Linux内核源代码情景分析-文件系统的安装

    执行sudo mount -t ext2 /dev/sdb1 /mnt/sdb，将文件系统挂在到/mnt/sdb上。系统调用mount，映射到内核层执行的是sys_mount。假设/dev/sdb1和/mnt/sdb都位于ext2文件系统中。

asmlinkage long sys_mount(char * dev_name, char * dir_name, char * type,  unsigned long flags, void * data)//dev_name指向了"/dev/sdb1",dir_name指向了"/mnt/sdb"，type是表示文件系统类型(即格式)的字符串,如"ext2"、"iso9660"，flags为安装模式，见下面{int retval;unsigned long data_page;unsigned long type_page;unsigned long dev_page;char *dir_page;retval = copy_mount_options (type, &type_page);//将参数从用户空间复制到系统空间。这些参数值的长度均以一个页面为限，并且返回页面的起始地址if (retval < 0)return retval;dir_page = getname(dir_name);//将参数从用户空间复制到系统空间，并返回指向该字符串的指针retval = PTR_ERR(dir_page);if (IS_ERR(dir_page))goto out1;retval = copy_mount_options (dev_name, &dev_page);//将参数从用户空间复制到系统空间。这些参数值的长度均以一个页面为限，并且返回页面的起始地址if (retval < 0)goto out2;retval = copy_mount_options (data, &data_page);//将参数从用户空间复制到系统空间。这些参数值的长度均以一个页面为限，并且返回页面的起始地址if (retval < 0)goto out3;lock_kernel();retval = do_mount((char*)dev_page, dir_page, (char*)type_page,  flags, (void*)data_page);unlock_kernel();free_page(data_page);out3:free_page(dev_page);out2:putname(dir_page);out1:free_page(type_page);return retval;}

    其中flags为安装模式：

#define MS_RDONLY 1/* Mount read-only */#define MS_NOSUID 2/* Ignore suid and sgid bits */#define MS_NODEV 4/* Disallow access to device special files */#define MS_NOEXEC 8/* Disallow program execution */#define MS_SYNCHRONOUS16/* Writes are synced at once */#define MS_REMOUNT32/* Alter flags of a mounted FS */#define MS_MANDLOCK64/* Allow mandatory locks on an FS */#define MS_NOATIME1024/* Do not update access times. */#define MS_NODIRATIME2048/* Do not update directory access times */#define MS_BIND4096/* * Flags that can be altered by MS_REMOUNT */#define MS_RMT_MASK(MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|\MS_SYNCHRONOUS|MS_MANDLOCK|MS_NOATIME|MS_NODIRATIME)/* * Magic mount flag number. Has to be or-ed to the flag values. */#define MS_MGC_VAL 0xC0ED0000/* magic flag number to indicate "new" flags */#define MS_MGC_MSK 0xffff0000/* magic flag number mask */

