OpenCloudOS-Kernel/arch/x86/mm/hugetlbpage.c

188 lines
4.4 KiB
C
Raw Normal View History

/*
* 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
mm/hugetlb: pmd_huge() returns true for non-present hugepage Migrating hugepages and hwpoisoned hugepages are considered as non-present hugepages, and they are referenced via migration entries and hwpoison entries in their page table slots. This behavior causes race condition because pmd_huge() doesn't tell non-huge pages from migrating/hwpoisoned hugepages. follow_page_mask() is one example where the kernel would call follow_page_pte() for such hugepage while this function is supposed to handle only normal pages. To avoid this, this patch makes pmd_huge() return true when pmd_none() is true *and* pmd_present() is false. We don't have to worry about mixing up non-present pmd entry with normal pmd (pointing to leaf level pte entry) because pmd_present() is true in normal pmd. The same race condition could happen in (x86-specific) gup_pmd_range(), where this patch simply adds pmd_present() check instead of pmd_huge(). This is because gup_pmd_range() is fast path. If we have non-present hugepage in this function, we will go into gup_huge_pmd(), then return 0 at flag mask check, and finally fall back to the slow path. Fixes: 290408d4a2 ("hugetlb: hugepage migration core") Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: 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> Cc: <stable@vger.kernel.org> [2.6.36+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:25:19 +08:00
/*
* 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)
{
mm/hugetlb: pmd_huge() returns true for non-present hugepage Migrating hugepages and hwpoisoned hugepages are considered as non-present hugepages, and they are referenced via migration entries and hwpoison entries in their page table slots. This behavior causes race condition because pmd_huge() doesn't tell non-huge pages from migrating/hwpoisoned hugepages. follow_page_mask() is one example where the kernel would call follow_page_pte() for such hugepage while this function is supposed to handle only normal pages. To avoid this, this patch makes pmd_huge() return true when pmd_none() is true *and* pmd_present() is false. We don't have to worry about mixing up non-present pmd entry with normal pmd (pointing to leaf level pte entry) because pmd_present() is true in normal pmd. The same race condition could happen in (x86-specific) gup_pmd_range(), where this patch simply adds pmd_present() check instead of pmd_huge(). This is because gup_pmd_range() is fast path. If we have non-present hugepage in this function, we will go into gup_huge_pmd(), then return 0 at flag mask check, and finally fall back to the slow path. Fixes: 290408d4a2 ("hugetlb: hugepage migration core") Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: 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> Cc: <stable@vger.kernel.org> [2.6.36+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:25:19 +08:00
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
x86/mm: Implement ASLR for hugetlb mappings Matthew noticed that hugetlb mappings don't participate in ASLR on x86-64: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 /proc/PID/maps entries for the mapping are always the same (except inode number): 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 8200 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 256 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 7180 /anon_hugepage (deleted) The reason is the generic hugetlb_get_unmapped_area() function which is used on x86-64. It doesn't support randomization and use bottom-up unmapped area lookup, instead of usual top-down on x86-64. x86 has arch-specific hugetlb_get_unmapped_area(), but it's used only on x86-32. Let's use arch-specific hugetlb_get_unmapped_area() on x86-64 too. That adds ASLR and switches hugetlb mappings to use top-down unmapped area lookup: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x7f4f08a00000 Returned address is 0x7fdda4200000 Returned address is 0x7febe0000000 /proc/PID/maps entries: 7f4f08a00000-7f4f18a00000 rw-p 00000000 00:0c 1168 /anon_hugepage (deleted) 7fdda4200000-7fddb4200000 rw-p 00000000 00:0c 7092 /anon_hugepage (deleted) 7febe0000000-7febf0000000 rw-p 00000000 00:0c 7183 /anon_hugepage (deleted) Unmapped area lookup policy for hugetlb mappings is consistent with normal mappings now -- the only difference is alignment requirements for huge pages. libhugetlbfs test-suite didn't detect any regressions with the patch applied (although it shows few failures on my machine regardless the patch). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mel Gorman <mgorman@suse.de> Link: http://lkml.kernel.org/r/20131119131750.EA45CE0090@blue.fi.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-19 21:17:50 +08:00
#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;
x86/mm: Implement ASLR for hugetlb mappings Matthew noticed that hugetlb mappings don't participate in ASLR on x86-64: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 /proc/PID/maps entries for the mapping are always the same (except inode number): 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 8200 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 256 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 7180 /anon_hugepage (deleted) The reason is the generic hugetlb_get_unmapped_area() function which is used on x86-64. It doesn't support randomization and use bottom-up unmapped area lookup, instead of usual top-down on x86-64. x86 has arch-specific hugetlb_get_unmapped_area(), but it's used only on x86-32. Let's use arch-specific hugetlb_get_unmapped_area() on x86-64 too. That adds ASLR and switches hugetlb mappings to use top-down unmapped area lookup: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x7f4f08a00000 Returned address is 0x7fdda4200000 Returned address is 0x7febe0000000 /proc/PID/maps entries: 7f4f08a00000-7f4f18a00000 rw-p 00000000 00:0c 1168 /anon_hugepage (deleted) 7fdda4200000-7fddb4200000 rw-p 00000000 00:0c 7092 /anon_hugepage (deleted) 7febe0000000-7febf0000000 rw-p 00000000 00:0c 7183 /anon_hugepage (deleted) Unmapped area lookup policy for hugetlb mappings is consistent with normal mappings now -- the only difference is alignment requirements for huge pages. libhugetlbfs test-suite didn't detect any regressions with the patch applied (although it shows few failures on my machine regardless the patch). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mel Gorman <mgorman@suse.de> Link: http://lkml.kernel.org/r/20131119131750.EA45CE0090@blue.fi.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-19 21:17:50 +08:00
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);
}
x86/mm: Implement ASLR for hugetlb mappings Matthew noticed that hugetlb mappings don't participate in ASLR on x86-64: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 Returned address is 0x2aaaaac00000 /proc/PID/maps entries for the mapping are always the same (except inode number): 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 8200 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 256 /anon_hugepage (deleted) 2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 7180 /anon_hugepage (deleted) The reason is the generic hugetlb_get_unmapped_area() function which is used on x86-64. It doesn't support randomization and use bottom-up unmapped area lookup, instead of usual top-down on x86-64. x86 has arch-specific hugetlb_get_unmapped_area(), but it's used only on x86-32. Let's use arch-specific hugetlb_get_unmapped_area() on x86-64 too. That adds ASLR and switches hugetlb mappings to use top-down unmapped area lookup: % for i in `seq 3`; do > tools/testing/selftests/vm/map_hugetlb | grep address > done Returned address is 0x7f4f08a00000 Returned address is 0x7fdda4200000 Returned address is 0x7febe0000000 /proc/PID/maps entries: 7f4f08a00000-7f4f18a00000 rw-p 00000000 00:0c 1168 /anon_hugepage (deleted) 7fdda4200000-7fddb4200000 rw-p 00000000 00:0c 7092 /anon_hugepage (deleted) 7febe0000000-7febf0000000 rw-p 00000000 00:0c 7183 /anon_hugepage (deleted) Unmapped area lookup policy for hugetlb mappings is consistent with normal mappings now -- the only difference is alignment requirements for huge pages. libhugetlbfs test-suite didn't detect any regressions with the patch applied (although it shows few failures on my machine regardless the patch). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mel Gorman <mgorman@suse.de> Link: http://lkml.kernel.org/r/20131119131750.EA45CE0090@blue.fi.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-19 21:17:50 +08:00
#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