The patch titled
Subject: udmabuf: pin the pages using pin_user_pages_fd() API
has been added to the -mm mm-unstable branch. Its filename is
udmabuf-pin-the-pages-using-pin_user_pages_fd-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-pin_user_pages_fd-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 pin_user_pages_fd() API
Date: Tue, 3 Oct 2023 00:44:46 -0700
Using pin_user_pages_fd() 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.
This patch also adds back support for mapping hugetlbfs pages by noting
the subpage offsets within the huge pages and uses this information while
populating the scatterlist.
Link: https://lkml.kernel.org/r/20231003074447.3245729-3-vivek.kasireddy@xxxxxxxxx
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@xxxxxxxxx>
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: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Gerd Hoffmann <kraxel@xxxxxxxxxx>
Cc: Dongwon Kim <dongwon.kim@xxxxxxxxx>
Cc: Junxiao Chang <junxiao.chang@xxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/dma-buf/udmabuf.c | 82 ++++++++++++++++++++++++++----------
1 file changed, 61 insertions(+), 21 deletions(-)
--- a/drivers/dma-buf/udmabuf.c~udmabuf-pin-the-pages-using-pin_user_pages_fd-api
+++ a/drivers/dma-buf/udmabuf.c
@@ -10,6 +10,7 @@
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/shmem_fs.h>
+#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/udmabuf.h>
#include <linux/vmalloc.h>
@@ -28,6 +29,7 @@ struct udmabuf {
struct page **pages;
struct sg_table *sg;
struct miscdevice *device;
+ pgoff_t *subpgoff;
};
static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -88,23 +90,31 @@ static struct sg_table *get_sg_table(str
{
struct udmabuf *ubuf = buf->priv;
struct sg_table *sg;
+ struct scatterlist *sgl;
+ pgoff_t offset;
+ unsigned long i = 0;
int ret;
sg = kzalloc(sizeof(*sg), GFP_KERNEL);
if (!sg)
return ERR_PTR(-ENOMEM);
- ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount,
- 0, ubuf->pagecount << PAGE_SHIFT,
- GFP_KERNEL);
+
+ ret = sg_alloc_table(sg, ubuf->pagecount, GFP_KERNEL);
if (ret < 0)
- goto err;
+ goto err_alloc;
+
+ for_each_sg(sg->sgl, sgl, ubuf->pagecount, i) {
+ offset = ubuf->subpgoff ? ubuf->subpgoff[i] : 0;
+ sg_set_page(sgl, ubuf->pages[i], PAGE_SIZE, offset);
+ }
ret = dma_map_sgtable(dev, sg, direction, 0);
if (ret < 0)
- goto err;
+ goto err_map;
return sg;
-err:
+err_map:
sg_free_table(sg);
+err_alloc:
kfree(sg);
return ERR_PTR(ret);
}
@@ -140,7 +150,9 @@ static void release_udmabuf(struct dma_b
put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
for (pg = 0; pg < ubuf->pagecount; pg++)
- put_page(ubuf->pages[pg]);
+ unpin_user_page(ubuf->pages[pg]);
+
+ kfree(ubuf->subpgoff);
kfree(ubuf->pages);
kfree(ubuf);
}
@@ -200,12 +212,13 @@ static long udmabuf_create(struct miscde
{
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
struct file *memfd = NULL;
- struct address_space *mapping = NULL;
struct udmabuf *ubuf;
struct dma_buf *buf;
- pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
- struct page *page;
- int seals, ret = -EINVAL;
+ pgoff_t pgoff, pgcnt, pgbuf = 0, pglimit, nr_pages;
+ pgoff_t subpgoff, maxsubpgs;
+ struct hstate *hpstate;
+ long ret = -EINVAL;
+ int seals;
u32 i, flags;
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
@@ -239,8 +252,7 @@ static long udmabuf_create(struct miscde
memfd = fget(list[i].memfd);
if (!memfd)
goto err;
- mapping = memfd->f_mapping;
- if (!shmem_mapping(mapping))
+ if (!shmem_file(memfd) && !is_file_hugepages(memfd))
goto err;
seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
if (seals == -EINVAL)
@@ -251,14 +263,41 @@ static long udmabuf_create(struct miscde
goto err;
pgoff = list[i].offset >> PAGE_SHIFT;
pgcnt = list[i].size >> PAGE_SHIFT;
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- page = shmem_read_mapping_page(mapping, pgoff + pgidx);
- if (IS_ERR(page)) {
- ret = PTR_ERR(page);
- goto err;
+ if (is_file_hugepages(memfd)) {
+ if (!ubuf->subpgoff) {
+ ubuf->subpgoff = kmalloc_array(ubuf->pagecount,
+ sizeof(*ubuf->subpgoff),
+ GFP_KERNEL);
+ if (!ubuf->subpgoff) {
+ ret = -ENOMEM;
+ goto err;
+ }
}
- ubuf->pages[pgbuf++] = page;
+ hpstate = hstate_file(memfd);
+ pgoff = list[i].offset >> huge_page_shift(hpstate);
+ subpgoff = (list[i].offset &
+ ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
+ maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
}
+
+ do {
+ nr_pages = shmem_file(memfd) ? pgcnt : 1;
+ ret = pin_user_pages_fd(list[i].memfd, pgoff,
+ nr_pages, FOLL_LONGTERM,
+ ubuf->pages + pgbuf);
+ if (ret < 0)
+ goto err;
+
+ if (is_file_hugepages(memfd)) {
+ ubuf->subpgoff[pgbuf] = subpgoff << PAGE_SHIFT;
+ if (++subpgoff == maxsubpgs) {
+ subpgoff = 0;
+ pgoff++;
+ }
+ }
+ pgbuf += nr_pages;
+ pgcnt -= nr_pages;
+ } while (pgcnt > 0);
fput(memfd);
memfd = NULL;
}
@@ -281,10 +320,11 @@ static long udmabuf_create(struct miscde
return dma_buf_fd(buf, flags);
err:
- while (pgbuf > 0)
- put_page(ubuf->pages[--pgbuf]);
+ while (pgbuf > 0 && ubuf->pages[--pgbuf])
+ unpin_user_page(ubuf->pages[pgbuf]);
if (memfd)
fput(memfd);
+ kfree(ubuf->subpgoff);
kfree(ubuf->pages);
kfree(ubuf);
return ret;
_
Patches currently in -mm which might be from vivek.kasireddy@xxxxxxxxx are
mm-gup-introduce-pin_user_pages_fd-for-pinning-shmem-hugetlbfs-file-pages.patch
udmabuf-pin-the-pages-using-pin_user_pages_fd-api.patch
selftests-dma-buf-udmabuf-add-tests-to-verify-data-after-page-migration.patch
