mm/gup: track dma-pinned pages: FOLL_PIN

index 7646bf993b25..f764432914c4 100644
@@ -1978,6 +1978,25 @@ 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)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+	/* Do a get_page() first, in case refs == page->_refcount */
+	get_page(page);
+	page_ref_sub(page, refs);
+	put_page(page);
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)

@@ -2007,32 +2026,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }

@@ -2079,28 +2086,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }

@@ -2120,28 +2118,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }

@@ -2157,28 +2146,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
+
 	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }

index f764432914c4..3ecce297a47f 100644
@@ -29,6 +29,21 @@ struct follow_page_context {
 	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;
+}
+
 /**
  * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.

@@ -1807,20 +1822,6 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
 	}
 }
 
-/*
- * Return the compund 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;
-}
-
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)

index ad8e4df1282b..4eae441f86c9 100644
@@ -337,13 +337,7 @@ static void pmem_release_disk(void *__pmem)
 	put_disk(pmem->disk);
 }
 
-static void pmem_pagemap_page_free(struct page *page)
-{
-	wake_up_var(&page->_refcount);
-}
-
 static const struct dev_pagemap_ops fsdax_pagemap_ops = {
-	.page_free		= pmem_pagemap_page_free,
 	.kill			= pmem_pagemap_kill,
 	.cleanup		= pmem_pagemap_cleanup,
 };

95 lines not on this page · raw message

index c97ea3b694e6..77a4df06c8a7 100644
@@ -952,9 +952,10 @@ static inline bool is_zone_device_page(const struct page *page)
 #endif
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
 {
 	if (!static_branch_unlikely(&devmap_managed_key))
 		return false;

@@ -963,7 +964,6 @@ static inline bool put_devmap_managed_page(struct page *page)
 	switch (page->pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
 	case MEMORY_DEVICE_FS_DAX:
-		__put_devmap_managed_page(page);
 		return true;
 	default:
 		break;

@@ -971,7 +971,14 @@ static inline bool put_devmap_managed_page(struct page *page)
 	return false;
 }
 
+bool put_devmap_managed_page(struct page *page);
+
 #else /* CONFIG_DEV_PAGEMAP_OPS */
+static inline bool page_is_devmap_managed(struct page *page)
+{
+	return false;
+}
+
 static inline bool put_devmap_managed_page(struct page *page)
 {
 	return false;

@@ -1028,8 +1035,10 @@ static inline void put_page(struct page *page)
 	 * need to inform the device driver through callback. See
 	 * include/linux/memremap.h and HMM for details.
 	 */
-	if (put_devmap_managed_page(page))
+	if (page_is_devmap_managed(page)) {
+		put_devmap_managed_page(page);
 		return;
+	}
 
 	if (put_page_testzero(page))
 		__put_page(page);

index e899fa876a62..2ba773859031 100644
@@ -411,20 +411,8 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
 {
-	int count = page_ref_dec_return(page);
-
-	/* still busy */
-	if (count > 1)
-		return;
-
-	/* only triggered by the dev_pagemap shutdown path */
-	if (count == 0) {
-		__put_page(page);
-		return;
-	}
-
 	/* notify page idle for dax */
 	if (!is_device_private_page(page)) {
 		wake_up_var(&page->_refcount);

@@ -461,5 +449,5 @@ void __put_devmap_managed_page(struct page *page)
 	page->mapping = NULL;
 	page->pgmap->ops->page_free(page);
 }
-EXPORT_SYMBOL(__put_devmap_managed_page);
+EXPORT_SYMBOL(free_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */

index 5341ae93861f..49f7c2eea0ba 100644
@@ -1102,3 +1102,27 @@ void __init swap_setup(void)
 	 * _really_ don't want to cluster much more
 	 */
 }
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+bool put_devmap_managed_page(struct page *page)
+{
+	bool is_devmap = page_is_devmap_managed(page);
+
+	if (is_devmap) {
+		int count = page_ref_dec_return(page);
+
+		/*
+		 * 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;
+}
+EXPORT_SYMBOL(put_devmap_managed_page);
+#endif

index cef0133aa47a..ef50c264db71 100644
@@ -257,12 +257,12 @@ static int goldfish_pipe_error_convert(int status)
 	}
 }
 
