linux-stable/arch/x86/include/asm/syscall.h
Andy Lutomirski 6365b842aa x86/syscalls: Split the x32 syscalls into their own table
For unfortunate historical reasons, the x32 syscalls and the x86_64
syscalls are not all numbered the same.  As an example, ioctl() is nr 16 on
x86_64 but 514 on x32.

This has potentially nasty consequences, since it means that there are two
valid RAX values to do ioctl(2) and two invalid RAX values.  The valid
values are 16 (i.e. ioctl(2) using the x86_64 ABI) and (514 | 0x40000000)
(i.e. ioctl(2) using the x32 ABI).

The invalid values are 514 and (16 | 0x40000000).  514 will enter the
"COMPAT_SYSCALL_DEFINE3(ioctl, ...)" entry point with in_compat_syscall()
and in_x32_syscall() returning false, whereas (16 | 0x40000000) will enter
the native entry point with in_compat_syscall() and in_x32_syscall()
returning true.  Both are bogus, and both will exercise code paths in the
kernel and in any running seccomp filters that really ought to be
unreachable.

Splitting out the x32 syscalls into their own tables, allows both bogus
invocations to return -ENOSYS.  I've checked glibc, musl, and Bionic, and
all of them appear to call syscalls with their correct numbers, so this
change should have no effect on them.

There is an added benefit going forward: new syscalls that need special
handling on x32 can share the same number on x32 and x86_64.  This means
that the special syscall range 512-547 can be treated as a legacy wart
instead of something that may need to be extended in the future.

Also add a selftest to verify the new behavior.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/208024256b764312598f014ebfb0a42472c19354.1562185330.git.luto@kernel.org
2019-07-22 10:31:23 +02:00

173 lines
4.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Access to user system call parameters and results
*
* Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved.
*
* See asm-generic/syscall.h for descriptions of what we must do here.
*/
#ifndef _ASM_X86_SYSCALL_H
#define _ASM_X86_SYSCALL_H
#include <uapi/linux/audit.h>
#include <linux/sched.h>
#include <linux/err.h>
#include <asm/asm-offsets.h> /* For NR_syscalls */
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
#ifdef CONFIG_X86_64
typedef asmlinkage long (*sys_call_ptr_t)(const struct pt_regs *);
#else
typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
#endif /* CONFIG_X86_64 */
extern const sys_call_ptr_t sys_call_table[];
#if defined(CONFIG_X86_32)
#define ia32_sys_call_table sys_call_table
#define __NR_syscall_compat_max __NR_syscall_max
#define IA32_NR_syscalls NR_syscalls
#endif
#if defined(CONFIG_IA32_EMULATION)
extern const sys_call_ptr_t ia32_sys_call_table[];
#endif
#ifdef CONFIG_X86_X32_ABI
extern const sys_call_ptr_t x32_sys_call_table[];
#endif
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
* This importantly ignores the high bits on 64-bit, so comparisons
* sign-extend the low 32 bits.
*/
static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
{
return regs->orig_ax;
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
regs->ax = regs->orig_ax;
}
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
unsigned long error = regs->ax;
#ifdef CONFIG_IA32_EMULATION
/*
* TS_COMPAT is set for 32-bit syscall entries and then
* remains set until we return to user mode.
*/
if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED))
/*
* Sign-extend the value so (int)-EFOO becomes (long)-EFOO
* and will match correctly in comparisons.
*/
error = (long) (int) error;
#endif
return IS_ERR_VALUE(error) ? error : 0;
}
static inline long syscall_get_return_value(struct task_struct *task,
struct pt_regs *regs)
{
return regs->ax;
}
static inline void syscall_set_return_value(struct task_struct *task,
struct pt_regs *regs,
int error, long val)
{
regs->ax = (long) error ?: val;
}
#ifdef CONFIG_X86_32
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
memcpy(args, &regs->bx, 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned int i, unsigned int n,
const unsigned long *args)
{
BUG_ON(i + n > 6);
memcpy(&regs->bx + i, args, n * sizeof(args[0]));
}
static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_I386;
}
#else /* CONFIG_X86_64 */
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
if (task->thread_info.status & TS_COMPAT) {
*args++ = regs->bx;
*args++ = regs->cx;
*args++ = regs->dx;
*args++ = regs->si;
*args++ = regs->di;
*args = regs->bp;
} else
# endif
{
*args++ = regs->di;
*args++ = regs->si;
*args++ = regs->dx;
*args++ = regs->r10;
*args++ = regs->r8;
*args = regs->r9;
}
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
const unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
if (task->thread_info.status & TS_COMPAT) {
regs->bx = *args++;
regs->cx = *args++;
regs->dx = *args++;
regs->si = *args++;
regs->di = *args++;
regs->bp = *args;
} else
# endif
{
regs->di = *args++;
regs->si = *args++;
regs->dx = *args++;
regs->r10 = *args++;
regs->r8 = *args++;
regs->r9 = *args;
}
}
static inline int syscall_get_arch(struct task_struct *task)
{
/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
return (IS_ENABLED(CONFIG_IA32_EMULATION) &&
task->thread_info.status & TS_COMPAT)
? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
#endif /* CONFIG_X86_32 */
#endif /* _ASM_X86_SYSCALL_H */