diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/filemap.c | 3572 |
1 files changed, 2018 insertions, 1554 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 1784478270e1..08341616ae7a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -21,6 +21,7 @@ #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> @@ -30,17 +31,19 @@ #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> -#include <linux/blkdev.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> -#include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> +#include <linux/page_idle.h> +#include <linux/migrate.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -69,23 +72,25 @@ * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) - * ->private_lock (__free_pte->__set_page_dirty_buffers) + * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * - * ->i_mutex - * ->i_mmap_rwsem (truncate->unmap_mapping_range) + * ->i_rwsem + * ->invalidate_lock (acquired by fs in truncate path) + * ->i_mmap_rwsem (truncate->unmap_mapping_range) * - * ->mmap_sem + * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * - * ->mmap_sem - * ->lock_page (access_process_vm) + * ->mmap_lock + * ->invalidate_lock (filemap_fault) + * ->lock_page (filemap_fault, access_process_vm) * - * ->i_mutex (generic_perform_write) - * ->mmap_sem (fault_in_pages_readable->do_page_fault) + * ->i_rwsem (generic_perform_write) + * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) @@ -101,8 +106,8 @@ * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) - * ->pgdat->lru_lock (follow_page->mark_page_accessed) - * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) + * ->lruvec->lru_lock (follow_page->mark_page_accessed) + * ->lruvec->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) @@ -110,117 +115,98 @@ * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) - * ->private_lock (zap_pte_range->__set_page_dirty_buffers) + * ->private_lock (zap_pte_range->block_dirty_folio) * * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ static void page_cache_delete(struct address_space *mapping, - struct page *page, void *shadow) + struct folio *folio, void *shadow) { - XA_STATE(xas, &mapping->i_pages, page->index); - unsigned int nr = 1; + XA_STATE(xas, &mapping->i_pages, folio->index); + long nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ - if (!PageHuge(page)) { - xas_set_order(&xas, page->index, compound_order(page)); - nr = compound_nr(page); + if (!folio_test_hugetlb(folio)) { + xas_set_order(&xas, folio->index, folio_order(folio)); + nr = folio_nr_pages(folio); } - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(nr != 1 && shadow, page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); - page->mapping = NULL; + folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - - if (shadow) { - mapping->nrexceptional += nr; - /* - * Make sure the nrexceptional update is committed before - * the nrpages update so that final truncate racing - * with reclaim does not see both counters 0 at the - * same time and miss a shadow entry. - */ - smp_wmb(); - } mapping->nrpages -= nr; } -static void unaccount_page_cache_page(struct address_space *mapping, - struct page *page) +static void filemap_unaccount_folio(struct address_space *mapping, + struct folio *folio) { - int nr; - - /* - * if we're uptodate, flush out into the cleancache, otherwise - * invalidate any existing cleancache entries. We can't leave - * stale data around in the cleancache once our page is gone - */ - if (PageUptodate(page) && PageMappedToDisk(page)) - cleancache_put_page(page); - else - cleancache_invalidate_page(mapping, page); - - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(page_mapped(page), page); - if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { - int mapcount; + long nr; + VM_BUG_ON_FOLIO(folio_mapped(folio), folio); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", - current->comm, page_to_pfn(page)); - dump_page(page, "still mapped when deleted"); + current->comm, folio_pfn(folio)); + dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); - mapcount = page_mapcount(page); - if (mapping_exiting(mapping) && - page_count(page) >= mapcount + 2) { - /* - * All vmas have already been torn down, so it's - * a good bet that actually the page is unmapped, - * and we'd prefer not to leak it: if we're wrong, - * some other bad page check should catch it later. - */ - page_mapcount_reset(page); - page_ref_sub(page, mapcount); + if (mapping_exiting(mapping) && !folio_test_large(folio)) { + int mapcount = page_mapcount(&folio->page); + + if (folio_ref_count(folio) >= mapcount + 2) { + /* + * All vmas have already been torn down, so it's + * a good bet that actually the page is unmapped + * and we'd rather not leak it: if we're wrong, + * another bad page check should catch it later. + */ + page_mapcount_reset(&folio->page); + folio_ref_sub(folio, mapcount); + } } } - /* hugetlb pages do not participate in page cache accounting. */ - if (PageHuge(page)) + /* hugetlb folios do not participate in page cache accounting. */ + if (folio_test_hugetlb(folio)) return; - nr = hpage_nr_pages(page); + nr = folio_nr_pages(folio); - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); - if (PageSwapBacked(page)) { - __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr); - if (PageTransHuge(page)) - __dec_node_page_state(page, NR_SHMEM_THPS); - } else if (PageTransHuge(page)) { - __dec_node_page_state(page, NR_FILE_THPS); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); + if (folio_test_swapbacked(folio)) { + __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); + } else if (folio_test_pmd_mappable(folio)) { + __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* - * At this point page must be either written or cleaned by - * truncate. Dirty page here signals a bug and loss of - * unwritten data. + * At this point folio must be either written or cleaned by + * truncate. Dirty folio here signals a bug and loss of + * unwritten data - on ordinary filesystems. + * + * But it's harmless on in-memory filesystems like tmpfs; and can + * occur when a driver which did get_user_pages() sets page dirty + * before putting it, while the inode is being finally evicted. * - * This fixes dirty accounting after removing the page entirely - * but leaves PageDirty set: it has no effect for truncated - * page and anyway will be cleared before returning page into + * Below fixes dirty accounting after removing the folio entirely + * but leaves the dirty flag set: it has no effect for truncated + * folio and anyway will be cleared before returning folio to * buddy allocator. */ - if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); + if (WARN_ON_ONCE(folio_test_dirty(folio) && + mapping_can_writeback(mapping))) + folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* @@ -228,84 +214,81 @@ static void unaccount_page_cache_page(struct address_space *mapping, * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ -void __delete_from_page_cache(struct page *page, void *shadow) +void __filemap_remove_folio(struct folio *folio, void *shadow) { - struct address_space *mapping = page->mapping; - - trace_mm_filemap_delete_from_page_cache(page); + struct address_space *mapping = folio->mapping; - unaccount_page_cache_page(mapping, page); - page_cache_delete(mapping, page, shadow); + trace_mm_filemap_delete_from_page_cache(folio); + filemap_unaccount_folio(mapping, folio); + page_cache_delete(mapping, folio, shadow); } -static void page_cache_free_page(struct address_space *mapping, - struct page *page) +void filemap_free_folio(struct address_space *mapping, struct folio *folio) { - void (*freepage)(struct page *); + void (*free_folio)(struct folio *); + int refs = 1; - freepage = mapping->a_ops->freepage; - if (freepage) - freepage(page); + free_folio = mapping->a_ops->free_folio; + if (free_folio) + free_folio(folio); - if (PageTransHuge(page) && !PageHuge(page)) { - page_ref_sub(page, HPAGE_PMD_NR); - VM_BUG_ON_PAGE(page_count(page) <= 0, page); - } else { - put_page(page); - } + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + refs = folio_nr_pages(folio); + folio_put_refs(folio, refs); } /** - * delete_from_page_cache - delete page from page cache - * @page: the page which the kernel is trying to remove from page cache + * filemap_remove_folio - Remove folio from page cache. + * @folio: The folio. * - * This must be called only on pages that have been verified to be in the page - * cache and locked. It will never put the page into the free list, the caller - * has a reference on the page. + * This must be called only on folios that are locked and have been + * verified to be in the page cache. It will never put the folio into + * the free list because the caller has a reference on the page. */ -void delete_from_page_cache(struct page *page) +void filemap_remove_folio(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - unsigned long flags; + struct address_space *mapping = folio->mapping; - BUG_ON(!PageLocked(page)); - xa_lock_irqsave(&mapping->i_pages, flags); - __delete_from_page_cache(page, NULL); - xa_unlock_irqrestore(&mapping->i_pages, flags); + BUG_ON(!folio_test_locked(folio)); + spin_lock(&mapping->host->i_lock); + xa_lock_irq(&mapping->i_pages); + __filemap_remove_folio(folio, NULL); + xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); - page_cache_free_page(mapping, page); + filemap_free_folio(mapping, folio); } -EXPORT_SYMBOL(delete_from_page_cache); /* - * page_cache_delete_batch - delete several pages from page cache - * @mapping: the mapping to which pages belong - * @pvec: pagevec with pages to delete + * page_cache_delete_batch - delete several folios from page cache + * @mapping: the mapping to which folios belong + * @fbatch: batch of folios to delete * - * The function walks over mapping->i_pages and removes pages passed in @pvec - * from the mapping. The function expects @pvec to be sorted by page index - * and is optimised for it to be dense. - * It tolerates holes in @pvec (mapping entries at those indices are not - * modified). The function expects only THP head pages to be present in the - * @pvec. + * The function walks over mapping->i_pages and removes folios passed in + * @fbatch from the mapping. The function expects @fbatch to be sorted + * by page index and is optimised for it to be dense. + * It tolerates holes in @fbatch (mapping entries at those indices are not + * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { - XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); - int total_pages = 0; + XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); + long total_pages = 0; int i = 0; - struct page *page; + struct folio *folio; mapping_set_update(&xas, mapping); - xas_for_each(&xas, page, ULONG_MAX) { - if (i >= pagevec_count(pvec)) + xas_for_each(&xas, folio, ULONG_MAX) { + if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our @@ -314,51 +297,48 @@ static void page_cache_delete_batch(struct address_space *mapping, * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ - if (page != pvec->pages[i]) { - VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, - page); + if (folio != fbatch->folios[i]) { + VM_BUG_ON_FOLIO(folio->index > + fbatch->folios[i]->index, folio); continue; } - WARN_ON_ONCE(!PageLocked(page)); + WARN_ON_ONCE(!folio_test_locked(folio)); - if (page->index == xas.xa_index) - page->mapping = NULL; - /* Leave page->index set: truncation lookup relies on it */ + folio->mapping = NULL; + /* Leave folio->index set: truncation lookup relies on it */ - /* - * Move to the next page in the vector if this is a regular - * page or the index is of the last sub-page of this compound - * page. - */ - if (page->index + compound_nr(page) - 1 == xas.xa_index) - i++; + i++; xas_store(&xas, NULL); - total_pages++; + total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { int i; - unsigned long flags; - if (!pagevec_count(pvec)) + if (!folio_batch_count(fbatch)) return; - xa_lock_irqsave(&mapping->i_pages, flags); - for (i = 0; i < pagevec_count(pvec); i++) { - trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); + spin_lock(&mapping->host->i_lock); + xa_lock_irq(&mapping->i_pages); + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; - unaccount_page_cache_page(mapping, pvec->pages[i]); + trace_mm_filemap_delete_from_page_cache(folio); + filemap_unaccount_folio(mapping, folio); } - page_cache_delete_batch(mapping, pvec); - xa_unlock_irqrestore(&mapping->i_pages, flags); + page_cache_delete_batch(mapping, fbatch); + xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); - for (i = 0; i < pagevec_count(pvec); i++) - page_cache_free_page(mapping, pvec->pages[i]); + for (i = 0; i < folio_batch_count(fbatch); i++) + filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) @@ -386,6 +366,32 @@ static int filemap_check_and_keep_errors(struct address_space *mapping) } /** + * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range + * @mapping: address space structure to write + * @wbc: the writeback_control controlling the writeout + * + * Call writepages on the mapping using the provided wbc to control the + * writeout. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc) +{ + int ret; + + if (!mapping_can_writeback(mapping) || + !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + return 0; + + wbc_attach_fdatawrite_inode(wbc, mapping->host); + ret = do_writepages(mapping, wbc); + wbc_detach_inode(wbc); + return ret; +} +EXPORT_SYMBOL(filemap_fdatawrite_wbc); + +/** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts @@ -405,7 +411,6 @@ static int filemap_check_and_keep_errors(struct address_space *mapping) int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { - int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, @@ -413,14 +418,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, .range_end = end, }; - if (!mapping_cap_writeback_dirty(mapping) || - !