linux/arch/x86/kernel/sys_x86_64.c
Dmitry Safonov a846446b19 x86/compat: Adjust in_compat_syscall() to generic code under !COMPAT
The result of in_compat_syscall() can be pictured as:

x86 platform:
    ---------------------------------------------------
    |  Arch\syscall  |  64-bit  |   ia32   |   x32    |
    |-------------------------------------------------|
    |     x86_64     |  false   |   true   |   true   |
    |-------------------------------------------------|
    |      i686      |          |  <true>  |          |
    ---------------------------------------------------

Other platforms:
    -------------------------------------------
    |  Arch\syscall  |  64-bit  |   compat    |
    |-----------------------------------------|
    |     64-bit     |  false   |    true     |
    |-----------------------------------------|
    |    32-bit(?)   |          |   <false>   |
    -------------------------------------------

As seen, the result of in_compat_syscall() on generic 32-bit platform
differs from i686.

There is no reason for in_compat_syscall() == true on native i686.  It also
easy to misread code if the result on native 32-bit platform differs
between arches.

Because of that non arch-specific code has many places with:
    if (IS_ENABLED(CONFIG_COMPAT) && in_compat_syscall())
in different variations.

It looks-like the only non-x86 code which uses in_compat_syscall() not
under CONFIG_COMPAT guard is in amd/amdkfd. But according to the commit
a18069c132 ("amdkfd: Disable support for 32-bit user processes"), it
actually should be disabled on native i686.

Rename in_compat_syscall() to in_32bit_syscall() for x86-specific code
and make in_compat_syscall() false under !CONFIG_COMPAT.

A follow on patch will clean up generic users which were forced to check
IS_ENABLED(CONFIG_COMPAT) with in_compat_syscall().

Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-efi@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: https://lkml.kernel.org/r/20181012134253.23266-2-dima@arista.com
2018-11-01 12:59:25 +01:00

246 lines
6.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/msg.h>
#include <linux/shm.h>
#include <linux/stat.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/uaccess.h>
#include <linux/elf.h>
#include <asm/elf.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
#include <asm/mpx.h>
/*
* Align a virtual address to avoid aliasing in the I$ on AMD F15h.
*/
static unsigned long get_align_mask(void)
{
/* handle 32- and 64-bit case with a single conditional */
if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
return 0;
if (!(current->flags & PF_RANDOMIZE))
return 0;
return va_align.mask;
}
/*
* To avoid aliasing in the I$ on AMD F15h, the bits defined by the
* va_align.bits, [12:upper_bit), are set to a random value instead of
* zeroing them. This random value is computed once per boot. This form
* of ASLR is known as "per-boot ASLR".
*
* To achieve this, the random value is added to the info.align_offset
* value before calling vm_unmapped_area() or ORed directly to the
* address.
*/
static unsigned long get_align_bits(void)
{
return va_align.bits & get_align_mask();
}
unsigned long align_vdso_addr(unsigned long addr)
{
unsigned long align_mask = get_align_mask();
addr = (addr + align_mask) & ~align_mask;
return addr | get_align_bits();
}
static int __init control_va_addr_alignment(char *str)
{
/* guard against enabling this on other CPU families */
if (va_align.flags < 0)
return 1;
if (*str == 0)
return 1;
if (*str == '=')
str++;
if (!strcmp(str, "32"))
va_align.flags = ALIGN_VA_32;
else if (!strcmp(str, "64"))
va_align.flags = ALIGN_VA_64;
else if (!strcmp(str, "off"))
va_align.flags = 0;
else if (!strcmp(str, "on"))
va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
else
return 0;
return 1;
}
__setup("align_va_addr", control_va_addr_alignment);
SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, off)
{
long error;
error = -EINVAL;
if (off & ~PAGE_MASK)
goto out;
error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
out:
return error;
}
static void find_start_end(unsigned long addr, unsigned long flags,
unsigned long *begin, unsigned long *end)
{
if (!in_32bit_syscall() && (flags & MAP_32BIT)) {
/* This is usually used needed to map code in small
model, so it needs to be in the first 31bit. Limit
it to that. This means we need to move the
unmapped base down for this case. This can give
conflicts with the heap, but we assume that glibc
malloc knows how to fall back to mmap. Give it 1GB
of playground for now. -AK */
*begin = 0x40000000;
*end = 0x80000000;
if (current->flags & PF_RANDOMIZE) {
*begin = randomize_page(*begin, 0x02000000);
}
return;
}
*begin = get_mmap_base(1);
if (in_32bit_syscall())
*end = task_size_32bit();
else
*end = task_size_64bit(addr > DEFAULT_MAP_WINDOW);
}
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
unsigned long begin, end;
addr = mpx_unmapped_area_check(addr, len, flags);
if (IS_ERR_VALUE(addr))
return addr;
if (flags & MAP_FIXED)
return addr;
find_start_end(addr, flags, &begin, &end);
if (len > end)
return -ENOMEM;
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (end - len >= addr &&
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = 0;
info.length = len;
info.low_limit = begin;
info.high_limit = end;
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
}
return vm_unmapped_area(&info);
}
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
const unsigned long len, const unsigned long pgoff,
const unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
addr = mpx_unmapped_area_check(addr, len, flags);
if (IS_ERR_VALUE(addr))
return addr;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
return -ENOMEM;
/* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED)
return addr;
/* for MAP_32BIT mappings we force the legacy mmap base */
if (!in_32bit_syscall() && (flags & MAP_32BIT))
goto bottomup;
/* requesting a specific address */
if (addr) {
addr &= PAGE_MASK;
if (!mmap_address_hint_valid(addr, len))
goto get_unmapped_area;
vma = find_vma(mm, addr);
if (!vma || addr + len <= vm_start_gap(vma))
return addr;
}
get_unmapped_area:
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
* in the full address space.
*
* !in_32bit_syscall() check to avoid high addresses for x32
* (and make it no op on native i386).
*/
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
}
addr = vm_unmapped_area(&info);
if (!(addr & ~PAGE_MASK))
return addr;
VM_BUG_ON(addr != -ENOMEM);
bottomup:
/*
* A failed mmap() very likely causes application failure,
* so fall back to the bottom-up function here. This scenario
* can happen with large stack limits and large mmap()
* allocations.
*/
return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}