arm64: mte: optimize GCR_EL1 modification on kernel entry/exit

Accessing GCR_EL1 and issuing an ISB can be expensive on some
microarchitectures. Although we must write to GCR_EL1, we can
restructure the code to avoid reading from it because the new value
can be derived entirely from the exclusion mask, which is already in
a GPR. Do so.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Link: https://linux-review.googlesource.com/id/I560a190a74176ca4cc5191dad08f77f6b1577c75
Link: https://lore.kernel.org/r/20210714013638.3995315-1-pcc@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/entry.S

@@ -168,15 +168,11 @@ alternative_else_nop_endif
 #endif
 	.endm
 
-	.macro mte_set_gcr, tmp, tmp2
+	.macro mte_set_gcr, mte_ctrl, tmp
 #ifdef CONFIG_ARM64_MTE
-	/*
+	ubfx	\tmp, \mte_ctrl, #MTE_CTRL_GCR_USER_EXCL_SHIFT, #16
-	 * Calculate and set the exclude mask preserving
+	orr	\tmp, \tmp, #SYS_GCR_EL1_RRND
-	 * the RRND (bit[16]) setting.
+	msr_s	SYS_GCR_EL1, \tmp
-	 */
-	mrs_s	\tmp2, SYS_GCR_EL1
-	bfxil	\tmp2, \tmp, #MTE_CTRL_GCR_USER_EXCL_SHIFT, #16
-	msr_s	SYS_GCR_EL1, \tmp2
 #endif
 	.endm