Skip to content
Snippets Groups Projects
  • Hugh Dickins's avatar
    mm/thp: fix __split_huge_pmd_locked() on shmem migration entry · 99fa8a48
    Hugh Dickins authored
    Patch series "mm/thp: fix THP splitting unmap BUGs and related", v10.
    
    Here is v2 batch of long-standing THP bug fixes that I had not got
    around to sending before, but prompted now by Wang Yugui's report
    https://lore.kernel.org/linux-mm/20210412180659.B9E3.409509F4@e16-tech.com/
    
    Wang Yugui has tested a rollup of these fixes applied to 5.10.39, and
    they have done no harm, but have *not* fixed that issue: something more
    is needed and I have no idea of what.
    
    This patch (of 7):
    
    Stressing huge tmpfs page migration racing hole punch often crashed on
    the VM_BUG_ON(!pmd_present) in pmdp_huge_clear_flush(), with DEBUG_VM=y
    kernel; or shortly afterwards, on a bad dereference in
    __split_huge_pmd_locked() when DEBUG_VM=n.  They forgot to allow for pmd
    migration entries in the non-anonymous case.
    
    Full disclosure: those particular experiments were on a kernel with more
    relaxed mmap_lock and i_mmap_rwsem locking, and were not repeated on the
    vanilla kernel: it is conceivable that stricter locking happens to avoid
    those cases, or makes them less likely; but __split_huge_pmd_locked()
    already allowed for pmd migration entries when handling anonymous THPs,
    so this commit brings the shmem and file THP handling into line.
    
    And while there: use old_pmd rather than _pmd, as in the following
    blocks; and make it clearer to the eye that the !vma_is_anonymous()
    block is self-contained, making an early return after accounting for
    unmapping.
    
    Link: https://lkml.kernel.org/r/af88612-1473-2eaa-903-8d1a448b26@google.com
    Link: https://lkml.kernel.org/r/dd221a99-efb3-cd1d-6256-7e646af29314@google.com
    
    
    Fixes: e71769ae ("mm: enable thp migration for shmem thp")
    Signed-off-by: default avatarHugh Dickins <hughd@google.com>
    Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
    Cc: Yang Shi <shy828301@gmail.com>
    Cc: Wang Yugui <wangyugui@e16-tech.com>
    Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
    Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
    Cc: Alistair Popple <apopple@nvidia.com>
    Cc: Ralph Campbell <rcampbell@nvidia.com>
    Cc: Zi Yan <ziy@nvidia.com>
    Cc: Miaohe Lin <linmiaohe@huawei.com>
    Cc: Minchan Kim <minchan@kernel.org>
    Cc: Jue Wang <juew@google.com>
    Cc: Peter Xu <peterx@redhat.com>
    Cc: Jan Kara <jack@suse.cz>
    Cc: Shakeel Butt <shakeelb@google.com>
    Cc: Oscar Salvador <osalvador@suse.de>
    Cc: <stable@vger.kernel.org>
    Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
    Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
    99fa8a48
Code owners
Assign users and groups as approvers for specific file changes. Learn more.
pgtable-generic.c 5.56 KiB
// SPDX-License-Identifier: GPL-2.0
/*
 *  mm/pgtable-generic.c
 *
 *  Generic pgtable methods declared in linux/pgtable.h
 *
 *  Copyright (C) 2010  Linus Torvalds
 */

#include <linux/pagemap.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <asm/tlb.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);
}

#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *p4d)
{
	p4d_ERROR(*p4d);
	p4d_clear(p4d);
}
#endif

#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *pud)
{
	pud_ERROR(*pud);
	pud_clear(pud);
}
#endif

/*
 * Note that the pmd variant below can't be stub'ed out just as for p4d/pud
 * above. pmd folding is special and typically pmd_* macros refer to upper
 * level even when folded
 */
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);
	VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
			   !pmd_devmap(*pmdp));
	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return pmd;
}

#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 */
	if (!pmd_huge_pte(mm, pmdp))
		INIT_LIST_HEAD(&pgtable->lru);
	else
		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 */
	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
pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
		     pmd_t *pmdp)
{
	pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return old;
}
#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);

	/* collapse entails shooting down ptes not pmd */
	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return pmd;
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */