arm64: flush: use local TLB and I-cache invalidation

There are a number of places where a single CPU is running with a
private page-table and we need to perform maintenance on the TLB and
I-cache in order to ensure correctness, but do not require the operation
to be broadcast to other CPUs.

This patch adds local variants of tlb_flush_all and __flush_icache_all
to support these use-cases and updates the callers respectively.
__local_flush_icache_all also implies an isb, since it is intended to be
used synchronously.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: David Daney <david.daney@cavium.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/cacheflush.h

@@ -115,6 +115,13 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
+static inline void __local_flush_icache_all(void)
+{
+	asm("ic iallu");
+	dsb(nsh);
+	isb();
+}
+
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");

arch/arm64/include/asm/tlbflush.h

@@ -63,6 +63,14 @@
  *		only require the D-TLB to be invalidated.
  *		- kaddr - Kernel virtual memory address
  */
+static inline void local_flush_tlb_all(void)
+{
+	dsb(nshst);
+	asm("tlbi	vmalle1");
+	dsb(nsh);
+	isb();
+}
+
 static inline void flush_tlb_all(void)
 {
 	dsb(ishst);

arch/arm64/kernel/efi.c

@@ -344,9 +344,9 @@ static void efi_set_pgd(struct mm_struct *mm)
 	else
 		cpu_switch_mm(mm->pgd, mm);
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 	if (icache_is_aivivt())
-		__flush_icache_all();
+		__local_flush_icache_all();
 }
 
 void efi_virtmap_load(void)

arch/arm64/kernel/smp.c

@@ -152,7 +152,7 @@ asmlinkage void secondary_start_kernel(void)
 	 * point to zero page to avoid speculatively fetching new entries.
 	 */
 	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
+	local_flush_tlb_all();
 	cpu_set_default_tcr_t0sz();
 
 	preempt_disable();

arch/arm64/kernel/suspend.c

@@ -90,7 +90,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		else
 			cpu_switch_mm(mm->pgd, mm);
 
-		flush_tlb_all();
+		local_flush_tlb_all();
 
 		/*
 		 * Restore per-cpu offset before any kernel

arch/arm64/mm/context.c

@@ -48,9 +48,9 @@ static void flush_context(void)
 {
 	/* set the reserved TTBR0 before flushing the TLB */
 	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
+	local_flush_tlb_all();
 	if (icache_is_aivivt())
-		__flush_icache_all();
+		__local_flush_icache_all();
 }
 
 static void set_mm_context(struct mm_struct *mm, unsigned int asid)

arch/arm64/mm/mmu.c

@@ -456,7 +456,7 @@ void __init paging_init(void)
 	 * point to zero page to avoid speculatively fetching new entries.
 	 */
 	cpu_set_reserved_ttbr0();
-	flush_tlb_all();
+	local_flush_tlb_all();
 	cpu_set_default_tcr_t0sz();
 }