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - return 0; - - wbc_attach_fdatawrite_inode(&wbc, mapping->host); - ret = do_writepages(mapping, &wbc); - wbc_detach_inode(&wbc); - return ret; + return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, @@ -626,12 +624,34 @@ EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { - if (dax_mapping(mapping)) - return mapping->nrexceptional; - return mapping->nrpages; } +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); + pgoff_t max = end_byte >> PAGE_SHIFT; + struct folio *folio; + + if (end_byte < start_byte) + return false; + + rcu_read_lock(); + xas_for_each(&xas, folio, max) { + if (xas_retry(&xas, folio)) + continue; + if (xa_is_value(folio)) + continue; + if (folio_test_dirty(folio) || folio_test_locked(folio) || + folio_test_writeback(folio)) + break; + } + rcu_read_unlock(); + return folio != NULL; +} +EXPORT_SYMBOL_GPL(filemap_range_has_writeback); + /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages @@ -648,7 +668,7 @@ static bool mapping_needs_writeback(struct address_space *mapping) int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - int err = 0; + int err = 0, err2; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, @@ -659,18 +679,12 @@ int filemap_write_and_wait_range(struct address_space *mapping, * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ - if (err != -EIO) { - int err2 = filemap_fdatawait_range(mapping, - lstart, lend); - if (!err) - err = err2; - } else { - /* Clear any previously stored errors */ - filemap_check_errors(mapping); - } - } else { - err = filemap_check_errors(mapping); + if (err != -EIO) + __filemap_fdatawait_range(mapping, lstart, lend); } + err2 = filemap_check_errors(mapping); + if (!err) + err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); @@ -774,7 +788,6 @@ EXPORT_SYMBOL(file_write_and_wait_range); * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with - * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and @@ -783,16 +796,15 @@ EXPORT_SYMBOL(file_write_and_wait_range); * caller must do that. * * The remove + add is atomic. This function cannot fail. - * - * Return: %0 */ -int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) +void replace_page_cache_page(struct page *old, struct page *new) { + struct folio *fold = page_folio(old); + struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; - void (*freepage)(struct page *) = mapping->a_ops->freepage; + void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); - unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); @@ -802,166 +814,204 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; - xas_lock_irqsave(&xas, flags); + mem_cgroup_migrate(fold, fnew); + + xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) - __dec_node_page_state(new, NR_FILE_PAGES); + __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) - __inc_node_page_state(new, NR_FILE_PAGES); + __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) - __dec_node_page_state(new, NR_SHMEM); + __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) - __inc_node_page_state(new, NR_SHMEM); - xas_unlock_irqrestore(&xas, flags); - mem_cgroup_migrate(old, new); - if (freepage) - freepage(old); - put_page(old); - - return 0; + __inc_lruvec_page_state(new, NR_SHMEM); + xas_unlock_irq(&xas); + if (free_folio) + free_folio(fold); + folio_put(fold); } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask, - void **shadowp) +noinline int __filemap_add_folio(struct address_space *mapping, + struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { - XA_STATE(xas, &mapping->i_pages, offset); - int huge = PageHuge(page); - struct mem_cgroup *memcg; - int error; - void *old; + XA_STATE(xas, &mapping->i_pages, index); + int huge = folio_test_hugetlb(folio); + bool charged = false; + long nr = 1; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageSwapBacked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); if (!huge) { - error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg, false); + int error = mem_cgroup_charge(folio, NULL, gfp); + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) return error; + charged = true; + xas_set_order(&xas, index, folio_order(folio)); + nr = folio_nr_pages(folio); } - get_page(page); - page->mapping = mapping; - page->index = offset; + gfp &= GFP_RECLAIM_MASK; + folio_ref_add(folio, nr); + folio->mapping = mapping; + folio->index = xas.xa_index; do { + unsigned int order = xa_get_order(xas.xa, xas.xa_index); + void *entry, *old = NULL; + + if (order > folio_order(folio)) + xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), + order, gfp); xas_lock_irq(&xas); - old = xas_load(&xas); - if (old && !xa_is_value(old)) - xas_set_err(&xas, -EEXIST); - xas_store(&xas, page); - if (xas_error(&xas)) - goto unlock; + xas_for_each_conflict(&xas, entry) { + old = entry; + if (!xa_is_value(entry)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + } - if (xa_is_value(old)) { - mapping->nrexceptional--; + if (old) { if (shadowp) *shadowp = old; + /* entry may have been split before we acquired lock */ + order = xa_get_order(xas.xa, xas.xa_index); + if (order > folio_order(folio)) { + /* How to handle large swap entries? */ + BUG_ON(shmem_mapping(mapping)); + xas_split(&xas, old, order); + xas_reset(&xas); + } } - mapping->nrpages++; + + xas_store(&xas, folio); + if (xas_error(&xas)) + goto unlock; + + mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ - if (!huge) - __inc_node_page_state(page, NR_FILE_PAGES); + if (!huge) { + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, + NR_FILE_THPS, nr); + } unlock: xas_unlock_irq(&xas); - } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); + } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) goto error; - if (!huge) - mem_cgroup_commit_charge(page, memcg, false, false); - trace_mm_filemap_add_to_page_cache(page); + trace_mm_filemap_add_to_page_cache(folio); return 0; error: - page->mapping = NULL; + if (charged) + mem_cgroup_uncharge(folio); + folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); - put_page(page); + folio_put_refs(folio, nr); return xas_error(&xas); } -ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); +ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); -/** - * add_to_page_cache_locked - add a locked page to the pagecache - * @page: page to add - * @mapping: the page's address_space - * @offset: page index - * @gfp_mask: page allocation mode - * - * This function is used to add a page to the pagecache. It must be locked. - * This function does not add the page to the LRU. The caller must do that. - * - * Return: %0 on success, negative error code otherwise. - */ -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) -{ - return __add_to_page_cache_locked(page, mapping, offset, - gfp_mask, NULL); -} -EXPORT_SYMBOL(add_to_page_cache_locked); - -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; - __SetPageLocked(page); - ret = __add_to_page_cache_locked(page, mapping, offset, - gfp_mask, &shadow); + __folio_set_locked(folio); + ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) - __ClearPageLocked(page); + __folio_clear_locked(folio); else { /* - * The page might have been evicted from cache only + * The folio might have been evicted from cache only * recently, in which case it should be activated like - * any other repeatedly accessed page. - * The exception is pages getting rewritten; evicting other + * any other repeatedly accessed folio. + * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - WARN_ON_ONCE(PageActive(page)); - if (!(gfp_mask & __GFP_WRITE) && shadow) - workingset_refault(page, shadow); - lru_cache_add(page); + WARN_ON_ONCE(folio_test_active(folio)); + if (!(gfp & __GFP_WRITE) && shadow) + workingset_refault(folio, shadow); + folio_add_lru(folio); } return ret; } -EXPORT_SYMBOL_GPL(add_to_page_cache_lru); +EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA -struct page *__page_cache_alloc(gfp_t gfp) +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { int n; - struct page *page; + struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - page = __alloc_pages_node(n, gfp, 0); - } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); + folio = __folio_alloc_node(gfp, order, n); + } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); - return page; + return folio; } - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } -EXPORT_SYMBOL(__page_cache_alloc); +EXPORT_SYMBOL(filemap_alloc_folio); #endif /* + * filemap_invalidate_lock_two - lock invalidate_lock for two mappings + * + * Lock exclusively invalidate_lock of any passed mapping that is not NULL. + * + * @mapping1: the first mapping to lock + * @mapping2: the second mapping to lock + */ +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2) +{ + if (mapping1 > mapping2) + swap(mapping1, mapping2); + if (mapping1) + down_write(&mapping1->invalidate_lock); + if (mapping2 && mapping1 != mapping2) + down_write_nested(&mapping2->invalidate_lock, 1); +} +EXPORT_SYMBOL(filemap_invalidate_lock_two); + +/* + * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings + * + * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. + * + * @mapping1: the first mapping to unlock + * @mapping2: the second mapping to unlock + */ +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2) +{ + if (mapping1) + up_write(&mapping1->invalidate_lock); + if (mapping2 && mapping1 != mapping2) + up_write(&mapping2->invalidate_lock); +} +EXPORT_SYMBOL(filemap_invalidate_unlock_two); + +/* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all @@ -973,11 +1023,11 @@ EXPORT_SYMBOL(__page_cache_alloc); */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) -static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; +static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; -static wait_queue_head_t *page_waitqueue(struct page *page) +static wait_queue_head_t *folio_waitqueue(struct folio *folio) { - return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; + return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) @@ -985,59 +1035,104 @@ void __init pagecache_init(void) int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) - init_waitqueue_head(&page_wait_table[i]); + init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } -/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ -struct wait_page_key { - struct page *page; - int bit_nr; - int page_match; -}; - -struct wait_page_queue { - struct page *page; - int bit_nr; - wait_queue_entry_t wait; -}; - +/* + * The page wait code treats the "wait->flags" somewhat unusually, because + * we have multiple different kinds of waits, not just the usual "exclusive" + * one. + * + * We have: + * + * (a) no special bits set: + * + * We're just waiting for the bit to be released, and when a waker + * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, + * and remove it from the wait queue. + * + * Simple and straightforward. + * + * (b) WQ_FLAG_EXCLUSIVE: + * + * The waiter is waiting to get the lock, and only one waiter should + * be woken up to avoid any thundering herd behavior. We'll set the + * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. + * + * This is the traditional exclusive wait. + * + * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: + * + * The waiter is waiting to get the bit, and additionally wants the + * lock to be transferred to it for fair lock behavior. If the lock + * cannot be taken, we stop walking the wait queue without waking + * the waiter. + * + * This is the "fair lock handoff" case, and in addition to setting + * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see + * that it now has the lock. + */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { + unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); - if (wait_page->page != key->page) - return 0; - key->page_match = 1; - - if (wait_page->bit_nr != key->bit_nr) + if (!wake_page_match(wait_page, key)) return 0; /* - * Stop walking if it's locked. - * Is this safe if put_and_wait_on_page_locked() is in use? - * Yes: the waker must hold a reference to this page, and if PG_locked - * has now already been set by another task, that task must also hold - * a reference to the *same usage* of this page; so there is no need - * to walk on to wake even the put_and_wait_on_page_locked() callers. + * If it's a lock handoff wait, we get the bit for it, and + * stop walking (and do not wake it up) if we can't. + */ + flags = wait->flags; + if (flags & WQ_FLAG_EXCLUSIVE) { + if (test_bit(key->bit_nr, &key->folio->flags)) + return -1; + if (flags & WQ_FLAG_CUSTOM) { + if (test_and_set_bit(key->bit_nr, &key->folio->flags)) + return -1; + flags |= WQ_FLAG_DONE; + } + } + + /* + * We are holding the wait-queue lock, but the waiter that + * is waiting for this will be checking the flags without + * any locking. + * + * So update the flags atomically, and wake up the waiter + * afterwards to avoid any races. This store-release pairs + * with the load-acquire in folio_wait_bit_common(). */ - if (test_bit(key->bit_nr, &key->page->flags)) - return -1; + smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); + wake_up_state(wait->private, mode); - return autoremove_wake_function(wait, mode, sync, key); + /* + * Ok, we have successfully done what we're waiting for, + * and we can unconditionally remove the wait entry. + * + * Note that this pairs with the "finish_wait()" in the + * waiter, and has to be the absolute last thing we do. + * After this list_del_init(&wait->entry) the wait entry + * might be de-allocated and the process might even have + * exited. + */ + list_del_init_careful(&wait->entry); + return (flags & WQ_FLAG_EXCLUSIVE) != 0; } -static void wake_up_page_bit(struct page *page, int bit_nr) +static void folio_wake_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; - key.page = page; + key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; @@ -1063,190 +1158,331 @@ static void wake_up_page_bit(struct page *page, int bit_nr) } /* - * It is possible for other pages to have collided on the waitqueue - * hash, so in that case check for a page match. That prevents a long- - * term waiter + * It's possible to miss clearing waiters here, when we woke our page + * waiters, but the hashed waitqueue has waiters for other pages on it. + * That's okay, it's a rare case. The next waker will clear it. * - * It is still possible to miss a case here, when we woke page waiters - * and removed them from the waitqueue, but there are still other - * page waiters. + * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, + * other), the flag may be cleared in the course of freeing the page; + * but that is not required for correctness. */ - if (!waitqueue_active(q) || !key.page_match) { - ClearPageWaiters(page); - /* - * It's possible to miss clearing Waiters here, when we woke - * our page waiters, but the hashed waitqueue has waiters for - * other pages on it. - * - * That's okay, it's a rare case. The next waker will clear it. - */ - } + if (!waitqueue_active(q) || !key.page_match) + folio_clear_waiters(folio); + spin_unlock_irqrestore(&q->lock, flags); } -static void wake_up_page(struct page *page, int bit) +static void folio_wake(struct folio *folio, int bit) { - if (!PageWaiters(page)) + if (!folio_test_waiters(folio)) return; - wake_up_page_bit(page, bit); + folio_wake_bit(folio, bit); } /* - * A choice of three behaviors for wait_on_page_bit_common(): + * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like - * __lock_page() waiting on then setting PG_locked. + * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like - * wait_on_page_writeback() waiting on PG_writeback. + * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, - * like put_and_wait_on_page_locked() on PG_locked. + * like folio_put_wait_locked() on PG_locked. */ }; -static inline int wait_on_page_bit_common(wait_queue_head_t *q, - struct page *page, int bit_nr, int state, enum behavior behavior) +/* + * Attempt to check (or get) the folio flag, and mark us done + * if successful. + */ +static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, + struct wait_queue_entry *wait) { + if (wait->flags & WQ_FLAG_EXCLUSIVE) { + if (test_and_set_bit(bit_nr, &folio->flags)) + return false; + } else if (test_bit(bit_nr, &folio->flags)) + return false; + + wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; + return true; +} + +/* How many times do we accept lock stealing from under a waiter? */ +int sysctl_page_lock_unfairness = 5; + +static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, + int state, enum behavior behavior) +{ + wait_queue_head_t *q = folio_waitqueue(folio); + int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; - bool bit_is_set; bool thrashing = false; - bool delayacct = false; unsigned long pflags; - int ret = 0; + bool in_thrashing; if (bit_nr == PG_locked && - !PageUptodate(page) && PageWorkingset(page)) { - if (!PageSwapBacked(page)) { - delayacct_thrashing_start(); - delayacct = true; - } + !folio_test_uptodate(folio) && folio_test_workingset(folio)) { + delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); - wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; - wait_page.page = page; + wait_page.folio = folio; wait_page.bit_nr = bit_nr; - for (;;) { - spin_lock_irq(&q->lock); - - if (likely(list_empty(&wait->entry))) { - __add_wait_queue_entry_tail(q, wait); - SetPageWaiters(page); - } +repeat: + wait->flags = 0; + if (behavior == EXCLUSIVE) { + wait->flags = WQ_FLAG_EXCLUSIVE; + if (--unfairness < 0) + wait->flags |= WQ_FLAG_CUSTOM; + } - set_current_state(state); + /* + * Do one last check whether we can get the + * page bit synchronously. + * + * Do the folio_set_waiters() marking before that + * to let any waker we _just_ missed know they + * need to wake us up (otherwise they'll never + * even go to the slow case that looks at the + * page queue), and add ourselves to the wait + * queue if we need to sleep. + * + * This part needs to be done under the queue + * lock to avoid races. + */ + spin_lock_irq(&q->lock); + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, bit_nr, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); - spin_unlock_irq(&q->lock); + /* + * From now on, all the logic will be based on + * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to + * see whether the page bit testing has already + * been done by the wake function. + * + * We can drop our reference to the folio. + */ + if (behavior == DROP) + folio_put(folio); - bit_is_set = test_bit(bit_nr, &page->flags); - if (behavior == DROP) - put_page(page); + /* + * Note that until the "finish_wait()", or until + * we see the WQ_FLAG_WOKEN flag, we need to + * be very careful with the 'wait->flags', because + * we may race with a waker that sets them. + */ + for (;;) { + unsigned int flags; - if (likely(bit_is_set)) - io_schedule(); + set_current_state(state); - if (behavior == EXCLUSIVE) { - if (!test_and_set_bit_lock(bit_nr, &page->flags)) - break; - } else if (behavior == SHARED) { - if (!test_bit(bit_nr, &page->flags)) + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(state, current)) break; + + io_schedule(); + continue; } - if (signal_pending_state(state, current)) { - ret = -EINTR; + /* If we were non-exclusive, we're done */ + if (behavior != EXCLUSIVE) break; - } - if (behavior == DROP) { - /* - * We can no longer safely access page->flags: - * even if CONFIG_MEMORY_HOTREMOVE is not enabled, - * there is a risk of waiting forever on a page reused - * for something that keeps it locked indefinitely. - * But best check for -EINTR above before breaking. - */ + /* If the waker got the lock for us, we're done */ + if (flags & WQ_FLAG_DONE) break; - } + + /* + * Otherwise, if we're getting the lock, we need to + * try to get it ourselves. + * + * And if that fails, we'll have to retry this all. + */ + if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) + goto repeat; + + wait->flags |= WQ_FLAG_DONE; + break; } + /* + * If a signal happened, this 'finish_wait()' may remove the last + * waiter from the wait-queues, but the folio waiters bit will remain + * set. That's ok. The next wakeup will take care of it, and trying + * to do it here would be difficult and prone to races. + */ finish_wait(q, wait); if (thrashing) { - if (delayacct) - delayacct_thrashing_end(); + delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* - * A signal could leave PageWaiters set. Clearing it here if - * !waitqueue_active would be possible (by open-coding finish_wait), - * but still fail to catch it in the case of wait hash collision. We - * already can fail to clear wait hash collision cases, so don't - * bother with signals either. + * NOTE! The wait->flags weren't stable until we've done the + * 'finish_wait()', and we could have exited the loop above due + * to a signal, and had a wakeup event happen after the signal + * test but before the 'finish_wait()'. + * + * So only after the finish_wait() can we reliably determine + * if we got woken up or not, so we can now figure out the final + * return value based on that state without races. + * + * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive + * waiter, but an exclusive one requires WQ_FLAG_DONE. */ + if (behavior == EXCLUSIVE) + return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; - return ret; + return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; +} + +#ifdef CONFIG_MIGRATION +/** + * migration_entry_wait_on_locked - Wait for a migration entry to be removed + * @entry: migration swap entry. + * @ptep: mapped pte pointer. Will return with the ptep unmapped. Only required + * for pte entries, pass NULL for pmd entries. + * @ptl: already locked ptl. This function will drop the lock. + * + * Wait for a migration entry referencing the given page to be removed. This is + * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except + * this can be called without taking a reference on the page. Instead this + * should be called while holding the ptl for the migration entry referencing + * the page. + * + * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock(). + * + * This follows the same logic as folio_wait_bit_common() so see the comments + * there. + */ +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl) +{ + struct wait_page_queue wait_page; + wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; + unsigned long pflags; + bool in_thrashing; + wait_queue_head_t *q; + struct folio *folio = page_folio(pfn_swap_entry_to_page(entry)); + + q = folio_waitqueue(folio); + if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { + delayacct_thrashing_start(&in_thrashing); + psi_memstall_enter(&pflags); + thrashing = true; + } + + init_wait(wait); + wait->func = wake_page_function; + wait_page.folio = folio; + wait_page.bit_nr = PG_locked; + wait->flags = 0; + + spin_lock_irq(&q->lock); + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, PG_locked, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); + + /* + * If a migration entry exists for the page the migration path must hold + * a valid reference to the page, and it must take the ptl to remove the + * migration entry. So the page is valid until the ptl is dropped. + */ + if (ptep) + pte_unmap_unlock(ptep, ptl); + else + spin_unlock(ptl); + + for (;;) { + unsigned int flags; + + set_current_state(TASK_UNINTERRUPTIBLE); + + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) + break; + + io_schedule(); + continue; + } + break; + } + + finish_wait(q, wait); + + if (thrashing) { + delayacct_thrashing_end(&in_thrashing); + psi_memstall_leave(&pflags); + } } +#endif -void wait_on_page_bit(struct page *page, int bit_nr) +void folio_wait_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); + folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit); +EXPORT_SYMBOL(folio_wait_bit); -int wait_on_page_bit_killable(struct page *page, int bit_nr) +int folio_wait_bit_killable(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); + return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit_killable); +EXPORT_SYMBOL(folio_wait_bit_killable); /** - * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked - * @page: The page to wait for. + * folio_put_wait_locked - Drop a reference and wait for it to be unlocked + * @folio: The folio to wait for. + * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * - * The caller should hold a reference on @page. They expect the page to + * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration - * (for example) by holding the reference while waiting for the page to + * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not - * dereference @page. + * dereference @folio. + * + * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ -void put_and_wait_on_page_locked(struct page *page) +static int folio_put_wait_locked(struct folio *folio, int state) { - wait_queue_head_t *q; - - page = compound_head(page); - q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); + return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** - * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue - * @page: Page defining the wait queue of interest + * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue + * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * - * Add an arbitrary @waiter to the wait queue for the nominated @page. + * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ -void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); - SetPageWaiters(page); + folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL_GPL(add_page_wait_queue); +EXPORT_SYMBOL_GPL(folio_add_wait_queue); #ifndef clear_bit_unlock_is_negative_byte @@ -1259,7 +1495,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue); * instead. * * The read of PG_waiters has to be after (or concurrently with) PG_locked - * being cleared, but a memory barrier should be unneccssary since it is + * being cleared, but a memory barrier should be unnecessary since it is * in the same byte as PG_locked. */ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) @@ -1272,55 +1508,117 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem #endif /** - * unlock_page - unlock a locked page - * @page: the page + * folio_unlock - Unlock a locked folio. + * @folio: The folio. * - * Unlocks the page and wakes up sleepers in ___wait_on_page_locked(). - * Also wakes sleepers in wait_on_page_writeback() because the wakeup - * mechanism between PageLocked pages and PageWriteback pages is shared. - * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. + * Unlocks the folio and wakes up any thread sleeping on the page lock. * - * Note that this depends on PG_waiters being the sign bit in the byte - * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to - * clear the PG_locked bit and test PG_waiters at the same time fairly - * portably (architectures that do LL/SC can test any bit, while x86 can - * test the sign bit). + * Context: May be called from interrupt or process context. May not be + * called from NMI context. */ -void unlock_page(struct page *page) +void folio_unlock(struct folio *folio) { + /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); - page = compound_head(page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) - wake_up_page_bit(page, PG_locked); + BUILD_BUG_ON(PG_locked > 7); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0))) + folio_wake_bit(folio, PG_locked); +} +EXPORT_SYMBOL(folio_unlock); + +/** + * folio_end_private_2 - Clear PG_private_2 and wake any waiters. + * @folio: The folio. + * + * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for + * it. The folio reference held for PG_private_2 being set is released. + * + * This is, for example, used when a netfs folio is being written to a local + * disk cache, thereby allowing writes to the cache for the same folio to be + * serialised. + */ +void folio_end_private_2(struct folio *folio) +{ + VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); + clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); + folio_wake_bit(folio, PG_private_2); + folio_put(folio); +} +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. + */ +void folio_wait_private_2(struct folio *folio) +{ + while (folio_test_private_2(folio)) + folio_wait_bit(folio, PG_private_2); +} +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. + * + * Return: + * - 0 if successful. + * - -EINTR if a fatal signal was encountered. + */ +int folio_wait_private_2_killable(struct folio *folio) +{ + int ret = 0; + + while (folio_test_private_2(folio)) { + ret = folio_wait_bit_killable(folio, PG_private_2); + if (ret < 0) + break; + } + + return ret; } -EXPORT_SYMBOL(unlock_page); +EXPORT_SYMBOL(folio_wait_private_2_killable); /** - * end_page_writeback - end writeback against a page - * @page: the page + * folio_end_writeback - End writeback against a folio. + * @folio: The folio. */ -void end_page_writeback(struct page *page) +void folio_end_writeback(struct folio *folio) { /* - * TestClearPageReclaim could be used here but it is an atomic - * operation and overkill in this particular case. Failing to - * shuffle a page marked for immediate reclaim is too mild to - * justify taking an atomic operation penalty at the end of - * ever page writeback. + * folio_test_clear_reclaim() could be used here but it is an + * atomic operation and overkill in this particular case. Failing + * to shuffle a folio marked for immediate reclaim is too mild + * a gain to justify taking an atomic operation penalty at the + * end of every folio writeback. */ - if (PageReclaim(page)) { - ClearPageReclaim(page); - rotate_reclaimable_page(page); + if (folio_test_reclaim(folio)) { + folio_clear_reclaim(folio); + folio_rotate_reclaimable(folio); } - if (!test_clear_page_writeback(page)) + /* + * Writeback does not hold a folio reference of its own, relying + * on truncation to wait for the clearing of PG_writeback. + * But here we must make sure that the folio is not freed and + * reused before the folio_wake(). + */ + folio_get(folio); + if (!