move compat select-related syscalls to fs/select.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 419 insertions, 2 deletions

diff --git a/fs/select.c b/fs/select.c
index e2112270d75a..dd70937ddb60 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -338,6 +338,53 @@ sticky:
 	return ret;
 }
 
+/*
+ * Scalable version of the fd_set.
+ */
+
+typedef struct {
+	unsigned long *in, *out, *ex;
+	unsigned long *res_in, *res_out, *res_ex;
+} fd_set_bits;
+
+/*
+ * How many longwords for "nr" bits?
+ */
+#define FDS_BITPERLONG	(8*sizeof(long))
+#define FDS_LONGS(nr)	(((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
+#define FDS_BYTES(nr)	(FDS_LONGS(nr)*sizeof(long))
+
+/*
+ * We do a VERIFY_WRITE here even though we are only reading this time:
+ * we'll write to it eventually..
+ *
+ * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
+ */
+static inline
+int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	nr = FDS_BYTES(nr);
+	if (ufdset)
+		return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
+
+	memset(fdset, 0, nr);
+	return 0;
+}
+
+static inline unsigned long __must_check
+set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	if (ufdset)
+		return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
+	return 0;
+}
+
+static inline
+void zero_fd_set(unsigned long nr, unsigned long *fdset)
+{
+	memset(fdset, 0, FDS_BYTES(nr));
+}
+
 #define FDS_IN(fds, n)		(fds->in + n)
 #define FDS_OUT(fds, n)		(fds->out + n)
 #define FDS_EX(fds, n)		(fds->ex + n)
@@ -401,7 +448,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
 		wait->_key |= POLLOUT_SET;
 }
 
-int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 {
 	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
@@ -881,7 +928,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list))  / \
 			sizeof(struct pollfd))
 
