gup.c

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>

#include <linux/mm.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>
#include <linux/sched/mm.h>

#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

#include "internal.h"

struct follow_page_context {
	struct dev_pagemap *pgmap;
	unsigned int page_mask;
};

/*
 * Return the compound head page with ref appropriately incremented,
 * or NULL if that failed.
 */
static inline struct page *try_get_compound_head(struct page *page, int refs)
{
	struct page *head = compound_head(page);

	if (WARN_ON_ONCE(page_ref_count(head) < 0))
		return NULL;
	if (unlikely(!page_cache_add_speculative(head, refs)))
		return NULL;
	return head;
}

/**
 * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
 * @pages:  array of pages to be maybe marked dirty, and definitely released.
 * @npages: number of pages in the @pages array.
 * @make_dirty: whether to mark the pages dirty
 *
 * "gup-pinned page" refers to a page that has had one of the get_user_pages()
 * variants called on that page.
 *
 * For each page in the @pages array, make that page (or its head page, if a
 * compound page) dirty, if @make_dirty is true, and if the page was previously
 * listed as clean. In any case, releases all pages using unpin_user_page(),
 * possibly via unpin_user_pages(), for the non-dirty case.
 *
 * Please see the unpin_user_page() documentation for details.
 *
 * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
 * required, then the caller should a) verify that this is really correct,
 * because _lock() is usually required, and b) hand code it:
 * set_page_dirty_lock(), unpin_user_page().
 *
 */
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
				 bool make_dirty)
{
	unsigned long index;

	/*
	 * TODO: this can be optimized for huge pages: if a series of pages is
	 * physically contiguous and part of the same compound page, then a
	 * single operation to the head page should suffice.
	 */

	if (!make_dirty) {
		unpin_user_pages(pages, npages);
		return;
	}

	for (index = 0; index < npages; index++) {
		struct page *page = compound_head(pages[index]);
		/*
		 * Checking PageDirty at this point may race with
		 * clear_page_dirty_for_io(), but that's OK. Two key
		 * cases:
		 *
		 * 1) This code sees the page as already dirty, so it
		 * skips the call to set_page_dirty(). That could happen
		 * because clear_page_dirty_for_io() called
		 * page_mkclean(), followed by set_page_dirty().
		 * However, now the page is going to get written back,
		 * which meets the original intention of setting it
		 * dirty, so all is well: clear_page_dirty_for_io() goes
		 * on to call TestClearPageDirty(), and write the page
		 * back.
		 *
		 * 2) This code sees the page as clean, so it calls
		 * set_page_dirty(). The page stays dirty, despite being
		 * written back, so it gets written back again in the
		 * next writeback cycle. This is harmless.
		 */
		if (!PageDirty(page))
			set_page_dirty_lock(page);
		unpin_user_page(page);
	}
}
EXPORT_SYMBOL(unpin_user_pages_dirty_lock);

/**
 * unpin_user_pages() - release an array of gup-pinned pages.
 * @pages:  array of pages to be marked dirty and released.
 * @npages: number of pages in the @pages array.
 *
 * For each page in the @pages array, release the page using unpin_user_page().
 *
 * Please see the unpin_user_page() documentation for details.
 */
void unpin_user_pages(struct page **pages, unsigned long npages)
{
	unsigned long index;

	/*
	 * TODO: this can be optimized for huge pages: if a series of pages is
	 * physically contiguous and part of the same compound page, then a
	 * single operation to the head page should suffice.
	 */
	for (index = 0; index < npages; index++)
		unpin_user_page(pages[index]);
}
EXPORT_SYMBOL(unpin_user_pages);

#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
		unsigned int flags)
{
	/*
	 * When core dumping an enormous anonymous area that nobody
	 * has touched so far, we don't want to allocate unnecessary pages or
	 * page tables.  Return error instead of NULL to skip handle_mm_fault,
	 * then get_dump_page() will return NULL to leave a hole in the dump.
	 * But we can only make this optimization where a hole would surely
	 * be zero-filled if handle_mm_fault() actually did handle it.
	 */
	if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
		return ERR_PTR(-EFAULT);
	return NULL;
}

static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
		pte_t *pte, unsigned int flags)
{
	/* No page to get reference */
	if (flags & FOLL_GET)
		return -EFAULT;

	if (flags & FOLL_TOUCH) {
		pte_t entry = *pte;

		if (flags & FOLL_WRITE)
			entry = pte_mkdirty(entry);
		entry = pte_mkyoung(entry);

		if (!pte_same(*pte, entry)) {
			set_pte_at(vma->vm_mm, address, pte, entry);
			update_mmu_cache(vma, address, pte);
		}
	}

	/* Proper page table entry exists, but no corresponding struct page */
	return -EEXIST;
}

/*
 * FOLL_FORCE can write to even unwritable pte's, but only
 * after we've gone through a COW cycle and they are dirty.
 */
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
	return pte_write(pte) ||
		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}

static struct page *follow_page_pte(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd, unsigned int flags,
		struct dev_pagemap **pgmap)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	spinlock_t *ptl;
	pte_t *ptep, pte;

	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
			 (FOLL_PIN | FOLL_GET)))
		return ERR_PTR(-EINVAL);
retry:
	if (unlikely(pmd_bad(*pmd)))
		return no_page_table(vma, flags);

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!pte_present(pte)) {
		swp_entry_t entry;
		/*
		 * KSM's break_ksm() relies upon recognizing a ksm page
		 * even while it is being migrated, so for that case we
		 * need migration_entry_wait().
		 */
		if (likely(!(flags & FOLL_MIGRATION)))
			goto no_page;
		if (pte_none(pte))
			goto no_page;
		entry = pte_to_swp_entry(pte);
		if (!is_migration_entry(entry))
			goto no_page;
		pte_unmap_unlock(ptep, ptl);
		migration_entry_wait(mm, pmd, address);
		goto retry;
	}
	if ((flags & FOLL_NUMA) && pte_protnone(pte))
		goto no_page;
	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
		pte_unmap_unlock(ptep, ptl);
		return NULL;
	}

	page = vm_normal_page(vma, address, pte);
	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
		/*
		 * Only return device mapping pages in the FOLL_GET case since
		 * they are only valid while holding the pgmap reference.
		 */
		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
		if (*pgmap)
			page = pte_page(pte);
		else
			goto no_page;
	} else if (unlikely(!page)) {
		if (flags & FOLL_DUMP) {
			/* Avoid special (like zero) pages in core dumps */
			page = ERR_PTR(-EFAULT);
			goto out;
		}

		if (is_zero_pfn(pte_pfn(pte))) {
			page = pte_page(pte);
		} else {
			int ret;

			ret = follow_pfn_pte(vma, address, ptep, flags);
			page = ERR_PTR(ret);
			goto out;
		}
	}

	if (flags & FOLL_SPLIT && PageTransCompound(page)) {
		int ret;
		get_page(page);
		pte_unmap_unlock(ptep, ptl);
		lock_page(page);
		ret = split_huge_page(page);
		unlock_page(page);
		put_page(page);
		if (ret)
			return ERR_PTR(ret);
		goto retry;
	}

	if (flags & FOLL_GET) {
		if (unlikely(!try_get_page(page))) {
			page = ERR_PTR(-ENOMEM);
			goto out;
		}
	}
	if (flags & FOLL_TOUCH) {
		if ((flags & FOLL_WRITE) &&
		    !pte_dirty(pte) && !PageDirty(page))
			set_page_dirty(page);
		/*
		 * pte_mkyoung() would be more correct here, but atomic care
		 * is needed to avoid losing the dirty bit: it is easier to use
		 * mark_page_accessed().
		 */
		mark_page_accessed(page);
	}
	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
		/* Do not mlock pte-mapped THP */
		if (PageTransCompound(page))
			goto out;

