All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: ceph-devel@vger.kernel.org
Cc: dhowells@redhat.com, jlayton@kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 1/3] ceph: Uninline the data on a file opened for writing
Date: Mon, 17 Jan 2022 12:44:33 +0000	[thread overview]
Message-ID: <164242347319.2763588.2514920080375140879.stgit@warthog.procyon.org.uk> (raw)

If a ceph file is made up of inline data, uninline that in the ceph_open()
rather than in ceph_page_mkwrite(), ceph_write_iter(), ceph_fallocate() or
ceph_write_begin().

This makes it easier to convert to using the netfs library for VM write
hooks.

Changes
=======
ver #2:
 - Removed the uninline-handling code from ceph_write_begin() also.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: ceph-devel@vger.kernel.org
---

 fs/ceph/addr.c  |   97 +++++++++++++------------------------------------------
 fs/ceph/file.c  |   28 +++++++++-------
 fs/ceph/super.h |    2 +
 3 files changed, 40 insertions(+), 87 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c98e5238a1b6..ef1caa43b521 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1274,45 +1274,11 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
-	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct folio *folio = NULL;
-	pgoff_t index = pos >> PAGE_SHIFT;
 	int r;
 
-	/*
-	 * Uninlining should have already been done and everything updated, EXCEPT
-	 * for inline_version sent to the MDS.
-	 */
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
-		if (aop_flags & AOP_FLAG_NOFS)
-			fgp_flags |= FGP_NOFS;
-		folio = __filemap_get_folio(mapping, index, fgp_flags,
-					    mapping_gfp_mask(mapping));
-		if (!folio)
-			return -ENOMEM;
-
-		/*
-		 * The inline_version on a new inode is set to 1. If that's the
-		 * case, then the folio is brand new and isn't yet Uptodate.
-		 */
-		r = 0;
-		if (index == 0 && ci->i_inline_version != 1) {
-			if (!folio_test_uptodate(folio)) {
-				WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n",
-					  ci->i_inline_version);
-				r = -EINVAL;
-			}
-			goto out;
-		}
-		zero_user_segment(&folio->page, 0, folio_size(folio));
-		folio_mark_uptodate(folio);
-		goto out;
-	}
-
 	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL,
 			      &ceph_netfs_read_ops, NULL);
-out:
 	if (r == 0)
 		folio_wait_fscache(folio);
 	if (r < 0) {
@@ -1508,19 +1474,6 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	ceph_block_sigs(&oldset);
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		struct page *locked_page = NULL;
-		if (off == 0) {
-			lock_page(page);
-			locked_page = page;
-		}
-		err = ceph_uninline_data(vma->vm_file, locked_page);
-		if (locked_page)
-			unlock_page(locked_page);
-		if (err < 0)
-			goto out_free;
-	}
-
 	if (off + thp_size(page) <= size)
 		len = thp_size(page);
 	else
@@ -1645,13 +1598,14 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 	}
 }
 
-int ceph_uninline_data(struct file *filp, struct page *locked_page)
+int ceph_uninline_data(struct file *file)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_request *req;
-	struct page *page = NULL;
+	struct folio *folio = NULL;
+	struct page *pages[1];
 	u64 len, inline_version;
 	int err = 0;
 	bool from_pagecache = false;
@@ -1667,34 +1621,30 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	    inline_version == CEPH_INLINE_NONE)
 		goto out;
 
-	if (locked_page) {
-		page = locked_page;
-		WARN_ON(!PageUptodate(page));
-	} else if (ceph_caps_issued(ci) &
-		   (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) {
-		page = find_get_page(inode->i_mapping, 0);
-		if (page) {
-			if (PageUptodate(page)) {
+	if (ceph_caps_issued(ci) & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) {
+		folio = filemap_get_folio(inode->i_mapping, 0);
+		if (folio) {
+			if (folio_test_uptodate(folio)) {
 				from_pagecache = true;
-				lock_page(page);
+				folio_lock(folio);
 			} else {
-				put_page(page);
-				page = NULL;
+				folio_put(folio);
+				folio = NULL;
 			}
 		}
 	}
 
