powerpc: Free a PTE bit on ppc64 with 64K pages

This frees a PTE bit when using 64K pages on ppc64.  This is done
by getting rid of the separate _PAGE_HASHPTE bit.  Instead, we just test
if any of the 16 sub-page bits is set.  For non-combo pages (ie. real
64K pages), we set SUB0 and the location encoding in that field.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/mm/hash_low_64.S

@@ -388,7 +388,7 @@ _GLOBAL(__hash_page_4K)
 	 */
 	rlwinm	r30,r4,32-9+7,31-7,31-7	/* _PAGE_RW -> _PAGE_DIRTY */
 	or	r30,r30,r31
-	ori	r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE
+	ori	r30,r30,_PAGE_BUSY | _PAGE_ACCESSED
 	oris	r30,r30,_PAGE_COMBO@h
 	/* Write the linux PTE atomically (setting busy) */
 	stdcx.	r30,0,r6
@@ -468,7 +468,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	 * go to out-of-line code to try to modify the HPTE. We look for
 	 * the bit at (1 >> (index + 32))
 	 */
-	andi.	r0,r31,_PAGE_HASHPTE
+	rldicl.	r0,r31,64-12,48
 	li	r26,0			/* Default hidx */
 	beq	htab_insert_pte
 
@@ -726,11 +726,11 @@ BEGIN_FTR_SECTION
 	bne-	ht64_bail_ok
 END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
 	/* Prepare new PTE value (turn access RW into DIRTY, then
-	 * add BUSY,HASHPTE and ACCESSED)
+	 * add BUSY and ACCESSED)
 	 */
 	rlwinm	r30,r4,32-9+7,31-7,31-7	/* _PAGE_RW -> _PAGE_DIRTY */
 	or	r30,r30,r31
-	ori	r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE
+	ori	r30,r30,_PAGE_BUSY | _PAGE_ACCESSED
 	/* Write the linux PTE atomically (setting busy) */
 	stdcx.	r30,0,r6
 	bne-	1b
@@ -798,18 +798,21 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	/* Check if we may already be in the hashtable, in this case, we
 	 * go to out-of-line code to try to modify the HPTE
 	 */
-	andi.	r0,r31,_PAGE_HASHPTE
+	rldicl.	r0,r31,64-12,48
 	bne	ht64_modify_pte
 
 ht64_insert_pte:
 	/* Clear hpte bits in new pte (we also clear BUSY btw) and
-	 * add _PAGE_HASHPTE
+	 * add _PAGE_HPTE_SUB0
 	 */
 	lis	r0,_PAGE_HPTEFLAGS@h
 	ori	r0,r0,_PAGE_HPTEFLAGS@l
 	andc	r30,r30,r0
+#ifdef CONFIG_PPC_64K_PAGES
+	oris	r30,r30,_PAGE_HPTE_SUB0@h
+#else
 	ori	r30,r30,_PAGE_HASHPTE
-
+#endif
 	/* Phyical address in r5 */
 	rldicl	r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT
 	sldi	r5,r5,PAGE_SHIFT

arch/powerpc/mm/hugetlbpage.c

@@ -458,8 +458,7 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access,
 		old_pte = pte_val(*ptep);
 		if (old_pte & _PAGE_BUSY)
 			goto out;
-		new_pte = old_pte | _PAGE_BUSY |
-			_PAGE_ACCESSED | _PAGE_HASHPTE;
+		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
 	} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
 					 old_pte, new_pte));
 
@@ -499,8 +498,11 @@ repeat:
 			      HPTES_PER_GROUP) & ~0x7UL;
 
 		/* clear HPTE slot informations in new PTE */
+#ifdef CONFIG_PPC_64K_PAGES
+		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
+#else
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
-
+#endif
 		/* Add in WIMG bits */
 		/* XXX We should store these in the pte */
 		/* --BenH: I think they are ... */

include/asm-powerpc/pgtable-4k.h

@@ -41,6 +41,7 @@
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 /* PTE bits */
+#define _PAGE_HASHPTE	0x0400 /* software: pte has an associated HPTE */
 #define _PAGE_SECONDARY 0x8000 /* software: HPTE is in secondary group */
 #define _PAGE_GROUP_IX  0x7000 /* software: HPTE index within group */
 #define _PAGE_F_SECOND  _PAGE_SECONDARY

include/asm-powerpc/pgtable-64k.h

@@ -75,6 +75,20 @@ static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
 #define _PAGE_COMBO	0x10000000 /* this is a combo 4k page */
 #define _PAGE_4K_PFN	0x20000000 /* PFN is for a single 4k page */
 
+/* For 64K page, we don't have a separate _PAGE_HASHPTE bit. Instead,
+ * we set that to be the whole sub-bits mask. The C code will only
+ * test this, so a multi-bit mask will work. For combo pages, this
+ * is equivalent as effectively, the old _PAGE_HASHPTE was an OR of
+ * all the sub bits. For real 64k pages, we now have the assembly set
+ * _PAGE_HPTE_SUB0 in addition to setting the HIDX bits which overlap
+ * that mask. This is fine as long as the HIDX bits are never set on
+ * a PTE that isn't hashed, which is the case today.
+ *
+ * A little nit is for the huge page C code, which does the hashing
+ * in C, we need to provide which bit to use.
+ */
+#define _PAGE_HASHPTE	_PAGE_HPTE_SUB
+
 /* Note the full page bits must be in the same location as for normal
  * 4k pages as the same asssembly will be used to insert 64K pages
  * wether the kernel has CONFIG_PPC_64K_PAGES or not
@@ -83,8 +97,7 @@ static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
 #define _PAGE_F_GIX     0x00007000 /* full page: hidx bits */
 
 /* PTE flags to conserve for HPTE identification */
-#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | _PAGE_HPTE_SUB |\
-                         _PAGE_COMBO)
+#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | _PAGE_COMBO)
 
 /* Shift to put page number into pte.
  *

include/asm-powerpc/pgtable-ppc64.h

@@ -91,7 +91,6 @@
 #define _PAGE_DIRTY	0x0080 /* C: page changed */
 #define _PAGE_ACCESSED	0x0100 /* R: page referenced */
 #define _PAGE_RW	0x0200 /* software: user write access allowed */
-#define _PAGE_HASHPTE	0x0400 /* software: pte has an associated HPTE */
 #define _PAGE_BUSY	0x0800 /* software: PTE & hash are busy */
 
 #define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)