[PATCH v7 00/24] mm/gup: track dma-pinned pages: FOLL_PIN

@@ -183,12 +183,12 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
 		data, size, dma->nr_pages);
 
-	err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+	err = pin_user_pages(data & PAGE_MASK, dma->nr_pages,
 			     flags | FOLL_LONGTERM, dma->pages, NULL);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
-		dprintk(1, "get_user_pages: err=%d [%d]\n", err,
+		dprintk(1, "pin_user_pages: err=%d [%d]\n", err,
 			dma->nr_pages);
 		return err < 0 ? err : -EINVAL;
 	}

@@ -349,11 +349,8 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
 	BUG_ON(dma->sglen);
 
 	if (dma->pages) {
-		for (i = 0; i < dma->nr_pages; i++) {
-			if (dma->direction == DMA_FROM_DEVICE)
-				set_page_dirty_lock(dma->pages[i]);
-			put_page(dma->pages[i]);
-		}
+		put_user_pages_dirty_lock(dma->pages, dma->nr_pages,
+					  dma->direction == DMA_FROM_DEVICE);
 		kfree(dma->pages);
 		dma->pages = NULL;
 	}

@@ -271,16 +271,13 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 	sg = umem->sg_head.sgl;
 
 	while (npages) {
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(cur_base,
-				     min_t(unsigned long, npages,
-					   PAGE_SIZE / sizeof (struct page *)),
-				     gup_flags | FOLL_LONGTERM,
-				     page_list, NULL);
-		if (ret < 0) {
-			up_read(&mm->mmap_sem);
+		ret = get_user_pages_fast(cur_base,
+					  min_t(unsigned long, npages,
+						PAGE_SIZE /
+						sizeof(struct page *)),
+					  gup_flags | FOLL_LONGTERM, page_list);
+		if (ret < 0)
 			goto umem_release;
-		}
 
 		cur_base += ret * PAGE_SIZE;
 		npages   -= ret;

@@ -288,8 +285,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 		sg = ib_umem_add_sg_table(sg, page_list, ret,
 			dma_get_max_seg_size(context->device->dma_device),
 			&umem->sg_nents);
-
-		up_read(&mm->mmap_sem);
 	}
 
 	sg_mark_end(sg);

@@ -271,7 +271,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 	sg = umem->sg_head.sgl;
 
 	while (npages) {
-		ret = get_user_pages_fast(cur_base,
+		ret = pin_user_pages_fast(cur_base,
 					  min_t(unsigned long, npages,
 						PAGE_SIZE /
 						sizeof(struct page *)),

@@ -495,9 +495,8 @@ EXPORT_SYMBOL(ib_umem_odp_release);
  * The function returns -EFAULT if the DMA mapping operation fails. It returns
  * -EAGAIN if a concurrent invalidation prevents us from updating the page.
  *
- * The page is released via put_user_page even if the operation failed. For
- * on-demand pinning, the page is released whenever it isn't stored in the
- * umem.
+ * The page is released via put_page even if the operation failed. For on-demand
+ * pinning, the page is released whenever it isn't stored in the umem.
  */
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,

@@ -542,7 +541,7 @@ static int ib_umem_odp_map_dma_single_page(
 	}
 
 out:
-	put_user_page(page);
+	put_page(page);
 
 	if (remove_existing_mapping) {
 		ib_umem_notifier_start_account(umem_odp);

@@ -665,7 +664,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 					ret = -EFAULT;
 					break;
 				}
-				put_user_page(local_page_list[j]);
+				put_page(local_page_list[j]);
 				continue;
 			}
 

@@ -692,8 +691,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			 * ib_umem_odp_map_dma_single_page().
 			 */
 			if (npages - (j + 1) > 0)
-				put_user_pages(&local_page_list[j+1],
-					       npages - (j + 1));
+				release_pages(&local_page_list[j+1],
+					      npages - (j + 1));
 			break;
 		}
 	}

@@ -106,7 +106,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 	int ret;
 	unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0);
 
-	ret = get_user_pages_fast(vaddr, npages, gup_flags, pages);
+	ret = pin_user_pages_fast(vaddr, npages, gup_flags, pages);
 	if (ret < 0)
 		return ret;
 

@@ -472,7 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 		goto out;
 	}
 
-	ret = get_user_pages_fast(uaddr & PAGE_MASK, 1,
+	ret = pin_user_pages_fast(uaddr & PAGE_MASK, 1,
 				  FOLL_WRITE | FOLL_LONGTERM, pages);
 	if (ret < 0)
 		goto out;

