块设备的读写框架

生成块设备

我们以虚拟文件的接口，来看这个框架；因为这是从从应用层到内核的必经之路；使用vfs_mknod来生成块设备文件，并初始化fops

mknod
    do_mknodat
        vfs_mknod
            shmem_mknod
                shmem_get_inode
                    init_special_inode
void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
	inode->i_mode = mode;
	if (S_ISCHR(mode)) {
		inode->i_fop = &def_chr_fops;
		inode->i_rdev = rdev;
	} else if (S_ISBLK(mode)) {
		if (IS_ENABLED(CONFIG_BLOCK))
			inode->i_fop = &def_blk_fops;
		inode->i_rdev = rdev;
	} else if (S_ISFIFO(mode))
		inode->i_fop = &pipefifo_fops;
	else if (S_ISSOCK(mode))
		;	/* leave it no_open_fops */
	else
		printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
				  " inode %s:%lu\n", mode, inode->i_sb->s_id,
				  inode->i_ino);
}
EXPORT_SYMBOL(init_special_inode);

const struct file_operations def_blk_fops = {
	.open		= blkdev_open,
	.release	= blkdev_release,
	.llseek		= blkdev_llseek,
	.read_iter	= blkdev_read_iter,
	.write_iter	= blkdev_write_iter,
	.iopoll		= iocb_bio_iopoll,
	.mmap		= blkdev_mmap,
	.fsync		= blkdev_fsync,
	.unlocked_ioctl	= blkdev_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
	.splice_read	= filemap_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= blkdev_fallocate,
};

打开块设备

open系统调用打开字符设备文件时，会调用do_dentry_open，里面的f->f_op = fops_get(inode->i_fop);就是把上面init_special_inode里的inode->i_fop = &def_blk_fops赋给f->f_op;其中的open为blkdev_open；会调用块设备驱动的open

open
    do_sys_open
        do_sys_openat2
            do_filp_open
                path_openat
                    vfs_open
                        do_dentry_open
static int do_dentry_open(struct file *f,
			  struct inode *inode,
			  int (*open)(struct inode *, struct file *))
{
	static const struct file_operations empty_fops = {};
	int error;
 
	path_get(&f->f_path);
	f->f_inode = inode;
	f->f_mapping = inode->i_mapping;
 
	/* Ensure that we skip any errors that predate opening of the file */
	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 
	if (unlikely(f->f_flags & O_PATH)) {
		f->f_mode = FMODE_PATH | FMODE_OPENED;
		f->f_op = &empty_fops;
		return 0;
	}
 
	/* Any file opened for execve()/uselib() has to be a regular file. */
	if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) {
		error = -EACCES;
		goto cleanup_file;
	}
 
	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
		error = get_write_access(inode);
		if (unlikely(error))
			goto cleanup_file;
		error = __mnt_want_write(f->f_path.mnt);
		if (unlikely(error)) {
			put_write_access(inode);
			goto cleanup_file;
		}
		f->f_mode |= FMODE_WRITER;
	}
 
	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
		f->f_mode |= FMODE_ATOMIC_POS;
 
	f->f_op = fops_get(inode->i_fop);
	if (WARN_ON(!f->f_op)) {
		error = -ENODEV;
		goto cleanup_all;
	}
 
	error = security_file_open(f);
	if (error)
		goto cleanup_all;
 
	error = break_lease(locks_inode(f), f->f_flags);
	if (error)
		goto cleanup_all;
 
	/* normally all 3 are set; ->open() can clear them if needed */
	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
	if (!open)
		open = f->f_op->open;
	if (open) {
		error = open(inode, f);
		if (error)
			goto cleanup_all;
	}
	f->f_mode |= FMODE_OPENED;
	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
		i_readcount_inc(inode);
	if ((f->f_mode & FMODE_READ) &&
	     likely(f->f_op->read || f->f_op->read_iter))
		f->f_mode |= FMODE_CAN_READ;
	if ((f->f_mode & FMODE_WRITE) &&
	     likely(f->f_op->write || f->f_op->write_iter))
		f->f_mode |= FMODE_CAN_WRITE;
 
	f->f_write_hint = WRITE_LIFE_NOT_SET;
	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
	/* NB: we're sure to have correct a_ops only after f_op->open */
	if (f->f_flags & O_DIRECT) {
		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
			return -EINVAL;
	}
	/*
	 * XXX: Huge page cache doesn't support writing yet. Drop all page
	 * cache for this file before processing writes.
	 */
	if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping))
		truncate_pagecache(inode, 0);
 
	return 0;
 
cleanup_all:
	if (WARN_ON_ONCE(error > 0))
		error = -EINVAL;
	fops_put(f->f_op);
	if (f->f_mode & FMODE_WRITER) {
		put_write_access(inode);
		__mnt_drop_write(f->f_path.mnt);
	}
cleanup_file:
	path_put(&f->f_path);
	f->f_path.mnt = NULL;
	f->f_path.dentry = NULL;
	f->f_inode = NULL;
	return error;
}

读块设备

不管有没有文件系统，应用层都是通过虚拟文件系统的接口来到内核的，通过open后；vfs_read里的file->f_op->read_iter就等于def_blk_fops的read_iter成员

ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_READ))
		return -EBADF;
	if (!(file->f_mode & FMODE_CAN_READ))
		return -EINVAL;
	if (unlikely(!access_ok(buf, count)))
		return -EFAULT;

	ret = rw_verify_area(READ, file, pos, count);
	if (ret)
		return ret;
	if (count > MAX_RW_COUNT)
		count =  MAX_RW_COUNT;

	if (file->f_op->read)
		ret = file->f_op->read(file, buf, count, pos);
	else if (file->f_op->read_iter)
		ret = new_sync_read(file, buf, count, pos);
	else
		ret = -EINVAL;
	if (ret > 0) {
		fsnotify_access(file);
		add_rchar(current, ret);
	}
	inc_syscr(current);
	return ret;
}

简化的read框图如下

写块设备

其中file->f_op->write_iter就等于def_blk_fops的write_iter成员

ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;
	if (!(file->f_mode & FMODE_CAN_WRITE))
		return -EINVAL;
	if (unlikely(!access_ok(buf, count)))
		return -EFAULT;

	ret = rw_verify_area(WRITE, file, pos, count);
	if (ret)
		return ret;
	if (count > MAX_RW_COUNT)
		count =  MAX_RW_COUNT;
	file_start_write(file);
	if (file->f_op->write)
		ret = file->f_op->write(file, buf, count, pos);
	else if (file->f_op->write_iter)
		ret = new_sync_write(file, buf, count, pos);
	else
		ret = -EINVAL;
	if (ret > 0) {
		fsnotify_modify(file);
		add_wchar(current, ret);
	}
	inc_syscw(current);
	file_end_write(file);
	return ret;
}

简化的write框图如下

 内核实例

比如插上sd卡，生成/dev/mmcblk0p1；然后usb的U盘功能的bind去打开这个块设备，就能在windows上枚举出一个U盘

drivers/usb/gadget/function/storage_common.c里面就会去，判断下/dev/mmcblk0p1这个设备的read/write相关的接口有没有

static int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
{
        int                             ro;
        struct file                     *filp = NULL;
        int                             rc = -EINVAL;
        struct inode                    *inode = NULL;
        loff_t                          size;
        loff_t                          num_sectors;
        loff_t                          min_sectors;
        unsigned int                    blkbits;
        unsigned int                    blksize;

        /* R/W if we can, R/O if we must */
        ro = curlun->initially_ro;
        if (!ro) {
                filp = filp_open(filename, O_RDWR | O_LARGEFILE, 0);
                if (PTR_ERR(filp) == -EROFS || PTR_ERR(filp) == -EACCES)
                        ro = 1;
        }
        if (ro)
                filp = filp_open(filename, O_RDONLY | O_LARGEFILE, 0);
        if (IS_ERR(filp)) {
                LINFO(curlun, "unable to open backing file: %s\n", filename);
                return PTR_ERR(filp);
        }

        if (!(filp->f_mode & FMODE_WRITE))
                ro = 1;

        inode = file_inode(filp);
        if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) {
                LINFO(curlun, "invalid file type: %s\n", filename);
                goto out;
        }

        /*
         * If we can't read the file, it's no good.
         * If we can't write the file, use it read-only.
         */
        if (!(filp->f_op->read || filp->f_op->read_iter)) {
                LINFO(curlun, "file not readable: %s\n", filename);
                goto out;
        }
        if (!(filp->f_op->write || filp->f_op->write_iter))
                ro = 1;

        size = i_size_read(inode->i_mapping->host);
        if (size < 0) {
                LINFO(curlun, "unable to find file size: %s\n", filename);
                rc = (int) size;
                goto out;
        }

        if (curlun->cdrom) {
                blksize = 2048;
                blkbits = 11;
        } else if (inode->i_bdev) {
                blksize = bdev_logical_block_size(inode->i_bdev);
                blkbits = blksize_bits(blksize);
        } else {
                blksize = 512;
                blkbits = 9;
        }

        num_sectors = size >> blkbits; /* File size in logic-block-size blocks */
        min_sectors = 1;
        if (curlun->cdrom) {
                min_sectors = 0;
                if (num_sectors >= 256*60*75) {
                        num_sectors = 256*60*75 - 1;
                        LINFO(curlun, "file too big: %s\n", filename);
                        LINFO(curlun, "using only first %d blocks\n",
                                        (int) num_sectors);
                }
        }
        if (num_sectors < min_sectors) {
                LINFO(curlun, "file too small: %s\n", filename);
                rc = -ETOOSMALL;
                goto out;
        }

        if (fsg_lun_is_open(curlun))
                fsg_lun_close(curlun);

        curlun->blksize = blksize;
        curlun->blkbits = blkbits;
        curlun->ro = ro;
        curlun->filp = filp;
        curlun->file_length = size;
        curlun->num_sectors = num_sectors;
        LDBG(curlun, "open backing file: %s\n", filename);
        return 0;

out:
        fput(filp);
        return rc;
}

根据最上面的def_blk_fops；5.4.195的内核是没有read成员的，只有read_iter；所以就会打印“file not readable”；需做如下修改