    所有的标志位都在低16位，而高16位则用作"magic_number"。

    do_mount是整个过程的核心，代码如下：

long do_mount(char * dev_name, char * dir_name, char *type_page, //dev_name指向了"/dev/sdb1",dir_name指向了"/mnt/sdb"  unsigned long flags, void *data_page){struct file_system_type * fstype;struct nameidata nd;struct vfsmount *mnt = NULL;struct super_block *sb;int retval = 0;/* Discard magic */if ((flags & MS_MGC_MSK) == MS_MGC_VAL)flags &= ~MS_MGC_MSK; /* Basic sanity checks */if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))//dir_name指针不能为NULL，并且字符串的第一个字符不为NULL，即不是空字符串，并且字符串的长度不超过一个页面return -EINVAL;if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))//如果dev_name指针非空，那么要求字符串的长度不得大于一个页面return -EINVAL;/* OK, looks good, now let's see what do they want *//* just change the flags? - capabilities are checked in do_remount() */if (flags & MS_REMOUNT)//暂不关心return do_remount(dir_name, flags & ~MS_REMOUNT,  (char *) data_page);/* "mount --bind"? Equivalent to older "mount -t bind" *//* No capabilities? What if users do thousands of these? */if (flags & MS_BIND)//暂不关心return do_loopback(dev_name, dir_name);/* For the rest we need the type */if (!type_page || !memchr(type_page, 0, PAGE_SIZE))//要求type_page指针不能为NULL，且字符串的长度不超过一个页面return -EINVAL;#if 0/* Can be deleted again. Introduced in patch-2.3.99-pre6 *//* loopback mount? This is special - requires fewer capabilities */if (strcmp(type_page, "bind")==0)return do_loopback(dev_name, dir_name);#endif/* for the rest we _really_ need capabilities... */if (!capable(CAP_SYS_ADMIN))//检查权限return -EPERM;/* ... filesystem driver... */fstype = get_fs_type(type_page);//根据文件系统类型名，找到对应的file_system_type结构if (!fstype)return -ENODEV;/* ... and mountpoint. Do the lookup first to force automounting. */if (path_init(dir_name,      LOOKUP_FOLLOW|LOOKUP_POSITIVE|LOOKUP_DIRECTORY, &nd))retval = path_walk(dir_name, &nd);//找到/mnt/sdb节点的mnt结构和dentry结构if (retval)goto fs_out;/* get superblock, locks mount_sem on success */if (fstype->fs_flags & FS_NOMOUNT)sb = ERR_PTR(-EINVAL);else if (fstype->fs_flags & FS_REQUIRES_DEV)//对于ext2文件系统来说，fs_flags为FS_REQUIRES_DEVsb = get_sb_bdev(fstype, dev_name, flags, data_page);//要把待安装设备的"超级块"读进来并根据超级块中的信息在内存中建立起相应的super_block数据结构else if (fstype->fs_flags & FS_SINGLE)sb = get_sb_single(fstype, flags, data_page);elsesb = get_sb_nodev(fstype, flags, data_page);retval = PTR_ERR(sb);if (IS_ERR(sb))goto dput_out;/* Something was mounted here while we slept */while(d_mountpoint(nd.dentry) && follow_down(&nd.mnt, &nd.dentry))//是否是挂载点;/* Refuse the same filesystem on the same mount point */retval = -EBUSY;if (nd.mnt && nd.mnt->mnt_sb == sb       && nd.mnt->mnt_root == nd.dentry)goto fail;retval = -ENOENT;if (!nd.dentry->d_inode)goto fail;down(&nd.dentry->d_inode->i_zombie);if (!IS_DEADDIR(nd.dentry->d_inode)) {retval = -ENOMEM;mnt = add_vfsmnt(&nd, sb->s_root, dev_name);//把待安装设备的super_block数据结构与安装点的dentry数据结构联系在一起}up(&nd.dentry->d_inode->i_zombie);if (!mnt)goto fail;retval = 0;unlock_out:up(&mount_sem);dput_out:path_release(&nd);fs_out:put_filesystem(fstype);return retval;fail:if (list_empty(&sb->s_mounts))kill_super(sb, 0);goto unlock_out;}

    

    系统支持的每一种文件系统都有一个file_system_type数据结构，他们都会链入file_systems结构。

struct file_system_type {const char *name;int fs_flags;struct super_block *(*read_super) (struct super_block *, void *, int);struct module *owner;struct vfsmount *kern_mnt; /* For kernel mount, if it's FS_SINGLE fs */struct file_system_type * next;};

    对于ext2文件系统来说：

static DECLARE_FSTYPE_DEV(ext2_fs_type, "ext2", ext2_read_super);

#define DECLARE_FSTYPE_DEV(var,type,read) \DECLARE_FSTYPE(var,type,read,FS_REQUIRES_DEV)

#define DECLARE_FSTYPE(var,type,read,flags) \struct file_system_type var = { \name:type, \read_super:read, \fs_flags:flags, \owner:THIS_MODULE, \}

