mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 14:36:46 +07:00
c1821c2e97
This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
364 lines
9.8 KiB
C
364 lines
9.8 KiB
C
/*
|
|
* include/asm-s390/uaccess.h
|
|
*
|
|
* S390 version
|
|
* Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation
|
|
* Author(s): Hartmut Penner (hp@de.ibm.com),
|
|
* Martin Schwidefsky (schwidefsky@de.ibm.com)
|
|
*
|
|
* Derived from "include/asm-i386/uaccess.h"
|
|
*/
|
|
#ifndef __S390_UACCESS_H
|
|
#define __S390_UACCESS_H
|
|
|
|
/*
|
|
* User space memory access functions
|
|
*/
|
|
#include <linux/sched.h>
|
|
#include <linux/errno.h>
|
|
|
|
#define VERIFY_READ 0
|
|
#define VERIFY_WRITE 1
|
|
|
|
|
|
/*
|
|
* The fs value determines whether argument validity checking should be
|
|
* performed or not. If get_fs() == USER_DS, checking is performed, with
|
|
* get_fs() == KERNEL_DS, checking is bypassed.
|
|
*
|
|
* For historical reasons, these macros are grossly misnamed.
|
|
*/
|
|
|
|
#define MAKE_MM_SEG(a) ((mm_segment_t) { (a) })
|
|
|
|
|
|
#define KERNEL_DS MAKE_MM_SEG(0)
|
|
#define USER_DS MAKE_MM_SEG(1)
|
|
|
|
#define get_ds() (KERNEL_DS)
|
|
#define get_fs() (current->thread.mm_segment)
|
|
|
|
#define set_fs(x) \
|
|
({ \
|
|
unsigned long __pto; \
|
|
current->thread.mm_segment = (x); \
|
|
__pto = current->thread.mm_segment.ar4 ? \
|
|
S390_lowcore.user_asce : S390_lowcore.kernel_asce; \
|
|
__ctl_load(__pto, 7, 7); \
|
|
})
|
|
|
|
#define segment_eq(a,b) ((a).ar4 == (b).ar4)
|
|
|
|
|
|
static inline int __access_ok(const void __user *addr, unsigned long size)
|
|
{
|
|
return 1;
|
|
}
|
|
#define access_ok(type,addr,size) __access_ok(addr,size)
|
|
|
|
/*
|
|
* The exception table consists of pairs of addresses: the first is the
|
|
* address of an instruction that is allowed to fault, and the second is
|
|
* the address at which the program should continue. No registers are
|
|
* modified, so it is entirely up to the continuation code to figure out
|
|
* what to do.
|
|
*
|
|
* All the routines below use bits of fixup code that are out of line
|
|
* with the main instruction path. This means when everything is well,
|
|
* we don't even have to jump over them. Further, they do not intrude
|
|
* on our cache or tlb entries.
|
|
*/
|
|
|
|
struct exception_table_entry
|
|
{
|
|
unsigned long insn, fixup;
|
|
};
|
|
|
|
struct uaccess_ops {
|
|
size_t (*copy_from_user)(size_t, const void __user *, void *);
|
|
size_t (*copy_from_user_small)(size_t, const void __user *, void *);
|
|
size_t (*copy_to_user)(size_t, void __user *, const void *);
|
|
size_t (*copy_to_user_small)(size_t, void __user *, const void *);
|
|
size_t (*copy_in_user)(size_t, void __user *, const void __user *);
|
|
size_t (*clear_user)(size_t, void __user *);
|
|
size_t (*strnlen_user)(size_t, const char __user *);
|
|
size_t (*strncpy_from_user)(size_t, const char __user *, char *);
|
|
int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
|
|
int (*futex_atomic_cmpxchg)(int __user *, int old, int new);
|
|
};
|
|
|
|
extern struct uaccess_ops uaccess;
|
|
extern struct uaccess_ops uaccess_std;
|
|
extern struct uaccess_ops uaccess_mvcos;
|
|
extern struct uaccess_ops uaccess_mvcos_switch;
|
|
extern struct uaccess_ops uaccess_pt;
|
|
|
|
static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
|
|
{
|
|
size = uaccess.copy_to_user_small(size, ptr, x);
|
|
return size ? -EFAULT : size;
|
|
}
|
|
|
|
static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
|
|
{
|
|
size = uaccess.copy_from_user_small(size, ptr, x);
|
|
return size ? -EFAULT : size;
|
|
}
|
|
|
|
/*
|
|
* These are the main single-value transfer routines. They automatically
|
|
* use the right size if we just have the right pointer type.
