#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/file.h>
+#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
-#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
+#include <linux/pid_namespace.h>
+#include <linux/smp_lock.h>
#include <asm/poll.h>
#include <asm/siginfo.h>
#include <asm/uaccess.h>
-void fastcall set_close_on_exec(unsigned int fd, int flag)
+void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
return res;
}
-/*
- * locate_fd finds a free file descriptor in the open_fds fdset,
- * expanding the fd arrays if necessary. Must be called with the
- * file_lock held for write.
- */
-
-static int locate_fd(struct files_struct *files,
- struct file *file, unsigned int orig_start)
-{
- unsigned int newfd;
- unsigned int start;
- int error;
- struct fdtable *fdt;
-
- error = -EINVAL;
- if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
- goto out;
-
-repeat:
- fdt = files_fdtable(files);
- /*
- * Someone might have closed fd's in the range
- * orig_start..fdt->next_fd
- */
- start = orig_start;
- if (start < files->next_fd)
- start = files->next_fd;
-
- newfd = start;
- if (start < fdt->max_fdset) {
- newfd = find_next_zero_bit(fdt->open_fds->fds_bits,
- fdt->max_fdset, start);
- }
-
- error = -EMFILE;
- if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
- goto out;
-
- error = expand_files(files, newfd);
- if (error < 0)
- goto out;
-
- /*
- * If we needed to expand the fs array we
- * might have blocked - try again.
- */
- if (error)
- goto repeat;
-
- /*
- * We reacquired files_lock, so we are safe as long as
- * we reacquire the fdtable pointer and use it while holding
- * the lock, no one can free it during that time.
- */
- if (start <= files->next_fd)
- files->next_fd = newfd + 1;
-
- error = newfd;
-
-out:
- return error;
-}
-
-static int dupfd(struct file *file, unsigned int start)
-{
- struct files_struct * files = current->files;
- struct fdtable *fdt;
- int fd;
-
- spin_lock(&files->file_lock);
- fd = locate_fd(files, file, start);
- if (fd >= 0) {
- /* locate_fd() may have expanded fdtable, load the ptr */
- fdt = files_fdtable(files);
- FD_SET(fd, fdt->open_fds);
- FD_CLR(fd, fdt->close_on_exec);
- spin_unlock(&files->file_lock);
- fd_install(fd, file);
- } else {
- spin_unlock(&files->file_lock);
- fput(file);
- }
-
- return fd;
-}
-
-asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
+SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{
int err = -EBADF;
struct file * file, *tofree;
struct files_struct * files = current->files;
struct fdtable *fdt;
- spin_lock(&files->file_lock);
- if (!(file = fcheck(oldfd)))
- goto out_unlock;
- err = newfd;
- if (newfd == oldfd)
- goto out_unlock;
- err = -EBADF;
- if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
- goto out_unlock;
- get_file(file); /* We are now finished with oldfd */
-
- err = expand_files(files, newfd);
- if (err < 0)
- goto out_fput;
+ if ((flags & ~O_CLOEXEC) != 0)
+ return -EINVAL;
- /* To avoid races with open() and dup(), we will mark the fd as
- * in-use in the open-file bitmap throughout the entire dup2()
- * process. This is quite safe: do_close() uses the fd array
- * entry, not the bitmap, to decide what work needs to be
- * done. --sct */
- /* Doesn't work. open() might be there first. --AV */
+ if (unlikely(oldfd == newfd))
+ return -EINVAL;
- /* Yes. It's a race. In user space. Nothing sane to do */
+ spin_lock(&files->file_lock);
+ err = expand_files(files, newfd);
+ file = fcheck(oldfd);
+ if (unlikely(!file))
+ goto Ebadf;
+ if (unlikely(err < 0)) {
+ if (err == -EMFILE)
+ goto Ebadf;
+ goto out_unlock;
+ }
+ /*
+ * We need to detect attempts to do dup2() over allocated but still
+ * not finished descriptor. NB: OpenBSD avoids that at the price of
+ * extra work in their equivalent of fget() - they insert struct
+ * file immediately after grabbing descriptor, mark it larval if
+ * more work (e.g. actual opening) is needed and make sure that
+ * fget() treats larval files as absent. Potentially interesting,
+ * but while extra work in fget() is trivial, locking implications
+ * and amount of surgery on open()-related paths in VFS are not.
+ * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
+ * deadlocks in rather amusing ways, AFAICS. All of that is out of
+ * scope of POSIX or SUS, since neither considers shared descriptor
+ * tables and this condition does not arise without those.
