diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/buffer.c | 54 | ||||
-rw-r--r-- | fs/cramfs/inode.c | 2 | ||||
-rw-r--r-- | fs/ext4/move_extent.c | 46 | ||||
-rw-r--r-- | fs/gfs2/glops.c | 2 | ||||
-rw-r--r-- | fs/gfs2/log.c | 2 | ||||
-rw-r--r-- | fs/gfs2/meta_io.c | 2 | ||||
-rw-r--r-- | fs/hugetlbfs/inode.c | 28 | ||||
-rw-r--r-- | fs/jbd2/commit.c | 33 | ||||
-rw-r--r-- | fs/jbd2/journal.c | 3 | ||||
-rw-r--r-- | fs/mpage.c | 16 | ||||
-rw-r--r-- | fs/nilfs2/btnode.c | 2 | ||||
-rw-r--r-- | fs/nilfs2/btree.c | 2 | ||||
-rw-r--r-- | fs/nilfs2/gcinode.c | 2 | ||||
-rw-r--r-- | fs/nilfs2/mdt.c | 4 | ||||
-rw-r--r-- | fs/nilfs2/segment.c | 2 | ||||
-rw-r--r-- | fs/ntfs3/inode.c | 33 | ||||
-rw-r--r-- | fs/ocfs2/journal.c | 16 | ||||
-rw-r--r-- | fs/proc/task_nommu.c | 2 | ||||
-rw-r--r-- | fs/ramfs/file-nommu.c | 2 | ||||
-rw-r--r-- | fs/reiserfs/journal.c | 4 | ||||
-rw-r--r-- | fs/reiserfs/tail_conversion.c | 2 | ||||
-rw-r--r-- | fs/romfs/mmap-nommu.c | 2 | ||||
-rw-r--r-- | fs/userfaultfd.c | 26 |
23 files changed, 137 insertions, 150 deletions
diff --git a/fs/buffer.c b/fs/buffer.c index d9c6d1fbb6dd..7e42d67bcaad 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -60,7 +60,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); - mark_page_accessed(bh->b_page); + folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); @@ -246,18 +246,18 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; - struct page *page; - int page_uptodate = 1; + struct folio *folio; + int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); - page = bh->b_page; + folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); - SetPageError(page); + folio_set_error(folio); } /* @@ -265,14 +265,14 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ - first = page_buffers(page); + first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) - page_uptodate = 0; + folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; @@ -285,9 +285,9 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * If all of the buffers are uptodate then we can set the page * uptodate. */ - if (page_uptodate) - SetPageUptodate(page); - unlock_page(page); + if (folio_uptodate) + folio_mark_uptodate(folio); + folio_unlock(folio); return; still_busy: @@ -321,7 +321,7 @@ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ if (uptodate && - fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { + fscrypt_inode_uses_fs_layer_crypto(bh->b_folio->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { @@ -344,21 +344,21 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; - struct page *page; + struct folio *folio; BUG_ON(!buffer_async_write(bh)); - page = bh->b_page; + folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); - SetPageError(page); + folio_set_error(folio); } - first = page_buffers(page); + first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); @@ -372,7 +372,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); - end_page_writeback(page); + folio_end_writeback(folio); return; still_busy: @@ -570,7 +570,7 @@ void write_boundary_block(struct block_device *bdev, void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; - struct address_space *buffer_mapping = bh->b_page->mapping; + struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); if (!mapping->private_data) { @@ -1073,7 +1073,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, * and then attach the address_space's inode to its superblock's dirty * inode list. * - * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, + * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) @@ -1095,16 +1095,16 @@ void mark_buffer_dirty(struct buffer_head *bh) } if (!test_set_buffer_dirty(bh)) { - struct page *page = bh->b_page; + struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; - lock_page_memcg(page); - if (!TestSetPageDirty(page)) { - mapping = page_mapping(page); + folio_memcg_lock(folio); + if (!folio_test_set_dirty(folio)) { + mapping = folio->mapping; if (mapping) - __set_page_dirty(page, mapping, 0); + __folio_mark_dirty(folio, mapping, 0); } - unlock_page_memcg(page); + folio_memcg_unlock(folio); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } @@ -1117,8 +1117,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh) set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ - if (bh->b_page && bh->b_page->mapping) - mapping_set_error(bh->b_page->mapping, -EIO); + if (bh->b_folio && bh->b_folio->mapping) + mapping_set_error(bh->b_folio->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); rcu_read_lock(); @@ -1154,7 +1154,7 @@ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { - struct address_space *buffer_mapping = bh->b_page->mapping; + struct address_space *buffer_mapping = bh->b_folio->mapping; spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 61ccf7722fc3..50e4e060db68 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -437,7 +437,7 @@ bailout: static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) { - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; + return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS; } static