Merge branch 'syscalls-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux

Pull removal of in-kernel calls to syscalls from Dominik Brodowski:
 "System calls are interaction points between userspace and the kernel.
  Therefore, system call functions such as sys_xyzzy() or
  compat_sys_xyzzy() should only be called from userspace via the
  syscall table, but not from elsewhere in the kernel.

  At least on 64-bit x86, it will likely be a hard requirement from
  v4.17 onwards to not call system call functions in the kernel: It is
  better to use use a different calling convention for system calls
  there, where struct pt_regs is decoded on-the-fly in a syscall wrapper
  which then hands processing over to the actual syscall function. This
  means that only those parameters which are actually needed for a
  specific syscall are passed on during syscall entry, instead of
  filling in six CPU registers with random user space content all the
  time (which may cause serious trouble down the call chain). Those
  x86-specific patches will be pushed through the x86 tree in the near
  future.

  Moreover, rules on how data may be accessed may differ between kernel
  data and user data. This is another reason why calling sys_xyzzy() is
  generally a bad idea, and -- at most -- acceptable in arch-specific
  code.

  This patchset removes all in-kernel calls to syscall functions in the
  kernel with the exception of arch/. On top of this, it cleans up the
  three places where many syscalls are referenced or prototyped, namely
  kernel/sys_ni.c, include/linux/syscalls.h and include/linux/compat.h"

* 'syscalls-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux: (109 commits)
  bpf: whitelist all syscalls for error injection
  kernel/sys_ni: remove {sys_,sys_compat} from cond_syscall definitions
  kernel/sys_ni: sort cond_syscall() entries
  syscalls/x86: auto-create compat_sys_*() prototypes
  syscalls: sort syscall prototypes in include/linux/compat.h
  net: remove compat_sys_*() prototypes from net/compat.h
  syscalls: sort syscall prototypes in include/linux/syscalls.h
  kexec: move sys_kexec_load() prototype to syscalls.h
  x86/sigreturn: use SYSCALL_DEFINE0
  x86: fix sys_sigreturn() return type to be long, not unsigned long
  x86/ioport: add ksys_ioperm() helper; remove in-kernel calls to sys_ioperm()
  mm: add ksys_readahead() helper; remove in-kernel calls to sys_readahead()
  mm: add ksys_mmap_pgoff() helper; remove in-kernel calls to sys_mmap_pgoff()
  mm: add ksys_fadvise64_64() helper; remove in-kernel call to sys_fadvise64_64()
  fs: add ksys_fallocate() wrapper; remove in-kernel calls to sys_fallocate()
  fs: add ksys_p{read,write}64() helpers; remove in-kernel calls to syscalls
  fs: add ksys_truncate() wrapper; remove in-kernel calls to sys_truncate()
  fs: add ksys_sync_file_range helper(); remove in-kernel calls to syscall
  kernel: add ksys_setsid() helper; remove in-kernel call to sys_setsid()
  kernel: add ksys_unshare() helper; remove in-kernel calls to sys_unshare()
  ...

1 files changed, 63 insertions, 11 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index f2289de20e19..ad692183dfe9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -69,6 +69,8 @@
 #include <asm/io.h>
 #include <asm/unistd.h>
 
