From: Gao Xiang <gaoxiang25@huawei.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
<devel@driverdev.osuosl.org>
Cc: <linux-fsdevel@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-erofs@lists.ozlabs.org>, <yuchao0@huawei.com>,
<miaoxie@huawei.com>, <weidu.du@huawei.com>, <hsiangkao@aol.com>,
<chao@kernel.org>, Gao Xiang <gaoxiang25@huawei.com>
Subject: [PATCH 04/25] staging: erofs: add raw address_space operations
Date: Thu, 26 Jul 2018 20:21:47 +0800 [thread overview]
Message-ID: <1532607728-103372-5-git-send-email-gaoxiang25@huawei.com> (raw)
In-Reply-To: <1532607728-103372-1-git-send-email-gaoxiang25@huawei.com>
This commit adds functions for meta and raw data, and also
provides address_space_operations for raw data access.
Signed-off-by: Miao Xie <miaoxie@huawei.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
drivers/staging/erofs/data.c | 362 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 362 insertions(+)
create mode 100644 drivers/staging/erofs/data.c
diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c
new file mode 100644
index 0000000..4ddb5c0
--- /dev/null
+++ b/drivers/staging/erofs/data.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/drivers/staging/erofs/data.c
+ *
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ * http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of the Linux
+ * distribution for more details.
+ */
+#include "internal.h"
+#include <linux/prefetch.h>
+
+static inline void read_endio(struct bio *bio)
+{
+ int i;
+ struct bio_vec *bvec;
+ const blk_status_t err = bio->bi_status;
+
+ bio_for_each_segment_all(bvec, bio, i) {
+ struct page *page = bvec->bv_page;
+
+ /* page is already locked */
+ BUG_ON(PageUptodate(page));
+
+ if (unlikely(err))
+ SetPageError(page);
+ else
+ SetPageUptodate(page);
+
+ unlock_page(page);
+ /* page could be reclaimed now */
+ }
+ bio_put(bio);
+}
+
+static void __submit_bio(struct bio *bio, unsigned op, unsigned op_flags)
+{
+ bio_set_op_attrs(bio, op, op_flags);
+ submit_bio(bio);
+}
+
+static struct bio *prepare_bio(struct super_block *sb,
+ erofs_blk_t blkaddr, unsigned nr_pages)
+{
+ struct bio *bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, nr_pages);
+
+ BUG_ON(bio == NULL);
+
+ bio->bi_end_io = read_endio;
+ bio_set_dev(bio, sb->s_bdev);
+ bio->bi_iter.bi_sector = blkaddr << LOG_SECTORS_PER_BLOCK;
+
+ return bio;
+}
+
+/* prio -- true is used for dir */
+struct page *erofs_get_meta_page(struct super_block *sb,
+ erofs_blk_t blkaddr, bool prio)
+{
+ struct inode *bd_inode = sb->s_bdev->bd_inode;
+ struct address_space *mapping = bd_inode->i_mapping;
+ struct page *page;
+
+repeat:
+ page = find_or_create_page(mapping, blkaddr,
+ /*
+ * Prefer looping in the allocator rather than here,
+ * at least that code knows what it's doing.
+ */
+ mapping_gfp_constraint(mapping, ~__GFP_FS) | __GFP_NOFAIL);
+
+ BUG_ON(!page || !PageLocked(page));
+
+ if (!PageUptodate(page)) {
+ struct bio *bio;
+ int err;
+
+ bio = prepare_bio(sb, blkaddr, 1);
+ err = bio_add_page(bio, page, PAGE_SIZE, 0);
+ BUG_ON(err != PAGE_SIZE);
+
+ __submit_bio(bio, REQ_OP_READ,
+ REQ_META | (prio ? REQ_PRIO : 0));
+
+ lock_page(page);
+
+ /* the page has been truncated by others? */
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ put_page(page);
+ goto repeat;
+ }
+
+ /* more likely a read error */
+ if (unlikely(!PageUptodate(page))) {
+ unlock_page(page);
+ put_page(page);
+
+ page = ERR_PTR(-EIO);
+ }
+ }
+ return page;
+}
+
+static int erofs_map_blocks_flatmode(struct inode *inode,
+ struct erofs_map_blocks *map,
+ int flags)
+{
+ erofs_blk_t nblocks, lastblk;
+ u64 offset = map->m_la;
+ struct erofs_vnode *vi = EROFS_V(inode);
+
+ BUG_ON(is_inode_layout_compression(inode));
+
+ nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+ lastblk = nblocks - is_inode_layout_inline(inode);
+
+ if (unlikely(offset >= inode->i_size)) {
+ /* leave out-of-bound access unmapped */
+ map->m_flags = 0;
+ map->m_plen = 0;
+ goto out;
+ }
+
+ /* there is no hole in flatmode */
+ map->m_flags = EROFS_MAP_MAPPED;
+
+ if (offset < blknr_to_addr(lastblk)) {
+ map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
