[PATCH RFC 6/9] mm/gup: Grab head page refcount once for group of subpages

[Joao Martins <joao.m.martins@oracle.com>]

Much like hugetlbfs or THPs, we treat device pagemaps with
compound pages like the rest of GUP handling of compound pages.

Rather than incrementing the refcount every 4K, we record
all sub pages and increment by @refs amount *once*.

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

 $ gup_benchmark -f /dev/dax0.2 -m 16384 -r 10 -S [-u,-a] -n 512 -w

(get_user_pages_fast 2M pages) ~75k us -> ~3.6k us
(pin_user_pages_fast 2M pages) ~125k us -> ~3.8k us

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
 mm/gup.c | 67 ++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 51 insertions(+), 16 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609..194e6981eb03 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2250,22 +2250,68 @@ 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)
+static int __gup_device_compound_huge(struct dev_pagemap *pgmap,
+				      struct page *head, unsigned long sz,
+				      unsigned long addr, unsigned long end,
+				      unsigned int flags, struct page **pages)
+{
+	struct page *page;
+	int refs;
+
+	if (!(pgmap->flags & PGMAP_COMPOUND))
+		return -1;
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	refs = record_subpages(page, addr, end, pages);
+
+	SetPageReferenced(page);
+	head = try_grab_compound_head(head, refs, flags);
+	if (!head) {
+		ClearPageReferenced(page);
+		return 0;
+	}
+
+	return refs;
+}
+
+static int __gup_device_huge(unsigned long pfn, unsigned long sz,
+			     unsigned long addr, unsigned long end,
+			     unsigned int flags, struct page **pages, int *nr)
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
 
 	do {
 		struct page *page = pfn_to_page(pfn);
+		int refs;
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
 			return 0;
 		}
+
+		refs = __gup_device_compound_huge(pgmap, page, sz, addr, end,
+						  flags, pages + *nr);
+		if (refs >= 0) {
+			*nr += refs;
+			put_dev_pagemap(pgmap);
+			return refs ? 1 : 0;
+		}
+
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
@@ -2289,7 +2335,7 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PMD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
@@ -2307,7 +2353,7 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PUD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
@@ -2334,17 +2380,6 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
-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;
-}
-
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
-- 
2.17.1
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org