open file process
This article is basically Linux5.15
When the application layer opens a file through the open api, how does the kernel handle it? It is used to describe the processing flow corresponding to the open system call in the kernel.
data structure
fdtable
A process can open many files, and the kernel uses fdtable to manage these files.
include/linux/fdtable.h
struct fdtable {
unsigned int max_fds;
struct file __rcu **fd; /* current fd array */
unsigned long *close_on_exec;
unsigned long *open_fds;
unsigned long *full_fds_bits;
struct rcu_head rcu;
};fd: array of file descriptors
open_fds: In order to facilitate the search for free items in the array, the bitmap created for the array
close_on_exec: Among the open files, some files are used for execution purposes and should be automatically closed after execution is complete
files_struct
For most processes, the number of open files is limited. An optimized design method is to allocate a small number of file descriptor pointer arrays for each process, but when the process needs more pointers, it will be dynamically expanded. For this reason, the process does not use fdtable directly, but uses the files_struct structure as a field of task_struct
/*
* Open file table structure
*/
struct files_struct {
/*
* read mostly part
*/
atomic_t count;
bool resize_in_progress;
wait_queue_head_t resize_wait;
struct fdtable __rcu *fdt;
struct fdtable fdtab;
/*
* written part on a separate cache line in SMP
*/
spinlock_t file_lock ____cacheline_aligned_in_smp;
unsigned int next_fd;
unsigned long close_on_exec_init[1];
unsigned long open_fds_init[1];
unsigned long full_fds_bits_init[1];
struct file __rcu * fd_array[NR_OPEN_DEFAULT];
};fdt points to the fdtable actually used by the process. For most processes, there are not a lot of sorting out of open files. At this time, there is no need to allocate additional space, and it directly points to the embedded structure, that is, the fdtab domain.
file
Each opened file corresponds to a file structure, through which the process operates on the file.
include/linux/fs.h
struct file {
union {
struct llist_node fu_llist;
struct rcu_head fu_rcuhead;
} f_u;
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
/*
* Protects f_ep_links, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
enum rw_hint f_write_hint;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
struct mutex f_pos_lock;
loff_t f_pos;
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
u64 f_version;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* needed for tty driver, and maybe others */
void *private_data;
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
errseq_t f_sb_err; /* for syncfs */
} __randomize_layoutf_path: file path
f_op: points to the file operation table, read/write and other operations will call the callback here
f_mapping: points to the file address space descriptor
f_pos: the offset value of the current file
processing flow
open system call
The overall system call stack is as follows:
#3 0xffffffff81218174 in do_filp_open (dfd=dfd@entry=-100, pathname=pathname@entry=0xffff888004950000, op=op@entry=0xffffc90000173ee4) at fs/namei.c:3396
#4 0xffffffff81203cfd in do_sys_openat2 (dfd=-100, filename=<optimized out>, how=how@entry=0xffffc90000173f20) at fs/open.c:1168
#5 0xffffffff81205135 in do_sys_open (dfd=<optimized out>, filename=<optimized out>, flags=<optimized out>, mode=<optimized out>) at fs/open.c:1184
#6 0xffffffff819bf903 in do_syscall_64 (nr=<optimized out>, regs=0xffffc90000173f58) at arch/x86/entry/common.c:46
#7 0xffffffff81a0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120The entry function of the open system call is defined as follows:
long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
struct open_how how = build_open_how(flags, mode);
