arm64: tlb: Avoid synchronous TLBIs when freeing page tables

By selecting HAVE_RCU_TABLE_INVALIDATE, we can rely on tlb_flush() being
called if we fail to batch table pages for freeing. This in turn allows
us to postpone walk-cache invalidation until tlb_finish_mmu(), which
avoids lots of unnecessary DSBs and means we can shoot down the ASID if
the range is large enough.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/Kconfig

@@ -143,6 +143,7 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
+	select HAVE_RCU_TABLE_INVALIDATE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS

arch/arm64/include/asm/tlb.h

@@ -54,7 +54,6 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
-	__flush_tlb_pgtable(tlb->mm, addr);
 	pgtable_page_dtor(pte);
 	tlb_remove_table(tlb, pte);
 }
@@ -63,7 +62,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_table(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -72,7 +70,6 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_table(tlb, virt_to_page(pudp));
 }
 #endif

arch/arm64/include/asm/tlbflush.h

@@ -215,17 +215,6 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
  * Used to invalidate the TLB (walk caches) corresponding to intermediate page
  * table levels (pgd/pud/pmd).
  */
-static inline void __flush_tlb_pgtable(struct mm_struct *mm,
-				       unsigned long uaddr)
-{
-	unsigned long addr = __TLBI_VADDR(uaddr, ASID(mm));
-
-	dsb(ishst);
-	__tlbi(vae1is, addr);
-	__tlbi_user(vae1is, addr);
-	dsb(ish);
-}
-
 static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 {
 	unsigned long addr = __TLBI_VADDR(kaddr, 0);