+ map->m_plen = blknr_to_addr(lastblk) - offset;
+ } else if (is_inode_layout_inline(inode)) {
+ /* 2 - inode inline B: inode, [xattrs], inline last blk... */
+ struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
+
+ map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize +
+ vi->xattr_isize + erofs_blkoff(map->m_la);
+ map->m_plen = inode->i_size - offset;
+
+ /* inline data should locate in one meta block */
+ BUG_ON(erofs_blkoff(map->m_pa) + map->m_plen > PAGE_SIZE);
+ map->m_flags |= EROFS_MAP_META;
+ } else {
+ errln("internal error @ nid: %llu (size %llu), m_la 0x%llx",
+ vi->nid, inode->i_size, map->m_la);
+ BUG();
+ }
+
+out:
+ map->m_llen = map->m_plen;
+ debugln("%s, m_la 0x%llx m_pa %llx m_len %llu",
+ __func__, map->m_la, map->m_pa, map->m_plen);
+ return 0;
+}
+
+int erofs_map_blocks(struct inode *inode,
+ struct erofs_map_blocks *map, int flags)
+{
+ if (unlikely(is_inode_layout_compression(inode)))
+ return -ENOTSUPP;
+
+ return erofs_map_blocks_flatmode(inode, map, flags);
+}
+
+static inline struct bio *erofs_read_raw_page(
+ struct bio *bio,
+ struct address_space *mapping,
+ struct page *page,
+ erofs_off_t *last_block,
+ unsigned nblocks,
+ bool ra)
+{
+ struct inode *inode = mapping->host;
+ erofs_off_t current_block = (erofs_off_t)page->index;
+ int err;
+
+ BUG_ON(!nblocks);
+
+ if (PageUptodate(page)) {
+ err = 0;
+ goto has_updated;
+ }
+
+ if (cleancache_get_page(page) == 0) {
+ err = 0;
+ SetPageUptodate(page);
+ goto has_updated;
+ }
+
+ /* note that for readpage case, bio also equals to NULL */
+ if (bio != NULL &&
+ /* not continuous */
+ *last_block + 1 != current_block) {
+submit_bio_retry:
+ __submit_bio(bio, REQ_OP_READ, 0);
+ bio = NULL;
+ }
+
+ if (bio == NULL) {
+ struct erofs_map_blocks map = {
+ .m_la = blknr_to_addr(current_block),
+ };
+
+ err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+ if (unlikely(err))
+ goto err_out;
+
+ /* zero out the holed page */
+ if (unlikely(!(map.m_flags & EROFS_MAP_MAPPED))) {
+ zero_user_segment(page, 0, PAGE_SIZE);
+ SetPageUptodate(page);
+
+ /* imply err = 0, see erofs_map_blocks */
+ goto has_updated;
+ }
+
+ /* for RAW access mode, m_plen must be equal to m_llen */
+ BUG_ON(map.m_plen != map.m_llen);
+
+ /* deal with inline page */
+ if (map.m_flags & EROFS_MAP_META) {
+ void *vsrc, *vto;
+ struct page *ipage;
+
+ BUG_ON(map.m_plen > PAGE_SIZE);
+
+ ipage = erofs_get_meta_page(inode->i_sb,
+ erofs_blknr(map.m_pa), 0);
+
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto err_out;
+ }
+
+ vsrc = kmap_atomic(ipage);
+ vto = kmap_atomic(page);
+ memcpy(vto, vsrc + erofs_blkoff(map.m_pa), map.m_plen);
+ memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen);
+ kunmap_atomic(vto);
+ kunmap_atomic(vsrc);
+ flush_dcache_page(page);
+
+ SetPageUptodate(page);
+ /* TODO: could we unlock the page earlier? */
+ unlock_page(ipage);
+ put_page(ipage);
+
+ /* imply err = 0, see erofs_map_blocks */
+ goto has_updated;
+ }
+
+ /* pa must be block-aligned for raw reading */
+ BUG_ON(erofs_blkoff(map.m_pa) != 0);
+
+ /* max # of continuous pages */
+ if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
+ nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
+ if (nblocks > BIO_MAX_PAGES)
+ nblocks = BIO_MAX_PAGES;
+
+ bio = prepare_bio(inode->i_sb, erofs_blknr(map.m_pa), nblocks);
+ }
+
+ err = bio_add_page(bio, page, PAGE_SIZE, 0);
+ /* out of the extent or bio is full */
+ if (err < PAGE_SIZE)
+ goto submit_bio_retry;
+
+ *last_block = current_block;
+
+ /* shift in advance in case of it followed by too many gaps */
+ if (unlikely(bio->bi_vcnt >= bio->bi_max_vecs)) {
+ /* err should reassign to 0 after submitting */
+ err = 0;
+ goto submit_bio_out;
+ }
+
+ return bio;
+
+err_out:
+ /* for sync reading, set page error immediately */
+ if (!ra) {
+ SetPageError(page);
+ ClearPageUptodate(page);
+ }
+has_updated:
+ unlock_page(page);
+
+ /* if updated manually, continuous pages has a gap */
+ if (bio != NULL)
+submit_bio_out:
+ __submit_bio(bio, REQ_OP_READ, 0);
+
+ return unlikely(err) ? ERR_PTR(err) : NULL;
+}
+
+/*
+ * since we dont have write or truncate flows, so no inode
+ * locking needs to be held at the moment.