return do_sys_openat2(dfd, filename, &how);
}
SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(AT_FDCWD, filename, flags, mode);
}The do_sys_open function calls do_sys_openat2, and its processing flow is as follows:
static long do_sys_openat2(int dfd, const char __user *filename,
struct open_how *how)
{
struct open_flags op;
int fd = build_open_flags(how, &op);
struct filename *tmp;
if (fd)
return fd;
tmp = getname(filename);
if (IS_ERR(tmp))
return PTR_ERR(tmp);
fd = get_unused_fd_flags(how->flags); /* 1 */
if (fd >= 0) {
struct file *f = do_filp_open(dfd, tmp, &op); /* 2 */
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
fsnotify_open(f);
fd_install(fd, f); /* 3 */
}
}
putname(tmp);
return fd;
}(1) Get a free fd
(2) Executing the real open process is the focus of analysis later
(3) After the open is successful, link fd to the task_struct structure of the current process
The processing flow of fd_install is as follows:
fs/file.c
void fd_install(unsigned int fd, struct file *file)
{
__fd_install(current->files, fd, file);
}
void __fd_install(struct files_struct *files, unsigned int fd,
struct file *file)
{
struct fdtable *fdt;
rcu_read_lock_sched();
if (unlikely(files->resize_in_progress)) {
rcu_read_unlock_sched();
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
return;
}
/* coupled with smp_wmb() in expand_fdtable() */
smp_rmb();
fdt = rcu_dereference_sched(files->fdt); /* 1 */
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file); /* 2 */
rcu_read_unlock_sched();
}(1) Find the fdt table corresponding to the process
(2) Assign the file structure to the corresponding fdt
The processing of the do_file_open function is as follows, mainly calling the path_openat function to execute the real open process:
fs/namei.c
do_sys_open->do_sys_openat2->do_filp_open
struct file *do_filp_open(int dfd, struct filename *pathname,
const struct open_flags *op)
{
struct nameidata nd;
int flags = op->lookup_flags;
struct file *filp;
set_nameidata(&nd, dfd, pathname);
filp = path_openat(&nd, op, flags | LOOKUP_RCU);
if (unlikely(filp == ERR_PTR(-ECHILD)))
filp = path_openat(&nd, op, flags);
if (unlikely(filp == ERR_PTR(-ESTALE)))
filp = path_openat(&nd, op, flags | LOOKUP_REVAL);
restore_nameidata();
return filp;
}path_openat: Execute the core process of open
fs/namei.c
do_sys_open->do_sys_openat2->do_filp_open->path_openat
static struct file *path_openat(struct nameidata *nd,
const struct open_flags *op, unsigned flags)
{
struct file *file;
int error;
file = alloc_empty_file(op->open_flag, current_cred()); /* 1 */
if (IS_ERR(file))
return file;
if (unlikely(file->f_flags & __O_TMPFILE)) {
error = do_tmpfile(nd, flags, op, file);
} else if (unlikely(file->f_flags & O_PATH)) {
error = do_o_path(nd, flags, file);
} else {
const char *s = path_init(nd, flags);
while (!(error = link_path_walk(s, nd)) && /* 2 */
(s = open_last_lookups(nd, file, op)) != NULL) /* 3 */
;
if (!error)
error = do_open(nd, file, op); /* 4 */
terminate_walk(nd);
}
if (likely(!error)) {
if (likely(file->f_mode & FMODE_OPENED))
return file;
WARN_ON(1);
error = -EINVAL;
}
fput(file);
if (error == -EOPENSTALE) {
if (flags & LOOKUP_RCU)
error = -ECHILD;
else
error = -ESTALE;
}
return ERR_PTR(error);
}(1) Apply for the file structure and initialize it
(2) Find the last component of the path
(3) To process the last component, it will check whether the file exists, and if it does not exist, it will look at the condition to create
(4) Execute the final step of open, such as calling the open callback
The following is a detailed description of steps 2, 3, and 4 above.
link_path_walk
The internal implementation of link_path_walk is a bit complicated. The general logic is to call the walk_component function repeatedly until the last component of the path is found.
