mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 18:13:04 +00:00
7868a2087e
A poisoned or migrated hugepage is stored as a swap entry in the page tables. On architectures that support hugepages consisting of contiguous page table entries (such as on arm64) this leads to ambiguity in determining the page table entry to return in huge_pte_offset() when a poisoned entry is encountered. Let's remove the ambiguity by adding a size parameter to convey additional information about the requested address. Also fixup the definition/usage of huge_pte_offset() throughout the tree. Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Steve Capper <steve.capper@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE) Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
192 lines
4.6 KiB
C
192 lines
4.6 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/sched/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/compat.h>
|
|
#include <asm/mman.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/elf.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, vma_mmu_pagesize(vma));
|
|
|
|
/* 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
|
|
|
|
/*
|
|
* pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
|
|
* hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
|
|
* Otherwise, returns 0.
|
|
*/
|
|
int pmd_huge(pmd_t pmd)
|
|
{
|
|
return !pmd_none(pmd) &&
|
|
(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
|
|
}
|
|
|
|
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 = get_mmap_base(1);
|
|
info.high_limit = in_compat_syscall() ?
|
|
tasksize_32bit() : tasksize_64bit();
|
|
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 = get_mmap_base(0);
|
|
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 <= vm_start_gap(vma)))
|
|
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 && boot_cpu_has(X86_FEATURE_GBPAGES)) {
|
|
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
|
|
} else {
|
|
hugetlb_bad_size();
|
|
printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
|
|
ps >> 20);
|
|
return 0;
|
|
}
|
|
return 1;
|
|
}
|
|
__setup("hugepagesz=", setup_hugepagesz);
|
|
|
|
#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
|
|
static __init int gigantic_pages_init(void)
|
|
{
|
|
/* With compaction or CMA we can allocate gigantic pages at runtime */
|
|
if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT))
|
|
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
|
|
return 0;
|
|
}
|
|
arch_initcall(gigantic_pages_init);
|
|
#endif
|
|
#endif
|