linux/fs/proc/fd.c

365 lines
7.7 KiB
C
Raw Normal View History

#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/dcache.h>
#include <linux/path.h>
#include <linux/fdtable.h>
#include <linux/namei.h>
#include <linux/pid.h>
#include <linux/security.h>
#include <linux/file.h>
#include <linux/seq_file.h>
proc: show locks in /proc/pid/fdinfo/X Let's show locks which are associated with a file descriptor in its fdinfo file. Currently we don't have a reliable way to determine who holds a lock. We can find some information in /proc/locks, but PID which is reported there can be wrong. For example, a process takes a lock, then forks a child and dies. In this case /proc/locks contains the parent pid, which can be reused by another process. $ cat /proc/locks ... 6: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF ... $ ps -C rpcbind PID TTY TIME CMD 332 ? 00:00:00 rpcbind $ cat /proc/332/fdinfo/4 pos: 0 flags: 0100000 mnt_id: 22 lock: 1: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF $ ls -l /proc/332/fd/4 lr-x------ 1 root root 64 Mar 5 14:43 /proc/332/fd/4 -> /run/rpcbind.lock $ ls -l /proc/324/fd/ total 0 lrwx------ 1 root root 64 Feb 27 14:50 0 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:50 1 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:49 2 -> /dev/pts/0 You can see that the process with the 324 pid doesn't hold the lock. This information is required for proper dumping and restoring file locks. Signed-off-by: Andrey Vagin <avagin@openvz.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Acked-by: Jeff Layton <jlayton@poochiereds.net> Acked-by: "J. Bruce Fields" <bfields@fieldses.org> Acked-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-17 03:49:38 +08:00
#include <linux/fs.h>
#include <linux/proc_fs.h>
#include "../mount.h"
#include "internal.h"
#include "fd.h"
static int seq_show(struct seq_file *m, void *v)
{
struct files_struct *files = NULL;
int f_flags = 0, ret = -ENOENT;
struct file *file = NULL;
struct task_struct *task;
task = get_proc_task(m->private);
if (!task)
return -ENOENT;
files = get_files_struct(task);
put_task_struct(task);
if (files) {
unsigned int fd = proc_fd(m->private);
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (file) {
struct fdtable *fdt = files_fdtable(files);
f_flags = file->f_flags;
if (close_on_exec(fd, fdt))
f_flags |= O_CLOEXEC;
get_file(file);
ret = 0;
}
spin_unlock(&files->file_lock);
put_files_struct(files);
}
proc: show locks in /proc/pid/fdinfo/X Let's show locks which are associated with a file descriptor in its fdinfo file. Currently we don't have a reliable way to determine who holds a lock. We can find some information in /proc/locks, but PID which is reported there can be wrong. For example, a process takes a lock, then forks a child and dies. In this case /proc/locks contains the parent pid, which can be reused by another process. $ cat /proc/locks ... 6: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF ... $ ps -C rpcbind PID TTY TIME CMD 332 ? 00:00:00 rpcbind $ cat /proc/332/fdinfo/4 pos: 0 flags: 0100000 mnt_id: 22 lock: 1: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF $ ls -l /proc/332/fd/4 lr-x------ 1 root root 64 Mar 5 14:43 /proc/332/fd/4 -> /run/rpcbind.lock $ ls -l /proc/324/fd/ total 0 lrwx------ 1 root root 64 Feb 27 14:50 0 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:50 1 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:49 2 -> /dev/pts/0 You can see that the process with the 324 pid doesn't hold the lock. This information is required for proper dumping and restoring file locks. Signed-off-by: Andrey Vagin <avagin@openvz.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Acked-by: Jeff Layton <jlayton@poochiereds.net> Acked-by: "J. Bruce Fields" <bfields@fieldses.org> Acked-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-17 03:49:38 +08:00
if (ret)
return ret;
seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
(long long)file->f_pos, f_flags,
real_mount(file->f_path.mnt)->mnt_id);
show_fd_locks(m, file, files);
if (seq_has_overflowed(m))
goto out;
if (file->f_op->show_fdinfo)
file->f_op->show_fdinfo(m, file);
proc: show locks in /proc/pid/fdinfo/X Let's show locks which are associated with a file descriptor in its fdinfo file. Currently we don't have a reliable way to determine who holds a lock. We can find some information in /proc/locks, but PID which is reported there can be wrong. For example, a process takes a lock, then forks a child and dies. In this case /proc/locks contains the parent pid, which can be reused by another process. $ cat /proc/locks ... 6: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF ... $ ps -C rpcbind PID TTY TIME CMD 332 ? 00:00:00 rpcbind $ cat /proc/332/fdinfo/4 pos: 0 flags: 0100000 mnt_id: 22 lock: 1: FLOCK ADVISORY WRITE 324 00:13:13431 0 EOF $ ls -l /proc/332/fd/4 lr-x------ 1 root root 64 Mar 5 14:43 /proc/332/fd/4 -> /run/rpcbind.lock $ ls -l /proc/324/fd/ total 0 lrwx------ 1 root root 64 Feb 27 14:50 0 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:50 1 -> /dev/pts/0 lrwx------ 1 root root 64 Feb 27 14:49 2 -> /dev/pts/0 You can see that the process with the 324 pid doesn't hold the lock. This information is required for proper dumping and restoring file locks. Signed-off-by: Andrey Vagin <avagin@openvz.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Acked-by: Jeff Layton <jlayton@poochiereds.net> Acked-by: "J. Bruce Fields" <bfields@fieldses.org> Acked-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-17 03:49:38 +08:00
