linux-next/arch/x86/mm/hugetlbpage.c
Naoya Horiguchi 61f77eda9b mm/hugetlb: reduce arch dependent code around follow_huge_*
Currently we have many duplicates in definitions around
follow_huge_addr(), follow_huge_pmd(), and follow_huge_pud(), so this
patch tries to remove the m.  The basic idea is to put the default
implementation for these functions in mm/hugetlb.c as weak symbols
(regardless of CONFIG_ARCH_WANT_GENERAL_HUGETL B), and to implement
arch-specific code only when the arch needs it.

For follow_huge_addr(), only powerpc and ia64 have their own
implementation, and in all other architectures this function just returns
ERR_PTR(-EINVAL).  So this patch sets returning ERR_PTR(-EINVAL) as
default.

As for follow_huge_(pmd|pud)(), if (pmd|pud)_huge() is implemented to
always return 0 in your architecture (like in ia64 or sparc,) it's never
called (the callsite is optimized away) no matter how implemented it is.
So in such architectures, we don't need arch-specific implementation.

In some architecture (like mips, s390 and tile,) their current
arch-specific follow_huge_(pmd|pud)() are effectively identical with the
common code, so this patch lets these architecture use the common code.

One exception is metag, where pmd_huge() could return non-zero but it
expects follow_huge_pmd() to always return NULL.  This means that we need
arch-specific implementation which returns NULL.  This behavior looks
strange to me (because non-zero pmd_huge() implies that the architecture
supports PMD-based hugepage, so follow_huge_pmd() can/should return some
relevant value,) but that's beyond this cleanup patch, so let's keep it.

Justification of non-trivial changes:
- in s390, follow_huge_pmd() checks !MACHINE_HAS_HPAGE at first, and this
  patch removes the check. This is OK because we can assume MACHINE_HAS_HPAGE
  is true when follow_huge_pmd() can be called (note that pmd_huge() has
  the same check and always returns 0 for !MACHINE_HAS_HPAGE.)
- in s390 and mips, we use HPAGE_MASK instead of PMD_MASK as done in common
  code. This patch forces these archs use PMD_MASK, but it's OK because
  they are identical in both archs.
  In s390, both of HPAGE_SHIFT and PMD_SHIFT are 20.
  In mips, HPAGE_SHIFT is defined as (PAGE_SHIFT + PAGE_SHIFT - 3) and
  PMD_SHIFT is define as (PAGE_SHIFT + PAGE_SHIFT + PTE_ORDER - 3), but
  PTE_ORDER is always 0, so these are identical.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Steve Capper <steve.capper@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 17:06:01 -08:00

181 lines
4.1 KiB
C

/*
* 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/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.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);
/* 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
int pmd_huge(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_PSE);
}
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 = current->mm->mmap_legacy_base;
info.high_limit = TASK_SIZE;
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 addr0, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
unsigned long addr;
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = current->mm->mmap_base;
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;
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;
if (len > TASK_SIZE)
return -ENOMEM;
if (flags & MAP_FIXED) {
if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
(!vma || addr + len <= vma->vm_start))
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);
}
#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 && cpu_has_gbpages) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
} else {
printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
ps >> 20);
return 0;
}
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
#ifdef CONFIG_CMA
static __init int gigantic_pages_init(void)
{
/* With CMA we can allocate gigantic pages at runtime */
if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
return 0;
}
arch_initcall(gigantic_pages_init);
#endif
#endif