arm: mm: introduce special ptes for LPAE

We need a mechanism to tag ptes as being special, this indicates that no
attempt should be made to access the underlying struct page * associated
with the pte.  This is used by the fast_gup when operating on ptes as it
has no means to access VMAs (that also contain this information)
locklessly.

The L_PTE_SPECIAL bit is already allocated for LPAE, this patch modifies
pte_special and pte_mkspecial to make use of it, and defines
__HAVE_ARCH_PTE_SPECIAL.

This patch also excludes special ptes from the icache/dcache sync logic.

Signed-off-by: Steve Capper <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Cc: Dann Frazier <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Russell King <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Christoffer Dall <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/arm/include/asm/pgtable-2level.h

@@ -182,6 +182,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_addr_end(addr,end) (end)
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#define pte_special(pte)	(0)
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
 /*
  * We don't have huge page support for short descriptors, for the moment

arch/arm/include/asm/pgtable-3level.h

@@ -213,6 +213,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
 
 #define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
+#define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	pte_val(pte) |= L_PTE_SPECIAL;
+	return pte;
+}
+#define	__HAVE_ARCH_PTE_SPECIAL
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))

arch/arm/include/asm/pgtable.h

@@ -226,7 +226,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_dirty(pte)		(pte_isset((pte), L_PTE_DIRTY))
 #define pte_young(pte)		(pte_isset((pte), L_PTE_YOUNG))
 #define pte_exec(pte)		(pte_isclear((pte), L_PTE_XN))
-#define pte_special(pte)	(0)
 
 #define pte_valid_user(pte)	\
 	(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
@@ -245,7 +244,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	unsigned long ext = 0;
 
 	if (addr < TASK_SIZE && pte_valid_user(pteval)) {
-		__sync_icache_dcache(pteval);
+		if (!pte_special(pteval))
+			__sync_icache_dcache(pteval);
 		ext |= PTE_EXT_NG;
 	}
 
@@ -264,8 +264,6 @@ PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 PTE_BIT_FUNC(mkexec,   &= ~L_PTE_XN);
 PTE_BIT_FUNC(mknexec,   |= L_PTE_XN);
 
-static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |