2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* SPARC64 Huge TLB page support.
|
|
|
|
*
|
2006-03-20 09:17:17 +00:00
|
|
|
* Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/mm.h>
|
2017-02-08 17:51:31 +00:00
|
|
|
#include <linux/sched/mm.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/hugetlb.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/sysctl.h>
|
|
|
|
|
|
|
|
#include <asm/mman.h>
|
|
|
|
#include <asm/pgalloc.h>
|
2016-07-29 07:54:21 +00:00
|
|
|
#include <asm/pgtable.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include <asm/cacheflush.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
|
2006-03-20 09:17:17 +00:00
|
|
|
/* Slightly simplified from the non-hugepage variant because by
|
|
|
|
* definition we don't have to worry about any page coloring stuff
|
|
|
|
*/
|
|
|
|
|
|
|
|
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
|
|
|
|
unsigned long addr,
|
|
|
|
unsigned long len,
|
|
|
|
unsigned long pgoff,
|
|
|
|
unsigned long flags)
|
|
|
|
{
|
2017-02-02 00:16:36 +00:00
|
|
|
struct hstate *h = hstate_file(filp);
|
2006-03-20 09:17:17 +00:00
|
|
|
unsigned long task_size = TASK_SIZE;
|
2012-12-12 00:02:25 +00:00
|
|
|
struct vm_unmapped_area_info info;
|
2006-03-20 09:17:17 +00:00
|
|
|
|
|
|
|
if (test_thread_flag(TIF_32BIT))
|
|
|
|
task_size = STACK_TOP32;
|
|
|
|
|
2012-12-12 00:02:25 +00:00
|
|
|
info.flags = 0;
|
|
|
|
info.length = len;
|
|
|
|
info.low_limit = TASK_UNMAPPED_BASE;
|
|
|
|
info.high_limit = min(task_size, VA_EXCLUDE_START);
|
2017-02-02 00:16:36 +00:00
|
|
|
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
|
2012-12-12 00:02:25 +00:00
|
|
|
info.align_offset = 0;
|
|
|
|
addr = vm_unmapped_area(&info);
|
|
|
|
|
|
|
|
if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) {
|
|
|
|
VM_BUG_ON(addr != -ENOMEM);
|
|
|
|
info.low_limit = VA_EXCLUDE_END;
|
|
|
|
info.high_limit = task_size;
|
|
|
|
addr = vm_unmapped_area(&info);
|
2006-03-20 09:17:17 +00:00
|
|
|
}
|
|
|
|
|
2012-12-12 00:02:25 +00:00
|
|
|
return addr;
|
2006-03-20 09:17:17 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long
|
|
|
|
hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
|
|
|
|
const unsigned long len,
|
|
|
|
const unsigned long pgoff,
|
|
|
|
const unsigned long flags)
|
|
|
|
{
|
2017-02-02 00:16:36 +00:00
|
|
|
struct hstate *h = hstate_file(filp);
|
2006-03-20 09:17:17 +00:00
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
unsigned long addr = addr0;
|
2012-12-12 00:02:25 +00:00
|
|
|
struct vm_unmapped_area_info info;
|
2006-03-20 09:17:17 +00:00
|
|
|
|
|
|
|
/* This should only ever run for 32-bit processes. */
|
|
|
|
BUG_ON(!test_thread_flag(TIF_32BIT));
|
|
|
|
|
2012-12-12 00:02:25 +00:00
|
|
|
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
|
|
|
|
info.length = len;
|
|
|
|
info.low_limit = PAGE_SIZE;
|
|
|
|
info.high_limit = mm->mmap_base;
|
2017-02-02 00:16:36 +00:00
|
|
|
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
|
2012-12-12 00:02:25 +00:00
|
|
|
info.align_offset = 0;
|
|
|
|
addr = vm_unmapped_area(&info);
|
2006-03-20 09:17:17 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2012-12-12 00:02:25 +00:00
|
|
|
if (addr & ~PAGE_MASK) {
|
|
|
|
VM_BUG_ON(addr != -ENOMEM);
|
|
|
|
info.flags = 0;
