From: NeilBrown Subject: mm: perform async writes to SWP_FS_OPS swap-space using ->swap_rw This patch switches swap-out to SWP_FS_OPS swap-spaces to use ->swap_rw and makes the writes asynchronous, like they are for other swap spaces. To make it async we need to allocate the kiocb struct from a mempool. This may block, but won't block as long as waiting for the write to complete. At most it will wait for some previous swap IO to complete. Link: https://lkml.kernel.org/r/164859778126.29473.12399585304843922231.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Signed-off-by: Andrew Morton --- mm/page_io.c | 98 +++++++++++++++++++++++++++++-------------------- 1 file changed, 58 insertions(+), 40 deletions(-) --- a/mm/page_io.c~mm-perform-async-writes-to-swp_fs_ops-swap-space-using-swap_rw +++ a/mm/page_io.c @@ -254,6 +254,57 @@ int sio_pool_init(void) return 0; } +static void sio_write_complete(struct kiocb *iocb, long ret) +{ + struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb); + struct page *page = sio->bvec.bv_page; + + if (ret != PAGE_SIZE) { + /* + * In the case of swap-over-nfs, this can be a + * temporary failure if the system has limited + * memory for allocating transmit buffers. + * Mark the page dirty and avoid + * folio_rotate_reclaimable but rate-limit the + * messages but do not flag PageError like + * the normal direct-to-bio case as it could + * be temporary. + */ + set_page_dirty(page); + ClearPageReclaim(page); + pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n", + ret, page_file_offset(page)); + } else + count_vm_event(PSWPOUT); + end_page_writeback(page); + mempool_free(sio, sio_pool); +} + +static int swap_writepage_fs(struct page *page, struct writeback_control *wbc) +{ + struct swap_iocb *sio; + struct swap_info_struct *sis = page_swap_info(page); + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct iov_iter from; + int ret; + + set_page_writeback(page); + unlock_page(page); + sio = mempool_alloc(sio_pool, GFP_NOIO); + init_sync_kiocb(&sio->iocb, swap_file); + sio->iocb.ki_complete = sio_write_complete; + sio->iocb.ki_pos = page_file_offset(page); + sio->bvec.bv_page = page; + sio->bvec.bv_len = PAGE_SIZE; + sio->bvec.bv_offset = 0; + iov_iter_bvec(&from, WRITE, &sio->bvec, 1, PAGE_SIZE); + ret = mapping->a_ops->swap_rw(&sio->iocb, &from); + if (ret != -EIOCBQUEUED) + sio_write_complete(&sio->iocb, ret); + return ret; +} + int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func) { @@ -262,46 +313,13 @@ int __swap_writepage(struct page *page, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (data_race(sis->flags & SWP_FS_OPS)) { - struct kiocb kiocb; - struct file *swap_file = sis->swap_file; - struct address_space *mapping = swap_file->f_mapping; - struct bio_vec bv = { - .bv_page = page, - .bv_len = PAGE_SIZE, - .bv_offset = 0 - }; - struct iov_iter from; - - iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); - init_sync_kiocb(&kiocb, swap_file); - kiocb.ki_pos = page_file_offset(page); - - set_page_writeback(page); - unlock_page(page); - ret = mapping->a_ops->direct_IO(&kiocb, &from); - if (ret == PAGE_SIZE) { - count_vm_event(PSWPOUT); - ret = 0; - } else { - /* - * In the case of swap-over-nfs, this can be a - * temporary failure if the system has limited - * memory for allocating transmit buffers. - * Mark the page dirty and avoid - * folio_rotate_reclaimable but rate-limit the - * messages but do not flag PageError like - * the normal direct-to-bio case as it could - * be temporary. - */ - set_page_dirty(page); - ClearPageReclaim(page); - pr_err_ratelimited("Write error on dio swapfile (%llu)\n", - page_file_offset(page)); - } - end_page_writeback(page); - return ret; - } + /* + * ->flags can be updated non-atomicially (scan_swap_map_slots), + * but that will never affect SWP_FS_OPS, so the data_race + * is safe. + */ + if (data_race(sis->flags & SWP_FS_OPS)) + return swap_writepage_fs(page, wbc); ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); if (!ret) { _