__folio_end_writeback(folio)) BUG(); smp_mb__after_atomic(); - wake_up_page(page, PG_writeback); + folio_wake(folio, PG_writeback); + acct_reclaim_writeback(folio); + folio_put(folio); } -EXPORT_SYMBOL(end_page_writeback); +EXPORT_SYMBOL(folio_end_writeback); /* * After completing I/O on a page, call this routine to update the page @@ -1328,91 +1626,116 @@ EXPORT_SYMBOL(end_page_writeback); */ void page_endio(struct page *page, bool is_write, int err) { + struct folio *folio = page_folio(page); + if (!is_write) { if (!err) { - SetPageUptodate(page); + folio_mark_uptodate(folio); } else { - ClearPageUptodate(page); - SetPageError(page); + folio_clear_uptodate(folio); + folio_set_error(folio); } - unlock_page(page); + folio_unlock(folio); } else { if (err) { struct address_space *mapping; - SetPageError(page); - mapping = page_mapping(page); + folio_set_error(folio); + mapping = folio_mapping(folio); if (mapping) mapping_set_error(mapping, err); } - end_page_writeback(page); + folio_end_writeback(folio); } } EXPORT_SYMBOL_GPL(page_endio); /** - * __lock_page - get a lock on the page, assuming we need to sleep to get it - * @__page: the page to lock + * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. + * @folio: The folio to lock */ -void __lock_page(struct page *__page) +void __folio_lock(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, + folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } -EXPORT_SYMBOL(__lock_page); +EXPORT_SYMBOL(__folio_lock); -int __lock_page_killable(struct page *__page) +int __folio_lock_killable(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, + return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } -EXPORT_SYMBOL_GPL(__lock_page_killable); +EXPORT_SYMBOL_GPL(__folio_lock_killable); + +static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) +{ + struct wait_queue_head *q = folio_waitqueue(folio); + int ret = 0; + + wait->folio = folio; + wait->bit_nr = PG_locked; + + spin_lock_irq(&q->lock); + __add_wait_queue_entry_tail(q, &wait->wait); + folio_set_waiters(folio); + ret = !folio_trylock(folio); + /* + * If we were successful now, we know we're still on the + * waitqueue as we're still under the lock. This means it's + * safe to remove and return success, we know the callback + * isn't going to trigger. + */ + if (!ret) + __remove_wait_queue(q, &wait->wait); + else + ret = -EIOCBQUEUED; + spin_unlock_irq(&q->lock); + return ret; +} /* * Return values: - * 1 - page is locked; mmap_sem is still held. - * 0 - page is not locked. - * mmap_sem has been released (up_read()), unless flags had both + * true - folio is locked; mmap_lock is still held. + * false - folio is not locked. + * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in - * which case mmap_sem is still held. + * which case mmap_lock is still held. * - * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 - * with the page locked and the mmap_sem unperturbed. + * If neither ALLOW_RETRY nor KILLABLE are set, will always return true + * with the folio locked and the mmap_lock unperturbed. */ -int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags) { - if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault_flag_allow_retry_first(flags)) { /* - * CAUTION! In this case, mmap_sem is not released + * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) - return 0; + return false; - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) - wait_on_page_locked_killable(page); + folio_wait_locked_killable(folio); else - wait_on_page_locked(page); - return 0; - } else { - if (flags & FAULT_FLAG_KILLABLE) { - int ret; + folio_wait_locked(folio); + return false; + } + if (flags & FAULT_FLAG_KILLABLE) { + bool ret; - ret = __lock_page_killable(page); - if (ret) { - up_read(&mm->mmap_sem); - return 0; - } - } else - __lock_page(page); - return 1; + ret = __folio_lock_killable(folio); + if (ret) { + mmap_read_unlock(mm); + return false; + } + } else { + __folio_lock(folio); } + + return true; } /** @@ -1487,167 +1810,160 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, } EXPORT_SYMBOL(page_cache_prev_miss); -/** - * find_get_entry - find and get a page cache entry +/* + * Lockless page cache protocol: + * On the lookup side: + * 1. Load the folio from i_pages + * 2. Increment the refcount if it's not zero + * 3. If the folio is not found by xas_reload(), put the refcount and retry + * + * On the removal side: + * A. Freeze the page (by zeroing the refcount if nobody else has a reference) + * B. Remove the page from i_pages + * C. Return the page to the page allocator + * + * This means that any page may have its reference count temporarily + * increased by a speculative page cache (or fast GUP) lookup as it can + * be allocated by another user before the RCU grace period expires. + * Because the refcount temporarily acquired here may end up being the + * last refcount on the page, any page allocation must be freeable by + * folio_put(). + */ + +/* + * mapping_get_entry - Get a page cache entry. * @mapping: the address_space to search - * @offset: the page cache index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned with an increased refcount. + * @index: The page cache index. * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. + * Looks up the page cache entry at @mapping & @index. If it is a folio, + * it is returned with an increased refcount. If it is a shadow entry + * of a previously evicted folio, or a swap entry from shmem/tmpfs, + * it is returned without further action. * - * Return: the found page or shadow entry, %NULL if nothing is found. + * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ -struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) +static void *mapping_get_entry(struct address_space *mapping, pgoff_t index) { - XA_STATE(xas, &mapping->i_pages, offset); - struct page *page; + XA_STATE(xas, &mapping->i_pages, index); + struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); - page = xas_load(&xas); - if (xas_retry(&xas, page)) + folio = xas_load(&xas); + if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ - if (!page || xa_is_value(page)) + if (!folio || xa_is_value(folio)) goto out; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto repeat; - /* - * Has the page moved or been split? - * This is part of the lockless pagecache protocol. See - * include/linux/pagemap.h for details. - */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); goto repeat; } - page = find_subpage(page, offset); out: rcu_read_unlock(); - return page; + return folio; } -EXPORT_SYMBOL(find_get_entry); /** - * find_lock_entry - locate, pin and lock a page cache entry - * @mapping: the address_space to search - * @offset: the page cache index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. - * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. - * - * find_lock_entry() may sleep. - * - * Return: the found page or shadow entry, %NULL if nothing is found. - */ -struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) -{ - struct page *page; - -repeat: - page = find_get_entry(mapping, offset); - if (page && !xa_is_value(page)) { - lock_page(page); - /* Has the page been truncated? */ - if (unlikely(page_mapping(page) != mapping)) { - unlock_page(page); - put_page(page); - goto repeat; - } - VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); - } - return page; -} -EXPORT_SYMBOL(find_lock_entry); - -/** - * pagecache_get_page - find and get a page reference - * @mapping: the address_space to search - * @offset: the page index - * @fgp_flags: PCG flags - * @gfp_mask: gfp mask to use for the page cache data page allocation - * - * Looks up the page cache slot at @mapping & @offset. - * - * PCG flags modify how the page is returned. - * - * @fgp_flags can be: - * - * - FGP_ACCESSED: the page will be marked accessed - * - FGP_LOCK: Page is return locked - * - FGP_CREAT: If page is not present then a new page is allocated using - * @gfp_mask and added to the page cache and the VM's LRU - * list. The page is returned locked and with an increased - * refcount. - * - FGP_FOR_MMAP: Similar to FGP_CREAT, only we want to allow the caller to do - * its own locking dance if the page is already in cache, or unlock the page - * before returning if we had to add the page to pagecache. - * - * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even - * if the GFP flags specified for FGP_CREAT are atomic. + * __filemap_get_folio - Find and get a reference to a folio. + * @mapping: The address_space to search. + * @index: The page index. + * @fgp_flags: %FGP flags modify how the folio is returned. + * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. + * + * Looks up the page cache entry at @mapping & @index. + * + * @fgp_flags can be zero or more of these flags: + * + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. + * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it + * instead of allocating a new folio to replace it. + * * %FGP_CREAT - If no page is present then a new page is allocated using + * @gfp and added to the page cache and the VM's LRU list. + * The page is returned locked and with an increased refcount. + * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the + * page is already in cache. If the page was allocated, unlock it before + * returning so the caller can do the same dance. + * * %FGP_WRITE - The page will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't get blocked by page lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * + * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even + * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * - * Return: the found page or %NULL otherwise. + * Return: The found folio or %NULL otherwise. */ -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t gfp_mask) +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) { - struct page *page; + struct folio *folio; repeat: - page = find_get_entry(mapping, offset); - if (xa_is_value(page)) - page = NULL; - if (!page) + folio = mapping_get_entry(mapping, index); + if (xa_is_value(folio)) { + if (fgp_flags & FGP_ENTRY) + return folio; + folio = NULL; + } + if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return NULL; } } else { - lock_page(page); + folio_lock(folio); } /* Has the page been truncated? */ - if (unlikely(compound_head(page)->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - VM_BUG_ON_PAGE(page->index != offset, page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) - mark_page_accessed(page); + folio_mark_accessed(folio); + else if (fgp_flags & FGP_WRITE) { + /* Clear idle flag for buffer write */ + if (folio_test_idle(folio)) + folio_clear_idle(folio); + } + if (fgp_flags & FGP_STABLE) + folio_wait_stable(folio); no_page: - if (!page && (fgp_flags & FGP_CREAT)) { + if (!folio && (fgp_flags & FGP_CREAT)) { int err; - if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; + if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) + gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) - gfp_mask &= ~__GFP_FS; + gfp &= ~__GFP_FS; + if (fgp_flags & FGP_NOWAIT) { + gfp &= ~GFP_KERNEL; + gfp |= GFP_NOWAIT | __GFP_NOWARN; + } - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) @@ -1655,153 +1971,195 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) - __SetPageReferenced(page); + __folio_set_referenced(folio); - err = add_to_page_cache_lru(page, mapping, offset, gfp_mask); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); - page = NULL; + folio_put(folio); + folio = NULL; if (err == -EEXIST) goto repeat; } /* - * add_to_page_cache_lru locks the page, and for mmap we expect - * an unlocked page. + * filemap_add_folio locks the page, and for mmap + * we expect an unlocked page. */ - if (page && (fgp_flags & FGP_FOR_MMAP)) - unlock_page(page); + if (folio && (fgp_flags & FGP_FOR_MMAP)) + folio_unlock(folio); } - return page; + return folio; +} +EXPORT_SYMBOL(__filemap_get_folio); + +static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, + xa_mark_t mark) +{ + struct folio *folio; + +retry: + if (mark == XA_PRESENT) + folio = xas_find(xas, max); + else + folio = xas_find_marked(xas, max, mark); + + if (xas_retry(xas, folio)) + goto retry; + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (!folio || xa_is_value(folio)) + return folio; + + if (!folio_try_get_rcu(folio)) + goto reset; + + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); + goto reset; + } + + return folio; +reset: + xas_reset(xas); + goto retry; } -EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index - * @nr_entries: The maximum number of entries - * @entries: Where the resulting entries are placed + * @end: The final page index (inclusive). + * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * - * find_get_entries() will search for and return a group of up to - * @nr_entries entries in the mapping. The entries are placed at - * @entries. find_get_entries() takes a reference against any actual - * pages it returns. + * find_get_entries() will search for and return a batch of entries in + * the mapping. The entries are placed in @fbatch. find_get_entries() + * takes a reference on any actual folios it returns. * - * The search returns a group of mapping-contiguous page cache entries - * with ascending indexes. There may be holes in the indices due to - * not-present pages. + * The entries have ascending indexes. The indices may not be consecutive + * due to not-present entries or large folios. * - * Any shadow entries of evicted pages, or swap entries from + * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * - * Return: the number of pages and shadow entries which were found. + * Return: The number of entries which were found. */ -unsigned find_get_entries(struct address_space *mapping, - pgoff_t start, unsigned int nr_entries, - struct page **entries, pgoff_t *indices) +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); - struct page *page; - unsigned int ret = 0; - - if (!nr_entries) - return 0; + struct folio *folio; rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { - if (xas_retry(&xas, page)) - continue; - /* - * A shadow entry of a recently evicted page, a swap - * entry from shmem/tmpfs or a DAX entry. Return it - * without attempting to raise page count. - */ - if (xa_is_value(page)) - goto export; + while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) + break; + } + rcu_read_unlock(); - if (!page_cache_get_speculative(page)) - goto retry; + return folio_batch_count(fbatch); +} - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - page = find_subpage(page, xas.xa_index); - -export: - indices[ret] = xas.xa_index; - entries[ret] = page; - if (++ret == nr_entries) +/** + * find_lock_entries - Find a batch of pagecache entries. + * @mapping: The address_space to search. + * @start: The starting page cache index. + * @end: The final page index (inclusive). + * @fbatch: Where the resulting entries are placed. + * @indices: The cache indices of the entries in @fbatch. + * + * find_lock_entries() will return a batch of entries from @mapping. + * Swap, shadow and DAX entries are included. Folios are returned + * locked and with an incremented refcount. Folios which are locked + * by somebody else or under writeback are skipped. Folios which are + * partially outside the range are not returned. + * + * The entries have ascending indexes. The indices may not be consecutive + * due to not-present entries, large folios, folios which could not be + * locked or folios under writeback. + * + * Return: The number of entries which were found. + */ +unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct folio *folio; + + rcu_read_lock(); + while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { + if (!xa_is_value(folio)) { + if (folio->index < start) + goto put; + if (folio->index + folio_nr_pages(folio) - 1 > end) + goto put; + if (!folio_trylock(folio)) + goto put; + if (folio->mapping != mapping || + folio_test_writeback(folio)) + goto unlock; + VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), + folio); + } + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) break; continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); +unlock: + folio_unlock(folio); +put: + folio_put(folio); } rcu_read_unlock(); - return ret; + + return folio_batch_count(fbatch); } /** - * find_get_pages_range - gang pagecache lookup + * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) - * @nr_pages: The maximum number of pages - * @pages: Where the resulting pages are placed + * @fbatch: The batch to fill. * - * find_get_pages_range() will search for and return a group of up to @nr_pages - * pages in the mapping starting at index @start and up to index @end - * (inclusive). The pages are placed at @pages. find_get_pages_range() takes - * a reference against the returned pages. + * Search for and return a batch of folios in the mapping starting at + * index @start and up to index @end (inclusive). The folios are returned + * in @fbatch with an elevated reference count. * - * The search returns a group of mapping-contiguous pages with ascending - * indexes. There may be holes in the indices due to not-present pages. - * We also update @start to index the next page for the traversal. + * The first folio may start before @start; if it does, it will contain + * @start. The final folio may extend beyond @end; if it does, it will + * contain @end. The folios have ascending