|
|
|
|
info.low_limit = TASK_UNMAPPED_BASE;
|
|
|
|
info.high_limit = STACK_TOP32;
|
|
|
|
addr = vm_unmapped_area(&info);
|
|
|
|
}
|
2006-03-20 09:17:17 +00:00
|
|
|
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long
|
|
|
|
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
|
|
|
|
unsigned long len, unsigned long pgoff, unsigned long flags)
|
|
|
|
{
|
2017-02-02 00:16:36 +00:00
|
|
|
struct hstate *h = hstate_file(file);
|
2006-03-20 09:17:17 +00:00
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
unsigned long task_size = TASK_SIZE;
|
|
|
|
|
|
|
|
if (test_thread_flag(TIF_32BIT))
|
|
|
|
task_size = STACK_TOP32;
|
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
if (len & ~huge_page_mask(h))
|
2006-03-20 09:17:17 +00:00
|
|
|
return -EINVAL;
|
|
|
|
if (len > task_size)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2007-05-06 21:50:10 +00:00
|
|
|
if (flags & MAP_FIXED) {
|
2008-07-24 04:27:41 +00:00
|
|
|
if (prepare_hugepage_range(file, addr, len))
|
2007-05-06 21:50:10 +00:00
|
|
|
return -EINVAL;
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
2006-03-20 09:17:17 +00:00
|
|
|
if (addr) {
|
2017-02-02 00:16:36 +00:00
|
|
|
addr = ALIGN(addr, huge_page_size(h));
|
2006-03-20 09:17:17 +00:00
|
|
|
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 11:03:24 +00:00
|
|
|
(!vma || addr + len <= vm_start_gap(vma)))
|
2006-03-20 09:17:17 +00:00
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
|
|
|
|
{
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
|
|
|
|
{
|
|
|
|
unsigned long hugepage_size = _PAGE_SZ4MB_4V;
|
|
|
|
|
|
|
|
pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
|
|
|
|
|
|
|
|
switch (shift) {
|
2017-03-09 22:22:23 +00:00
|
|
|
case HPAGE_2GB_SHIFT:
|
|
|
|
hugepage_size = _PAGE_SZ2GB_4V;
|
|
|
|
pte_val(entry) |= _PAGE_PMD_HUGE;
|
|
|
|
break;
|
2017-02-02 00:16:36 +00:00
|
|
|
case HPAGE_256MB_SHIFT:
|
|
|
|
hugepage_size = _PAGE_SZ256MB_4V;
|
|
|
|
pte_val(entry) |= _PAGE_PMD_HUGE;
|
|
|
|
break;
|
|
|
|
case HPAGE_SHIFT:
|
|
|
|
pte_val(entry) |= _PAGE_PMD_HUGE;
|
|
|
|
break;
|
2017-02-06 20:33:26 +00:00
|
|
|
case HPAGE_64K_SHIFT:
|
|
|
|
hugepage_size = _PAGE_SZ64K_4V;
|
|
|
|
break;
|
2017-02-02 00:16:36 +00:00
|
|
|
default:
|
|
|
|
WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift);
|
|
|
|
}
|
|
|
|
|
|
|
|
pte_val(entry) = pte_val(entry) | hugepage_size;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift)
|
|
|
|
{
|
|
|
|
if (tlb_type == hypervisor)
|
|
|
|
return sun4v_hugepage_shift_to_tte(entry, shift);
|
|
|
|
else
|
|
|
|
return sun4u_hugepage_shift_to_tte(entry, shift);
|
|
|
|
}
|
|
|
|
|
|
|
|
pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
|
|
|
|
struct page *page, int writeable)
|
|
|
|
{
|
|
|
|
unsigned int shift = huge_page_shift(hstate_vma(vma));
|
|
|
|
|
|
|
|
return hugepage_shift_to_tte(entry, shift);
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
|
|
|
|
{
|
|
|
|
unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4V;
|
|
|
|
unsigned int shift;
|
|
|
|
|
|
|
|
switch (tte_szbits) {
|
2017-03-09 22:22:23 +00:00
|
|
|
case _PAGE_SZ2GB_4V:
|
|
|
|
shift = HPAGE_2GB_SHIFT;
|
|
|
|
break;
|
2017-02-02 00:16:36 +00:00
|
|
|
case _PAGE_SZ256MB_4V:
|
|
|
|
shift = HPAGE_256MB_SHIFT;
|