@@ -108,7 +108,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 
 	down_read(&current->mm->mmap_sem);
 	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages(start_page + got * PAGE_SIZE,
+		ret = pin_user_pages(start_page + got * PAGE_SIZE,
 				     num_pages - got,
 				     FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);

@@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 		else
 			j = npages;
 
-		ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
+		ret = pin_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
 		if (ret != j) {
 			i = 0;
 			j = ret;

@@ -141,7 +141,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	ret = 0;
 
 	while (npages) {
-		ret = get_user_pages(cur_base,
+		ret = pin_user_pages(cur_base,
 				     min_t(unsigned long, npages,
 				     PAGE_SIZE / sizeof(struct page *)),
 				     gup_flags | FOLL_LONGTERM,

@@ -426,7 +426,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
 		while (nents) {
 			struct page **plist = &umem->page_chunk[i].plist[got];
 
-			rv = get_user_pages(first_page_va, nents,
+			rv = pin_user_pages(first_page_va, nents,
 					    foll_flags | FOLL_LONGTERM,
 					    plist, NULL);
 			if (rv < 0)

@@ -274,7 +274,7 @@ static int pin_goldfish_pages(unsigned long first_page,
 		*iter_last_page_size = last_page_size;
 	}
 
-	ret = get_user_pages_fast(first_page, requested_pages,
+	ret = pin_user_pages_fast(first_page, requested_pages,
 				  !is_write ? FOLL_WRITE : 0,
 				  pages);
 	if (ret <= 0)

@@ -285,18 +285,6 @@ static int pin_goldfish_pages(unsigned long first_page,
 	return ret;
 }
 
-static void release_user_pages(struct page **pages, int pages_count,
-			       int is_write, s32 consumed_size)
-{
-	int i;
-
-	for (i = 0; i < pages_count; i++) {
-		if (!is_write && consumed_size > 0)
-			set_page_dirty(pages[i]);
-		put_page(pages[i]);
-	}
-}
-
 /* Populate the call parameters, merging adjacent pages together */
 static void populate_rw_params(struct page **pages,
 			       int pages_count,

@@ -372,7 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
 
 	*consumed_size = pipe->command_buffer->rw_params.consumed_size;
 
-	release_user_pages(pipe->pages, pages_count, is_write, *consumed_size);
+	put_user_pages_dirty_lock(pipe->pages, pages_count,
+				  !is_write && *consumed_size > 0);
 
 	mutex_unlock(&pipe->lock);
 	return 0;

@@ -53,7 +53,7 @@ Which flags are set by each wrapper
 For these pin_user_pages*() functions, FOLL_PIN is OR'd in with whatever gup
 flags the caller provides. The caller is required to pass in a non-null struct
 pages* array, and the function then pin pages by incrementing each by a special
-value. For now, that value is +1, just like get_user_pages*().::
+value: GUP_PIN_COUNTING_BIAS.::
 
  Function
  --------

@@ -1054,6 +1054,21 @@ static inline __must_check bool try_get_page(struct page *page)
 	return true;
 }
 
+__must_check bool try_pin_compound_head(struct page *page, int refs);
+
+/**
+ * try_pin_page() - mark a page as being used by pin_user_pages*().
+ *
+ * This is the FOLL_PIN counterpart to try_get_page().
+ *
+ * @page:	pointer to page to be marked
+ * @Return:	true for success, false for failure
+ */
+static inline __must_check bool try_pin_page(struct page *page)
+{
+	return try_pin_compound_head(page, 1);
+}
+
 static inline void put_page(struct page *page)
 {
 	page = compound_head(page);

@@ -1071,29 +1086,70 @@ static inline void put_page(struct page *page)
 		__put_page(page);
 }
 