+ */
+static int erofs_raw_access_readpage(struct file *file, struct page *page)
+{
+ erofs_off_t last_block;
+ struct bio *bio;
+
+ bio = erofs_read_raw_page(NULL, page->mapping,
+ page, &last_block, 1, false);
+
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ BUG_ON(bio != NULL); /* since we have only one bio -- must be NULL */
+ return 0;
+}
+
+static int erofs_raw_access_readpages(struct file *filp,
+ struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ erofs_off_t last_block;
+ struct bio *bio = NULL;
+ gfp_t gfp = readahead_gfp_mask(mapping);
+
+ for (; nr_pages; --nr_pages) {
+ struct page *page = list_entry(pages->prev, struct page, lru);
+
+ prefetchw(&page->flags);
+ list_del(&page->lru);
+
+ if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) {
+ bio = erofs_read_raw_page(bio, mapping, page,
+ &last_block, nr_pages, true);
+
+ /* all the page errors are ignored when readahead */
+ if (IS_ERR(bio)) {
+ pr_err("%s, readahead error at page %lu of nid %llu\n",
+ __func__, page->index,
+ EROFS_V(mapping->host)->nid);
+
+ bio = NULL;
+ }
+ }
+
+ /* pages could still be locked */
+ put_page(page);
+ }
+ BUG_ON(!list_empty(pages));
+
+ /* the rare case (end in gaps) */
+ if (unlikely(bio != NULL))
+ __submit_bio(bio, REQ_OP_READ, 0);
+ return 0;
+}
+
+/* for uncompressed (aligned) files and raw access for other files */
+const struct address_space_operations erofs_raw_access_aops = {
+ .readpage = erofs_raw_access_readpage,
+ .readpages = erofs_raw_access_readpages,
+};
+
--
1.9.1
next prev parent reply other threads:[~2018-07-26 12:24 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-31 11:06 [NOMERGE] [RFC PATCH 00/12] erofs: introduce erofs file system Gao Xiang
2018-06-01 7:48 ` Richard Weinberger
2018-06-01 9:11 ` Gao Xiang
2018-06-01 9:28 ` Richard Weinberger
2018-06-01 11:16 ` Gao Xiang
2018-06-07 10:26 ` Pavel Machek
2018-07-27 0:55 ` Joey Pabalinas
2018-07-27 0:57 ` Joey Pabalinas
2018-07-26 12:21 ` [PATCH 00/25] staging: " Gao Xiang
2018-07-26 12:21 ` [PATCH 01/25] staging: erofs: add on-disk layout Gao Xiang
2018-07-26 12:21 ` [PATCH 02/25] staging: erofs: add erofs in-memory stuffs Gao Xiang
2018-07-26 12:21 ` [PATCH 03/25] staging: erofs: add super block operations Gao Xiang
2018-07-26 12:21 ` Gao Xiang [this message]
2018-07-26 12:21 ` [PATCH 05/25] staging: erofs: add inode operations Gao Xiang
2018-07-26 12:21 ` [PATCH 06/25] staging: erofs: add directory operations Gao Xiang
2018-07-26 12:21 ` [PATCH 07/25] staging: erofs: add namei functions Gao Xiang
2018-07-26 12:21 ` [PATCH 08/25] staging: erofs: update Kconfig and Makefile Gao Xiang
2018-07-26 12:21 ` [PATCH 09/25] staging: erofs: introduce xattr & acl support Gao Xiang
2018-07-26 12:21 ` [PATCH 10/25] staging: erofs: support special inode Gao Xiang
2018-07-26 12:21 ` [PATCH 11/25] staging: erofs: introduce error injection infrastructure Gao Xiang
2018-07-26 12:21 ` [PATCH 12/25] staging: erofs: support tracepoint Gao Xiang
2018-07-26 12:21 ` [PATCH 13/25] staging: erofs: <linux/tagptr.h>: introduce tagged pointer Gao Xiang
