[PATCH] arm64: smp: distinguish secondary CPUs that hang after reaching head.S

@@ -20,6 +20,16 @@
 /* Fatal system error detected by secondary CPU, crash the system */
 #define CPU_PANIC_KERNEL		(3)
 
+/*
+ * Best-effort marker written early in secondary_entry (PSCI/hotplug
+ * path) so __cpu_up() can tell whether a stuck CPU ever ran head.S.
+ * Not authoritative: spin-table secondaries use secondary_holding_pen
+ * and never write it, and the word has no CPU identity. Value must sit
+ * in the low byte, stay out of {0,1,2,3}, and set no CPU_STUCK_REASON_*
+ * bits.
+ */
+#define CPU_BOOT_ASM_ENTERED		(0x10)
+
 #define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
 #define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
 

@@ -353,6 +353,22 @@ SYM_FUNC_END(secondary_holding_pen)
 	 * be used where CPUs are brought online dynamically by the kernel.
 	 */
 SYM_FUNC_START(secondary_entry)
+	/*
+	 * Record that this CPU reached head.S, before init_kernel_el()
+	 * sets SCTLR_ELx.EE. A single-byte store to the reader's low
+	 * byte (__cpu_up() zeroed the word) is endian-agnostic, so a
+	 * big-endian kernel still reads 0x10. Flush it like
+	 * update_early_cpu_boot_status.
+	 */
+	adr_l	x2, __early_cpu_boot_status
+	mov	w1, #CPU_BOOT_ASM_ENTERED
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	strb	w1, [x2, #7]	// low byte at top address
+#else
+	strb	w1, [x2]
+#endif
+	dmb	sy
+	dc	ivac, x2
 	mov	x0, xzr
 	bl	init_kernel_el			// w0=cpu_boot_mode
 	b	secondary_startup

@@ -386,7 +402,6 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	mov	x0, x20
 	bl	finalise_el2
 
-	str_l	xzr, __early_cpu_boot_status, x3
 	adr_l	x5, vectors
 	msr	vbar_el1, x5
 	isb

@@ -395,6 +410,13 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
 
+	/*
+	 * Don't clear the marker here; nothing on the secondary clears
+	 * it. Once the CPU sets CPU_BOOT_SUCCESS in
+	 * secondary_data.status, __cpu_up() stops reading
+	 * __early_cpu_boot_status (and resets it before the next
+	 * release), so a stall before that still reports 0x10.
+	 */
 	init_cpu_task x2, x1, x3
 
 #ifdef CONFIG_ARM64_PTR_AUTH

@@ -120,6 +120,17 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	secondary_data.task = idle;
 	update_cpu_boot_status(CPU_MMU_OFF);
 
+	/*
+	 * Reset the marker before releasing this secondary: head.S
+	 * never clears it, so without this a CPU that never reaches
+	 * head.S would inherit a stale 0x10 from a previous CPU. Flush
+	 * it so the MMU-off secondary sees the reset.
+	 */
+	WRITE_ONCE(__early_cpu_boot_status, 0);
+	dcache_clean_inval_poc((unsigned long)&__early_cpu_boot_status,
+			       (unsigned long)&__early_cpu_boot_status +
+			       sizeof(__early_cpu_boot_status));
+
 	/* Now bring the CPU into our world */
 	ret = boot_secondary(cpu, idle);
 	if (ret) {

@@ -145,10 +156,20 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	switch (status & CPU_BOOT_STATUS_MASK) {
 	default:
+		/*
+		 * 0x0 usually means the CPU never ran head.S, but
+		 * treat it as a hint: spin-table secondaries never
+		 * write the marker and the word has no CPU identity.
+		 */
 		pr_err("CPU%u: failed in unknown state : 0x%lx\n",
 		       cpu, status);
 		cpus_stuck_in_kernel++;
 		break;
+	case CPU_BOOT_ASM_ENTERED:
+		pr_err("CPU%u: entered head.S but not online : 0x%lx\n",
+		       cpu, status);
+		cpus_stuck_in_kernel++;
+		break;
 	case CPU_KILL_ME:
 		if (!op_cpu_kill(cpu)) {
 			pr_crit("CPU%u: died during early boot\n", cpu);