arm64: mm: Refactor __flush_tlb_range() to take flags

We have function variants with "_nosync", "_local", "_nonotify" as well
as the "last_level" parameter. Let's generalize and simplify by using a
flags parameter to encode all these variants.

As a first step, convert the "last_level" boolean parameter to a flags
parameter and create the first flag, TLBF_NOWALKCACHE. When present,
walk cache entries are not evicted, which is the same as the old
last_level=true.

Reviewed-by: Linu Cherian <linu.cherian@arm.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: ryanhrob

arch/arm64/include/asm/hugetlb.h

@@ -71,23 +71,23 @@ static inline void __flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 					     unsigned long start,
 					     unsigned long end,
 					     unsigned long stride,
-					     bool last_level)
+					     tlbf_t flags)
 {
 	switch (stride) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		__flush_tlb_range(vma, start, end, PUD_SIZE, last_level, 1);
+		__flush_tlb_range(vma, start, end, PUD_SIZE, 1, flags);
 		break;
 #endif
 	case CONT_PMD_SIZE:
 	case PMD_SIZE:
-		__flush_tlb_range(vma, start, end, PMD_SIZE, last_level, 2);
+		__flush_tlb_range(vma, start, end, PMD_SIZE, 2, flags);
 		break;
 	case CONT_PTE_SIZE:
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, 3);
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, 3, flags);
 		break;
 	default:
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, TLBI_TTL_UNKNOWN);
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, TLBI_TTL_UNKNOWN, flags);
 	}
 }
 
@@ -98,7 +98,7 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	__flush_hugetlb_tlb_range(vma, start, end, stride, false);
+	__flush_hugetlb_tlb_range(vma, start, end, stride, TLBF_NONE);
 }
 
 #endif /* __ASM_HUGETLB_H */

arch/arm64/include/asm/pgtable.h

@@ -89,9 +89,9 @@ static inline void arch_leave_lazy_mmu_mode(void)
 
 /* Set stride and tlb_level in flush_*_tlb_range */
 #define flush_pmd_tlb_range(vma, addr, end)	\
-	__flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2)
+	__flush_tlb_range(vma, addr, end, PMD_SIZE, 2, TLBF_NONE)
 #define flush_pud_tlb_range(vma, addr, end)	\
-	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
+	__flush_tlb_range(vma, addr, end, PUD_SIZE, 1, TLBF_NONE)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*

arch/arm64/include/asm/tlb.h

@@ -53,7 +53,7 @@ static inline int tlb_get_level(struct mmu_gather *tlb)
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
-	bool last_level = !tlb->freed_tables;
+	tlbf_t flags = tlb->freed_tables ? TLBF_NONE : TLBF_NOWALKCACHE;
 	unsigned long stride = tlb_get_unmap_size(tlb);
 	int tlb_level = tlb_get_level(tlb);
 
@@ -63,13 +63,13 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 	 * reallocate our ASID without invalidating the entire TLB.
 	 */
 	if (tlb->fullmm) {
-		if (!last_level)
+		if (tlb->freed_tables)
 			flush_tlb_mm(tlb->mm);
 		return;
 	}
 
 	__flush_tlb_range(&vma, tlb->start, tlb->end, stride,
-			  last_level, tlb_level);
+			  tlb_level, flags);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,

arch/arm64/include/asm/tlbflush.h

@@ -286,16 +286,16 @@ static inline void __tlbi_sync_s1ish_hyp(void)
  *		CPUs, ensuring that any walk-cache entries associated with the
  *		translation are also invalidated.
  *
- *	__flush_tlb_range(vma, start, end, stride, last_level, tlb_level)
+ *	__flush_tlb_range(vma, start, end, stride, tlb_level, flags)
  *		Invalidate the virtual-address range '[start, end)' on all
  *		CPUs for the user address space corresponding to 'vma->mm'.
  *		The invalidation operations are issued at a granularity
- *		determined by 'stride' and only affect any walk-cache entries
- *		if 'last_level' is equal to false. tlb_level is the level at
+ *		determined by 'stride'. tlb_level is the level at
  *		which the invalidation must take place. If the level is wrong,
  *		no invalidation may take place. In the case where the level
  *		cannot be easily determined, the value TLBI_TTL_UNKNOWN will
- *		perform a non-hinted invalidation.
+ *		perform a non-hinted invalidation. flags may be TLBF_NONE (0) or
+ *		TLBF_NOWALKCACHE (elide eviction of walk cache entries).
  *
  *	local_flush_tlb_page(vma, addr)
  *		Local variant of flush_tlb_page().  Stale TLB entries may
@@ -544,10 +544,18 @@ static inline bool __flush_tlb_range_limit_excess(unsigned long pages,
 	return pages >= (MAX_DVM_OPS * stride) >> PAGE_SHIFT;
 }
 
