linux_dsm_epyc7002/arch/x86/mm/hugetlbpage.c
Kirill A. Shutemov 1e0f25dbf2 x86/mm: Prevent non-MAP_FIXED mapping across DEFAULT_MAP_WINDOW border
In case of 5-level paging, the kernel does not place any mapping above
47-bit, unless userspace explicitly asks for it.

Userspace can request an allocation from the full address space by
specifying the mmap address hint above 47-bit.

Nicholas noticed that the current implementation violates this interface:

  If user space requests a mapping at the end of the 47-bit address space
  with a length which causes the mapping to cross the 47-bit border
  (DEFAULT_MAP_WINDOW), then the vma is partially in the address space
  below and above.

Sanity check the mmap address hint so that start and end of the resulting
vma are on the same side of the 47-bit border. If that's not the case fall
back to the code path which ignores the address hint and allocate from the
regular address space below 47-bit.

To make the checks consistent, mask out the address hints lower bits
(either PAGE_MASK or huge_page_mask()) instead of using ALIGN() which can
push them up to the next boundary.

[ tglx: Moved the address check to a function and massaged comment and
  	changelog ]

Reported-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20171115143607.81541-1-kirill.shutemov@linux.intel.com
2017-11-16 11:43:11 +01:00

217 lines
5.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* IA-32 Huge TLB Page Support for Kernel.
*
* Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <linux/compat.h>
#include <asm/mman.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/elf.h>
#include <asm/mpx.h>
#if 0 /* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
unsigned long start = address;
int length = 1;
int nr;
struct page *page;
struct vm_area_struct *vma;
vma = find_vma(mm, addr);
if (!vma || !is_vm_hugetlb_page(vma))
return ERR_PTR(-EINVAL);
pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
/* hugetlb should be locked, and hence, prefaulted */
WARN_ON(!pte || pte_none(*pte));
page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
WARN_ON(!PageHead(page));
return page;
}
int pmd_huge(pmd_t pmd)
{
return 0;
}
int pud_huge(pud_t pud)
{
return 0;
}
#else
/*
* pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
* hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
* Otherwise, returns 0.
*/
int pmd_huge(pmd_t pmd)
{
return !pmd_none(pmd) &&
(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
}
int pud_huge(pud_t pud)
{
return !!(pud_val(pud) & _PAGE_PSE);
}
#endif
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
info.flags = 0;
info.length = len;
info.low_limit = get_mmap_base(1);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
* in the full address space.
*/
info.high_limit = in_compat_syscall() ?
task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
return vm_unmapped_area(&info);
}
static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
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.
*/
if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
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_LOW;
addr = vm_unmapped_area(&info);
}
return addr;
}
unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
if (len & ~huge_page_mask(h))
return -EINVAL;
addr = mpx_unmapped_area_check(addr, len, flags);
if (IS_ERR_VALUE(addr))
return addr;
if (len > TASK_SIZE)
return -ENOMEM;
/* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED) {
if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
addr &= huge_page_mask(h);
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:
if (mm->get_unmapped_area == arch_get_unmapped_area)
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
else
return hugetlb_get_unmapped_area_topdown(file, addr, len,
pgoff, flags);
}
#endif /* CONFIG_HUGETLB_PAGE */
#ifdef CONFIG_X86_64
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
if (ps == PMD_SIZE) {
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
} else {
hugetlb_bad_size();
printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
ps >> 20);
return 0;
}
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
static __init int gigantic_pages_init(void)
{
/* With compaction or CMA we can allocate gigantic pages at runtime */
if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT))
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
return 0;
}
arch_initcall(gigantic_pages_init);
#endif
#endif