fa697140f9
Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems:
Each syscall defines a stub which takes struct pt_regs as its only
argument. It decodes just those parameters it needs, e.g:
asmlinkage long sys_xyzzy(const struct pt_regs *regs)
{
return SyS_xyzzy(regs->di, regs->si, regs->dx);
}
This approach avoids leaking random user-provided register content down
the call chain.
For example, for sys_recv() which is a 4-parameter syscall, the assembly
now is (in slightly reordered fashion):
<sys_recv>:
callq <__fentry__>
/* decode regs->di, ->si, ->dx and ->r10 */
mov 0x70(%rdi),%rdi
mov 0x68(%rdi),%rsi
mov 0x60(%rdi),%rdx
mov 0x38(%rdi),%rcx
[ SyS_recv() is automatically inlined by the compiler,
as it is not [yet] used anywhere else ]
/* clear %r9 and %r8, the 5th and 6th args */
xor %r9d,%r9d
xor %r8d,%r8d
/* do the actual work */
callq __sys_recvfrom
/* cleanup and return */
cltq
retq
The only valid place in an x86-64 kernel which rightfully calls
a syscall function on its own -- vsyscall -- needs to be modified
to pass struct pt_regs onwards as well.
To keep the syscall table generation working independent of
SYSCALL_PTREGS being enabled, the stubs are named the same as the
"original" syscall stubs, i.e. sys_*().
This patch is based on an original proof-of-concept
| From: Linus Torvalds <torvalds@linux-foundation.org>
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
and was split up and heavily modified by me, in particular to base it on
ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being,
and to update the vsyscall to the new calling convention.
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
31 lines
1.1 KiB
C
31 lines
1.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* System call table for x86-64. */
|
|
|
|
#include <linux/linkage.h>
|
|
#include <linux/sys.h>
|
|
#include <linux/cache.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/syscall.h>
|
|
|
|
#ifdef CONFIG_SYSCALL_PTREGS
|
|
/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
|
|
extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
|
|
#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
|
|
#else /* CONFIG_SYSCALL_PTREGS */
|
|
extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
|
|
#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
|
|
#endif /* CONFIG_SYSCALL_PTREGS */
|
|
#include <asm/syscalls_64.h>
|
|
#undef __SYSCALL_64
|
|
|
|
#define __SYSCALL_64(nr, sym, qual) [nr] = sym,
|
|
|
|
asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
|
|
/*
|
|
* Smells like a compiler bug -- it doesn't work
|
|
* when the & below is removed.
|
|
*/
|
|
[0 ... __NR_syscall_max] = &sys_ni_syscall,
|
|
#include <asm/syscalls_64.h>
|
|
};
|