Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The biggest change is the cleanup/simplification of the load-balancer:
  instead of the current practice of architectures twiddling scheduler
  internal data structures and providing the scheduler domains in
  colorfully inconsistent ways, we now have generic scheduler code in
  kernel/sched/core.c:sched_init_numa() that looks at the architecture's
  node_distance() parameters and (while not fully trusting it) deducts a
  NUMA topology from it.

  This inevitably changes balancing behavior - hopefully for the better.

  There are various smaller optimizations, cleanups and fixlets as well"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Taint kernel with TAINT_WARN after sleep-in-atomic bug
  sched: Remove stale power aware scheduling remnants and dysfunctional knobs
  sched/debug: Fix printing large integers on 32-bit platforms
  sched/fair: Improve the ->group_imb logic
  sched/nohz: Fix rq->cpu_load[] calculations
  sched/numa: Don't scale the imbalance
  sched/fair: Revert sched-domain iteration breakage
  sched/x86: Rewrite set_cpu_sibling_map()
  sched/numa: Fix the new NUMA topology bits
  sched/numa: Rewrite the CONFIG_NUMA sched domain support
  sched/fair: Propagate 'struct lb_env' usage into find_busiest_group
  sched/fair: Add some serialization to the sched_domain load-balance walk
  sched/fair: Let minimally loaded cpu balance the group
  sched: Change rq->nr_running to unsigned int
  x86/numa: Check for nonsensical topologies on real hw as well
  x86/numa: Hard partition cpu topology masks on node boundaries
  x86/numa: Allow specifying node_distance() for numa=fake
  x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly
  sched: Update documentation and comments
  sched_rt: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt()

4 files changed, 83 insertions, 79 deletions

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index b9676ae37ada..095b21507b6a 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -92,44 +92,6 @@ extern void setup_node_to_cpumask_map(void);
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
-#ifdef CONFIG_X86_32
-# define SD_CACHE_NICE_TRIES	1
-# define SD_IDLE_IDX		1
-#else
-# define SD_CACHE_NICE_TRIES	2
-# define SD_IDLE_IDX		2
-#endif
-
-/* sched_domains SD_NODE_INIT for NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 8,					\
-	.max_interval		= 32,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= SD_CACHE_NICE_TRIES,			\
-	.busy_idx		= 3,					\
-	.idle_idx		= SD_IDLE_IDX,				\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-}
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index dc8ca8ea78c4..8040b752ee4f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -582,9 +582,17 @@ int mwait_usable(const struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
 
+	/* Use mwait if idle=mwait boot option is given */
 	if (boot_option_idle_override == IDLE_FORCE_MWAIT)
 		return 1;
 
+	/*
+	 * Any idle= boot option other than idle=mwait means that we must not
+	 * use mwait. Eg: idle=halt or idle=poll or idle=nomwait
+	 */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return 0;
+
 	if (c->cpuid_level < MWAIT_INFO)
 		return 0;
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3acaf51dfddb..433529e29be4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -299,59 +299,90 @@ void __cpuinit smp_store_cpu_info(int id)
 		identify_secondary_cpu(c);
 }
 
-static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+static bool __cpuinit
+topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
 {
-	cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
-	cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
-	cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
-	cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
-	cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
-	cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
+	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+	return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2),
+		"sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
+		"[node: %d != %d]. Ignoring dependency.\n",
+		cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
 }
 
+#define link_mask(_m, c1, c2)						\
+do {									\
+	cpumask_set_cpu((c1), cpu_##_m##_mask(c2));			\
+	cpumask_set_cpu((c2), cpu_##_m##_mask(c1));			\
+} while (0)
+
+static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+		if (c->phys_proc_id == o->phys_proc_id &&
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
+		    c->compute_unit_id == o->compute_unit_id)
+			return topology_sane(c, o, "smt");
+
+	} else if (c->phys_proc_id == o->phys_proc_id &&
+		   c->cpu_core_id == o->cpu_core_id) {
+		return topology_sane(c, o, "smt");
+	}
+
+	return false;
+}
+
+static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+	if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
+	    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
+		return topology_sane(c, o, "llc");
+
+	return false;
+}
+
+static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if (c->phys_proc_id == o->phys_proc_id)
+		return topology_sane(c, o, "mc");
+
+	return false;
+}
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
-	int i;
+	bool has_mc = boot_cpu_data.x86_max_cores > 1;
+	bool has_smt = smp_num_siblings > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct cpuinfo_x86 *o;
+	int i;
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
-	if (smp_num_siblings > 1) {
-		for_each_cpu(i, cpu_sibling_setup_mask) {
-			struct cpuinfo_x86 *o = &cpu_data(i);
-
-			if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
-				if (c->phys_proc_id == o->phys_proc_id &&
-				    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
-				    c->compute_unit_id == o->compute_unit_id)
-					link_thread_siblings(cpu, i);
-			} else if (c->phys_proc_id == o->phys_proc_id &&
-				   c->cpu_core_id == o->cpu_core_id) {
-				link_thread_siblings(cpu, i);
-			}
-		}
-	} else {
+	if (!has_smt && !has_mc) {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
-	}
-
-	cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
-
-	if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
-		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
+		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
+		cpumask_set_cpu(cpu, cpu_core_mask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
 
 	for_each_cpu(i, cpu_sibling_setup_mask) {
-		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
-		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
-			cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
-		}
-		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
-			cpumask_set_cpu(i, cpu_core_mask(cpu));
-			cpumask_set_cpu(cpu, cpu_core_mask(i));
+		o = &cpu_data(i);
+
+		if ((i == cpu) || (has_smt && match_smt(c, o)))
+			link_mask(sibling, cpu, i);
+
+		if ((i == cpu) || (has_mc && match_llc(c, o)))
+			link_mask(llc_shared, cpu, i);
+
+		if ((i == cpu) || (has_mc && match_mc(c, o))) {
+			link_mask(core, cpu, i);
+
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
@@ -382,8 +413,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	 * For perf, we return last level cache shared map.
 	 * And for power savings, we return cpu_core_map
 	 */
-	if ((sched_mc_power_savings || sched_smt_power_savings) &&
-	    !(cpu_has(c, X86_FEATURE_AMD_DCM)))
+	if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
 		return cpu_core_mask(cpu);
 	else
 		return cpu_llc_shared_mask(cpu);
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 53489ff6bf82..871dd8868170 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -339,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	} else {
 		unsigned long n;
 
-		n = simple_strtoul(emu_cmdline, NULL, 0);
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
 		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
 	}
+	if (*emu_cmdline == ':')
+		emu_cmdline++;
 
 	if (ret < 0)
 		goto no_emu;
@@ -418,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 			int physj = emu_nid_to_phys[j];
 			int dist;
 
-			if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+			if (get_option(&emu_cmdline, &dist) == 2)
+				;
+			else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
 				dist = physi == physj ?
 					LOCAL_DISTANCE : REMOTE_DISTANCE;
 			else