[PATCH v2 2/2] arm64: entry: Simplify tramp_alias macro and tramp_exit routine

[Ard Biesheuvel]

The tramp_alias macro constructs the virtual alias of a symbol in the
trampoline text mapping, based on its kernel text address, and does so
in a way that is more convoluted than necessary. So let's simplify that.

Also, now that the address of the vector table is kept in a per-CPU
variable, there is no need to defer the load and the assignment of
VBAR_EL1 to tramp_exit(). This means we can use a PC-relative reference
to the per-CPU variable instead of storing its absolute address in a
global variable in the trampoline rodata.

And given that tramp_alias no longer needs a temp register, this means
we can restore X30 earlier as well, and only leave X29 for tramp_exit()
to restore.

While at it, give some related symbols static linkage, considering that
they are only referenced from the object file that defines them.

Signed-off-by: Ard Biesheuvel <ardb at kernel.org>
---
 arch/arm64/kernel/entry.S | 47 +++++++++-----------
 1 file changed, 20 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 16fbd0d9790dd436..a40e5e50fa55232e 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -101,12 +101,11 @@
 .org .Lventry_start\@ + 128	// Did we overflow the ventry slot?
 	.endm
 
-	.macro tramp_alias, dst, sym, tmp
-	mov_q	\dst, TRAMP_VALIAS
-	adr_l	\tmp, \sym
-	add	\dst, \dst, \tmp
-	adr_l	\tmp, .entry.tramp.text
-	sub	\dst, \dst, \tmp
+	.macro	tramp_alias, dst, sym
+	.set	.Lalias\@, TRAMP_VALIAS + \sym - .entry.tramp.text
+	movz	\dst, :abs_g2_s:.Lalias\@
+	movk	\dst, :abs_g1_nc:.Lalias\@
+	movk	\dst, :abs_g0_nc:.Lalias\@
 	.endm
 
 	/*
@@ -436,8 +435,13 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
 alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	msr	far_el1, x29
-	tramp_alias	x30, tramp_exit_native, x29
-	br	x30
+
+	ldr_this_cpu	x30, this_cpu_vector, x29
+	tramp_alias	x29, tramp_exit
+	msr		vbar_el1, x30		// install vector table
+	ldr		lr, [sp, #S_LR]		// restore x30
+	add		sp, sp, #PT_REGS_SIZE	// restore sp
+	br		x29
 #endif
 	.else
 	ldr	lr, [sp, #S_LR]
@@ -728,20 +732,6 @@ alternative_else_nop_endif
 .org 1b + 128	// Did we overflow the ventry slot?
 	.endm
 
-	.macro tramp_exit, regsize = 64
-	tramp_data_read_var	x30, this_cpu_vector
-	get_this_cpu_offset x29
-	ldr	x30, [x30, x29]
-
-	msr	vbar_el1, x30
-	ldr	lr, [sp, #S_LR]
-	tramp_unmap_kernel	x29
-	mrs	x29, far_el1
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
-	eret
-	sb
-	.endm
-
 	.macro	generate_tramp_vector,	kpti, bhb
 .Lvector_start\@:
 	.space	0x400
@@ -762,7 +752,7 @@ alternative_else_nop_endif
  */
 	.pushsection ".entry.tramp.text", "ax"
 	.align	11
-SYM_CODE_START_NOALIGN(tramp_vectors)
+SYM_CODE_START_LOCAL_NOALIGN(tramp_vectors)
 #ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
 	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_LOOP
 	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_FW
@@ -771,9 +761,12 @@ SYM_CODE_START_NOALIGN(tramp_vectors)
 	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_NONE
 SYM_CODE_END(tramp_vectors)
 
-SYM_CODE_START(tramp_exit_native)
-	tramp_exit
-SYM_CODE_END(tramp_exit_native)
+SYM_CODE_START_LOCAL(tramp_exit)
+	tramp_unmap_kernel	x29
+	mrs		x29, far_el1		// restore x29
+	eret
+	sb
+SYM_CODE_END(tramp_exit)
 	.popsection				// .entry.tramp.text
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
@@ -1067,7 +1060,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
 alternative_else_nop_endif
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3
+	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline
 	br	x5
 #endif
 SYM_CODE_END(__sdei_asm_handler)
-- 
2.39.2