+typedef unsigned __bitwise tlbf_t;
+
+/* No special behaviour. */
+#define TLBF_NONE		((__force tlbf_t)0)
+
+/* Invalidate tlb entries only, leaving the page table walk cache intact. */
+#define TLBF_NOWALKCACHE	((__force tlbf_t)BIT(0))
+
 static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
 				     unsigned long start, unsigned long end,
-				     unsigned long stride, bool last_level,
-				     int tlb_level)
+				     unsigned long stride, int tlb_level,
+				     tlbf_t flags)
 {
 	unsigned long asid, pages;
 
@@ -563,7 +571,7 @@ static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
 	dsb(ishst);
 	asid = ASID(mm);
 
-	if (last_level)
+	if (flags & TLBF_NOWALKCACHE)
 		__flush_s1_tlb_range_op(vale1is, start, pages, stride,
 				     asid, tlb_level);
 	else
@@ -575,11 +583,11 @@ static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
-				     unsigned long stride, bool last_level,
-				     int tlb_level)
+				     unsigned long stride, int tlb_level,
+				     tlbf_t flags)
 {
 	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
-				 last_level, tlb_level);
+				 tlb_level, flags);
 	__tlbi_sync_s1ish();
 }
 
@@ -607,7 +615,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	 * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough
 	 * information here.
 	 */
-	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, TLBI_TTL_UNKNOWN, TLBF_NONE);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
@@ -648,7 +656,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
 		struct mm_struct *mm, unsigned long start, unsigned long end)
 {
-	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
+	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, 3, TLBF_NOWALKCACHE);
 }
 
 static inline bool __pte_flags_need_flush(ptdesc_t oldval, ptdesc_t newval)

arch/arm64/mm/contpte.c

@@ -225,7 +225,8 @@ static void contpte_convert(struct mm_struct *mm, unsigned long addr,
 	 */
 
 	if (!system_supports_bbml2_noabort())
-		__flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3);
+		__flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, 3,
+				  TLBF_NOWALKCACHE);
 
 	__set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
 }
@@ -552,7 +553,7 @@ int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
 		 * eliding the trailing DSB applies here.
 		 */
 		__flush_tlb_range_nosync(vma->vm_mm, addr, end,
-					 PAGE_SIZE, true, 3);
+					 PAGE_SIZE, 3, TLBF_NOWALKCACHE);
 	}
 
 	return young;

arch/arm64/mm/hugetlbpage.c

@@ -181,7 +181,7 @@ static pte_t get_clear_contig_flush(struct mm_struct *mm,
 	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
 	unsigned long end = addr + (pgsize * ncontig);
 
-	__flush_hugetlb_tlb_range(&vma, addr, end, pgsize, true);
+	__flush_hugetlb_tlb_range(&vma, addr, end, pgsize, TLBF_NOWALKCACHE);
 	return orig_pte;
 }
 
@@ -209,7 +209,7 @@ static void clear_flush(struct mm_struct *mm,
 	if (mm == &init_mm)
 		flush_tlb_kernel_range(saddr, addr);
 	else
-		__flush_hugetlb_tlb_range(&vma, saddr, addr, pgsize, true);
+		__flush_hugetlb_tlb_range(&vma, saddr, addr, pgsize, TLBF_NOWALKCACHE);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,

arch/arm64/mm/mmu.c

@@ -2149,7 +2149,7 @@ pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
 		 */
 		if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte))
 			__flush_tlb_range(vma, addr, nr * PAGE_SIZE,
-					  PAGE_SIZE, true, 3);
+					  PAGE_SIZE, 3, TLBF_NOWALKCACHE);
 	}
 
 	return pte;