return NULL;
}
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+ if (flags & FOLL_PIN) {
+ mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
+ refs);
+
+ if (hpage_pincount_available(page))
+ hpage_pincount_sub(page, refs);
+ else
+ refs *= GUP_PIN_COUNTING_BIAS;
+ }
+
+ VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+ /*
+ * Calling put_page() for each ref is unnecessarily slow. Only the last
+ * ref needs a put_page().
+ */
+ if (refs > 1)
+ page_ref_sub(page, refs - 1);
+ put_page(page);
+}
+
/**
* try_grab_page() - elevate a page's refcount by a flag-dependent amount
*
return true;
}
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-static bool __unpin_devmap_managed_user_page(struct page *page)
-{
- int count, refs = 1;
-
- if (!page_is_devmap_managed(page))
- return false;
-
- if (hpage_pincount_available(page))
- hpage_pincount_sub(page, 1);
- else
- refs = GUP_PIN_COUNTING_BIAS;
-
- count = page_ref_sub_return(page, refs);
-
- mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
- /*
- * devmap page refcounts are 1-based, rather than 0-based: if
- * refcount is 1, then the page is free and the refcount is
- * stable because nobody holds a reference on the page.
- */
- if (count == 1)
- free_devmap_managed_page(page);
- else if (!count)
- __put_page(page);
-
- return true;
-}
-#else
-static bool __unpin_devmap_managed_user_page(struct page *page)
-{
- return false;
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
/**
* unpin_user_page() - release a dma-pinned page
* @page: pointer to page to be released
*/
void unpin_user_page(struct page *page)
{
- int refs = 1;
-
- page = compound_head(page);
-
- /*
- * For devmap managed pages we need to catch refcount transition from
- * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the
- * page is free and we need to inform the device driver through
- * callback. See include/linux/memremap.h and HMM for details.
- */
- if (__unpin_devmap_managed_user_page(page))
- return;
-
- if (hpage_pincount_available(page))
- hpage_pincount_sub(page, 1);
- else
- refs = GUP_PIN_COUNTING_BIAS;
-
- if (page_ref_sub_and_test(page, refs))
- __put_page(page);
-
- mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
+ put_compound_head(compound_head(page), 1, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_page);
if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
return -EFAULT;
+ if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
+ return -EOPNOTSUPP;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
goto next_page;
}
- if (!vma || check_vma_flags(vma, gup_flags)) {
+ if (!vma) {
ret = -EFAULT;
goto out;
}
+ ret = check_vma_flags(vma, gup_flags);
+ if (ret)
+ goto out;
+
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
}
#endif /* CONFIG_ELF_CORE */
-#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
-static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
-{
- long i;
- struct vm_area_struct *vma_prev = NULL;
-
- for (i = 0; i < nr_pages; i++) {
- struct vm_area_struct *vma = vmas[i];
-
- if (vma == vma_prev)
- continue;
-
- vma_prev = vma;
-
- if (vma_is_fsdax(vma))
- return true;
- }
- return false;
-}
-
#ifdef CONFIG_CMA
static long check_and_migrate_cma_pages(struct mm_struct *mm,
unsigned long start,
struct vm_area_struct **vmas,
unsigned int gup_flags)
{
- struct vm_area_struct **vmas_tmp = vmas;
unsigned long flags = 0;
- long rc, i;
+ long rc;
- if (gup_flags & FOLL_LONGTERM) {
- if (!pages)
- return -EINVAL;
-
- if (!vmas_tmp) {
- vmas_tmp = kcalloc(nr_pages,
- sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas_tmp)
- return -ENOMEM;
- }
+ if (gup_flags & FOLL_LONGTERM)
flags = memalloc_nocma_save();
- }
- rc = __get_user_pages_locked(mm, start, nr_pages, pages,
- vmas_tmp, NULL, gup_flags);
+ rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
+ gup_flags);
if (gup_flags & FOLL_LONGTERM) {
- if (rc < 0)
- goto out;
-
- if (check_dax_vmas(vmas_tmp, rc)) {
- if (gup_flags & FOLL_PIN)
- unpin_user_pages(pages, rc);
- else
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
- rc = -EOPNOTSUPP;
- goto out;
- }
-
- rc = check_and_migrate_cma_pages(mm, start, rc, pages,
- vmas_tmp, gup_flags);
-out:
+ if (rc > 0)
+ rc = check_and_migrate_cma_pages(mm, start, rc, pages,
+ vmas, gup_flags);
memalloc_nocma_restore(flags);
}
-
- if (vmas_tmp != vmas)
- kfree(vmas_tmp);
return rc;
}
-#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