-static int pin_user_pages(unsigned long first_page,
-			  unsigned long last_page,
-			  unsigned int last_page_size,
-			  int is_write,
-			  struct page *pages[MAX_BUFFERS_PER_COMMAND],
-			  unsigned int *iter_last_page_size)
+static int goldfish_pin_pages(unsigned long first_page,
+			      unsigned long last_page,
+			      unsigned int last_page_size,
+			      int is_write,
+			      struct page *pages[MAX_BUFFERS_PER_COMMAND],
+			      unsigned int *iter_last_page_size)
 {
 	int ret;
 	int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1;

@@ -354,9 +354,9 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
 	if (mutex_lock_interruptible(&pipe->lock))
 		return -ERESTARTSYS;
 
-	pages_count = pin_user_pages(first_page, last_page,
-				     last_page_size, is_write,
-				     pipe->pages, &iter_last_page_size);
+	pages_count = goldfish_pin_pages(first_page, last_page,
+					 last_page_size, is_write,
+					 pipe->pages, &iter_last_page_size);
 	if (pages_count < 0) {
 		mutex_unlock(&pipe->lock);
 		return pages_count;

index 3ecce297a47f..c0c56888e7cc 100644
@@ -29,6 +29,13 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
+						  struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long nr_pages,
+						  struct page **pages,
+						  struct vm_area_struct **vmas,
+						  unsigned int flags);
 /*
  * Return the compound head page with ref appropriately incremented,
  * or NULL if that failed.

@@ -1179,13 +1186,23 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		struct vm_area_struct **vmas, int *locked)
 {
 	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
 	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
+	 * 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 (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
+	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,

index 2ada8e6cdb88..b800fc9a0251 100644
@@ -322,7 +322,6 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 {
 	struct page *page[1];
 	struct vm_area_struct *vma;
-	struct vm_area_struct *vmas[1];
 	unsigned int flags = 0;
 	int ret;
 

@@ -330,33 +329,14 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
-	if (mm == current->mm) {
-		ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
-				     vmas);
-	} else {
-		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
-					    vmas, NULL);
-		/*
-		 * The lifetime of a vaddr_get_pfn() page pin is
-		 * userspace-controlled. In the fs-dax case this could
-		 * lead to indefinite stalls in filesystem operations.
-		 * Disallow attempts to pin fs-dax pages via this
-		 * interface.
-		 */
-		if (ret > 0 && vma_is_fsdax(vmas[0])) {
-			ret = -EOPNOTSUPP;
-			put_page(page[0]);
-		}
-	}
-	up_read(&mm->mmap_sem);
-
+	ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
-		return 0;
+		ret = 0;
+		goto done;
 	}
 
-	down_read(&mm->mmap_sem);
-
 	vaddr = untagged_addr(vaddr);
 
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);

@@ -366,7 +346,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		if (is_invalid_reserved_pfn(*pfn))
 			ret = 0;
 	}
-
+done:
 	up_read(&mm->mmap_sem);
 	return ret;
 }

index c0c56888e7cc..958ab0757389 100644
@@ -2414,7 +2414,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
 	unsigned long addr, len, end;
 	int nr = 0, ret = 0;
 
-	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+				       FOLL_FORCE)))
 		return -EINVAL;
 
 	start = untagged_addr(start) & PAGE_MASK;

index 7a3b99597ead..214e87aa609d 100644
@@ -266,16 +266,13 @@ 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;

@@ -283,8 +280,6 @@ 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);

105 lines not on this page · raw message

212 lines not on this page · raw message

index ef50c264db71..2a5901efecde 100644
@@ -274,7 +274,7 @@ static int goldfish_pin_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 goldfish_pin_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;

index 214e87aa609d..55daefaa9b88 100644
@@ -266,7 +266,7 @@ 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 *)),

index e42d44e501fd..abc3bb6578cc 100644
@@ -308,9 +308,8 @@ 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,

