Beispiel #1
0
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = *pmdp;

		next = pmd_addr_end(addr, end);
		if (pmd_none(pmd))
			return 0;
		if (pmd_huge(pmd)) {
			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
					 write, pages, nr))
				return 0;
		} else if (is_hugepd(pmdp)) {
			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
					addr, next, write, pages, nr))
				return 0;
		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
			return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}
Beispiel #2
0
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = ACCESS_ONCE(*pmdp);

		next = pmd_addr_end(addr, end);
		/*
		 * If we find a splitting transparent hugepage we
		 * return zero. That will result in taking the slow
		 * path which will call wait_split_huge_page()
		 * if the pmd is still in splitting state
		 */
		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
			return 0;
		if (pmd_huge(pmd) || pmd_large(pmd)) {
			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
					 write, pages, nr))
				return 0;
		} else if (is_hugepd(pmdp)) {
			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
					addr, next, write, pages, nr))
				return 0;
		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
			return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}
static void change_page_attr(unsigned long addr, int numpages,
			     pte_t (*set) (pte_t))
{
	pte_t *ptep, pte;
	pmd_t *pmdp;
	pud_t *pudp;
	pgd_t *pgdp;
	int i;

	for (i = 0; i < numpages; i++) {
		pgdp = pgd_offset(&init_mm, addr);
		pudp = pud_offset(pgdp, addr);
		pmdp = pmd_offset(pudp, addr);
		if (pmd_huge(*pmdp)) {
			WARN_ON_ONCE(1);
			continue;
		}
		ptep = pte_offset_kernel(pmdp, addr);

		pte = *ptep;
		pte = set(pte);
		__ptep_ipte(addr, ptep);
		*ptep = pte;
		addr += PAGE_SIZE;
	}
}
Beispiel #4
0
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
#ifdef CONFIG_HUGETLB_SUPER_PAGES
	pte_t *pte;
#endif

	/* Get the top-level page table entry. */
	pgd = (pgd_t *)get_pte((pte_t *)mm->pgd, pgd_index(addr), 0);

	/* We don't have four levels. */
	pud = pud_offset(pgd, addr);
#ifndef __PAGETABLE_PUD_FOLDED
# error support fourth page table level
#endif
	if (!pud_present(*pud))
		return NULL;

	/* Check for an L0 huge PTE, if we have three levels. */
#ifndef __PAGETABLE_PMD_FOLDED
	if (pud_huge(*pud))
		return (pte_t *)pud;

	pmd = (pmd_t *)get_pte((pte_t *)pud_page_vaddr(*pud),
			       pmd_index(addr), 1);
	if (!pmd_present(*pmd))
		return NULL;
#else
	pmd = pmd_offset(pud, addr);
#endif

	/* Check for an L1 huge PTE. */
	if (pmd_huge(*pmd))
		return (pte_t *)pmd;

#ifdef CONFIG_HUGETLB_SUPER_PAGES
	/* Check for an L2 huge PTE. */
	pte = get_pte((pte_t *)pmd_page_vaddr(*pmd), pte_index(addr), 2);
	if (!pte_present(*pte))
		return NULL;
	if (pte_super(*pte))
		return pte;
#endif

	return NULL;
}
Beispiel #5
0
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = READ_ONCE(*pmdp);

		next = pmd_addr_end(addr, end);
		/*
		 * If we find a splitting transparent hugepage we
		 * return zero. That will result in taking the slow
		 * path which will call wait_split_huge_page()
		 * if the pmd is still in splitting state
		 */
		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
			return 0;
		if (pmd_huge(pmd) || pmd_large(pmd)) {
			/*
			 * NUMA hinting faults need to be handled in the GUP
			 * slowpath for accounting purposes and so that they
			 * can be serialised against THP migration.
			 */
			if (pmd_numa(pmd))
				return 0;

			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
					 write, pages, nr))
				return 0;
		} else if (is_hugepd(pmdp)) {
			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
					addr, next, write, pages, nr))
				return 0;
		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
			return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}
Beispiel #6
0
void radix__change_memory_range(unsigned long start, unsigned long end,
				unsigned long clear)
{
	unsigned long idx;
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	start = ALIGN_DOWN(start, PAGE_SIZE);
	end = PAGE_ALIGN(end); // aligns up

	pr_debug("Changing flags on range %lx-%lx removing 0x%lx\n",
		 start, end, clear);