unsigned long cramfs_physmem_get_unmapped_area(struct file *file, diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 8dbb87edf24c..2de9829aed63 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -110,22 +110,23 @@ out: } /** - * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2 + * mext_folio_double_lock - Grab and lock folio on both @inode1 and @inode2 * * @inode1: the inode structure * @inode2: the inode structure - * @index1: page index - * @index2: page index - * @page: result page vector + * @index1: folio index + * @index2: folio index + * @folio: result folio vector * - * Grab two locked pages for inode's by inode order + * Grab two locked folio for inode's by inode order */ static int -mext_page_double_lock(struct inode *inode1, struct inode *inode2, - pgoff_t index1, pgoff_t index2, struct page *page[2]) +mext_folio_double_lock(struct inode *inode1, struct inode *inode2, + pgoff_t index1, pgoff_t index2, struct folio *folio[2]) { struct address_space *mapping[2]; unsigned int flags; + unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; BUG_ON(!inode1 || !inode2); if (inode1 < inode2) { @@ -138,28 +139,30 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, } flags = memalloc_nofs_save(); - page[0] = grab_cache_page_write_begin(mapping[0], index1); - if (!page[0]) { + folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags, + mapping_gfp_mask(mapping[0])); + if (!folio[0]) { memalloc_nofs_restore(flags); return -ENOMEM; } - page[1] = grab_cache_page_write_begin(mapping[1], index2); + folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags, + mapping_gfp_mask(mapping[1])); memalloc_nofs_restore(flags); - if (!page[1]) { - unlock_page(page[0]); - put_page(page[0]); + if (!folio[1]) { + folio_unlock(folio[0]); + folio_put(folio[0]); return -ENOMEM; } /* - * grab_cache_page_write_begin() may not wait on page's writeback if + * __filemap_get_folio() may not wait on folio's writeback if * BDI not demand that. But it is reasonable to be very conservative - * here and explicitly wait on page's writeback + * here and explicitly wait on folio's writeback */ - wait_on_page_writeback(page[0]); - wait_on_page_writeback(page[1]); + folio_wait_writeback(folio[0]); + folio_wait_writeback(folio[1]); if (inode1 > inode2) - swap(page[0], page[1]); + swap(folio[0], folio[1]); return 0; } @@ -252,7 +255,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, int block_len_in_page, int unwritten, int *err) { struct inode *orig_inode = file_inode(o_filp); - struct page *pagep[2] = {NULL, NULL}; struct folio *folio[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset, donor_blk_offset; @@ -303,8 +305,8 @@ again: replaced_size = data_size; - *err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset, - donor_page_offset, pagep); + *err = mext_folio_double_lock(orig_inode, donor_inode, orig_page_offset, + donor_page_offset, folio); if (unlikely(*err < 0)) goto stop_journal; /* @@ -314,8 +316,6 @@ again: * hold page's lock, if it is still the case data copy is not * necessary, just swap data blocks between orig and donor. */ - folio[0] = page_folio(pagep[0]); - folio[1] = page_folio(pagep[1]); VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]); VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index d78b61ecc1cd..081422644ec5 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -39,7 +39,7 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page " "state 0x%lx\n", bh, (unsigned long long)bh->b_blocknr, bh->b_state, - bh->b_page->mapping, bh->b_page->flags); + bh->b_folio->mapping, bh->b_folio->flags); fs_err(sdp, "AIL glock %u:%llu mapping %p\n", gl->gl_name.ln_type, gl->gl_name.ln_number, gfs2_glock2aspace(gl)); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 723639376ae2..1fcc829f02ab 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -127,7 +127,7 @@ __acquires(&sdp->sd_ail_lock) continue; gl = bd->bd_gl; list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list); - mapping = bh->b_page->mapping; + mapping = bh->b_folio->mapping; if (!mapping) continue; spin_unlock(&sdp->sd_ail_lock); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3c41b864ee5b..924361fa510b 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -334,7 +334,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) void gfs2_remove_from_journal(struct buffer_head *bh, int meta) { - struct address_space *mapping = bh->b_page->mapping; + struct address_space *mapping = bh->b_folio->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct gfs2_bufdata *bd = bh->b_private; struct gfs2_trans *tr = current->journal_info; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 790d2727141a..48f1a8ad2243 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -388,9 +388,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, { pte_t *ptep, pte; - ptep = huge_pte_offset(vma->vm_mm, addr, - huge_page_size(hstate_vma(vma))); - + ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; @@ -412,10 +410,12 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, */ static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start) { + unsigned long offset = 0; + if (vma->vm_pgoff < start) - return (start - vma->vm_pgoff) << PAGE_SHIFT; - else - return 0; + offset = (start - vma->vm_pgoff) << PAGE_SHIFT; + + return vma->vm_start + offset; } static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end) @@ -457,7 +457,7 @@ retry: v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - if (!hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page)) + if (!hugetlb_vma_maps_page(vma, v_start, page)) continue; if (!hugetlb_vma_trylock_write(vma)) { @@ -473,8 +473,8 @@ retry: break; } - unmap_hugepage_range(vma, vma->vm_start + v_start, v_end, - NULL, ZAP_FLAG_DROP_MARKER); + unmap_hugepage_range(vma, v_start, v_end, NULL, + ZAP_FLAG_DROP_MARKER); hugetlb_vma_unlock_write(vma); } @@ -507,10 +507,9 @@ retry: */ v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - if (hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page)) - unmap_hugepage_range(vma, vma->vm_start + v_start, - v_end, NULL, - ZAP_FLAG_DROP_MARKER); + if (hugetlb_vma_maps_page(vma, v_start, page)) + unmap_hugepage_range(vma, v_start, v_end, NULL, + ZAP_FLAG_DROP_MARKER); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); hugetlb_vma_unlock_write(vma); @@ -540,8 +539,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - unmap_hugepage_range(vma, vma->vm_start + v_start, v_end, - NULL, zap_flags); + unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags); /* * Note that vma lock only exists for shared/non-private diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 4810438b7856..b33155dd7001 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -63,16 +63,12 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) static void release_buffer_page(struct buffer_head *bh) { struct folio *folio; - struct page *page; if (buffer_dirty(bh)) goto nope; if (atomic_read(&bh->b_count) != 1) goto nope; - page = bh->b_page; - if (!page) - goto nope; - folio = page_folio(page); + folio = bh->b_folio; if (folio->mapping) goto nope; @@ -181,31 +177,6 @@ static int journal_wait_on_commit_record(journal_t *journal, return ret; } -/* - * write the filemap data using writepage() address_space_operations. - * We don't do block allocation here even for delalloc. We don't - * use writepages() because with delayed allocation we may be doing - * block allocation in writepages(). - */ -int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) -{ - struct address_space *mapping = jinode->i_vfs_inode->i_mapping; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = mapping->nrpages * 2, - .range_start = jinode->i_dirty_start, - .range_end = jinode->i_dirty_end, - }; - - /* - * submit the inode data buffers. We use writepage - * instead of writepages. Because writepages can do - * block allocation with delalloc. We need to write - * only allocated blocks here. - */ - return generic_writepages(mapping, &wbc); -} - /* Send all the data buffers related to an inode */ int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode) { @@ -1040,7 +1011,7 @@ restart_loop: * already detached from the mapping and buffers cannot * get reused. */ - mapping = READ_ONCE(bh->b_page->mapping); + mapping = READ_ONCE(bh->b_folio->mapping); if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { clear_buffer_mapped(bh); clear_buffer_new(bh); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2696f43e7239..e80c781731f8 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -89,7 +89,6 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); -EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); @@ -2938,7 +2937,7 @@ repeat: } else { J_ASSERT_BH(bh, (atomic_read(&bh->b_count) > 0) || - (bh->b_page && bh->b_page->mapping)); + (bh->b_folio && bh->b_folio->mapping)); if (!new_jh) { jbd_unlock_bh_journal_head(bh); diff --git a/fs/mpage.c b/fs/mpage.c index 0f8ae954a579..b8e7975159bc 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -198,7 +198,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) /* * Then do more get_blocks calls until we are done with this folio. */ - map_bh->b_page = &folio->page; + map_bh->b_folio = folio; while (page_block < blocks_per_page) { map_bh->b_state = 0; map_bh->b_size = 0; @@ -524,6 +524,12 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, */ BUG_ON(!PageUptodate(page)); block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); + /* + * Whole page beyond EOF? Skip allocating blocks to avoid leaking + * space. + */ + if (block_in_file >= (i_size + (1 << blkbits) - 1) >> blkbits) + goto page_is_mapped; last_block = (i_size - 1) >> blkbits; map_bh.b_page = page; for (page_block = 0; page_block < blocks_per_page; ) { @@ -641,14 +647,6 @@ out: * * This is a library function, which implements the writepages() * address_space_operation. - * - * If a page is already under I/O, generic_writepages() skips it, even - * if it's dirty. This is desirable behaviour for memory-cleaning writeback, - * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() - * and msync() need to