[PATCH 1/9] huge_pages: get rid of process_huge_page()

[Ankur Arora <ankur.a.arora@oracle.com>]

process_huge_pages() (and the subsequent call to process_subpage())
translate between base-addr[index], struct page *, first when calling
clear/copy_subpage() which then translates to the parameters
needed in clear/copy_user_highpage().

There's no runtime cost in doing this, but it's unnecessary complexity
for something that only has two users.

Accordingly, fold process_huge_page() back in its callers.

Link: https://lore.kernel.org/lkml/20220606202109.1306034-1-ankur.a.arora@oracle.com/
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 mm/memory.c | 126 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 73 insertions(+), 53 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index f456f3b5049c..d54bc27a35ca 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5629,63 +5629,13 @@ EXPORT_SYMBOL(__might_fault);
 #endif
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
-/*
- * Process all subpages of the specified huge page with the specified
- * operation.  The target subpage will be processed last to keep its
- * cache lines hot.
- */
-static inline void process_huge_page(
-	unsigned long addr_hint, unsigned int pages_per_huge_page,
-	void (*process_subpage)(unsigned long addr, int idx, void *arg),
-	void *arg)
-{
-	int i, n, base, l;
-	unsigned long addr = addr_hint &
-		~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
-
-	/* Process target subpage last to keep its cache lines hot */
-	might_sleep();
-	n = (addr_hint - addr) / PAGE_SIZE;
-	if (2 * n <= pages_per_huge_page) {
-		/* If target subpage in first half of huge page */
-		base = 0;
-		l = n;
-		/* Process subpages at the end of huge page */
-		for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
-			cond_resched();
-			process_subpage(addr + i * PAGE_SIZE, i, arg);
-		}
-	} else {
-		/* If target subpage in second half of huge page */
-		base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
-		l = pages_per_huge_page - n;
-		/* Process subpages at the begin of huge page */
-		for (i = 0; i < base; i++) {
-			cond_resched();
-			process_subpage(addr + i * PAGE_SIZE, i, arg);
-		}
-	}
-	/*
-	 * Process remaining subpages in left-right-left-right pattern
-	 * towards the target subpage
-	 */
-	for (i = 0; i < l; i++) {
-		int left_idx = base + i;
-		int right_idx = base + 2 * l - 1 - i;
-
-		cond_resched();
-		process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg);
-		cond_resched();
-		process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg);
-	}
-}
 
 static void clear_gigantic_page(struct page *page,
 				unsigned long addr,
 				unsigned int pages_per_huge_page)
 {
 	int i;
-	struct page *p;
+	struct page *p = page;
 
 	might_sleep();
 	for (i = 0; i < pages_per_huge_page; i++) {
@@ -5707,13 +5657,48 @@ void clear_huge_page(struct page *page,
 {
 	unsigned long addr = addr_hint &
 		~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
+	int i, n, base, l;
 
 	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
 		clear_gigantic_page(page, addr, pages_per_huge_page);
 		return;
 	}
 
-	process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page);
+	/* Process target subpage last to keep its cache lines hot */
+	might_sleep();
+	n = (addr_hint - addr) / PAGE_SIZE;
+	if (2 * n <= pages_per_huge_page) {
+		/* If target subpage in first half of huge page */
+		base = 0;
+		l = n;
+		/* Process subpages at the end of huge page */
+		for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
+			cond_resched();
+			clear_subpage(addr + i * PAGE_SIZE, i, (void *)page);
+		}
+	} else {
+		/* If target subpage in second half of huge page */
+		base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
+		l = pages_per_huge_page - n;
+		/* Process subpages at the begin of huge page */
+		for (i = 0; i < base; i++) {
+			cond_resched();
+			clear_subpage(addr + i * PAGE_SIZE, i, (void *)page);
+		}
+	}
+	/*
+	 * Process remaining subpages in left-right-left-right pattern
+	 * towards the target subpage
+	 */
+	for (i = 0; i < l; i++) {
+		int left_idx = base + i;
+		int right_idx = base + 2 * l - 1 - i;
+
+		cond_resched();
+		clear_subpage(addr + left_idx * PAGE_SIZE, left_idx, (void *)page);
+		cond_resched();
+		clear_subpage(addr + right_idx * PAGE_SIZE, right_idx, (void *)page);
+	}
 }
 
 static void copy_user_gigantic_page(struct page *dst, struct page *src,
@@ -5759,6 +5744,7 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 		.src = src,
 		.vma = vma,
 	};
+	int i, n, base, l;
 
 	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
 		copy_user_gigantic_page(dst, src, addr, vma,
@@ -5766,7 +5752,41 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 		return;
 	}
 
-	process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg);
+	/* Process target subpage last to keep its cache lines hot */
+	might_sleep();
+	n = (addr_hint - addr) / PAGE_SIZE;
+	if (2 * n <= pages_per_huge_page) {
+		/* If target subpage in first half of huge page */
+		base = 0;
+		l = n;
+		/* Process subpages at the end of huge page */
+		for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
+			cond_resched();
+			copy_subpage(addr + i * PAGE_SIZE, i, &arg);
+		}
+	} else {
+		/* If target subpage in second half of huge page */
+		base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
+		l = pages_per_huge_page - n;
+		/* Process subpages at the begin of huge page */
+		for (i = 0; i < base; i++) {
+			cond_resched();
+			copy_subpage(addr + i * PAGE_SIZE, i, &arg);
+		}
+	}
+	/*
+	 * Process remaining subpages in left-right-left-right pattern
+	 * towards the target subpage
+	 */
+	for (i = 0; i < l; i++) {
+		int left_idx = base + i;
+		int right_idx = base + 2 * l - 1 - i;
+
+		cond_resched();
+		copy_subpage(addr + left_idx * PAGE_SIZE, left_idx, &arg);
+		cond_resched();
+		copy_subpage(addr + right_idx * PAGE_SIZE, right_idx, &arg);
+	}
 }
 
 long copy_huge_page_from_user(struct page *dst_page,
-- 
2.31.1