@@ -363,7 +362,7 @@ static int ib_umem_odp_map_dma_single_page(
 	}
 
 out:
-	put_user_page(page);
+	put_page(page);
 	return ret;
 }
 

@@ -473,7 +472,7 @@ 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;
 			}
 

@@ -500,8 +499,8 @@ 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;
 		}
 	}

index 469acb961fbd..9a94761765c0 100644
@@ -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;
 

index edccfd6e178f..8269ab040c21 100644
@@ -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;

index 6bf764e41891..7fc4b5f81fcd 100644
@@ -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);

index 05190edc2611..1a3cc2957e3a 100644
@@ -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;

index 62e6ffa9ad78..600896727d34 100644
@@ -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,

index e99983f07663..e53b07dcfed5 100644
@@ -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)

index 357aa7bef6c0..fd20ab675b85 100644
@@ -42,12 +42,11 @@ static int process_vm_rw_pages(struct page **pages,
 		if (copy > len)
 			copy = len;
 
-		if (vm_write) {
+		if (vm_write)
 			copied = copy_page_from_iter(page, offset, copy, iter);
-			set_page_dirty_lock(page);
-		} else {
+		else
 			copied = copy_page_to_iter(page, offset, copy, iter);
-		}
+
 		len -= copied;
 		if (copied < copy && iov_iter_count(iter))
 			return -EFAULT;

@@ -96,7 +95,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		flags |= FOLL_WRITE;
 
 	while (!rc && nr_pages && iov_iter_count(iter)) {
-		int pages = min(nr_pages, max_pages_per_loop);
+		int pinned_pages = min(nr_pages, max_pages_per_loop);
 		int locked = 1;
 		size_t bytes;
 

@@ -106,14 +105,15 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		 * current/current->mm
 		 */
 		down_read(&mm->mmap_sem);
-		pages = get_user_pages_remote(task, mm, pa, pages, flags,
-					      process_pages, NULL, &locked);
+		pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages,
+						     flags, process_pages,
+						     NULL, &locked);
 		if (locked)
 			up_read(&mm->mmap_sem);
-		if (pages <= 0)
+		if (pinned_pages <= 0)
 			return -EFAULT;
 
-		bytes = pages * PAGE_SIZE - start_offset;
+		bytes = pinned_pages * PAGE_SIZE - start_offset;
 		if (bytes > len)
 			bytes = len;
 

@@ -122,10 +122,12 @@ static int process_vm_rw_single_vec(unsigned long addr,
 					 vm_write);
 		len -= bytes;
 		start_offset = 0;
-		nr_pages -= pages;
-		pa += pages * PAGE_SIZE;
-		while (pages)
-			put_page(process_pages[--pages]);
+		nr_pages -= pinned_pages;
+		pa += pinned_pages * PAGE_SIZE;
+
+		/* If vm_write is set, the pages need to be made dirty: */
+		put_user_pages_dirty_lock(process_pages, pinned_pages,
+					  vm_write);
 	}
 
 	return rc;

index 3db000aacd26..37c5e572993a 100644
@@ -239,7 +239,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	vsg->pages = vzalloc(array_size(sizeof(struct page *), vsg->num_pages));
 	if (NULL == vsg->pages)
 		return -ENOMEM;
-	ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
+	ret = pin_user_pages_fast((unsigned long)xfer->mem_addr,
 			vsg->num_pages,
 			vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
 			vsg->pages);

index 405be10da73d..9639ebc21e8a 100644
@@ -4521,7 +4521,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ret = 0;
 		down_read(&current->mm->mmap_sem);
-		pret = get_user_pages(ubuf, nr_pages,
+		pret = pin_user_pages(ubuf, nr_pages,
 				      FOLL_WRITE | FOLL_LONGTERM,
 				      pages, vmas);
 		if (pret == nr_pages) {

index 3049af269fbf..d071003b5e76 100644
@@ -291,7 +291,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
 		return -ENOMEM;
 
 	down_read(&current->mm->mmap_sem);
-	npgs = get_user_pages(umem->address, umem->npgs,
+	npgs = pin_user_pages(umem->address, umem->npgs,
 			      gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
 	up_read(&current->mm->mmap_sem);
 

index 66a6c6c236a7..28262190c3ab 100644
@@ -349,8 +349,11 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
 	BUG_ON(dma->sglen);
 
 	if (dma->pages) {
-		for (i = 0; i < dma->nr_pages; i++)
+		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]);
+		}
 		kfree(dma->pages);
 		dma->pages = NULL;
 	}

index 28262190c3ab..162a2633b1e3 100644
@@ -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;
 	}

index b800fc9a0251..18bfc2fc8e6d 100644
@@ -309,9 +309,8 @@ static int put_pfn(unsigned long pfn, int prot)
 {
 	if (!is_invalid_reserved_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
-		if (prot & IOMMU_WRITE)
-			SetPageDirty(page);
-		put_page(page);
+
+		put_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE);
 		return 1;
 	}
 	return 0;

