Received-SPF: pass (google.com: domain of linux-kernel+bounces-78901-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Sender: John Groves <grovesaustin@gmail.com>
From: John Groves <John@Groves.net>
To: John Groves <jgroves@micron.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Dan Williams <dan.j.williams@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Dave Jiang <dave.jiang@intel.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>,
	Jan Kara <jack@suse.cz>,
	Matthew Wilcox <willy@infradead.org>,
	linux-cxl@vger.kernel.org,
	linux-fsdevel@vger.kernel.org,
	linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	nvdimm@lists.linux.dev
Cc: John@Groves.net,
	john@jagalactic.com,
	Dave Chinner <david@fromorbit.com>,
	Christoph Hellwig <hch@infradead.org>,
	dave.hansen@linux.intel.com,
	gregory.price@memverge.com,
	John Groves <john@groves.net>
Subject: [RFC PATCH 14/20] famfs: Add struct file_operations
Date: Fri, 23 Feb 2024 11:41:58 -0600
Message-Id: <3f19cd8daab0dc3c4d0381019ce61cd106970097.1708709155.git.john@groves.net>
In-Reply-To: <cover.1708709155.git.john@groves.net>
References: <cover.1708709155.git.john@groves.net>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

This commit introduces the famfs file_operations. We call
thp_get_unmapped_area() to force PMD page alignment. Our read and
write handlers (famfs_dax_read_iter() and famfs_dax_write_iter())
call dax_iomap_rw() to do the work.

famfs_file_invalid() checks for various ways a famfs file can be
in an invalid state so we can fail I/O or fault resolution in those
cases. Those cases include the following:

* No famfs metadata
* file i_size does not match the originally allocated size
* file is not flagged as DAX
* errors were detected previously on the file

An invalid file can often be fixed by replaying the log, or by
umount/mount/log replay - all of which are user space operations.

Signed-off-by: John Groves <john@groves.net>
---
 fs/famfs/famfs_file.c | 136 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 136 insertions(+)

diff --git a/fs/famfs/famfs_file.c b/fs/famfs/famfs_file.c
index fc667d5f7be8..5228e9de1e3b 100644
--- a/fs/famfs/famfs_file.c
+++ b/fs/famfs/famfs_file.c
@@ -19,6 +19,142 @@
 #include <uapi/linux/famfs_ioctl.h>
 #include "famfs_internal.h"
 
+/*********************************************************************
+ * file_operations
+ */
+
+/* Reject I/O to files that aren't in a valid state */
+static ssize_t
+famfs_file_invalid(struct inode *inode)
+{
+	size_t i_size       = i_size_read(inode);
+	struct famfs_file_meta *meta = inode->i_private;
+
+	if (!meta) {
+		pr_err("%s: un-initialized famfs file\n", __func__);
+		return -EIO;
+	}
+	if (i_size != meta->file_size) {
+		pr_err("%s: something changed the size from  %ld to %ld\n",
+		       __func__, meta->file_size, i_size);
+		meta->error = 1;
+		return -ENXIO;
+	}
+	if (!IS_DAX(inode)) {
+		pr_err("%s: inode %llx IS_DAX is false\n", __func__, (u64)inode);
+		meta->error = 1;
+		return -ENXIO;
+	}
+	if (meta->error) {
+		pr_err("%s: previously detected metadata errors\n", __func__);
+		meta->error = 1;
+		return -EIO;
+	}
+	return 0;
+}
+
+static ssize_t
+famfs_dax_read_iter(
+	struct kiocb		*iocb,
+	struct iov_iter		*to)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	size_t i_size       = i_size_read(inode);
+	size_t count        = iov_iter_count(to);
+	size_t max_count;
+	ssize_t rc;
+
+	rc = famfs_file_invalid(inode);
+	if (rc)
+		return rc;
+
+	max_count = max_t(size_t, 0, i_size - iocb->ki_pos);
+
+	if (count > max_count)
+		iov_iter_truncate(to, max_count);
+
+	if (!iov_iter_count(to))
+		return 0;
+
+	rc = dax_iomap_rw(iocb, to, &famfs_iomap_ops);
+
+	file_accessed(iocb->ki_filp);
+	return rc;
+}
+
+/**
+ * famfs_write_iter()
+ *
+ * We need our own write-iter in order to prevent append
+ */
+static ssize_t
+famfs_dax_write_iter(
+	struct kiocb    *iocb,
+	struct iov_iter *from)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	size_t i_size       = i_size_read(inode);
+	size_t count        = iov_iter_count(from);
+	size_t max_count;
+	ssize_t rc;
+
+	rc = famfs_file_invalid(inode);
+	if (rc)
+		return rc;
+
+	/* Starting offset of write is: iocb->ki_pos
+	 * length is iov_iter_count(from)
+	 */
+	max_count = max_t(size_t, 0, i_size - iocb->ki_pos);
+
+	/* If write would go past EOF, truncate it to end at EOF since famfs does not
+	 * alloc-on-write
+	 */
+	if (count > max_count)
+		iov_iter_truncate(from, max_count);
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	return dax_iomap_rw(iocb, from, &famfs_iomap_ops);
+}
+
+static int
+famfs_file_mmap(
+	struct file		*file,
+	struct vm_area_struct	*vma)
+{
+	struct inode		*inode = file_inode(file);
+	ssize_t rc;
+
+	rc = famfs_file_invalid(inode);
+	if (rc)
+		return (int)rc;
+
+	file_accessed(file);
+	vma->vm_ops = &famfs_file_vm_ops;
+	vm_flags_set(vma, VM_HUGEPAGE);
+	return 0;
+}
+
+const struct file_operations famfs_file_operations = {
+	.owner             = THIS_MODULE,
+
+	/* Custom famfs operations */
+	.write_iter	   = famfs_dax_write_iter,
+	.read_iter	   = famfs_dax_read_iter,
+	.mmap		   = famfs_file_mmap,
+
+	/* Force PMD alignment for mmap */
+	.get_unmapped_area = thp_get_unmapped_area,
+
+	/* Generic Operations */
+	.fsync		   = noop_fsync,
+	.splice_read	   = filemap_splice_read,
+	.splice_write	   = iter_file_splice_write,
+	.llseek		   = generic_file_llseek,
+};
+
 /*********************************************************************
  * iomap_operations
  *
-- 
2.43.0