arm64/mm: Hoist barriers out of set_ptes_anysz() loop

set_ptes_anysz() previously called __set_pte() for each PTE in the
range, which would conditionally issue a DSB and ISB to make the new PTE
value immediately visible to the table walker if the new PTE was valid
and for kernel space.

We can do better than this; let's hoist those barriers out of the loop
so that they are only issued once at the end of the loop. We then reduce
the cost by the number of PTEs in the range.

Reviewed-by: Catalin Marinas <[email protected]>
Reviewed-by: Anshuman Khandual <[email protected]>
Signed-off-by: Ryan Roberts <[email protected]>
Tested-by: Luiz Capitulino <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Ryan Roberts

arch/arm64/include/asm/pgtable.h

@@ -320,20 +320,24 @@ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 	WRITE_ONCE(*ptep, pte);
 }
 
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_complete(pte_t pte)
 {
-	__set_pte_nosync(ptep, pte);
-
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
-	 * or update_mmu_cache() have the necessary barriers.
+	 * has the necessary barriers.
 	 */
 	if (pte_valid_not_user(pte)) {
 		dsb(ishst);
 		isb();
 	}
 }
 
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+	__set_pte_nosync(ptep, pte);
+	__set_pte_complete(pte);
+}
+
 static inline pte_t __ptep_get(pte_t *ptep)
 {
 	return READ_ONCE(*ptep);
@@ -658,12 +662,14 @@ static inline void __set_ptes_anysz(struct mm_struct *mm, pte_t *ptep,
 
 	for (;;) {
 		__check_safe_pte_update(mm, ptep, pte);
-		__set_pte(ptep, pte);
+		__set_pte_nosync(ptep, pte);
 		if (--nr == 0)
 			break;
 		ptep++;
 		pte = pte_advance_pfn(pte, stride);
 	}
+
+	__set_pte_complete(pte);
 }
 
 static inline void __set_ptes(struct mm_struct *mm,