On 06.11.23 07:15, Vivek Kasireddy wrote:
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)
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Daniel Vetter <daniel.vetter@xxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Gerd Hoffmann <kraxel@xxxxxxxxxx>
Cc: Dongwon Kim <dongwon.kim@xxxxxxxxx>
Cc: Junxiao Chang <junxiao.chang@xxxxxxxxx>
Suggested-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@xxxxxxxxx>
---
include/linux/mm.h | 2 +
mm/gup.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 101 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf5d0b1b16f4..f6cc17b14653 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2457,6 +2457,8 @@ 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 2f8a2d89fde1..d30b9dfebbb6 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3400,3 +3400,102 @@ 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)
+{
+ struct page *page = ERR_PTR(-ENOMEM);
+ struct folio *folio;
+ int err;
+
+ if (shmem_file(file))
+ return shmem_read_mapping_page(file->f_mapping, idx);
+
As the build reports indicate, this might have to be fenced with
#ifdef CONFIG_HUGETLB_PAGE
+ 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;
+}
+
+/**
+ * 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 hugetlbfs. The pages are either found in the page cache or allocated
nit: s/hugetlbfs/hugetlb/
+ * if necessary. Once the pages are located, they are all pinned via FOLL_PIN.
+ * And, these pinned pages need to be released using unpin_user_pages() or
+ * unpin_user_page().
+ *
It might be reasonable to add that the behavior mimics FOLL_LONGTERM
semantics: the page may be held for an indefinite time period _often_
under userspace control.
+ * 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:
missing memalloc_pin_restore() ?
+ while (i > 0 && pages[--i])
+ unpin_user_page(pages[i]);
So if any pages[] would be 0, we would stop completely? Shouldn't this
be something like:
while (i-- > 0)
if (pages[i])
unpin_user_page(pages[i]);
--
Cheers,
David / dhildenb
