The patch titled
Subject: udmabuf: pin the pages using memfd_pin_folios() API
has been added to the -mm mm-unstable branch. Its filename is
udmabuf-pin-the-pages-using-memfd_pin_folios-api.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/udmabuf-pin-the-pages-using-memfd_pin_folios-api.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Vivek Kasireddy <vivek.kasireddy@xxxxxxxxx>
Subject: udmabuf: pin the pages using memfd_pin_folios() API
Date: Wed, 10 Apr 2024 23:59:43 -0700
Using memfd_pin_folios() will ensure that the pages are pinned correctly
using FOLL_PIN. And, this also ensures that we don't accidentally break
features such as memory hotunplug as it would not allow pinning pages in
the movable zone.
Using this new API also simplifies the code as we no longer have to deal
with extracting individual pages from their mappings or handle shmem and
hugetlb cases separately.
Link: https://lkml.kernel.org/r/20240411070157.3318425-8-vivek.kasireddy@xxxxxxxxx
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Daniel Vetter <daniel.vetter@xxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Gerd Hoffmann <kraxel@xxxxxxxxxx>
Cc: Dongwon Kim <dongwon.kim@xxxxxxxxx>
Cc: Junxiao Chang <junxiao.chang@xxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/dma-buf/udmabuf.c | 153 ++++++++++++++++++------------------
1 file changed, 78 insertions(+), 75 deletions(-)
--- a/drivers/dma-buf/udmabuf.c~udmabuf-pin-the-pages-using-memfd_pin_folios-api
+++ a/drivers/dma-buf/udmabuf.c
@@ -30,6 +30,12 @@ struct udmabuf {
struct sg_table *sg;
struct miscdevice *device;
pgoff_t *offsets;
+ struct list_head unpin_list;
+};
+
+struct udmabuf_folio {
+ struct folio *folio;
+ struct list_head list;
};
static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -153,17 +159,43 @@ static void unmap_udmabuf(struct dma_buf
return put_sg_table(at->dev, sg, direction);
}
+static void unpin_all_folios(struct list_head *unpin_list)
+{
+ struct udmabuf_folio *ubuf_folio;
+
+ while (!list_empty(unpin_list)) {
+ ubuf_folio = list_first_entry(unpin_list,
+ struct udmabuf_folio, list);
+ unpin_folio(ubuf_folio->folio);
+
+ list_del(&ubuf_folio->list);
+ kfree(ubuf_folio);
+ }
+}
+
+static int add_to_unpin_list(struct list_head *unpin_list,
+ struct folio *folio)
+{
+ struct udmabuf_folio *ubuf_folio;
+
+ ubuf_folio = kzalloc(sizeof(*ubuf_folio), GFP_KERNEL);
+ if (!ubuf_folio)
+ return -ENOMEM;
+
+ ubuf_folio->folio = folio;
+ list_add_tail(&ubuf_folio->list, unpin_list);
+ return 0;
+}
+
static void release_udmabuf(struct dma_buf *buf)
{
struct udmabuf *ubuf = buf->priv;
struct device *dev = ubuf->device->this_device;
- pgoff_t pg;
if (ubuf->sg)
put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
- for (pg = 0; pg < ubuf->pagecount; pg++)
- folio_put(ubuf->folios[pg]);
+ unpin_all_folios(&ubuf->unpin_list);
kfree(ubuf->offsets);
kfree(ubuf->folios);
kfree(ubuf);
@@ -218,64 +250,6 @@ static const struct dma_buf_ops udmabuf_
#define SEALS_WANTED (F_SEAL_SHRINK)
#define SEALS_DENIED (F_SEAL_WRITE)
-static int handle_hugetlb_pages(struct udmabuf *ubuf, struct file *memfd,
- pgoff_t offset, pgoff_t pgcnt,
- pgoff_t *pgbuf)
-{
- struct hstate *hpstate = hstate_file(memfd);
- pgoff_t mapidx = offset >> huge_page_shift(hpstate);
- pgoff_t subpgoff = (offset & ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
- pgoff_t maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
- struct folio *folio = NULL;
- pgoff_t pgidx;
-
- mapidx <<= huge_page_order(hpstate);