+ */
err = -EBUSY;
fdt = files_fdtable(files);
tofree = fdt->fd[newfd];
if (!tofree && FD_ISSET(newfd, fdt->open_fds))
- goto out_fput;
-
+ goto out_unlock;
+ get_file(file);
rcu_assign_pointer(fdt->fd[newfd], file);
FD_SET(newfd, fdt->open_fds);
- FD_CLR(newfd, fdt->close_on_exec);
+ if (flags & O_CLOEXEC)
+ FD_SET(newfd, fdt->close_on_exec);
+ else
+ FD_CLR(newfd, fdt->close_on_exec);
spin_unlock(&files->file_lock);
if (tofree)
filp_close(tofree, files);
- err = newfd;
-out:
- return err;
+
+ return newfd;
+
+Ebadf:
+ err = -EBADF;
out_unlock:
spin_unlock(&files->file_lock);
- goto out;
+ return err;
+}
-out_fput:
- spin_unlock(&files->file_lock);
- fput(file);
- goto out;
+SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
+{
+ if (unlikely(newfd == oldfd)) { /* corner case */
+ struct files_struct *files = current->files;
+ int retval = oldfd;
+
+ rcu_read_lock();
+ if (!fcheck_files(files, oldfd))
+ retval = -EBADF;
+ rcu_read_unlock();
+ return retval;
+ }
+ return sys_dup3(oldfd, newfd, 0);
}
-asmlinkage long sys_dup(unsigned int fildes)
+SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
int ret = -EBADF;
- struct file * file = fget(fildes);
-
- if (file)
- ret = dupfd(file, 0);
+ struct file *file = fget(fildes);
+
+ if (file) {
+ ret = get_unused_fd();
+ if (ret >= 0)
+ fd_install(ret, file);
+ else
+ fput(file);
+ }
return ret;
}
-#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | FASYNC | O_DIRECT | O_NOATIME)
+#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
static int setfl(int fd, struct file * filp, unsigned long arg)
{
- struct inode * inode = filp->f_dentry->d_inode;
+ struct inode * inode = filp->f_path.dentry->d_inode;
int error = 0;
/*
/* O_NOATIME can only be set by the owner or superuser */
if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
- if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EPERM;
/* required for strict SunOS emulation */
if (error)
return error;
- lock_kernel();
- if ((arg ^ filp->f_flags) & FASYNC) {
- if (filp->f_op && filp->f_op->fasync) {
- error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
- if (error < 0)
- goto out;
- }
+ /*
+ * ->fasync() is responsible for setting the FASYNC bit.
+ */
+ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op &&
+ filp->f_op->fasync) {
+ error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
+ if (error < 0)
+ goto out;
+ if (error > 0)
+ error = 0;
}
-
+ spin_lock(&filp->f_lock);
filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
+ spin_unlock(&filp->f_lock);
+
out:
- unlock_kernel();
return error;
}
-static void f_modown(struct file *filp, unsigned long pid,
+static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
uid_t uid, uid_t euid, int force)
{
write_lock_irq(&filp->f_owner.lock);
if (force || !filp->f_owner.pid) {
- filp->f_owner.pid = pid;
+ put_pid(filp->f_owner.pid);
+ filp->f_owner.pid = get_pid(pid);
+ filp->f_owner.pid_type = type;
filp->f_owner.uid = uid;
filp->f_owner.euid = euid;
}
write_unlock_irq(&filp->f_owner.lock);
}
-int f_setown(struct file *filp, unsigned long arg, int force)
+int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
+ int force)
{
+ const struct cred *cred = current_cred();
int err;
err = security_file_set_fowner(filp);
if (err)
return err;
- f_modown(filp, arg, current->uid, current->euid, force);
+ f_modown(filp, pid, type, cred->uid, cred->euid, force);
return 0;
}
+EXPORT_SYMBOL(__f_setown);
+int f_setown(struct file *filp, unsigned long arg, int force)
+{
+ enum pid_type type;
+ struct pid *pid;
+ int who = arg;
+ int result;
+ type = PIDTYPE_PID;
+ if (who < 0) {
+ type = PIDTYPE_PGID;
+ who = -who;
+ }
+ rcu_read_lock();
+ pid = find_vpid(who);
+ result = __f_setown(filp, pid, type, force);
+ rcu_read_unlock();
+ return result;
+}
EXPORT_SYMBOL(f_setown);
void f_delown(struct file *filp)
{
- f_modown(filp, 0, 0, 0, 1);
+ f_modown(filp, NULL, PIDTYPE_PID, 0, 0, 1);
+}
+
+pid_t f_getown(struct file *filp)
+{
+ pid_t pid;
+ read_lock(&filp->f_owner.lock);
+ pid = pid_vnr(filp->f_owner.pid);
+ if (filp->f_owner.pid_type == PIDTYPE_PGID)
+ pid = -pid;
+ read_unlock(&filp->f_owner.lock);
+ return pid;
}
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
switch (cmd) {
case F_DUPFD:
- get_file(filp);
- err = dupfd(filp, arg);
+ case F_DUPFD_CLOEXEC:
+ if (arg >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
+ break;
+ err = alloc_fd(arg, cmd == F_DUPFD_CLOEXEC ? O_CLOEXEC : 0);
+ if (err >= 0) {
+ get_file(filp);
+ fd_install(err, filp);
+ }
break;
case F_GETFD:
err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
* current syscall conventions, the only way
* to fix this will be in libc.