-static __always_inline long __gup_longterm_locked(struct mm_struct *mm,
- unsigned long start,
- unsigned long nr_pages,
- struct page **pages,
- struct vm_area_struct **vmas,
- unsigned int flags)
-{
- return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
- NULL, flags);
-}
-#endif /* CONFIG_FS_DAX || CONFIG_CMA */
static bool is_valid_gup_flags(unsigned int gup_flags)
{
EXPORT_SYMBOL(get_user_pages);
/**
- * get_user_pages_locked() is suitable to replace the form:
+ * get_user_pages_locked() - variant of get_user_pages()
+ *
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup 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.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * It is suitable to replace the form:
*
* mmap_read_lock(mm);
* do_something()
* if (locked)
* mmap_read_unlock(mm);
*
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying lookup 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.
- * @locked: pointer to lock flag indicating whether lock is held and
- * subsequently whether VM_FAULT_RETRY functionality can be
- * utilised. Lock must initially be held.
- *
* We can leverage the VM_FAULT_RETRY functionality in the page fault
* paths better by using either get_user_pages_locked() or
* get_user_pages_unlocked().
*/
#ifdef CONFIG_HAVE_FAST_GUP
-static void put_compound_head(struct page *page, int refs, unsigned int flags)
-{
- if (flags & FOLL_PIN) {
- mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
- refs);
-
- if (hpage_pincount_available(page))
- hpage_pincount_sub(page, refs);
- else
- refs *= GUP_PIN_COUNTING_BIAS;
- }
-
- VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
- /*
- * Calling put_page() for each ref is unnecessarily slow. Only the last
- * ref needs a put_page().
- */
- if (refs > 1)
- page_ref_sub(page, refs - 1);
- put_page(page);
-}
-
-#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
-
-/*
- * WARNING: only to be used in the get_user_pages_fast() implementation.
- *
- * With get_user_pages_fast(), we walk down the pagetables without taking any
- * locks. For this we would like to load the pointers atomically, but sometimes
- * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What
- * we do have is the guarantee that a PTE will only either go from not present
- * to present, or present to not present or both -- it will not switch to a
- * completely different present page without a TLB flush in between; something
- * that we are blocking by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- *
- * ptep->pte_high = h;
- * smp_wmb();
- * ptep->pte_low = l;
- *
- * And present to not present goes:
- *
- * ptep->pte_low = 0;
- * smp_wmb();
- * ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
- * We load pte_high *after* loading pte_low, which ensures we don't see an older
- * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't
- * picked up a changed pte high. We might have gotten rubbish values from
- * pte_low and pte_high, but we are guaranteed that pte_low will not have the
- * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
- * operates on present ptes we're safe.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
- pte_t pte;
-
- do {
- pte.pte_low = ptep->pte_low;
- smp_rmb();
- pte.pte_high = ptep->pte_high;
- smp_rmb();
- } while (unlikely(pte.pte_low != ptep->pte_low));
-
- return pte;
-}
-#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
-/*
- * We require that the PTE can be read atomically.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
- return ptep_get(ptep);
-}
-#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
-
static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
unsigned int flags,
struct page **pages)
ptem = ptep = pte_offset_map(&pmd, addr);
do {
- pte_t pte = gup_get_pte(ptep);
+ pte_t pte = ptep_get_lockless(ptep);
struct page *head, *page;
/*
return ret;
}
-static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+static unsigned long lockless_pages_from_mm(unsigned long start,
+ unsigned long end,
+ unsigned int gup_flags,
+ struct page **pages)
+{
+ unsigned long flags;
+ int nr_pinned = 0;
+ unsigned seq;
+
+ if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
+ !gup_fast_permitted(start, end))
+ return 0;
+
+ if (gup_flags & FOLL_PIN) {
+ seq = raw_read_seqcount(¤t->mm->write_protect_seq);
+ if (seq & 1)
+ return 0;
+ }
+
+ /*
+ * Disable interrupts. The nested form is used, in order to allow full,
+ * general purpose use of this routine.