		/*
		 * The preliminary mapping check is mainly to avoid the
		 * pointless overhead of lock_page on the ZERO_PAGE
		 * which might bounce very badly if there is contention.
		 *
		 * If the page is already locked, we don't need to
		 * handle it now - vmscan will handle it later if and
		 * when it attempts to reclaim the page.
		 */
		if (page->mapping && trylock_page(page)) {
			lru_add_drain();  /* push cached pages to LRU */
			/*
			 * Because we lock page here, and migration is
			 * blocked by the pte's page reference, and we
			 * know the page is still mapped, we don't even
			 * need to check for file-cache page truncation.
			 */
			mlock_vma_page(page);
			unlock_page(page);
		}
	}
out:
	pte_unmap_unlock(ptep, ptl);
	return page;
no_page:
	pte_unmap_unlock(ptep, ptl);
	if (!pte_none(pte))
		return NULL;
	return no_page_table(vma, flags);
}

static struct page *follow_pmd_mask(struct vm_area_struct *vma,
				    unsigned long address, pud_t *pudp,
				    unsigned int flags,
				    struct follow_page_context *ctx)
{
	pmd_t *pmd, pmdval;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	pmd = pmd_offset(pudp, address);
	/*
	 * The READ_ONCE() will stabilize the pmdval in a register or
	 * on the stack so that it will stop changing under the code.
	 */
	pmdval = READ_ONCE(*pmd);
	if (pmd_none(pmdval))
		return no_page_table(vma, flags);
	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
		page = follow_huge_pmd(mm, address, pmd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (is_hugepd(__hugepd(pmd_val(pmdval)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(pmd_val(pmdval)), flags,
				      PMD_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
retry:
	if (!pmd_present(pmdval)) {
		if (likely(!(flags & FOLL_MIGRATION)))
			return no_page_table(vma, flags);
		VM_BUG_ON(thp_migration_supported() &&
				  !is_pmd_migration_entry(pmdval));
		if (is_pmd_migration_entry(pmdval))
			pmd_migration_entry_wait(mm, pmd);
		pmdval = READ_ONCE(*pmd);
		/*
		 * MADV_DONTNEED may convert the pmd to null because
		 * mmap_sem is held in read mode
		 */
		if (pmd_none(pmdval))
			return no_page_table(vma, flags);
		goto retry;
	}
	if (pmd_devmap(pmdval)) {
		ptl = pmd_lock(mm, pmd);
		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
		spin_unlock(ptl);
		if (page)
			return page;
	}
	if (likely(!pmd_trans_huge(pmdval)))
		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);

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

retry_locked:
	ptl = pmd_lock(mm, pmd);
	if (unlikely(pmd_none(*pmd))) {
		spin_unlock(ptl);
		return no_page_table(vma, flags);
	}
	if (unlikely(!pmd_present(*pmd))) {
		spin_unlock(ptl);
		if (likely(!(flags & FOLL_MIGRATION)))
			return no_page_table(vma, flags);
		pmd_migration_entry_wait(mm, pmd);
		goto retry_locked;
	}
	if (unlikely(!pmd_trans_huge(*pmd))) {
		spin_unlock(ptl);
		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
	}
	if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
		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 if (flags & FOLL_SPLIT) {
			if (unlikely(!try_get_page(page))) {
				spin_unlock(ptl);
				return ERR_PTR(-ENOMEM);
			}
			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);
		} else {  /* flags & FOLL_SPLIT_PMD */
			spin_unlock(ptl);
			split_huge_pmd(vma, pmd, address);
			ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
		}

		return ret ? ERR_PTR(ret) :
			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
	}
	page = follow_trans_huge_pmd(vma, address, pmd, flags);
	spin_unlock(ptl);
	ctx->page_mask = HPAGE_PMD_NR - 1;
	return page;
}