	for (idx = start; idx < end; idx += PAGE_SIZE) {
		pgdp = pgd_offset_k(idx);
		pudp = pud_alloc(&init_mm, pgdp, idx);
		if (!pudp)
			continue;
		if (pud_huge(*pudp)) {
			ptep = (pte_t *)pudp;
			goto update_the_pte;
		}
		pmdp = pmd_alloc(&init_mm, pudp, idx);
		if (!pmdp)
			continue;
		if (pmd_huge(*pmdp)) {
			ptep = pmdp_ptep(pmdp);
			goto update_the_pte;
		}
		ptep = pte_alloc_kernel(pmdp, idx);
		if (!ptep)
			continue;
update_the_pte:
		radix__pte_update(&init_mm, idx, ptep, clear, 0, 0);
	}

	radix__flush_tlb_kernel_range(start, end);
}
Beispiel #7
0
/*
 * Handle a fault on the vmalloc area.
 */
static inline int vmalloc_fault(pgd_t *pgd, unsigned long address)
{
	pmd_t *pmd_k;
	pte_t *pte_k;

	/* Make sure we are in vmalloc area */
	if (!(address >= VMALLOC_START && address < VMALLOC_END))
		return -1;

	/*
	 * Synchronize this task's top level page-table
	 * with the 'reference' page table.
	 */
	pmd_k = vmalloc_sync_one(pgd, address);
	if (!pmd_k)
		return -1;
	if (pmd_huge(*pmd_k))
		return 0;   /* support TILE huge_vmap() API */
	pte_k = pte_offset_kernel(pmd_k, address);
	if (!pte_present(*pte_k))
		return -1;
	return 0;
}
Beispiel #8
0
pte_t *huge_pte_offset(struct mm_struct *mm,
		       unsigned long addr, unsigned long sz)
{
	pgd_t *pgdp;
	pud_t *pudp, pud;
	pmd_t *pmdp, pmd;

	pgdp = pgd_offset(mm, addr);
	if (!pgd_present(READ_ONCE(*pgdp)))
		return NULL;

	pudp = pud_offset(pgdp, addr);
	pud = READ_ONCE(*pudp);
	if (sz != PUD_SIZE && pud_none(pud))
		return NULL;
	/* hugepage or swap? */
	if (pud_huge(pud) || !pud_present(pud))
		return (pte_t *)pudp;
	/* table; check the next level */

	if (sz == CONT_PMD_SIZE)
		addr &= CONT_PMD_MASK;

	pmdp = pmd_offset(pudp, addr);
	pmd = READ_ONCE(*pmdp);
	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
	    pmd_none(pmd))
		return NULL;
	if (pmd_huge(pmd) || !pmd_present(pmd))
		return (pte_t *)pmdp;

	if (sz == CONT_PTE_SIZE)
		return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));

	return NULL;
}
Beispiel #9
0
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd = NULL;
	pte_t *pte = NULL;

	pgd = pgd_offset(mm, addr);
	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
	if (!pgd_present(*pgd))
		return NULL;
	pud = pud_offset(pgd, addr);
	if (!pud_present(*pud))
		return NULL;

	if (pud_huge(*pud))
		return (pte_t *)pud;
	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd))
		return NULL;

	if (pte_cont(pmd_pte(*pmd))) {
		pmd = pmd_offset(
			pud, (addr & CONT_PMD_MASK));
		return (pte_t *)pmd;
	}
	if (pmd_huge(*pmd))
		return (pte_t *)pmd;
	pte = pte_offset_kernel(pmd, addr);
	if (pte_present(*pte) && pte_cont(*pte)) {
		pte = pte_offset_kernel(
			pmd, (addr & CONT_PTE_MASK));
		return pte;
	}
	return NULL;
}
Beispiel #10
0
/*
 * For hugepage we have pfn in the pmd, we use PTE_RPN_SHIFT bits for flags
 * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address.
 */
struct page *pmd_page(pmd_t pmd)
{
	if (pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))
		return pte_page(pmd_pte(pmd));
	return virt_to_page(pmd_page_vaddr(pmd));
}
Beispiel #11
0
/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
 * @page_mask: on output, *page_mask is set according to the size of the page
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * Returns the mapped (struct page *), %NULL if no mapping exists, or
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      unsigned int *page_mask)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	*page_mask = 0;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		return page;
	}