+ *
+ * With interrupts disabled, we block page table pages from being freed
+ * from under us. See struct mmu_table_batch comments in
+ * include/asm-generic/tlb.h for more details.
+ *
+ * We do not adopt an rcu_read_lock() here as we also want to block IPIs
+ * that come from THPs splitting.
+ */
+ local_irq_save(flags);
+ gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
+ local_irq_restore(flags);
+
+ /*
+ * When pinning pages for DMA there could be a concurrent write protect
+ * from fork() via copy_page_range(), in this case always fail fast GUP.
+ */
+ if (gup_flags & FOLL_PIN) {
+ if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) {
+ unpin_user_pages(pages, nr_pinned);
+ return 0;
+ }
+ }
+ return nr_pinned;
+}
+
+static int internal_get_user_pages_fast(unsigned long start,
+ unsigned long nr_pages,
unsigned int gup_flags,
struct page **pages)
{
- unsigned long addr, len, end;
- unsigned long flags;
- int nr_pinned = 0, ret = 0;
+ unsigned long len, end;
+ unsigned long nr_pinned;
+ int ret;
if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
FOLL_FORCE | FOLL_PIN | FOLL_GET |
might_lock_read(¤t->mm->mmap_lock);
start = untagged_addr(start) & PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- if (end <= start)
+ len = nr_pages << PAGE_SHIFT;
+ if (check_add_overflow(start, len, &end))
return 0;
if (unlikely(!access_ok((void __user *)start, len)))
return -EFAULT;
- /*
- * Disable interrupts. The nested form is used, in order to allow
- * full, general purpose use of this routine.
- *
- * With interrupts disabled, we block page table pages from being
- * freed from under us. See struct mmu_table_batch comments in
- * include/asm-generic/tlb.h for more details.
- *
- * We do not adopt an rcu_read_lock(.) here as we also want to
- * block IPIs that come from THPs splitting.
- */
- if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) {
- unsigned long fast_flags = gup_flags;
+ nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
+ if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
+ return nr_pinned;
- local_irq_save(flags);
- gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned);
- local_irq_restore(flags);
- ret = nr_pinned;
- }
-
- if (nr_pinned < nr_pages && !(gup_flags & FOLL_FAST_ONLY)) {
- /* Try to get the remaining pages with get_user_pages */
- start += nr_pinned << PAGE_SHIFT;
- pages += nr_pinned;
-
- ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned,
- gup_flags, pages);
-
- /* Have to be a bit careful with return values */
- if (nr_pinned > 0) {
- if (ret < 0)
- ret = nr_pinned;
- else
- ret += nr_pinned;
- }
+ /* Slow path: try to get the remaining pages with get_user_pages */
+ start += nr_pinned << PAGE_SHIFT;
+ pages += nr_pinned;
+ ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
+ pages);
+ if (ret < 0) {
+ /*
+ * The caller has to unpin the pages we already pinned so
+ * returning -errno is not an option
+ */
+ if (nr_pinned)
+ return nr_pinned;
+ return ret;
}
-
- return ret;
+ return ret + nr_pinned;
}
+
/**
* get_user_pages_fast_only() - pin user pages in memory
* @start: starting user address
projects / linux-2.6-microblaze.git / blobdiff