *page, unsigned short order) +static inline void __update_page_owner_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + gfp_t gfp_mask, + short last_migrate_reason, u64 ts_nsec, + pid_t pid, pid_t tgid, char *comm) { int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + page_owner->handle = handle; + page_owner->order = order; + page_owner->gfp_mask = gfp_mask; + page_owner->last_migrate_reason = last_migrate_reason; + page_owner->pid = pid; + page_owner->tgid = tgid; + page_owner->ts_nsec = ts_nsec; + strscpy(page_owner->comm, comm, + sizeof(page_owner->comm)); + __set_bit(PAGE_EXT_OWNER, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_ext = page_ext_next(page_ext); + } +} + +static inline void __update_page_owner_free_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + pid_t pid, pid_t tgid, + u64 free_ts_nsec) +{ + int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + /* Only __reset_page_owner() wants to clear the bit */ + if (handle) { + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner->free_handle = handle; + } + page_owner->free_ts_nsec = free_ts_nsec; + page_owner->free_pid = current->pid; + page_owner->free_tgid = current->tgid; + page_ext = page_ext_next(page_ext); + } +} + +void __reset_page_owner(struct page *page, unsigned short order) +{ struct page_ext *page_ext; depot_stack_handle_t handle; depot_stack_handle_t alloc_handle; @@ -245,16 +300,10 @@ void __reset_page_owner(struct page *page, unsigned short order) alloc_handle = page_owner->handle; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); - for (i = 0; i < (1 << order); i++) { - __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_owner->free_handle = handle; - page_owner->free_ts_nsec = free_ts_nsec; - page_owner->free_pid = current->pid; - page_owner->free_tgid = current->tgid; - page_ext = page_ext_next(page_ext); - page_owner = get_page_owner(page_ext); - } + __update_page_owner_free_handle(page_ext, handle, order, current->pid, + current->tgid, free_ts_nsec); page_ext_put(page_ext); + if (alloc_handle != early_handle) /* * early_handle is being set as a handle for all those @@ -263,39 +312,14 @@ void __reset_page_owner(struct page *page, unsigned short order) * the machinery is not ready yet, we cannot decrement * their refcount either. */ - dec_stack_record_count(alloc_handle); -} - -static inline void __set_page_owner_handle(struct page_ext *page_ext, - depot_stack_handle_t handle, - unsigned short order, gfp_t gfp_mask) -{ - struct page_owner *page_owner; - int i; - u64 ts_nsec = local_clock(); - - for (i = 0; i < (1 << order); i++) { - page_owner = get_page_owner(page_ext); - page_owner->handle = handle; - page_owner->order = order; - page_owner->gfp_mask = gfp_mask; - page_owner->last_migrate_reason = -1; - page_owner->pid = current->pid; - page_owner->tgid = current->tgid; - page_owner->ts_nsec = ts_nsec; - strscpy(page_owner->comm, current->comm, - sizeof(page_owner->comm)); - __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - - page_ext = page_ext_next(page_ext); - } + dec_stack_record_count(alloc_handle, 1 << order); } noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext; + u64 ts_nsec = local_clock(); depot_stack_handle_t handle; handle = save_stack(gfp_mask); @@ -303,9 +327,11 @@ noinline void __set_page_owner(struct page *page, unsigned short order, page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; - __set_page_owner_handle(page_ext, handle, order, gfp_mask); + __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1, + ts_nsec, current->pid, current->tgid, + current->comm); page_ext_put(page_ext); - inc_stack_record_count(handle, gfp_mask); + inc_stack_record_count(handle, gfp_mask, 1 << order); } void __set_page_owner_migrate_reason(struct page *page, int reason) @@ -340,9 +366,12 @@ void __split_page_owner(struct page *page, int old_order, int new_order) void __folio_copy_owner(struct folio *newfolio, struct folio *old) { + int i; struct page_ext *old_ext; struct page_ext *new_ext; - struct page_owner *old_page_owner, *new_page_owner; + struct page_owner *old_page_owner; + struct page_owner *new_page_owner; + depot_stack_handle_t migrate_handle; old_ext = page_ext_get(&old->page); if (unlikely(!old_ext)) @@ -356,30 +385,32 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old) old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); - new_page_owner->order = old_page_owner->order; - new_page_owner->gfp_mask = old_page_owner->gfp_mask; - new_page_owner->last_migrate_reason = - old_page_owner->last_migrate_reason; - new_page_owner->handle = old_page_owner->handle; - new_page_owner->pid = old_page_owner->pid; - new_page_owner->tgid = old_page_owner->tgid; - new_page_owner->free_pid = old_page_owner->free_pid; - new_page_owner->free_tgid = old_page_owner->free_tgid; - new_page_owner->ts_nsec = old_page_owner->ts_nsec; - new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; - strcpy(new_page_owner->comm, old_page_owner->comm); - + migrate_handle = new_page_owner->handle; + __update_page_owner_handle(new_ext, old_page_owner->handle, + old_page_owner->order, old_page_owner->gfp_mask, + old_page_owner->last_migrate_reason, + old_page_owner->ts_nsec, old_page_owner->pid, + old_page_owner->tgid, old_page_owner->comm); + /* + * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio + * will be freed after migration. Keep them until then as they may be + * useful. + */ + __update_page_owner_free_handle(new_ext, 0, old_page_owner->order, + old_page_owner->free_pid, + old_page_owner->free_tgid, + old_page_owner->free_ts_nsec); /* - * We don't clear the bit on the old folio as it's going to be freed - * after migration. Until then, the info can be useful in case of - * a bug, and the overall stats will be off a bit only temporarily. - * Also, migrate_misplaced_transhuge_page() can still fail the - * migration and then we want the old folio to retain the info. But - * in that case we also don't need to explicitly clear the info from - * the new page, which will be freed. + * We linked the original stack to the new folio, we need to do the same + * for the new one and the old folio otherwise there will be an imbalance + * when subtracting those pages from the stack. */ - __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); + for (i = 0; i < (1 << new_page_owner->order); i++) { + old_page_owner->handle = migrate_handle; + old_ext = page_ext_next(old_ext); + old_page_owner = get_page_owner(old_ext); + } + page_ext_put(new_ext); page_ext_put(old_ext); } @@ -787,8 +818,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) goto ext_put_continue; /* Found early allocated page */ - __set_page_owner_handle(page_ext, early_handle, - 0, 0); + __update_page_owner_handle(page_ext, early_handle, 0, 0, + -1, local_clock(), current->pid, + current->tgid, current->comm); count++; ext_put_continue: page_ext_put(page_ext); @@ -840,13 +872,11 @@ static void *stack_start(struct seq_file *m, loff_t *ppos) * value of stack_list. */ stack = smp_load_acquire(&stack_list); + m->private = stack; } else { stack = m->private; - stack = stack->next; } - m->private = stack; - return stack; } @@ -861,11 +891,11 @@ static void *stack_next(struct seq_file *m, void *v, loff_t *ppos) return stack; } -static unsigned long page_owner_stack_threshold; +static unsigned long page_owner_pages_threshold; static int stack_print(struct seq_file *m, void *v) { - int i, stack_count; + int i, nr_base_pages; struct stack *stack = v; unsigned long *entries; unsigned long nr_entries; @@ -876,14 +906,14 @@ static int stack_print(struct seq_file *m, void *v) nr_entries = stack_record->size; entries = stack_record->entries; - stack_count = refcount_read(&stack_record->count) - 1; + nr_base_pages = refcount_read(&stack_record->count) - 1; - if (stack_count < 1 || stack_count < page_owner_stack_threshold) + if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold) return 0; for (i = 0; i < nr_entries; i++) seq_printf(m, " %pS\n", (void *)entries[i]); - seq_printf(m, "stack_count: %d\n\n", stack_count); + seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages); return 0; } @@ -913,13 +943,13 @@ static const struct file_operations page_owner_stack_operations = { static int page_owner_threshold_get(void *data, u64 *val) { - *val = READ_ONCE(page_owner_stack_threshold); + *val = READ_ONCE(page_owner_pages_threshold); return 0; } static int page_owner_threshold_set(void *data, u64 val) { - WRITE_ONCE(page_owner_stack_threshold, val); + WRITE_ONCE(page_owner_pages_threshold, val); return 0; } diff --git a/mm/readahead.c b/mm/readahead.c index 130c0e7df99f..d55138e9560b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -490,6 +490,7 @@ void page_cache_ra_order(struct readahead_control *ractl, pgoff_t index = readahead_index(ractl); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; + unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); @@ -504,6 +505,8 @@ void page_cache_ra_order(struct readahead_control *ractl, new_order = min_t(unsigned int, new_order, ilog2(ra->size)); } + /* See comment in page_cache_ra_unbounded() */ + nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); while (index <= limit) { unsigned int order = new_order; @@ -527,6 +530,7 @@ void page_cache_ra_order(struct readahead_control *ractl, read_pages(ractl); filemap_invalidate_unlock_shared(mapping); + memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have