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);
	p4d = p4d_offset(pgd, address);
	if (p4d_none(*p4d))
		return no_page_table(vma, flags);
	BUILD_BUG_ON(p4d_huge(*p4d));
	if (unlikely(p4d_bad(*p4d)))
		return no_page_table(vma, flags);
	pud = pud_offset(p4d, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pud(mm, address, pud, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (pud_devmap(*pud)) {
		ptl = pud_lock(mm, pud);
		page = follow_devmap_pud(vma, address, pud, flags);
		spin_unlock(ptl);
		if (page)
			return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return no_page_table(vma, flags);
	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pmd(mm, address, pmd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (pmd_devmap(*pmd)) {
		ptl = pmd_lock(mm, pmd);
		page = follow_devmap_pmd(vma, address, pmd, flags);
		spin_unlock(ptl);
		if (page)
			return page;
	}
	if (likely(!pmd_trans_huge(*pmd)))
		return follow_page_pte(vma, address, pmd, flags);

	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
		return no_page_table(vma, flags);

	ptl = pmd_lock(mm, pmd);
	if (unlikely(!pmd_trans_huge(*pmd))) {
		spin_unlock(ptl);
		return follow_page_pte(vma, address, pmd, flags);
	}
	if (flags & FOLL_SPLIT) {
		int ret;
		page = pmd_page(*pmd);
		if (is_huge_zero_page(page)) {
			spin_unlock(ptl);
			ret = 0;
			split_huge_pmd(vma, pmd, address);
			if (pmd_trans_unstable(pmd))
				ret = -EBUSY;
		} else {
			get_page(page);
			spin_unlock(ptl);
			lock_page(page);
			ret = split_huge_page(page);
			unlock_page(page);
			put_page(page);
			if (pmd_none(*pmd))
				return no_page_table(vma, flags);
		}

		return ret ? ERR_PTR(ret) :
			follow_page_pte(vma, address, pmd, flags);
	}

	page = follow_trans_huge_pmd(vma, address, pmd, flags);
	spin_unlock(ptl);
	*page_mask = HPAGE_PMD_NR - 1;
	return page;
}
Beispiel #12
0
/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
 * @page_mask: on output, *page_mask is set according to the size of the page
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * Returns the mapped (struct page *), %NULL if no mapping exists, or
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      unsigned int *page_mask)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	*page_mask = 0;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		return page;
	}

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		if (flags & FOLL_GET)
			return NULL;
		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
		return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return no_page_table(vma, flags);
	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
		if (flags & FOLL_GET) {
			/*
			 * Refcount on tail pages are not well-defined and
			 * shouldn't be taken. The caller should handle a NULL
			 * return when trying to follow tail pages.
			 */
			if (PageHead(page))
				get_page(page);
			else
				page = NULL;
		}
		return page;
	}
	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
		return no_page_table(vma, flags);
	if (pmd_trans_huge(*pmd)) {
		if (flags & FOLL_SPLIT) {
			split_huge_page_pmd(vma, address, pmd);
			return follow_page_pte(vma, address, pmd, flags);
		}
		ptl = pmd_lock(mm, pmd);
		if (likely(pmd_trans_huge(*pmd))) {
			if (unlikely(pmd_trans_splitting(*pmd))) {
				spin_unlock(ptl);
				wait_split_huge_page(vma->anon_vma, pmd);
			} else {
				page = follow_trans_huge_pmd(vma, address,
							     pmd, flags);
				spin_unlock(ptl);
				*page_mask = HPAGE_PMD_NR - 1;
				return page;
			}
		} else
			spin_unlock(ptl);
	}
	return follow_page_pte(vma, address, pmd, flags);
}
Beispiel #13
0
/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
 * @page_mask: on output, *page_mask is set according to the size of the page
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * Returns the mapped (struct page *), %NULL if no mapping exists, or
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      unsigned int *page_mask)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	*page_mask = 0;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		return page;
	}

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pud(mm, address, pud, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return no_page_table(vma, flags);
	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pmd(mm, address, pmd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
		return no_page_table(vma, flags);
	if (pmd_trans_huge(*pmd)) {
		if (flags & FOLL_SPLIT) {
			split_huge_page_pmd(vma, address, pmd);
			return follow_page_pte(vma, address, pmd, flags);
		}
		ptl = pmd_lock(mm, pmd);
		if (likely(pmd_trans_huge(*pmd))) {
			if (unlikely(pmd_trans_splitting(*pmd))) {
				spin_unlock(ptl);
				wait_split_huge_page(vma->anon_vma, pmd);
			} else {
				page = follow_trans_huge_pmd(vma, address,
							     pmd, flags);
				spin_unlock(ptl);
				*page_mask = HPAGE_PMD_NR - 1;
				return page;
			}
		} else
			spin_unlock(ptl);
	}
	return follow_page_pte(vma, address, pmd, flags);
}