2018-07-26 12:21 ` [PATCH 14/25] staging: erofs: introduce pagevec for unzip subsystem Gao Xiang
2018-07-26 12:21 ` [PATCH 15/25] staging: erofs: add erofs_map_blocks_iter Gao Xiang
2018-07-26 12:21 ` [PATCH 16/25] staging: erofs: add erofs_allocpage Gao Xiang
2018-07-26 12:22 ` [PATCH 17/25] staging: erofs: globalize prepare_bio and __submit_bio Gao Xiang
2018-07-26 12:22 ` [PATCH 18/25] staging: erofs: introduce a customized LZ4 decompression Gao Xiang
2018-07-26 12:22 ` [PATCH 19/25] staging: erofs: add a generic z_erofs VLE decompressor Gao Xiang
2018-07-26 12:22 ` [PATCH 20/25] staging: erofs: introduce superblock registration Gao Xiang
2018-07-26 12:22 ` [PATCH 21/25] staging: erofs: introduce erofs shrinker Gao Xiang
2018-07-26 12:22 ` [PATCH 22/25] staging: erofs: introduce workstation for decompression Gao Xiang
2018-07-26 12:22 ` [PATCH 23/25] staging: erofs: introduce VLE decompression support Gao Xiang
2018-07-26 12:22 ` [PATCH 24/25] staging: erofs: introduce cached decompression Gao Xiang
2018-07-26 12:22 ` [PATCH 25/25] staging: erofs: add a TODO and update MAINTAINERS for staging Gao Xiang
2018-07-28 7:10 ` [PATCH] staging: erofs: fix a compile warning of Z_EROFS_VLE_VMAP_ONSTACK_PAGES Gao Xiang
2018-07-28 10:43 ` Chao Yu
2018-07-29 5:34 ` [PATCH 1/2] staging: erofs: fix compile error without built-in decompression support Gao Xiang
2018-07-29 5:37 ` [PATCH 2/2] staging: erofs: fix conditional uninitialized `pcn' in z_erofs_map_blocks_iter Gao Xiang
2018-07-30 1:51 ` [PATCH] staging: erofs: use the wrapped PTR_ERR_OR_ZERO instead of open code Gao Xiang
2018-07-30 6:58 ` Chao Yu
2018-08-01 6:38 ` [PATCH 1/2] staging: erofs: add the missing break in z_erofs_map_blocks_iter Gao Xiang
2018-08-01 6:38 ` [PATCH 2/2] staging: erofs: remove a redundant marco in xattr Gao Xiang
2018-08-01 9:02 ` [PATCH 1/2] staging: erofs: add the missing break in z_erofs_map_blocks_iter Dan Carpenter
2018-08-01 9:19 ` Gao Xiang
2018-08-01 9:36 ` [PATCH RESEND " Gao Xiang
2018-08-01 11:36 ` Dan Carpenter
2018-08-01 12:08 ` Gao Xiang
2018-07-30 2:07 ` [PATCH 2/2] staging: erofs: fix conditional uninitialized `pcn' " Chao Yu
2018-07-30 2:07 ` [PATCH 1/2] staging: erofs: fix compile error without built-in decompression support Chao Yu
2018-07-30 2:32 ` Gao Xiang
2018-07-30 3:07 ` Chao Yu
2018-07-30 3:55 ` Gao Xiang
2018-07-27 0:25 ` [PATCH 00/25] staging: erofs: introduce erofs file system Christian Kujau
2018-07-27 1:39 ` Gao Xiang
2018-07-27 1:56 ` Gao Xiang
2018-07-28 7:25 ` Greg Kroah-Hartman
2018-07-28 9:33 ` Gao Xiang
2018-07-28 10:34 ` Chao Yu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1532607728-103372-5-git-send-email-gaoxiang25@huawei.com \
--to=gaoxiang25@huawei.com \
--cc=chao@kernel.org \
--cc=devel@driverdev.osuosl.org \
--cc=gregkh@linuxfoundation.org \
--cc=hsiangkao@aol.com \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miaoxie@huawei.com \
--cc=weidu.du@huawei.com \
--cc=yuchao0@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).