[PATCH] i386 boottime for_each_cpu broken

for_each_cpu walks through all processors in cpu_possible_map, which is
defined as cpu_callout_map on i386 and isn't initialised until all
processors have been booted. This breaks things which do for_each_cpu
iterations early during boot. So, define cpu_possible_map as a bitmap with
NR_CPUS bits populated. This was triggered by a patch i'm working on which
does alloc_percpu before bringing up secondary processors.

From: Alexander Nyberg <[email protected]>

i386-boottime-for_each_cpu-broken.patch
i386-boottime-for_each_cpu-broken-fix.patch

The SMP version of __alloc_percpu checks the cpu_possible_map before
allocating memory for a certain cpu.  With the above patches the BSP cpuid
is never set in cpu_possible_map which breaks CONFIG_SMP on uniprocessor
machines (as soon as someone tries to dereference something allocated via
__alloc_percpu, which in fact is never allocated since the cpu is not set
in cpu_possible_map).

Signed-off-by: Zwane Mwaikambo <[email protected]>
Signed-off-by: Alexander Nyberg <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/i386/kernel/mpparse.c

@@ -122,7 +122,7 @@ static int MP_valid_apicid(int apicid, int version)
 
 static void __init MP_processor_info (struct mpc_config_processor *m)
 {
- 	int ver, apicid;
+ 	int ver, apicid, cpu, found_bsp = 0;
 	physid_mask_t tmp;
 
 	if (!(m->mpc_cpuflag & CPU_ENABLED))
@@ -181,6 +181,7 @@ static void __init MP_processor_info (struct mpc_config_processor *m)
 	if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) {
 		Dprintk("    Bootup CPU\n");
 		boot_cpu_physical_apicid = m->mpc_apicid;
+		found_bsp = 1;
 	}
 
 	if (num_processors >= NR_CPUS) {
@@ -204,6 +205,11 @@ static void __init MP_processor_info (struct mpc_config_processor *m)
 		return;
 	}
 
+	if (found_bsp)
+		cpu = 0;
+	else
+		cpu = num_processors - 1;
+	cpu_set(cpu, cpu_possible_map);
 	tmp = apicid_to_cpu_present(apicid);
 	physids_or(phys_cpu_present_map, phys_cpu_present_map, tmp);
 

arch/i386/kernel/smpboot.c

@@ -88,6 +88,8 @@ EXPORT_SYMBOL(cpu_online_map);
 cpumask_t cpu_callin_map;
 cpumask_t cpu_callout_map;
 EXPORT_SYMBOL(cpu_callout_map);
+cpumask_t cpu_possible_map;
+EXPORT_SYMBOL(cpu_possible_map);
 static cpumask_t smp_commenced_mask;
 
 /* TSC's upper 32 bits can't be written in eariler CPU (before prescott), there
@@ -1265,6 +1267,7 @@ void __devinit smp_prepare_boot_cpu(void)
 	cpu_set(smp_processor_id(), cpu_online_map);
 	cpu_set(smp_processor_id(), cpu_callout_map);
 	cpu_set(smp_processor_id(), cpu_present_map);
+	cpu_set(smp_processor_id(), cpu_possible_map);
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 }
 

arch/i386/mach-voyager/voyager_smp.c

@@ -242,6 +242,8 @@ static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 cpumask_t cpu_callin_map = CPU_MASK_NONE;
 cpumask_t cpu_callout_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_callout_map);
+cpumask_t cpu_possible_map = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
 
 /* The per processor IRQ masks (these are usually kept in sync) */
 static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
@@ -1910,6 +1912,7 @@ void __devinit smp_prepare_boot_cpu(void)
 {
 	cpu_set(smp_processor_id(), cpu_online_map);
 	cpu_set(smp_processor_id(), cpu_callout_map);
+	cpu_set(smp_processor_id(), cpu_possible_map);
 }
 
 int __devinit

include/asm-i386/smp.h

@@ -59,7 +59,7 @@ extern void cpu_uninit(void);
 
 extern cpumask_t cpu_callout_map;
 extern cpumask_t cpu_callin_map;
-#define cpu_possible_map cpu_callout_map
+extern cpumask_t cpu_possible_map;
 
 /* We don't mark CPUs online until __cpu_up(), so we need another measure */
 static inline int num_booting_cpus(void)