[v1,1/3] mm/gup: replace FOLL_NUMA by gup_can_follow_protnone()

Commit Message

David Hildenbrand Aug. 25, 2022, 4:46 p.m. UTC

No need for a special flag that is not even properly documented to be
internal-only.

Let's just factor this check out and get rid of this flag. The separate
function has the nice benefit that we can centralize comments.

Signed-off-by: David Hildenbrand <[e-mail]>
---
 include/linux/mm.h | 16 +++++++++++++++-
 mm/gup.c           | 12 ++----------
 mm/huge_memory.c   |  2 +-
 3 files changed, 18 insertions(+), 12 deletions(-)

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 982f2607180b..8b85765d7a98 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2881,7 +2881,6 @@  struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 				 * and return without waiting upon it */
 #define FOLL_NOFAULT	0x80	/* do not fault in pages */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
-#define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
@@ -2997,6 +2996,21 @@  static inline bool gup_must_unshare(unsigned int flags, struct page *page)
 	return !PageAnonExclusive(page);
 }
 
+/*
+ * Indicates whether GUP can follow a PROT_NONE mapped page, or whether
+ * a (NUMA hinting) fault is required.
+ */
+static inline bool gup_can_follow_protnone(unsigned int flags)
+{
+	/*
+	 * FOLL_FORCE has to be able to make progress even if the VMA is
+	 * inaccessible. Further, FOLL_FORCE access usually does not represent
+	 * application behaviour and we should avoid triggering NUMA hinting
+	 * faults.
+	 */
+	return flags & FOLL_FORCE;
+}
+
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
diff --git a/mm/gup.c b/mm/gup.c
index 5abdaf487460..a1355dbd848e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -554,7 +554,7 @@  static struct page *follow_page_pte(struct vm_area_struct *vma,
 		migration_entry_wait(mm, pmd, address);
 		goto retry;
 	}
-	if ((flags & FOLL_NUMA) && pte_protnone(pte))
+	if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
 		goto no_page;
 
 	page = vm_normal_page(vma, address, pte);
@@ -707,7 +707,7 @@  static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	if (likely(!pmd_trans_huge(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
-	if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
+	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags))
 		return no_page_table(vma, flags);
 
 retry_locked:
@@ -1153,14 +1153,6 @@  static long __get_user_pages(struct mm_struct *mm,
 
 	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
 
-	/*
-	 * If FOLL_FORCE is set then do not force a full fault as the hinting
-	 * fault information is unrelated to the reference behaviour of a task
-	 * using the address space
-	 */
-	if (!(gup_flags & FOLL_FORCE))
-		gup_flags |= FOLL_NUMA;
-
 	do {
 		struct page *page;
 		unsigned int foll_flags = gup_flags;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e9414ee57c5b..482c1826e723 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1449,7 +1449,7 @@  struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		return ERR_PTR(-EFAULT);
 
 	/* Full NUMA hinting faults to serialise migration in fault paths */
-	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
+	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags))
 		return NULL;
 
 	if (!pmd_write(*pmd) && gup_must_unshare(flags, page))