open_last_lookups
open_lask_lookups calls the lookup_open function to perform lookup and maybe create operations
fs/namei.c
do_sys_open->do_sys_openat2->do_filp_open->path_openat->open_last_lookups->lookup_open
static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
const struct open_flags *op,
bool got_write)
{
struct dentry *dir = nd->path.dentry;
struct inode *dir_inode = dir->d_inode;
int open_flag = op->open_flag;
struct dentry *dentry;
int error, create_error = 0;
umode_t mode = op->mode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
if (unlikely(IS_DEADDIR(dir_inode)))
return ERR_PTR(-ENOENT);
file->f_mode &= ~FMODE_CREATED;
dentry = d_lookup(dir, &nd->last); /* 1 */
for (;;) {
if (!dentry) {
dentry = d_alloc_parallel(dir, &nd->last, &wq);
if (IS_ERR(dentry))
return dentry;
}
if (d_in_lookup(dentry))
break;
error = d_revalidate(dentry, nd->flags);
if (likely(error > 0))
break;
if (error)
goto out_dput;
d_invalidate(dentry);
dput(dentry);
dentry = NULL;
}
if (dentry->d_inode) {
/* Cached positive dentry: will open in f_op->open */
return dentry;
}
/*
* Checking write permission is tricky, bacuse we don't know if we are
* going to actually need it: O_CREAT opens should work as long as the
* file exists. But checking existence breaks atomicity. The trick is
* to check access and if not granted clear O_CREAT from the flags.
*
* Another problem is returing the "right" error value (e.g. for an
* O_EXCL open we want to return EEXIST not EROFS).
*/
if (unlikely(!got_write))
open_flag &= ~O_TRUNC;
if (open_flag & O_CREAT) {
if (open_flag & O_EXCL)
open_flag &= ~O_TRUNC;
if (!IS_POSIXACL(dir->d_inode))
mode &= ~current_umask();
if (likely(got_write))
create_error = may_o_create(&nd->path, dentry, mode);
else
create_error = -EROFS;
}
if (create_error)
open_flag &= ~O_CREAT;
if (dir_inode->i_op->atomic_open) {
dentry = atomic_open(nd, dentry, file, open_flag, mode);
if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT))
dentry = ERR_PTR(create_error);
return dentry;
}
if (d_in_lookup(dentry)) {
struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry,
nd->flags); /* 2 */
d_lookup_done(dentry);
if (unlikely(res)) {
if (IS_ERR(res)) {
error = PTR_ERR(res);
goto out_dput;
}
dput(dentry);
dentry = res;
}
}
/* Negative dentry, just create the file */
if (!dentry->d_inode && (open_flag & O_CREAT)) {
file->f_mode |= FMODE_CREATED;
audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
if (!dir_inode->i_op->create) {
error = -EACCES;
goto out_dput;
}
error = dir_inode->i_op->create(dir_inode, dentry, mode,
open_flag & O_EXCL); /* 3 */
if (error)
goto out_dput;
}
if (unlikely(create_error) && !dentry->d_inode) {
error = create_error;
goto out_dput;
}
return dentry;
out_dput:
dput(dentry);
return ERR_PTR(error);
}(1) Find the dentry from the cache
(2) If not found, call the lookup method of the file system to search
(3) If not found and O_CREAT, call the create method of the file system to create
do_open
After finding the corresponding file, do_open performs the final finishing work on it.
fs/namei.c
do_sys_open->do_sys_openat2->do_filp_open->path_openat->do_open
static int do_open(struct nameidata *nd,
struct file *file, const struct open_flags *op)
{
int open_flag = op->open_flag;
bool do_truncate;
int acc_mode;
int error;
if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) {
error = complete_walk(nd);
if (error)
return error;
}
if (!(file->f_mode & FMODE_CREATED))
audit_inode(nd->name, nd->path.dentry, 0);
if (open_flag & O_CREAT) {
if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED))
return -EEXIST;
if (d_is_dir(nd->path.dentry))
return -EISDIR;
error = may_create_in_sticky(nd->dir_mode, nd->dir_uid,
d_backing_inode(nd->path.dentry));
if (unlikely(error))
return error;
}
if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
return -ENOTDIR;
do_truncate = false;
acc_mode = op->acc_mode;
if (file->f_mode & FMODE_CREATED) {
/* Don't check for write permission, don't truncate */
open_flag &= ~O_TRUNC;
acc_mode = 0;
} else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) {
error = mnt_want_write(nd->path.mnt);
if (error)
return error;
do_truncate = true;
}
error = may_open(&nd->path, acc_mode, open_flag); /* 1 */
if (!error && !(file->f_mode & FMODE_OPENED))
error = vfs_open(&nd->path, file); /* 2 */
if (!error)
error = ima_file_check(file, op->acc_mode);
if (!error && do_truncate)
error = handle_truncate(file);
if (unlikely(error > 0)) {
WARN_ON(1);
error = -EINVAL;
}
if (do_truncate)
mnt_drop_write(nd->path.mnt);
return error;
}(1) map_open will do some permission checks, such as checking whether the file system is readonly
(2) Call vfs_open to execute the final open process
fs/open.c
do_sys_open->do_sys_openat2->do_filp_open->path_openat->do_open->vfs_open
int vfs_open(const struct path *path, struct file *file)
{
file->f_path = *path;
return do_dentry_open(file, d_backing_inode(path->dentry), NULL);
}
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;
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
f->f_sb_err = file_sample_sb_err(f); /* 1 */
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
f->f_op = &empty_fops;
return 0;
}
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); /* 2 */
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); /* 3 */
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;
}(1) (2) Set some members of the file structure
(3) Find the open callback and execute it
exfat related callbacks
The following takes the exfat file system as an example to introduce the specific implementation of related callbacks in the open process.
