[PATCH] mm/gup: Introduce pin_user_pages_fd() for pinning shmem/hugetlbfs file pages (v3)

[Vivek Kasireddy]

For drivers that would like to longterm-pin the pages associated
with a file, the pin_user_pages_fd() API provides an option to
not only pin the pages via FOLL_PIN but also to check and migrate
them if they reside in movable zone or CMA block. This API
currently works with files that belong to either shmem or hugetlbfs.
Files belonging to other filesystems are rejected for now.

The pages need to be located first before pinning them via FOLL_PIN.
If they are found in the page cache, they can be immediately pinned.
Otherwise, they need to be allocated using the filesystem specific
APIs and then pinned.

v2:
- Drop gup_flags and improve comments and commit message (David)
- Allocate a page if we cannot find in page cache for the hugetlbfs
  case as well (David)
- Don't unpin pages if there is a migration related failure (David)
- Drop the unnecessary nr_pages <= 0 check (Jason)
- Have the caller of the API pass in file * instead of fd (Jason)

v3: (David)
- Enclose the huge page allocation code with #ifdef CONFIG_HUGETLB_PAGE
  (Build error reported by kernel test robot <lkp at intel.com>)
- Don't forget memalloc_pin_restore() on non-migration related errors
- Improve the readability of the cleanup code associated with
  non-migration related errors
- Augment the comments by describing FOLL_LONGTERM like behavior
- Include the R-b tag from Jason

Cc: David Hildenbrand <david at redhat.com>
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
Cc: Mike Kravetz <mike.kravetz at oracle.com>
Cc: Hugh Dickins <hughd at google.com>
Cc: Peter Xu <peterx at redhat.com>
Cc: Gerd Hoffmann <kraxel at redhat.com>
Cc: Dongwon Kim <dongwon.kim at intel.com>
Cc: Junxiao Chang <junxiao.chang at intel.com>
Suggested-by: Jason Gunthorpe <jgg at nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg at nvidia.com> (v2)
Signed-off-by: Vivek Kasireddy <vivek.kasireddy at intel.com>
---
 include/linux/mm.h |   2 +
 mm/gup.c           | 109 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 111 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..1b675fa35059 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2472,6 +2472,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
+long pin_user_pages_fd(struct file *file, pgoff_t start,
+		       unsigned long nr_pages, struct page **pages);
 
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
diff --git a/mm/gup.c b/mm/gup.c
index 231711efa390..b3af967cdff1 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3410,3 +3410,112 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 				     &locked, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+static struct page *alloc_file_page(struct file *file, pgoff_t idx)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+	struct page *page = ERR_PTR(-ENOMEM);
+	struct folio *folio;
+	int err;
+
+	if (is_file_hugepages(file)) {
+		folio = alloc_hugetlb_folio_nodemask(hstate_file(file),
+						     NUMA_NO_NODE,
+						     NULL,
+						     GFP_USER);
+		if (folio && folio_try_get(folio)) {
+			page = &folio->page;
+			err = hugetlb_add_to_page_cache(folio,
+							file->f_mapping,
+							idx);
+			if (err) {
+				folio_put(folio);
+				free_huge_folio(folio);
+				page = ERR_PTR(err);
+			}
+		}
+		return page;
+	}
+#endif
+	return shmem_read_mapping_page(file->f_mapping, idx);
+}
+
+/**
+ * pin_user_pages_fd() - pin user pages associated with a file
+ * @file:       the file whose pages are to be pinned
+ * @start:      starting file offset
+ * @nr_pages:   number of pages from start to pin
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at-least nr_pages long.
+ *
+ * Attempt to pin pages associated with a file that belongs to either shmem
+ * or hugetlb. The pages are either found in the page cache or allocated if
+ * necessary. Once the pages are located, they are all pinned via FOLL_PIN.
+ * And, these pinned pages need to be released either using unpin_user_pages()
+ * or unpin_user_page().
+ *
+ * It must be noted that the pages may be pinned for an indefinite amount
+ * of time. And, in most cases, the duration of time they may stay pinned
+ * would be controlled by the userspace. This behavior is effectively the
+ * same as using FOLL_LONGTERM with other GUP APIs.
+ *
+ * Returns number of pages pinned. This would be equal to the number of
+ * pages requested. If no pages were pinned, it returns -errno.
+ */
+long pin_user_pages_fd(struct file *file, pgoff_t start,
+		       unsigned long nr_pages, struct page **pages)
+{
+	struct page *page;
+	unsigned int flags, i;
+	long ret;
+
+	if (start < 0)
+		return -EINVAL;
+
+	if (!file)
+	    return -EINVAL;
+
+	if (!shmem_file(file) && !is_file_hugepages(file))
+	    return -EINVAL;
+
+	flags = memalloc_pin_save();
+	do {
+		for (i = 0; i < nr_pages; i++) {
+			/*
+ 			 * In most cases, we should be able to find the page
+			 * in the page cache. If we cannot find it, we try to
+			 * allocate one and add it to the page cache.
+			 */
+			page = find_get_page_flags(file->f_mapping,
+						   start + i,
+						   FGP_ACCESSED);
+			if (!page) {
+				page = alloc_file_page(file, start + i);
+				if (IS_ERR(page)) {
+					ret = PTR_ERR(page);
+					goto err;
+				}
+			}
+			ret = try_grab_page(page, FOLL_PIN);
+			if (unlikely(ret))
+				goto err;
+
+			pages[i] = page;
+			put_page(pages[i]);
+		}
+
+		ret = check_and_migrate_movable_pages(nr_pages, pages);
+	} while (ret == -EAGAIN);
+
+	memalloc_pin_restore(flags);
+	return ret ? ret : nr_pages;
+err:
+	memalloc_pin_restore(flags);
+	while (i-- > 0)
+		if (pages[i])
+			unpin_user_page(pages[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fd);
+
-- 
2.39.2