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, 45 insertions, 16 deletions

diff --git a/fs/namei.c b/fs/namei.c
index cafa365eeb70..5c2b953c352d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3729,8 +3729,8 @@ static int may_mknod(umode_t mode)
 	}
 }
 
-SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
-		unsigned, dev)
+long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+		unsigned int dev)
 {
 	struct dentry *dentry;
 	struct path path;
@@ -3773,9 +3773,15 @@ out:
 	return error;
 }
 
+SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
+		unsigned int, dev)
+{
+	return do_mknodat(dfd, filename, mode, dev);
+}
+
 SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
 {
-	return sys_mknodat(AT_FDCWD, filename, mode, dev);
+	return do_mknodat(AT_FDCWD, filename, mode, dev);
 }
 
 int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
@@ -3804,7 +3810,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
-SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
+long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
@@ -3829,9 +3835,14 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
+{
+	return do_mkdirat(dfd, pathname, mode);
+}
+
 SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 {
-	return sys_mkdirat(AT_FDCWD, pathname, mode);
+	return do_mkdirat(AT_FDCWD, pathname, mode);
 }
 
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
@@ -3873,7 +3884,7 @@ out:
 }
 EXPORT_SYMBOL(vfs_rmdir);
 
-static long do_rmdir(int dfd, const char __user *pathname)
+long do_rmdir(int dfd, const char __user *pathname)
 {
 	int error = 0;
 	struct filename *name;
@@ -4109,8 +4120,8 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
-		int, newdfd, const char __user *, newname)
+long do_symlinkat(const char __user *oldname, int newdfd,
+		  const char __user *newname)
 {
 	int error;
 	struct filename *from;
@@ -4140,9 +4151,15 @@ out_putname:
 	return error;
 }
 
+SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return do_symlinkat(oldname, newdfd, newname);
+}
+
 SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_symlinkat(oldname, AT_FDCWD, newname);
+	return do_symlinkat(oldname, AT_FDCWD, newname);
 }
 
 /**
@@ -4234,8 +4251,8 @@ EXPORT_SYMBOL(vfs_link);
  * with linux 2.0, and to avoid hard-linking to directories
  * and other special files.  --ADM
  */
-SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
-		int, newdfd, const char __user *, newname, int, flags)
+int do_linkat(int olddfd, const char __user *oldname, int newdfd,
+	      const char __user *newname, int flags)
 {
 	struct dentry *new_dentry;
 	struct path old_path, new_path;
@@ -4299,9 +4316,15 @@ out:
 	return error;
 }
 
+SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, int, flags)
+{
+	return do_linkat(olddfd, oldname, newdfd, newname, flags);
+}
+
 SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 /**
@@ -4479,8 +4502,8 @@ out:
 }
 EXPORT_SYMBOL(vfs_rename);
 
-SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
-		int, newdfd, const char __user *, newname, unsigned int, flags)
+static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
+			const char __user *newname, unsigned int flags)
 {
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
@@ -4622,15 +4645,21 @@ exit:
 	return error;
 }
 
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, unsigned int, flags)
+{
+	return do_renameat2(olddfd, oldname, newdfd, newname, flags);
+}
+
 SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
 {
-	return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+	return do_renameat2(olddfd, oldname, newdfd, newname, 0);
 }
 
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+	return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 int vfs_whiteout(struct inode *dir, struct dentry *dentry)