hexagon/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 16 GiB (was 32
GiB).

While at it, mask the type in __swp_entry().

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: David Hildenbrand <[email protected]>
Cc: Brian Cain <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

arch/hexagon/include/asm/pgtable.h

@@ -61,6 +61,9 @@ extern unsigned long empty_zero_page;
  * So we'll put up with a bit of inefficiency for now...
  */
 
+/* We borrow bit 6 to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	(1<<6)
+
 /*
  * Top "FOURTH" level (pgd), which for the Hexagon VM is really
  * only the second from the bottom, pgd and pud both being collapsed.
@@ -359,9 +362,12 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
 
 /*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
  * Swap/file PTE definitions.  If _PAGE_PRESENT is zero, the rest of the PTE is
  * interpreted as swap information.  The remaining free bits are interpreted as
- * swap type/offset tuple.  Rather than have the TLB fill handler test
+ * listed below.  Rather than have the TLB fill handler test
  * _PAGE_PRESENT, we're going to reserve the permissions bits and set them to
  * all zeros for swap entries, which speeds up the miss handler at the cost of
  * 3 bits of offset.  That trade-off can be revisited if necessary, but Hexagon
@@ -371,9 +377,10 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
  * Format of swap PTE:
  *	bit	0:	Present (zero)
  *	bits	1-5:	swap type (arch independent layer uses 5 bits max)
- *	bits	6-9:	bits 3:0 of offset
+ *	bit	6:	exclusive marker
+ *	bits	7-9:	bits 2:0 of offset
  *	bits	10-12:	effectively _PAGE_PROTNONE (all zero)
- *	bits	13-31:  bits 22:4 of swap offset
+ *	bits	13-31:  bits 21:3 of swap offset
  *
  * The split offset makes some of the following macros a little gnarly,
  * but there's plenty of precedent for this sort of thing.
@@ -383,11 +390,29 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define __swp_type(swp_pte)		(((swp_pte).val >> 1) & 0x1f)
 
 #define __swp_offset(swp_pte) \
-	((((swp_pte).val >> 6) & 0xf) | (((swp_pte).val >> 9) & 0x7ffff0))
+	((((swp_pte).val >> 7) & 0x7) | (((swp_pte).val >> 10) & 0x3ffff8))
 
 #define __swp_entry(type, offset) \
 	((swp_entry_t)	{ \
-		((type << 1) | \
-		 ((offset & 0x7ffff0) << 9) | ((offset & 0xf) << 6)) })
+		(((type & 0x1f) << 1) | \
+		 ((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) })
+
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_SWP_EXCLUSIVE;
+	return pte;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	pte_val(pte) &= ~_PAGE_SWP_EXCLUSIVE;
+	return pte;
+}
 
 #endif