From: David Howells <dhowells@redhat.com>
To: Trond Myklebust <trondmy@hammerspace.com>,
Anna Schumaker <anna.schumaker@netapp.com>,
Steve French <sfrench@samba.org>,
Dominique Martinet <asmadeus@codewreck.org>
Cc: Jeff Layton <jlayton@kernel.org>,
ceph-devel@vger.kernel.org, linux-cachefs@redhat.com,
linux-fsdevel@vger.kernel.org, dhowells@redhat.com,
Jeff Layton <jlayton@redhat.com>,
David Wysochanski <dwysocha@redhat.com>,
"Matthew Wilcox (Oracle)" <willy@infradead.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-cachefs@redhat.com, linux-afs@lists.infradead.org,
linux-nfs@vger.kernel.org, linux-cifs@vger.kernel.org,
ceph-devel@vger.kernel.org, v9fs-developer@lists.sourceforge.net,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH 33/33] ceph: convert ceph_readpages to ceph_readahead
Date: Mon, 15 Feb 2021 15:51:01 +0000 [thread overview]
Message-ID: <161340426195.1303470.14717135788428630282.stgit@warthog.procyon.org.uk> (raw)
In-Reply-To: <161340385320.1303470.2392622971006879777.stgit@warthog.procyon.org.uk>
From: Jeff Layton <jlayton@kernel.org>
Convert ceph_readpages to ceph_readahead and make it use
netfs_readahead. With this we can rip out a lot of the old
readpage/readpages infrastructure.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: ceph-devel@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
---
fs/ceph/addr.c | 229 ++++++++------------------------------------------------
1 file changed, 34 insertions(+), 195 deletions(-)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18f660611ba1..0dd64d31eff6 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -322,214 +322,53 @@ static int ceph_readpage(struct file *file, struct page *page)
return netfs_readpage(file, page, &ceph_readpage_netfs_ops, NULL);
}
-/*
- * Finish an async read(ahead) op.
- */
-static void finish_read(struct ceph_osd_request *req)
+static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
{
- struct inode *inode = req->r_inode;
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_osd_data *osd_data;
- int rc = req->r_result <= 0 ? req->r_result : 0;
- int bytes = req->r_result >= 0 ? req->r_result : 0;
- int num_pages;
- int i;
-
- dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
- if (rc == -EBLOCKLISTED)
- ceph_inode_to_client(inode)->blocklisted = true;
-
- /* unlock all pages, zeroing any data we didn't read */
- osd_data = osd_req_op_extent_osd_data(req, 0);
- BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
- num_pages = calc_pages_for((u64)osd_data->alignment,
- (u64)osd_data->length);
- for (i = 0; i < num_pages; i++) {
- struct page *page = osd_data->pages[i];
-
- if (rc < 0 && rc != -ENOENT)
- goto unlock;
- if (bytes < (int)PAGE_SIZE) {
- /* zero (remainder of) page */
- int s = bytes < 0 ? 0 : bytes;
- zero_user_segment(page, s, PAGE_SIZE);
- }
- dout("finish_read %p uptodate %p idx %lu\n", inode, page,
- page->index);
- flush_dcache_page(page);
- SetPageUptodate(page);
-unlock:
- unlock_page(page);
- put_page(page);
- bytes -= PAGE_SIZE;
- }
-
- ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
- req->r_end_latency, rc);
-
- kfree(osd_data->pages);
-}
-
-/*
- * start an async read(ahead) operation. return nr_pages we submitted
- * a read for on success, or negative error code.
