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()
  ...

6 files changed, 150 insertions, 32 deletions

diff --git a/mm/fadvise.c b/mm/fadvise.c
index 767887f5f3bf..afa41491d324 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -26,7 +26,8 @@
  * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
  * deactivate the pages and clear PG_Referenced.
  */
-SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+
+int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 {
 	struct fd f = fdget(fd);
 	struct inode *inode;
@@ -185,11 +186,16 @@ out:
 	return ret;
 }
 
+SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+{
+	return ksys_fadvise64_64(fd, offset, len, advice);
+}
+
 #ifdef __ARCH_WANT_SYS_FADVISE64
 
 SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
 {
-	return sys_fadvise64_64(fd, offset, len, advice);
+	return ksys_fadvise64_64(fd, offset, len, advice);
 }
 
 #endif
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 32cba0332787..01cbb7078d6c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1336,9 +1336,9 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
 	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
 }
 
-SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
-		unsigned long, mode, const unsigned long __user *, nmask,
-		unsigned long, maxnode, unsigned, flags)
+static long kernel_mbind(unsigned long start, unsigned long len,
+			 unsigned long mode, const unsigned long __user *nmask,
+			 unsigned long maxnode, unsigned int flags)
 {
 	nodemask_t nodes;
 	int err;
@@ -1357,9 +1357,16 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
 }
 
+SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
+		unsigned long, mode, const unsigned long __user *, nmask,
+		unsigned long, maxnode, unsigned int, flags)
+{
+	return kernel_mbind(start, len, mode, nmask, maxnode, flags);
+}
+
 /* Set the process memory policy */
-SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
-		unsigned long, maxnode)
+static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
+				 unsigned long maxnode)
 {
 	int err;
 	nodemask_t nodes;
@@ -1377,9 +1384,15 @@ SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
 	return do_set_mempolicy(mode, flags, &nodes);
 }
 
-SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
-		const unsigned long __user *, old_nodes,
-		const unsigned long __user *, new_nodes)
+SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
+		unsigned long, maxnode)
+{
+	return kernel_set_mempolicy(mode, nmask, maxnode);
+}
+
+static int kernel_migrate_pages(pid_t pid, unsigned long maxnode,
+				const unsigned long __user *old_nodes,
+				const unsigned long __user *new_nodes)
 {
 	struct mm_struct *mm = NULL;
 	struct task_struct *task;
@@ -1469,11 +1482,20 @@ out_put:
 
 }
 
+SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
+		const unsigned long __user *, old_nodes,
+		const unsigned long __user *, new_nodes)
+{
+	return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes);
+}
+
 
 /* Retrieve NUMA policy */
-SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
-		unsigned long __user *, nmask, unsigned long, maxnode,
-		unsigned long, addr, unsigned long, flags)
+static int kernel_get_mempolicy(int __user *policy,
+				unsigned long __user *nmask,
+				unsigned long maxnode,
+				unsigned long addr,
+				unsigned long flags)
 {
 	int err;
 	int uninitialized_var(pval);
@@ -1496,6 +1518,13 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 	return err;
 }
 
+SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
+		unsigned long __user *, nmask, unsigned long, maxnode,
+		unsigned long, addr, unsigned long, flags)
+{
+	return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags);
+}
+
 #ifdef CONFIG_COMPAT
 
 COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
@@ -1514,7 +1543,7 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 	if (nmask)
 		nm = compat_alloc_user_space(alloc_size);
 
-	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
+	err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
 
 	if (!err && nmask) {
 		unsigned long copy_size;
@@ -1546,7 +1575,7 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 			return -EFAULT;
 	}
 
-	return sys_set_mempolicy(mode, nm, nr_bits+1);
+	return kernel_set_mempolicy(mode, nm, nr_bits+1);
 }
 
 COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
@@ -1568,10 +1597,43 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 			return -EFAULT;
 	}
 
-	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
+	return kernel_mbind(start, len, mode, nm, nr_bits+1, flags);
 }
 
