On Wed, Jul 28, 2021 at 1:08 PM Joao Martins [off-list ref] wrote:

On 7/28/21 8:55 PM, Dan Williams wrote:

quoted

On Wed, Jul 14, 2021 at 12:36 PM Joao Martins [off-list ref] wrote:

quoted

Use try_grab_compound_head() for device-dax GUP when configured with a
compound pagemap.

Rather than incrementing the refcount for each page, do one atomic
addition for all the pages to be pinned.

Performance measured by gup_benchmark improves considerably
get_user_pages_fast() and pin_user_pages_fast() with NVDIMMs:

 $ gup_test -f /dev/dax1.0 -m 16384 -r 10 -S [-u,-a] -n 512 -w
(get_user_pages_fast 2M pages) ~59 ms -> ~6.1 ms
(pin_user_pages_fast 2M pages) ~87 ms -> ~6.2 ms
[altmap]
(get_user_pages_fast 2M pages) ~494 ms -> ~9 ms
(pin_user_pages_fast 2M pages) ~494 ms -> ~10 ms

 $ gup_test -f /dev/dax1.0 -m 129022 -r 10 -S [-u,-a] -n 512 -w
(get_user_pages_fast 2M pages) ~492 ms -> ~49 ms
(pin_user_pages_fast 2M pages) ~493 ms -> ~50 ms
[altmap with -m 127004]
(get_user_pages_fast 2M pages) ~3.91 sec -> ~70 ms
(pin_user_pages_fast 2M pages) ~3.97 sec -> ~74 ms

Signed-off-by: Joao Martins <redacted>
---
 mm/gup.c | 53 +++++++++++++++++++++++++++++++++--------------------
 1 file changed, 33 insertions(+), 20 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 42b8b1fa6521..9baaa1c0b7f3 100644
--- a/mm/gup.c
+++ b/mm/gup.c

@@ -2234,31 +2234,55 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 }
 #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */

+
+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;
+}
+
 #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static int __gup_device_huge(unsigned long pfn, unsigned long addr,
                             unsigned long end, unsigned int flags,
                             struct page **pages, int *nr)
 {
-       int nr_start = *nr;
+       int refs, nr_start = *nr;
        struct dev_pagemap *pgmap = NULL;

        do {
-               struct page *page = pfn_to_page(pfn);
+               struct page *pinned_head, *head, *page = pfn_to_page(pfn);
+               unsigned long next;

                pgmap = get_dev_pagemap(pfn, pgmap);
                if (unlikely(!pgmap)) {
                        undo_dev_pagemap(nr, nr_start, flags, pages);
                        return 0;
                }
-               SetPageReferenced(page);
-               pages[*nr] = page;
-               if (unlikely(!try_grab_page(page, flags))) {
-                       undo_dev_pagemap(nr, nr_start, flags, pages);
+
+               head = compound_head(page);
+               /* @end is assumed to be limited at most one compound page */
+               next = PageCompound(head) ? end : addr + PAGE_SIZE;

Please no ternary operator for this check, but otherwise this patch
looks good to me.

OK. I take that you prefer this instead:

unsigned long next = addr + PAGE_SIZE;

[...]

/* @end is assumed to be limited at most one compound page */
if (PageCompound(head))
        next = end;

Yup.