@@ -329,7 +328,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+	ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
 				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);

index 56cc84520577..a86547822034 100644
@@ -103,7 +103,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	for (entry = 0; entry < entries; entry += chunk) {
 		unsigned long n = min(entries - entry, chunk);
 
-		ret = get_user_pages(ua + (entry << PAGE_SHIFT), n,
+		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
 				mem->hpages + entry, NULL);
 		if (ret == n) {

@@ -167,9 +167,8 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	return 0;
 
 free_exit:
-	/* free the reference taken */
-	for (i = 0; i < pinned; i++)
-		put_page(mem->hpages[i]);
+	/* free the references taken */
+	put_user_pages(mem->hpages, pinned);
 
 	vfree(mem->hpas);
 	kfree(mem);

@@ -215,7 +214,8 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
 			SetPageDirty(page);
 
-		put_page(page);
+		put_user_page(page);
+
 		mem->hpas[i] = 0;
 	}
 }

index 7dd602d7f8db..7fc44d25eca7 100644
@@ -48,18 +48,21 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = (next - addr) / PAGE_SIZE;
 		}
 
+		/* Filter out most gup flags: only allow a tiny subset here: */
+		gup->flags &= FOLL_WRITE;
+
 		switch (cmd) {
 		case GUP_FAST_BENCHMARK:
-			nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+			nr = get_user_pages_fast(addr, nr, gup->flags,
 						 pages + i);
 			break;
 		case GUP_LONGTERM_BENCHMARK:
 			nr = get_user_pages(addr, nr,
-					    (gup->flags & 1) | FOLL_LONGTERM,
+					    gup->flags | FOLL_LONGTERM,
 					    pages + i, NULL);
 			break;
 		case GUP_BENCHMARK:
-			nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+			nr = get_user_pages(addr, nr, gup->flags, pages + i,
 					    NULL);
 			break;
 		default:

index 485cf06ef013..389327e9b30a 100644
@@ -18,6 +18,9 @@
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE	0x01	/* check pte is writable */
+
 struct gup_benchmark {
 	__u64 get_delta_usec;
 	__u64 put_delta_usec;

@@ -85,7 +88,8 @@ int main(int argc, char **argv)
 	}
 
 	gup.nr_pages_per_call = nr_pages;
-	gup.flags = write;
+	if (write)
+		gup.flags |= FOLL_WRITE;
 
 	fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
 	if (fd == -1)

index a86547822034..eba73ebd8ae5 100644
@@ -168,7 +168,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 
 free_exit:
 	/* free the references taken */
-	put_user_pages(mem->hpages, pinned);
+	unpin_user_pages(mem->hpages, pinned);
 
 	vfree(mem->hpas);
 	kfree(mem);

@@ -214,7 +214,7 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
 			SetPageDirty(page);
 
-		put_user_page(page);
+		unpin_user_page(page);
 
 		mem->hpas[i] = 0;
 	}

index 37c5e572993a..719d036c9384 100644
@@ -188,8 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
-					  (vsg->direction == DMA_FROM_DEVICE));
+		unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
+					   (vsg->direction == DMA_FROM_DEVICE));
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);

index 55daefaa9b88..a6094766b6f5 100644
@@ -54,7 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
+		unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
 	}
 
 	sg_free_table(&umem->sg_head);

index 9a94761765c0..3b505006c0a6 100644
@@ -118,7 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty)
 {
-	put_user_pages_dirty_lock(p, npages, dirty);
+	unpin_user_pages_dirty_lock(p, npages, dirty);
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		atomic64_sub(npages, &mm->pinned_vm);

index 8269ab040c21..78a48aea3faf 100644
@@ -482,7 +482,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 
 	ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
 	if (ret < 0) {
-		put_user_page(pages[0]);
+		unpin_user_page(pages[0]);
 		goto out;
 	}
 

