On Mon, Aug 03, 2026 at 02:29:07AM +0000, John Groves wrote:
> From: John Groves <[email protected]>
>
> This commit introduces fs/famfs/famfs_file.c and the famfs
> file_operations for read/write.
>
> This is not usable yet because:
>
> * It calls dax_iomap_rw() with NULL iomap_ops (which will be
> introduced in a subsequent commit).
> * famfs_ioctl() is coming in a later commit, and it is necessary
> to map a file to a memory allocation.
>
> Signed-off-by: John Groves <[email protected]>
> ---
> fs/famfs/Makefile | 2 +-
> fs/famfs/famfs_file.c | 138 ++++++++++++++++++++++++++++++++++++++
> fs/famfs/famfs_inode.c | 2 +-
> fs/famfs/famfs_internal.h | 2 +
> 4 files changed, 142 insertions(+), 2 deletions(-)
> create mode 100644 fs/famfs/famfs_file.c
>
> diff --git a/fs/famfs/Makefile b/fs/famfs/Makefile
> index 62230bcd6793..8cac90c090a4 100644
> --- a/fs/famfs/Makefile
> +++ b/fs/famfs/Makefile
> @@ -2,4 +2,4 @@
>
> obj-$(CONFIG_FAMFS) += famfs.o
>
> -famfs-y := famfs_inode.o
> +famfs-y := famfs_inode.o famfs_file.o
> diff --git a/fs/famfs/famfs_file.c b/fs/famfs/famfs_file.c
> new file mode 100644
> index 000000000000..e192b573c51f
> --- /dev/null
> +++ b/fs/famfs/famfs_file.c
> @@ -0,0 +1,138 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * famfs - dax file system for shared fabric-attached memory
> + *
> + * Copyright 2023-2024 Micron Technology, Inc.
> + *
> + * This file system, originally based on ramfs the dax support from xfs,
> + * is intended to allow multiple host systems to mount a common file system
> + * view of dax files that map to shared memory.
> + */
> +
> +#include <linux/fs.h>
> +#include <linux/mm.h>
> +#include <linux/dax.h>
> +#include <linux/iomap.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)
> +{
> + if (!IS_DAX(inode)) {
> + pr_debug("%s: inode %llx IS_DAX is false\n",
> + __func__, (u64)inode);
> + return -ENXIO;
> + }
> + return 0;
> +}
> +
> +static ssize_t
> +famfs_rw_prep(struct kiocb *iocb, struct iov_iter *ubuf)
> +{
> + struct inode *inode = iocb->ki_filp->f_mapping->host;
> + struct super_block *sb = inode->i_sb;
> + struct famfs_fs_info *fsi = sb->s_fs_info;
> + size_t i_size = i_size_read(inode);
> + size_t count = iov_iter_count(ubuf);
> + size_t max_count;
> + ssize_t rc;
> +
> + if (fsi->deverror)
> + return -ENODEV;
> +
> + rc = famfs_file_invalid(inode);
> + if (rc)
> + return rc;
> +
> + /* Avoid unsigned underflow if position is past EOF */
> + if (iocb->ki_pos >= i_size)
> + max_count = 0;
> + else
> + max_count = i_size - iocb->ki_pos;
> +
> + if (count > max_count)
> + iov_iter_truncate(ubuf, max_count);
> +
> + if (!iov_iter_count(ubuf))
> + return 0;
> +
> + return rc;
> +}
> +
> +static ssize_t
> +famfs_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
> +{
> + struct inode *inode = iocb->ki_filp->f_mapping->host;
> + ssize_t rc;
> +
> + /* dax_iomap_rw() requires i_rwsem held (shared for read) */
> + inode_lock_shared(inode);
> + rc = famfs_rw_prep(iocb, to);
> + if (rc || !iov_iter_count(to)) {
> + inode_unlock_shared(inode);
> + return rc;
> + }
> +
> + rc = dax_iomap_rw(iocb, to, NULL /*&famfs_iomap_ops */);
> + inode_unlock_shared(inode);
> +
> + file_accessed(iocb->ki_filp);
Is it really accessed if rc != 0?
> + return rc;
> +}
> +
> +/**
> + * famfs_dax_write_iter()
> + *
> + * We need our own write-iter in order to prevent append
> + *
> + * @iocb:
> + * @from: iterator describing the user memory source for the write
> + */
> +static ssize_t
> +famfs_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
> +{
> + struct inode *inode = iocb->ki_filp->f_mapping->host;
> + struct famfs_fs_info *fsi = inode->i_sb->s_fs_info;
> + ssize_t rc;
> +
> + if (!famfs_opt_enabled(fsi, FAMFS_OPT_WRITE))
> + return -EPERM;
> +
> + /* dax_iomap_rw() requires i_rwsem held (exclusive for write) */
> + inode_lock(inode);
> + rc = famfs_rw_prep(iocb, from);
> + if (rc || !iov_iter_count(from)) {
> + inode_unlock(inode);
> + return rc;
> + }
> +
> + rc = dax_iomap_rw(iocb, from, NULL /*&famfs_iomap_ops*/);
What happens if you pass a null iomap ops? TBH I was expecting you to
define the iomap ops with a dummy ->iomap_begin that returns EIO or
something.
> + inode_unlock(inode);
> + return rc;
Do you need to update mtime here?
--D
> +}
> +
> +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,
> + .unlocked_ioctl = NULL /*famfs_file_ioctl*/,
> + .mmap = NULL /* 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,
> +};
> +
> diff --git a/fs/famfs/famfs_inode.c b/fs/famfs/famfs_inode.c
> index efc6b852eca0..910a143dad30 100644
> --- a/fs/famfs/famfs_inode.c
> +++ b/fs/famfs/famfs_inode.c
> @@ -58,7 +58,7 @@ static struct inode *famfs_get_inode(
> break;
> case S_IFREG:
> inode->i_op = &famfs_file_inode_operations;
> - inode->i_fop = NULL /* &famfs_file_operations */;
> + inode->i_fop = &famfs_file_operations;
> break;
> case S_IFDIR:
> inode->i_op = &famfs_dir_inode_operations;
> diff --git a/fs/famfs/famfs_internal.h b/fs/famfs/famfs_internal.h
> index 485087588a11..26f5abda96dc 100644
> --- a/fs/famfs/famfs_internal.h
> +++ b/fs/famfs/famfs_internal.h
> @@ -15,6 +15,8 @@
> #include <linux/bits.h>
> #include <linux/build_bug.h>
>
> +extern const struct file_operations famfs_file_operations;
> +
> struct famfs_mount_opts {
> umode_t mode;
> };
> --
> 2.53.0
>
>