- */
-static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx,
- struct list_head *page_list, int max)
-{
- struct ceph_osd_client *osdc =
- &ceph_inode_to_client(inode)->client->osdc;
+ struct inode *inode = mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct page *page = lru_to_page(page_list);
- struct ceph_vino vino;
- struct ceph_osd_request *req;
- u64 off;
- u64 len;
- int i;
- struct page **pages;
- pgoff_t next_index;
- int nr_pages = 0;
- int got = 0;
- int ret = 0;
-
- if (!rw_ctx) {
- /* caller of readpages does not hold buffer and read caps
- * (fadvise, madvise and readahead cases) */
- int want = CEPH_CAP_FILE_CACHE;
- ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want,
- true, &got);
- if (ret < 0) {
- dout("start_read %p, error getting cap\n", inode);
- } else if (!(got & want)) {
- dout("start_read %p, no cache cap\n", inode);
- ret = 0;
- }
- if (ret <= 0) {
- if (got)
- ceph_put_cap_refs(ci, got);
- while (!list_empty(page_list)) {
- page = lru_to_page(page_list);
- list_del(&page->lru);
- put_page(page);
- }
- return ret;
- }
- }
-
- off = (u64) page_offset(page);
-
- /* count pages */
- next_index = page->index;
- list_for_each_entry_reverse(page, page_list, lru) {
- if (page->index != next_index)
- break;
- nr_pages++;
- next_index++;
- if (max && nr_pages == max)
- break;
- }
- len = nr_pages << PAGE_SHIFT;
- dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
- off, len);
- vino = ceph_vino(inode);
- req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
- 0, 1, CEPH_OSD_OP_READ,
- CEPH_OSD_FLAG_READ, NULL,
- ci->i_truncate_seq, ci->i_truncate_size,
- false);
- if (IS_ERR(req)) {
- ret = PTR_ERR(req);
- goto out;
- }
-
- /* build page vector */
- nr_pages = calc_pages_for(0, len);
- pages = kmalloc_array(nr_pages, sizeof(*pages), GFP_KERNEL);
- if (!pages) {
- ret = -ENOMEM;
- goto out_put;
- }
- for (i = 0; i < nr_pages; ++i) {
- page = list_entry(page_list->prev, struct page, lru);
- BUG_ON(PageLocked(page));
- list_del(&page->lru);
-
- dout("start_read %p adding %p idx %lu\n", inode, page,
- page->index);
- if (add_to_page_cache_lru(page, &inode->i_data, page->index,
- GFP_KERNEL)) {
- put_page(page);
- dout("start_read %p add_to_page_cache failed %p\n",
- inode, page);
- nr_pages = i;
- if (nr_pages > 0) {
- len = nr_pages << PAGE_SHIFT;
- osd_req_op_extent_update(req, 0, len);
- break;
- }
- goto out_pages;
- }
- pages[i] = page;
- }
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
- req->r_callback = finish_read;
- req->r_inode = inode;
-
- dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
- ret = ceph_osdc_start_request(osdc, req, false);
- if (ret < 0)
- goto out_pages;
- ceph_osdc_put_request(req);
+ int got = (int)(uintptr_t)priv;
- /* After adding locked pages to page cache, the inode holds cache cap.
- * So we can drop our cap refs. */
if (got)
ceph_put_cap_refs(ci, got);
-
- return nr_pages;
-
-out_pages:
- for (i = 0; i < nr_pages; ++i)
- unlock_page(pages[i]);
- ceph_put_page_vector(pages, nr_pages, false);
-out_put:
- ceph_osdc_put_request(req);
-out:
- if (got)
- ceph_put_cap_refs(ci, got);
- return ret;
}
+const struct netfs_read_request_ops ceph_readahead_netfs_ops = {
+ .init_rreq = ceph_init_rreq,
+ .is_cache_enabled = ceph_is_cache_enabled,
+ .begin_cache_operation = ceph_begin_cache_operation,
+ .issue_op = ceph_netfs_issue_op,
+ .clamp_length = ceph_netfs_clamp_length,
+ .cleanup = ceph_readahead_cleanup,
+};
-
-/*
- * Read multiple pages. Leave pages we don't read + unlock in page_list;
- * the caller (VM) cleans them up.