    我们再看看其他文件系统：

static DECLARE_FSTYPE(pipe_fs_type, "pipefs", pipefs_read_super,FS_NOMOUNT|FS_SINGLE);

static DECLARE_FSTYPE(ramfs_fs_type, "ramfs", ramfs_read_super, FS_LITTER);

    get_fs_type根据文件系统类型名，找到对应的file_system_type结构，代码如下：

struct file_system_type *get_fs_type(const char *name){struct file_system_type *fs;read_lock(&file_systems_lock);fs = *(find_filesystem(name));//根据name在file_systems中寻找file_system_type结构if (fs && !try_inc_mod_count(fs->owner))fs = NULL;read_unlock(&file_systems_lock);if (!fs && (request_module(name) == 0)) {read_lock(&file_systems_lock);fs = *(find_filesystem(name));if (fs && !try_inc_mod_count(fs->owner))fs = NULL;read_unlock(&file_systems_lock);}return fs;}

static struct file_system_type **find_filesystem(const char *name){struct file_system_type **p;for (p=&file_systems; *p; p=&(*p)->next)//根据name在file_systems中寻找file_system_type结构if (strcmp((*p)->name,name) == 0)break;return p;}

    返回到do_mount，执行get_sb_bdev，要把待安装设备的"超级块"读进来并根据超级块中的信息在内存中建立起相应的super_block数据结构，代码如下：

static struct super_block *get_sb_bdev(struct file_system_type *fs_type,char *dev_name, int flags, void * data){struct inode *inode;struct block_device *bdev;struct block_device_operations *bdops;struct super_block * sb;struct nameidata nd;kdev_t dev;int error = 0;/* What device it is? */if (!dev_name || !*dev_name)return ERR_PTR(-EINVAL);if (path_init(dev_name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd))error = path_walk(dev_name, &nd);//找到/mnt/sdb1节点的mnt结构和dentry结构if (error)return ERR_PTR(error);inode = nd.dentry->d_inode;error = -ENOTBLK;if (!S_ISBLK(inode->i_mode))//一定要是设备节点goto out;error = -EACCES;if (IS_NODEV(inode))goto out;bdev = inode->i_bdev;//得到block_device结构bdops = devfs_get_ops ( devfs_get_handle_from_inode (inode) );if (bdops) bdev->bd_op = bdops;/* Done with lookups, semaphore down */down(&mount_sem);dev = to_kdev_t(bdev->bd_dev);//设备号sb = get_super(dev);//根据设备号在super_blocks中查找super_block结构if (sb) {//如果有就返回if (fs_type == sb->s_type &&    ((flags ^ sb->s_flags) & MS_RDONLY) == 0) {path_release(&nd);return sb;}} else {//如果没有mode_t mode = FMODE_READ; /* we always need it ;-) */if (!(flags & MS_RDONLY))mode |= FMODE_WRITE;error = blkdev_get(bdev, mode, 0, BDEV_FS);if (error)goto out;check_disk_change(dev);error = -EACCES;if (!(flags & MS_RDONLY) && is_read_only(dev))goto out1;error = -EINVAL;sb = read_super(dev, bdev, fs_type, flags, data, 0);if (sb) {get_filesystem(fs_type);path_release(&nd);return sb;}out1:blkdev_put(bdev, BDEV_FS);}out:path_release(&nd);up(&mount_sem);return ERR_PTR(error);}

    path_walk，和Linux内核源代码情景分析-从路径名到目标节点，一文中的区别在于：

for (block = 0; block < EXT2_N_BLOCKS; block++)inode->u.ext2_i.i_data[block] = raw_inode->i_block[block];if (inode->i_ino == EXT2_ACL_IDX_INO ||    inode->i_ino == EXT2_ACL_DATA_INO)/* Nothing to do */ ;else if (S_ISREG(inode->i_mode)) {inode->i_op = &ext2_file_inode_operations;inode->i_fop = &ext2_file_operations;inode->i_mapping->a_ops = &ext2_aops;} else if (S_ISDIR(inode->i_mode)) {inode->i_op = &ext2_dir_inode_operations;inode->i_fop = &ext2_dir_operations;} else if (S_ISLNK(inode->i_mode)) {if (!inode->i_blocks)inode->i_op = &ext2_fast_symlink_inode_operations;else {inode->i_op = &page_symlink_inode_operations;inode->i_mapping->a_ops = &ext2_aops;}} else //会执行这里init_special_inode(inode, inode->i_mode,   le32_to_cpu(raw_inode->i_block[0]));//i_block[0]是设备号

