[PATCH RFC v3 07/21] mm/pgtable: define (pgd|p4d|pud)_offset_lockless() for folded page tables

[Yeoreum Yun <yeoreum.yun@arm.com>]

From: "David Hildenbrand (Arm)" <david@kernel.org>

The default helpers fallback to pud_offset(), passing a pointer to the
stack value.

Let's provide variants that do exactly what (pgd|p4d|pud)_offset() do,
but ignore the passed pgd_t/p4d_t/pud_t, consequently not working on a
pointer to the stack value like the default handlers would.

With this patch, Drop the arm64 custom variant that did that. As it documents:

	Note: reusing the original pointer means that it may be
	dereferenced the same (live) page-table entry multiple times.
	This is safe because it is still only loaded once in the
	context of each level and the CPU guarantees same-address
	read-after-read ordering.

Do not document this, as the double read will be removed in the next patch.

Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
---
 arch/arm64/include/asm/pgtable.h    | 23 -----------------------
 include/asm-generic/pgtable-nop4d.h |  7 +++++++
 include/asm-generic/pgtable-nopmd.h |  7 +++++++
 include/asm-generic/pgtable-nopud.h |  7 +++++++
 4 files changed, 21 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e89ec5f4787b..a3c882e46777 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1180,29 +1180,6 @@ static inline bool pgtable_l5_enabled(void) { return false; }
 #define p4d_clear_fixmap()
 
 #define p4d_offset_kimg(dir,addr)	((p4d_t *)dir)
-
-static inline
-p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr)
-{
-	/*
-	 * With runtime folding of the pud, pud_offset_lockless() passes
-	 * the 'pgd_t *' we return here to p4d_to_folded_pud(), which
-	 * will offset the pointer assuming that it points into
-	 * a page-table page. However, the fast GUP path passes us a
-	 * pgd_t allocated on the stack and so we must use the original
-	 * pointer in 'pgdp' to construct the p4d pointer instead of
-	 * using the generic p4d_offset_lockless() implementation.
-	 *
-	 * Note: reusing the original pointer means that we may
-	 * dereference the same (live) page-table entry multiple times.
-	 * This is safe because it is still only loaded once in the
-	 * context of each level and the CPU guarantees same-address
-	 * read-after-read ordering.
-	 */
-	return p4d_offset(pgdp, addr);
-}
-#define p4d_offset_lockless p4d_offset_lockless_folded
-
 #endif  /* CONFIG_PGTABLE_LEVELS > 4 */
 
 #define pgd_set_fixmap(addr)	((pgd_t *)set_fixmap_offset(FIX_PGD, addr))
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index c6a5a43899b5..019c3f074b77 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -39,6 +39,13 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 	return (p4d_t *)pgd;
 }
 
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd,
+		unsigned long address)
+{
+	return (p4d_t *)pgdp;
+}
+#define p4d_offset_lockless p4d_offset_lockless
+
 #define p4d_val(x)				(pgd_val((x).pgd))
 #define __p4d(x)				((p4d_t) { __pgd(x) })
 
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index 4e5aaf253b6a..1dd5b165234b 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -49,6 +49,13 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
 }
 #define pmd_offset pmd_offset
 
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud,
+		unsigned long address)
+{
+	return (pmd_t *)pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
 #define pmd_val(x)				(pud_val((x).pud))
 #define __pmd(x)				((pmd_t) { __pud(x) } )
 
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 6c9bca78047c..5a2b0a81ae19 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -47,6 +47,13 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 }
 #define pud_offset pud_offset
 
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d,
+		unsigned long address)
+{
+	return (pud_t *)p4dp;
+}
+#define pud_offset_lockless pud_offset_lockless
+
 #define pud_val(x)				(p4d_val((x).p4d))
 #define __pud(x)				((pud_t) { __p4d(x) })
 

-- 
2.43.0