+#include "uid16.h"
+
 #ifndef SET_UNALIGN_CTL
 # define SET_UNALIGN_CTL(a, b)	(-EINVAL)
 #endif
@@ -340,7 +342,7 @@ out_unlock:
  *      operations (as far as semantic preservation is concerned).
  */
 #ifdef CONFIG_MULTIUSER
-SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
+long __sys_setregid(gid_t rgid, gid_t egid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -392,12 +394,17 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
+{
+	return __sys_setregid(rgid, egid);
+}
+
 /*
  * setgid() is implemented like SysV w/ SAVED_IDS
  *
  * SMP: Same implicit races as above.
  */
-SYSCALL_DEFINE1(setgid, gid_t, gid)
+long __sys_setgid(gid_t gid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -429,6 +436,11 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE1(setgid, gid_t, gid)
+{
+	return __sys_setgid(gid);
+}
+
 /*
  * change the user struct in a credentials set to match the new UID
  */
@@ -473,7 +485,7 @@ static int set_user(struct cred *new)
  * 100% compatible with BSD.  A program which uses just setuid() will be
  * 100% compatible with POSIX with saved IDs.
  */
-SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
+long __sys_setreuid(uid_t ruid, uid_t euid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -533,6 +545,11 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
+{
+	return __sys_setreuid(ruid, euid);
+}
+
 /*
  * setuid() is implemented like SysV with SAVED_IDS
  *
@@ -544,7 +561,7 @@ error:
  * will allow a root program to temporarily drop privileges and be able to
  * regain them by swapping the real and effective uid.
  */
-SYSCALL_DEFINE1(setuid, uid_t, uid)
+long __sys_setuid(uid_t uid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -586,12 +603,17 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE1(setuid, uid_t, uid)
+{
+	return __sys_setuid(uid);
+}
+
 
 /*
  * This function implements a generic ability to update ruid, euid,
  * and suid.  This allows you to implement the 4.4 compatible seteuid().
  */
-SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
+long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -656,6 +678,11 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
+{
+	return __sys_setresuid(ruid, euid, suid);
+}
+
 SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
 {
 	const struct cred *cred = current_cred();
@@ -678,7 +705,7 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t _
 /*
  * Same as above, but for rgid, egid, sgid.
  */
-SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
+long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 {
 	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
@@ -730,6 +757,11 @@ error:
 	return retval;
 }
 
+SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
+{
+	return __sys_setresgid(rgid, egid, sgid);
+}
+
 SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
 {
 	const struct cred *cred = current_cred();
@@ -757,7 +789,7 @@ SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t _
  * whatever uid it wants to). It normally shadows "euid", except when
  * explicitly set by setfsuid() or for access..
  */
-SYSCALL_DEFINE1(setfsuid, uid_t, uid)
+long __sys_setfsuid(uid_t uid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -793,10 +825,15 @@ change_okay:
 	return old_fsuid;
 }
 
+SYSCALL_DEFINE1(setfsuid, uid_t, uid)
+{
+	return __sys_setfsuid(uid);
+}
+
 /*
  * Samma på svenska..
  */
-SYSCALL_DEFINE1(setfsgid, gid_t, gid)
+long __sys_setfsgid(gid_t gid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -830,6 +867,11 @@ change_okay:
 	commit_creds(new);
 	return old_fsgid;
 }
+
+SYSCALL_DEFINE1(setfsgid, gid_t, gid)
+{
+	return __sys_setfsgid(gid);
+}
 #endif /* CONFIG_MULTIUSER */
 
 /**
@@ -1027,7 +1069,7 @@ out:
 	return err;
 }
 
-SYSCALL_DEFINE1(getpgid, pid_t, pid)
+static int do_getpgid(pid_t pid)
 {
 	struct task_struct *p;
 	struct pid *grp;
@@ -1055,11 +1097,16 @@ out:
 	return retval;
 }
 
+SYSCALL_DEFINE1(getpgid, pid_t, pid)
+{
+	return do_getpgid(pid);
+}
+
 #ifdef __ARCH_WANT_SYS_GETPGRP
 
 SYSCALL_DEFINE0(getpgrp)
 {
-	return sys_getpgid(0);
+	return do_getpgid(0);
 }
 
 #endif
@@ -1103,7 +1150,7 @@ static void set_special_pids(struct pid *pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
 }
 
-SYSCALL_DEFINE0(setsid)
+int ksys_setsid(void)
 {
 	struct task_struct *group_leader = current->group_leader;
 	struct pid *sid = task_pid(group_leader);
@@ -1136,6 +1183,11 @@ out:
 	return err;
 }
 
+SYSCALL_DEFINE0(setsid)
+{
+	return ksys_setsid();
+}
+
 DECLARE_RWSEM(uts_sem);
 
 #ifdef COMPAT_UTS_MACHINE