    还记得在Linux内核源代码情景分析-从路径名到目标节点，一文中：

bh = ext2_find_entry (dir, dentry->d_name.name, dentry->d_name.len, &de);//根据父节点的inode结构中inode->u.ext2_i.i_data找到对应的目录项

    在上面的片段中：

for (block = 0; block < EXT2_N_BLOCKS; block++)inode->u.ext2_i.i_data[block] = raw_inode->i_block[block];

    所以总结raw_inode->i_block[block]，如果得到是目录节点的inode，那么i_block[]存储着目录项的位置。如果是文件节点的inode，那么i_block[]存储着真正数据的位置，现在设备节点的inode存储着设备号(包含了主设备号和次设备号)。
    接下里我们来看init_special_inode。

void init_special_inode(struct inode *inode, umode_t mode, int rdev){inode->i_mode = mode;if (S_ISCHR(mode)) {inode->i_fop = &def_chr_fops;inode->i_rdev = to_kdev_t(rdev);} else if (S_ISBLK(mode)) {//块设备inode->i_fop = &def_blk_fops;inode->i_rdev = to_kdev_t(rdev);inode->i_bdev = bdget(rdev);} else if (S_ISFIFO(mode))inode->i_fop = &def_fifo_fops;else if (S_ISSOCK(mode))inode->i_fop = &bad_sock_fops;elseprintk(KERN_DEBUG "init_special_inode: bogus imode (%o)\n", mode);}

struct block_device *bdget(dev_t dev){struct list_head * head = bdev_hashtable + hash(dev);struct block_device *bdev, *new_bdev;spin_lock(&bdev_lock);bdev = bdfind(dev, head);spin_unlock(&bdev_lock);if (bdev)return bdev;new_bdev = alloc_bdev();//分配block_device结构if (!new_bdev)return NULL;atomic_set(&new_bdev->bd_count,1);new_bdev->bd_dev = dev;//设备号new_bdev->bd_op = NULL;spin_lock(&bdev_lock);bdev = bdfind(dev, head);//在hash表中寻找block_device结构if (!bdev) {list_add(&new_bdev->bd_hash, head);//如果没有找到，就添加到hash表中，以便下次能够找到spin_unlock(&bdev_lock);return new_bdev;}spin_unlock(&bdev_lock);destroy_bdev(new_bdev);return bdev;}

    

    返回到get_sb_bdev，继续执行，如果get_super获取不到block_device结构，那么首先执行blkdev_get，设置bdev->bd_op，代码如下：

int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags, int kind){int ret = -ENODEV;kdev_t rdev = to_kdev_t(bdev->bd_dev); /* this should become bdev */down(&bdev->bd_sem);if (!bdev->bd_op)bdev->bd_op = get_blkfops(MAJOR(rdev));//bdev->bd_op......return ret;}

const struct block_device_operations * get_blkfops(unsigned int major){const struct block_device_operations *ret = NULL;/* major 0 is used for non-device mounts */if (major && major < MAX_BLKDEV) {#ifdef CONFIG_KMODif (!blkdevs[major].bdops) {char name[20];sprintf(name, "block-major-%d", major);request_module(name);}#endifret = blkdevs[major].bdops;}return ret;}

    然后执行关键的read_super，根据设备号把设备的超级块从硬盘中读出来，代码如下：

static struct super_block * read_super(kdev_t dev, struct block_device *bdev,       struct file_system_type *type, int flags,       void *data, int silent){struct super_block * s;s = get_empty_super();if (!s)goto out;s->s_dev = dev;///设备号s->s_bdev = bdev;//对应的block_devices->s_flags = flags;s->s_dirt = 0;sema_init(&s->s_vfs_rename_sem,1);sema_init(&s->s_nfsd_free_path_sem,1);s->s_type = type;//文件系统类型sema_init(&s->s_dquot.dqio_sem, 1);sema_init(&s->s_dquot.dqoff_sem, 1);s->s_dquot.flags = 0;lock_super(s);if (!type->read_super(s, data, silent))//根据设备号，把文件系统的超级块从硬盘中读入goto out_fail;unlock_super(s);/* tell bdcache that we are going to keep this one */if (bdev)atomic_inc(&bdev->bd_count);out:return s;out_fail:s->s_dev = 0;s->s_bdev = 0;s->s_type = NULL;unlock_super(s);return NULL;}