static struct page *follow_pud_mask(struct vm_area_struct *vma,
				    unsigned long address, p4d_t *p4dp,
				    unsigned int flags,
				    struct follow_page_context *ctx)
{
	pud_t *pud;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	pud = pud_offset(p4dp, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
		page = follow_huge_pud(mm, address, pud, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (is_hugepd(__hugepd(pud_val(*pud)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(pud_val(*pud)), flags,
				      PUD_SHIFT);
		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, &ctx->pgmap);
		spin_unlock(ptl);
		if (page)
			return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	return follow_pmd_mask(vma, address, pud, flags, ctx);
}

static struct page *follow_p4d_mask(struct vm_area_struct *vma,
				    unsigned long address, pgd_t *pgdp,
				    unsigned int flags,
				    struct follow_page_context *ctx)
{
	p4d_t *p4d;
	struct page *page;

	p4d = p4d_offset(pgdp, 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);

	if (is_hugepd(__hugepd(p4d_val(*p4d)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(p4d_val(*p4d)), flags,
				      P4D_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	return follow_pud_mask(vma, address, p4d, flags, ctx);
}

/**
 * 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
 * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
 *       pointer to output page_mask
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
 * the device's dev_pagemap metadata to avoid repeating expensive lookups.
 *
 * On output, the @ctx->page_mask is set according to the size of the page.
 *
 * Return: 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()).
 */
static struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      struct follow_page_context *ctx)
{
	pgd_t *pgd;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	ctx->page_mask = 0;

	/* make this handle hugepd */
	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);

	if (pgd_huge(*pgd)) {
		page = follow_huge_pgd(mm, address, pgd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
	if (is_hugepd(__hugepd(pgd_val(*pgd)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(pgd_val(*pgd)), flags,
				      PGDIR_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}

	return follow_p4d_mask(vma, address, pgd, flags, ctx);
}

struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
			 unsigned int foll_flags)
{
	struct follow_page_context ctx = { NULL };
	struct page *page;

	page = follow_page_mask(vma, address, foll_flags, &ctx);
	if (ctx.pgmap)
		put_dev_pagemap(ctx.pgmap);
	return page;
}

static int get_gate_page(struct mm_struct *mm, unsigned long address,
		unsigned int gup_flags, struct vm_area_struct **vma,
		struct page **page)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int ret = -EFAULT;

	/* user gate pages are read-only */
	if (gup_flags & FOLL_WRITE)
		return -EFAULT;
	if (address > TASK_SIZE)
		pgd = pgd_offset_k(address);
	else
		pgd = pgd_offset_gate(mm, address);
	if (pgd_none(*pgd))
		return -EFAULT;
	p4d = p4d_offset(pgd, address);
	if (p4d_none(*p4d))
		return -EFAULT;
	pud = pud_offset(p4d, address);
	if (pud_none(*pud))
		return -EFAULT;
	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return -EFAULT;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	pte = pte_offset_map(pmd, address);
	if (pte_none(*pte))
		goto unmap;
	*vma = get_gate_vma(mm);
	if (!page)
		goto out;
	*page = vm_normal_page(*vma, address, *pte);
	if (!*page) {
		if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
			goto unmap;
		*page = pte_page(*pte);
	}
	if (unlikely(!try_get_page(*page))) {
		ret = -ENOMEM;
		goto unmap;
	}
out:
	ret = 0;
unmap:
	pte_unmap(pte);
	return ret;
}

/*
 * mmap_sem must be held on entry.  If @nonblocking != NULL and
 * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
 * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
 */
static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
		unsigned long address, unsigned int *flags, int *nonblocking)
{
	unsigned int fault_flags = 0;
	vm_fault_t ret;

	/* mlock all present pages, but do not fault in new pages */
	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
		return -ENOENT;
	if (*flags & FOLL_WRITE)
		fault_flags |= FAULT_FLAG_WRITE;
	if (*flags & FOLL_REMOTE)
		fault_flags |= FAULT_FLAG_REMOTE;
	if (nonblocking)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
	if (*flags & FOLL_NOWAIT)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
	if (*flags & FOLL_TRIED) {
		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
		fault_flags |= FAULT_FLAG_TRIED;
	}

	ret = handle_mm_fault(vma, address, fault_flags);
	if (ret & VM_FAULT_ERROR) {
		int err = vm_fault_to_errno(ret, *flags);

		if (err)
			return err;
		BUG();
	}

	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}

	if (ret & VM_FAULT_RETRY) {
		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
			*nonblocking = 0;
		return -EBUSY;
	}

	/*
	 * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
	 * necessary, even if maybe_mkwrite decided not to set pte_write. We
	 * can thus safely do subsequent page lookups as if they were reads.
	 * But only do so when looping for pte_write is futile: in some cases
	 * userspace may also be wanting to write to the gotten user page,
	 * which a read fault here might prevent (a readonly page might get
	 * reCOWed by userspace write).
	 */
	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
		*flags |= FOLL_COW;
	return 0;
}

static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
	vm_flags_t vm_flags = vma->vm_flags;
	int write = (gup_flags & FOLL_WRITE);
	int foreign = (gup_flags & FOLL_REMOTE);

	if (vm_flags & (VM_IO | VM_PFNMAP))
		return -EFAULT;

	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
		return -EFAULT;

	if (write) {
		if (!(vm_flags & VM_WRITE)) {
			if (!(gup_flags & FOLL_FORCE))
				return -EFAULT;
			/*
			 * We used to let the write,force case do COW in a
			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
			 * set a breakpoint in a read-only mapping of an
			 * executable, without corrupting the file (yet only
			 * when that file had been opened for writing!).
			 * Anon pages in shared mappings are surprising: now
			 * just reject it.
			 */
			if (!is_cow_mapping(vm_flags))
				return -EFAULT;
		}
	} else if (!(vm_flags & VM_READ)) {
		if (!(gup_flags & FOLL_FORCE))
			return -EFAULT;
		/*
		 * Is there actually any vma we can reach here which does not
		 * have VM_MAYREAD set?
		 */
		if (!(vm_flags & VM_MAYREAD))
			return -EFAULT;
	}
	/*
	 * gups are always data accesses, not instruction
	 * fetches, so execute=false here
	 */
	if (!arch_vma_access_permitted(vma, write, false, foreign))
		return -EFAULT;
	return 0;
}

/**
 * __get_user_pages() - pin user pages in memory
 * @tsk:	task_struct of target task
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @gup_flags:	flags modifying pin behaviour
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 * @nonblocking: whether waiting for disk IO or mmap_sem contention
 *
 * Returns either number of pages pinned (which may be less than the
 * number requested), or an error. Details about the return value:
 *
 * -- If nr_pages is 0, returns 0.
 * -- If nr_pages is >0, but no pages were pinned, returns -errno.
 * -- If nr_pages is >0, and some pages were pinned, returns the number of
 *    pages pinned. Again, this may be less than nr_pages.
 *
 * The caller is responsible for releasing returned @pages, via put_page().
 *
 * @vmas are valid only as long as mmap_sem is held.
 *
 * Must be called with mmap_sem held.  It may be released.  See below.
 *
 * __get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * __get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
 * the page is written to, set_page_dirty (or set_page_dirty_lock, as
 * appropriate) must be called after the page is finished with, and
 * before put_page is called.
 *
 * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
 * or mmap_sem contention, and if waiting is needed to pin all pages,
 * *@nonblocking will be set to 0.  Further, if @gup_flags does not
 * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
 * this case.
 *
 * A caller using such a combination of @nonblocking and @gup_flags
 * must therefore hold the mmap_sem for reading only, and recognize
 * when it's been released.  Otherwise, it must be held for either
 * reading or writing and will not be released.
 *
 * In most cases, get_user_pages or get_user_pages_fast should be used
 * instead of __get_user_pages. __get_user_pages should be used only if
 * you need some special @gup_flags.
 */
static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages,
		unsigned int gup_flags, struct page **pages,
		struct vm_area_struct **vmas, int *nonblocking)
{
	long ret = 0, i = 0;
	struct vm_area_struct *vma = NULL;
	struct follow_page_context ctx = { NULL };

	if (!nr_pages)
		return 0;

	start = untagged_addr(start);