|
|
|
break;
|
|
|
|
case _PAGE_SZ4MB_4V:
|
|
|
|
shift = REAL_HPAGE_SHIFT;
|
|
|
|
break;
|
2017-02-06 20:33:26 +00:00
|
|
|
case _PAGE_SZ64K_4V:
|
|
|
|
shift = HPAGE_64K_SHIFT;
|
|
|
|
break;
|
2017-02-02 00:16:36 +00:00
|
|
|
default:
|
|
|
|
shift = PAGE_SHIFT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return shift;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int sun4u_huge_tte_to_shift(pte_t entry)
|
|
|
|
{
|
|
|
|
unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4U;
|
|
|
|
unsigned int shift;
|
|
|
|
|
|
|
|
switch (tte_szbits) {
|
|
|
|
case _PAGE_SZ256MB_4U:
|
|
|
|
shift = HPAGE_256MB_SHIFT;
|
|
|
|
break;
|
|
|
|
case _PAGE_SZ4MB_4U:
|
|
|
|
shift = REAL_HPAGE_SHIFT;
|
|
|
|
break;
|
2017-02-06 20:33:26 +00:00
|
|
|
case _PAGE_SZ64K_4U:
|
|
|
|
shift = HPAGE_64K_SHIFT;
|
|
|
|
break;
|
2017-02-02 00:16:36 +00:00
|
|
|
default:
|
|
|
|
shift = PAGE_SHIFT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return shift;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int huge_tte_to_shift(pte_t entry)
|
|
|
|
{
|
|
|
|
unsigned long shift;
|
|
|
|
|
|
|
|
if (tlb_type == hypervisor)
|
|
|
|
shift = sun4v_huge_tte_to_shift(entry);
|
|
|
|
else
|
|
|
|
shift = sun4u_huge_tte_to_shift(entry);
|
|
|
|
|
|
|
|
if (shift == PAGE_SHIFT)
|
|
|
|
WARN_ONCE(1, "tto_to_shift: invalid hugepage tte=0x%lx\n",
|
|
|
|
pte_val(entry));
|
|
|
|
|
|
|
|
return shift;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long huge_tte_to_size(pte_t pte)
|
|
|
|
{
|
|
|
|
unsigned long size = 1UL << huge_tte_to_shift(pte);
|
|
|
|
|
|
|
|
if (size == REAL_HPAGE_SIZE)
|
|
|
|
size = HPAGE_SIZE;
|
|
|
|
return size;
|
|
|
|
}
|
|
|
|
|
2008-07-24 04:27:41 +00:00
|
|
|
pte_t *huge_pte_alloc(struct mm_struct *mm,
|
|
|
|
unsigned long addr, unsigned long sz)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
pud_t *pud;
|
2017-02-06 20:33:26 +00:00
|
|
|
pmd_t *pmd;
|
2005-04-16 22:20:36 +00:00
|
|
|
pte_t *pte = NULL;
|
|
|
|
|
|
|
|
pgd = pgd_offset(mm, addr);
|
2006-03-22 08:49:59 +00:00
|
|
|
pud = pud_alloc(mm, pgd, addr);
|
2017-02-06 20:33:26 +00:00
|
|
|
if (pud) {
|
|
|
|
pmd = pmd_alloc(mm, pud, addr);
|
|
|
|
if (!pmd)
|
|
|
|
return NULL;
|
|
|
|
|
2017-03-03 22:40:44 +00:00
|
|
|
if (sz >= PMD_SIZE)
|
2017-02-06 20:33:26 +00:00
|
|
|
pte = (pte_t *)pmd;
|
|
|
|
else
|
|
|
|
pte = pte_alloc_map(mm, pmd, addr);
|
|
|
|
}
|
2016-07-29 07:54:21 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
|
2005-06-22 00:14:44 +00:00
|
|
|
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
pud_t *pud;
|
2017-02-06 20:33:26 +00:00
|
|
|
pmd_t *pmd;
|
2005-04-16 22:20:36 +00:00
|
|
|
pte_t *pte = NULL;
|
|
|
|
|
|
|
|
pgd = pgd_offset(mm, addr);
|
2006-03-20 09:17:17 +00:00
|
|
|
if (!pgd_none(*pgd)) {
|
2005-04-16 22:20:36 +00:00
|
|
|
pud = pud_offset(pgd, addr);
|
2017-02-06 20:33:26 +00:00
|
|
|
if (!pud_none(*pud)) {
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
if (!pmd_none(*pmd)) {
|
|
|
|
if (is_hugetlb_pmd(*pmd))
|
|
|
|
pte = (pte_t *)pmd;
|
|
|
|
else
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
|
|
|
}
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2017-02-06 20:33:26 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
|
2005-06-22 00:14:44 +00:00
|
|
|
