From: David Hildenbrand <david@redhat.com>
Date: Fri, 2 Aug 2024 15:55:20 +0000 (+0200)
Subject: mm/huge_memory: convert split_huge_pages_pid() from follow_page() to folio_walk
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=8710f6ed34e7bcf98971d65acfb5eaed5fc469b0;p=users%2Fhch%2Fmisc.git

mm/huge_memory: convert split_huge_pages_pid() from follow_page() to folio_walk

Let's remove yet another follow_page() user.  Note that we have to do the
split without holding the PTL, after folio_walk_end().  We don't care
about losing the secretmem check in follow_page().

[david@redhat.com: teach can_split_folio() that we are not holding an additional reference]
  Link: https://lkml.kernel.org/r/c75d1c6c-8ea6-424f-853c-1ccda6c77ba2@redhat.com
Link: https://lkml.kernel.org/r/20240802155524.517137-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e25d9ebfdf89..ce44caa40eed 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -314,7 +314,7 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 		unsigned long len, unsigned long pgoff, unsigned long flags,
 		vm_flags_t vm_flags);
 
-bool can_split_folio(struct folio *folio, int *pextra_pins);
+bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
 int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
 static inline int split_huge_page(struct page *page)
@@ -470,7 +470,7 @@ thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
 }
 
 static inline bool
-can_split_folio(struct folio *folio, int *pextra_pins)
+can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
 {
 	return false;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 29e76d285e4b..666fa675e5b6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -40,6 +40,7 @@
 #include <linux/memory-tiers.h>
 #include <linux/compat.h>
 #include <linux/pgalloc_tag.h>
+#include <linux/pagewalk.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -3017,7 +3018,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 }
 
 /* Racy check whether the huge page can be split */
-bool can_split_folio(struct folio *folio, int *pextra_pins)
+bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
 {
 	int extra_pins;
 
@@ -3029,7 +3030,8 @@ bool can_split_folio(struct folio *folio, int *pextra_pins)
 		extra_pins = folio_nr_pages(folio);
 	if (pextra_pins)
 		*pextra_pins = extra_pins;
-	return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1;
+	return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins -
+					caller_pins;
 }
 
 /*
@@ -3197,7 +3199,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 	 * Racy check if we can split the page, before unmap_folio() will
 	 * split PMDs
 	 */
-	if (!can_split_folio(folio, &extra_pins)) {
+	if (!can_split_folio(folio, 1, &extra_pins)) {
 		ret = -EAGAIN;
 		goto out_unlock;
 	}
@@ -3504,7 +3506,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 	 */
 	for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
 		struct vm_area_struct *vma = vma_lookup(mm, addr);
-		struct page *page;
+		struct folio_walk fw;
 		struct folio *folio;
 
 		if (!vma)
@@ -3516,13 +3518,10 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 			continue;
 		}
 
-		/* FOLL_DUMP to ignore special (like zero) pages */
-		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
-
-		if (IS_ERR_OR_NULL(page))
+		folio = folio_walk_start(&fw, vma, addr, 0);
+		if (!folio)
 			continue;
 
-		folio = page_folio(page);
 		if (!is_transparent_hugepage(folio))
 			goto next;
 
@@ -3536,18 +3535,24 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		 * can be split or not. So skip the check here.
 		 */
 		if (!folio_test_private(folio) &&
-		    !can_split_folio(folio, NULL))
+		    !can_split_folio(folio, 0, NULL))
 			goto next;
 
 		if (!folio_trylock(folio))
 			goto next;
+		folio_get(folio);
+		folio_walk_end(&fw, vma);
 
 		if (!split_folio_to_order(folio, new_order))
 			split++;
 
 		folio_unlock(folio);
-next:
 		folio_put(folio);
+
+		cond_resched();
+		continue;
+next:
+		folio_walk_end(&fw, vma);
 		cond_resched();
 	}
 	mmap_read_unlock(mm);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6b70e80ca0ee..96ce889ea3d0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1227,7 +1227,7 @@ retry:
 					goto keep_locked;
 				if (folio_test_large(folio)) {
 					/* cannot split folio, skip it */
-					if (!can_split_folio(folio, NULL))
+					if (!can_split_folio(folio, 1, NULL))
 						goto activate_locked;
 					/*
 					 * Split partially mapped folios right away.