-/**
- * put_user_page() - release a gup-pinned page
- * @page:            pointer to page to be released
+/*
+ * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
+ * the page's refcount so that two separate items are tracked: the original page
+ * reference count, and also a new count of how many pin_user_pages() calls were
+ * made against the page. ("gup-pinned" is another term for the latter).
  *
- * Pages that were pinned via pin_user_pages*() must be released via either
- * put_user_page(), or one of the put_user_pages*() routines. This is so that
- * eventually such pages can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special handling.
+ * With this scheme, pin_user_pages() becomes special: such pages are marked as
+ * distinct from normal pages. As such, the put_user_page() call (and its
+ * variants) must be used in order to release gup-pinned pages.
  *
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with pin*() calls.
+ * Choice of value:
+ *
+ * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
+ * counts with respect to pin_user_pages() and put_user_page() becomes simpler,
+ * due to the fact that adding an even power of two to the page refcount has the
+ * effect of using only the upper N bits, for the code that counts up using the
+ * bias value. This means that the lower bits are left for the exclusive use of
+ * the original code that increments and decrements by one (or at least, by much
+ * smaller values than the bias value).
+ *
+ * Of course, once the lower bits overflow into the upper bits (and this is
+ * OK, because subtraction recovers the original values), then visual inspection
+ * no longer suffices to directly view the separate counts. However, for normal
+ * applications that don't have huge page reference counts, this won't be an
+ * issue.
+ *
+ * Locking: the lockless algorithm described in page_cache_get_speculative()
+ * and page_cache_gup_pin_speculative() provides safe operation for
+ * get_user_pages and page_mkclean and other calls that race to set up page
+ * table entries.
  */
-static inline void put_user_page(struct page *page)
-{
-	put_page(page);
-}
+#define GUP_PIN_COUNTING_BIAS (1UL << 10)
 
+void put_user_page(struct page *page);
 void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 			       bool make_dirty);
-
 void put_user_pages(struct page **pages, unsigned long npages);
 
+/**
+ * page_dma_pinned() - report if a page is pinned for DMA.
+ *
+ * This function checks if a page has been pinned via a call to
+ * pin_user_pages*().
+ *
+ * The return value is partially fuzzy: false is not fuzzy, because it means
+ * "definitely not pinned for DMA", but true means "probably pinned for DMA, but
+ * possibly a false positive due to having at least GUP_PIN_COUNTING_BIAS worth
+ * of normal page references".
+ *
+ * False positives are OK, because: a) it's unlikely for a page to get that many
+ * refcounts, and b) all the callers of this routine are expected to be able to
+ * deal gracefully with a false positive.
+ *
+ * For more information, please see Documentation/vm/pin_user_pages.rst.
+ *
+ * @page:	pointer to page to be queried.
+ * @Return:	True, if it is likely that the page has been "dma-pinned".
+ *		False, if the page is definitely not dma-pinned.
+ */
+static inline bool page_dma_pinned(struct page *page)
+{
+	return (page_ref_count(compound_head(page))) >= GUP_PIN_COUNTING_BIAS;
+}
+
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTION_IN_PAGE_FLAGS
 #endif

@@ -2675,6 +2731,33 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  * Please see Documentation/vm/pin_user_pages.rst for more information.
  */
 
+/**
+ * grab_page() - elevate a page's refcount by a flag-dependent amount
+ *
+ * @page:	pointer to page to be grabbed
+ * @flags:	gup flags: these are the FOLL_* flag values.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
+ * time. (That's true throughout the get_user_pages*() and pin_user_pages*()
+ * APIs.) Cases:
+ *
+ *	FOLL_GET: page's refcount will be incremented by 1.
+ *	FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * @Return: true for for success, false for failure. If neither FOLL_GET nor
+ * FOLL_PIN is set, that's also considered "success", even though nothing is
+ * done: no page refcount changes are made in that case.
+ */
+static inline bool grab_page(struct page *page, unsigned int flags)
+{
+	if (flags & FOLL_GET)
+		get_page(page);
+	else if (flags & FOLL_PIN)
+		return try_pin_page(page);
+
+	return true;
+}
+
 static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
 {
 	if (vm_fault & VM_FAULT_OOM)

@@ -244,6 +244,8 @@ enum node_stat_item {
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
 	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
+	NR_FOLL_PIN_REQUESTED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
+	NR_FOLL_PIN_RETURNED,	/* pages returned via put_user_page() */
 	NR_VM_NODE_STAT_ITEMS
 };
 

@@ -102,6 +102,16 @@ static inline void page_ref_sub(struct page *page, int nr)
 		__page_ref_mod(page, -nr);
 }
 
+static inline int page_ref_sub_return(struct page *page, int nr)
+{
+	int ret = atomic_sub_return(nr, &page->_refcount);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+		__page_ref_mod(page, -nr);
+
+	return ret;
+}
+
 static inline void page_ref_inc(struct page *page)
 {
 	atomic_inc(&page->_refcount);