*/
- err = filp->f_owner.pid;
+ err = f_getown(filp);
force_successful_syscall_return();
break;
case F_SETOWN:
return err;
}
-asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg)
+SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
struct file *filp;
long err = -EBADF;
}
#if BITS_PER_LONG == 32
-asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg)
+SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+ unsigned long, arg)
{
struct file * filp;
long err;
static inline int sigio_perm(struct task_struct *p,
struct fown_struct *fown, int sig)
{
- return (((fown->euid == 0) ||
- (fown->euid == p->suid) || (fown->euid == p->uid) ||
- (fown->uid == p->suid) || (fown->uid == p->uid)) &&
- !security_file_send_sigiotask(p, fown, sig));
+ const struct cred *cred;
+ int ret;
+
+ rcu_read_lock();
+ cred = __task_cred(p);
+ ret = ((fown->euid == 0 ||
+ fown->euid == cred->suid || fown->euid == cred->uid ||
+ fown->uid == cred->suid || fown->uid == cred->uid) &&
+ !security_file_send_sigiotask(p, fown, sig));
+ rcu_read_unlock();
+ return ret;
}
static void send_sigio_to_task(struct task_struct *p,
/* Make sure we are called with one of the POLL_*
reasons, otherwise we could leak kernel stack into
userspace. */
- if ((reason & __SI_MASK) != __SI_POLL)
- BUG();
+ BUG_ON((reason & __SI_MASK) != __SI_POLL);
if (reason - POLL_IN >= NSIGPOLL)
si.si_band = ~0L;
else
void send_sigio(struct fown_struct *fown, int fd, int band)
{
struct task_struct *p;
- int pid;
+ enum pid_type type;
+ struct pid *pid;
read_lock(&fown->lock);
+ type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
read_lock(&tasklist_lock);
- if (pid > 0) {
- p = find_task_by_pid(pid);
- if (p) {
- send_sigio_to_task(p, fown, fd, band);
- }
- } else {
- do_each_task_pid(-pid, PIDTYPE_PGID, p) {
- send_sigio_to_task(p, fown, fd, band);
- } while_each_task_pid(-pid, PIDTYPE_PGID, p);
- }
+ do_each_pid_task(pid, type, p) {
+ send_sigio_to_task(p, fown, fd, band);
+ } while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
out_unlock_fown:
read_unlock(&fown->lock);
int send_sigurg(struct fown_struct *fown)
{
struct task_struct *p;
- int pid, ret = 0;
+ enum pid_type type;
+ struct pid *pid;
+ int ret = 0;
read_lock(&fown->lock);
+ type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
ret = 1;
read_lock(&tasklist_lock);
- if (pid > 0) {
- p = find_task_by_pid(pid);
- if (p) {
- send_sigurg_to_task(p, fown);
- }
- } else {
- do_each_task_pid(-pid, PIDTYPE_PGID, p) {
- send_sigurg_to_task(p, fown);
- } while_each_task_pid(-pid, PIDTYPE_PGID, p);
- }
+ do_each_pid_task(pid, type, p) {
+ send_sigurg_to_task(p, fown);
+ } while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
out_unlock_fown:
read_unlock(&fown->lock);
}
static DEFINE_RWLOCK(fasync_lock);
-static kmem_cache_t *fasync_cache __read_mostly;
+static struct kmem_cache *fasync_cache __read_mostly;
/*
- * fasync_helper() is used by some character device drivers (mainly mice)
+ * fasync_helper() is used by almost all character device drivers
* to set up the fasync queue. It returns negative on error, 0 if it did
* no changes and positive if it added/deleted the entry.
*/
int result = 0;
if (on) {
- new = kmem_cache_alloc(fasync_cache, SLAB_KERNEL);
+ new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
if (!new)
return -ENOMEM;
}
+
+ /*
+ * We need to take f_lock first since it's not an IRQ-safe
+ * lock.
+ */
+ spin_lock(&filp->f_lock);
write_lock_irq(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
if (fa->fa_file == filp) {
result = 1;
}
out:
+ if (on)
+ filp->f_flags |= FASYNC;
+ else
+ filp->f_flags &= ~FASYNC;
write_unlock_irq(&fasync_lock);
+ spin_unlock(&filp->f_lock);
return result;
}
static int __init fasync_init(void)
{
fasync_cache = kmem_cache_create("fasync_cache",
- sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL, NULL);
+ sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
return 0;
}