[PATCH] sched: fix SCHED_SMT & numa=fake=2 lockup

This patch fixes an interaction between the numa=fake=<domains> feature,
the domain setup code and cpu_siblings_map[].  The bug leads to a bootup
crash when using numa=fake=2 on a 2-way/4-way SMP+HT box.

When SCHED_SMT is turned on the domains-setup code relies on siblings not
spanning multiple domains (which makes perfect sense).  But numa=fake=2
creates an assymetric 1101/0010 splitup between CPUs, which results in two
siblings being on different nodes.

The patch adds a check_siblings_map() function that checks the sibling maps
and fixes them up if they violate this rule.  (it also prints a warning in
that case.)

The patch also turns SCHED_DOMAIN_DEBUG back on - had this been enabled
we'd have noticed this bug much earlier.

From: Badari Pulavarty <pbadari@us.ibm.com>

  arch/x86_64/mm/numa.c: In function `numa_setup':
  arch/x86_64/mm/numa.c:332: error: `numa_fake' undeclared (first use in this function)
  arch/x86_64/mm/numa.c:332: error: (Each undeclared identifier is reported only once
  arch/x86_64/mm/numa.c:332: error: for each function it appears in.)

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index e6746a26b7a8d76ff4afe62a7b5c43c1c83b9930..df85a94d3ba6086a47bbc31806220007e05c02db 100644 (file)
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -264,11 +264,13 @@ __init int numa_setup(char *opt)
 { 
        if (!strcmp(opt,"off"))
                numa_off = 1;
+#ifdef CONFIG_NUMA_EMU
        if(!strncmp(opt, "fake=", 5)) {
                numa_fake = simple_strtoul(opt+5,NULL,0); ;
                if (numa_fake >= MAX_NUMNODES)
                        numa_fake = MAX_NUMNODES;
        }
+#endif
        return 1;
 } 
 

diff --git a/kernel/sched.c b/kernel/sched.c
index 3b498fa4f3d75b54d6e77f4bded611fb9972a087..5dc237eb32a5af0fda8cc383dee8089489466c8d 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4189,6 +4189,30 @@ static int __devinit cpu_to_node_group(int cpu)
 }
 #endif
 
+#if defined(CONFIG_SCHED_SMT) && defined(CONFIG_NUMA)
+/*
+ * The domains setup code relies on siblings not spanning
+ * multiple nodes. Make sure the architecture has a proper
+ * siblings map:
+ */
+static void check_sibling_maps(void)
+{
+       int i, j;
+
+       for_each_online_cpu(i) {
+               for_each_cpu_mask(j, cpu_sibling_map[i]) {
+                       if (cpu_to_node(i) != cpu_to_node(j)) {
+                               printk(KERN_INFO "warning: CPU %d siblings map "
+                                       "to different node - isolating "
+                                       "them.\n", i);
+                               cpu_sibling_map[i] = cpumask_of_cpu(i);
+                               break;
+                       }
+               }
+       }
+}
+#endif
+
 /*
  * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
  */
@@ -4197,6 +4221,9 @@ static void __devinit arch_init_sched_domains(void)
        int i;
        cpumask_t cpu_default_map;
 
+#if defined(CONFIG_SCHED_SMT) && defined(CONFIG_NUMA)
+       check_sibling_maps();
+#endif
        /*
         * Setup mask for cpus without special case scheduling requirements.
         * For now this just excludes isolated cpus, but could be used to
@@ -4319,7 +4346,7 @@ static void __devinit arch_destroy_sched_domains(void)
 
 #endif /* ARCH_HAS_SCHED_DOMAIN */
 
-#undef SCHED_DOMAIN_DEBUG
+#define SCHED_DOMAIN_DEBUG
 #ifdef SCHED_DOMAIN_DEBUG
 static void sched_domain_debug(void)
 {