armv8: move low-level assembly functions into function-sections

TPL builds today don't need to call into firmware or set up the MMU
(if this changes, it should be controlled through a config option
whether to include this or not), but include the needed support code
for this anyway.  By moving these unused low-level functions into
seperate function-sections, the linker can garbage-collect the unused
sections.

Note that (if DM support is enabled), there will be a call to the
cache-flushing code from alloc_priv(...) in drivers/core/device.c.
This then add 52 bytes of binary size (an increase from 20589 to 20641
bytes) compared to completely removing this code.

Even for a feature-rich TPL (including DM support as for the RK3368),
this equates to a size difference of significantly more than 10% in
TPL binary size.

Signed-off-by: Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
Reviewed-by: Simon Glass <sjg@chromium.org>
diff --git a/arch/arm/cpu/armv8/cache.S b/arch/arm/cpu/armv8/cache.S
index 7cba308..ea845d1 100644
--- a/arch/arm/cpu/armv8/cache.S
+++ b/arch/arm/cpu/armv8/cache.S
@@ -22,6 +22,7 @@
  * x1: 0 clean & invalidate, 1 invalidate only
  * x2~x9: clobbered
  */
+.pushsection .text.__asm_dcache_level, "ax"
 ENTRY(__asm_dcache_level)
 	lsl	x12, x0, #1
 	msr	csselr_el1, x12		/* select cache level */
@@ -58,6 +59,7 @@
 
 	ret
 ENDPROC(__asm_dcache_level)
+.popsection
 
 /*
  * void __asm_flush_dcache_all(int invalidate_only)
@@ -66,6 +68,7 @@
  *
  * flush or invalidate all data cache by SET/WAY.
  */
+.pushsection .text.__asm_dcache_all, "ax"
 ENTRY(__asm_dcache_all)
 	mov	x1, x0
 	dsb	sy
@@ -102,16 +105,21 @@
 finished:
 	ret
 ENDPROC(__asm_dcache_all)
+.popsection
 
+.pushsection .text.__asm_flush_dcache_all, "ax"
 ENTRY(__asm_flush_dcache_all)
 	mov	x0, #0
 	b	__asm_dcache_all
 ENDPROC(__asm_flush_dcache_all)
+.popsection
 
+.pushsection .text.__asm_invalidate_dcache_all, "ax"
 ENTRY(__asm_invalidate_dcache_all)
 	mov	x0, #0x1
 	b	__asm_dcache_all
 ENDPROC(__asm_invalidate_dcache_all)
+.popsection
 
 /*
  * void __asm_flush_dcache_range(start, end)
@@ -121,6 +129,7 @@
  * x0: start address
  * x1: end address
  */
+.pushsection .text.__asm_flush_dcache_range, "ax"
 ENTRY(__asm_flush_dcache_range)
 	mrs	x3, ctr_el0
 	lsr	x3, x3, #16
@@ -138,6 +147,7 @@
 	dsb	sy
 	ret
 ENDPROC(__asm_flush_dcache_range)
+.popsection
 /*
  * void __asm_invalidate_dcache_range(start, end)
  *
@@ -146,6 +156,7 @@
  * x0: start address
  * x1: end address
  */
+.pushsection .text.__asm_invalidate_dcache_range, "ax"
 ENTRY(__asm_invalidate_dcache_range)
 	mrs	x3, ctr_el0
 	ubfm	x3, x3, #16, #19
@@ -162,41 +173,51 @@
 	dsb	sy
 	ret
 ENDPROC(__asm_invalidate_dcache_range)
+.popsection
 
 /*
  * void __asm_invalidate_icache_all(void)
  *
  * invalidate all tlb entries.
  */
+.pushsection .text.__asm_invalidate_icache_all, "ax"
 ENTRY(__asm_invalidate_icache_all)
 	ic	ialluis
 	isb	sy
 	ret
 ENDPROC(__asm_invalidate_icache_all)
+.popsection
 
+.pushsection .text.__asm_invalidate_l3_dcache, "ax"
 ENTRY(__asm_invalidate_l3_dcache)
 	mov	x0, #0			/* return status as success */
 	ret
 ENDPROC(__asm_invalidate_l3_dcache)
 	.weak	__asm_invalidate_l3_dcache
+.popsection
 
+.pushsection .text.__asm_flush_l3_dcache, "ax"
 ENTRY(__asm_flush_l3_dcache)
 	mov	x0, #0			/* return status as success */
 	ret
 ENDPROC(__asm_flush_l3_dcache)
 	.weak	__asm_flush_l3_dcache
+.popsection
 
+.pushsection .text.__asm_invalidate_l3_icache, "ax"
 ENTRY(__asm_invalidate_l3_icache)
 	mov	x0, #0			/* return status as success */
 	ret
 ENDPROC(__asm_invalidate_l3_icache)
 	.weak	__asm_invalidate_l3_icache
+.popsection
 
 /*
  * void __asm_switch_ttbr(ulong new_ttbr)
  *
  * Safely switches to a new page table.
  */
+.pushsection .text.__asm_switch_ttbr, "ax"
 ENTRY(__asm_switch_ttbr)
 	/* x2 = SCTLR (alive throghout the function) */
 	switch_el x4, 3f, 2f, 1f
@@ -244,3 +265,4 @@
 
 	ret	x3
 ENDPROC(__asm_switch_ttbr)
+.popsection
diff --git a/arch/arm/cpu/armv8/tlb.S b/arch/arm/cpu/armv8/tlb.S
index 945445b..6743111 100644
--- a/arch/arm/cpu/armv8/tlb.S
+++ b/arch/arm/cpu/armv8/tlb.S
@@ -14,7 +14,8 @@
  * void __asm_invalidate_tlb_all(void)
  *
  * invalidate all tlb entries.
- */
+*/
+.pushsection .text.__asm_invalidate_tlb_all, "ax"
 ENTRY(__asm_invalidate_tlb_all)
 	switch_el x9, 3f, 2f, 1f
 3:	tlbi	alle3
@@ -31,3 +32,4 @@
 0:
 	ret
 ENDPROC(__asm_invalidate_tlb_all)
+.popsection
diff --git a/arch/arm/cpu/armv8/transition.S b/arch/arm/cpu/armv8/transition.S
index ca07465..7aa6935 100644
--- a/arch/arm/cpu/armv8/transition.S
+++ b/arch/arm/cpu/armv8/transition.S
@@ -10,6 +10,7 @@
 #include <linux/linkage.h>
 #include <asm/macro.h>
 
+.pushsection .text.armv8_switch_to_el2, "ax"
 ENTRY(armv8_switch_to_el2)
 	switch_el x6, 1f, 0f, 0f
 0:
@@ -30,7 +31,9 @@
 	br x4
 1:	armv8_switch_to_el2_m x4, x5, x6
 ENDPROC(armv8_switch_to_el2)
+.popsection
 
+.pushsection .text.armv8_switch_to_el1, "ax"
 ENTRY(armv8_switch_to_el1)
 	switch_el x6, 0f, 1f, 0f
 0:
@@ -40,7 +43,10 @@
 	br x4
 1:	armv8_switch_to_el1_m x4, x5, x6
 ENDPROC(armv8_switch_to_el1)
+.popsection
 
+.pushsection .text.armv8_el2_to_aarch32, "ax"
 WEAK(armv8_el2_to_aarch32)
 	ret
 ENDPROC(armv8_el2_to_aarch32)
+.popsection