In the open process, three specific callbacks are involved: lookup, create, open
Where lookup and create are located in inode_operations, open
struct inode_operations {
****
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
int (*create) (struct inode *,struct dentry *, umode_t, bool);
****
}
struct file_operations {
struct module *owner;
*****
int (*open) (struct inode *, struct file *);
*****
}Among them, exfat does not implement the open function, but only implements the create and lookup functions.
exfat_lookup
static struct dentry *exfat_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
struct dentry *alias;
struct exfat_dir_entry info;
int err;
loff_t i_pos;
mode_t i_mode;
mutex_lock(&EXFAT_SB(sb)->s_lock);
err = exfat_find(dir, &dentry->d_name, &info); /* 1 */
if (err) {
if (err == -ENOENT) {
inode = NULL;
goto out;
}
goto unlock;
}
i_pos = exfat_make_i_pos(&info);
inode = exfat_build_inode(sb, &info, i_pos); /* 2 */
err = PTR_ERR_OR_ZERO(inode);
if (err)
goto unlock;
i_mode = inode->i_mode;
alias = d_find_alias(inode);
/*
* Checking "alias->d_parent == dentry->d_parent" to make sure
* FS is not corrupted (especially double linked dir).
*/
if (alias && alias->d_parent == dentry->d_parent &&
!exfat_d_anon_disconn(alias)) {
/*
* Unhashed alias is able to exist because of revalidate()
* called by lookup_fast. You can easily make this status
* by calling create and lookup concurrently
* In such case, we reuse an alias instead of new dentry
*/
if (d_unhashed(alias)) {
WARN_ON(alias->d_name.hash_len !=
dentry->d_name.hash_len);
exfat_info(sb, "rehashed a dentry(%p) in read lookup",
alias);
d_drop(dentry);
d_rehash(alias);
} else if (!S_ISDIR(i_mode)) {
/*
* This inode has non anonymous-DCACHE_DISCONNECTED
* dentry. This means, the user did ->lookup() by an
* another name (longname vs 8.3 alias of it) in past.
*
* Switch to new one for reason of locality if possible.
*/
d_move(alias, dentry);
}
iput(inode);
mutex_unlock(&EXFAT_SB(sb)->s_lock);
return alias;
}
dput(alias);
out:
mutex_unlock(&EXFAT_SB(sb)->s_lock);
if (!inode)
exfat_d_version_set(dentry, inode_query_iversion(dir));
return d_splice_alias(inode, dentry); /* 3 */
unlock:
mutex_unlock(&EXFAT_SB(sb)->s_lock);
return ERR_PTR(err);
}The input parameters of the lookup function are defined as:
dir: the inode corresponding to the parent directory
dentry: the dentry corresponding to the file you need to find
The return value is the dentry corresponding to the found file.
Before calling this function, a dentry has been assigned to the child node, and it is associated with the dentry of the parent directory, but it has not been associated with the inode.
This function should find the file in the parent directory and allocate an inode associated with the corresponding dentry.
