Split __flush_tlb_range() into __flush_tlb_range_nosync() +
__flush_tlb_range(), in the same way as the existing flush_tlb_page()
arrangement. This allows calling __flush_tlb_range_nosync() to elide the
trailing DSB. Forthcoming "contpte" code will take advantage of this
when clearing the young bit from a contiguous range of ptes.
Ordering between dsb and mmu_notifier_arch_invalidate_secondary_tlbs()
has changed, but now aligns with the ordering of __flush_tlb_page(). It
has been discussed that __flush_tlb_page() may be wrong though.
Regardless, both will be resolved separately if needed.
Reviewed-by: David Hildenbrand <david@redhat.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
arch/arm64/include/asm/tlbflush.h | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
@@ -422,7 +422,7 @@ do { \
#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled());
-static inline void __flush_tlb_range(struct vm_area_struct *vma,
+static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long stride, bool last_level,
int tlb_level)
@@ -456,10 +456,19 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
__flush_tlb_range_op(vae1is, start, pages, stride, asid,
tlb_level, true, lpa2_is_enabled());
- dsb(ish);
mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
}
+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)
+{
+ __flush_tlb_range_nosync(vma, start, end, stride,
+ last_level, tlb_level);
+ dsb(ish);
+}
+
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{