arm64: KVM: Add invalidate_icache_range helper

We currently tightly couple dcache clean with icache invalidation,
but KVM could do without the initial flush to PoU, as we've
already flushed things to PoC.

Let's introduce invalidate_icache_range which is limited to
invalidating the icache from the linear mapping (and thus
has none of the userspace fault handling complexity), and
wire it in KVM instead of flush_icache_range.
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

arch/arm64/include/asm/assembler.h

@@ -387,6 +387,27 @@ alternative_endif
 	dsb	\domain
 	.endm
 
+/*
+ * Macro to perform an instruction cache maintenance for the interval
+ * [start, end)
+ *
+ * 	start, end:	virtual addresses describing the region
+ *	label:		A label to branch to on user fault.
+ * 	Corrupts:	tmp1, tmp2
+ */
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+	icache_line_size \tmp1, \tmp2
+	sub	\tmp2, \tmp1, #1
+	bic	\tmp2, \start, \tmp2
+9997:
+USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
+	add	\tmp2, \tmp2, \tmp1
+	cmp	\tmp2, \end
+	b.lo	9997b
+	dsb	ish
+	isb
+	.endm
+
 /*
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */

arch/arm64/include/asm/cacheflush.h

@@ -52,6 +52,12 @@
  *		- start  - virtual start address
  *		- end    - virtual end address
  *
+ *	invalidate_icache_range(start, end)
+ *
+ *		Invalidate the I-cache in the region described by start, end.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
  *	__flush_cache_user_range(start, end)
  *
  *		Ensure coherency between the I-cache and the D-cache in the
@@ -66,6 +72,7 @@
  *		- size   - region size
  */
 extern void flush_icache_range(unsigned long start, unsigned long end);
+extern int  invalidate_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
 extern void __clean_dcache_area_poc(void *addr, size_t len);

arch/arm64/include/asm/kvm_mmu.h

@@ -250,7 +250,7 @@ static inline void __invalidate_icache_guest_page(struct kvm_vcpu *vcpu,
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
 		void *va = page_address(pfn_to_page(pfn));
 
-		flush_icache_range((unsigned long)va,
+		invalidate_icache_range((unsigned long)va,
 					(unsigned long)va + size);
 	}
 }

arch/arm64/mm/cache.S

@@ -60,16 +60,7 @@ user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	b.lo	1b
 	dsb	ish
 
-	icache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x4, x0, x3
-1:
-USER(9f, ic	ivau, x4	)		// invalidate I line PoU
-	add	x4, x4, x2
-	cmp	x4, x1
-	b.lo	1b
-	dsb	ish
-	isb
+	invalidate_icache_by_line x0, x1, x2, x3, 9f
 	mov	x0, #0
 1:
 	uaccess_ttbr0_disable x1
@@ -80,6 +71,27 @@ USER(9f, ic	ivau, x4	)		// invalidate I line PoU
 ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 
+/*
+ *	invalidate_icache_range(start,end)
+ *
+ *	Ensure that the I cache is invalid within specified region.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(invalidate_icache_range)
+	uaccess_ttbr0_enable x2, x3
+
+	invalidate_icache_by_line x0, x1, x2, x3, 2f
+	mov	x0, xzr
+1:
+	uaccess_ttbr0_disable x1
+	ret
+2:
+	mov	x0, #-EFAULT
+	b	1b
+ENDPROC(invalidate_icache_range)
+
 /*
  *	__flush_dcache_area(kaddr, size)
  *