indices. There may be gaps + * between the folios if there are indices which have no folio in the + * page cache. If folios are added to or removed from the page cache + * while this is running, they may or may not be found by this call. * - * Return: the number of pages which were found. If this number is - * smaller than @nr_pages, the end of specified range has been - * reached. + * Return: The number of folios which were found. + * We also update @start to index the next folio for the traversal. */ -unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, - pgoff_t end, unsigned int nr_pages, - struct page **pages) +unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, + pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); - struct page *page; - unsigned ret = 0; - - if (unlikely(!nr_pages)) - return 0; + struct folio *folio; rcu_read_lock(); - xas_for_each(&xas, page, end) { - if (xas_retry(&xas, page)) - continue; + while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { /* Skip over shadow, swap and DAX entries */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; + if (!folio_batch_add(fbatch, folio)) { + unsigned long nr = folio_nr_pages(folio); - if (!page_cache_get_speculative(page)) - goto retry; - - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - - pages[ret] = find_subpage(page, xas.xa_index); - if (++ret == nr_pages) { - *start = xas.xa_index + 1; + if (folio_test_hugetlb(folio)) + nr = 1; + *start = folio->index + nr; goto out; } - continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); } /* @@ -1817,65 +2175,95 @@ retry: out: rcu_read_unlock(); - return ret; + return folio_batch_count(fbatch); +} +EXPORT_SYMBOL(filemap_get_folios); + +static inline +bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max) +{ + if (!folio_test_large(folio) || folio_test_hugetlb(folio)) + return false; + if (index >= max) + return false; + return index < folio->index + folio_nr_pages(folio) - 1; } /** - * find_get_pages_contig - gang contiguous pagecache lookup + * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search - * @index: The starting page index - * @nr_pages: The maximum number of pages - * @pages: Where the resulting pages are placed + * @start: The starting page index + * @end: The final page index (inclusive) + * @fbatch: The batch to fill * - * find_get_pages_contig() works exactly like find_get_pages(), except - * that the returned number of pages are guaranteed to be contiguous. + * filemap_get_folios_contig() works exactly like filemap_get_folios(), + * except the returned folios are guaranteed to be contiguous. This may + * not return all contiguous folios if the batch gets filled up. * - * Return: the number of pages which were found. + * Return: The number of folios found. + * Also update @start to be positioned for traversal of the next folio. */ -unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, - unsigned int nr_pages, struct page **pages) -{ - XA_STATE(xas, &mapping->i_pages, index); - struct page *page; - unsigned int ret = 0; - if (unlikely(!nr_pages)) - return 0; +unsigned filemap_get_folios_contig(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) +{ + XA_STATE(xas, &mapping->i_pages, *start); + unsigned long nr; + struct folio *folio; rcu_read_lock(); - for (page = xas_load(&xas); page; page = xas_next(&xas)) { - if (xas_retry(&xas, page)) + + for (folio = xas_load(&xas); folio && xas.xa_index <= end; + folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ - if (xa_is_value(page)) - break; + if (xa_is_value(folio)) + goto update_start; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto retry; - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; + if (unlikely(folio != xas_reload(&xas))) + goto put_folio; - pages[ret] = find_subpage(page, xas.xa_index); - if (++ret == nr_pages) - break; + if (!folio_batch_add(fbatch, folio)) { + nr = folio_nr_pages(folio); + + if (folio_test_hugetlb(folio)) + nr = 1; + *start = folio->index + nr; + goto out; + } continue; -put_page: - put_page(page); +put_folio: + folio_put(folio); + retry: xas_reset(&xas); } + +update_start: + nr = folio_batch_count(fbatch); + + if (nr) { + folio = fbatch->folios[nr - 1]; + if (folio_test_hugetlb(folio)) + *start = folio->index + 1; + else + *start = folio->index + folio_nr_pages(folio); + } +out: rcu_read_unlock(); - return ret; + return folio_batch_count(fbatch); } -EXPORT_SYMBOL(find_get_pages_contig); +EXPORT_SYMBOL(filemap_get_folios_contig); /** - * find_get_pages_range_tag - find and return pages in given range matching @tag + * find_get_pages_range_tag - Find and return head pages matching @tag. * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) @@ -1883,8 +2271,9 @@ EXPORT_SYMBOL(find_get_pages_contig); * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * - * Like find_get_pages, except we only return pages which are tagged with - * @tag. We update @index to index the next page for the traversal. + * Like find_get_pages_range(), except we only return head pages which are + * tagged with @tag. @index is updated to the index immediately after the + * last page we return, ready for the next iteration. * * Return: the number of pages which were found. */ @@ -1893,41 +2282,27 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); - struct page *page; + struct folio *folio; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - xas_for_each_marked(&xas, page, end, tag) { - if (xas_retry(&xas, page)) - continue; + while ((folio = find_get_entry(&xas, end, tag))) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - if (!page_cache_get_speculative(page)) - goto retry; - - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - - pages[ret] = find_subpage(page, xas.xa_index); + pages[ret] = &folio->page; if (++ret == nr_pages) { - *index = xas.xa_index + 1; + *index = folio->index + folio_nr_pages(folio); goto out; } - continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); } /* @@ -1962,280 +2337,414 @@ EXPORT_SYMBOL(find_get_pages_range_tag); * * It is going insane. Fix it by quickly scaling down the readahead size. */ -static void shrink_readahead_size_eio(struct file *filp, - struct file_ra_state *ra) +static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } -/** - * generic_file_buffered_read - generic file read routine - * @iocb: the iocb to read - * @iter: data destination - * @written: already copied +/* + * filemap_get_read_batch - Get a batch of folios for read * - * This is a generic file read routine, and uses the - * mapping->a_ops->readpage() function for the actual low-level stuff. + * Get a batch of folios which represent a contiguous range of bytes in + * the file. No exceptional entries will be returned. If @index is in + * the middle of a folio, the entire folio will be returned. The last + * folio in the batch may have the readahead flag set or the uptodate flag + * clear so that the caller can take the appropriate action. + */ +static void filemap_get_read_batch(struct address_space *mapping, + pgoff_t index, pgoff_t max, struct folio_batch *fbatch) +{ + XA_STATE(xas, &mapping->i_pages, index); + struct folio *folio; + + rcu_read_lock(); + for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) + continue; + if (xas.xa_index > max || xa_is_value(folio)) + break; + if (xa_is_sibling(folio)) + break; + if (!folio_try_get_rcu(folio)) + goto retry; + + if (unlikely(folio != xas_reload(&xas))) + goto put_folio; + + if (!folio_batch_add(fbatch, folio)) + break; + if (!folio_test_uptodate(folio)) + break; + if (folio_test_readahead(folio)) + break; + xas_advance(&xas, folio->index + folio_nr_pages(folio) - 1); + continue; +put_folio: + folio_put(folio); +retry: + xas_reset(&xas); + } + rcu_read_unlock(); +} + +static int filemap_read_folio(struct file *file, filler_t filler, + struct folio *folio) +{ + bool workingset = folio_test_workingset(folio); + unsigned long pflags; + int error; + + /* + * A previous I/O error may have been due to temporary failures, + * eg. multipath errors. PG_error will be set again if read_folio + * fails. + */ + folio_clear_error(folio); + + /* Start the actual read. The read will unlock the page. */ + if (unlikely(workingset)) + psi_memstall_enter(&pflags); + error = filler(file, folio); + if (unlikely(workingset)) + psi_memstall_leave(&pflags); + if (error) + return error; + + error = folio_wait_locked_killable(folio); + if (error) + return error; + if (folio_test_uptodate(folio)) + return 0; + if (file) + shrink_readahead_size_eio(&file->f_ra); + return -EIO; +} + +static bool filemap_range_uptodate(struct address_space *mapping, + loff_t pos, struct iov_iter *iter, struct folio *folio) +{ + int count; + + if (folio_test_uptodate(folio)) + return true; + /* pipes can't handle partially uptodate pages */ + if (iov_iter_is_pipe(iter)) + return false; + if (!mapping->a_ops->is_partially_uptodate) + return false; + if (mapping->host->i_blkbits >= folio_shift(folio)) + return false; + + count = iter->count; + if (folio_pos(folio) > pos) { + count -= folio_pos(folio) - pos; + pos = 0; + } else { + pos -= folio_pos(folio); + } + + return mapping->a_ops->is_partially_uptodate(folio, pos, count); +} + +static int filemap_update_page(struct kiocb *iocb, + struct address_space *mapping, struct iov_iter *iter, + struct folio *folio) +{ + int error; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!filemap_invalidate_trylock_shared(mapping)) + return -EAGAIN; + } else { + filemap_invalidate_lock_shared(mapping); + } + + if (!folio_trylock(folio)) { + error = -EAGAIN; + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) + goto unlock_mapping; + if (!(iocb->ki_flags & IOCB_WAITQ)) { + filemap_invalidate_unlock_shared(mapping); + /* + * This is where we usually end up waiting for a + * previously submitted readahead to finish. + */ + folio_put_wait_locked(folio, TASK_KILLABLE); + return AOP_TRUNCATED_PAGE; + } + error = __folio_lock_async(folio, iocb->ki_waitq); + if (error) + goto unlock_mapping; + } + + error = AOP_TRUNCATED_PAGE; + if (!folio->mapping) + goto unlock; + + error = 0; + if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, folio)) + goto unlock; + + error = -EAGAIN; + if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) + goto unlock; + + error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, + folio); + goto unlock_mapping; +unlock: + folio_unlock(folio); +unlock_mapping: + filemap_invalidate_unlock_shared(mapping); + if (error == AOP_TRUNCATED_PAGE) + folio_put(folio); + return error; +} + +static int filemap_create_folio(struct file *file, + struct address_space *mapping, pgoff_t index, + struct folio_batch *fbatch) +{ + struct folio *folio; + int error; + + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); + if (!folio) + return -ENOMEM; + + /* + * Protect against truncate / hole punch. Grabbing invalidate_lock + * here assures we cannot instantiate and bring uptodate new + * pagecache folios after evicting page cache during truncate + * and before actually freeing blocks. Note that we could + * release invalidate_lock after inserting the folio into + * the page cache as the locked folio would then be enough to + * synchronize with hole punching. But there are code paths + * such as filemap_update_page() filling in partially uptodate + * pages or ->readahead() that need to hold invalidate_lock + * while mapping blocks for IO so let's hold the lock here as + * well to keep locking rules simple. + */ + filemap_invalidate_lock_shared(mapping); + error = filemap_add_folio(mapping, folio, index, + mapping_gfp_constraint(mapping, GFP_KERNEL)); + if (error == -EEXIST) + error = AOP_TRUNCATED_PAGE; + if (error) + goto error; + + error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); + if (error) + goto error; + + filemap_invalidate_unlock_shared(mapping); + folio_batch_add(fbatch, folio); + return 0; +error: + filemap_invalidate_unlock_shared(mapping); + folio_put(folio); + return error; +} + +static int filemap_readahead(struct kiocb *iocb, struct file *file, + struct address_space *mapping, struct folio *folio, + pgoff_t last_index) +{ + DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); + + if (iocb->ki_flags & IOCB_NOIO) + return -EAGAIN; + page_cache_async_ra(&ractl, folio, last_index - folio->index); + return 0; +} + +static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter, + struct folio_batch *fbatch) +{ + struct file *filp = iocb->ki_filp; + struct address_space *mapping = filp->f_mapping; + struct file_ra_state *ra = &filp->f_ra; + pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; + pgoff_t last_index; + struct folio *folio; + int err = 0; + + last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE); +retry: + if (fatal_signal_pending(current)) + return -EINTR; + + filemap_get_read_batch(mapping, index, last_index, fbatch); + if (!folio_batch_count(fbatch)) { + if (iocb->ki_flags & IOCB_NOIO) + return -EAGAIN; + page_cache_sync_readahead(mapping, ra, filp, index, + last_index - index); + filemap_get_read_batch(mapping, index, last_index, fbatch); + } + if (!folio_batch_count(fbatch)) { + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) + return -EAGAIN; + err = filemap_create_folio(filp, mapping, + iocb->ki_pos >> PAGE_SHIFT, fbatch); + if (err == AOP_TRUNCATED_PAGE) + goto retry; + return err; + } + + folio = fbatch->folios[folio_batch_count(fbatch) - 1]; + if (folio_test_readahead(folio)) { + err = filemap_readahead(iocb, filp, mapping, folio, last_index); + if (err) + goto err; + } + if (!folio_test_uptodate(folio)) { + if ((iocb->ki_flags & IOCB_WAITQ) && + folio_batch_count(fbatch) > 1) + iocb->ki_flags |= IOCB_NOWAIT; + err = filemap_update_page(iocb, mapping, iter, folio); + if (err) + goto err; + } + + return 0; +err: + if (err < 0) + folio_put(folio); + if (likely(--fbatch->nr)) + return 0; + if (err == AOP_TRUNCATED_PAGE) + goto retry; + return err; +} + +static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) +{ + unsigned int shift = folio_shift(folio); + + return (pos1 >> shift == pos2 >> shift); +} + +/** + * filemap_read - Read data from the page cache. + * @iocb: The iocb to read. + * @iter: Destination for the data. + * @already_read: Number of bytes already read by the caller. * - * This is really ugly. But the goto's actually try to clarify some - * of the logic when it comes to error handling etc. + * Copies data from the page cache. If the data is not currently present, + * uses the readahead and read_folio address_space operations to fetch it. * - * Return: - * * total number of bytes copied, including those the were already @written - * * negative error code if nothing was copied + * Return: Total number of bytes copied, including those already read by + * the caller. If an error happens before any bytes are copied, returns + * a negative error number. */ -static ssize_t generic_file_buffered_read(struct kiocb *iocb, - struct iov_iter *iter, ssize_t written) +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, + ssize_t already_read) { struct file *filp = iocb->ki_filp; + struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; - struct file_ra_state *ra = &filp->f_ra; - loff_t *ppos = &iocb->ki_pos; - pgoff_t index; - pgoff_t last_index; - pgoff_t prev_index; - unsigned long offset; /* offset into pagecache page */ - unsigned int prev_offset; - int error = 0; + struct folio_batch fbatch; + int i, error = 0; + bool writably_mapped; + loff_t isize, end_offset; - if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) + if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; + if (unlikely(!iov_iter_count(iter))) + return 0; + iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + folio_batch_init(&fbatch); - index = *ppos >> PAGE_SHIFT; - prev_index = ra->prev_pos >> PAGE_SHIFT; - prev_offset = ra->prev_pos & (PAGE_SIZE-1); - last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; - offset = *ppos & ~PAGE_MASK; + do { + cond_resched(); - for (;;) { - struct page *page; - pgoff_t end_index; - loff_t isize; - unsigned long nr, ret; + /* + * If we've already successfully copied some data, then we + * can no longer safely return -EIOCBQUEUED. Hence mark + * an async read NOWAIT at that point. + */ + if ((iocb->ki_flags & IOCB_WAITQ) && already_read) + iocb->ki_flags |= IOCB_NOWAIT; - cond_resched(); -find_page: - if (fatal_signal_pending(current)) { - error = -EINTR; - goto out; - } + if (unlikely(iocb->ki_pos >= i_size_read(inode))) + break; - page = find_get_page(mapping, index); - if (!page) { - if (iocb->ki_flags & IOCB_NOWAIT) - goto would_block; - page_cache_sync_readahead(mapping, - ra, filp, - index, last_index - index); - page = find_get_page(mapping, index); - if (unlikely(page == NULL)) - goto no_cached_page; - } - if (PageReadahead(page)) { - page_cache_async_readahead(mapping, - ra, filp, page, - index, last_index - index); - } - if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_NOWAIT) { - put_page(page); - goto would_block; - } + error = filemap_get_pages(iocb, iter, &fbatch); + if (error < 0) + break; - /* - * See comment in do_read_cache_page on why - * wait_on_page_locked is used to avoid unnecessarily - * serialisations and why it's safe. - */ - error = wait_on_page_locked_killable(page); - if (unlikely(error)) - goto readpage_error; - if (PageUptodate(page)) - goto page_ok; - - if (inode->i_blkbits == PAGE_SHIFT || - !mapping->a_ops->is_partially_uptodate) - goto page_not_up_to_date; - /* pipes can't handle partially uptodate pages */ - if (unlikely(iov_iter_is_pipe(iter))) - goto page_not_up_to_date; - if (!trylock_page(page)) - goto page_not_up_to_date; - /* Did it get truncated before we got the lock? */ - if (!page->mapping) - goto page_not_up_to_date_locked; - if (!mapping->a_ops->is_partially_uptodate(page, - offset, iter->count)) - goto page_not_up_to_date_locked; - unlock_page(page); - } -page_ok: /* - * i_size must be checked after we know the page is Uptodate. + * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ - isize = i_size_read(inode); - end_index = (isize - 1) >> PAGE_SHIFT; - if (unlikely(!isize || index > end_index)) { - put_page(page); - goto out; - } - - /* nr is the maximum number of bytes to copy from this page */ - nr = PAGE_SIZE; - if (index == end_index) { - nr = ((isize - 1) & ~PAGE_MASK) + 1; - if (nr <= offset) { - put_page(page); - goto out; - } - } - nr = nr - offset; - - /* If users can be writing to this page using arbitrary - * virtual addresses, take care about potential aliasing - * before reading the page on the kernel side. - */ - if (mapping_writably_mapped(mapping)) - flush_dcache_page(page); + if (unlikely(iocb->ki_pos >= isize)) + goto put_folios; + end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* - * When a sequential read accesses a page several times, - * only mark it as accessed the first time. + * Once we start copying data, we don't want to be touching any + * cachelines that might be contended: */ - if (prev_index != index || offset != prev_offset) - mark_page_accessed(page); - prev_index = index; + writably_mapped = mapping_writably_mapped(mapping); /* - * Ok, we have the page, and it's up-to-date, so - * now we can copy it to user space... + * When a read accesses the same folio several times, only + * mark it as accessed the first time. */ + if (!pos_same_folio(iocb->ki_pos, ra->prev_pos - 1, + fbatch.folios[0])) + folio_mark_accessed(fbatch.folios[0]); + + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + size_t fsize = folio_size(folio); + size_t offset = iocb->ki_pos & (fsize - 1); + size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, + fsize - offset); + size_t copied; + + if (end_offset < folio_pos(folio)) + break; + if (i > 0) + folio_mark_accessed(folio); + /* + * If users can be writing to this folio using arbitrary + * virtual addresses, take care of potential aliasing + * before reading the folio on the kernel side. + */ + if (writably_mapped) + flush_dcache_folio(folio); - ret = copy_page_to_iter(page, offset, nr, iter); - offset += ret; - index += offset >> PAGE_SHIFT; - offset &= ~PAGE_MASK; - prev_offset = offset; - - put_page(page); - written += ret; - if (!iov_iter_count(iter)) - goto out; - if (ret < nr) { - error = -EFAULT; - goto out; - } - continue; - -page_not_up_to_date: - /* Get exclusive access to the page ... */ - error = lock_page_killable(page); - if (unlikely(error)) - goto readpage_error; - -page_not_up_to_date_locked: - /* Did it get truncated before we got the lock? */ - if (!page->mapping) { - unlock_page(page); - put_page(page); - continue; - } - - /* Did somebody else fill it already? */ - if (PageUptodate(page)) { - unlock_page(page); - goto page_ok; - } + copied = copy_folio_to_iter(folio, offset, bytes, iter); -readpage: - /* - * A previous I/O error may have been due to temporary - * failures, eg. multipath errors. - * PG_error will be set again if readpage fails. - */ - ClearPageError(page); - /* Start the actual read. The read will unlock the page. */ - error = mapping->a_ops->readpage(filp, page); - - if (unlikely(error)) { - if (error == AOP_TRUNCATED_PAGE) { - put_page(page); - error = 0; - goto find_page; - } - goto readpage_error; - } + already_read += copied; + iocb->ki_pos += copied; + ra->prev_pos = iocb->ki_pos; - if (!PageUptodate(page)) { - error = lock_page_killable(page); - if (unlikely(error)) - goto readpage_error; - if (!PageUptodate(page)) { - if (page->mapping == NULL) { - /* - * invalidate_mapping_pages got it - */ - unlock_page(page); - put_page(page); - goto find_page; - } - unlock_page(page); - shrink_readahead_size_eio(filp, ra); - error = -EIO; - goto readpage_error; + if (copied < bytes) { + error = -EFAULT; + break; } - unlock_page(page); } +put_folios: + for (i = 0; i < folio_batch_count(&fbatch); i++) + folio_put(fbatch.folios[i]); + folio_batch_init(&fbatch); + } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); - goto page_ok; - -readpage_error: - /* UHHUH! A synchronous read error occurred. Report it */ - put_page(page); - goto out; - -no_cached_page: - /* - * Ok, it wasn't cached, so we need to create a new - * page.. - */ - page = page_cache_alloc(mapping); - if (!page) { - error = -ENOMEM; - goto out; - } - error = add_to_page_cache_lru(page, mapping, index, - mapping_gfp_constraint(mapping, GFP_KERNEL)); - if (error) { - put_page(page); - if (error == -EEXIST) { - error = 0; - goto find_page; - } - goto out; - } - goto readpage; - } - -would_block: - error = -EAGAIN; -out: - ra->prev_pos = prev_index; - ra->prev_pos <<= PAGE_SHIFT; - ra->prev_pos |= prev_offset; - - *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); - return written ? written : error; + + return already_read ? already_read : error; } +EXPORT_SYMBOL_GPL(filemap_read); /** * generic_file_read_iter - generic filesystem read routine @@ -2244,9 +2753,19 @@ out: * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. + * + * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall + * be returned when no data can be read without waiting for I/O requests + * to complete; it doesn't prevent readahead. + * + * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O + * requests shall be made for the read or for readahead. When no data + * can be read, -EAGAIN shall be returned. When readahead would be + * triggered, a partial, possibly empty read shall be returned. + * * Return: * * number of bytes copied, even for partial reads - * * negative error code if nothing was read + * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) @@ -2255,25 +2774,23 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t retval = 0; if (!count) - goto out; /* skip atime */ + return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - loff_t size; - size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { - if (filemap_range_has_page(mapping, iocb->ki_pos, - iocb->ki_pos + count - 1)) + if (filemap_range_needs_writeback(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1)) return -EAGAIN; } else { retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (retval < 0) - goto out; + return retval; } file_accessed(file); @@ -2283,7 +2800,8 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) iocb->ki_pos += retval; count -= retval; } - iov_iter_revert(iter, count - iov_iter_count(iter)); + if (retval != -EIOCBQUEUED) + iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter @@ -2294,39 +2812,143 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ - if (retval < 0 || !count || iocb->ki_pos >= size || - IS_DAX(inode)) - goto out; + if (retval < 0 || !count || IS_DAX(inode)) + return retval; + if (iocb->ki_pos >= i_size_read(inode)) + return retval; } - retval = generic_file_buffered_read(iocb, iter, retval); -out: - return retval; + return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); +static inline loff_t folio_seek_hole_data(struct xa_state *xas, + struct address_space *mapping, struct folio *folio, + loff_t start, loff_t end, bool seek_data) +{ + const struct address_space_operations *ops = mapping->a_ops; + size_t offset, bsz = i_blocksize(mapping->host); + + if (xa_is_value(folio) || folio_test_uptodate(folio)) + return seek_data ? start : end; + if (!ops->is_partially_uptodate) + return seek_data ? end : start; + + xas_pause(xas); + rcu_read_unlock(); + folio_lock(folio); + if (unlikely(folio->mapping != mapping)) + goto unlock; + + offset = offset_in_folio(folio, start) & ~(bsz - 1); + + do { + if (ops->is_partially_uptodate(folio, offset, bsz) == + seek_data) + break; + start = (start + bsz) & ~(bsz - 1); + offset += bsz; + } while (offset < folio_size(folio)); +unlock: + folio_unlock(folio); + rcu_read_lock(); + return start; +} + +static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) +{ + if (xa_is_value(folio)) + return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); + return folio_size(folio); +} + +/** + * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * @mapping: Address space to search. + * @start: First byte to consider. + * @end: Limit of search (exclusive). + * @whence: Either SEEK_HOLE or SEEK_DATA. + * + * If the page cache knows which blocks contain holes and which blocks + * contain data, your filesystem can use this function to implement + * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are + * entirely memory-based such as tmpfs, and filesystems which support + * unwritten extents. + * + * Return: The requested offset on success, or -ENXIO if @whence specifies + * SEEK_DATA and there is no data after @start. There is an implicit hole + * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start + * and @end contain data. + */ +loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, + loff_t end, int whence) +{ + XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); + pgoff_t max = (end - 1) >> PAGE_SHIFT; + bool seek_data = (whence == SEEK_DATA); + struct folio *folio; + + if (end <= start) + return -ENXIO; + + rcu_read_lock(); + while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { + loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; + size_t seek_size; + + if (start < pos) { + if (!seek_data) + goto unlock; + start = pos; + } + + seek_size = seek_folio_size(&xas, folio); + pos = round_up((u64)pos + 1, seek_size); + start = folio_seek_hole_data(&xas, mapping, folio, start, pos, + seek_data); + if (start < pos) + goto unlock; + if (start >= end) + break; + if (seek_size > PAGE_SIZE) + xas_set(&xas, pos >> PAGE_SHIFT); + if (!xa_is_value(folio)) + folio_put(folio); + } + if (seek_data) + start = -ENXIO; +unlock: + rcu_read_unlock(); + if (folio && !xa_is_value(folio)) + folio_put(folio); + if (start > end) + return end; + return start; +} + #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* - * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem + * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. - * @page - the page to lock. + * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * - * This works similar to lock_page_or_retry in that it can drop the mmap_sem. - * It differs in that it actually returns the page locked if it returns 1 and 0 - * if it couldn't lock the page. If we did have to drop the mmap_sem then fpin - * will point to the pinned file and needs to be fput()'ed at a later point. + * This works similar to lock_folio_or_retry in that it can drop the + * mmap_lock. It differs in that it actually returns the folio locked + * if it returns 1 and 0 if it couldn't lock the folio. If we did have + * to drop the mmap_lock then fpin will point to the pinned file and + * needs to be fput()'ed at a later point. */ -static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, +static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { - if (trylock_page(page)) + if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with - * the mmap_sem still held. That's how FAULT_FLAG_RETRY_NOWAIT + * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) @@ -2334,23 +2956,23 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { - if (__lock_page_killable(page)) { + if (__folio_lock_killable(folio)) { /* - * We didn't have the right flags to drop the mmap_sem, + * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals * if we return VM_FAULT_RETRY, so we need to drop the - * mmap_sem here and return 0 if we don't have a fpin. + * mmap_lock here and return 0 if we don't have a fpin. */ if (*fpin == NULL) - up_read(&vmf->vma->vm_mm->mmap_sem); + mmap_read_unlock(vmf->vma->vm_mm); return 0; } } else - __lock_page(page); + __folio_lock(folio); + return 1; } - /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have @@ -2363,67 +2985,90 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; + DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; - pgoff_t offset = vmf->pgoff; + unsigned long vm_flags = vmf->vma->vm_flags; + unsigned int mmap_miss; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* Use the readahead code, even if readahead is disabled */ + if (vm_flags & VM_HUGEPAGE) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); + ra->size = HPAGE_PMD_NR; + /* + * Fetch two PMD folios, so we get the chance to actually + * readahead, unless we've been told not to. + */ + if (!