- */
-static int ceph_readpages(struct file *file, struct address_space *mapping,
- struct list_head *page_list, unsigned nr_pages)
+static void ceph_readahead(struct readahead_control *ractl)
{
- struct inode *inode = file_inode(file);
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_file_info *fi = file->private_data;
+ struct inode *inode = file_inode(ractl->file);
+ struct ceph_file_info *fi = ractl->file->private_data;
struct ceph_rw_context *rw_ctx;
- int rc = 0;
- int max = 0;
+ int got = 0;
+ int ret = 0;
if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE)
- return -EINVAL;
+ return;
rw_ctx = ceph_find_rw_context(fi);
- max = fsc->mount_options->rsize >> PAGE_SHIFT;
- dout("readpages %p file %p ctx %p nr_pages %d max %d\n",
- inode, file, rw_ctx, nr_pages, max);
- while (!list_empty(page_list)) {
- rc = start_read(inode, rw_ctx, page_list, max);
- if (rc < 0)
- goto out;
+ if (!rw_ctx) {
+ /*
+ * readahead callers do not necessarily hold Fcb caps
+ * (e.g. fadvise, madvise).
+ */
+ int want = CEPH_CAP_FILE_CACHE;
+
+ ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got);
+ if (ret < 0)
+ dout("start_read %p, error getting cap\n", inode);
+ else if (!(got & want))
+ dout("start_read %p, no cache cap\n", inode);
+
+ if (ret <= 0)
+ return;
}
-out:
- dout("readpages %p file %p ret %d\n", inode, file, rc);
- return rc;
+ netfs_readahead(ractl, &ceph_readahead_netfs_ops, (void *)(uintptr_t)got);
}
struct ceph_writeback_ctl
@@ -1482,7 +1321,7 @@ static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter)
const struct address_space_operations ceph_aops = {
.readpage = ceph_readpage,
- .readpages = ceph_readpages,
+ .readahead = ceph_readahead,
.writepage = ceph_writepage,
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
next prev parent reply other threads:[~2021-02-15 15:59 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-15 15:44 [PATCH 00/33] Network fs helper library & fscache kiocb API [ver #3] David Howells
2021-02-15 15:44 ` [PATCH 01/33] iov_iter: Add ITER_XARRAY David Howells
2021-02-15 15:44 ` [PATCH 02/33] mm: Add an unlock function for PG_private_2/PG_fscache David Howells
2021-02-16 10:26 ` Christoph Hellwig
2021-02-15 15:44 ` [PATCH 03/33] mm: Implement readahead_control pageset expansion David Howells
2021-02-16 10:32 ` Christoph Hellwig
2021-02-16 13:22 ` Matthew Wilcox
2021-02-17 14:36 ` Mike Marshall
2021-02-17 15:42 ` David Howells
2021-02-17 16:59 ` Mike Marshall
2021-02-17 22:20 ` David Howells
2021-02-16 11:48 ` David Howells
2021-02-17 16:13 ` Matthew Wilcox
2021-02-17 22:34 ` David Howells
2021-02-17 22:49 ` Matthew Wilcox
2021-02-18 17:47 ` David Howells
2021-02-15 15:45 ` [PATCH 04/33] vfs: Export rw_verify_area() for use by cachefiles David Howells
2021-02-16 10:26 ` Christoph Hellwig
2021-02-16 11:55 ` David Howells
2021-02-15 15:45 ` [PATCH 05/33] netfs: Make a netfs helper module David Howells
2021-02-15 15:45 ` [PATCH 06/33] netfs, mm: Move PG_fscache helper funcs to linux/netfs.h David Howells
2021-02-15 15:45 ` [PATCH 07/33] netfs, mm: Add unlock_page_fscache() and wait_on_page_fscache() David Howells
2021-02-15 15:45 ` [PATCH 08/33] netfs: Provide readahead and readpage netfs helpers David Howells
2021-02-15 15:45 ` [PATCH 09/33] netfs: Add tracepoints David Howells
2021-02-15 15:46 ` [PATCH 10/33] netfs: Gather stats David Howells
2021-02-15 15:46 ` [PATCH 11/33] netfs: Add write_begin helper David Howells
2021-02-15 15:46 ` [PATCH 12/33] netfs: Define an interface to talk to a cache David Howells
