powerpc/mm/book3s-64: Use physical addresses in upper page table tree levels

This changes the Linux page tables to store physical addresses
rather than kernel virtual addresses in the upper levels of the
tree (pgd, pud and pmd) for 64-bit Book 3S machines.

This also changes the hugepd pointers used to implement hugepages
when the base page size is 4k to store physical addresses rather than
virtual addresses (again just for 64-bit Book3S machines).

This frees up some high order bits, and will be needed with
PowerISA v3.0 machines which read the page table tree in hardware
in radix mode.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -64,7 +64,7 @@
 #define pgd_none(pgd)		(!pgd_val(pgd))
 #define pgd_bad(pgd)		(pgd_val(pgd) == 0)
 #define pgd_present(pgd)	(pgd_val(pgd) != 0)
-#define pgd_page_vaddr(pgd)	(pgd_val(pgd) & ~PGD_MASKED_BITS)
+#define pgd_page_vaddr(pgd)	__va(pgd_val(pgd) & ~PGD_MASKED_BITS)
 
 static inline void pgd_clear(pgd_t *pgdp)
 {

arch/powerpc/include/asm/book3s/64/hash.h

@@ -222,13 +222,14 @@
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
 #ifndef __ASSEMBLY__
-#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
-				 || (pmd_val(pmd) & PMD_BAD_BITS))
-#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+#define	pmd_bad(pmd)		(pmd_val(pmd) & PMD_BAD_BITS)
+#define pmd_page_vaddr(pmd)	__va(pmd_val(pmd) & ~PMD_MASKED_BITS)
 
-#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
-				 || (pud_val(pud) & PUD_BAD_BITS))
-#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
+#define	pud_bad(pud)		(pud_val(pud) & PUD_BAD_BITS)
+#define pud_page_vaddr(pud)	__va(pud_val(pud) & ~PUD_MASKED_BITS)
+
+/* Pointers in the page table tree are physical addresses */
+#define __pgtable_ptr_val(ptr)	__pa(ptr)
 
 #define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
 #define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))

arch/powerpc/include/asm/hugetlb.h

@@ -19,7 +19,7 @@ static inline pte_t *hugepd_page(hugepd_t hpd)
 	 * We have only four bits to encode, MMU page size
 	 */
 	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
-	return (pte_t *)(hpd.pd & ~HUGEPD_SHIFT_MASK);
+	return __va(hpd.pd & HUGEPD_ADDR_MASK);
 }
 
 static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)

arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -108,6 +108,9 @@
 #ifndef __ASSEMBLY__
 /* pte_clear moved to later in this file */
 
+/* Pointers in the page table tree are virtual addresses */
+#define __pgtable_ptr_val(ptr)	((unsigned long)(ptr))
+
 #define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 

arch/powerpc/include/asm/page.h

@@ -271,6 +271,13 @@ extern long long virt_phys_offset;
 #else
 #define PD_HUGE 0x80000000
 #endif
+
+#else	/* CONFIG_PPC_BOOK3S_64 */
+/*
+ * Book3S 64 stores real addresses in the hugepd entries to
+ * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
+ */
+#define HUGEPD_ADDR_MASK	(0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 /*

arch/powerpc/include/asm/pgalloc-64.h

@@ -53,7 +53,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 #ifndef CONFIG_PPC_64K_PAGES
 
-#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, (unsigned long)PUD)
+#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, __pgtable_ptr_val(PUD))
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -68,19 +68,19 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pud_set(pud, (unsigned long)pmd);
+	pud_set(pud, __pgtable_ptr_val(pmd));
 }
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
 {
-	pmd_set(pmd, (unsigned long)pte);
+	pmd_set(pmd, __pgtable_ptr_val(pte));
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, (unsigned long)page_address(pte_page));
+	pmd_set(pmd, __pgtable_ptr_val(page_address(pte_page)));
 }
 
 #define pmd_pgtable(pmd) pmd_page(pmd)
@@ -171,23 +171,23 @@ extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
 extern void __tlb_remove_table(void *_table);
 #endif
 
-#define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
+#define pud_populate(mm, pud, pmd)	pud_set(pud, __pgtable_ptr_val(pmd))
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
 {
-	pmd_set(pmd, (unsigned long)pte);
+	pmd_set(pmd, __pgtable_ptr_val(pte));
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, (unsigned long)pte_page);
+	pmd_set(pmd, __pgtable_ptr_val(pte_page));
 }
 
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS);
+	return (pgtable_t)pmd_page_vaddr(pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,

arch/powerpc/mm/hugetlbpage.c

@@ -107,8 +107,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 		kmem_cache_free(cachep, new);
 	else {
 #ifdef CONFIG_PPC_BOOK3S_64
-		hpdp->pd = (unsigned long)new |
-			    (shift_to_mmu_psize(pshift) << 2);
+		hpdp->pd = __pa(new) | (shift_to_mmu_psize(pshift) << 2);
 #else
 		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
 #endif