@@ -490,7 +490,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 				 mthca_uarc_virt(dev, uar, i));
 	if (ret) {
 		pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-		put_user_page(sg_page(&db_tab->page[i].mem));
+		unpin_user_page(sg_page(&db_tab->page[i].mem));
 		goto out;
 	}
 

@@ -556,7 +556,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar,
 		if (db_tab->page[i].uvirt) {
 			mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1);
 			pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-			put_user_page(sg_page(&db_tab->page[i].mem));
+			unpin_user_page(sg_page(&db_tab->page[i].mem));
 		}
 	}
 

index 7fc4b5f81fcd..342e3172ca40 100644
@@ -40,7 +40,7 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	put_user_pages_dirty_lock(p, num_pages, dirty);
+	unpin_user_pages_dirty_lock(p, num_pages, dirty);
 }
 
 /**

index 1a3cc2957e3a..a67599b5a550 100644
@@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
 		 * the caller can ignore this page.
 		 */
 		if (put) {
-			put_user_page(page);
+			unpin_user_page(page);
 		} else {
 			/* coalesce case */
 			kunmap(page);

@@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
 			kunmap(pkt->addr[i].page);
 
 		if (pkt->addr[i].put_page)
-			put_user_page(pkt->addr[i].page);
+			unpin_user_page(pkt->addr[i].page);
 		else
 			__free_page(pkt->addr[i].page);
 	} else if (pkt->addr[i].kvaddr) {

@@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	/* if error, return all pages not managed by pkt */
 free_pages:
 	while (i < j)
-		put_user_page(pages[i++]);
+		unpin_user_page(pages[i++]);
 
 done:
 	return ret;

index 600896727d34..bd9f944b68fc 100644
@@ -75,7 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
 		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
 			page = sg_page(sg);
 			pa = sg_phys(sg);
-			put_user_pages_dirty_lock(&page, 1, dirty);
+			unpin_user_pages_dirty_lock(&page, 1, dirty);
 			usnic_dbg("pa: %pa\n", &pa);
 		}
 		kfree(chunk);

index e53b07dcfed5..e2061dc0b043 100644
@@ -63,7 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index)
 static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
 			   bool dirty)
 {
-	put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
+	unpin_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
 }
 
 void siw_umem_release(struct siw_umem *umem, bool dirty)

index 162a2633b1e3..13b65ed9e74c 100644
@@ -349,8 +349,8 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
 	BUG_ON(dma->sglen);
 
 	if (dma->pages) {
-		put_user_pages_dirty_lock(dma->pages, dma->nr_pages,
-					  dma->direction == DMA_FROM_DEVICE);
+		unpin_user_pages_dirty_lock(dma->pages, dma->nr_pages,
+					    dma->direction == DMA_FROM_DEVICE);
 		kfree(dma->pages);
 		dma->pages = NULL;
 	}

index 2a5901efecde..1ab207ec9c94 100644
@@ -360,8 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
 
 	*consumed_size = pipe->command_buffer->rw_params.consumed_size;
 
-	put_user_pages_dirty_lock(pipe->pages, pages_count,
-				  !is_write && *consumed_size > 0);
+	unpin_user_pages_dirty_lock(pipe->pages, pages_count,
+				    !is_write && *consumed_size > 0);
 
 	mutex_unlock(&pipe->lock);
 	return 0;

index 18bfc2fc8e6d..a177bf2c6683 100644
@@ -310,7 +310,7 @@ static int put_pfn(unsigned long pfn, int prot)
 	if (!is_invalid_reserved_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 
-		put_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE);
+		unpin_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE);
 		return 1;
 	}
 	return 0;

index 9639ebc21e8a..f5a378251995 100644
@@ -4400,7 +4400,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
 		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
 
 		for (j = 0; j < imu->nr_bvecs; j++)
-			put_user_page(imu->bvec[j].bv_page);
+			unpin_user_page(imu->bvec[j].bv_page);
 
 		if (ctx->account_mem)
 			io_unaccount_mem(ctx->user, imu->nr_bvecs);