@@ -51,6 +51,96 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
 	return head;
 }
 
+#ifdef CONFIG_DEBUG_VM
+static inline void __update_proc_vmstat(struct page *page,
+					enum node_stat_item item, int count)
+{
+	mod_node_page_state(page_pgdat(page), item, count);
+}
+#else
+static inline void __update_proc_vmstat(struct page *page,
+					enum node_stat_item item, int count)
+{
+}
+#endif
+
+/**
+ * try_pin_compound_head() - mark a compound page as being used by
+ * pin_user_pages*().
+ *
+ * This is the FOLL_PIN counterpart to try_get_compound_head().
+ *
+ * @page:	pointer to page to be marked
+ * @Return:	true for success, false for failure
+ */
+__must_check bool try_pin_compound_head(struct page *page, int refs)
+{
+	page = try_get_compound_head(page, GUP_PIN_COUNTING_BIAS * refs);
+	if (!page)
+		return false;
+
+	__update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, refs);
+	return true;
+}
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+static bool __put_devmap_managed_user_page(struct page *page)
+{
+	bool is_devmap = page_is_devmap_managed(page);
+
+	if (is_devmap) {
+		int count = page_ref_sub_return(page, GUP_PIN_COUNTING_BIAS);
+
+		__update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 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 is_devmap;
+}
+#else
+static bool __put_devmap_managed_user_page(struct page *page)
+{
+	return false;
+}
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
+
+/**
+ * put_user_page() - release a dma-pinned page
+ * @page:            pointer to page to be released
+ *
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * put_user_page(), or one of the put_user_pages*() routines. This is so that
+ * such pages can be separately tracked and uniquely handled. In particular,
+ * interactions with RDMA and filesystems need special handling.
+ */
+void put_user_page(struct page *page)
+{
+	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 (__put_devmap_managed_user_page(page))
+		return;
+
+	if (page_ref_sub_and_test(page, GUP_PIN_COUNTING_BIAS))
+		__put_page(page);
+
+	__update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 1);
+}
+EXPORT_SYMBOL(put_user_page);
+
 /**
  * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.

@@ -237,10 +327,11 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	}
 
 	page = vm_normal_page(vma, address, pte);
-	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
+	if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
 		/*
-		 * Only return device mapping pages in the FOLL_GET case since
-		 * they are only valid while holding the pgmap reference.
+		 * Only return device mapping pages in the FOLL_GET or FOLL_PIN
+		 * case since they are only valid while holding the pgmap
+		 * reference.
 		 */
 		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
 		if (*pgmap)

@@ -283,6 +374,11 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 			page = ERR_PTR(-ENOMEM);
 			goto out;
 		}
+	} else if (flags & FOLL_PIN) {
+		if (unlikely(!try_pin_page(page))) {
+			page = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 	}
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&

@@ -544,8 +640,8 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 	/* make this handle hugepd */
 	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
 	if (!IS_ERR(page)) {
-		BUG_ON(flags & FOLL_GET);
-		return page;
+		WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN));
+		return NULL;
 	}
 
 	pgd = pgd_offset(mm, address);

@@ -1125,6 +1221,36 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 	return pages_done;
 }
 
+static long __get_user_pages_remote(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 *locked)
+{
+	/*
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas. However, this only comes up if locked is set, and there are
+	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
+	 * allow what we can.
+	 */
+	if (gup_flags & FOLL_LONGTERM) {
+		if (WARN_ON_ONCE(locked))
+			return -EINVAL;
+		/*
+		 * This will check the vmas (even if our vmas arg is NULL)
+		 * and return -ENOTSUPP if DAX isn't allowed in this case:
+		 */
+		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+					     vmas, gup_flags | FOLL_TOUCH |
+					     FOLL_REMOTE);
+	}
+
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+				       locked,
+				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+
 /*
  * get_user_pages_remote() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or

@@ -1193,28 +1319,8 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	/*
-	 * Parts of FOLL_LONGTERM behavior are incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas. However, this only comes up if locked is set, and there are
-	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
-	 * allow what we can.
-	 */
-	if (gup_flags & FOLL_LONGTERM) {
-		if (WARN_ON_ONCE(locked))
-			return -EINVAL;
-		/*
-		 * This will check the vmas (even if our vmas arg is NULL)
-		 * and return -ENOTSUPP if DAX isn't allowed in this case:
-		 */
-		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
-					     vmas, gup_flags | FOLL_TOUCH |
-					     FOLL_REMOTE);
-	}
-
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       locked,
-				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+	return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags,
+				       pages, vmas, locked);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
 