diff --git a/mm/shmem.c b/mm/shmem.c index 0aad0d9a621b..1f84a41aeb85 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -748,12 +748,6 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY -bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) -{ - return false; -} - static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { @@ -3473,8 +3467,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return error; } - simple_offset_remove(shmem_get_offset_ctx(old_dir), old_dentry); - error = simple_offset_add(shmem_get_offset_ctx(new_dir), old_dentry); + error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); if (error) return error; diff --git a/mm/slab.h b/mm/slab.h index d2bc9b191222..78e205b46e19 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -496,9 +496,6 @@ struct slabinfo { }; void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo); -void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s); -ssize_t slabinfo_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos); #ifdef CONFIG_SLUB_DEBUG #ifdef CONFIG_SLUB_DEBUG_ON diff --git a/mm/slab_common.c b/mm/slab_common.c index f5234672f03c..c37f8c41ffb0 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -916,22 +916,15 @@ void __init create_kmalloc_caches(void) * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined */ for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) { - for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[type][i]) - new_kmalloc_cache(i, type); - - /* - * Caches that are not of the two-to-the-power-of size. - * These have to be created immediately after the - * earlier power of two caches - */ - if (KMALLOC_MIN_SIZE <= 32 && i == 6 && - !kmalloc_caches[type][1]) - new_kmalloc_cache(1, type); - if (KMALLOC_MIN_SIZE <= 64 && i == 7 && - !kmalloc_caches[type][2]) - new_kmalloc_cache(2, type); - } + /* Caches that are NOT of the two-to-the-power-of size. */ + if (KMALLOC_MIN_SIZE <= 32) + new_kmalloc_cache(1, type); + if (KMALLOC_MIN_SIZE <= 64) + new_kmalloc_cache(2, type); + + /* Caches that are of the two-to-the-power-of size. */ + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) + new_kmalloc_cache(i, type); } #ifdef CONFIG_RANDOM_KMALLOC_CACHES random_kmalloc_seed = get_random_u64(); @@ -1078,7 +1071,6 @@ static void cache_show(struct kmem_cache *s, struct seq_file *m) sinfo.limit, sinfo.batchcount, sinfo.shared); seq_printf(m, " : slabdata %6lu %6lu %6lu", sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail); - slabinfo_show_stats(m, s); seq_putc(m, '\n'); } @@ -1155,7 +1147,6 @@ static const struct proc_ops slabinfo_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = slabinfo_open, .proc_read = seq_read, - .proc_write = slabinfo_write, .proc_lseek = seq_lseek, .proc_release = seq_release, }; diff --git a/mm/slub.c b/mm/slub.c index 1bb2a93cf7b6..4954999183d5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -557,6 +557,26 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) *(freeptr_t *)freeptr_addr = freelist_ptr_encode(s, fp, freeptr_addr); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + /* Loop over all objects in a slab */ #define for_each_object(__p, __s, __addr, __objects) \ for (__p = fixup_red_left(__s, __addr); \ @@ -604,11 +624,21 @@ static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); s->cpu_partial_slabs = nr_slabs; } + +static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s) +{ + return s->cpu_partial_slabs; +} #else static inline void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) { } + +static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s) +{ + return 0; +} #endif /* CONFIG_SLUB_CPU_PARTIAL */ /* @@ -845,26 +875,6 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } -/* - * See comment in calculate_sizes(). - */ -static inline bool freeptr_outside_object(struct kmem_cache *s) -{ - return s->offset >= s->inuse; -} - -/* - * Return offset of the end of info block which is inuse + free pointer if - * not overlapping with object. - */ -static inline unsigned int get_info_end(struct kmem_cache *s) -{ - if (freeptr_outside_object(s)) - return s->inuse + sizeof(void *); - else - return s->inuse; -} - static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { @@ -2092,15 +2102,20 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) * * The initialization memset's clear the object and the metadata, * but don't touch the SLAB redzone. + * + * The object's freepointer is also avoided if stored outside the + * object. */ if (unlikely(init)) { int rsize; + unsigned int inuse; + inuse = get_info_end(s); if (!kasan_has_integrated_init()) memset(kasan_reset_tag(x), 0, s->object_size); rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0; - memset((char *)kasan_reset_tag(x) + s->inuse, 0, - s->size - s->inuse - rsize); + memset((char *)kasan_reset_tag(x) + inuse, 0, + s->size - inuse - rsize); } /* KASAN might put x into memory quarantine, delaying its reuse. */ return !kasan_slab_free(s, x, init); @@ -2604,19 +2619,18 @@ static struct slab *get_partial_node(struct kmem_cache *s, if (!partial) { partial = slab; stat(s, ALLOC_FROM_PARTIAL); + + if ((slub_get_cpu_partial(s) == 0)) { + break; + } } else { put_cpu_partial(s, slab, 0); stat(s, CPU_PARTIAL_NODE); - partial_slabs++; - } -#ifdef CONFIG_SLUB_CPU_PARTIAL - if (!kmem_cache_has_cpu_partial(s) - || partial_slabs > s->cpu_partial_slabs / 2) - break; -#else - break; -#endif + if (++partial_slabs > slub_get_cpu_partial(s) / 2) { + break; + } + } } spin_unlock_irqrestore(&n->list_lock, flags); return partial; @@ -2699,7 +2713,7 @@ static struct slab *get_partial(struct kmem_cache *s, int node, searchnode = numa_mem_id(); slab = get_partial_node(s, get_node(s, searchnode), pc); - if (slab || node != NUMA_NO_NODE) + if (slab || (node != NUMA_NO_NODE && (pc->flags & __GFP_THISNODE))) return slab; return get_any_partial(s, pc); @@ -2797,7 +2811,7 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab, struct slab new; struct slab old; - if (slab->freelist) { + if (READ_ONCE(slab->freelist)) { stat(s, DEACTIVATE_REMOTE_FREES); tail = DEACTIVATE_TO_TAIL; } @@ -3229,6 +3243,43 @@ static unsigned long count_partial(struct kmem_cache_node *n, #endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */ #ifdef CONFIG_SLUB_DEBUG +#define MAX_PARTIAL_TO_SCAN 10000 + +static unsigned long count_partial_free_approx(struct kmem_cache_node *n) +{ + unsigned long flags; + unsigned long x = 0; + struct slab *slab; + + spin_lock_irqsave(&n->list_lock, flags); + if (n->nr_partial <= MAX_PARTIAL_TO_SCAN) { + list_for_each_entry(slab, &n->partial, slab_list) + x += slab->objects - slab->inuse; + } else { + /* + * For a long list, approximate the total count of objects in + * it to meet the limit on the number of slabs to scan. + * Scan from both the list's head and tail for better accuracy. + */ + unsigned long scanned = 0; + + list_for_each_entry(slab, &n->partial, slab_list) { + x += slab->objects - slab->inuse; + if (++scanned == MAX_PARTIAL_TO_SCAN / 2) + break; + } + list_for_each_entry_reverse(slab, &n->partial, slab_list) { + x += slab->objects - slab->inuse; + if (++scanned == MAX_PARTIAL_TO_SCAN) + break; + } + x = mult_frac(x, n->nr_partial, scanned); + x = min(x, node_nr_objs(n)); + } + spin_unlock_irqrestore(&n->list_lock, flags); + return x; +} + static noinline void slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { @@ -3255,7 +3306,7 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) unsigned long nr_objs; unsigned long nr_free; - nr_free = count_partial(n, count_free); + nr_free = count_partial_free_approx(n); nr_slabs = node_nr_slabs(n); nr_objs = node_nr_objs(n); @@ -3375,6 +3426,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, struct slab *slab; unsigned long flags; struct partial_context pc; + bool try_thisnode = true; stat(s, ALLOC_SLOWPATH); @@ -3501,6 +3553,21 @@ new_slab: new_objects: pc.flags = gfpflags; + /* + * When a preferred node is indicated but no __GFP_THISNODE + * + * 1) try to get a partial slab from target node only by having + * __GFP_THISNODE in pc.flags for get_partial() + * 2) if 1) failed, try to allocate a new slab from target node with + * GPF_NOWAIT | __GFP_THISNODE opportunistically + * 3) if 2) failed, retry with original gfpflags which will allow + * get_partial() try partial lists of other nodes before potentially + * allocating new page from other nodes + */ + if (unlikely(node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) + && try_thisnode)) + pc.flags = GFP_NOWAIT | __GFP_THISNODE; + pc.orig_size = orig_size; slab = get_partial(s, node, &pc); if (slab) { @@ -3522,10 +3589,15 @@ new_objects: } slub_put_cpu_ptr(s->cpu_slab); - slab = new_slab(s, gfpflags, node); + slab = new_slab(s, pc.flags, node); c = slub_get_cpu_ptr(s->cpu_slab); if (unlikely(!slab)) { + if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE) + && try_thisnode) { + try_thisnode = false; + goto new_objects; + } slab_out_of_memory(s, gfpflags, node); return NULL; } @@ -3722,7 +3794,8 @@ static void *__slab_alloc_node(struct kmem_cache *s, static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, void *obj) { - if (unlikely(slab_want_init_on_free(s)) && obj) + if (unlikely(slab_want_init_on_free(s)) && obj && + !freeptr_outside_object(s)) memset((void *)((char *)kasan_reset_tag(obj) + s->offset), 0, sizeof(void *)); } @@ -4226,7 +4299,7 @@ redo: c = raw_cpu_ptr(s->cpu_slab); tid = READ_ONCE(c->tid); - /* Same