[AArch64][SME] Add BTI and No Exec Stack markers to sme-abi.S (#84895)

Adding BTI landing pads compiler-rt is built with -mbranch-protectoin.
Tabulators are changed to 2 spaces for consistency.

compiler-rt/lib/builtins/aarch64/sme-abi.S

@@ -26,32 +26,34 @@
 // abort(). Note that there is no need to preserve any state before the call,
 // because the function does not return.
 DEFINE_COMPILERRT_PRIVATE_FUNCTION(do_abort)
-.cfi_startproc
-	.variant_pcs SYMBOL_NAME(do_abort)
-	stp	x29, x30, [sp, #-32]!
+  .cfi_startproc
+  .variant_pcs SYMBOL_NAME(do_abort)
+  BTI_C
+  stp  x29, x30, [sp, #-32]!
   cntd x0
   // Store VG to a stack location that we describe with .cfi_offset
   str x0, [sp, #16]
   .cfi_def_cfa_offset 32
   .cfi_offset w30, -24
   .cfi_offset w29, -32
   .cfi_offset 46, -16
-	bl	__arm_sme_state
-	tbz	x0, #0, 2f
+  bl  __arm_sme_state
+  tbz  x0, #0, 2f
 1:
-	smstop sm
+  smstop sm
 2:
   // We can't make this into a tail-call because the unwinder would
   // need to restore the value of VG.
-	bl	SYMBOL_NAME(abort)
-.cfi_endproc
+  bl  SYMBOL_NAME(abort)
+  .cfi_endproc
 END_COMPILERRT_FUNCTION(do_abort)
 
 // __arm_sme_state fills the result registers based on a local
 // that is set as part of the compiler-rt startup code.
 //   __aarch64_has_sme_and_tpidr2_el0
 DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_sme_state)
-	.variant_pcs __arm_sme_state
+  .variant_pcs __arm_sme_state
+  BTI_C
   mov x0, xzr
   mov x1, xzr
 
@@ -68,7 +70,8 @@ DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_sme_state)
 END_COMPILERRT_OUTLINE_FUNCTION(__arm_sme_state)
 
 DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_tpidr2_restore)
-	.variant_pcs __arm_tpidr2_restore
+  .variant_pcs __arm_tpidr2_restore
+  BTI_C
   // If TPIDR2_EL0 is nonnull, the subroutine aborts in some platform-specific
   // manner.
   mrs x14, TPIDR2_EL0
@@ -103,7 +106,8 @@ DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_tpidr2_restore)
 END_COMPILERRT_OUTLINE_FUNCTION(__arm_tpidr2_restore)
 
 DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_tpidr2_save)
-	.variant_pcs __arm_tpidr2_restore
+  .variant_pcs __arm_tpidr2_restore
+  BTI_C
   // If the current thread does not have access to TPIDR2_EL0, the subroutine
   // does nothing.
   adrp  x14, TPIDR2_SYMBOL
@@ -143,7 +147,8 @@ DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_tpidr2_save)
 END_COMPILERRT_OUTLINE_FUNCTION(__arm_tpidr2_save)
 
 DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_za_disable)
-	.variant_pcs __arm_tpidr2_restore
+  .variant_pcs __arm_tpidr2_restore
+  BTI_C
   // If the current thread does not have access to SME, the subroutine does
   // nothing.
   adrp  x14, TPIDR2_SYMBOL
@@ -174,3 +179,8 @@ DEFINE_COMPILERRT_OUTLINE_FUNCTION_UNMANGLED(__arm_za_disable)
 0:
   ret
 END_COMPILERRT_OUTLINE_FUNCTION(__arm_za_disable)
+
+NO_EXEC_STACK_DIRECTIVE
+
+// GNU property note for BTI and PAC
+GNU_PROPERTY_BTI_PAC