|
|
*/
|
|
#define __put_user(x, ptr) \
|
|
({ \
|
|
__typeof__(*(ptr)) __x = (x); \
|
|
int __pu_err = -EFAULT; \
|
|
__chk_user_ptr(ptr); \
|
|
switch (sizeof (*(ptr))) { \
|
|
case 1: \
|
|
case 2: \
|
|
case 4: \
|
|
case 8: \
|
|
__pu_err = __put_user_fn(sizeof (*(ptr)), \
|
|
ptr, &__x); \
|
|
break; \
|
|
default: \
|
|
__put_user_bad(); \
|
|
break; \
|
|
} \
|
|
__pu_err; \
|
|
})
|
|
|
|
#define put_user(x, ptr) \
|
|
({ \
|
|
might_sleep(); \
|
|
__put_user(x, ptr); \
|
|
})
|
|
|
|
|
|
extern int __put_user_bad(void) __attribute__((noreturn));
|
|
|
|
#define __get_user(x, ptr) \
|
|
({ \
|
|
int __gu_err = -EFAULT; \
|
|
__chk_user_ptr(ptr); \
|
|
switch (sizeof(*(ptr))) { \
|
|
case 1: { \
|
|
unsigned char __x; \
|
|
__gu_err = __get_user_fn(sizeof (*(ptr)), \
|
|
ptr, &__x); \
|
|
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
|
|
break; \
|
|
}; \
|
|
case 2: { \
|
|
unsigned short __x; \
|
|
__gu_err = __get_user_fn(sizeof (*(ptr)), \
|
|
ptr, &__x); \
|
|
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
|
|
break; \
|
|
}; \
|
|
case 4: { \
|
|
unsigned int __x; \
|
|
__gu_err = __get_user_fn(sizeof (*(ptr)), \
|
|
ptr, &__x); \
|
|
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
|
|
break; \
|
|
}; \
|
|
case 8: { \
|
|
unsigned long long __x; \
|
|
__gu_err = __get_user_fn(sizeof (*(ptr)), \
|
|
ptr, &__x); \
|
|
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
|
|
break; \
|
|
}; \
|
|
default: \
|
|
__get_user_bad(); \
|
|
break; \
|
|
} \
|
|
__gu_err; \
|
|
})
|
|
|
|
#define get_user(x, ptr) \
|
|
({ \
|
|
might_sleep(); \
|
|
__get_user(x, ptr); \
|
|
})
|
|
|
|
extern int __get_user_bad(void) __attribute__((noreturn));
|
|
|
|
#define __put_user_unaligned __put_user
|
|
#define __get_user_unaligned __get_user
|
|
|
|
/**
|
|
* __copy_to_user: - Copy a block of data into user space, with less checking.
|
|
* @to: Destination address, in user space.
|
|
* @from: Source address, in kernel space.
|
|
* @n: Number of bytes to copy.
|
|
*
|
|
* Context: User context only. This function may sleep.
|
|
*
|
|
* Copy data from kernel space to user space. Caller must check
|
|
* the specified block with access_ok() before calling this function.
|
|
*
|
|
* Returns number of bytes that could not be copied.
|
|
* On success, this will be zero.
|
|
*/
|
|
static inline unsigned long __must_check
|
|
__copy_to_user(void __user *to, const void *from, unsigned long n)
|
|
{
|
|
if (__builtin_constant_p(n) && (n <= 256))
|
|
return uaccess.copy_to_user_small(n, to, from);
|
|
else
|
|
return uaccess.copy_to_user(n, to, from);
|
|
}
|
|
|
|
#define __copy_to_user_inatomic __copy_to_user
|
|
#define __copy_from_user_inatomic __copy_from_user
|
|
|
|
/**
|
|
* copy_to_user: - Copy a block of data into user space.
|
|
* @to: Destination address, in user space.
|
|
* @from: Source address, in kernel space.
|
|
* @n: Number of bytes to copy.
|
|
*
|
|
* Context: User context only. This function may sleep.
|
|
*
|
|
* Copy data from kernel space to user space.
|
|
*
|
|
* Returns number of bytes that could not be copied.
|
|
* On success, this will be zero.
|
|
*/
|
|
static inline unsigned long __must_check
|
|
copy_to_user(void __user *to, const void *from, unsigned long n)
|
|
{
|
|
might_sleep();
|
|
if (access_ok(VERIFY_WRITE, to, n))
|
|
n = __copy_to_user(to, from, n);
|
|
return n;
|
|
}
|
|
|
|
/**
|
|
* __copy_from_user: - Copy a block of data from user space, with less checking.