	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));

	/*
	 * If FOLL_FORCE is set then do not force a full fault as the hinting
	 * fault information is unrelated to the reference behaviour of a task
	 * using the address space
	 */
	if (!(gup_flags & FOLL_FORCE))
		gup_flags |= FOLL_NUMA;

	do {
		struct page *page;
		unsigned int foll_flags = gup_flags;
		unsigned int page_increm;

		/* first iteration or cross vma bound */
		if (!vma || start >= vma->vm_end) {
			vma = find_extend_vma(mm, start);
			if (!vma && in_gate_area(mm, start)) {
				ret = get_gate_page(mm, start & PAGE_MASK,
						gup_flags, &vma,
						pages ? &pages[i] : NULL);
				if (ret)
					goto out;
				ctx.page_mask = 0;
				goto next_page;
			}

			if (!vma || check_vma_flags(vma, gup_flags)) {
				ret = -EFAULT;
				goto out;
			}
			if (is_vm_hugetlb_page(vma)) {
				i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &nr_pages, i,
						gup_flags, nonblocking);
				continue;
			}
		}
retry:
		/*
		 * If we have a pending SIGKILL, don't keep faulting pages and
		 * potentially allocating memory.
		 */
		if (fatal_signal_pending(current)) {
			ret = -ERESTARTSYS;
			goto out;
		}
		cond_resched();

		page = follow_page_mask(vma, start, foll_flags, &ctx);
		if (!page) {
			ret = faultin_page(tsk, vma, start, &foll_flags,
					nonblocking);
			switch (ret) {
			case 0:
				goto retry;
			case -EBUSY:
				ret = 0;
				/* FALLTHRU */
			case -EFAULT:
			case -ENOMEM:
			case -EHWPOISON:
				goto out;
			case -ENOENT:
				goto next_page;
			}
			BUG();
		} else if (PTR_ERR(page) == -EEXIST) {
			/*
			 * Proper page table entry exists, but no corresponding
			 * struct page.
			 */
			goto next_page;
		} else if (IS_ERR(page)) {
			ret = PTR_ERR(page);
			goto out;
		}
		if (pages) {
			pages[i] = page;
			flush_anon_page(vma, page, start);
			flush_dcache_page(page);
			ctx.page_mask = 0;
		}
next_page:
		if (vmas) {
			vmas[i] = vma;
			ctx.page_mask = 0;
		}
		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
		if (page_increm > nr_pages)
			page_increm = nr_pages;
		i += page_increm;
		start += page_increm * PAGE_SIZE;
		nr_pages -= page_increm;
	} while (nr_pages);
out:
	if (ctx.pgmap)
		put_dev_pagemap(ctx.pgmap);
	return i ? i : ret;
}

static bool vma_permits_fault(struct vm_area_struct *vma,
			      unsigned int fault_flags)
{
	bool write   = !!(fault_flags & FAULT_FLAG_WRITE);
	bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE);
	vm_flags_t vm_flags = write ? VM_WRITE : VM_READ;

	if (!(vm_flags & vma->vm_flags))
		return false;