@@ -4545,7 +4545,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			 * release any pages we did get
 			 */
 			if (pret > 0)
-				put_user_pages(pages, pret);
+				unpin_user_pages(pages, pret);
 			if (ctx->account_mem)
 				io_unaccount_mem(ctx->user, nr_pages);
 			kvfree(imu->bvec);

index 0fb9929e00af..6a1a357e7d86 100644
@@ -1045,27 +1045,27 @@ static inline void put_page(struct page *page)
 }
 
 /**
- * put_user_page() - release a gup-pinned page
+ * unpin_user_page() - release a gup-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
- * eventually such pages can be separately tracked and uniquely handled. In
+ * unpin_user_page(), or one of the unpin_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.
  *
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
+ * unpin_user_page() and put_page() are not interchangeable, despite this early
+ * implementation that makes them look the same. unpin_user_page() calls must
  * be perfectly matched up with pin*() calls.
  */
-static inline void put_user_page(struct page *page)
+static inline void unpin_user_page(struct page *page)
 {
 	put_page(page);
 }
 
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty);
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty);
 
-void put_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_pages(struct page **pages, unsigned long npages);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTION_IN_PAGE_FLAGS

@@ -2595,7 +2595,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
-#define FOLL_PIN	0x40000	/* pages must be released via put_user_page() */
+#define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
 
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each

@@ -2630,7 +2630,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  * Direct IO). This lets the filesystem know that some non-file-system entity is
  * potentially changing the pages' data. In contrast to FOLL_GET (whose pages
  * are released via put_page()), FOLL_PIN pages must be released, ultimately, by
- * a call to put_user_page().
+ * a call to unpin_user_page().
  *
  * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
  * and separate refcounting mechanisms, however, and that means that each has

@@ -2638,7 +2638,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  *
  *     FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
  *
- *     FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release.
+ *     FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release.
  *
  * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
  * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based

@@ -2648,7 +2648,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
  * directly by the caller. That's in order to help avoid mismatches when
  * releasing pages: get_user_pages*() pages must be released via put_page(),
- * while pin_user_pages*() pages must be released via put_user_page().
+ * while pin_user_pages*() pages must be released via unpin_user_page().
  *
  * Please see Documentation/vm/pin_user_pages.rst for more information.
  */

index 4862ff982bc3..73aedcefa4bd 100644
@@ -52,7 +52,7 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
 }
 
 /**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * 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

@@ -62,19 +62,19 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
  *
  * 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 put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
+ * 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 put_user_page() documentation for details.
+ * 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(), put_user_page().
+ * set_page_dirty_lock(), unpin_user_page().
  *
  */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty)
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty)
 {
 	unsigned long index;
 

@@ -85,7 +85,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 	 */
 
 	if (!make_dirty) {
-		put_user_pages(pages, npages);
+		unpin_user_pages(pages, npages);
 		return;
 	}
 

@@ -113,21 +113,21 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 */
 		if (!PageDirty(page))
 			set_page_dirty_lock(page);
-		put_user_page(page);
+		unpin_user_page(page);
 	}
 }
-EXPORT_SYMBOL(put_user_pages_dirty_lock);
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
 /**
- * put_user_pages() - release an array of gup-pinned pages.
+ * 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 put_user_page().
+ * For each page in the @pages array, release the page using unpin_user_page().
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  */
-void put_user_pages(struct page **pages, unsigned long npages)
+void unpin_user_pages(struct page **pages, unsigned long npages)
 {
 	unsigned long index;
 

@@ -137,9 +137,9 @@ void put_user_pages(struct page **pages, unsigned long npages)
 	 * single operation to the head page should suffice.
 	 */
 	for (index = 0; index < npages; index++)
-		put_user_page(pages[index]);
+		unpin_user_page(pages[index]);
 }
-EXPORT_SYMBOL(put_user_pages);
+EXPORT_SYMBOL(unpin_user_pages);
 
 #ifdef CONFIG_MMU
 static struct page *no_page_table(struct vm_area_struct *vma,

index fd20ab675b85..de41e830cdac 100644
@@ -126,8 +126,8 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		pa += pinned_pages * PAGE_SIZE;
 