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
|
|
pte_t *ptep, pte_t entry)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2017-02-06 20:33:26 +00:00
|
|
|
unsigned int i, nptes, orig_shift, shift;
|
2017-02-02 00:16:36 +00:00
|
|
|
unsigned long size;
|
2016-07-29 07:54:21 +00:00
|
|
|
pte_t orig;
|
2005-06-22 00:14:44 +00:00
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
size = huge_tte_to_size(entry);
|
2017-02-06 20:33:26 +00:00
|
|
|
shift = size >= HPAGE_SIZE ? PMD_SHIFT : PAGE_SHIFT;
|
|
|
|
nptes = size >> shift;
|
2017-02-02 00:16:36 +00:00
|
|
|
|
2006-03-22 08:49:59 +00:00
|
|
|
if (!pte_present(*ptep) && pte_present(entry))
|
2017-02-02 00:16:36 +00:00
|
|
|
mm->context.hugetlb_pte_count += nptes;
|
2006-03-22 08:49:59 +00:00
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
addr &= ~(size - 1);
|
2016-07-29 07:54:21 +00:00
|
|
|
orig = *ptep;
|
2017-02-24 11:03:16 +00:00
|
|
|
orig_shift = pte_none(orig) ? PAGE_SHIFT : huge_tte_to_shift(orig);
|
2016-03-30 18:17:13 +00:00
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
for (i = 0; i < nptes; i++)
|
2017-02-06 20:33:26 +00:00
|
|
|
ptep[i] = __pte(pte_val(entry) + (i << shift));
|
2017-02-02 00:16:36 +00:00
|
|
|
|
2017-02-06 20:33:26 +00:00
|
|
|
maybe_tlb_batch_add(mm, addr, ptep, orig, 0, orig_shift);
|
2017-02-02 00:16:36 +00:00
|
|
|
/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
|
|
|
|
if (size == HPAGE_SIZE)
|
|
|
|
maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0,
|
2017-02-06 20:33:26 +00:00
|
|
|
orig_shift);
|
2005-06-22 00:14:44 +00:00
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2005-06-22 00:14:44 +00:00
|
|
|
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
|
|
|
|
pte_t *ptep)
|
|
|
|
{
|
2017-02-02 00:16:36 +00:00
|
|
|
unsigned int i, nptes, hugepage_shift;
|
|
|
|
unsigned long size;
|
2005-06-22 00:14:44 +00:00
|
|
|
pte_t entry;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2005-06-22 00:14:44 +00:00
|
|
|
entry = *ptep;
|
2017-02-02 00:16:36 +00:00
|
|
|
size = huge_tte_to_size(entry);
|
2017-02-06 20:33:26 +00:00
|
|
|
if (size >= HPAGE_SIZE)
|
|
|
|
nptes = size >> PMD_SHIFT;
|
|
|
|
else
|
|
|
|
nptes = size >> PAGE_SHIFT;
|
|
|
|
|
2017-02-24 11:03:16 +00:00
|
|
|
hugepage_shift = pte_none(entry) ? PAGE_SHIFT :
|
|
|
|
huge_tte_to_shift(entry);
|
2017-02-02 00:16:36 +00:00
|
|
|
|
2006-03-22 08:49:59 +00:00
|
|
|
if (pte_present(entry))
|
2017-02-02 00:16:36 +00:00
|
|
|
mm->context.hugetlb_pte_count -= nptes;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
addr &= ~(size - 1);
|
|
|
|
for (i = 0; i < nptes; i++)
|
|
|
|
ptep[i] = __pte(0UL);
|
2005-06-22 00:14:44 +00:00
|
|
|
|
2017-02-02 00:16:36 +00:00
|
|
|
maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_shift);
|
|
|
|
/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
|
|
|
|
if (size == HPAGE_SIZE)
|
|
|
|
maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0,
|
|
|
|
hugepage_shift);
|
2016-03-30 18:17:13 +00:00
|
|
|
|
2005-06-22 00:14:44 +00:00
|
|
|
return entry;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
int pmd_huge(pmd_t pmd)
|
|
|
|
{
|
2016-07-29 07:54:21 +00:00
|
|
|
return !pmd_none(pmd) &&
|
|
|
|
(pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2008-07-24 04:27:50 +00:00
