arm/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE

Let's support __HAVE_ARCH_PTE_SWP_EXCLUSIVE by stealing one bit from the
offset.  This reduces the maximum swap space per file to 64 GiB (was 128
GiB).

While at it drop the PTE_TYPE_FAULT from __swp_entry_to_pte() which is
defined to be 0 and is rather confusing because we should be dealing with
"Linux PTEs" not "hardware PTEs".  Also, properly mask the type in
__swp_entry().

Link: https://lkml.kernel.org/r/20230113171026.582290-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 34 insertions, 7 deletions

diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 92abd4cd8ca2..ce543cd9380c 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -126,6 +126,9 @@
 #define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 11)
 
+/* We borrow bit 7 to store the exclusive marker in swap PTEs. */
+#define L_PTE_SWP_EXCLUSIVE	L_PTE_RDONLY
+
 /*
  * These are the memory types, defined to be compatible with
  * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index eabe72ff7381..106049791500 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -76,6 +76,9 @@
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
 #define L_PTE_RDONLY		(_AT(pteval_t, 1) << 58)	/* READ ONLY */
 
+/* We borrow bit 7 to store the exclusive marker in swap PTEs. */
+#define L_PTE_SWP_EXCLUSIVE	(_AT(pteval_t, 1) << 7)
+
 #define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
 #define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
 #define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f049072b2e85..886c275995a2 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -271,27 +271,48 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 }
 
 /*
- * Encode and decode a swap entry.  Swap entries are stored in the Linux
- * page tables as follows:
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTEs:
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset ------------------------> < type -> 0 0
+ *   <------------------- offset ------------------> E < type -> 0 0
+ *
+ *   E is the exclusive marker that is not stored in swap entries.
  *
- * This gives us up to 31 swap files and 128GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	2
 #define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
-#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT + 1)
 
 #define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
 #define __swp_offset(x)		((x).val >> __SWP_OFFSET_SHIFT)
-#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+#define __swp_entry(type, offset) ((swp_entry_t) { (((type) & __SWP_TYPE_BITS) << __SWP_TYPE_SHIFT) | \
+						   ((offset) << __SWP_OFFSET_SHIFT) })
 
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(swp)	__pte((swp).val | PTE_TYPE_FAULT)
+#define __swp_entry_to_pte(swp)	__pte((swp).val)
+
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_isset(pte, L_PTE_SWP_EXCLUSIVE);
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(L_PTE_SWP_EXCLUSIVE));
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(L_PTE_SWP_EXCLUSIVE));
+}
 
 /*
  * It is an error for the kernel to have more swap files than we can