@@ -1842,13 +1948,17 @@ static inline pte_t gup_get_pte(pte_t *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)
 {
 	while ((*nr) - nr_start) {
 		struct page *page = pages[--(*nr)];
 
 		ClearPageReferenced(page);
-		put_page(page);
+		if (flags & FOLL_PIN)
+			put_user_page(page);
+		else
+			put_page(page);
 	}
 }
 

@@ -1881,7 +1991,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
-				undo_dev_pagemap(nr, nr_start, pages);
+				undo_dev_pagemap(nr, nr_start, flags, pages);
 				goto pte_unmap;
 			}
 		} else if (pte_special(pte))

@@ -1890,9 +2000,15 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
-		head = try_get_compound_head(page, 1);
-		if (!head)
-			goto pte_unmap;
+		if (flags & FOLL_PIN) {
+			head = page;
+			if (unlikely(!try_pin_page(head)))
+				goto pte_unmap;
+		} else {
+			head = try_get_compound_head(page, 1);
+			if (!head)
+				goto pte_unmap;
+		}
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
 			put_page(head);

@@ -1946,12 +2062,20 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
-			undo_dev_pagemap(nr, nr_start, pages);
+			undo_dev_pagemap(nr, nr_start, flags, pages);
 			return 0;
 		}
 		SetPageReferenced(page);
 		pages[*nr] = page;
-		get_page(page);
+
+		if (flags & FOLL_PIN) {
+			if (unlikely(!try_pin_page(page))) {
+				undo_dev_pagemap(nr, nr_start, flags, pages);
+				return 0;
+			}
+		} else
+			get_page(page);
+
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);

@@ -1973,7 +2097,7 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		undo_dev_pagemap(nr, nr_start, pages);
+		undo_dev_pagemap(nr, nr_start, flags, pages);
 		return 0;
 	}
 	return 1;

@@ -1991,7 +2115,7 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		undo_dev_pagemap(nr, nr_start, pages);
+		undo_dev_pagemap(nr, nr_start, flags, pages);
 		return 0;
 	}
 	return 1;

@@ -2014,8 +2138,8 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
-static int __record_subpages(struct page *page, unsigned long addr,
-			     unsigned long end, struct page **pages)
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
 {
 	int nr;
 

@@ -2025,12 +2149,31 @@ static int __record_subpages(struct page *page, unsigned long addr,
 	return nr;
 }
 
-static void put_compound_head(struct page *page, int refs)
+static bool grab_compound_head(struct page *head, int refs, unsigned int flags)
 {
+	if (flags & FOLL_PIN) {
+		if (unlikely(!try_pin_compound_head(head, refs)))
+			return false;
+	} else {
+		head = try_get_compound_head(head, refs);
+		if (!head)
+			return false;
+	}
+
+	return true;
+}
+
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+	struct page *head = compound_head(page);
+
+	if (flags & FOLL_PIN)
+		refs *= GUP_PIN_COUNTING_BIAS;
+
 	/* Do a get_page() first, in case refs == page->_refcount */
-	get_page(page);
-	page_ref_sub(page, refs);
-	put_page(page);
+	get_page(head);
+	page_ref_sub(head, refs);
+	put_page(head);
 }
 
 #ifdef CONFIG_ARCH_HAS_HUGEPD

@@ -2064,14 +2207,13 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 
 	head = pte_page(pte);
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	refs = __record_subpages(page, addr, end, pages + *nr);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(head, refs);
-	if (!head)
+	if (!grab_compound_head(head, refs, flags))
 		return 0;
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		put_compound_head(head, refs);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 

@@ -2124,14 +2266,14 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	}
 
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	refs = __record_subpages(page, addr, end, pages + *nr);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head)
+	head = pmd_page(orig);
+	if (!grab_compound_head(head, refs, flags))
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		put_compound_head(head, refs);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}
 

@@ -2158,14 +2300,14 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	}
 
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	refs = __record_subpages(page, addr, end, pages + *nr);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
-	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head)
+	head = pud_page(orig);
+	if (!grab_compound_head(head, refs, flags))
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		put_compound_head(head, refs);
+		put_compound_head(head, refs, flags);
 		return 0;
 	}