Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   David Howells <dhowells@redhat.com>
To:     Jeff Layton <jlayton@kernel.org>, Steve French <smfrench@gmail.com>
Cc:     David Howells <dhowells@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Marc Dionne <marc.dionne@auristor.com>,
        Paulo Alcantara <pc@manguebit.com>,
        Shyam Prasad N <sprasad@microsoft.com>,
        Tom Talpey <tom@talpey.com>,
        Dominique Martinet <asmadeus@codewreck.org>,
        Ilya Dryomov <idryomov@gmail.com>,
        Christian Brauner <christian@brauner.io>,
        linux-afs@lists.infradead.org, linux-cifs@vger.kernel.org,
        linux-nfs@vger.kernel.org, ceph-devel@vger.kernel.org,
        v9fs@lists.linux.dev, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-cachefs@redhat.com
Subject: [RFC PATCH 30/53] netfs: Allow buffered shared-writeable mmap through netfs_page_mkwrite()
Date:   Fri, 13 Oct 2023 17:03:59 +0100
Message-ID: <20231013160423.2218093-31-dhowells@redhat.com>
In-Reply-To: <20231013160423.2218093-1-dhowells@redhat.com>
References: <20231013160423.2218093-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Provide an entry point to delegate a filesystem's ->page_mkwrite() to.
This checks for conflicting writes, then attached any netfs-specific group
marking (e.g. ceph snap) to the page to be considered dirty.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 59 +++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |  4 +++
 2 files changed, 63 insertions(+)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 60e7da53cbd2..3c1f26f32351 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -413,3 +413,62 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 EXPORT_SYMBOL(netfs_file_write_iter);
+
+/*
+ * Notification that a previously read-only page is about to become writable.
+ * Note that the caller indicates a single page of a multipage folio.
+ */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
+{
+	struct folio *folio = page_folio(vmf->page);
+	struct file *file = vmf->vma->vm_file;
+	struct inode *inode = file_inode(file);
+	vm_fault_t ret = VM_FAULT_RETRY;
+	int err;
+
+	_enter("%lx", folio->index);
+
+	sb_start_pagefault(inode->i_sb);
+
+	if (folio_wait_writeback_killable(folio))
+		goto out;
+
+	if (folio_lock_killable(folio) < 0)
+		goto out;
+
+	/* Can we see a streaming write here? */
+	if (WARN_ON(!folio_test_uptodate(folio))) {
+		ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
+		goto out;
+	}
+
+	if (netfs_folio_group(folio) != netfs_group) {
+		folio_unlock(folio);
+		err = filemap_fdatawait_range(inode->i_mapping,
+					      folio_pos(folio),
+					      folio_pos(folio) + folio_size(folio));
+		switch (err) {
+		case 0:
+			ret = VM_FAULT_RETRY;
+			goto out;
+		case -ENOMEM:
+			ret = VM_FAULT_OOM;
+			goto out;
+		default:
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+	}
+
+	if (folio_test_dirty(folio))
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus);
+	else
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite);
+	netfs_set_group(folio, netfs_group);
+	file_update_time(file);
+	ret = VM_FAULT_LOCKED;
+out:
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_page_mkwrite);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d1dc7ba62f17..e2a5a441b7fc 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -403,6 +403,10 @@ int netfs_write_begin(struct netfs_inode *, struct file *,
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp);
 
+/* VMA operations API. */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
+
+/* (Sub)request management API. */
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);