linux/include/linux/mman.h
Rick Edgecombe 29f890d105 x86/mm: Introduce MAP_ABOVE4G
The x86 Control-flow Enforcement Technology (CET) feature includes a new
type of memory called shadow stack. This shadow stack memory has some
unusual properties, which require some core mm changes to function
properly.

One of the properties is that the shadow stack pointer (SSP), which is a
CPU register that points to the shadow stack like the stack pointer points
to the stack, can't be pointing outside of the 32 bit address space when
the CPU is executing in 32 bit mode. It is desirable to prevent executing
in 32 bit mode when shadow stack is enabled because the kernel can't easily
support 32 bit signals.

On x86 it is possible to transition to 32 bit mode without any special
interaction with the kernel, by doing a "far call" to a 32 bit segment.
So the shadow stack implementation can use this address space behavior
as a feature, by enforcing that shadow stack memory is always mapped
outside of the 32 bit address space. This way userspace will trigger a
general protection fault which will in turn trigger a segfault if it
tries to transition to 32 bit mode with shadow stack enabled.

This provides a clean error generating border for the user if they try
attempt to do 32 bit mode shadow stack, rather than leave the kernel in a
half working state for userspace to be surprised by.

So to allow future shadow stack enabling patches to map shadow stacks
out of the 32 bit address space, introduce MAP_ABOVE4G. The behavior
is pretty much like MAP_32BIT, except that it has the opposite address
range. The are a few differences though.

If both MAP_32BIT and MAP_ABOVE4G are provided, the kernel will use the
MAP_ABOVE4G behavior. Like MAP_32BIT, MAP_ABOVE4G is ignored in a 32 bit
syscall.

Since the default search behavior is top down, the normal kaslr base can
be used for MAP_ABOVE4G. This is unlike MAP_32BIT which has to add its
own randomization in the bottom up case.

For MAP_32BIT, only the bottom up search path is used. For MAP_ABOVE4G
both are potentially valid, so both are used. In the bottomup search
path, the default behavior is already consistent with MAP_ABOVE4G since
mmap base should be above 4GB.

Without MAP_ABOVE4G, the shadow stack will already normally be above 4GB.
So without introducing MAP_ABOVE4G, trying to transition to 32 bit mode
with shadow stack enabled would usually segfault anyway. This is already
pretty decent guard rails. But the addition of MAP_ABOVE4G is some small
complexity spent to make it make it more complete.

Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Tested-by: Pengfei Xu <pengfei.xu@intel.com>
Tested-by: John Allen <john.allen@amd.com>
Tested-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/all/20230613001108.3040476-21-rick.p.edgecombe%40intel.com
2023-07-11 14:12:19 -07:00

198 lines
4.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MMAN_H
#define _LINUX_MMAN_H
#include <linux/mm.h>
#include <linux/percpu_counter.h>
#include <linux/atomic.h>
#include <uapi/linux/mman.h>
/*
* Arrange for legacy / undefined architecture specific flags to be
* ignored by mmap handling code.
*/
#ifndef MAP_32BIT
#define MAP_32BIT 0
#endif
#ifndef MAP_ABOVE4G
#define MAP_ABOVE4G 0
#endif
#ifndef MAP_HUGE_2MB
#define MAP_HUGE_2MB 0
#endif
#ifndef MAP_HUGE_1GB
#define MAP_HUGE_1GB 0
#endif
#ifndef MAP_UNINITIALIZED
#define MAP_UNINITIALIZED 0
#endif
#ifndef MAP_SYNC
#define MAP_SYNC 0
#endif
/*
* The historical set of flags that all mmap implementations implicitly
* support when a ->mmap_validate() op is not provided in file_operations.
*
* MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the
* kernel.
*/
#define LEGACY_MAP_MASK (MAP_SHARED \
| MAP_PRIVATE \
| MAP_FIXED \
| MAP_ANONYMOUS \
| MAP_DENYWRITE \
| MAP_EXECUTABLE \
| MAP_UNINITIALIZED \
| MAP_GROWSDOWN \
| MAP_LOCKED \
| MAP_NORESERVE \
| MAP_POPULATE \
| MAP_NONBLOCK \
| MAP_STACK \
| MAP_HUGETLB \
| MAP_32BIT \
| MAP_ABOVE4G \
| MAP_HUGE_2MB \
| MAP_HUGE_1GB)
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern unsigned long sysctl_overcommit_kbytes;
extern struct percpu_counter vm_committed_as;
#ifdef CONFIG_SMP
extern s32 vm_committed_as_batch;
extern void mm_compute_batch(int overcommit_policy);
#else
#define vm_committed_as_batch 0
static inline void mm_compute_batch(int overcommit_policy)
{
}
#endif
unsigned long vm_memory_committed(void);
static inline void vm_acct_memory(long pages)
{
percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch);
}
static inline void vm_unacct_memory(long pages)
{
vm_acct_memory(-pages);
}
/*
* Allow architectures to handle additional protection and flag bits. The
* overriding macros must be defined in the arch-specific asm/mman.h file.
*/
#ifndef arch_calc_vm_prot_bits
#define arch_calc_vm_prot_bits(prot, pkey) 0
#endif
#ifndef arch_calc_vm_flag_bits
#define arch_calc_vm_flag_bits(flags) 0
#endif
#ifndef arch_validate_prot
/*
* This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have
* already been masked out.
*
* Returns true if the prot flags are valid
*/
static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
{
return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0;
}
#define arch_validate_prot arch_validate_prot
#endif
#ifndef arch_validate_flags
/*
* This is called from mmap() and mprotect() with the updated vma->vm_flags.
*
* Returns true if the VM_* flags are valid.
*/
static inline bool arch_validate_flags(unsigned long flags)
{
return true;
}
#define arch_validate_flags arch_validate_flags
#endif
/*
* Optimisation macro. It is equivalent to:
* (x & bit1) ? bit2 : 0
* but this version is faster.
* ("bit1" and "bit2" must be single bits)
*/
#define _calc_vm_trans(x, bit1, bit2) \
((!(bit1) || !(bit2)) ? 0 : \
((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \
: ((x) & (bit1)) / ((bit1) / (bit2))))
/*
* Combine the mmap "prot" argument into "vm_flags" used internally.
*/
static inline unsigned long
calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
{
return _calc_vm_trans(prot, PROT_READ, VM_READ ) |
_calc_vm_trans(prot, PROT_WRITE, VM_WRITE) |
_calc_vm_trans(prot, PROT_EXEC, VM_EXEC) |
arch_calc_vm_prot_bits(prot, pkey);
}
/*
* Combine the mmap "flags" argument into "vm_flags" used internally.
*/
static inline unsigned long
calc_vm_flag_bits(unsigned long flags)
{
return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) |
_calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) |
_calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) |
arch_calc_vm_flag_bits(flags);
}
unsigned long vm_commit_limit(void);
/*
* Denies creating a writable executable mapping or gaining executable permissions.
*
* This denies the following:
*
* a) mmap(PROT_WRITE | PROT_EXEC)
*
* b) mmap(PROT_WRITE)
* mprotect(PROT_EXEC)
*
* c) mmap(PROT_WRITE)
* mprotect(PROT_READ)
* mprotect(PROT_EXEC)
*
* But allows the following:
*
* d) mmap(PROT_READ | PROT_EXEC)
* mmap(PROT_READ | PROT_EXEC | PROT_BTI)
*/
static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags)
{
if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
return false;
if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
return true;
if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
return true;
return false;
}
#endif /* _LINUX_MMAN_H */