linux-stable/arch/s390/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

206 lines
5.5 KiB
C

/*
* IBM System z Huge TLB Page Support for Kernel.
*
* Copyright IBM Corp. 2007
* Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
static inline pmd_t __pte_to_pmd(pte_t pte)
{
pmd_t pmd;
/*
* Convert encoding pte bits pmd bits
* .IR...wrdytp dy..R...I...wr
* empty .10...000000 -> 00..0...1...00
* prot-none, clean, old .11...000001 -> 00..1...1...00
* prot-none, clean, young .11...000101 -> 01..1...1...00
* prot-none, dirty, old .10...001001 -> 10..1...1...00
* prot-none, dirty, young .10...001101 -> 11..1...1...00
* read-only, clean, old .11...010001 -> 00..1...1...01
* read-only, clean, young .01...010101 -> 01..1...0...01
* read-only, dirty, old .11...011001 -> 10..1...1...01
* read-only, dirty, young .01...011101 -> 11..1...0...01
* read-write, clean, old .11...110001 -> 00..0...1...11
* read-write, clean, young .01...110101 -> 01..0...0...11
* read-write, dirty, old .10...111001 -> 10..0...1...11
* read-write, dirty, young .00...111101 -> 11..0...0...11
*/
if (pte_present(pte)) {
pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_READ) >> 4;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_WRITE) >> 4;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_INVALID) >> 5;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_PROTECT);
pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10;
} else
pmd_val(pmd) = _SEGMENT_ENTRY_INVALID;
return pmd;
}
static inline pte_t __pmd_to_pte(pmd_t pmd)
{
pte_t pte;
/*
* Convert encoding pmd bits pte bits
* dy..R...I...wr .IR...wrdytp
* empty 00..0...1...00 -> .10...001100
* prot-none, clean, old 00..0...1...00 -> .10...000001
* prot-none, clean, young 01..0...1...00 -> .10...000101
* prot-none, dirty, old 10..0...1...00 -> .10...001001
* prot-none, dirty, young 11..0...1...00 -> .10...001101
* read-only, clean, old 00..1...1...01 -> .11...010001
* read-only, clean, young 01..1...1...01 -> .11...010101
* read-only, dirty, old 10..1...1...01 -> .11...011001
* read-only, dirty, young 11..1...1...01 -> .11...011101
* read-write, clean, old 00..0...1...11 -> .10...110001
* read-write, clean, young 01..0...1...11 -> .10...110101
* read-write, dirty, old 10..0...1...11 -> .10...111001
* read-write, dirty, young 11..0...1...11 -> .10...111101
*/
if (pmd_present(pmd)) {
pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE;
pte_val(pte) |= _PAGE_LARGE | _PAGE_PRESENT;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_READ) << 4;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT);
pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10;
pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10;
} else
pte_val(pte) = _PAGE_INVALID;
return pte;
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
pmd_t pmd;
pmd = __pte_to_pmd(pte);
if (!MACHINE_HAS_HPAGE) {
/* Emulated huge ptes loose the dirty and young bit */
pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
pmd_val(pmd) |= pte_page(pte)[1].index;
} else
pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
*(pmd_t *) ptep = pmd;
}
pte_t huge_ptep_get(pte_t *ptep)
{
unsigned long origin;
pmd_t pmd;
pmd = *(pmd_t *) ptep;
if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) {
origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN;
pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
pmd_val(pmd) |= *(unsigned long *) origin;
/* Emulated huge ptes are young and dirty by definition */
pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG | _SEGMENT_ENTRY_DIRTY;
}
return __pmd_to_pte(pmd);
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pmd_t *pmdp = (pmd_t *) ptep;
pte_t pte = huge_ptep_get(ptep);
pmdp_flush_direct(mm, addr, pmdp);
pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
return pte;
}
int arch_prepare_hugepage(struct page *page)
{
unsigned long addr = page_to_phys(page);
pte_t pte;
pte_t *ptep;
int i;
if (MACHINE_HAS_HPAGE)
return 0;
ptep = (pte_t *) pte_alloc_one(&init_mm, addr);
if (!ptep)
return -ENOMEM;
pte_val(pte) = addr;
for (i = 0; i < PTRS_PER_PTE; i++) {
set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte);
pte_val(pte) += PAGE_SIZE;
}
page[1].index = (unsigned long) ptep;
return 0;
}
void arch_release_hugepage(struct page *page)
{
pte_t *ptep;
if (MACHINE_HAS_HPAGE)
return;
ptep = (pte_t *) page[1].index;
if (!ptep)
return;
clear_table((unsigned long *) ptep, _PAGE_INVALID,
PTRS_PER_PTE * sizeof(pte_t));
page_table_free(&init_mm, (unsigned long *) ptep);
page[1].index = 0;
}
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp = NULL;
pgdp = pgd_offset(mm, addr);
pudp = pud_alloc(mm, pgdp, addr);
if (pudp)
pmdp = pmd_alloc(mm, pudp, addr);
return (pte_t *) pmdp;
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp = NULL;
pgdp = pgd_offset(mm, addr);
if (pgd_present(*pgdp)) {
pudp = pud_offset(pgdp, addr);
if (pud_present(*pudp))
pmdp = pmd_offset(pudp, addr);
}
return (pte_t *) pmdp;
}
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
return 0;
}
int pmd_huge(pmd_t pmd)
{
if (!MACHINE_HAS_HPAGE)
return 0;
return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE);
}
int pud_huge(pud_t pud)
{
return 0;
}