x86/smpboot: Reference count on smpboot_setup_warm_reset_vector()

When bringing up a secondary CPU from do_boot_cpu(), the warm reset flag
is set in CMOS and the starting IP for the trampoline written inside the
BDA at 0x467. Once the CPU is running, the CMOS flag is unset and the
value in the BDA cleared.

To allow for parallel bringup of CPUs, add a reference count to track the
number of CPUs currently bring brought up, and clear the state only when
the count reaches zero.

Since the RTC spinlock is required to write to the CMOS, it can be used
for mutual exclusion on the refcount too.

Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Usama Arif <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Tested-by: Kim Phillips <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
Tested-by: Guilherme G. Piccoli <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: dwmw2

arch/x86/kernel/smpboot.c

@@ -121,17 +121,20 @@ int arch_update_cpu_topology(void)
 	return retval;
 }
 
+
+static unsigned int smpboot_warm_reset_vector_count;
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	CMOS_WRITE(0xa, 0xf);
+	if (!smpboot_warm_reset_vector_count++) {
+		CMOS_WRITE(0xa, 0xf);
+		*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4;
+		*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf;
+	}
 	spin_unlock_irqrestore(&rtc_lock, flags);
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
-							start_eip >> 4;
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
-							start_eip & 0xf;
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
@@ -143,10 +146,12 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	 * to default values.
 	 */
 	spin_lock_irqsave(&rtc_lock, flags);
-	CMOS_WRITE(0, 0xf);
+	if (!--smpboot_warm_reset_vector_count) {
+		CMOS_WRITE(0, 0xf);
+		*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
+	}
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
 /*