sparc64: Fix get_user_pages_fast() wrt. THP.

Mostly mirrors the s390 logic, as unlike x86 we don't need the
SetPageReferenced() bits.

On sparc64 we also lack a user/privileged bit in the huge PMDs.

In order to make this work for THP and non-THP builds, some header
file adjustments were necessary.  Namely, provide the PMD_HUGE_* bit
defines and the pmd_large() inline unconditionally rather than
protected by TRANSPARENT_HUGEPAGE.

Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2013-02-13 12:21:06 -08:00
parent b9156ebb7b
commit 89a77915e0
2 changed files with 63 additions and 10 deletions

View File

@ -71,7 +71,6 @@
#define PMD_PADDR _AC(0xfffffffe,UL)
#define PMD_PADDR_SHIFT _AC(11,UL)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define PMD_ISHUGE _AC(0x00000001,UL)
/* This is the PMD layout when PMD_ISHUGE is set. With 4MB huge
@ -86,7 +85,6 @@
#define PMD_HUGE_ACCESSED _AC(0x00000080,UL)
#define PMD_HUGE_EXEC _AC(0x00000040,UL)
#define PMD_HUGE_SPLITTING _AC(0x00000020,UL)
#endif
/* PGDs point to PMD tables which are 8K aligned. */
#define PGD_PADDR _AC(0xfffffffc,UL)
@ -628,6 +626,12 @@ static inline unsigned long pte_special(pte_t pte)
return pte_val(pte) & _PAGE_SPECIAL;
}
static inline int pmd_large(pmd_t pmd)
{
return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) ==
(PMD_ISHUGE | PMD_HUGE_PRESENT);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_young(pmd_t pmd)
{
@ -646,12 +650,6 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return val >> (PAGE_SHIFT - PMD_PADDR_SHIFT);
}
static inline int pmd_large(pmd_t pmd)
{
return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) ==
(PMD_ISHUGE | PMD_HUGE_PRESENT);
}
static inline int pmd_trans_splitting(pmd_t pmd)
{
return (pmd_val(pmd) & (PMD_ISHUGE|PMD_HUGE_SPLITTING)) ==

View File

@ -66,6 +66,56 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
return 1;
}
static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages,
int *nr)
{
struct page *head, *page, *tail;
u32 mask;
int refs;
mask = PMD_HUGE_PRESENT;
if (write)
mask |= PMD_HUGE_WRITE;
if ((pmd_val(pmd) & mask) != mask)
return 0;
refs = 0;
head = pmd_page(pmd);
page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
tail = page;
do {
VM_BUG_ON(compound_head(page) != head);
pages[*nr] = page;
(*nr)++;
page++;
refs++;
} while (addr += PAGE_SIZE, addr != end);
if (!page_cache_add_speculative(head, refs)) {
*nr -= refs;
return 0;
}
if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
*nr -= refs;
while (refs--)
put_page(head);
return 0;
}
/* Any tail page need their mapcount reference taken before we
* return.
*/
while (refs--) {
if (PageTail(tail))
get_huge_page_tail(tail);
tail++;
}
return 1;
}
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
@ -77,9 +127,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
pmd_t pmd = *pmdp;
next = pmd_addr_end(addr, end);
if (pmd_none(pmd))
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
if (!gup_pte_range(pmd, addr, next, write, pages, nr))
if (unlikely(pmd_large(pmd))) {
if (!gup_huge_pmd(pmdp, pmd, addr, next,
write, pages, nr))
return 0;
} else if (!gup_pte_range(pmd, addr, next, write,
pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);