WSL2-Linux-Kernel/arch/sh/mm/mmap.c

185 строки
4.6 KiB
C
Исходник Обычный вид История

/*
* arch/sh/mm/mmap.c
*
* Copyright (C) 2008 - 2009 Paul Mundt
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*/
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/mman.h>
#include <linux/module.h>
#include <asm/page.h>
#include <asm/processor.h>
unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */
EXPORT_SYMBOL(shm_align_mask);
#ifdef CONFIG_MMU
sh/mm: enable ARCH_HAS_VM_GET_PAGE_PROT This enables ARCH_HAS_VM_GET_PAGE_PROT on the platform and exports standard vm_get_page_prot() implementation via DECLARE_VM_GET_PAGE_PROT, which looks up a private and static protection_map[] array. Subsequently all __SXXX and __PXXX macros can be dropped which are no longer needed. Link: https://lkml.kernel.org/r/20220711070600.2378316-26-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Brian Cain <bcain@quicinc.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dinh Nguyen <dinguyen@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Russell King <linux@armlinux.org.uk> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@kernel.org> Cc: WANG Xuerui <kernel@xen0n.name> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-11 10:05:59 +03:00
static const pgprot_t protection_map[16] = {
[VM_NONE] = PAGE_NONE,
[VM_READ] = PAGE_READONLY,
[VM_WRITE] = PAGE_COPY,
[VM_WRITE | VM_READ] = PAGE_COPY,
[VM_EXEC] = PAGE_EXECREAD,
[VM_EXEC | VM_READ] = PAGE_EXECREAD,
[VM_EXEC | VM_WRITE] = PAGE_COPY,
[VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY,
[VM_SHARED] = PAGE_NONE,
[VM_SHARED | VM_READ] = PAGE_READONLY,
[VM_SHARED | VM_WRITE] = PAGE_WRITEONLY,
[VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED,
[VM_SHARED | VM_EXEC] = PAGE_EXECREAD,
[VM_SHARED | VM_EXEC | VM_READ] = PAGE_EXECREAD,
[VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX,
[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX
};
DECLARE_VM_GET_PAGE_PROT
/*
* To avoid cache aliases, we map the shared page with same color.
*/
static inline unsigned long COLOUR_ALIGN(unsigned long addr,
unsigned long pgoff)
{
unsigned long base = (addr + shm_align_mask) & ~shm_align_mask;
unsigned long off = (pgoff << PAGE_SHIFT) & shm_align_mask;
return base + off;
}
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;
int do_colour_align;
struct vm_unmapped_area_info info;
if (flags & MAP_FIXED) {
/* We do not accept a shared mapping if it would violate
* cache aliasing constraints.
*/
if ((flags & MAP_SHARED) &&
((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
return -EINVAL;
return addr;
}
if (unlikely(len > TASK_SIZE))
return -ENOMEM;
do_colour_align = 0;
if (filp || (flags & MAP_SHARED))
do_colour_align = 1;
if (addr) {
if (do_colour_align)
addr = COLOUR_ALIGN(addr, pgoff);
else
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov <oleg@redhat.com> Original-patch-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Helge Deller <deller@gmx.de> # parisc Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 14:03:24 +03:00
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = 0;
info.length = len;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = TASK_SIZE;
info.align_mask = do_colour_align ? (PAGE_MASK & shm_align_mask) : 0;
info.align_offset = pgoff << PAGE_SHIFT;
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;
int do_colour_align;
struct vm_unmapped_area_info info;
if (flags & MAP_FIXED) {
/* We do not accept a shared mapping if it would violate
* cache aliasing constraints.
*/
if ((flags & MAP_SHARED) &&
((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
return -EINVAL;
return addr;
}
if (unlikely(len > TASK_SIZE))
return -ENOMEM;
do_colour_align = 0;
if (filp || (flags & MAP_SHARED))
do_colour_align = 1;
/* requesting a specific address */
if (addr) {
if (do_colour_align)
addr = COLOUR_ALIGN(addr, pgoff);
else
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov <oleg@redhat.com> Original-patch-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Helge Deller <deller@gmx.de> # parisc Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 14:03:24 +03:00
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = mm->mmap_base;
info.align_mask = do_colour_align ? (PAGE_MASK & shm_align_mask) : 0;
info.align_offset = pgoff << PAGE_SHIFT;
addr = vm_unmapped_area(&info);
/*
* 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.
*/
if (addr & ~PAGE_MASK) {
VM_BUG_ON(addr != -ENOMEM);
info.flags = 0;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = TASK_SIZE;
addr = vm_unmapped_area(&info);
}
return addr;
}
#endif /* CONFIG_MMU */
/*
* You really shouldn't be using read() or write() on /dev/mem. This
* might go away in the future.
*/
int valid_phys_addr_range(phys_addr_t addr, size_t count)
{
if (addr < __MEMORY_START)
return 0;
if (addr + count > __pa(high_memory))
return 0;
return 1;
}
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
return 1;
}