(1) According to the name, find the corresponding entry in the parent directory
(2) Create the corresponding inode
(3) Establish the connection between inode and dentry
Among them, the process of exfat_find is as follows:
/* lookup a file */
static int exfat_find(struct inode *dir, struct qstr *qname,
struct exfat_dir_entry *info)
{
int ret, dentry, num_entries, count;
struct exfat_chain cdir;
struct exfat_uni_name uni_name;
struct super_block *sb = dir->i_sb;
struct exfat_sb_info *sbi = EXFAT_SB(sb);
struct exfat_inode_info *ei = EXFAT_I(dir);
struct exfat_dentry *ep, *ep2;
struct exfat_entry_set_cache *es;
if (qname->len == 0)
return -ENOENT;
/* check the validity of directory name in the given pathname */
ret = exfat_resolve_path_for_lookup(dir, qname->name, &cdir, &uni_name);
if (ret)
return ret;
num_entries = exfat_calc_num_entries(&uni_name);
if (num_entries < 0)
return num_entries;
/* check the validation of hint_stat and initialize it if required */
if (ei->version != (inode_peek_iversion_raw(dir) & 0xffffffff)) {
ei->hint_stat.clu = cdir.dir;
ei->hint_stat.eidx = 0;
ei->version = (inode_peek_iversion_raw(dir) & 0xffffffff);
ei->hint_femp.eidx = EXFAT_HINT_NONE;
}
/* search the file name for directories */
dentry = exfat_find_dir_entry(sb, ei, &cdir, &uni_name,
num_entries, TYPE_ALL); /* 1 */
if (dentry < 0)
return dentry; /* -error value */
info->dir = cdir;
info->entry = dentry;
info->num_subdirs = 0;
es = exfat_get_dentry_set(sb, &cdir, dentry, ES_2_ENTRIES);
if (!es)
return -EIO;
ep = exfat_get_dentry_cached(es, 0);
ep2 = exfat_get_dentry_cached(es, 1);
info->type = exfat_get_entry_type(ep); /* 2 */
info->attr = le16_to_cpu(ep->dentry.file.attr);
info->size = le64_to_cpu(ep2->dentry.stream.valid_size);
if ((info->type == TYPE_FILE) && (info->size == 0)) {
info->flags = ALLOC_NO_FAT_CHAIN;
info->start_clu = EXFAT_EOF_CLUSTER;
} else {
info->flags = ep2->dentry.stream.flags;
info->start_clu =
le32_to_cpu(ep2->dentry.stream.start_clu);
}
exfat_get_entry_time(sbi, &info->crtime,
ep->dentry.file.create_tz,
ep->dentry.file.create_time,
ep->dentry.file.create_date,
ep->dentry.file.create_time_cs);
exfat_get_entry_time(sbi, &info->mtime,
ep->dentry.file.modify_tz,
ep->dentry.file.modify_time,
ep->dentry.file.modify_date,
ep->dentry.file.modify_time_cs);
exfat_get_entry_time(sbi, &info->atime,
ep->dentry.file.access_tz,
ep->dentry.file.access_time,
ep->dentry.file.access_date,
0);
exfat_free_dentry_set(es, false);
if (ei->start_clu == EXFAT_FREE_CLUSTER) {
exfat_fs_error(sb,
"non-zero size file starts with zero cluster (size : %llu, p_dir : %u, entry : 0x%08x)",
i_size_read(dir), ei->dir.dir, ei->entry);
return -EIO;
}
if (info->type == TYPE_DIR) {
exfat_chain_set(&cdir, info->start_clu,
EXFAT_B_TO_CLU(info->size, sbi), info->flags);
count = exfat_count_dir_entries(sb, &cdir);
if (count < 0)
return -EIO;
info->num_subdirs = count + EXFAT_MIN_SUBDIR;
}
return 0;
}Logically speaking, what this function should do is to traverse the cluster of the parent directory and find the matching entry according to the name.