	/*
	 * The architecture might have a hardware protection
	 * mechanism other than read/write that can deny access.
	 *
	 * gup always represents data access, not instruction
	 * fetches, so execute=false here:
	 */
	if (!arch_vma_access_permitted(vma, write, false, foreign))
		return false;

	return true;
}

/*
 * fixup_user_fault() - manually resolve a user page fault
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @address:	user address
 * @fault_flags:flags to pass down to handle_mm_fault()
 * @unlocked:	did we unlock the mmap_sem while retrying, maybe NULL if caller
 *		does not allow retry
 *
 * This is meant to be called in the specific scenario where for locking reasons
 * we try to access user memory in atomic context (within a pagefault_disable()
 * section), this returns -EFAULT, and we want to resolve the user fault before
 * trying again.
 *
 * Typically this is meant to be used by the futex code.
 *
 * The main difference with get_user_pages() is that this function will
 * unconditionally call handle_mm_fault() which will in turn perform all the
 * necessary SW fixup of the dirty and young bits in the PTE, while
 * get_user_pages() only guarantees to update these in the struct page.
 *
 * This is important for some architectures where those bits also gate the
 * access permission to the page because they are maintained in software.  On
 * such architectures, gup() will not be enough to make a subsequent access
 * succeed.
 *
 * This function will not return with an unlocked mmap_sem. So it has not the
 * same semantics wrt the @mm->mmap_sem as does filemap_fault().
 */
int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long address, unsigned int fault_flags,
		     bool *unlocked)
{
	struct vm_area_struct *vma;
	vm_fault_t ret, major = 0;

	address = untagged_addr(address);

	if (unlocked)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;

retry:
	vma = find_extend_vma(mm, address);
	if (!vma || address < vma->vm_start)
		return -EFAULT;

	if (!vma_permits_fault(vma, fault_flags))
		return -EFAULT;

	ret = handle_mm_fault(vma, address, fault_flags);
	major |= ret & VM_FAULT_MAJOR;
	if (ret & VM_FAULT_ERROR) {
		int err = vm_fault_to_errno(ret, 0);

		if (err)
			return err;
		BUG();
	}

	if (ret & VM_FAULT_RETRY) {
		down_read(&mm->mmap_sem);
		if (!(fault_flags & FAULT_FLAG_TRIED)) {
			*unlocked = true;
			fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
			fault_flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}

	if (tsk) {
		if (major)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(fixup_user_fault);

static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
						struct mm_struct *mm,
						unsigned long start,
						unsigned long nr_pages,
						struct page **pages,
						struct vm_area_struct **vmas,
						int *locked,
						unsigned int flags)
{
	long ret, pages_done;
	bool lock_dropped;

	if (locked) {
		/* if VM_FAULT_RETRY can be returned, vmas become invalid */
		BUG_ON(vmas);
		/* check caller initialized locked */
		BUG_ON(*locked != 1);
	}

	/*
	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
	 * is to set FOLL_GET if the caller wants pages[] filled in (but has
	 * carelessly failed to specify FOLL_GET), so keep doing that, but only
	 * for FOLL_GET, not for the newer FOLL_PIN.
	 *
	 * FOLL_PIN always expects pages to be non-null, but no need to assert
	 * that here, as any failures will be obvious enough.
	 */
	if (pages && !(flags & FOLL_PIN))
		flags |= FOLL_GET;

	pages_done = 0;
	lock_dropped = false;
	for (;;) {
		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
				       vmas, locked);
		if (!locked)
			/* VM_FAULT_RETRY couldn't trigger, bypass */
			return ret;

		/* VM_FAULT_RETRY cannot return errors */
		if (!*locked) {
			BUG_ON(ret < 0);
			BUG_ON(ret >= nr_pages);
		}

		if (ret > 0) {
			nr_pages -= ret;
			pages_done += ret;
			if (!nr_pages)
				break;
		}
		if (*locked) {
			/*
			 * VM_FAULT_RETRY didn't trigger or it was a
			 * FOLL_NOWAIT.
			 */
			if (!pages_done)
				pages_done = ret;
			break;
		}
		/*
		 * VM_FAULT_RETRY triggered, so seek to the faulting offset.
		 * For the prefault case (!pages) we only update counts.
		 */
		if (likely(pages))
			pages += ret;