guarantee that all the data which was dirty at the time - * the call was made get new I/O started against them. If wbc->sync_mode is - * WB_SYNC_ALL then we were called for data integrity and we must wait for - * existing IO to complete. */ int mpage_writepages(struct address_space *mapping, diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e74fda212620..e956f886a1a1 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -188,7 +188,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, struct page *opage = obh->b_page; lock_page(opage); retry: - /* BUG_ON(oldkey != obh->b_page->index); */ + /* BUG_ON(oldkey != obh->b_folio->index); */ if (unlikely(oldkey != opage->index)) NILFS_PAGE_BUG(opage, "invalid oldkey %lld (newkey=%lld)", diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 40ce92a332fe..b5f997e5e670 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -398,7 +398,7 @@ int nilfs_btree_broken_node_block(struct buffer_head *bh) if (buffer_nilfs_checked(bh)) return 0; - inode = bh->b_page->mapping->host; + inode = bh->b_folio->mapping->host; ret = nilfs_btree_node_broken((struct nilfs_btree_node *)bh->b_data, bh->b_size, inode, bh->b_blocknr); if (likely(!ret)) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index b0d22ff24b67..48fe71d309cb 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -140,7 +140,7 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) { - struct inode *inode = bh->b_page->mapping->host; + struct inode *inode = bh->b_folio->mapping->host; nilfs_err(inode->i_sb, "I/O error reading %s block for GC (ino=%lu, vblocknr=%llu)", diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index cbf4fa60eea2..19c8158605ed 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -563,7 +563,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int blkbits = inode->i_blkbits; - page = grab_cache_page(shadow->inode->i_mapping, bh->b_page->index); + page = grab_cache_page(shadow->inode->i_mapping, bh->b_folio->index); if (!page) return -ENOMEM; @@ -595,7 +595,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int n; - page = find_lock_page(shadow->inode->i_mapping, bh->b_page->index); + page = find_lock_page(shadow->inode->i_mapping, bh->b_folio->index); if (page) { if (page_has_buffers(page)) { n = bh_offset(bh) >> inode->i_blkbits; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 76c3bd88b858..f7a14ed12a66 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1581,7 +1581,7 @@ nilfs_segctor_update_payload_blocknr(struct nilfs_sc_info *sci, nblocks = le32_to_cpu(finfo->fi_nblocks); ndatablk = le32_to_cpu(finfo->fi_ndatablk); - inode = bh->b_page->mapping->host; + inode = bh->b_folio->mapping->host; if (mode == SC_LSEG_DSYNC) sc_op = &nilfs_sc_dsync_ops; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 20b953871574..6b50b6e32378 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -832,32 +832,29 @@ out: return err; } -static int ntfs_writepage(struct page *page, struct writeback_control *wbc) +static int ntfs_resident_writepage(struct page *page, + struct writeback_control *wbc, void *data) { - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; - struct ntfs_inode *ni = ntfs_i(inode); - int err; + struct address_space *mapping = data; + struct ntfs_inode *ni = ntfs_i(mapping->host); + int ret; - if (is_resident(ni)) { - ni_lock(ni); - err = attr_data_write_resident(ni, page); - ni_unlock(ni); - if (err != E_NTFS_NONRESIDENT) { - unlock_page(page); - return err; - } - } + ni_lock(ni); + ret = attr_data_write_resident(ni, page); + ni_unlock(ni); - return block_write_full_page(page, ntfs_get_block, wbc); + if (ret != E_NTFS_NONRESIDENT) + unlock_page(page); + mapping_set_error(mapping, ret); + return ret; } static int ntfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - /* Redirect call to 'ntfs_writepage' for resident files. */ if (is_resident(ntfs_i(mapping->host))) - return generic_writepages(mapping, wbc); + return write_cache_pages(mapping, wbc, ntfs_resident_writepage, + mapping); return mpage_writepages(mapping, wbc, ntfs_get_block); } @@ -2066,13 +2063,13 @@ const struct inode_operations ntfs_link_inode_operations = { const struct address_space_operations ntfs_aops = { .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, - .writepage = ntfs_writepage, .writepages = ntfs_writepages, .write_begin = ntfs_write_begin, .write_end = ntfs_write_end, .direct_IO = ntfs_direct_IO, .bmap = ntfs_bmap, .dirty_folio = block_dirty_folio, + .migrate_folio = buffer_migrate_folio, .invalidate_folio = block_invalidate_folio, }; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 3fb98b4569a2..25d8072ccfce 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -15,6 +15,7 @@ #include <linux/time.h> #include <linux/random.h> #include <linux/delay.h> +#include <linux/writeback.h> #include <cluster/masklog.h> @@ -841,6 +842,19 @@ bail: return status; } +static int ocfs2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) +{ + struct address_space *mapping = jinode->i_vfs_inode->i_mapping; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = mapping->nrpages * 2, + .range_start = jinode->i_dirty_start, + .range_end = jinode->i_dirty_end, + }; + + return filemap_fdatawrite_wbc(mapping, &wbc); +} + int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) { int status = -1; @@ -910,7 +924,7 @@ int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty) journal->j_journal = j_journal; journal->j_journal->j_submit_inode_data_buffers = - jbd2_journal_submit_inode_data_buffers; + ocfs2_journal_submit_inode_data_buffers; journal->j_journal->j_finish_inode_data_buffers = jbd2_journal_finish_inode_data_buffers; journal->j_inode = inode; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 2fd06f52b6a4..0ec35072a8e5 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -38,7 +38,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) } if (atomic_read(&mm->mm_count) > 1 || - vma->vm_flags & VM_MAYSHARE) { + is_nommu_shared_mapping(vma->vm_flags)) { sbytes += size; } else { bytes += size; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index cb240eac5036..cd4537692751 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -264,7 +264,7 @@ out: */ static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma) { - if (!(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) + if (!is_nommu_shared_mapping(vma->vm_flags)) return -ENOSYS; file_accessed(file); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 9f62da7471c9..9ce4ec296b74 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -601,7 +601,7 @@ static int journal_list_still_alive(struct super_block *s, */ static void release_buffer_page(struct buffer_head *bh) { - struct folio *folio = page_folio(bh->b_page); + struct folio *folio = bh->b_folio; if (!folio->mapping && folio_trylock(folio)) { folio_get(folio); put_bh(bh); @@ -866,7 +866,7 @@ loop_next: * will ever write the buffer. We're safe if we write the * page one last time after freeing the journal header. */ - if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) { + if (buffer_dirty(bh) && unlikely(bh->b_folio->mapping == NULL)) { spin_unlock(lock); write_dirty_buffer(bh, 0); spin_lock(lock); diff --git a/fs/reiserfs/tail_conversion.c b/fs/reiserfs/tail_conversion.c index b0ae088dffc7..2cec61af2a9e 100644 --- a/fs/reiserfs/tail_conversion.c +++ b/fs/reiserfs/tail_conversion.c @@ -177,7 +177,7 @@ void reiserfs_unmap_buffer(struct buffer_head *bh) * BUG() on attempt to write not mapped buffer */ if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) { - struct inode *inode = bh->b_page->mapping->host; + struct inode *inode = bh->b_folio->mapping->host; struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb); spin_lock(&j->j_dirty_buffers_lock); list_del_init(&bh->b_assoc_buffers); diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index 2c4a23113fb5..4578dc45e50a 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -63,7 +63,7 @@ static unsigned long romfs_get_unmapped_area(struct file *file, */ static int romfs_mmap(struct file *file, struct vm_area_struct *vma) { - return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; + return is_nommu_shared_mapping(vma->vm_flags) ? 0 : -ENOSYS; } static unsigned romfs_mmap_capabilities(struct file *file) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index cc694846617a..15a5bf765d43 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -252,14 +252,12 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, unsigned long flags, unsigned long reason) { - struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; - mmap_assert_locked(mm); - - ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); + mmap_assert_locked(ctx->mm); + ptep = hugetlb_walk(vma, address, vma_mmu_pagesize(vma)); if (!ptep) goto out; @@ -391,7 +389,8 @@ static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { - struct mm_struct *mm = vmf->vma->vm_mm; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; @@ -418,7 +417,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) */ mmap_assert_locked(mm); - ctx = vmf->vma->vm_userfaultfd_ctx.ctx; + ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; @@ -508,6 +507,15 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) blocking_state = userfaultfd_get_blocking_state(vmf->flags); + /* + * Take the vma lock now, in order to safely call + * userfaultfd_huge_must_wait() later. Since acquiring the + * (sleepable) vma lock can modify the current task state, that + * must be before explicitly calling set_current_state(). + */ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_lock_read(vma); + spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland @@ -522,13 +530,15 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); - if (!is_vm_hugetlb_page(vmf->vma)) + if (!is_vm_hugetlb_page(vma)) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else - must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, + must_wait = userfaultfd_huge_must_wait(ctx, vma, vmf->address, vmf->flags, reason); + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_unlock_read(vma); mmap_read_unlock(mm); if (likely(must_wait && !READ_ONCE(ctx->released))) { |