(1) Find the corresponding entry according to the name
(2) The relevant information recorded in the entry is recorded in the structure of struct exfat_dir_entry *info
exfat_create
static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
struct exfat_chain cdir;
struct exfat_dir_entry info;
loff_t i_pos;
int err;
mutex_lock(&EXFAT_SB(sb)->s_lock);
exfat_set_volume_dirty(sb);
err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_FILE,
&info); /* 1 */
exfat_clear_volume_dirty(sb);
if (err)
goto unlock;
inode_inc_iversion(dir);
dir->i_ctime = dir->i_mtime = current_time(dir);
if (IS_DIRSYNC(dir))
exfat_sync_inode(dir);
else
mark_inode_dirty(dir);
i_pos = exfat_make_i_pos(&info);
inode = exfat_build_inode(sb, &info, i_pos); /* 2 */
err = PTR_ERR_OR_ZERO(inode);
if (err)
goto unlock;
inode_inc_iversion(inode);
inode->i_mtime = inode->i_atime = inode->i_ctime =
EXFAT_I(inode)->i_crtime = current_time(inode);
exfat_truncate_atime(&inode->i_atime);
/* timestamp is already written, so mark_inode_dirty() is unneeded. */
d_instantiate(dentry, inode); /* 3 */
unlock:
mutex_unlock(&EXFAT_SB(sb)->s_lock);
return err;
}exfat_create is used to create files under a directory. The first parameter is the inode corresponding to the directory, and the second parameter is the dentry corresponding to the file to be created.
What this function should do is to create a new file in the file system, and create an inode, which is associated with the corresponding dentry.
(1) Add an entry to the directory
(2) Create inodes
(3) Manage inode and denty
The main process of exfat_add_entry is as follows:
static int exfat_add_entry(struct inode *inode, const char *path,
struct exfat_chain *p_dir, unsigned int type,
struct exfat_dir_entry *info)
{
int ret, dentry, num_entries;
struct super_block *sb = inode->i_sb;
struct exfat_sb_info *sbi = EXFAT_SB(sb);
struct exfat_uni_name uniname;
struct exfat_chain clu;
int clu_size = 0;
unsigned int start_clu = EXFAT_FREE_CLUSTER;
ret = exfat_resolve_path(inode, path, p_dir, &uniname);
if (ret)
goto out;
num_entries = exfat_calc_num_entries(&uniname);
if (num_entries < 0) {
ret = num_entries;
goto out;
}
/* exfat_find_empty_entry must be called before alloc_cluster() */
dentry = exfat_find_empty_entry(inode, p_dir, num_entries); /* 1 */
if (dentry < 0) {
ret = dentry; /* -EIO or -ENOSPC */
goto out;
}
if (type == TYPE_DIR) {
ret = exfat_alloc_new_dir(inode, &clu);
if (ret)
goto out;
start_clu = clu.dir;
clu_size = sbi->cluster_size;
}
/* update the directory entry */
/* fill the dos name directory entry information of the created file.
* the first cluster is not determined yet. (0)
*/
ret = exfat_init_dir_entry(inode, p_dir, dentry, type,
start_clu, clu_size); /* 2 */
if (ret)
goto out;
ret = exfat_init_ext_entry(inode, p_dir, dentry, num_entries, &uniname);
if (ret)
goto out;
info->dir = *p_dir;
info->entry = dentry;
info->flags = ALLOC_NO_FAT_CHAIN;
info->type = type;
if (type == TYPE_FILE) {
info->attr = ATTR_ARCHIVE;
info->start_clu = EXFAT_EOF_CLUSTER;
info->size = 0;
info->num_subdirs = 0;
} else {
info->attr = ATTR_SUBDIR;
info->start_clu = start_clu;
info->size = clu_size;
info->num_subdirs = EXFAT_MIN_SUBDIR;
}
memset(&info->crtime, 0, sizeof(info->crtime));
memset(&info->mtime, 0, sizeof(info->mtime));
memset(&info->atime, 0, sizeof(info->atime));
out:
return ret;
}(1) Find a free entry in the directory. In this case, it will traverse the cluster of the entire directory until it finds an unused entry
(2) According to the found entry, initialize the relevant metadata