     get_empty_super分配super_block结构，并链入super_blocks，以便下次能够查找到，代码如下：

struct super_block *get_empty_super(void){struct super_block *s;for (s  = sb_entry(super_blocks.next);//还是现在super_blocks里面查找     s != sb_entry(&super_blocks);      s  = sb_entry(s->s_list.next)) {if (s->s_dev)continue;if (!s->s_lock)return s;printk("VFS: empty superblock %p locked!\n", s);}/* Need a new one... */if (nr_super_blocks >= max_super_blocks)return NULL;s = kmalloc(sizeof(struct super_block),  GFP_USER);//分配super_block 结构if (s) {nr_super_blocks++;memset(s, 0, sizeof(struct super_block));INIT_LIST_HEAD(&s->s_dirty);list_add (&s->s_list, super_blocks.prev);//链入super_blocksinit_waitqueue_head(&s->s_wait);INIT_LIST_HEAD(&s->s_files);INIT_LIST_HEAD(&s->s_mounts);}return s;}

    执行完get_sb_bdev，获得了设备的超级块结构，返回到do_mount继续执行add_vfsmnt，代码如下：

static struct vfsmount *add_vfsmnt(struct nameidata *nd,struct dentry *root,const char *dev_name){struct vfsmount *mnt;struct super_block *sb = root->d_inode->i_sb;char *name;mnt = kmalloc(sizeof(struct vfsmount), GFP_KERNEL);if (!mnt)goto out;memset(mnt, 0, sizeof(struct vfsmount));if (nd || dev_name)mnt->mnt_flags = MNT_VISIBLE;/* It may be NULL, but who cares? */if (dev_name) {name = kmalloc(strlen(dev_name)+1, GFP_KERNEL);if (name) {strcpy(name, dev_name);mnt->mnt_devname = name;}}mnt->mnt_owner = current->uid;atomic_set(&mnt->mnt_count,1);mnt->mnt_sb = sb;spin_lock(&dcache_lock);if (nd && !IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))goto fail;mnt->mnt_root = dget(root);mnt->mnt_mountpoint = nd ? dget(nd->dentry) : dget(root);//挂载节点的dentry结构mnt->mnt_parent = nd ? mntget(nd->mnt) : mnt;if (nd) {list_add(&mnt->mnt_child, &nd->mnt->mnt_mounts);list_add(&mnt->mnt_clash, &nd->dentry->d_vfsmnt);//while(d_mountpoint(nd.dentry)会查找到} else {INIT_LIST_HEAD(&mnt->mnt_child);INIT_LIST_HEAD(&mnt->mnt_clash);}INIT_LIST_HEAD(&mnt->mnt_mounts);list_add(&mnt->mnt_instances, &sb->s_mounts);list_add(&mnt->mnt_list, vfsmntlist.prev);spin_unlock(&dcache_lock);out:return mnt;fail:spin_unlock(&dcache_lock);if (mnt->mnt_devname)kfree(mnt->mnt_devname);kfree(mnt);return NULL;}

    vfsmount结构如下：

struct vfsmount{struct dentry *mnt_mountpoint;/* dentry of mountpoint */struct dentry *mnt_root;/* root of the mounted tree */struct vfsmount *mnt_parent;/* fs we are mounted on */struct list_head mnt_instances;/* other vfsmounts of the same fs */struct list_head mnt_clash;/* those who are mounted on (other *//* instances) of the same dentry */struct super_block *mnt_sb;/* pointer to superblock */struct list_head mnt_mounts;/* list of children, anchored here */struct list_head mnt_child;/* and going through their mnt_child */atomic_t mnt_count;int mnt_flags;char *mnt_devname;/* Name of device e.g. /dev/dsk/hda1 */struct list_head mnt_list;uid_t mnt_owner;};

    

  

    至此，文件系统的安装就写完了。