-#endif
+COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
+		       compat_ulong_t, maxnode,
+		       const compat_ulong_t __user *, old_nodes,
+		       const compat_ulong_t __user *, new_nodes)
+{
+	unsigned long __user *old = NULL;
+	unsigned long __user *new = NULL;
+	nodemask_t tmp_mask;
+	unsigned long nr_bits;
+	unsigned long size;
+
+	nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES);
+	size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
+	if (old_nodes) {
+		if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits))
+			return -EFAULT;
+		old = compat_alloc_user_space(new_nodes ? size * 2 : size);
+		if (new_nodes)
+			new = old + size / sizeof(unsigned long);
+		if (copy_to_user(old, nodes_addr(tmp_mask), size))
+			return -EFAULT;
+	}
+	if (new_nodes) {
+		if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits))
+			return -EFAULT;
+		if (new == NULL)
+			new = compat_alloc_user_space(size);
+		if (copy_to_user(new, nodes_addr(tmp_mask), size))
+			return -EFAULT;
+	}
+	return kernel_migrate_pages(pid, nr_bits + 1, old, new);
+}
+
+#endif /* CONFIG_COMPAT */
 
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
diff --git a/mm/migrate.c b/mm/migrate.c
index 1e5525a25691..003886606a22 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -34,6 +34,7 @@
 #include <linux/backing-dev.h>
 #include <linux/compaction.h>
 #include <linux/syscalls.h>
+#include <linux/compat.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
@@ -1745,10 +1746,10 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
  * Move a list of pages in the address space of the currently executing
  * process.
  */
-SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
-		const void __user * __user *, pages,
-		const int __user *, nodes,
-		int __user *, status, int, flags)
+static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
+			     const void __user * __user *pages,
+			     const int __user *nodes,
+			     int __user *status, int flags)
 {
 	struct task_struct *task;
 	struct mm_struct *mm;
@@ -1807,6 +1808,36 @@ out:
 	return err;
 }
 
+SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
+		const void __user * __user *, pages,
+		const int __user *, nodes,
+		int __user *, status, int, flags)
+{
+	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
+		       compat_uptr_t __user *, pages32,
+		       const int __user *, nodes,
+		       int __user *, status,
+		       int, flags)
+{
+	const void __user * __user *pages;
+	int i;
+
+	pages = compat_alloc_user_space(nr_pages * sizeof(void *));
+	for (i = 0; i < nr_pages; i++) {
+		compat_uptr_t p;
+
+		if (get_user(p, pages32 + i) ||
+			put_user(compat_ptr(p), pages + i))
+			return -EFAULT;
+	}
+	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
+}
+#endif /* CONFIG_COMPAT */
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
diff --git a/mm/mmap.c b/mm/mmap.c
index 9efdc021ad22..aa0dc8231c0d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1488,9 +1488,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	return addr;
 }
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, unsigned long, pgoff)
+unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
+			      unsigned long prot, unsigned long flags,
+			      unsigned long fd, unsigned long pgoff)
 {
 	struct file *file = NULL;
 	unsigned long retval;
@@ -1537,6 +1537,13 @@ out_fput:
 	return retval;
 }
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
 #ifdef __ARCH_WANT_SYS_OLD_MMAP
 struct mmap_arg_struct {
 	unsigned long addr;
@@ -1556,8 +1563,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 	if (offset_in_page(a.offset))
 		return -EINVAL;
 
-	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
-			      a.offset >> PAGE_SHIFT);
+	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			       a.offset >> PAGE_SHIFT);
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 838a8fdec5c2..4f8720243ae7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1403,9 +1403,9 @@ error_getting_region:
 	return -ENOMEM;
 }
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, unsigned long, pgoff)
+unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
+			      unsigned long prot, unsigned long flags,
+			      unsigned long fd, unsigned long pgoff)
 {
 	struct file *file = NULL;
 	unsigned long retval = -EBADF;
@@ -1427,6 +1427,13 @@ out:
 	return retval;
 }
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
 #ifdef __ARCH_WANT_SYS_OLD_MMAP
 struct mmap_arg_struct {
 	unsigned long addr;
@@ -1446,8 +1453,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 	if (offset_in_page(a.offset))
 		return -EINVAL;
 
-	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
-			      a.offset >> PAGE_SHIFT);
+	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			       a.offset >> PAGE_SHIFT);
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
diff --git a/mm/readahead.c b/mm/readahead.c
index c4ca70239233..4d57b4644f98 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -573,7 +573,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	return force_page_cache_readahead(mapping, filp, index, nr);
 }
 
-SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
+ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
 	struct fd f;
@@ -592,3 +592,8 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
 	}
 	return ret;
 }
+
+SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
+{
+	return ksys_readahead(fd, offset, count);
+}