 		/* If vm_write is set, the pages need to be made dirty: */
-		put_user_pages_dirty_lock(process_pages, pinned_pages,
-					  vm_write);
+		unpin_user_pages_dirty_lock(process_pages, pinned_pages,
+					    vm_write);
 	}
 
 	return rc;

index d071003b5e76..ac182c38f7b0 100644
@@ -212,7 +212,7 @@ static int xdp_umem_map_pages(struct xdp_umem *umem)
 
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
-	put_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
+	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
 
 	kfree(umem->pgs);
 	umem->pgs = NULL;

103 lines not on this page · raw message

index 89d8ff06c9ce..a7418f7a44da 100644
@@ -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 unpin_user_page() */
 	NR_VM_NODE_STAT_ITEMS
 };
 

index 14d14beb1f7f..b9cbe553d1e7 100644
@@ -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);

596 lines not on this page · raw message

index 41a0fbddc96b..430e55673e35 100644
@@ -945,6 +945,11 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 	 */
 	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		return NULL;
 

@@ -960,7 +965,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 	 * device mapped pages can only be returned if the
 	 * caller will manage the page reference count.
 	 */
-	if (!(flags & FOLL_GET))
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
 		return ERR_PTR(-EEXIST);
 
 	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;

@@ -968,7 +973,8 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 	if (!*pgmap)
 		return ERR_PTR(-EFAULT);
 	page = pfn_to_page(pfn);
-	get_page(page);
+	if (!try_grab_page(page, flags))
+		page = ERR_PTR(-EFAULT);
 
 	return page;
 }

@@ -1088,6 +1094,11 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 	if (flags & FOLL_WRITE && !pud_write(*pud))
 		return NULL;
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 	if (pud_present(*pud) && pud_devmap(*pud))
 		/* pass */;
 	else

@@ -1099,8 +1110,10 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 	/*
 	 * device mapped pages can only be returned if the
 	 * caller will manage the page reference count.
+	 *
+	 * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here:
 	 */
-	if (!(flags & FOLL_GET))
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
 		return ERR_PTR(-EEXIST);
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;

@@ -1108,7 +1121,8 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 	if (!*pgmap)
 		return ERR_PTR(-EFAULT);
 	page = pfn_to_page(pfn);
-	get_page(page);
+	if (!try_grab_page(page, flags))
+		page = ERR_PTR(-EFAULT);
 
 	return page;
 }

@@ -1522,8 +1536,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 skip_mlock:
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
-	if (flags & FOLL_GET)
-		get_page(page);
+	if (!try_grab_page(page, flags))
+		page = ERR_PTR(-EFAULT);
 
 out:
 	return page;

index ac65bb5e38ac..0aab6fe0072f 100644
@@ -4356,7 +4356,13 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);
-			get_page(pages[i]);
+			if (!try_grab_page(pages[i], flags)) {
+				spin_unlock(ptl);
+				remainder = 0;
+				err = -ENOMEM;
+				WARN_ON_ONCE(1);
+				break;
+			}
 		}
 
 		if (vmas)

@@ -4916,6 +4922,12 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	pte_t pte;
+
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 retry:
 	ptl = pmd_lockptr(mm, pmd);
 	spin_lock(ptl);

@@ -4928,8 +4940,11 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	pte = huge_ptep_get((pte_t *)pmd);
 	if (pte_present(pte)) {
 		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
-		if (flags & FOLL_GET)
-			get_page(page);
+		if (unlikely(!try_grab_page(page, flags))) {
+			WARN_ON_ONCE(1);
+			page = NULL;
+			goto out;
+		}
 	} else {
 		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);

@@ -4950,7 +4965,7 @@ struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
 		pud_t *pud, int flags)
 {
-	if (flags & FOLL_GET)
+	if (flags & (FOLL_GET | FOLL_PIN))
 		return NULL;
 
 	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);

@@ -4959,7 +4974,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 struct page * __weak
 follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags)
 {
-	if (flags & FOLL_GET)
+	if (flags & (FOLL_GET | FOLL_PIN))
 		return NULL;
 