2021-02-15 15:46 ` [PATCH 13/33] netfs: Hold a ref on a page when PG_private_2 is set David Howells
2021-02-15 15:47 ` [PATCH 14/33] fscache, cachefiles: Add alternate API to use kiocb for read/write to cache David Howells
2021-02-16 10:49 ` Christoph Hellwig
2021-02-16 15:08 ` David Howells
2021-02-15 15:47 ` [PATCH 15/33] afs: Disable use of the fscache I/O routines David Howells
2021-02-15 15:47 ` [PATCH 16/33] afs: Pass page into dirty region helpers to provide THP size David Howells
2021-02-15 15:47 ` [PATCH 17/33] afs: Print the operation debug_id when logging an unexpected data version David Howells
2021-02-15 15:47 ` [PATCH 18/33] afs: Move key to afs_read struct David Howells
2021-02-15 15:47 ` [PATCH 19/33] afs: Don't truncate iter during data fetch David Howells
2021-02-15 15:48 ` [PATCH 20/33] afs: Log remote unmarshalling errors David Howells
2021-02-15 15:48 ` [PATCH 21/33] afs: Set up the iov_iter before calling afs_extract_data() David Howells
2021-02-15 15:48 ` [PATCH 22/33] afs: Use ITER_XARRAY for writing David Howells
2021-02-15 15:48 ` [PATCH 23/33] afs: Wait on PG_fscache before modifying/releasing a page David Howells
2021-02-15 15:49 ` [PATCH 24/33] afs: Extract writeback extension into its own function David Howells
2021-02-15 15:49 ` [PATCH 25/33] afs: Prepare for use of THPs David Howells
2021-02-15 15:49 ` [PATCH 26/33] afs: Use the fs operation ops to handle FetchData completion David Howells
2021-02-15 15:49 ` [PATCH 27/33] afs: Use new fscache read helper API David Howells
2021-02-15 15:49 ` [PATCH 28/33] ceph: disable old fscache readpage handling David Howells
2021-02-15 15:50 ` [PATCH 29/33] ceph: rework PageFsCache handling David Howells
2021-02-15 15:50 ` [PATCH 30/33] ceph: fix fscache invalidation David Howells
2021-02-15 15:50 ` [PATCH 31/33] ceph: convert readpage to fscache read helper David Howells
2021-02-15 15:50 ` [PATCH 32/33] ceph: plug write_begin into " David Howells
2021-02-15 15:51 ` David Howells [this message]
2021-02-15 18:05 ` [PATCH 00/33] Network fs helper library & fscache kiocb API [ver #3] Jeff Layton
2021-02-16 0:40 ` Steve French
2021-02-16 2:10 ` Matthew Wilcox
2021-02-16 5:18 ` Steve French
2021-02-16 5:22 ` Steve French
2021-02-23 20:27 ` Matthew Wilcox
2021-02-24 4:57 ` Steve French
2021-02-24 13:32 ` David Howells
2021-02-24 15:51 ` Matthew Wilcox
2021-02-16 11:01 ` Jeff Layton
2021-02-15 22:46 ` [PATCH 34/33] netfs: Use in_interrupt() not in_softirq() David Howells
2021-02-16 8:42 ` Christoph Hellwig
2021-02-16 9:06 ` Sebastian Andrzej Siewior
2021-02-16 9:29 ` David Howells
2021-02-16 9:30 ` Christoph Hellwig
2021-02-18 14:02 ` [PATCH 34/33] netfs: Pass flag rather than use in_softirq() David Howells
2021-02-18 15:06 ` Marc Dionne
2021-02-18 15:16 ` Marc Dionne
2021-02-19 9:01 ` Sebastian Andrzej Siewior
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=161340426195.1303470.14717135788428630282.stgit@warthog.procyon.org.uk \
--to=dhowells@redhat.com \
--cc=anna.schumaker@netapp.com \
--cc=asmadeus@codewreck.org \
--cc=ceph-devel@vger.kernel.org \
--cc=dwysocha@redhat.com \
--cc=jlayton@kernel.org \
--cc=jlayton@redhat.com \
--cc=linux-afs@lists.infradead.org \
--cc=linux-cachefs@redhat.com \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=sfrench@samba.org \
--cc=trondmy@hammerspace.com \
--cc=v9fs-developer@lists.sourceforge.net \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/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).