linux/arch/x86/mm/hugetlbpage.c

192 lines
4.6 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/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);
mm/hugetlb: add size parameter to huge_pte_offset() 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>
2017-07-06 22:39:42 +00:00
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
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>
2015-02-11 23:25:19 +00:00
/*
* 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>
2015-02-11 23:25:19 +00:00
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 13:17:50 +00:00
#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;
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 &&
mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov <oleg@redhat.com> Original-patch-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Helge Deller <deller@gmx.de> # parisc Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 11:03:24 +00:00
(!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);
}
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 13:17:50 +00:00
#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