(vm_flags & VM_RAND_READ)) + ra->size *= 2; + ra->async_size = HPAGE_PMD_NR; + page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); + return fpin; + } +#endif /* If we don't want any read-ahead, don't bother */ - if (vmf->vma->vm_flags & VM_RAND_READ) + if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; - if (vmf->vma->vm_flags & VM_SEQ_READ) { + if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); - page_cache_sync_readahead(mapping, ra, file, offset, - ra->ra_pages); + page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ - if (ra->mmap_miss < MMAP_LOTSAMISS * 10) - ra->mmap_miss++; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss < MMAP_LOTSAMISS * 10) + WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ - if (ra->mmap_miss > MMAP_LOTSAMISS) + if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); - ra->start = max_t(long, 0, offset - ra->ra_pages / 2); + ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; - ra_submit(ra, mapping, file); + ractl._index = ra->start; + page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that - * was pinned if we have to drop the mmap_sem in order to do IO. + * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, - struct page *page) + struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; - struct address_space *mapping = file->f_mapping; + DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; - pgoff_t offset = vmf->pgoff; + unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ - if (vmf->vma->vm_flags & VM_RAND_READ) + if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; - if (ra->mmap_miss > 0) - ra->mmap_miss--; - if (PageReadahead(page)) { + + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss) + WRITE_ONCE(ra->mmap_miss, --mmap_miss); + + if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); - page_cache_async_readahead(mapping, ra, file, - page, offset, ra->ra_pages); + page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } @@ -2439,12 +3084,12 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * - * vma->vm_mm->mmap_sem must be held on entry. + * vma->vm_mm->mmap_lock must be held on entry. * - * If our return value has VM_FAULT_RETRY set, it's because the mmap_sem - * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). + * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock + * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * - * If our return value does not have VM_FAULT_RETRY set, the mmap_sem + * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. @@ -2457,84 +3102,111 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; - struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; - pgoff_t offset = vmf->pgoff; - pgoff_t max_off; - struct page *page; + pgoff_t max_idx, index = vmf->pgoff; + struct folio *folio; vm_fault_t ret = 0; + bool mapping_locked = false; - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) + max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ - page = find_get_page(mapping, offset); - if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { + folio = filemap_get_folio(mapping, index); + if (likely(folio)) { /* - * We found the page, so try async readahead before - * waiting for the lock. + * We found the page, so try async readahead before waiting for + * the lock. */ - fpin = do_async_mmap_readahead(vmf, page); - } else if (!page) { + if (!(vmf->flags & FAULT_FLAG_TRIED)) + fpin = do_async_mmap_readahead(vmf, folio); + if (unlikely(!folio_test_uptodate(folio))) { + filemap_invalidate_lock_shared(mapping); + mapping_locked = true; + } + } else { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: - page = pagecache_get_page(mapping, offset, + /* + * See comment in filemap_create_folio() why we need + * invalidate_lock + */ + if (!mapping_locked) { + filemap_invalidate_lock_shared(mapping); + mapping_locked = true; + } + folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); - if (!page) { + if (!folio) { if (fpin) goto out_retry; - return vmf_error(-ENOMEM); + filemap_invalidate_unlock_shared(mapping); + return VM_FAULT_OOM; } } - if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) + if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ - if (unlikely(compound_head(page)->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto retry_find; } - VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ - if (unlikely(!PageUptodate(page))) + if (unlikely(!folio_test_uptodate(folio))) { + /* + * The page was in cache and uptodate and now it is not. + * Strange but possible since we didn't hold the page lock all + * the time. Let's drop everything get the invalidate lock and + * try again. + */ + if (!mapping_locked) { + folio_unlock(folio); + folio_put(folio); + goto retry_find; + } goto page_not_uptodate; + } /* - * We've made it this far and we had to drop our mmap_sem, now is the + * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { - unlock_page(page); + folio_unlock(folio); goto out_retry; } + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) { - unlock_page(page); - put_page(page); + max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(index >= max_idx)) { + folio_unlock(folio); + folio_put(folio); return VM_FAULT_SIGBUS; } - vmf->page = page; + vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: @@ -2544,131 +3216,224 @@ page_not_uptodate: * because there really aren't any performance issues here * and we need to check for errors. */ - ClearPageError(page); fpin = maybe_unlock_mmap_for_io(vmf, fpin); - error = mapping->a_ops->readpage(file, page); - if (!error) { - wait_on_page_locked(page); - if (!PageUptodate(page)) - error = -EIO; - } + error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; - put_page(page); + folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; + filemap_invalidate_unlock_shared(mapping); - /* Things didn't work out. Return zero to tell the mm layer so. */ - shrink_readahead_size_eio(file, ra); return VM_FAULT_SIGBUS; out_retry: /* - * We dropped the mmap_sem, we need to return to the fault handler to + * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ - if (page) - put_page(page); + if (folio) + folio_put(folio); + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); -void filemap_map_pages(struct vm_fault *vmf, - pgoff_t start_pgoff, pgoff_t end_pgoff) +static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) { - struct file *file = vmf->vma->vm_file; - struct address_space *mapping = file->f_mapping; - pgoff_t last_pgoff = start_pgoff; - unsigned long max_idx; - XA_STATE(xas, &mapping->i_pages, start_pgoff); - struct page *page; + struct mm_struct *mm = vmf->vma->vm_mm; - rcu_read_lock(); - xas_for_each(&xas, page, end_pgoff) { - if (xas_retry(&xas, page)) - continue; - if (xa_is_value(page)) - goto next; + /* Huge page is mapped? No need to proceed. */ + if (pmd_trans_huge(*vmf->pmd)) { + unlock_page(page); + put_page(page); + return true; + } - /* - * Check for a locked page first, as a speculative - * reference may adversely influence page migration. - */ - if (PageLocked(page)) - goto next; - if (!page_cache_get_speculative(page)) - goto next; + if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { + vm_fault_t ret = do_set_pmd(vmf, page); + if (!ret) { + /* The page is mapped successfully, reference consumed. */ + unlock_page(page); + return true; + } + } + + if (pmd_none(*vmf->pmd)) + pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); + + /* See comment in handle_pte_fault() */ + if (pmd_devmap_trans_unstable(vmf->pmd)) { + unlock_page(page); + put_page(page); + return true; + } + + return false; +} +static struct folio *next_uptodate_page(struct folio *folio, + struct address_space *mapping, + struct xa_state *xas, pgoff_t end_pgoff) +{ + unsigned long max_idx; + + do { + if (!folio) + return NULL; + if (xas_retry(xas, folio)) + continue; + if (xa_is_value(folio)) + continue; + if (folio_test_locked(folio)) + continue; + if (!folio_try_get_rcu(folio)) + continue; /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) + if (unlikely(folio != xas_reload(xas))) goto skip; - page = find_subpage(page, xas.xa_index); - - if (!PageUptodate(page) || - PageReadahead(page) || - PageHWPoison(page)) + if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto skip; - - if (page->mapping != mapping || !PageUptodate(page)) + if (folio->mapping != mapping) + goto unlock; + if (!folio_test_uptodate(folio)) goto unlock; - max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); - if (page->index >= max_idx) + if (xas->xa_index >= max_idx) goto unlock; + return folio; +unlock: + folio_unlock(folio); +skip: + folio_put(folio); + } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); - if (file->f_ra.mmap_miss > 0) - file->f_ra.mmap_miss--; + return NULL; +} + +static inline struct folio *first_map_page(struct address_space *mapping, + struct xa_state *xas, + pgoff_t end_pgoff) +{ + return next_uptodate_page(xas_find(xas, end_pgoff), + mapping, xas, end_pgoff); +} + +static inline struct folio *next_map_page(struct address_space *mapping, + struct xa_state *xas, + pgoff_t end_pgoff) +{ + return next_uptodate_page(xas_next_entry(xas, end_pgoff), + mapping, xas, end_pgoff); +} - vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; - if (vmf->pte) - vmf->pte += xas.xa_index - last_pgoff; +vm_fault_t filemap_map_pages(struct vm_fault *vmf, + pgoff_t start_pgoff, pgoff_t end_pgoff) +{ + struct vm_area_struct *vma = vmf->vma; + struct file *file = vma->vm_file; + struct address_space *mapping = file->f_mapping; + pgoff_t last_pgoff = start_pgoff; + unsigned long addr; + XA_STATE(xas, &mapping->i_pages, start_pgoff); + struct folio *folio; + struct page *page; + unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); + vm_fault_t ret = 0; + + rcu_read_lock(); + folio = first_map_page(mapping, &xas, end_pgoff); + if (!folio) + goto out; + + if (filemap_map_pmd(vmf, &folio->page)) { + ret = VM_FAULT_NOPAGE; + goto out; + } + + addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); + do { +again: + page = folio_file_page(folio, xas.xa_index); + if (PageHWPoison(page)) + goto unlock; + + if (mmap_miss > 0) + mmap_miss--; + + addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; + vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - if (alloc_set_pte(vmf, NULL, page)) + + /* + * NOTE: If there're PTE markers, we'll leave them to be + * handled in the specific fault path, and it'll prohibit the + * fault-around logic. + */ + if (!pte_none(*vmf->pte)) goto unlock; - unlock_page(page); - goto next; + + /* We're about to handle the fault */ + if (vmf->address == addr) + ret = VM_FAULT_NOPAGE; + + do_set_pte(vmf, page, addr); + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, addr, vmf->pte); + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } + folio_unlock(folio); + continue; unlock: - unlock_page(page); -skip: - put_page(page); -next: - /* Huge page is mapped? No need to proceed. */ - if (pmd_trans_huge(*vmf->pmd)) - break; - } + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + goto again; + } + folio_unlock(folio); + folio_put(folio); + } while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL); + pte_unmap_unlock(vmf->pte, vmf->ptl); +out: rcu_read_unlock(); + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); + return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { - struct page *page = vmf->page; - struct inode *inode = file_inode(vmf->vma->vm_file); + struct address_space *mapping = vmf->vma->vm_file->f_mapping; + struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; - sb_start_pagefault(inode->i_sb); + sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); - lock_page(page); - if (page->mapping != inode->i_mapping) { - unlock_page(page); + folio_lock(folio); + if (folio->mapping != mapping) { + folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* - * We mark the page dirty already here so that when freeze is in + * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will - * see the dirty page and writeprotect it again. + * see the dirty folio and writeprotect it again. */ - set_page_dirty(page); - wait_for_stable_page(page); + folio_mark_dirty(folio); + folio_wait_stable(folio); out: - sb_end_pagefault(inode->i_sb); + sb_end_pagefault(mapping->host->i_sb); return ret; } @@ -2680,11 +3445,11 @@ const struct vm_operations_struct generic_file_vm_ops = { /* This is used for a general mmap of a disk file */ -int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; - if (!mapping->a_ops->readpage) + if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; @@ -2705,11 +3470,11 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } -int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } -int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } @@ -2719,137 +3484,105 @@ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); -static struct page *wait_on_page_read(struct page *page) +static struct folio *do_read_cache_folio(struct address_space *mapping, + pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - put_page(page); - page = ERR_PTR(-EIO); - } - } - return page; -} - -static struct page *do_read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data, - gfp_t gfp) -{ - struct page *page; + struct folio *folio; int err; + + if (!filler) + filler = mapping->a_ops->read_folio; repeat: - page = find_get_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp); - if (!page) + folio = filemap_get_folio(mapping, index); + if (!folio) { + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return ERR_PTR(-ENOMEM); - err = add_to_page_cache_lru(page, mapping, index, gfp); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); + folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } -filler: - if (filler) - err = filler(data, page); - else - err = mapping->a_ops->readpage(data, page); - - if (err < 0) { - put_page(page); - return ERR_PTR(err); - } - - page = wait_on_page_read(page); - if (IS_ERR(page)) - return page; - goto out; + goto filler; } - if (PageUptodate(page)) - goto out; - - /* - * Page is not up to date and may be locked due one of the following - * case a: Page is being filled and the page lock is held - * case b: Read/write error clearing the page uptodate status - * case c: Truncation in progress (page locked) - * case d: Reclaim in progress - * - * Case a, the page will be up to date when the page is unlocked. - * There is no need to serialise on the page lock here as the page - * is pinned so the lock gives no additional protection. Even if the - * the page is truncated, the data is still valid if PageUptodate as - * it's a race vs truncate race. - * Case b, the page will not be up to date - * Case c, the page may be truncated but in itself, the data may still - * be valid after IO completes as it's a read vs truncate race. The - * operation must restart if the page is not uptodate on unlock but - * otherwise serialising on page lock to stabilise the mapping gives - * no additional guarantees to the caller as the page lock is - * released before return. - * Case d, similar to truncation. If reclaim holds the page lock, it - * will be a race with remove_mapping that determines if the mapping - * is valid on unlock but otherwise the data is valid and there is - * no need to serialise with page lock. - * - * As the page lock gives no additional guarantee, we optimistically - * wait on the page to be unlocked and check if it's up to date and - * use the page if it is. Otherwise, the page lock is required to - * distinguish between the different cases. The motivation is that we - * avoid spurious serialisations and wakeups when multiple processes - * wait on the same page for IO to complete. - */ - wait_on_page_locked(page); - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) goto out; - /* Distinguish between all the cases under the safety of the lock */ - lock_page(page); + if (!folio_trylock(folio)) { + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + goto repeat; + } - /* Case c or d, restart the operation */ - if (!page->mapping) { - unlock_page(page); - put_page(page); + /* Folio was truncated from mapping */ + if (!folio->mapping) { + folio_unlock(folio); + folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ - if (PageUptodate(page)) { - unlock_page(page); + if (folio_test_uptodate(folio)) { + folio_unlock(folio); goto out; } - goto filler; + +filler: + err = filemap_read_folio(file, filler, folio); + if (err) { + folio_put(folio); + if (err == AOP_TRUNCATED_PAGE) + goto repeat; + return ERR_PTR(err); + } out: - mark_page_accessed(page); - return page; + folio_mark_accessed(folio); + return folio; } /** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL + * read_cache_folio - Read into page cache, fill it if needed. + * @mapping: The address_space to read from. + * @index: The index to read. + * @filler: Function to perform the read, or NULL to use aops->read_folio(). + * @file: Passed to filler function, may be NULL if not required. * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page and wait for it to become unlocked. + * Read one page into the page cache. If it succeeds, the folio returned + * will contain @index, but it may not be the first page of the folio. * - * If the page does not get brought uptodate, return -EIO. + * If the filler function returns an error, it will be returned to the + * caller. * - * Return: up to date page on success, ERR_PTR() on failure. + * Context: May sleep. Expects mapping->invalidate_lock to be held. + * Return: An uptodate folio on success, ERR_PTR() on failure. */ +struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, + filler_t filler, struct file *file) +{ + return do_read_cache_folio(mapping, index, filler, file, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(read_cache_folio); + +static struct page *do_read_cache_page(struct address_space *mapping, + pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) +{ + struct folio *folio; + + folio = do_read_cache_folio(mapping, index, filler, file, gfp); + if (IS_ERR(folio)) + return &folio->page; + return folio_file_page(folio, index); +} + struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) + pgoff_t index, filler_t *filler, struct file *file) { - return do_read_cache_page(mapping, index, filler, data, + return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); @@ -2865,6 +3598,8 @@ EXPORT_SYMBOL(read_cache_page); * * If the page does not get brought uptodate, return -EIO. * + * The function expects mapping->invalidate_lock to be already held. + * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, @@ -2876,259 +3611,15 @@ struct page *read_cache_page_gfp(struct address_space *mapping, EXPORT_SYMBOL(read_cache_page_gfp); /* - * Don't operate on ranges the page cache doesn't support, and don't exceed the - * LFS limits. If pos is under the limit it becomes a short access. If it - * exceeds the limit we return -EFBIG. - */ -static int generic_write_check_limits(struct file *file, loff_t pos, - loff_t *count) -{ - struct inode *inode = file->f_mapping->host; - loff_t max_size = inode->i_sb->s_maxbytes; - loff_t limit = rlimit(RLIMIT_FSIZE); - - if (limit != RLIM_INFINITY) { - if (pos >= limit) { - send_sig(SIGXFSZ, current, 0); - return -EFBIG; - } - *count = min(*count, limit - pos); - } - - if (!(file->f_flags & O_LARGEFILE)) - max_size = MAX_NON_LFS; - - if (unlikely(pos >= max_size)) - return -EFBIG; - - *count = min(*count, max_size - pos); - - return 0; -} - -/* - * Performs necessary checks before doing a write - * - * Can adjust writing position or amount of bytes to write. - * Returns appropriate error code that caller should return or - * zero in case that write should be allowed. - */ -inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - loff_t count; - int ret; - - if (IS_SWAPFILE(inode)) - return -ETXTBSY; - - if (!iov_iter_count(from)) - return 0; - - /* FIXME: this is for backwards compatibility with 2.4 */ - if (iocb->ki_flags & IOCB_APPEND) - iocb->ki_pos = i_size_read(inode); - - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) - return -EINVAL; - - count = iov_iter_count(from); - ret = generic_write_check_limits(file, iocb->ki_pos, &count); - if (ret) - return ret; - - iov_iter_truncate(from, count); - return iov_iter_count(from); -} -EXPORT_SYMBOL(generic_write_checks); - -/* - * Performs necessary checks before doing a clone. - * - * Can adjust amount of bytes to clone via @req_count argument. - * Returns appropriate error code that caller should return or - * zero in case the clone should be allowed. - */ -int generic_remap_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *req_count, unsigned int remap_flags) -{ - struct inode *inode_in = file_in->f_mapping->host; - struct inode *inode_out = file_out->f_mapping->host; - uint64_t count = *req_count; - uint64_t bcount; - loff_t size_in, size_out; - loff_t bs = inode_out->i_sb->s_blocksize; - int ret; - - /* The start of both ranges must be aligned to an fs block. */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) - return -EINVAL; - - /* Ensure offsets don't wrap. */ - if (pos_in + count < pos_in || pos_out + count < pos_out) - return -EINVAL; - - size_in = i_size_read(inode_in); - size_out = i_size_read(inode_out); - - /* Dedupe requires both ranges to be within EOF. */ - if ((remap_flags & REMAP_FILE_DEDUP) && - (pos_in >= size_in || pos_in + count > size_in || - pos_out >= size_out || pos_out + count > size_out)) - return -EINVAL; - - /* Ensure the infile range is within the infile. */ - if (pos_in >= size_in) - return -EINVAL; - count = min(count, size_in - (uint64_t)pos_in); - - ret = generic_write_check_limits(file_out, pos_out, &count); - if (ret) - return ret; - - /* - * If the user wanted us to link to the infile's EOF, round up to the - * next block boundary for this check. - * - * Otherwise, make sure the count is also block-aligned, having - * already confirmed the starting offsets' block alignment. - */ - if (pos_in + count == size_in) { - bcount = ALIGN(size_in, bs) - pos_in; - } else { - if (!IS_ALIGNED(count, bs)) - count = ALIGN_DOWN(count, bs); - bcount = count; - } - - /* Don't allow overlapped cloning within the same file. */ - if (inode_in == inode_out && - pos_out + bcount > pos_in && - pos_out < pos_in + bcount) - return -EINVAL; - - /* - * We shortened the request but the caller can't deal with that, so - * bounce the request back to userspace. - */ - if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) - return -EINVAL; - - *req_count = count; - return 0; -} - - -/* - * Performs common checks before doing a file copy/clone - * from @file_in to @file_out. - */ -int generic_file_rw_checks(struct file *file_in, struct file *file_out) -{ - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); - - /* Don't copy dirs, pipes, sockets... */ - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; - - if (!(file_in->f_mode & FMODE_READ) || - !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND)) - return -EBADF; - - return 0; -} - -/* - * Performs necessary checks before doing a file copy - * - * Can adjust amount of bytes to copy via @req_count argument. - * Returns appropriate error code that caller should return or - * zero in case the copy should be allowed. - */ -int generic_copy_file_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t *req_count, unsigned int flags) -{ - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); - uint64_t count = *req_count; - loff_t size_in; - int ret; - - ret = generic_file_rw_checks(file_in, file_out); - if (ret) - return ret; - - /* Don't touch certain kinds of inodes */ - if (IS_IMMUTABLE(inode_out)) - return -EPERM; - - if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) - return -ETXTBSY; - - /* Ensure offsets don't wrap. */ - if (pos_in + count < pos_in || pos_out + count < pos_out) - return -EOVERFLOW; - - /* Shorten the copy to EOF */ - size_in = i_size_read(inode_in); - if (pos_in >= size_in) - count = 0; - else - count = min(count, size_in - (uint64_t)pos_in); - - ret = generic_write_check_limits(file_out, pos_out, &count); - if (ret) - return ret; - - /* Don't allow overlapped copying within the same file. */ - if (inode_in == inode_out && - pos_out + count > pos_in && - pos_out < pos_in + count) - return -EINVAL; - - *req_count = count; - return 0; -} - -int pagecache_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) -{ - const struct address_space_operations *aops = mapping->a_ops; - - return aops->write_begin(file, mapping, pos, len, flags, - pagep, fsdata); -} -EXPORT_SYMBOL(pagecache_write_begin); - -int pagecache_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - const struct address_space_operations *aops = mapping->a_ops; - - return aops->write_end(file, mapping, pos, len, copied, page, fsdata); -} -EXPORT_SYMBOL(pagecache_write_end); - -/* * Warn about a page cache invalidation failure during a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; - struct inode *inode = file_inode(filp); char *path; - errseq_set(&inode->i_mapping->wb_err, -EIO); + errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) @@ -3155,7 +3646,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ - if (filemap_range_has_page(inode->i_mapping, pos, + if (filemap_range_has_page(file->f_mapping, pos, pos + write_len - 1)) return -EAGAIN; } else { @@ -3215,49 +3706,28 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) } iocb->ki_pos = pos; } - iov_iter_revert(from, write_len - iov_iter_count(from)); + if (written != -EIOCBQUEUED) + iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } EXPORT_SYMBOL(generic_file_direct_write); -/* - * Find or create a page at the given pagecache position. Return the locked - * page. This function is specifically for buffered writes. - */ -struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags) -{ - struct page *page; - int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; - - if (flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - - page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (page) - wait_for_stable_page(page); - - return page; -} -EXPORT_SYMBOL(grab_cache_page_write_begin); - -ssize_t generic_perform_write(struct file *file, - struct iov_iter *i, loff_t pos) +ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { + struct file *file = iocb->ki_filp; + loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; - unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ - void *fsdata; + void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, @@ -3269,12 +3739,8 @@ again: * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. - * - * Not only is this an optimisation, but it is also required - * to check that the address is actually valid, when atomic - * usercopies are used, below. */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } @@ -3284,7 +3750,7 @@ again: break; } - status = a_ops->write_begin(file, mapping, pos, bytes, flags, + status = a_ops->write_begin(file, mapping, pos, bytes, &page, &fsdata); if (unlikely(status < 0)) break; @@ -3292,33 +3758,31 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); + copied = copy_page_from_iter_atomic(page, offset, bytes, i); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); - if (unlikely(status < 0)) - break; - copied = status; - + if (unlikely(status != copied)) { + iov_iter_revert(i, copied - max(status, 0L)); + if (unlikely(status < 0)) + break; + } cond_resched(); - iov_iter_advance(i, copied); - if (unlikely(copied == 0)) { + if (unlikely(status == 0)) { /* - * If we were unable to copy any data at all, we must - * fall back to a single segment length write. - * - * If we didn't fallback here, we could livelock - * because not all segments in the iov can be copied at - * once without a pagefault. + * A short copy made ->write_end() reject the + * thing entirely. Might be memory poisoning + * halfway through, might be a race with munmap, + * might be severe memory pressure. */ - bytes = min_t(unsigned long, PAGE_SIZE - offset, - iov_iter_single_seg_count(i)); + if (copied) + bytes = copied; goto again; } - pos += copied; - written += copied; + pos += status; + written += status; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); @@ -3337,12 +3801,12 @@ EXPORT_SYMBOL(generic_perform_write); * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * - * It expects i_mutex to be grabbed unless we work on a block device or similar + * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to - * avoid syncing under i_mutex. + * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes @@ -3351,7 +3815,7 @@ EXPORT_SYMBOL(generic_perform_write); ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space * mapping = file->f_mapping; + struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; @@ -3381,7 +3845,8 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; - status = generic_perform_write(file, from, pos = iocb->ki_pos); + pos = iocb->ki_pos; + status = generic_perform_write(iocb, from); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were @@ -3413,7 +3878,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) */ } } else { - written = generic_perform_write(file, from, iocb->ki_pos); + written = generic_perform_write(iocb, from); if (likely(written > 0)) iocb->ki_pos += written; } @@ -3430,7 +3895,7 @@ EXPORT_SYMBOL(__generic_file_write_iter); * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file - * and acquires i_mutex as needed. + * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write @@ -3455,33 +3920,32 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) EXPORT_SYMBOL(generic_file_write_iter); /** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) + * filemap_release_folio() - Release fs-specific metadata on a folio. + * @folio: The folio which the kernel is trying to free. + * @gfp: Memory allocation flags (and I/O mode). * - * The address_space is to try to release any data against the page - * (presumably at page->private). + * The address_space is trying to release any data attached to a folio + * (presumably at folio->private). * - * This may also be called if PG_fscache is set on a page, indicating that the - * page is known to the local caching routines. + * This will also be called if the private_2 flag is set on a page, + * indicating that the folio has other metadata associated with it. * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). + * The @gfp argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block + * (__GFP_RECLAIM & __GFP_FS). * - * Return: %1 if the release was successful, otherwise return zero. + * Return: %true if the release was successful, otherwise %false. */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) +bool filemap_release_folio(struct folio *folio, gfp_t gfp) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = folio->mapping; - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; + BUG_ON(!folio_test_locked(folio)); + if (folio_test_writeback(folio)) + return false; - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); + if (mapping && mapping->a_ops->release_folio) + return mapping->a_ops->release_folio(folio, gfp); + return try_to_free_buffers(folio); } - -EXPORT_SYMBOL(try_to_release_page); +EXPORT_SYMBOL(filemap_release_folio); |