linux/arch/x86/mm/hugetlbpage.c
Naoya Horiguchi 1fdbed657a arch/x86/mm/hugetlbpage.c: pud_huge() returns 0 when using 2-level paging
The following bug is reported to be triggered when starting X on x86-32
system with i915:

  [  225.777375] kernel BUG at mm/memory.c:2664!
  [  225.777391] invalid opcode: 0000 [#1] PREEMPT SMP
  [  225.777405] CPU: 0 PID: 2402 Comm: Xorg Not tainted 6.1.0-rc3-bdg+ #86
  [  225.777415] Hardware name:  /8I865G775-G, BIOS F1 08/29/2006
  [  225.777421] EIP: __apply_to_page_range+0x24d/0x31c
  [  225.777437] Code: ff ff 8b 55 e8 8b 45 cc e8 0a 11 ec ff 89 d8 83 c4 28 5b 5e 5f 5d c3 81 7d e0 a0 ef 96 c1 74 ad 8b 45 d0 e8 2d 83 49 00 eb a3 <0f> 0b 25 00 f0 ff ff 81 eb 00 00 00 40 01 c3 8b 45 ec 8b 00 e8 76
  [  225.777446] EAX: 00000001 EBX: c53a3b58 ECX: b5c00000 EDX: c258aa00
  [  225.777454] ESI: b5c00000 EDI: b5900000 EBP: c4b0fdb4 ESP: c4b0fd80
  [  225.777462] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 EFLAGS: 00010202
  [  225.777470] CR0: 80050033 CR2: b5900000 CR3: 053a3000 CR4: 000006d0
  [  225.777479] Call Trace:
  [  225.777486]  ? i915_memcpy_init_early+0x63/0x63 [i915]
  [  225.777684]  apply_to_page_range+0x21/0x27
  [  225.777694]  ? i915_memcpy_init_early+0x63/0x63 [i915]
  [  225.777870]  remap_io_mapping+0x49/0x75 [i915]
  [  225.778046]  ? i915_memcpy_init_early+0x63/0x63 [i915]
  [  225.778220]  ? mutex_unlock+0xb/0xd
  [  225.778231]  ? i915_vma_pin_fence+0x6d/0xf7 [i915]
  [  225.778420]  vm_fault_gtt+0x2a9/0x8f1 [i915]
  [  225.778644]  ? lock_is_held_type+0x56/0xe7
  [  225.778655]  ? lock_is_held_type+0x7a/0xe7
  [  225.778663]  ? 0xc1000000
  [  225.778670]  __do_fault+0x21/0x6a
  [  225.778679]  handle_mm_fault+0x708/0xb21
  [  225.778686]  ? mt_find+0x21e/0x5ae
  [  225.778696]  exc_page_fault+0x185/0x705
  [  225.778704]  ? doublefault_shim+0x127/0x127
  [  225.778715]  handle_exception+0x130/0x130
  [  225.778723] EIP: 0xb700468a

Recently pud_huge() got aware of non-present entry by commit 3a194f3f8a
("mm/hugetlb: make pud_huge() and follow_huge_pud() aware of non-present
pud entry") to handle some special states of gigantic page.  However, it's
overlooked that pud_none() always returns false when running with 2-level
paging, and as a result pud_huge() can return true pointlessly.

Introduce "#if CONFIG_PGTABLE_LEVELS > 2" to pud_huge() to deal with this.

Link: https://lkml.kernel.org/r/20221107021010.2449306-1-naoya.horiguchi@linux.dev
Fixes: 3a194f3f8a ("mm/hugetlb: make pud_huge() and follow_huge_pud() aware of non-present pud entry")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-11-08 15:57:25 -08:00

175 lines
4.3 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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/elf.h>
/*
* 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;
}
/*
* pud_huge() returns 1 if @pud is hugetlb related entry, that is normal
* hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
* Otherwise, returns 0.
*/
int pud_huge(pud_t pud)
{
#if CONFIG_PGTABLE_LEVELS > 2
return !pud_none(pud) &&
(pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
#else
return 0;
#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);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
* in the full address space.
*/
info.high_limit = in_32bit_syscall() ?
task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
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 addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
* in the full address space.
*/
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
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_LOW;
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;
/* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED) {
if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
addr &= huge_page_mask(h);
if (!mmap_address_hint_valid(addr, len))
goto get_unmapped_area;
vma = find_vma(mm, addr);
if (!vma || addr + len <= vm_start_gap(vma))
return addr;
}
get_unmapped_area:
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
bool __init arch_hugetlb_valid_size(unsigned long size)
{
if (size == PMD_SIZE)
return true;
else if (size == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES))
return true;
else
return false;
}
#ifdef CONFIG_CONTIG_ALLOC
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))
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
return 0;
}
arch_initcall(gigantic_pages_init);
#endif
#endif