arm64: Implement stack trace termination record

Reliable stacktracing requires that we identify when a stacktrace is
terminated early. We can do this by ensuring all tasks have a final
frame record at a known location on their task stack, and checking
that this is the final frame record in the chain.

We'd like to use task_pt_regs(task)->stackframe as the final frame
record, as this is already setup upon exception entry from EL0. For
kernel tasks we need to consistently reserve the pt_regs and point x29
at this, which we can do with small changes to __primary_switched,
__secondary_switched, and copy_process().

Since the final frame record must be at a specific location, we must
create the final frame record in __primary_switched and
__secondary_switched rather than leaving this to start_kernel and
secondary_start_kernel. Thus, __primary_switched and
__secondary_switched will now show up in stacktraces for the idle tasks.

Since the final frame record is now identified by its location rather
than by its contents, we identify it at the start of unwind_frame(),
before we read any values from it.

External debuggers may terminate the stack trace when FP == 0. In the
pt_regs->stackframe, the PC is 0 as well. So, stack traces taken in the
debugger may print an extra record 0x0 at the end. While this is not
pretty, this does not do any harm. This is a small price to pay for
having reliable stack trace termination in the kernel. That said, gdb
does not show the extra record probably because it uses DWARF and not
frame pointers for stack traces.

Signed-off-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
[Mark: rebase, use ASM_BUG(), update comments, update commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20210510110026.18061-1-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 19 insertions, 6 deletions

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 96873dfa67fd..cc2d45d54838 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -16,6 +16,7 @@
 #include <asm/asm_pointer_auth.h>
 #include <asm/assembler.h>
 #include <asm/boot.h>
+#include <asm/bug.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
@@ -393,6 +394,18 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	ret	x28
 SYM_FUNC_END(__create_page_tables)
 
+	/*
+	 * 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
+	sub	sp, sp, #PT_REGS_SIZE
+	stp	xzr, xzr, [sp, #S_STACKFRAME]
+	add	x29, sp, #S_STACKFRAME
+	.endm
+
 /*
  * The following fragment of code is executed with the MMU enabled.
  *
@@ -447,9 +460,9 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 #endif
 	bl	switch_to_vhe			// Prefer VHE if possible
 	add	sp, sp, #16
-	mov	x29, #0
-	mov	x30, #0
-	b	start_kernel
+	setup_final_frame
+	bl	start_kernel
+	ASM_BUG()
 SYM_FUNC_END(__primary_switched)
 
 	.pushsection ".rodata", "a"
@@ -639,14 +652,14 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
 	scs_load x2, x3
-	mov	x29, #0
-	mov	x30, #0
+	setup_final_frame
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 	ptrauth_keys_init_cpu x2, x3, x4, x5
 #endif
 
-	b	secondary_start_kernel
+	bl	secondary_start_kernel
+	ASM_BUG()
 SYM_FUNC_END(__secondary_switched)
 
 SYM_FUNC_START_LOCAL(__secondary_too_slow)