with comment on barrier() in slab_alloc_node() */ + /* Same with comment on barrier() in __slab_alloc_node() */ barrier(); if (unlikely(slab != c->slab)) { @@ -4847,7 +4920,6 @@ static void early_kmem_cache_node_alloc(int node) BUG_ON(!n); #ifdef CONFIG_SLUB_DEBUG init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); - init_tracking(kmem_cache_node, n); #endif n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false); slab->freelist = get_freepointer(kmem_cache_node, n); @@ -5060,9 +5132,7 @@ static int calculate_sizes(struct kmem_cache *s) if ((int)order < 0) return 0; - s->allocflags = 0; - if (order) - s->allocflags |= __GFP_COMP; + s->allocflags = __GFP_COMP; if (s->flags & SLAB_CACHE_DMA) s->allocflags |= GFP_DMA; @@ -6036,7 +6106,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, else if (flags & SO_OBJECTS) WARN_ON_ONCE(1); else - x = slab->slabs; + x = data_race(slab->slabs); total += x; nodes[node] += x; } @@ -6241,7 +6311,7 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); if (slab) - slabs += slab->slabs; + slabs += data_race(slab->slabs); } #endif @@ -6255,7 +6325,7 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); if (slab) { - slabs = READ_ONCE(slab->slabs); + slabs = data_race(slab->slabs); objects = (slabs * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, " C%d=%d(%d)", cpu, objects, slabs); @@ -7089,7 +7159,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo) for_each_kmem_cache_node(s, node, n) { nr_slabs += node_nr_slabs(n); nr_objs += node_nr_objs(n); - nr_free += count_partial(n, count_free); + nr_free += count_partial_free_approx(n); } sinfo->active_objs = nr_objs - nr_free; @@ -7099,14 +7169,4 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo) sinfo->objects_per_slab = oo_objects(s->oo); sinfo->cache_order = oo_order(s->oo); } - -void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s) -{ -} - -ssize_t slabinfo_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos) -{ - return -EIO; -} #endif /* CONFIG_SLUB_DEBUG */ diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 3c3539c573e7..829f7b1089fc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -316,6 +316,38 @@ out_release: goto out; } +static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + struct folio *folio; + int ret = -ENOMEM; + + folio = vma_alloc_zeroed_movable_folio(dst_vma, dst_addr); + if (!folio) + return ret; + + if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) + goto out_put; + + /* + * The memory barrier inside __folio_mark_uptodate makes sure that + * zeroing out the folio become visible before mapping the page + * using set_pte_at(). See do_anonymous_page(). + */ + __folio_mark_uptodate(folio); + + ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, + &folio->page, true, 0); + if (ret) + goto out_put; + + return 0; +out_put: + folio_put(folio); + return ret; +} + static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) @@ -324,6 +356,9 @@ static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, spinlock_t *ptl; int ret; + if (mm_forbids_zeropage(dst_vma->vm_mm)) + return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr); + _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); ret = -EAGAIN; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 68fa001648cc..125427cbdb87 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2710,7 +2710,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) * get_order(0) returns funny result. Just warn and terminate * early. */ - return NULL; + return ERR_PTR(-EINVAL); } order = get_order(size); diff --git a/mm/zswap.c b/mm/zswap.c index caed028945b0..6f8850c44b61 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1331,15 +1331,22 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!gfp_has_io_fs(sc->gfp_mask)) return 0; -#ifdef CONFIG_MEMCG_KMEM - mem_cgroup_flush_stats(memcg); - nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; - nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); -#else - /* use pool stats instead of memcg stats */ - nr_backing = zswap_pool_total_size >> PAGE_SHIFT; - nr_stored = atomic_read(&zswap_nr_stored); -#endif + /* + * For memcg, use the cgroup-wide ZSWAP stats since we don't + * have them per-node and thus per-lruvec. Careful if memcg is + * runtime-disabled: we can get sc->memcg == NULL, which is ok + * for the lruvec, but not for memcg_page_state(). + * + * Without memcg, use the zswap pool-wide metrics. + */ + if (!mem_cgroup_disabled()) { + mem_cgroup_flush_stats(memcg); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); + } else { + nr_backing = zswap_pool_total_size >> PAGE_SHIFT; + nr_stored = atomic_read(&zswap_nr_stored); + } if (!nr_stored) return 0; |