ARMv8: Allow dynamic early stack pointer

U-Boot typically uses a hard-coded value for the stack pointer before
relocation. Implement option SYS_INIT_SP_BSS_OFFSET to instead calculate
the initial SP at run-time. This is useful to avoid hard-coding addresses
into U-Boot, so that can be loaded and executed at arbitrary addresses and
thus avoid using arbitrary addresses at runtime. This option's value is
the offset added to &_bss_start in order to calculate the stack pointer.
This offset should be large enough so that the early malloc region, global
data (gd), and early stack usage do not overlap any appended DTB.

Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Tom Warren <twarren@nvidia.com>

arch/arm/Kconfig

@@ -19,6 +19,19 @@ config POSITION_INDEPENDENT
 	  from almost any address. This logic relies on the relocation
 	  information that is embedded into the binary to support U-Boot
 	  relocating itself to the top-of-RAM later during execution.
+
+config SYS_INIT_SP_BSS_OFFSET
+	int
+	help
+	  U-Boot typically uses a hard-coded value for the stack pointer
+	  before relocation. Define this option to instead calculate the
+	  initial SP at run-time. This is useful to avoid hard-coding addresses
+	  into U-Boot, so that can be loaded and executed at arbitrary
+	  addresses and thus avoid using arbitrary addresses at runtime. This
+	  option's value is the offset added to &_bss_start in order to
+	  calculate the stack pointer. This offset should be large enough so
+	  that the early malloc region, global data (gd), and early stack usage
+	  do not overlap any appended DTB.
 endif
 
 config STATIC_RELA

arch/arm/lib/crt0_64.S

@@ -73,6 +73,9 @@ ENTRY(_main)
 	ldr	x0, =(CONFIG_TPL_STACK)
 #elif defined(CONFIG_SPL_BUILD) && defined(CONFIG_SPL_STACK)
 	ldr	x0, =(CONFIG_SPL_STACK)
+#elif defined(CONFIG_SYS_INIT_SP_BSS_OFFSET)
+	adr	x0, __bss_start
+	add	x0, x0, #CONFIG_SYS_INIT_SP_BSS_OFFSET
 #else
 	ldr	x0, =(CONFIG_SYS_INIT_SP_ADDR)
 #endif