arm64: entry: Make the trampoline cleanup optional

commit d739da1694a0eaef0358a42b76904b611539b77b upstream.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 0414b0494dd37e0bfc9c7aaf5e04c420dec3b646..160a3131a190d7c63b5749af0a7217d3c2e6dd72 100644 (file)
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -76,16 +76,20 @@
        .align 7
 .Lventry_start\@:
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-alternative_if ARM64_UNMAP_KERNEL_AT_EL0
        .if     \el == 0
+       /*
+        * 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
+.Lskip_tramp_vectors_cleanup\@:
        .endif
-alternative_else_nop_endif
 #endif
 
        sub     sp, sp, #S_FRAME_SIZE
@@ -934,7 +938,7 @@ __ni_sys_trace:
 #endif
        prfm    plil1strm, [x30, #(1b - tramp_vectors)]
        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?