|
|
|
int pud_huge(pud_t pud)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2016-07-29 07:54:21 +00:00
|
|
|
|
|
|
|
static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
|
|
|
|
unsigned long addr)
|
|
|
|
{
|
|
|
|
pgtable_t token = pmd_pgtable(*pmd);
|
|
|
|
|
|
|
|
pmd_clear(pmd);
|
|
|
|
pte_free_tlb(tlb, token, addr);
|
|
|
|
atomic_long_dec(&tlb->mm->nr_ptes);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
|
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
unsigned long floor, unsigned long ceiling)
|
|
|
|
{
|
|
|
|
pmd_t *pmd;
|
|
|
|
unsigned long next;
|
|
|
|
unsigned long start;
|
|
|
|
|
|
|
|
start = addr;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
do {
|
|
|
|
next = pmd_addr_end(addr, end);
|
|
|
|
if (pmd_none(*pmd))
|
|
|
|
continue;
|
|
|
|
if (is_hugetlb_pmd(*pmd))
|
|
|
|
pmd_clear(pmd);
|
|
|
|
else
|
|
|
|
hugetlb_free_pte_range(tlb, pmd, addr);
|
|
|
|
} while (pmd++, addr = next, addr != end);
|
|
|
|
|
|
|
|
start &= PUD_MASK;
|
|
|
|
if (start < floor)
|
|
|
|
return;
|
|
|
|
if (ceiling) {
|
|
|
|
ceiling &= PUD_MASK;
|
|
|
|
if (!ceiling)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (end - 1 > ceiling - 1)
|
|
|
|
return;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, start);
|
|
|
|
pud_clear(pud);
|
|
|
|
pmd_free_tlb(tlb, pmd, start);
|
|
|
|
mm_dec_nr_pmds(tlb->mm);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
|
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
unsigned long floor, unsigned long ceiling)
|
|
|
|
{
|
|
|
|
pud_t *pud;
|
|
|
|
unsigned long next;
|
|
|
|
unsigned long start;
|
|
|
|
|
|
|
|
start = addr;
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
|
|
do {
|
|
|
|
next = pud_addr_end(addr, end);
|
|
|
|
if (pud_none_or_clear_bad(pud))
|
|
|
|
continue;
|
|
|
|
hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
|
|
|
|
ceiling);
|
|
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
|
|
|
|
start &= PGDIR_MASK;
|
|
|
|
if (start < floor)
|
|
|
|
return;
|
|
|
|
if (ceiling) {
|
|
|
|
ceiling &= PGDIR_MASK;
|
|
|
|
if (!ceiling)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (end - 1 > ceiling - 1)
|
|
|
|
return;
|
|
|
|
|
|
|
|
pud = pud_offset(pgd, start);
|
|
|
|
pgd_clear(pgd);
|
|
|
|
pud_free_tlb(tlb, pud, start);
|
|
|
|
}
|
|
|
|
|
|
|
|
void hugetlb_free_pgd_range(struct mmu_gather *tlb,
|
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
unsigned long floor, unsigned long ceiling)
|
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
unsigned long next;
|
|
|
|
|
2017-04-17 22:46:41 +00:00
|
|
|
addr &= PMD_MASK;
|
|
|
|
if (addr < floor) {
|
|
|
|
addr += PMD_SIZE;
|
|
|
|
if (!addr)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (ceiling) {
|
|
|
|
ceiling &= PMD_MASK;
|
|
|
|
if (!ceiling)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (end - 1 > ceiling - 1)
|
|
|
|
end -= PMD_SIZE;
|
|
|
|
if (addr > end - 1)
|
|
|
|
return;
|
|
|
|
|
2016-07-29 07:54:21 +00:00
|
|
|
pgd = pgd_offset(tlb->mm, addr);
|
|
|
|
do {
|
|
|
|
next = pgd_addr_end(addr, end);
|
|
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
|
|
continue;
|
|
|
|
hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
|
|
|
|
} while (pgd++, addr = next, addr != end);
|
|
|
|
}
|