-int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
+static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
@@ -1053,3 +1100,373 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
+
+static
+int compat_poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec ts;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&ts);
+	ts = timespec_sub(*end_time, ts);
+	if (ts.tv_sec < 0)
+		ts.tv_sec = ts.tv_nsec = 0;
+
+	if (timeval) {
+		struct compat_timeval rtv;
+
+		rtv.tv_sec = ts.tv_sec;
+		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+	} else {
+		struct compat_timespec rts;
+
+		rts.tv_sec = ts.tv_sec;
+		rts.tv_nsec = ts.tv_nsec;
+
+		if (!copy_to_user(p, &rts, sizeof(rts)))
+			return ret;
+	}
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
+/*
+ * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
+ * 64-bit unsigned longs.
+ */
+static
+int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+			unsigned long *fdset)
+{
+	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
+	if (ufdset) {
+		unsigned long odd;
+
+		if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t)))
+			return -EFAULT;
+
+		odd = nr & 1UL;
+		nr &= ~1UL;
+		while (nr) {
+			unsigned long h, l;
+			if (__get_user(l, ufdset) || __get_user(h, ufdset+1))
+				return -EFAULT;
+			ufdset += 2;
+			*fdset++ = h << 32 | l;
+			nr -= 2;
+		}
+		if (odd && __get_user(*fdset, ufdset))
+			return -EFAULT;
+	} else {
+		/* Tricky, must clear full unsigned long in the
+		 * kernel fdset at the end, this makes sure that
+		 * actually happens.
+		 */
+		memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t));
+	}
+	return 0;
+}
+
+static
+int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+		      unsigned long *fdset)
+{
+	unsigned long odd;
+	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
+
+	if (!ufdset)
+		return 0;
+
+	odd = nr & 1UL;
+	nr &= ~1UL;
+	while (nr) {
+		unsigned long h, l;
+		l = *fdset++;
+		h = l >> 32;
+		if (__put_user(l, ufdset) || __put_user(h, ufdset+1))
+			return -EFAULT;
+		ufdset += 2;
+		nr -= 2;
+	}
+	if (odd && __put_user(*fdset, ufdset))
+		return -EFAULT;
+	return 0;
+}
+
+
+/*
+ * This is a virtual copy of sys_select from fs/select.c and probably
+ * should be compared to it from time to time
+ */
+
+/*
+ * We can actually return ERESTARTSYS instead of EINTR, but I'd
+ * like to be certain this leads to no problems. So I return
+ * EINTR just for safety.
+ *
+ * Update: ERESTARTSYS breaks at least the xview clock binary, so
+ * I'm trying ERESTARTNOHAND which restart only when you want to.
+ */
+static int compat_core_sys_select(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct timespec *end_time)
+{
+	fd_set_bits fds;
+	void *bits;
+	int size, max_fds, ret = -EINVAL;
+	struct fdtable *fdt;
+	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
+
+	if (n < 0)
+		goto out_nofds;
+
+	/* max_fds can increase, so grab it once to avoid race */
+	rcu_read_lock();
+	fdt = files_fdtable(current->files);
+	max_fds = fdt->max_fds;
+	rcu_read_unlock();
+	if (n > max_fds)
+		n = max_fds;
+
+	/*
+	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
+	 * since we used fdset we need to allocate memory in units of
+	 * long-words.
+	 */
+	size = FDS_BYTES(n);
+	bits = stack_fds;
+	if (size > sizeof(stack_fds) / 6) {
+		bits = kmalloc(6 * size, GFP_KERNEL);
+		ret = -ENOMEM;
+		if (!bits)
+			goto out_nofds;
+	}
+	fds.in      = (unsigned long *)  bits;
+	fds.out     = (unsigned long *) (bits +   size);
+	fds.ex      = (unsigned long *) (bits + 2*size);
+	fds.res_in  = (unsigned long *) (bits + 3*size);
+	fds.res_out = (unsigned long *) (bits + 4*size);
+	fds.res_ex  = (unsigned long *) (bits + 5*size);
+
+	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
+	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
+	    (ret = compat_get_fd_set(n, exp, fds.ex)))
+		goto out;
+	zero_fd_set(n, fds.res_in);
+	zero_fd_set(n, fds.res_out);
+	zero_fd_set(n, fds.res_ex);
+
+	ret = do_select(n, &fds, end_time);
+
+	if (ret < 0)
+		goto out;
+	if (!ret) {
+		ret = -ERESTARTNOHAND;
+		if (signal_pending(current))
+			goto out;
+		ret = 0;
+	}
+
+	if (compat_set_fd_set(n, inp, fds.res_in) ||
+	    compat_set_fd_set(n, outp, fds.res_out) ||
+	    compat_set_fd_set(n, exp, fds.res_ex))
+		ret = -EFAULT;
+out:
+	if (bits != stack_fds)
+		kfree(bits);
+out_nofds:
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timeval __user *, tvp)
+{
+	struct timespec end_time, *to = NULL;
+	struct compat_timeval tv;
+	int ret;
+
+	if (tvp) {
+		if (copy_from_user(&tv, tvp, sizeof(tv)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to,
+				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
+				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
+			return -EINVAL;
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret);
+
+	return ret;
+}
+
+struct compat_sel_arg_struct {
+	compat_ulong_t n;
+	compat_uptr_t inp;
+	compat_uptr_t outp;
+	compat_uptr_t exp;
+	compat_uptr_t tvp;
+};
+
+COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
+{
+	struct compat_sel_arg_struct a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+	return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
+				 compat_ptr(a.exp), compat_ptr(a.tvp));
+}
+
+static long do_compat_pselect(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
+	compat_size_t sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	if (ret == -ERESTARTNOHAND) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+					sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timespec __user *, tsp, void __user *, sig)
+{
+	compat_size_t sigsetsize = 0;
+	compat_uptr_t up = 0;
+
+	if (sig) {
+		if (!access_ok(VERIFY_READ, sig,
+				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
+		    	__get_user(up, (compat_uptr_t __user *)sig) ||
+		    	__get_user(sigsetsize,
+				(compat_size_t __user *)(sig+sizeof(up))))
+			return -EFAULT;
+	}
+	return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
+				 sigsetsize);
+}
+
+COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
+	unsigned int,  nfds, struct compat_timespec __user *, tsp,
+	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_sys_poll(ufds, nfds, to);
+
+	/* We can restart this syscall, usually */
+	if (ret == -EINTR) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+				sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+		ret = -ERESTARTNOHAND;
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	return ret;
+}
+#endif