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);

index 78d53378db99..b56808bae1b4 100644
@@ -1168,6 +1168,8 @@ const char * const vmstat_text[] = {
 	"nr_dirtied",
 	"nr_written",
 	"nr_kernel_misc_reclaimable",
+	"nr_foll_pin_requested",
+	"nr_foll_pin_returned",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",

index 7fc44d25eca7..76d32db48af8 100644
@@ -8,6 +8,8 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
+#define PIN_FAST_BENCHMARK	_IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK		_IOWR('g', 5, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;

@@ -19,6 +21,42 @@ struct gup_benchmark {
 	__u64 expansion[10];	/* For future use */
 };
 
+static void put_back_pages(int cmd, struct page **pages, unsigned long nr_pages)
+{
+	int i;
+
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+	case GUP_LONGTERM_BENCHMARK:
+	case GUP_BENCHMARK:
+		for (i = 0; i < nr_pages; i++)
+			put_page(pages[i]);
+		break;
+
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+		unpin_user_pages(pages, nr_pages);
+		break;
+	}
+}
+
+static void verify_dma_pinned(int cmd, struct page **pages,
+			      unsigned long nr_pages)
+{
+	int i;
+
+	switch (cmd) {
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+		for (i = 0; i < nr_pages; i++) {
+			if (WARN(!page_dma_pinned(pages[i]),
+				 "pages[%d] is NOT dma-pinned\n", i))
+				break;
+		}
+		break;
+	}
+}
+
 static int __gup_benchmark_ioctl(unsigned int cmd,
 		struct gup_benchmark *gup)
 {

@@ -65,6 +103,14 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = get_user_pages(addr, nr, gup->flags, pages + i,
 					    NULL);
 			break;
+		case PIN_FAST_BENCHMARK:
+			nr = pin_user_pages_fast(addr, nr, gup->flags,
+						 pages + i);
+			break;
+		case PIN_BENCHMARK:
+			nr = pin_user_pages(addr, nr, gup->flags, pages + i,
+					    NULL);
+			break;
 		default:
 			return -1;
 		}

@@ -75,15 +121,22 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	}
 	end_time = ktime_get();
 
+	/* Shifting the meaning of nr_pages: now it is actual number pinned: */
+	nr_pages = i;
+
 	gup->get_delta_usec = ktime_us_delta(end_time, start_time);
 	gup->size = addr - gup->addr;
 
+	/*
+	 * Take an un-benchmark-timed moment to verify DMA pinned
+	 * state: print a warning if any non-dma-pinned pages are found:
+	 */
+	verify_dma_pinned(cmd, pages, nr_pages);
+
 	start_time = ktime_get();
-	for (i = 0; i < nr_pages; i++) {
-		if (!pages[i])
-			break;
-		put_page(pages[i]);
-	}
+
+	put_back_pages(cmd, pages, nr_pages);
+
 	end_time = ktime_get();
 	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 

@@ -101,6 +154,8 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
 	case GUP_FAST_BENCHMARK:
 	case GUP_LONGTERM_BENCHMARK:
 	case GUP_BENCHMARK:
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
 		break;
 	default:
 		return -EINVAL;

index 389327e9b30a..43b4dfe161a2 100644
@@ -18,6 +18,10 @@
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
+/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
+#define PIN_FAST_BENCHMARK	_IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK		_IOWR('g', 5, struct gup_benchmark)
+
 /* Just the flags we need, copied from mm.h: */
 #define FOLL_WRITE	0x01	/* check pte is writable */
 

@@ -40,8 +44,14 @@ int main(int argc, char **argv)
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
 		switch (opt) {
+		case 'a':
+			cmd = PIN_FAST_BENCHMARK;
+			break;
+		case 'b':
+			cmd = PIN_BENCHMARK;
+			break;
 		case 'm':
 			size = atoi(optarg) * MB;
 			break;

@@ -63,6 +73,9 @@ int main(int argc, char **argv)
 		case 'U':
 			cmd = GUP_BENCHMARK;
 			break;
+		case 'u':
+			cmd = GUP_FAST_BENCHMARK;
+			break;
 		case 'w':
 			write = 1;
 			break;