|
|
* @to: Destination address, in kernel space.
|
|
* @from: Source address, in user space.
|
|
* @n: Number of bytes to copy.
|
|
*
|
|
* Context: User context only. This function may sleep.
|
|
*
|
|
* Copy data from user space to kernel space. Caller must check
|
|
* the specified block with access_ok() before calling this function.
|
|
*
|
|
* Returns number of bytes that could not be copied.
|
|
* On success, this will be zero.
|
|
*
|
|
* If some data could not be copied, this function will pad the copied
|
|
* data to the requested size using zero bytes.
|
|
*/
|
|
static inline unsigned long __must_check
|
|
__copy_from_user(void *to, const void __user *from, unsigned long n)
|
|
{
|
|
if (__builtin_constant_p(n) && (n <= 256))
|
|
return uaccess.copy_from_user_small(n, from, to);
|
|
else
|
|
return uaccess.copy_from_user(n, from, to);
|
|
}
|
|
|
|
/**
|
|
* copy_from_user: - Copy a block of data from user space.
|
|
* @to: Destination address, in kernel space.
|
|
* @from: Source address, in user space.
|
|
* @n: Number of bytes to copy.
|
|
*
|
|
* Context: User context only. This function may sleep.
|
|
*
|
|
* Copy data from user space to kernel space.
|
|
*
|
|
* Returns number of bytes that could not be copied.
|
|
* On success, this will be zero.
|
|
*
|
|
* If some data could not be copied, this function will pad the copied
|
|
* data to the requested size using zero bytes.
|
|
*/
|
|
static inline unsigned long __must_check
|
|
copy_from_user(void *to, const void __user *from, unsigned long n)
|
|
{
|
|
might_sleep();
|
|
if (access_ok(VERIFY_READ, from, n))
|
|
n = __copy_from_user(to, from, n);
|
|
else
|
|
memset(to, 0, n);
|
|
return n;
|
|
}
|
|
|
|
static inline unsigned long __must_check
|
|
__copy_in_user(void __user *to, const void __user *from, unsigned long n)
|
|
{
|
|
return uaccess.copy_in_user(n, to, from);
|
|
}
|
|
|
|
static inline unsigned long __must_check
|
|
copy_in_user(void __user *to, const void __user *from, unsigned long n)
|
|
{
|
|
might_sleep();
|
|
if (__access_ok(from,n) && __access_ok(to,n))
|
|
n = __copy_in_user(to, from, n);
|
|
return n;
|
|
}
|
|
|
|
/*
|
|
* Copy a null terminated string from userspace.
|
|
*/
|
|
static inline long __must_check
|
|
strncpy_from_user(char *dst, const char __user *src, long count)
|
|
{
|
|
long res = -EFAULT;
|
|
might_sleep();
|
|
if (access_ok(VERIFY_READ, src, 1))
|
|
res = uaccess.strncpy_from_user(count, src, dst);
|
|
return res;
|
|
}
|
|
|
|
static inline unsigned long
|
|
strnlen_user(const char __user * src, unsigned long n)
|
|
{
|
|
might_sleep();
|
|
return uaccess.strnlen_user(n, src);
|
|
}
|
|
|
|
/**
|
|
* strlen_user: - Get the size of a string in user space.
|
|
* @str: The string to measure.
|
|
*
|
|
* Context: User context only. This function may sleep.
|
|
*
|
|
* Get the size of a NUL-terminated string in user space.
|
|
*
|
|
* Returns the size of the string INCLUDING the terminating NUL.
|
|
* On exception, returns 0.
|
|
*
|
|
* If there is a limit on the length of a valid string, you may wish to
|
|
* consider using strnlen_user() instead.
|
|
*/
|
|
#define strlen_user(str) strnlen_user(str, ~0UL)
|
|
|
|
/*
|
|
* Zero Userspace
|
|
*/
|
|
|
|
static inline unsigned long __must_check
|
|
__clear_user(void __user *to, unsigned long n)
|
|
{
|
|
return uaccess.clear_user(n, to);
|
|
}
|
|
|
|
static inline unsigned long __must_check
|
|
clear_user(void __user *to, unsigned long n)
|
|
{
|
|
might_sleep();
|
|
if (access_ok(VERIFY_WRITE, to, n))
|
|
n = uaccess.clear_user(n, to);
|
|
return n;
|
|
}
|
|
|
|
#endif /* __S390_UACCESS_H */
|