linux-brain/mm/pgtable-generic.c

212 lines
5.3 KiB
C
Raw Normal View History

/*
* mm/pgtable-generic.c
*
* Generic pgtable methods declared in asm-generic/pgtable.h
*
* Copyright (C) 2010 Linus Torvalds
*/
#include <linux/pagemap.h>
#include <asm/tlb.h>
#include <asm-generic/pgtable.h>
/*
* If a p?d_bad entry is found while walking page tables, report
* the error, before resetting entry to p?d_none. Usually (but
* very seldom) called out from the p?d_none_or_clear_bad macros.
*/
void pgd_clear_bad(pgd_t *pgd)
{
pgd_ERROR(*pgd);
pgd_clear(pgd);
}
void p4d_clear_bad(p4d_t *p4d)
{
p4d_ERROR(*p4d);
p4d_clear(p4d);
}
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
pud_clear(pud);
}
void pmd_clear_bad(pmd_t *pmd)
{
pmd_ERROR(*pmd);
pmd_clear(pmd);
}
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
/*
* Only sets the access flags (dirty, accessed), as well as write
* permission. Furthermore, we know it always gets set to a "more
* permissive" setting, which allows most architectures to optimize
* this. We return whether the PTE actually changed, which in turn
* instructs the caller to do things like update__mmu_cache. This
* used to be done in the caller, but sparc needs minor faults to
* force that call on sun4c so we changed this macro slightly
*/
int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
int changed = !pte_same(*ptep, entry);
if (changed) {
set_pte_at(vma->vm_mm, address, ptep, entry);
flush_tlb_fix_spurious_fault(vma, address);
}
return changed;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
int young;
young = ptep_test_and_clear_young(vma, address, ptep);
if (young)
flush_tlb_page(vma, address);
return young;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
struct mm_struct *mm = (vma)->vm_mm;
pte_t pte;
pte = ptep_get_and_clear(mm, address, ptep);
if (pte_accessible(mm, pte))
flush_tlb_page(vma, address);
return pte;
}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty)
{
int changed = !pmd_same(*pmdp, entry);
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
if (changed) {
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
return changed;
}
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
int young;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
young = pmdp_test_and_clear_young(vma, address, pmdp);
if (young)
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return young;
}
#endif
#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
mm: thp: enable thp migration in generic path Add thp migration's core code, including conversions between a PMD entry and a swap entry, setting PMD migration entry, removing PMD migration entry, and waiting on PMD migration entries. This patch makes it possible to support thp migration. If you fail to allocate a destination page as a thp, you just split the source thp as we do now, and then enter the normal page migration. If you succeed to allocate destination thp, you enter thp migration. Subsequent patches actually enable thp migration for each caller of page migration by allowing its get_new_page() callback to allocate thps. [zi.yan@cs.rutgers.edu: fix gcc-4.9.0 -Wmissing-braces warning] Link: http://lkml.kernel.org/r/A0ABA698-7486-46C3-B209-E95A9048B22C@cs.rutgers.edu [akpm@linux-foundation.org: fix x86_64 allnoconfig warning] Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 08:10:57 +09:00
VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
!pmd_devmap(*pmdp)) || !pmd_present(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 07:57:02 +09:00
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
pud_t *pudp)
{
pud_t pud;
VM_BUG_ON(address & ~HPAGE_PUD_MASK);
VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
return pud;
}
#endif
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable)
{
assert_spin_locked(pmd_lockptr(mm, pmdp));
/* FIFO */
2013-11-15 07:30:59 +09:00
if (!pmd_huge_pte(mm, pmdp))
INIT_LIST_HEAD(&pgtable->lru);
else
2013-11-15 07:30:59 +09:00
list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
pmd_huge_pte(mm, pmdp) = pgtable;
}
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
/* no "address" argument so destroys page coloring of some arch */
pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
pgtable_t pgtable;
assert_spin_locked(pmd_lockptr(mm, pmdp));
/* FIFO */
2013-11-15 07:30:59 +09:00
pgtable = pmd_huge_pte(mm, pmdp);
pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru,
struct page, lru);
if (pmd_huge_pte(mm, pmdp))
list_del(&pgtable->lru);
return pgtable;
}
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t entry = *pmdp;
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
#endif
#ifndef pmdp_collapse_flush
pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
/*
* pmd and hugepage pte format are same. So we could
* use the same function.
*/
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
VM_BUG_ON(pmd_trans_huge(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
mm,thp: khugepaged: call pte flush at the time of collapse This showed up on ARC when running LMBench bw_mem tests as Overlapping TLB Machine Check Exception triggered due to STLB entry (2M pages) overlapping some NTLB entry (regular 8K page). bw_mem 2m touches a large chunk of vaddr creating NTLB entries. In the interim khugepaged kicks in, collapsing the contiguous ptes into a single pmd. pmdp_collapse_flush()->flush_pmd_tlb_range() is called to flush out NTLB entries for the ptes. This for ARC (by design) can only shootdown STLB entries (for pmd). The stray NTLB entries cause the overlap with the subsequent STLB entry for collapsed page. So make pmdp_collapse_flush() call pte flush interface not pmd flush. Note that originally all thp flush call sites in generic code called flush_tlb_range() leaving it to architecture to implement the flush for pte and/or pmd. Commit 12ebc1581ad11454 changed this by calling a new opt-in API flush_pmd_tlb_range() which made the semantics more explicit but failed to distinguish the pte vs pmd flush in generic code, which is what this patch fixes. Note that ARC can fixed w/o touching the generic pmdp_collapse_flush() by defining a ARC version, but that defeats the purpose of generic version, plus sementically this is the right thing to do. Fixes STAR 9000961194: LMBench on AXS103 triggering duplicate TLB exceptions with super pages Fixes: 12ebc1581ad11454 ("mm,thp: introduce flush_pmd_tlb_range") Signed-off-by: Vineet Gupta <vgupta@synopsys.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: <stable@vger.kernel.org> [4.4] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-12 09:13:09 +09:00
/* collapse entails shooting down ptes not pmd */
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */