mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Eric W. Biederman](/assets/img/avatar_default.png)
When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Now that get_files_struct has no more users and can not cause the problems for posix file locking and fget_light remove get_files_struct so that it does not gain any new users. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> v1: https://lkml.kernel.org/r/20200817220425.9389-13-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-24-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
134 lines
3.6 KiB
C
134 lines
3.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* descriptor table internals; you almost certainly want file.h instead.
|
|
*/
|
|
|
|
#ifndef __LINUX_FDTABLE_H
|
|
#define __LINUX_FDTABLE_H
|
|
|
|
#include <linux/posix_types.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/nospec.h>
|
|
#include <linux/types.h>
|
|
#include <linux/init.h>
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/atomic.h>
|
|
|
|
/*
|
|
* The default fd array needs to be at least BITS_PER_LONG,
|
|
* as this is the granularity returned by copy_fdset().
|
|
*/
|
|
#define NR_OPEN_DEFAULT BITS_PER_LONG
|
|
#define NR_OPEN_MAX ~0U
|
|
|
|
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;
|
|
};
|
|
|
|
static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt)
|
|
{
|
|
return test_bit(fd, fdt->close_on_exec);
|
|
}
|
|
|
|
static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
|
|
{
|
|
return test_bit(fd, fdt->open_fds);
|
|
}
|
|
|
|
/*
|
|
* 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];
|
|
};
|
|
|
|
struct file_operations;
|
|
struct vfsmount;
|
|
struct dentry;
|
|
|
|
#define rcu_dereference_check_fdtable(files, fdtfd) \
|
|
rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock))
|
|
|
|
#define files_fdtable(files) \
|
|
rcu_dereference_check_fdtable((files), (files)->fdt)
|
|
|
|
/*
|
|
* The caller must ensure that fd table isn't shared or hold rcu or file lock
|
|
*/
|
|
static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
|
|
{
|
|
struct fdtable *fdt = rcu_dereference_raw(files->fdt);
|
|
|
|
if (fd < fdt->max_fds) {
|
|
fd = array_index_nospec(fd, fdt->max_fds);
|
|
return rcu_dereference_raw(fdt->fd[fd]);
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
|
|
{
|
|
RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock),
|
|
"suspicious rcu_dereference_check() usage");
|
|
return files_lookup_fd_raw(files, fd);
|
|
}
|
|
|
|
static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd)
|
|
{
|
|
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
|
|
"suspicious rcu_dereference_check() usage");
|
|
return files_lookup_fd_raw(files, fd);
|
|
}
|
|
|
|
static inline struct file *lookup_fd_rcu(unsigned int fd)
|
|
{
|
|
return files_lookup_fd_rcu(current->files, fd);
|
|
}
|
|
|
|
struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd);
|
|
struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd);
|
|
|
|
struct task_struct;
|
|
|
|
void put_files_struct(struct files_struct *fs);
|
|
int unshare_files(void);
|
|
struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
|
|
void do_close_on_exec(struct files_struct *);
|
|
int iterate_fd(struct files_struct *, unsigned,
|
|
int (*)(const void *, struct file *, unsigned),
|
|
const void *);
|
|
|
|
extern int close_fd(unsigned int fd);
|
|
extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
|
|
extern int close_fd_get_file(unsigned int fd, struct file **res);
|
|
extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
|
|
struct files_struct **new_fdp);
|
|
|
|
extern struct kmem_cache *files_cachep;
|
|
|
|
#endif /* __LINUX_FDTABLE_H */
|