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- if (!folio) {
- folio = __filemap_get_folio(memfd->f_mapping,
- mapidx,
- FGP_ACCESSED, 0);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
- }
-
- folio_get(folio);
- ubuf->folios[*pgbuf] = folio;
- ubuf->offsets[*pgbuf] = subpgoff << PAGE_SHIFT;
- (*pgbuf)++;
- if (++subpgoff == maxsubpgs) {
- folio_put(folio);
- folio = NULL;
- subpgoff = 0;
- mapidx += pages_per_huge_page(hpstate);
- }
- }
-
- if (folio)
- folio_put(folio);
-
- return 0;
-}
-
-static int handle_shmem_pages(struct udmabuf *ubuf, struct file *memfd,
- pgoff_t offset, pgoff_t pgcnt,
- pgoff_t *pgbuf)
-{
- pgoff_t pgidx, pgoff = offset >> PAGE_SHIFT;
- struct folio *folio = NULL;
-
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- folio = shmem_read_folio(memfd->f_mapping, pgoff + pgidx);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
-
- ubuf->folios[*pgbuf] = folio;
- (*pgbuf)++;
- }
-
- return 0;
-}
-
static int check_memfd_seals(struct file *memfd)
{
int seals;
@@ -321,16 +295,19 @@ static long udmabuf_create(struct miscde
struct udmabuf_create_list *head,
struct udmabuf_create_item *list)
{
- pgoff_t pgcnt, pgbuf = 0, pglimit;
+ pgoff_t pgoff, pgcnt, pglimit, pgbuf = 0;
+ long nr_folios, ret = -EINVAL;
struct file *memfd = NULL;
+ struct folio **folios;
struct udmabuf *ubuf;
- int ret = -EINVAL;
- u32 i, flags;
+ u32 i, j, k, flags;
+ loff_t end;
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
if (!ubuf)
return -ENOMEM;
+ INIT_LIST_HEAD(&ubuf->unpin_list);
pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
for (i = 0; i < head->count; i++) {
if (!IS_ALIGNED(list[i].offset, PAGE_SIZE))
@@ -366,17 +343,44 @@ static long udmabuf_create(struct miscde
goto err;
pgcnt = list[i].size >> PAGE_SHIFT;
- if (is_file_hugepages(memfd))
- ret = handle_hugetlb_pages(ubuf, memfd,
- list[i].offset,
- pgcnt, &pgbuf);
- else
- ret = handle_shmem_pages(ubuf, memfd,
- list[i].offset,
- pgcnt, &pgbuf);
- if (ret < 0)
+ folios = kmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL);
+ if (!folios) {
+ ret = -ENOMEM;
goto err;
+ }
+
+ end = list[i].offset + (pgcnt << PAGE_SHIFT) - 1;
+ ret = memfd_pin_folios(memfd, list[i].offset, end,
+ folios, pgcnt, &pgoff);
+ if (ret < 0) {
+ kfree(folios);
+ goto err;
+ }
+
+ nr_folios = ret;
+ pgoff >>= PAGE_SHIFT;
+ for (j = 0, k = 0; j < pgcnt; j++) {
+ ubuf->folios[pgbuf] = folios[k];
+ ubuf->offsets[pgbuf] = pgoff << PAGE_SHIFT;
+
+ if (j == 0 || ubuf->folios[pgbuf-1] != folios[k]) {
+ ret = add_to_unpin_list(&ubuf->unpin_list,
+ folios[k]);
+ if (ret < 0) {
+ kfree(folios);
+ goto err;
+ }
+ }
+
+ pgbuf++;
+ if (++pgoff == folio_nr_pages(folios[k])) {
+ pgoff = 0;
+ if (++k == nr_folios)
+ break;
+ }
+ }
+ kfree(folios);
fput(memfd);
}
@@ -388,10 +392,9 @@ static long udmabuf_create(struct miscde
return ret;
err:
- while (pgbuf > 0)
- folio_put(ubuf->folios[--pgbuf]);
if (memfd)
fput(memfd);
+ unpin_all_folios(&ubuf->unpin_list);
kfree(ubuf->offsets);
kfree(ubuf->folios);
kfree(ubuf);
_
Patches currently in -mm which might be from vivek.kasireddy@xxxxxxxxx are
mm-gup-introduce-unpin_folio-unpin_folios-helpers.patch
mm-gup-introduce-check_and_migrate_movable_folios.patch
mm-gup-introduce-memfd_pin_folios-for-pinning-memfd-folios.patch
udmabuf-use-vmf_insert_pfn-and-vm_pfnmap-for-handling-mmap.patch
udmabuf-add-back-support-for-mapping-hugetlb-pages.patch
udmabuf-convert-udmabuf-driver-to-use-folios.patch
udmabuf-pin-the-pages-using-memfd_pin_folios-api.patch
selftests-udmabuf-add-tests-to-verify-data-after-page-migration.patch
