Change folio_zero_user() to clear contiguous page ranges instead of
clearing using the current page-at-a-time approach. Exposing the largest
feasible length can be useful in enabling processors to optimize based
on extent.

However, clearing in large chunks can have two problems:

 - cache locality when clearing small folios (< MAX_ORDER_NR_PAGES)
   (larger folios don't have any expectation of cache locality).

 - preemption latency when clearing large folios.

Handle the first by splitting the clearing in three parts: the
faulting page and its immediate locality, its left and right
regions; with the local neighbourhood cleared last.

The second problem becomes relevant when running under cooperative
preemption models. Limit the worst case preemption latency by clearing
in architecture specified PAGE_CONTIG_NR units, using a default value
of 1 where not specified.

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 include/linux/mm.h |  6 ++++
 mm/memory.c        | 82 ++++++++++++++++++++++++++++++++++------------
 2 files changed, 67 insertions(+), 21 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0cde9b01da5e..29b2a8bf7b4f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3768,6 +3768,12 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 				unsigned int order) {}
 #endif	/* CONFIG_DEBUG_PAGEALLOC */
 
+#ifndef ARCH_PAGE_CONTIG_NR
+#define PAGE_CONTIG_NR	1
+#else
+#define PAGE_CONTIG_NR	ARCH_PAGE_CONTIG_NR
+#endif
+
 #ifndef clear_pages
 /**
  * clear_pages() - clear a page range using a kernel virtual address.
diff --git a/mm/memory.c b/mm/memory.c
index 0ba4f6b71847..0f5b1900b480 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -7021,40 +7021,80 @@ static inline int process_huge_page(
 	return 0;
 }
 
-static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint,
-				unsigned int nr_pages)
+/*
+ * Clear contiguous pages chunking them up when running under
+ * non-preemptible models.
+ */
+static void clear_contig_highpages(struct page *page, unsigned long addr,
+				   unsigned int npages)
 {
-	unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio));
-	int i;
+	unsigned int i, count, unit;
 
-	might_sleep();
-	for (i = 0; i < nr_pages; i++) {
+	unit = preempt_model_preemptible() ? npages : PAGE_CONTIG_NR;
+
+	for (i = 0; i < npages; ) {
+		count = min(unit, npages - i);
+		clear_user_highpages(nth_page(page, i),
+				     addr + i * PAGE_SIZE, count);
+		i += count;
 		cond_resched();
-		clear_user_highpage(folio_page(folio, i), addr + i * PAGE_SIZE);
 	}
 }
 
-static int clear_subpage(unsigned long addr, int idx, void *arg)
-{
-	struct folio *folio = arg;
-
-	clear_user_highpage(folio_page(folio, idx), addr);
-	return 0;
-}
-
 /**
  * folio_zero_user - Zero a folio which will be mapped to userspace.
  * @folio: The folio to zero.
- * @addr_hint: The address will be accessed or the base address if uncelar.
+ * @addr_hint: The address accessed by the user or the base address.
+ *
+ * Uses architectural support for clear_pages() to zero page extents
+ * instead of clearing page-at-a-time.
+ *
+ * Clearing of small folios (< MAX_ORDER_NR_PAGES) is split in three parts:
+ * pages in the immediate locality of the faulting page, and its left, right
+ * regions; the local neighbourhood cleared last in order to keep cache
+ * lines of the target region hot.
+ *
+ * For larger folios we assume that there is no expectation of cache locality
+ * and just do a straight zero.
  */
 void folio_zero_user(struct folio *folio, unsigned long addr_hint)
 {
-	unsigned int nr_pages = folio_nr_pages(folio);
+	unsigned long base_addr = ALIGN_DOWN(addr_hint, folio_size(folio));
+	const long fault_idx = (addr_hint - base_addr) / PAGE_SIZE;
+	const struct range pg = DEFINE_RANGE(0, folio_nr_pages(folio) - 1);
+	const int width = 2; /* number of pages cleared last on either side */
+	struct range r[3];
+	int i;
 
-	if (unlikely(nr_pages > MAX_ORDER_NR_PAGES))
-		clear_gigantic_page(folio, addr_hint, nr_pages);
-	else
-		process_huge_page(addr_hint, nr_pages, clear_subpage, folio);
+	if (folio_nr_pages(folio) > MAX_ORDER_NR_PAGES) {
+		clear_contig_highpages(folio_page(folio, 0),
+					base_addr, folio_nr_pages(folio));
+		return;
+	}
+
+	/*
+	 * Faulting page and its immediate neighbourhood. Cleared at the end to
+	 * ensure it sticks around in the cache.
+	 */
+	r[2] = DEFINE_RANGE(clamp_t(s64, fault_idx - width, pg.start, pg.end),
+			    clamp_t(s64, fault_idx + width, pg.start, pg.end));
+
+	/* Region to the left of the fault */
+	r[1] = DEFINE_RANGE(pg.start,
+			    clamp_t(s64, r[2].start-1, pg.start-1, r[2].start));
+
+	/* Region to the right of the fault: always valid for the common fault_idx=0 case. */
+	r[0] = DEFINE_RANGE(clamp_t(s64, r[2].end+1, r[2].end, pg.end+1),
+			    pg.end);
+
+	for (i = 0; i <= 2; i++) {
+		unsigned int npages = range_len(&r[i]);
+		struct page *page = folio_page(folio, r[i].start);
+		unsigned long addr = base_addr + folio_page_idx(folio, page) * PAGE_SIZE;
+
+		if (npages > 0)
+			clear_contig_highpages(page, addr, npages);
+	}
 }
 
 static int copy_user_gigantic_page(struct folio *dst, struct folio *src,
-- 
2.43.5