out:
fput(file);
return 0;
}
static int seq_fdinfo_open(struct inode *inode, struct file *file)
{
return single_open(file, seq_show, inode);
}
static const struct file_operations proc_fdinfo_file_operations = {
.open = seq_fdinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
{
struct files_struct *files;
struct task_struct *task;
const struct cred *cred;
struct inode *inode;
unsigned int fd;
if (flags & LOOKUP_RCU)
return -ECHILD;
inode = d_inode(dentry);
task = get_proc_task(inode);
fd = proc_fd(inode);
if (task) {
files = get_files_struct(task);
if (files) {
struct file *file;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
unsigned f_mode = file->f_mode;
rcu_read_unlock();
put_files_struct(files);
if (task_dumpable(task)) {
rcu_read_lock();
cred = __task_cred(task);
inode->i_uid = cred->euid;
inode->i_gid = cred->egid;
rcu_read_unlock();
} else {
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
}
if (S_ISLNK(inode->i_mode)) {
unsigned i_mode = S_IFLNK;
if (f_mode & FMODE_READ)
i_mode |= S_IRUSR | S_IXUSR;
if (f_mode & FMODE_WRITE)
i_mode |= S_IWUSR | S_IXUSR;
inode->i_mode = i_mode;
}
security_task_to_inode(task, inode);
put_task_struct(task);
return 1;
}
rcu_read_unlock();
put_files_struct(files);
}
put_task_struct(task);
}
return 0;
}
static const struct dentry_operations tid_fd_dentry_operations = {
.d_revalidate = tid_fd_revalidate,
.d_delete = pid_delete_dentry,
};
static int proc_fd_link(struct dentry *dentry, struct path *path)
{
struct files_struct *files = NULL;
struct task_struct *task;
int ret = -ENOENT;
task = get_proc_task(d_inode(dentry));
if (task) {
files = get_files_struct(task);
put_task_struct(task);
}
if (files) {
unsigned int fd = proc_fd(d_inode(dentry));
struct file *fd_file;
spin_lock(&files->file_lock);
fd_file = fcheck_files(files, fd);
if (fd_file) {
*path = fd_file->f_path;
path_get(&fd_file->f_path);
ret = 0;
}
spin_unlock(&files->file_lock);
put_files_struct(files);
}
return ret;
}
static int
proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
struct task_struct *task, const void *ptr)
{
unsigned fd = (unsigned long)ptr;
struct proc_inode *ei;
struct inode *inode;
inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK);
if (!inode)
goto out;
ei = PROC_I(inode);
ei->fd = fd;
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (tid_fd_revalidate(dentry, 0))
return 0;
out:
return -ENOENT;
}
static struct dentry *proc_lookupfd_common(struct inode *dir,
struct dentry *dentry,
instantiate_t instantiate)
{
struct task_struct *task = get_proc_task(dir);
int result = -ENOENT;
unsigned fd = name_to_int(&dentry->d_name);
if (!task)
goto out_no_task;
if (fd == ~0U)
goto out;
result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
out:
put_task_struct(task);
out_no_task:
return ERR_PTR(result);
}
static int proc_readfd_common(struct file *file, struct dir_context *ctx,
instantiate_t instantiate)
{
struct task_struct *p = get_proc_task(file_inode(file));
struct files_struct *files;
unsigned int fd;
if (!p)
return -ENOENT;
if (!dir_emit_dots(file, ctx))
goto out;
files = get_files_struct(p);
if (!files)
goto out;
rcu_read_lock();
for (fd = ctx->pos - 2;
fd < files_fdtable(files)->max_fds;
fd++, ctx->pos++) {
char name[PROC_NUMBUF];
int len;
if (!fcheck_files(files, fd))
continue;
rcu_read_unlock();
len = snprintf(name, sizeof(name), "%u", fd);
if (!proc_fill_cache(file, ctx,
name, len, instantiate, p,
(void *)(unsigned long)fd))
goto out_fd_loop;
cond_resched();
rcu_read_lock();
}
rcu_read_unlock();
out_fd_loop:
put_files_struct(files);
out:
put_task_struct(p);
return 0;
}
static int proc_readfd(struct file *file, struct dir_context *ctx)
{
return proc_readfd_common(file, ctx, proc_fd_instantiate);
}
const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
.iterate_shared = proc_readfd,
.llseek = generic_file_llseek,
};
static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
}
/*
* /proc/pid/fd needs a special permission handler so that a process can still
* access /proc/self/fd after it has executed a setuid().
*/
int proc_fd_permission(struct inode *inode, int mask)
{
struct task_struct *p;
int rv;
rv = generic_permission(inode, mask);
if (rv == 0)
return rv;
rcu_read_lock();
p = pid_task(proc_pid(inode), PIDTYPE_PID);
if (p && same_thread_group(p, current))
rv = 0;
rcu_read_unlock();
return rv;
}
const struct inode_operations proc_fd_inode_operations = {
.lookup = proc_lookupfd,
.permission = proc_fd_permission,
.setattr = proc_setattr,
};
static int
proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
struct task_struct *task, const void *ptr)
{
unsigned fd = (unsigned long)ptr;
struct proc_inode *ei;
struct inode *inode;
inode = proc_pid_make_inode(dir->i_sb, task, S_IFREG | S_IRUSR);
if (!inode)
goto out;
ei = PROC_I(inode);
ei->fd = fd;
inode->i_fop = &proc_fdinfo_file_operations;
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (tid_fd_revalidate(dentry, 0))
return 0;
out:
return -ENOENT;
}
static struct dentry *
proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
}
static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
{
return proc_readfd_common(file, ctx,
proc_fdinfo_instantiate);
}
const struct inode_operations proc_fdinfo_inode_operations = {
.lookup = proc_lookupfdinfo,
.setattr = proc_setattr,
};
const struct file_operations proc_fdinfo_operations = {
.read = generic_read_dir,
.iterate_shared = proc_readfdinfo,
.llseek = generic_file_llseek,
};