-	if (page) {
+	if (folio) {
 		len = i_size_read(inode);
-		if (len > PAGE_SIZE)
-			len = PAGE_SIZE;
+		if (len >  folio_size(folio))
+			len = folio_size(folio);
 	} else {
-		page = __page_cache_alloc(GFP_NOFS);
-		if (!page) {
+		folio = filemap_alloc_folio(GFP_NOFS, 0);
+		if (!folio) {
 			err = -ENOMEM;
 			goto out;
 		}
-		err = __ceph_do_getattr(inode, page,
+		err = __ceph_do_getattr(inode, folio_page(folio, 0),
 					CEPH_STAT_CAP_INLINE_DATA, true);
 		if (err < 0) {
 			/* no inline data */
@@ -1732,7 +1682,8 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 		goto out;
 	}
 
-	osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false);
+	pages[0] = folio_page(folio, 0);
+	osd_req_op_extent_osd_data_pages(req, 1, pages, len, 0, false, false);
 
 	{
 		__le64 xattr_buf = cpu_to_le64(inline_version);
@@ -1769,12 +1720,10 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	if (err == -ECANCELED)
 		err = 0;
 out:
-	if (page && page != locked_page) {
-		if (from_pagecache) {
-			unlock_page(page);
-			put_page(page);
-		} else
-			__free_pages(page, 0);
+	if (folio) {
+		if (from_pagecache)
+			folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 9d9304e712d9..d1d28220f691 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -205,6 +205,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi;
+	int ret;
 
 	dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
 			inode->i_mode, isdir ? "dir" : "regular");
@@ -235,7 +236,22 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 	INIT_LIST_HEAD(&fi->rw_contexts);
 	fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
 
+	if ((file->f_mode & FMODE_WRITE) &&
+	    ci->i_inline_version != CEPH_INLINE_NONE) {
+		ret = ceph_uninline_data(file);
+		if (ret < 0)
+			goto error;
+	}
+
 	return 0;
+
+error:
+	ceph_fscache_unuse_cookie(inode, file->f_mode & FMODE_WRITE);
+	ceph_put_fmode(ci, fi->fmode, 1);
+	kmem_cache_free(ceph_file_cachep, fi);
+	/* wake up anyone waiting for caps on this inode */
+	wake_up_all(&ci->i_cap_wq);
+	return ret;
 }
 
 /*
@@ -1763,12 +1779,6 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err)
 		goto out;
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		err = ceph_uninline_data(file, NULL);
-		if (err < 0)
-			goto out;
-	}
-
 	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
 	     inode, ceph_vinop(inode), pos, count, i_size_read(inode));
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
@@ -2094,12 +2104,6 @@ static long ceph_fallocate(struct file *file, int mode,
 		goto unlock;
 	}
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		ret = ceph_uninline_data(file, NULL);
-		if (ret < 0)
-			goto unlock;
-	}
-
 	size = i_size_read(inode);
 
 	/* Are we punching a hole beyond EOF? */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d0142cc5c41b..f1cec05e4eb8 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1207,7 +1207,7 @@ extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
 /* addr.c */
 extern const struct address_space_operations ceph_aops;
 extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
-extern int ceph_uninline_data(struct file *filp, struct page *locked_page);
+extern int ceph_uninline_data(struct file *file);
 extern int ceph_pool_perm_check(struct inode *inode, int need);
 extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
 int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate);



             reply	other threads:[~2022-01-17 12:44 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-17 12:44 David Howells [this message]
2022-01-17 12:44 ` [PATCH 2/3] ceph: Remove some other inline-setting bits David Howells
2022-01-17 12:44 ` [PATCH 3/3] ceph: Make ceph_netfs_issue_op() handle inlined data (untested) David Howells
2022-01-17 13:47 ` [PATCH 1/3] ceph: Uninline the data on a file opened for writing Matthew Wilcox
2022-01-17 14:11   ` Jeff Layton
2022-01-17 14:27   ` David Howells
2022-01-17 14:30     ` Jeff Layton
2022-01-17 15:24   ` David Howells
2022-01-17 15:45     ` Jeff Layton
2022-01-17 15:57 ` David Howells

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=164242347319.2763588.2514920080375140879.stgit@warthog.procyon.org.uk \
    --to=dhowells@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=jlayton@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --subject='Re: [PATCH 1/3] ceph: Uninline the data on a file opened for writing' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.