arm64: smp: unify task and sp setup

Once we enable the MMU, we have to initialize:

* SP_EL0 to point at the active task
* SP to point at the active task's stack
* SCS_SP to point at the active task's shadow stack

For all tasks (including init_task), this information can be derived
from the task's task_struct.

Let's unify __primary_switched and __secondary_switched to consistently
acquire this information from the relevant task_struct. At the same
time, let's fold this together with initializing a task's final frame.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Suzuki Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20210520115031.18509-6-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: mrutland-arm

arch/arm64/kernel/head.S

@@ -395,15 +395,24 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 SYM_FUNC_END(__create_page_tables)
 
 	/*
+	 * Initialize CPU registers with task-specific and cpu-specific context.
+	 *
 	 * Create a final frame record at task_pt_regs(current)->stackframe, so
 	 * that the unwinder can identify the final frame record of any task by
 	 * its location in the task stack. We reserve the entire pt_regs space
 	 * for consistency with user tasks and kthreads.
 	 */
-	.macro setup_final_frame
+	.macro	init_cpu_task tsk, tmp
+	msr	sp_el0, \tsk
+
+	ldr	\tmp, [\tsk, #TSK_STACK]
+	add	sp, \tmp, #THREAD_SIZE
 	sub	sp, sp, #PT_REGS_SIZE
+
 	stp	xzr, xzr, [sp, #S_STACKFRAME]
 	add	x29, sp, #S_STACKFRAME
+
+	scs_load \tsk, \tmp
 	.endm
 
 /*
@@ -412,22 +421,16 @@ SYM_FUNC_END(__create_page_tables)
  *   x0 = __PHYS_OFFSET
  */
 SYM_FUNC_START_LOCAL(__primary_switched)
-	adrp	x4, init_thread_union
-	add	sp, x4, #THREAD_SIZE
-	adr_l	x5, init_task
-	msr	sp_el0, x5			// Save thread_info
+	adr_l	x4, init_task
+	init_cpu_task x4, x5
 
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
 	isb
 
-	stp	xzr, x30, [sp, #-16]!
+	stp	x29, x30, [sp, #-16]!
 	mov	x29, sp
 
-#ifdef CONFIG_SHADOW_CALL_STACK
-	adr_l	scs_sp, init_shadow_call_stack	// Set shadow call stack
-#endif
-
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 
 	ldr_l	x4, kimage_vaddr		// Save the offset between
@@ -459,8 +462,7 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 0:
 #endif
 	bl	switch_to_vhe			// Prefer VHE if possible
-	add	sp, sp, #16
-	setup_final_frame
+	ldp	x29, x30, [sp], #16
 	bl	start_kernel
 	ASM_BUG()
 SYM_FUNC_END(__primary_switched)
@@ -648,12 +650,7 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
 
-	ldr	x1, [x2, #TSK_STACK]
-	add	sp, x1, #THREAD_SIZE
-
-	msr	sp_el0, x2
-	scs_load x2, x3
-	setup_final_frame
+	init_cpu_task x2, x1
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 	ptrauth_keys_init_cpu x2, x3, x4, x5