arm64: entry: Make the trampoline cleanup optional

Subsequent patches will add additional sets of vectors that use
the same tricks as the kpti vectors to reach the full-fat vectors.
The full-fat vectors contain some cleanup for kpti that is patched
in by alternatives when kpti is in use. Once there are additional
vectors, the cleanup will be needed in more cases.

But on big/little systems, the cleanup would be harmful if no
trampoline vector were in use. Instead of forcing CPUs that don't
need a trampoline vector to use one, make the trampoline cleanup
optional.

Entry at the top of the vectors will skip the cleanup. The trampoline
vectors can then skip the first instruction, triggering the cleanup
to run.
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>

arch/arm64/kernel/entry.S

@@ -40,14 +40,18 @@
 .Lventry_start\@:
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
-alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+	/*
+	 * This must be the first instruction of the EL0 vector entries. It is
+	 * skipped by the trampoline vectors, to trigger the cleanup.
+	 */
+	b	.Lskip_tramp_vectors_cleanup\@
 	.if	\regsize == 64
 	mrs	x30, tpidrro_el0
 	msr	tpidrro_el0, xzr
 	.else
 	mov	x30, xzr
 	.endif
-alternative_else_nop_endif
+.Lskip_tramp_vectors_cleanup\@:
 	.endif
 #endif
 
@@ -661,7 +665,7 @@ alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
 alternative_else_nop_endif
 	msr	vbar_el1, x30
-	add	x30, x30, #(1b - tramp_vectors)
+	add	x30, x30, #(1b - tramp_vectors + 4)
 	isb
 	ret
 .org 1b + 128	// Did we overflow the ventry slot?