arm64: hugetlb: add support for PTE contiguous bit

The arm64 MMU supports a Contiguous bit which is a hint that the TTE
is one of a set of contiguous entries which can be cached in a single
TLB entry.  Supporting this bit adds new intermediate huge page sizes.

The set of huge page sizes available depends on the base page size.
Without using contiguous pages the huge page sizes are as follows.

 4KB:   2MB  1GB
64KB: 512MB

With a 4KB granule, the contiguous bit groups together sets of 16 pages
and with a 64KB granule it groups sets of 32 pages.  This enables two new
huge page sizes in each case, so that the full set of available sizes
is as follows.

 4KB:  64KB   2MB  32MB  1GB
64KB:   2MB 512MB  16GB

If a 16KB granule is used then the contiguous bit groups 128 pages
at the PTE level and 32 pages at the PMD level.

If the base page size is set to 64KB then 2MB pages are enabled by
default.  It is possible in the future to make 2MB the default huge
page size for both 4KB and 64KB granules.

Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com>
Reviewed-by: Steve Capper <steve.capper@linaro.org>
Signed-off-by: David Woods <dwoods@ezchip.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@
 	return *ptep;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
 
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
 
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
@@ -97,4 +68,19 @@
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+				      unsigned long addr, pte_t *ptep,
+				      pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep);
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e8..5c25b83 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -90,7 +90,23 @@
 /*
  * Contiguous page definitions.
  */
-#define CONT_PTES		(_AC(1, UL) << CONT_SHIFT)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define CONT_PTE_SHIFT		5
+#define CONT_PMD_SHIFT		5
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define CONT_PTE_SHIFT		7
+#define CONT_PMD_SHIFT		5
+#else
+#define CONT_PTE_SHIFT		4
+#define CONT_PMD_SHIFT		4
+#endif
+
+#define CONT_PTES		(1 << CONT_PTE_SHIFT)
+#define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
+#define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
+#define CONT_PMDS		(1 << CONT_PMD_SHIFT)
+#define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
+#define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
 /* the the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 450b355..35a318c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -227,7 +227,8 @@
 
 static inline pte_t pte_mkcont(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_CONT));
+	pte = set_pte_bit(pte, __pgprot(PTE_CONT));
+	return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
 }
 
 static inline pte_t pte_mknoncont(pte_t pte)
@@ -235,6 +236,11 @@
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
+static inline pmd_t pmd_mkcont(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
@@ -304,7 +310,7 @@
 /*
  * Hugetlb definitions.
  */
-#define HUGE_MAX_HSTATE		2
+#define HUGE_MAX_HSTATE		4
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))